WorldWideScience

Sample records for one-class object recognition

  1. Specific and Class Object Recognition for Service Robots through Autonomous and Interactive Methods

    Science.gov (United States)

    Mansur, Al; Kuno, Yoshinori

    Service robots need to be able to recognize and identify objects located within complex backgrounds. Since no single method may work in every situation, several methods need to be combined and robots have to select the appropriate one automatically. In this paper we propose a scheme to classify situations depending on the characteristics of the object of interest and user demand. We classify situations into four groups and employ different techniques for each. We use Scale-invariant feature transform (SIFT), Kernel Principal Components Analysis (KPCA) in conjunction with Support Vector Machine (SVM) using intensity, color, and Gabor features for five object categories. We show that the use of appropriate features is important for the use of KPCA and SVM based techniques on different kinds of objects. Through experiments we show that by using our categorization scheme a service robot can select an appropriate feature and method, and considerably improve its recognition performance. Yet, recognition is not perfect. Thus, we propose to combine the autonomous method with an interactive method that allows the robot to recognize the user request for a specific object and class when the robot fails to recognize the object. We also propose an interactive way to update the object model that is used to recognize an object upon failure in conjunction with the user's feedback.

  2. Knowledge-based object recognition for different morphological classes of plants

    Science.gov (United States)

    Brendel, Thorsten; Schwanke, Joerg; Jensch, Peter F.; Megnet, Roland

    1995-01-01

    Micropropagation of plants is done by cutting juvenile plants and placing them into special container-boxes with nutrient-solution where the pieces can grow up and be cut again several times. To produce high amounts of biomass it is necessary to do plant micropropagation by a robotic syshoot. In this paper we describe parts of the vision syshoot that recognizes plants and their particular cutting points. Therefore, it is necessary to extract elements of the plants and relations between these elements (for example root, shoot, leaf). Different species vary in their morphological appearance, variation is also immanent in plants of the same species. Therefore, we introduce several morphological classes of plants from that we expect same recognition methods. As a result of our work we present rules which help users to create specific algorithms for object recognition of plant species.

  3. General object recognition is specific: Evidence from novel and familiar objects.

    Science.gov (United States)

    Richler, Jennifer J; Wilmer, Jeremy B; Gauthier, Isabel

    2017-09-01

    In tests of object recognition, individual differences typically correlate modestly but nontrivially across familiar categories (e.g. cars, faces, shoes, birds, mushrooms). In theory, these correlations could reflect either global, non-specific mechanisms, such as general intelligence (IQ), or more specific mechanisms. Here, we introduce two separate methods for effectively capturing category-general performance variation, one that uses novel objects and one that uses familiar objects. In each case, we show that category-general performance variance is unrelated to IQ, thereby implicating more specific mechanisms. The first approach examines three newly developed novel object memory tests (NOMTs). We predicted that NOMTs would exhibit more shared, category-general variance than familiar object memory tests (FOMTs) because novel objects, unlike familiar objects, lack category-specific environmental influences (e.g. exposure to car magazines or botany classes). This prediction held, and remarkably, virtually none of the substantial shared variance among NOMTs was explained by IQ. Also, while NOMTs correlated nontrivially with two FOMTs (faces, cars), these correlations were smaller than among NOMTs and no larger than between the face and car tests themselves, suggesting that the category-general variance captured by NOMTs is specific not only relative to IQ, but also, to some degree, relative to both face and car recognition. The second approach averaged performance across multiple FOMTs, which we predicted would increase category-general variance by averaging out category-specific factors. This prediction held, and as with NOMTs, virtually none of the shared variance among FOMTs was explained by IQ. Overall, these results support the existence of object recognition mechanisms that, though category-general, are specific relative to IQ and substantially separable from face and car recognition. They also add sensitive, well-normed NOMTs to the tools available to study

  4. Random clustering ferns for multimodal object recognition

    OpenAIRE

    Villamizar Vergel, Michael Alejandro; Garrell Zulueta, Anais; Sanfeliu Cortés, Alberto; Moreno-Noguer, Francesc

    2017-01-01

    The final publication is available at link.springer.com We propose an efficient and robust method for the recognition of objects exhibiting multiple intra-class modes, where each one is associated with a particular object appearance. The proposed method, called random clustering ferns, combines synergically a single and real-time classifier, based on the boosted assembling of extremely randomized trees (ferns), with an unsupervised and probabilistic approach in order to recognize efficient...

  5. Object recognition with hierarchical discriminant saliency networks.

    Science.gov (United States)

    Han, Sunhyoung; Vasconcelos, Nuno

    2014-01-01

    The benefits of integrating attention and object recognition are investigated. While attention is frequently modeled as a pre-processor for recognition, we investigate the hypothesis that attention is an intrinsic component of recognition and vice-versa. This hypothesis is tested with a recognition model, the hierarchical discriminant saliency network (HDSN), whose layers are top-down saliency detectors, tuned for a visual class according to the principles of discriminant saliency. As a model of neural computation, the HDSN has two possible implementations. In a biologically plausible implementation, all layers comply with the standard neurophysiological model of visual cortex, with sub-layers of simple and complex units that implement a combination of filtering, divisive normalization, pooling, and non-linearities. In a convolutional neural network implementation, all layers are convolutional and implement a combination of filtering, rectification, and pooling. The rectification is performed with a parametric extension of the now popular rectified linear units (ReLUs), whose parameters can be tuned for the detection of target object classes. This enables a number of functional enhancements over neural network models that lack a connection to saliency, including optimal feature denoising mechanisms for recognition, modulation of saliency responses by the discriminant power of the underlying features, and the ability to detect both feature presence and absence. In either implementation, each layer has a precise statistical interpretation, and all parameters are tuned by statistical learning. Each saliency detection layer learns more discriminant saliency templates than its predecessors and higher layers have larger pooling fields. This enables the HDSN to simultaneously achieve high selectivity to target object classes and invariance. The performance of the network in saliency and object recognition tasks is compared to those of models from the biological and

  6. Paradigms in object recognition

    International Nuclear Information System (INIS)

    Mutihac, R.; Mutihac, R.C.

    1999-09-01

    A broad range of approaches has been proposed and applied for the complex and rather difficult task of object recognition that involves the determination of object characteristics and object classification into one of many a priori object types. Our paper revises briefly the three main different paradigms in pattern recognition, namely Bayesian statistics, neural networks, and expert systems. (author)

  7. A new selective developmental deficit: Impaired object recognition with normal face recognition.

    Science.gov (United States)

    Germine, Laura; Cashdollar, Nathan; Düzel, Emrah; Duchaine, Bradley

    2011-05-01

    Studies of developmental deficits in face recognition, or developmental prosopagnosia, have shown that individuals who have not suffered brain damage can show face recognition impairments coupled with normal object recognition (Duchaine and Nakayama, 2005; Duchaine et al., 2006; Nunn et al., 2001). However, no developmental cases with the opposite dissociation - normal face recognition with impaired object recognition - have been reported. The existence of a case of non-face developmental visual agnosia would indicate that the development of normal face recognition mechanisms does not rely on the development of normal object recognition mechanisms. To see whether a developmental variant of non-face visual object agnosia exists, we conducted a series of web-based object and face recognition tests to screen for individuals showing object recognition memory impairments but not face recognition impairments. Through this screening process, we identified AW, an otherwise normal 19-year-old female, who was then tested in the lab on face and object recognition tests. AW's performance was impaired in within-class visual recognition memory across six different visual categories (guns, horses, scenes, tools, doors, and cars). In contrast, she scored normally on seven tests of face recognition, tests of memory for two other object categories (houses and glasses), and tests of recall memory for visual shapes. Testing confirmed that her impairment was not related to a general deficit in lower-level perception, object perception, basic-level recognition, or memory. AW's results provide the first neuropsychological evidence that recognition memory for non-face visual object categories can be selectively impaired in individuals without brain damage or other memory impairment. These results indicate that the development of recognition memory for faces does not depend on intact object recognition memory and provide further evidence for category-specific dissociations in visual

  8. Enlarge the training set based on inter-class relationship for face recognition from one image per person.

    Science.gov (United States)

    Li, Qin; Wang, Hua Jing; You, Jane; Li, Zhao Ming; Li, Jin Xue

    2013-01-01

    In some large-scale face recognition task, such as driver license identification and law enforcement, the training set only contains one image per person. This situation is referred to as one sample problem. Because many face recognition techniques implicitly assume that several (at least two) images per person are available for training, they cannot deal with the one sample problem. This paper investigates principal component analysis (PCA), Fisher linear discriminant analysis (LDA), and locality preserving projections (LPP) and shows why they cannot perform well in one sample problem. After that, this paper presents four reasons that make one sample problem itself difficult: the small sample size problem; the lack of representative samples; the underestimated intra-class variation; and the overestimated inter-class variation. Based on the analysis, this paper proposes to enlarge the training set based on the inter-class relationship. This paper also extends LDA and LPP to extract features from the enlarged training set. The experimental results show the effectiveness of the proposed method.

  9. Enlarge the training set based on inter-class relationship for face recognition from one image per person.

    Directory of Open Access Journals (Sweden)

    Qin Li

    Full Text Available In some large-scale face recognition task, such as driver license identification and law enforcement, the training set only contains one image per person. This situation is referred to as one sample problem. Because many face recognition techniques implicitly assume that several (at least two images per person are available for training, they cannot deal with the one sample problem. This paper investigates principal component analysis (PCA, Fisher linear discriminant analysis (LDA, and locality preserving projections (LPP and shows why they cannot perform well in one sample problem. After that, this paper presents four reasons that make one sample problem itself difficult: the small sample size problem; the lack of representative samples; the underestimated intra-class variation; and the overestimated inter-class variation. Based on the analysis, this paper proposes to enlarge the training set based on the inter-class relationship. This paper also extends LDA and LPP to extract features from the enlarged training set. The experimental results show the effectiveness of the proposed method.

  10. One-trial object recognition memory in the domestic rabbit (Oryctolagus cuniculus) is disrupted by NMDA receptor antagonists.

    Science.gov (United States)

    Hoffman, Kurt Leroy; Basurto, Enrique

    2013-08-01

    The spontaneous response to novelty is the basis of one-trial object recognition tests for the study of object recognition memory (ORM) in rodents. We describe an object recognition task for the rabbit, based on its natural tendency to scent-mark ("chin") novel objects. The object recognition task comprised a 15min sample phase in which the rabbit was placed into an open field arena containing two similar objects, then removed for a 5-360min delay, and then returned to the same arena that contained one object similar to the original ones ("Familiar") and one that differed from the original ones ("Novel"), for a 15min test phase. Chin-marks directed at each of the objects were registered. Some animals received injections (sc) of saline, ketamine (1mg/kg), or MK-801 (37μg/kg), 5 or 20min before the sample phase. We found that chinning decreased across the sample phase, and that this response showed stimulus specificity, a defining characteristic of habituation: in the test phase, chinning directed at the Novel, but not Familiar, object was increased. Chinning directed preferentially at the novel object, which we interpret as novelty-induced sensitization and the behavioral correlate of ORM, was promoted by tactile/visual and spatial novelty. ORM deficits were induced by pre-treatment with MK-801 and, to a lesser extent, ketamine. Novel object discrimination was not observed after delays longer than 5min. These results suggest that short-term habituation and sensitization, not long-term memory, underlie novel object discrimination in this test paradigm. Copyright © 2013 Elsevier B.V. All rights reserved.

  11. Object recognition memory in zebrafish.

    Science.gov (United States)

    May, Zacnicte; Morrill, Adam; Holcombe, Adam; Johnston, Travis; Gallup, Joshua; Fouad, Karim; Schalomon, Melike; Hamilton, Trevor James

    2016-01-01

    The novel object recognition, or novel-object preference (NOP) test is employed to assess recognition memory in a variety of organisms. The subject is exposed to two identical objects, then after a delay, it is placed back in the original environment containing one of the original objects and a novel object. If the subject spends more time exploring one object, this can be interpreted as memory retention. To date, this test has not been fully explored in zebrafish (Danio rerio). Zebrafish possess recognition memory for simple 2- and 3-dimensional geometrical shapes, yet it is unknown if this translates to complex 3-dimensional objects. In this study we evaluated recognition memory in zebrafish using complex objects of different sizes. Contrary to rodents, zebrafish preferentially explored familiar over novel objects. Familiarity preference disappeared after delays of 5 mins. Leopard danios, another strain of D. rerio, also preferred the familiar object after a 1 min delay. Object preference could be re-established in zebra danios by administration of nicotine tartrate salt (50mg/L) prior to stimuli presentation, suggesting a memory-enhancing effect of nicotine. Additionally, exploration biases were present only when the objects were of intermediate size (2 × 5 cm). Our results demonstrate zebra and leopard danios have recognition memory, and that low nicotine doses can improve this memory type in zebra danios. However, exploration biases, from which memory is inferred, depend on object size. These findings suggest zebrafish ecology might influence object preference, as zebrafish neophobia could reflect natural anti-predatory behaviour. Copyright © 2015 Elsevier B.V. All rights reserved.

  12. Higher-Order Neural Networks Applied to 2D and 3D Object Recognition

    Science.gov (United States)

    Spirkovska, Lilly; Reid, Max B.

    1994-01-01

    A Higher-Order Neural Network (HONN) can be designed to be invariant to geometric transformations such as scale, translation, and in-plane rotation. Invariances are built directly into the architecture of a HONN and do not need to be learned. Thus, for 2D object recognition, the network needs to be trained on just one view of each object class, not numerous scaled, translated, and rotated views. Because the 2D object recognition task is a component of the 3D object recognition task, built-in 2D invariance also decreases the size of the training set required for 3D object recognition. We present results for 2D object recognition both in simulation and within a robotic vision experiment and for 3D object recognition in simulation. We also compare our method to other approaches and show that HONNs have distinct advantages for position, scale, and rotation-invariant object recognition. The major drawback of HONNs is that the size of the input field is limited due to the memory required for the large number of interconnections in a fully connected network. We present partial connectivity strategies and a coarse-coding technique for overcoming this limitation and increasing the input field to that required by practical object recognition problems.

  13. Object recognition with hierarchical discriminant saliency networks

    Directory of Open Access Journals (Sweden)

    Sunhyoung eHan

    2014-09-01

    Full Text Available The benefits of integrating attention and object recognition are investigated. While attention is frequently modeled as pre-processor for recognition, we investigate the hypothesis that attention is an intrinsic component of recognition and vice-versa. This hypothesis is tested with a recognitionmodel, the hierarchical discriminant saliency network (HDSN, whose layers are top-down saliency detectors, tuned for a visual class according to the principles of discriminant saliency. The HDSN has two possible implementations. In a biologically plausible implementation, all layers comply with the standard neurophysiological model of visual cortex, with sub-layers of simple and complex units that implement a combination of filtering, divisive normalization, pooling, and non-linearities. In a neuralnetwork implementation, all layers are convolutional and implement acombination of filtering, rectification, and pooling. The rectificationis performed with a parametric extension of the now popular rectified linearunits (ReLUs, whose parameters can be tuned for the detection of targetobject classes. This enables a number of functional enhancementsover neural network models that lack a connection to saliency, including optimal feature denoising mechanisms for recognition, modulation ofsaliency responses by the discriminant power of the underlying features,and the ability to detect both feature presence and absence.In either implementation, each layer has a precise statistical interpretation, and all parameters are tuned by statistical learning. Each saliency detection layer learns more discriminant saliency templates than its predecessors and higher layers have larger pooling fields. This enables the HDSN to simultaneously achieve high selectivity totarget object classes and invariance. The resulting performance demonstrates benefits for all the functional enhancements of the HDSN.

  14. Neural-Network Object-Recognition Program

    Science.gov (United States)

    Spirkovska, L.; Reid, M. B.

    1993-01-01

    HONTIOR computer program implements third-order neural network exhibiting invariance under translation, change of scale, and in-plane rotation. Invariance incorporated directly into architecture of network. Only one view of each object needed to train network for two-dimensional-translation-invariant recognition of object. Also used for three-dimensional-transformation-invariant recognition by training network on only set of out-of-plane rotated views. Written in C language.

  15. Learning object-to-class kernels for scene classification.

    Science.gov (United States)

    Zhang, Lei; Zhen, Xiantong; Shao, Ling

    2014-08-01

    High-level image representations have drawn increasing attention in visual recognition, e.g., scene classification, since the invention of the object bank. The object bank represents an image as a response map of a large number of pretrained object detectors and has achieved superior performance for visual recognition. In this paper, based on the object bank representation, we propose the object-to-class (O2C) distances to model scene images. In particular, four variants of O2C distances are presented, and with the O2C distances, we can represent the images using the object bank by lower-dimensional but more discriminative spaces, called distance spaces, which are spanned by the O2C distances. Due to the explicit computation of O2C distances based on the object bank, the obtained representations can possess more semantic meanings. To combine the discriminant ability of the O2C distances to all scene classes, we further propose to kernalize the distance representation for the final classification. We have conducted extensive experiments on four benchmark data sets, UIUC-Sports, Scene-15, MIT Indoor, and Caltech-101, which demonstrate that the proposed approaches can significantly improve the original object bank approach and achieve the state-of-the-art performance.

  16. New neural-networks-based 3D object recognition system

    Science.gov (United States)

    Abolmaesumi, Purang; Jahed, M.

    1997-09-01

    Three-dimensional object recognition has always been one of the challenging fields in computer vision. In recent years, Ulman and Basri (1991) have proposed that this task can be done by using a database of 2-D views of the objects. The main problem in their proposed system is that the correspondent points should be known to interpolate the views. On the other hand, their system should have a supervisor to decide which class does the represented view belong to. In this paper, we propose a new momentum-Fourier descriptor that is invariant to scale, translation, and rotation. This descriptor provides the input feature vectors to our proposed system. By using the Dystal network, we show that the objects can be classified with over 95% precision. We have used this system to classify the objects like cube, cone, sphere, torus, and cylinder. Because of the nature of the Dystal network, this system reaches to its stable point by a single representation of the view to the system. This system can also classify the similar views to a single class (e.g., for the cube, the system generated 9 different classes for 50 different input views), which can be used to select an optimum database of training views. The system is also very flexible to the noise and deformed views.

  17. Use of the recognition heuristic depends on the domain's recognition validity, not on the recognition validity of selected sets of objects.

    Science.gov (United States)

    Pohl, Rüdiger F; Michalkiewicz, Martha; Erdfelder, Edgar; Hilbig, Benjamin E

    2017-07-01

    According to the recognition-heuristic theory, decision makers solve paired comparisons in which one object is recognized and the other not by recognition alone, inferring that recognized objects have higher criterion values than unrecognized ones. However, success-and thus usefulness-of this heuristic depends on the validity of recognition as a cue, and adaptive decision making, in turn, requires that decision makers are sensitive to it. To this end, decision makers could base their evaluation of the recognition validity either on the selected set of objects (the set's recognition validity), or on the underlying domain from which the objects were drawn (the domain's recognition validity). In two experiments, we manipulated the recognition validity both in the selected set of objects and between domains from which the sets were drawn. The results clearly show that use of the recognition heuristic depends on the domain's recognition validity, not on the set's recognition validity. In other words, participants treat all sets as roughly representative of the underlying domain and adjust their decision strategy adaptively (only) with respect to the more general environment rather than the specific items they are faced with.

  18. Structured Kernel Dictionary Learning with Correlation Constraint for Object Recognition.

    Science.gov (United States)

    Wang, Zhengjue; Wang, Yinghua; Liu, Hongwei; Zhang, Hao

    2017-06-21

    In this paper, we propose a new discriminative non-linear dictionary learning approach, called correlation constrained structured kernel KSVD, for object recognition. The objective function for dictionary learning contains a reconstructive term and a discriminative term. In the reconstructive term, signals are implicitly non-linearly mapped into a space, where a structured kernel dictionary, each sub-dictionary of which lies in the span of the mapped signals from the corresponding class, is established. In the discriminative term, by analyzing the classification mechanism, the correlation constraint is proposed in kernel form, constraining the correlations between different discriminative codes, and restricting the coefficient vectors to be transformed into a feature space, where the features are highly correlated inner-class and nearly independent between-classes. The objective function is optimized by the proposed structured kernel KSVD. During the classification stage, the specific form of the discriminative feature is needless to be known, while the inner product of the discriminative feature with kernel matrix embedded is available, and is suitable for a linear SVM classifier. Experimental results demonstrate that the proposed approach outperforms many state-of-the-art dictionary learning approaches for face, scene and synthetic aperture radar (SAR) vehicle target recognition.

  19. Inductive class representation and its central role in pattern recognition

    Energy Technology Data Exchange (ETDEWEB)

    Goldfarb, L. [Univ. of New Brunswick, Fredericton, New Brunswick (Canada)

    1996-12-31

    The definition of inductive learning (IL) based on the new concept of inductive class representation (ICR) is given. The ICR, in addition to the ability to recognize a noise-corrupted object from the class, must also provide the means to generate every element in the resulting approximation of the class, i.e., the emphasis is on the generative capability of the ICR. Thus, the IL problem absorbs the main difficulties associated with a satisfactory formulation of the pattern recognition problem. This formulation of the IL problem appeared gradually as a result of the development of a fundamentally new formal model of IL--evolving transformation system (ETS) model. The model with striking clarity suggests that IL is the basic process which produces all the necessary {open_quotes}structures{close_quotes} for the recognition process, which is built directly on top of it. Based on the training set, the IL process, constructs optimal discriminatory (symbolic) weighted {open_quotes}features{close_quotes} which induce the corresponding optimal (symbolic) distance measure. The distance measure is a generalization of the weighted Levenshtein, or edit, distance defined on strings over a finite alphabet. The ETS model has emerged as a result of an attempt to unify two basic, but inadequate, approaches to pattern recognition: the classical vector space based and the syntactic approaches. ETS also elucidates with remarkable clarity the nature of the interrelationships between the corresponding symbolic and numeric mechanisms, in which the symbolic mechanisms play a more fundamental part. The model, in fact, suggests the first formal definition of the symbolic mathematical structure and also suggests a fundamentally different, more satisfactory, way of introducing the concept of fuzziness. The importance of the ICR concept to semiotics and semantics should become apparent as soon as one fully realizes that it represents the class and specifies the semantics of the class.

  20. Modified-hybrid optical neural network filter for multiple object recognition within cluttered scenes

    Science.gov (United States)

    Kypraios, Ioannis; Young, Rupert C. D.; Chatwin, Chris R.

    2009-08-01

    Motivated by the non-linear interpolation and generalization abilities of the hybrid optical neural network filter between the reference and non-reference images of the true-class object we designed the modifiedhybrid optical neural network filter. We applied an optical mask to the hybrid optical neural network's filter input. The mask was built with the constant weight connections of a randomly chosen image included in the training set. The resulted design of the modified-hybrid optical neural network filter is optimized for performing best in cluttered scenes of the true-class object. Due to the shift invariance properties inherited by its correlator unit the filter can accommodate multiple objects of the same class to be detected within an input cluttered image. Additionally, the architecture of the neural network unit of the general hybrid optical neural network filter allows the recognition of multiple objects of different classes within the input cluttered image by modifying the output layer of the unit. We test the modified-hybrid optical neural network filter for multiple objects of the same and of different classes' recognition within cluttered input images and video sequences of cluttered scenes. The filter is shown to exhibit with a single pass over the input data simultaneously out-of-plane rotation, shift invariance and good clutter tolerance. It is able to successfully detect and classify correctly the true-class objects within background clutter for which there has been no previous training.

  1. Cognitive object recognition system (CORS)

    Science.gov (United States)

    Raju, Chaitanya; Varadarajan, Karthik Mahesh; Krishnamurthi, Niyant; Xu, Shuli; Biederman, Irving; Kelley, Troy

    2010-04-01

    We have developed a framework, Cognitive Object Recognition System (CORS), inspired by current neurocomputational models and psychophysical research in which multiple recognition algorithms (shape based geometric primitives, 'geons,' and non-geometric feature-based algorithms) are integrated to provide a comprehensive solution to object recognition and landmarking. Objects are defined as a combination of geons, corresponding to their simple parts, and the relations among the parts. However, those objects that are not easily decomposable into geons, such as bushes and trees, are recognized by CORS using "feature-based" algorithms. The unique interaction between these algorithms is a novel approach that combines the effectiveness of both algorithms and takes us closer to a generalized approach to object recognition. CORS allows recognition of objects through a larger range of poses using geometric primitives and performs well under heavy occlusion - about 35% of object surface is sufficient. Furthermore, geon composition of an object allows image understanding and reasoning even with novel objects. With reliable landmarking capability, the system improves vision-based robot navigation in GPS-denied environments. Feasibility of the CORS system was demonstrated with real stereo images captured from a Pioneer robot. The system can currently identify doors, door handles, staircases, trashcans and other relevant landmarks in the indoor environment.

  2. Object feature extraction and recognition model

    International Nuclear Information System (INIS)

    Wan Min; Xiang Rujian; Wan Yongxing

    2001-01-01

    The characteristics of objects, especially flying objects, are analyzed, which include characteristics of spectrum, image and motion. Feature extraction is also achieved. To improve the speed of object recognition, a feature database is used to simplify the data in the source database. The feature vs. object relationship maps are stored in the feature database. An object recognition model based on the feature database is presented, and the way to achieve object recognition is also explained

  3. Breaking object correspondence across saccadic eye movements deteriorates object recognition

    Directory of Open Access Journals (Sweden)

    Christian H. Poth

    2015-12-01

    Full Text Available Visual perception is based on information processing during periods of eye fixations that are interrupted by fast saccadic eye movements. The ability to sample and relate information on task-relevant objects across fixations implies that correspondence between presaccadic and postsaccadic objects is established. Postsaccadic object information usually updates and overwrites information on the corresponding presaccadic object. The presaccadic object representation is then lost. In contrast, the presaccadic object is conserved when object correspondence is broken. This helps transsaccadic memory but it may impose attentional costs on object recognition. Therefore, we investigated how breaking object correspondence across the saccade affects postsaccadic object recognition. In Experiment 1, object correspondence was broken by a brief postsaccadic blank screen. Observers made a saccade to a peripheral object which was displaced during the saccade. This object reappeared either immediately after the saccade or after the blank screen. Within the postsaccadic object, a letter was briefly presented (terminated by a mask. Observers reported displacement direction and letter identity in different blocks. Breaking object correspondence by blanking improved displacement identification but deteriorated postsaccadic letter recognition. In Experiment 2, object correspondence was broken by changing the object’s contrast-polarity. There were no object displacements and observers only reported letter identity. Again, breaking object correspondence deteriorated postsaccadic letter recognition. These findings identify transsaccadic object correspondence as a key determinant of object recognition across the saccade. This is in line with the recent hypothesis that breaking object correspondence results in separate representations of presaccadic and postsaccadic objects which then compete for limited attentional processing resources (Schneider, 2013. Postsaccadic

  4. Running Improves Pattern Separation during Novel Object Recognition.

    Science.gov (United States)

    Bolz, Leoni; Heigele, Stefanie; Bischofberger, Josef

    2015-10-09

    Running increases adult neurogenesis and improves pattern separation in various memory tasks including context fear conditioning or touch-screen based spatial learning. However, it is unknown whether pattern separation is improved in spontaneous behavior, not emotionally biased by positive or negative reinforcement. Here we investigated the effect of voluntary running on pattern separation during novel object recognition in mice using relatively similar or substantially different objects.We show that running increases hippocampal neurogenesis but does not affect object recognition memory with 1.5 h delay after sample phase. By contrast, at 24 h delay, running significantly improves recognition memory for similar objects, whereas highly different objects can be distinguished by both, running and sedentary mice. These data show that physical exercise improves pattern separation, independent of negative or positive reinforcement. In sedentary mice there is a pronounced temporal gradient for remembering object details. In running mice, however, increased neurogenesis improves hippocampal coding and temporally preserves distinction of novel objects from familiar ones.

  5. Infant visual attention and object recognition.

    Science.gov (United States)

    Reynolds, Greg D

    2015-05-15

    This paper explores the role visual attention plays in the recognition of objects in infancy. Research and theory on the development of infant attention and recognition memory are reviewed in three major sections. The first section reviews some of the major findings and theory emerging from a rich tradition of behavioral research utilizing preferential looking tasks to examine visual attention and recognition memory in infancy. The second section examines research utilizing neural measures of attention and object recognition in infancy as well as research on brain-behavior relations in the early development of attention and recognition memory. The third section addresses potential areas of the brain involved in infant object recognition and visual attention. An integrated synthesis of some of the existing models of the development of visual attention is presented which may account for the observed changes in behavioral and neural measures of visual attention and object recognition that occur across infancy. Copyright © 2015 Elsevier B.V. All rights reserved.

  6. Joint Tensor Feature Analysis For Visual Object Recognition.

    Science.gov (United States)

    Wong, Wai Keung; Lai, Zhihui; Xu, Yong; Wen, Jiajun; Ho, Chu Po

    2015-11-01

    Tensor-based object recognition has been widely studied in the past several years. This paper focuses on the issue of joint feature selection from the tensor data and proposes a novel method called joint tensor feature analysis (JTFA) for tensor feature extraction and recognition. In order to obtain a set of jointly sparse projections for tensor feature extraction, we define the modified within-class tensor scatter value and the modified between-class tensor scatter value for regression. The k-mode optimization technique and the L(2,1)-norm jointly sparse regression are combined together to compute the optimal solutions. The convergent analysis, computational complexity analysis and the essence of the proposed method/model are also presented. It is interesting to show that the proposed method is very similar to singular value decomposition on the scatter matrix but with sparsity constraint on the right singular value matrix or eigen-decomposition on the scatter matrix with sparse manner. Experimental results on some tensor datasets indicate that JTFA outperforms some well-known tensor feature extraction and selection algorithms.

  7. SVM-Fold: a tool for discriminative multi-class protein fold and superfamily recognition.

    Science.gov (United States)

    Melvin, Iain; Ie, Eugene; Kuang, Rui; Weston, Jason; Stafford, William Noble; Leslie, Christina

    2007-05-22

    Predicting a protein's structural class from its amino acid sequence is a fundamental problem in computational biology. Much recent work has focused on developing new representations for protein sequences, called string kernels, for use with support vector machine (SVM) classifiers. However, while some of these approaches exhibit state-of-the-art performance at the binary protein classification problem, i.e. discriminating between a particular protein class and all other classes, few of these studies have addressed the real problem of multi-class superfamily or fold recognition. Moreover, there are only limited software tools and systems for SVM-based protein classification available to the bioinformatics community. We present a new multi-class SVM-based protein fold and superfamily recognition system and web server called SVM-Fold, which can be found at http://svm-fold.c2b2.columbia.edu. Our system uses an efficient implementation of a state-of-the-art string kernel for sequence profiles, called the profile kernel, where the underlying feature representation is a histogram of inexact matching k-mer frequencies. We also employ a novel machine learning approach to solve the difficult multi-class problem of classifying a sequence of amino acids into one of many known protein structural classes. Binary one-vs-the-rest SVM classifiers that are trained to recognize individual structural classes yield prediction scores that are not comparable, so that standard "one-vs-all" classification fails to perform well. Moreover, SVMs for classes at different levels of the protein structural hierarchy may make useful predictions, but one-vs-all does not try to combine these multiple predictions. To deal with these problems, our method learns relative weights between one-vs-the-rest classifiers and encodes information about the protein structural hierarchy for multi-class prediction. In large-scale benchmark results based on the SCOP database, our code weighting approach

  8. Possibility of object recognition using Altera's model based design approach

    International Nuclear Information System (INIS)

    Tickle, A J; Harvey, P K; Smith, J S; Wu, F

    2009-01-01

    Object recognition is an image processing task of finding a given object in a selected image or video sequence. Object recognition can be divided into two areas: one of these is decision-theoretic and deals with patterns described by quantitative descriptors, for example such as length, area, shape and texture. With this Graphical User Interface Circuitry (GUIC) methodology employed here being relatively new for object recognition systems, the aim of this work is to identify if the developed circuitry can detect certain shapes or strings within the target image. A much smaller reference image feeds the preset data for identification, tests are conducted for both binary and greyscale and the additional mathematical morphology to highlight the area within the target image with the object(s) are located is also presented. This then provides proof that basic recognition methods are valid and would allow the progression to developing decision-theoretical and learning based approaches using GUICs for use in multidisciplinary tasks.

  9. Eye movements during object recognition in visual agnosia.

    Science.gov (United States)

    Charles Leek, E; Patterson, Candy; Paul, Matthew A; Rafal, Robert; Cristino, Filipe

    2012-07-01

    This paper reports the first ever detailed study about eye movement patterns during single object recognition in visual agnosia. Eye movements were recorded in a patient with an integrative agnosic deficit during two recognition tasks: common object naming and novel object recognition memory. The patient showed normal directional biases in saccades and fixation dwell times in both tasks and was as likely as controls to fixate within object bounding contour regardless of recognition accuracy. In contrast, following initial saccades of similar amplitude to controls, the patient showed a bias for short saccades. In object naming, but not in recognition memory, the similarity of the spatial distributions of patient and control fixations was modulated by recognition accuracy. The study provides new evidence about how eye movements can be used to elucidate the functional impairments underlying object recognition deficits. We argue that the results reflect a breakdown in normal functional processes involved in the integration of shape information across object structure during the visual perception of shape. Copyright © 2012 Elsevier Ltd. All rights reserved.

  10. Logarithmic r-θ mapping for hybrid optical neural network filter for multiple objects recognition within cluttered scenes

    Science.gov (United States)

    Kypraios, Ioannis; Young, Rupert C. D.; Chatwin, Chris R.; Birch, Phil M.

    2009-04-01

    θThe window unit in the design of the complex logarithmic r-θ mapping for hybrid optical neural network filter can allow multiple objects of the same class to be detected within the input image. Additionally, the architecture of the neural network unit of the complex logarithmic r-θ mapping for hybrid optical neural network filter becomes attractive for accommodating the recognition of multiple objects of different classes within the input image by modifying the output layer of the unit. We test the overall filter for multiple objects of the same and of different classes' recognition within cluttered input images and video sequences of cluttered scenes. Logarithmic r-θ mapping for hybrid optical neural network filter is shown to exhibit with a single pass over the input data simultaneously in-plane rotation, out-of-plane rotation, scale, log r-θ map translation and shift invariance, and good clutter tolerance by recognizing correctly the different objects within the cluttered scenes. We record in our results additional extracted information from the cluttered scenes about the objects' relative position, scale and in-plane rotation.

  11. Integration trumps selection in object recognition

    Science.gov (United States)

    Saarela, Toni P.; Landy, Michael S.

    2015-01-01

    Summary Finding and recognizing objects is a fundamental task of vision. Objects can be defined by several “cues” (color, luminance, texture etc.), and humans can integrate sensory cues to improve detection and recognition [1–3]. Cortical mechanisms fuse information from multiple cues [4], and shape-selective neural mechanisms can display cue-invariance by responding to a given shape independent of the visual cue defining it [5–8]. Selective attention, in contrast, improves recognition by isolating a subset of the visual information [9]. Humans can select single features (red or vertical) within a perceptual dimension (color or orientation), giving faster and more accurate responses to items having the attended feature [10,11]. Attention elevates neural responses and sharpens neural tuning to the attended feature, as shown by studies in psychophysics and modeling [11,12], imaging [13–16], and single-cell and neural population recordings [17,18]. Besides single features, attention can select whole objects [19–21]. Objects are among the suggested “units” of attention because attention to a single feature of an object causes the selection of all of its features [19–21]. Here, we pit integration against attentional selection in object recognition. We find, first, that humans can integrate information near-optimally from several perceptual dimensions (color, texture, luminance) to improve recognition. They cannot, however, isolate a single dimension even when the other dimensions provide task-irrelevant, potentially conflicting information. For object recognition, it appears that there is mandatory integration of information from multiple dimensions of visual experience. The advantage afforded by this integration, however, comes at the expense of attentional selection. PMID:25802154

  12. Integration trumps selection in object recognition.

    Science.gov (United States)

    Saarela, Toni P; Landy, Michael S

    2015-03-30

    Finding and recognizing objects is a fundamental task of vision. Objects can be defined by several "cues" (color, luminance, texture, etc.), and humans can integrate sensory cues to improve detection and recognition [1-3]. Cortical mechanisms fuse information from multiple cues [4], and shape-selective neural mechanisms can display cue invariance by responding to a given shape independent of the visual cue defining it [5-8]. Selective attention, in contrast, improves recognition by isolating a subset of the visual information [9]. Humans can select single features (red or vertical) within a perceptual dimension (color or orientation), giving faster and more accurate responses to items having the attended feature [10, 11]. Attention elevates neural responses and sharpens neural tuning to the attended feature, as shown by studies in psychophysics and modeling [11, 12], imaging [13-16], and single-cell and neural population recordings [17, 18]. Besides single features, attention can select whole objects [19-21]. Objects are among the suggested "units" of attention because attention to a single feature of an object causes the selection of all of its features [19-21]. Here, we pit integration against attentional selection in object recognition. We find, first, that humans can integrate information near optimally from several perceptual dimensions (color, texture, luminance) to improve recognition. They cannot, however, isolate a single dimension even when the other dimensions provide task-irrelevant, potentially conflicting information. For object recognition, it appears that there is mandatory integration of information from multiple dimensions of visual experience. The advantage afforded by this integration, however, comes at the expense of attentional selection. Copyright © 2015 Elsevier Ltd. All rights reserved.

  13. View-invariant object recognition ability develops after discrimination, not mere exposure, at several viewing angles.

    Science.gov (United States)

    Yamashita, Wakayo; Wang, Gang; Tanaka, Keiji

    2010-01-01

    One usually fails to recognize an unfamiliar object across changes in viewing angle when it has to be discriminated from similar distractor objects. Previous work has demonstrated that after long-term experience in discriminating among a set of objects seen from the same viewing angle, immediate recognition of the objects across 30-60 degrees changes in viewing angle becomes possible. The capability for view-invariant object recognition should develop during the within-viewing-angle discrimination, which includes two kinds of experience: seeing individual views and discriminating among the objects. The aim of the present study was to determine the relative contribution of each factor to the development of view-invariant object recognition capability. Monkeys were first extensively trained in a task that required view-invariant object recognition (Object task) with several sets of objects. The animals were then exposed to a new set of objects over 26 days in one of two preparatory tasks: one in which each object view was seen individually, and a second that required discrimination among the objects at each of four viewing angles. After the preparatory period, we measured the monkeys' ability to recognize the objects across changes in viewing angle, by introducing the object set to the Object task. Results indicated significant view-invariant recognition after the second but not first preparatory task. These results suggest that discrimination of objects from distractors at each of several viewing angles is required for the development of view-invariant recognition of the objects when the distractors are similar to the objects.

  14. Hippocampal histone acetylation regulates object recognition and the estradiol-induced enhancement of object recognition.

    Science.gov (United States)

    Zhao, Zaorui; Fan, Lu; Fortress, Ashley M; Boulware, Marissa I; Frick, Karyn M

    2012-02-15

    Histone acetylation has recently been implicated in learning and memory processes, yet necessity of histone acetylation for such processes has not been demonstrated using pharmacological inhibitors of histone acetyltransferases (HATs). As such, the present study tested whether garcinol, a potent HAT inhibitor in vitro, could impair hippocampal memory consolidation and block the memory-enhancing effects of the modulatory hormone 17β-estradiol E2. We first showed that bilateral infusion of garcinol (0.1, 1, or 10 μg/side) into the dorsal hippocampus (DH) immediately after training impaired object recognition memory consolidation in ovariectomized female mice. A behaviorally effective dose of garcinol (10 μg/side) also significantly decreased DH HAT activity. We next examined whether DH infusion of a behaviorally subeffective dose of garcinol (1 ng/side) could block the effects of DH E2 infusion on object recognition and epigenetic processes. Immediately after training, ovariectomized female mice received bilateral DH infusions of vehicle, E2 (5 μg/side), garcinol (1 ng/side), or E2 plus garcinol. Forty-eight hours later, garcinol blocked the memory-enhancing effects of E2. Garcinol also reversed the E2-induced increase in DH histone H3 acetylation, HAT activity, and levels of the de novo methyltransferase DNMT3B, as well as the E2-induced decrease in levels of the memory repressor protein histone deacetylase 2. Collectively, these findings suggest that histone acetylation is critical for object recognition memory consolidation and the beneficial effects of E2 on object recognition. Importantly, this work demonstrates that the role of histone acetylation in memory processes can be studied using a HAT inhibitor.

  15. Associative recognition and the hippocampus: differential effects of hippocampal lesions on object-place, object-context and object-place-context memory.

    Science.gov (United States)

    Langston, Rosamund F; Wood, Emma R

    2010-10-01

    The hippocampus is thought to be required for the associative recognition of objects together with the spatial or temporal contexts in which they occur. However, recent data showing that rats with fornix lesions perform as well as controls in an object-place task, while being impaired on an object-place-context task (Eacott and Norman (2004) J Neurosci 24:1948-1953), suggest that not all forms of context-dependent associative recognition depend on the integrity of the hippocampus. To examine the role of the hippocampus in context-dependent recognition directly, the present study tested the effects of large, selective, bilateral hippocampus lesions in rats on performance of a series of spontaneous recognition memory tasks: object recognition, object-place recognition, object-context recognition and object-place-context recognition. Consistent with the effects of fornix lesions, animals with hippocampus lesions were impaired only on the object-place-context task. These data confirm that not all forms of context-dependent associative recognition are mediated by the hippocampus. Subsequent experiments suggested that the object-place task does not require an allocentric representation of space, which could account for the lack of impairment following hippocampus lesions. Importantly, as the object-place-context task has similar spatial requirements, the selective deficit in object-place-context recognition suggests that this task requires hippocampus-dependent neural processes distinct from those required for allocentric spatial memory, or for object memory, object-place memory or object-context memory. Two possibilities are that object, place, and context information converge only in the hippocampus, or that recognition of integrated object-place-context information requires a hippocampus-dependent mode of retrieval, such as recollection. © 2009 Wiley-Liss, Inc.

  16. Active exploration and keypoint clustering for object recognition

    NARCIS (Netherlands)

    Kootstra, G.W.; Ypma, J; de Boer, B.

    2008-01-01

    Object recognition is a challenging problem for artificial systems. This is especially true for objects that are placed in cluttered and uncontrolled environments. To challenge this problem, we discuss an active approach to object recognition. Instead of passively observing objects, we use a robot

  17. The Role of Perceptual Load in Object Recognition

    Science.gov (United States)

    Lavie, Nilli; Lin, Zhicheng; Zokaei, Nahid; Thoma, Volker

    2009-01-01

    Predictions from perceptual load theory (Lavie, 1995, 2005) regarding object recognition across the same or different viewpoints were tested. Results showed that high perceptual load reduces distracter recognition levels despite always presenting distracter objects from the same view. They also showed that the levels of distracter recognition were…

  18. Fast neuromimetic object recognition using FPGA outperforms GPU implementations.

    Science.gov (United States)

    Orchard, Garrick; Martin, Jacob G; Vogelstein, R Jacob; Etienne-Cummings, Ralph

    2013-08-01

    Recognition of objects in still images has traditionally been regarded as a difficult computational problem. Although modern automated methods for visual object recognition have achieved steadily increasing recognition accuracy, even the most advanced computational vision approaches are unable to obtain performance equal to that of humans. This has led to the creation of many biologically inspired models of visual object recognition, among them the hierarchical model and X (HMAX) model. HMAX is traditionally known to achieve high accuracy in visual object recognition tasks at the expense of significant computational complexity. Increasing complexity, in turn, increases computation time, reducing the number of images that can be processed per unit time. In this paper we describe how the computationally intensive and biologically inspired HMAX model for visual object recognition can be modified for implementation on a commercial field-programmable aate Array, specifically the Xilinx Virtex 6 ML605 evaluation board with XC6VLX240T FPGA. We show that with minor modifications to the traditional HMAX model we can perform recognition on images of size 128 × 128 pixels at a rate of 190 images per second with a less than 1% loss in recognition accuracy in both binary and multiclass visual object recognition tasks.

  19. One-single physical exercise session after object recognition learning promotes memory persistence through hippocampal noradrenergic mechanisms.

    Science.gov (United States)

    da Silva de Vargas, Liane; Neves, Ben-Hur Souto das; Roehrs, Rafael; Izquierdo, Iván; Mello-Carpes, Pâmela

    2017-06-30

    Previously we showed the involvement of the hippocampal noradrenergic system in the consolidation and persistence of object recognition (OR) memory. Here we show that one-single physical exercise session performed immediately after learning promotes OR memory persistence and increases norepinephrine levels in the hippocampus. Additionally, effects of exercise on memory are avoided by an intra-hippocampal beta-adrenergic antagonist infusion. Taken together, these results suggest that exercise effects on memory can be related to noradrenergic mechanisms and acute physical exercise can be a non-pharmacological intervention to assist memory consolidation and persistence, with few or no side effects. Copyright © 2017 Elsevier B.V. All rights reserved.

  20. Crossmodal object recognition in rats with and without multimodal object pre-exposure: no effect of hippocampal lesions.

    Science.gov (United States)

    Reid, James M; Jacklin, Derek L; Winters, Boyer D

    2012-10-01

    The neural mechanisms and brain circuitry involved in the formation, storage, and utilization of multisensory object representations are poorly understood. We have recently introduced a crossmodal object recognition (CMOR) task that enables the study of such questions in rats. Our previous research has indicated that the perirhinal and posterior parietal cortices functionally interact to mediate spontaneous (tactile-to-visual) CMOR performance in rats; however, it remains to be seen whether other brain regions, particularly those receiving polymodal sensory inputs, contribute to this cognitive function. In the current study, we assessed the potential contribution of one such polymodal region, the hippocampus (HPC), to crossmodal object recognition memory. Rats with bilateral excitotoxic HPC lesions were tested in two versions of crossmodal object recognition: (1) the original CMOR task, which requires rats to compare between a stored tactile object representation and visually-presented objects to discriminate the novel and familiar stimuli; and (2) a novel 'multimodal pre-exposure' version of the CMOR task (PE/CMOR), in which simultaneous exploration of the tactile and visual sensory features of an object 24 h prior to the sample phase enhances CMOR performance across longer retention delays. Hippocampus-lesioned rats performed normally on both crossmodal object recognition tasks, but were impaired on a radial arm maze test of spatial memory, demonstrating the functional effectiveness of the lesions. These results strongly suggest that the HPC, despite its polymodal anatomical connections, is not critically involved in tactile-to-visual crossmodal object recognition memory. Copyright © 2012 Elsevier Inc. All rights reserved.

  1. Object Recognition and Localization: The Role of Tactile Sensors

    Directory of Open Access Journals (Sweden)

    Achint Aggarwal

    2014-02-01

    Full Text Available Tactile sensors, because of their intrinsic insensitivity to lighting conditions and water turbidity, provide promising opportunities for augmenting the capabilities of vision sensors in applications involving object recognition and localization. This paper presents two approaches for haptic object recognition and localization for ground and underwater environments. The first approach called Batch Ransac and Iterative Closest Point augmented Particle Filter (BRICPPF is based on an innovative combination of particle filters, Iterative-Closest-Point algorithm, and a feature-based Random Sampling and Consensus (RANSAC algorithm for database matching. It can handle a large database of 3D-objects of complex shapes and performs a complete six-degree-of-freedom localization of static objects. The algorithms are validated by experimentation in ground and underwater environments using real hardware. To our knowledge this is the first instance of haptic object recognition and localization in underwater environments. The second approach is biologically inspired, and provides a close integration between exploration and recognition. An edge following exploration strategy is developed that receives feedback from the current state of recognition. A recognition by parts approach is developed which uses the BRICPPF for object sub-part recognition. Object exploration is either directed to explore a part until it is successfully recognized, or is directed towards new parts to endorse the current recognition belief. This approach is validated by simulation experiments.

  2. Differential effects of spaced vs. massed training in long-term object-identity and object-location recognition memory.

    Science.gov (United States)

    Bello-Medina, Paola C; Sánchez-Carrasco, Livia; González-Ornelas, Nadia R; Jeffery, Kathryn J; Ramírez-Amaya, Víctor

    2013-08-01

    Here we tested whether the well-known superiority of spaced training over massed training is equally evident in both object identity and object location recognition memory. We trained animals with objects placed in a variable or in a fixed location to produce a location-independent object identity memory or a location-dependent object representation. The training consisted of 5 trials that occurred either on one day (Massed) or over the course of 5 consecutive days (Spaced). The memory test was done in independent groups of animals either 24h or 7 days after the last training trial. In each test the animals were exposed to either a novel object, when trained with the objects in variable locations, or to a familiar object in a novel location, when trained with objects in fixed locations. The difference in time spent exploring the changed versus the familiar objects was used as a measure of recognition memory. For the object-identity-trained animals, spaced training produced clear evidence of recognition memory after both 24h and 7 days, but massed-training animals showed it only after 24h. In contrast, for the object-location-trained animals, recognition memory was evident after both retention intervals and with both training procedures. When objects were placed in variable locations for the two types of training and the test was done with a brand-new location, only the spaced-training animals showed recognition at 24h, but surprisingly, after 7 days, animals trained using both procedures were able to recognize the change, suggesting a post-training consolidation process. We suggest that the two training procedures trigger different neural mechanisms that may differ in the two segregated streams that process object information and that may consolidate differently. Copyright © 2013 Elsevier B.V. All rights reserved.

  3. Recognition judgments and the performance of the recognition heuristic depend on the size of the reference class

    Directory of Open Access Journals (Sweden)

    Ulrich Hoffrage

    2011-02-01

    Full Text Available In a series of three experiments, participants made inferences about which one of a pair of two objects scored higher on a criterion. The first experiment was designed to contrast the prediction of Probabilistic Mental Model theory (Gigerenzer, Hoffrage, and Kleinbolting, 1991 concerning sampling procedure with the hard-easy effect. The experiment failed to support the theory's prediction that a particular pair of randomly sampled item sets would differ in percentage correct; but the observation that German participants performed practically as well on comparisons between U.S. cities (many of which they did not even recognize than on comparisons between German cities (about which they knew much more ultimately led to the formulation of the recognition heuristic. Experiment 2 was a second, this time successful, attempt to unconfound item difficulty and sampling procedure. In Experiment 3, participants' knowledge and recognition of each city was elicited, and how often this could be used to make an inference was manipulated. Choices were consistent with the recognition heuristic in about 80% of the cases when it discriminated and people had no additional knowledge about the recognized city (and in about 90% when they had such knowledge. The frequency with which the heuristic could be used affected the percentage correct, mean confidence, and overconfidence as predicted. The size of the reference class, which was also manipulated, modified these effects in meaningful and theoretically important ways.

  4. Object recognition memory: neurobiological mechanisms of encoding, consolidation and retrieval.

    Science.gov (United States)

    Winters, Boyer D; Saksida, Lisa M; Bussey, Timothy J

    2008-07-01

    Tests of object recognition memory, or the judgment of the prior occurrence of an object, have made substantial contributions to our understanding of the nature and neurobiological underpinnings of mammalian memory. Only in recent years, however, have researchers begun to elucidate the specific brain areas and neural processes involved in object recognition memory. The present review considers some of this recent research, with an emphasis on studies addressing the neural bases of perirhinal cortex-dependent object recognition memory processes. We first briefly discuss operational definitions of object recognition and the common behavioural tests used to measure it in non-human primates and rodents. We then consider research from the non-human primate and rat literature examining the anatomical basis of object recognition memory in the delayed nonmatching-to-sample (DNMS) and spontaneous object recognition (SOR) tasks, respectively. The results of these studies overwhelmingly favor the view that perirhinal cortex (PRh) is a critical region for object recognition memory. We then discuss the involvement of PRh in the different stages--encoding, consolidation, and retrieval--of object recognition memory. Specifically, recent work in rats has indicated that neural activity in PRh contributes to object memory encoding, consolidation, and retrieval processes. Finally, we consider the pharmacological, cellular, and molecular factors that might play a part in PRh-mediated object recognition memory. Recent studies in rodents have begun to indicate the remarkable complexity of the neural substrates underlying this seemingly simple aspect of declarative memory.

  5. Color descriptors for object category recognition

    NARCIS (Netherlands)

    van de Sande, K.E.A.; Gevers, T.; Snoek, C.G.M.

    2008-01-01

    Category recognition is important to access visual information on the level of objects. A common approach is to compute image descriptors first and then to apply machine learning to achieve category recognition from annotated examples. As a consequence, the choice of image descriptors is of great

  6. Evaluating color descriptors for object and scene recognition.

    Science.gov (United States)

    van de Sande, Koen E A; Gevers, Theo; Snoek, Cees G M

    2010-09-01

    Image category recognition is important to access visual information on the level of objects and scene types. So far, intensity-based descriptors have been widely used for feature extraction at salient points. To increase illumination invariance and discriminative power, color descriptors have been proposed. Because many different descriptors exist, a structured overview is required of color invariant descriptors in the context of image category recognition. Therefore, this paper studies the invariance properties and the distinctiveness of color descriptors (software to compute the color descriptors from this paper is available from http://www.colordescriptors.com) in a structured way. The analytical invariance properties of color descriptors are explored, using a taxonomy based on invariance properties with respect to photometric transformations, and tested experimentally using a data set with known illumination conditions. In addition, the distinctiveness of color descriptors is assessed experimentally using two benchmarks, one from the image domain and one from the video domain. From the theoretical and experimental results, it can be derived that invariance to light intensity changes and light color changes affects category recognition. The results further reveal that, for light intensity shifts, the usefulness of invariance is category-specific. Overall, when choosing a single descriptor and no prior knowledge about the data set and object and scene categories is available, the OpponentSIFT is recommended. Furthermore, a combined set of color descriptors outperforms intensity-based SIFT and improves category recognition by 8 percent on the PASCAL VOC 2007 and by 7 percent on the Mediamill Challenge.

  7. Enhancing Perception with Tactile Object Recognition in Adaptive Grippers for Human–Robot Interaction

    Directory of Open Access Journals (Sweden)

    Juan M. Gandarias

    2018-02-01

    Full Text Available The use of tactile perception can help first response robotic teams in disaster scenarios, where visibility conditions are often reduced due to the presence of dust, mud, or smoke, distinguishing human limbs from other objects with similar shapes. Here, the integration of the tactile sensor in adaptive grippers is evaluated, measuring the performance of an object recognition task based on deep convolutional neural networks (DCNNs using a flexible sensor mounted in adaptive grippers. A total of 15 classes with 50 tactile images each were trained, including human body parts and common environment objects, in semi-rigid and flexible adaptive grippers based on the fin ray effect. The classifier was compared against the rigid configuration and a support vector machine classifier (SVM. Finally, a two-level output network has been proposed to provide both object-type recognition and human/non-human classification. Sensors in adaptive grippers have a higher number of non-null tactels (up to 37% more, with a lower mean of pressure values (up to 72% less than when using a rigid sensor, with a softer grip, which is needed in physical human–robot interaction (pHRI. A semi-rigid implementation with 95.13% object recognition rate was chosen, even though the human/non-human classification had better results (98.78% with a rigid sensor.

  8. Enhancing Perception with Tactile Object Recognition in Adaptive Grippers for Human-Robot Interaction.

    Science.gov (United States)

    Gandarias, Juan M; Gómez-de-Gabriel, Jesús M; García-Cerezo, Alfonso J

    2018-02-26

    The use of tactile perception can help first response robotic teams in disaster scenarios, where visibility conditions are often reduced due to the presence of dust, mud, or smoke, distinguishing human limbs from other objects with similar shapes. Here, the integration of the tactile sensor in adaptive grippers is evaluated, measuring the performance of an object recognition task based on deep convolutional neural networks (DCNNs) using a flexible sensor mounted in adaptive grippers. A total of 15 classes with 50 tactile images each were trained, including human body parts and common environment objects, in semi-rigid and flexible adaptive grippers based on the fin ray effect. The classifier was compared against the rigid configuration and a support vector machine classifier (SVM). Finally, a two-level output network has been proposed to provide both object-type recognition and human/non-human classification. Sensors in adaptive grippers have a higher number of non-null tactels (up to 37% more), with a lower mean of pressure values (up to 72% less) than when using a rigid sensor, with a softer grip, which is needed in physical human-robot interaction (pHRI). A semi-rigid implementation with 95.13% object recognition rate was chosen, even though the human/non-human classification had better results (98.78%) with a rigid sensor.

  9. Very deep recurrent convolutional neural network for object recognition

    Science.gov (United States)

    Brahimi, Sourour; Ben Aoun, Najib; Ben Amar, Chokri

    2017-03-01

    In recent years, Computer vision has become a very active field. This field includes methods for processing, analyzing, and understanding images. The most challenging problems in computer vision are image classification and object recognition. This paper presents a new approach for object recognition task. This approach exploits the success of the Very Deep Convolutional Neural Network for object recognition. In fact, it improves the convolutional layers by adding recurrent connections. This proposed approach was evaluated on two object recognition benchmarks: Pascal VOC 2007 and CIFAR-10. The experimental results prove the efficiency of our method in comparison with the state of the art methods.

  10. Neural substrates of view-invariant object recognition developed without experiencing rotations of the objects.

    Science.gov (United States)

    Okamura, Jun-Ya; Yamaguchi, Reona; Honda, Kazunari; Wang, Gang; Tanaka, Keiji

    2014-11-05

    One fails to recognize an unfamiliar object across changes in viewing angle when it must be discriminated from similar distractor objects. View-invariant recognition gradually develops as the viewer repeatedly sees the objects in rotation. It is assumed that different views of each object are associated with one another while their successive appearance is experienced in rotation. However, natural experience of objects also contains ample opportunities to discriminate among objects at each of the multiple viewing angles. Our previous behavioral experiments showed that after experiencing a new set of object stimuli during a task that required only discrimination at each of four viewing angles at 30° intervals, monkeys could recognize the objects across changes in viewing angle up to 60°. By recording activities of neurons from the inferotemporal cortex after various types of preparatory experience, we here found a possible neural substrate for the monkeys' performance. For object sets that the monkeys had experienced during the task that required only discrimination at each of four viewing angles, many inferotemporal neurons showed object selectivity covering multiple views. The degree of view generalization found for these object sets was similar to that found for stimulus sets with which the monkeys had been trained to conduct view-invariant recognition. These results suggest that the experience of discriminating new objects in each of several viewing angles develops the partially view-generalized object selectivity distributed over many neurons in the inferotemporal cortex, which in turn bases the monkeys' emergent capability to discriminate the objects across changes in viewing angle. Copyright © 2014 the authors 0270-6474/14/3415047-13$15.00/0.

  11. Object recognition in images by human vision and computer vision

    NARCIS (Netherlands)

    Chen, Q.; Dijkstra, J.; Vries, de B.

    2010-01-01

    Object recognition plays a major role in human behaviour research in the built environment. Computer based object recognition techniques using images as input are challenging, but not an adequate representation of human vision. This paper reports on the differences in object shape recognition

  12. Representing Objects using Global 3D Relational Features for Recognition Tasks

    DEFF Research Database (Denmark)

    Mustafa, Wail

    2015-01-01

    representations. For representing objects, we derive global descriptors encoding shape using viewpoint-invariant features obtained from multiple sensors observing the scene. Objects are also described using color independently. This allows for combining color and shape when it is required for the task. For more...... robust color description, color calibration is performed. The framework was used in three recognition tasks: object instance recognition, object category recognition, and object spatial relationship recognition. For the object instance recognition task, we present a system that utilizes color and scale...

  13. Left posterior BA37 is involved in object recognition: a TMS study

    DEFF Research Database (Denmark)

    Stewart, Lauren; Meyer, Bernd-Ulrich; Frith, Uta

    2001-01-01

    Functional imaging studies have proposed a role for left BA37 in phonological retrieval, semantic processing, face processing and object recognition. The present study targeted the posterior aspect of BA37 to see whether a deficit, specific to one of the above types of processing could be induced...... to name pictures when TMS was given over lBA37 compared to vertex or rBA37. rTMS over lBA37 had no significant effect on word reading, nonword reading or colour naming. The picture naming deficit is suggested to result from a disruption to object recognition processes. This study corroborates the finding...... from a recent imaging study, that the most posterior part of left hemispheric BA37 has a necessary role in object recognition....

  14. Utilization-based object recognition in confined spaces

    Science.gov (United States)

    Shirkhodaie, Amir; Telagamsetti, Durga; Chan, Alex L.

    2017-05-01

    Recognizing substantially occluded objects in confined spaces is a very challenging problem for ground-based persistent surveillance systems. In this paper, we discuss the ontology inference of occluded object recognition in the context of in-vehicle group activities (IVGA) and describe an approach that we refer to as utilization-based object recognition method. We examine the performance of three types of classifiers tailored for the recognition of objects with partial visibility, namely, (1) Hausdorff Distance classifier, (2) Hamming Network classifier, and (3) Recurrent Neural Network classifier. In order to train these classifiers, we have generated multiple imagery datasets containing a mixture of common objects appearing inside a vehicle with full or partial visibility and occultation. To generate dynamic interactions between multiple people, we model the IVGA scenarios using a virtual simulation environment, in which a number of simulated actors perform a variety of IVGA tasks independently or jointly. This virtual simulation engine produces the much needed imagery datasets for the verification and validation of the efficiency and effectiveness of the selected object recognizers. Finally, we improve the performance of these object recognizers by incorporating human gestural information that differentiates various object utilization or handling methods through the analyses of dynamic human-object interactions (HOI), human-human interactions (HHI), and human-vehicle interactions (HVI) in the context of IVGA.

  15. Contextual System of Symbol Structural Recognition based on an Object-Process Methodology

    OpenAIRE

    Delalandre, Mathieu

    2005-01-01

    We present in this paper a symbol recognition system for the graphic documents. This one is based on a contextual approach for symbol structural recognition exploiting an Object-Process Methodology. It uses a processing library composed of structural recognition processings and contextual evaluation processings. These processings allow our system to deal with the multi-representation of symbols. The different processings are controlled, in an automatic way, by an inference engine during the r...

  16. Transformation-tolerant object recognition in rats revealed by visual priming.

    Science.gov (United States)

    Tafazoli, Sina; Di Filippo, Alessandro; Zoccolan, Davide

    2012-01-04

    Successful use of rodents as models for studying object vision crucially depends on the ability of their visual system to construct representations of visual objects that tolerate (i.e., remain relatively unchanged with respect to) the tremendous changes in object appearance produced, for instance, by size and viewpoint variation. Whether this is the case is still controversial, despite some recent demonstration of transformation-tolerant object recognition in rats. In fact, it remains unknown to what extent such a tolerant recognition has a spontaneous, perceptual basis, or, alternatively, mainly reflects learning of arbitrary associative relations among trained object appearances. In this study, we addressed this question by training rats to categorize a continuum of morph objects resulting from blending two object prototypes. The resulting psychometric curve (reporting the proportion of responses to one prototype along the morph line) served as a reference when, in a second phase of the experiment, either prototype was briefly presented as a prime, immediately before a test morph object. The resulting shift of the psychometric curve showed that recognition became biased toward the identity of the prime. Critically, this bias was observed also when the primes were transformed along a variety of dimensions (i.e., size, position, viewpoint, and their combination) that the animals had never experienced before. These results indicate that rats spontaneously perceive different views/appearances of an object as similar (i.e., as instances of the same object) and argue for the existence of neuronal substrates underlying formation of transformation-tolerant object representations in rats.

  17. Object Recognition System-on-Chip Using the Support Vector Machines

    Directory of Open Access Journals (Sweden)

    Houzet Dominique

    2005-01-01

    Full Text Available The first aim of this work is to propose the design of a system-on-chip (SoC platform dedicated to digital image and signal processing, which is tuned to implement efficiently multiply-and-accumulate (MAC vector/matrix operations. The second aim of this work is to implement a recent promising neural network method, namely, the support vector machine (SVM used for real-time object recognition, in order to build a vision machine. With such a reconfigurable and programmable SoC platform, it is possible to implement any SVM function dedicated to any object recognition problem. The final aim is to obtain an automatic reconfiguration of the SoC platform, based on the results of the learning phase on an objects' database, which makes it possible to recognize practically any object without manual programming. Recognition can be of any kind that is from image to signal data. Such a system is a general-purpose automatic classifier. Many applications can be considered as a classification problem, but are usually treated specifically in order to optimize the cost of the implemented solution. The cost of our approach is more important than a dedicated one, but in a near future, hundreds of millions of gates will be common and affordable compared to the design cost. What we are proposing here is a general-purpose classification neural network implemented on a reconfigurable SoC platform. The first version presented here is limited in size and thus in object recognition performances, but can be easily upgraded according to technology improvements.

  18. Cultural differences in visual object recognition in 3-year-old children

    Science.gov (United States)

    Kuwabara, Megumi; Smith, Linda B.

    2016-01-01

    Recent research indicates that culture penetrates fundamental processes of perception and cognition (e.g. Nisbett & Miyamoto, 2005). Here, we provide evidence that these influences begin early and influence how preschool children recognize common objects. The three tasks (n=128) examined the degree to which nonface object recognition by 3 year olds was based on individual diagnostic features versus more configural and holistic processing. Task 1 used a 6-alternative forced choice task in which children were asked to find a named category in arrays of masked objects in which only 3 diagnostic features were visible for each object. U.S. children outperformed age-matched Japanese children. Task 2 presented pictures of objects to children piece by piece. U.S. children recognized the objects given fewer pieces than Japanese children and likelihood of recognition increased for U.S., but not Japanese children when the piece added was rated by both U.S. and Japanese adults as highly defining. Task 3 used a standard measure of configural progressing, asking the degree to which recognition of matching pictures was disrupted by the rotation of one picture. Japanese children’s recognition was more disrupted by inversion than was that of U.S. children, indicating more configural processing by Japanese than U.S. children. The pattern suggests early cross-cultural differences in visual processing; findings that raise important questions about how visual experiences differ across cultures and about universal patterns of cognitive development. PMID:26985576

  19. Cultural differences in visual object recognition in 3-year-old children.

    Science.gov (United States)

    Kuwabara, Megumi; Smith, Linda B

    2016-07-01

    Recent research indicates that culture penetrates fundamental processes of perception and cognition. Here, we provide evidence that these influences begin early and influence how preschool children recognize common objects. The three tasks (N=128) examined the degree to which nonface object recognition by 3-year-olds was based on individual diagnostic features versus more configural and holistic processing. Task 1 used a 6-alternative forced choice task in which children were asked to find a named category in arrays of masked objects where only three diagnostic features were visible for each object. U.S. children outperformed age-matched Japanese children. Task 2 presented pictures of objects to children piece by piece. U.S. children recognized the objects given fewer pieces than Japanese children, and the likelihood of recognition increased for U.S. children, but not Japanese children, when the piece added was rated by both U.S. and Japanese adults as highly defining. Task 3 used a standard measure of configural progressing, asking the degree to which recognition of matching pictures was disrupted by the rotation of one picture. Japanese children's recognition was more disrupted by inversion than was that of U.S. children, indicating more configural processing by Japanese than U.S. children. The pattern suggests early cross-cultural differences in visual processing; findings that raise important questions about how visual experiences differ across cultures and about universal patterns of cognitive development. Copyright © 2016 Elsevier Inc. All rights reserved.

  20. Communicative Signals Promote Object Recognition Memory and Modulate the Right Posterior STS.

    Science.gov (United States)

    Redcay, Elizabeth; Ludlum, Ruth S; Velnoskey, Kayla R; Kanwal, Simren

    2016-01-01

    Detection of communicative signals is thought to facilitate knowledge acquisition early in life, but less is known about the role these signals play in adult learning or about the brain systems supporting sensitivity to communicative intent. The current study examined how ostensive gaze cues and communicative actions affect adult recognition memory and modulate neural activity as measured by fMRI. For both the behavioral and fMRI experiments, participants viewed a series of videos of an actress acting on one of two objects in front of her. Communicative context in the videos was manipulated in a 2 × 2 design in which the actress either had direct gaze (Gaze) or wore a visor (NoGaze) and either pointed at (Point) or reached for (Reach) one of the objects (target) in front of her. Participants then completed a recognition memory task with old (target and nontarget) objects and novel objects. Recognition memory for target objects in the Gaze conditions was greater than NoGaze, but no effects of gesture type were seen. Similarly, the fMRI video-viewing task revealed a significant effect of Gaze within right posterior STS (pSTS), but no significant effects of Gesture. Furthermore, pSTS sensitivity to Gaze conditions was related to greater memory for objects viewed in Gaze, as compared with NoGaze, conditions. Taken together, these results demonstrate that the ostensive, communicative signal of direct gaze preceding an object-directed action enhances recognition memory for attended items and modulates the pSTS response to object-directed actions. Thus, establishment of a communicative context through ostensive signals remains an important component of learning and memory into adulthood, and the pSTS may play a role in facilitating this type of social learning.

  1. Model-based recognition of 3-D objects by geometric hashing technique

    International Nuclear Information System (INIS)

    Severcan, M.; Uzunalioglu, H.

    1992-09-01

    A model-based object recognition system is developed for recognition of polyhedral objects. The system consists of feature extraction, modelling and matching stages. Linear features are used for object descriptions. Lines are obtained from edges using rotation transform. For modelling and recognition process, geometric hashing method is utilized. Each object is modelled using 2-D views taken from the viewpoints on the viewing sphere. A hidden line elimination algorithm is used to find these views from the wire frame model of the objects. The recognition experiments yielded satisfactory results. (author). 8 refs, 5 figs

  2. Multispectral image analysis for object recognition and classification

    Science.gov (United States)

    Viau, C. R.; Payeur, P.; Cretu, A.-M.

    2016-05-01

    Computer and machine vision applications are used in numerous fields to analyze static and dynamic imagery in order to assist or automate decision-making processes. Advancements in sensor technologies now make it possible to capture and visualize imagery at various wavelengths (or bands) of the electromagnetic spectrum. Multispectral imaging has countless applications in various fields including (but not limited to) security, defense, space, medical, manufacturing and archeology. The development of advanced algorithms to process and extract salient information from the imagery is a critical component of the overall system performance. The fundamental objective of this research project was to investigate the benefits of combining imagery from the visual and thermal bands of the electromagnetic spectrum to improve the recognition rates and accuracy of commonly found objects in an office setting. A multispectral dataset (visual and thermal) was captured and features from the visual and thermal images were extracted and used to train support vector machine (SVM) classifiers. The SVM's class prediction ability was evaluated separately on the visual, thermal and multispectral testing datasets.

  3. Experience moderates overlap between object and face recognition, suggesting a common ability.

    Science.gov (United States)

    Gauthier, Isabel; McGugin, Rankin W; Richler, Jennifer J; Herzmann, Grit; Speegle, Magen; Van Gulick, Ana E

    2014-07-03

    Some research finds that face recognition is largely independent from the recognition of other objects; a specialized and innate ability to recognize faces could therefore have little or nothing to do with our ability to recognize objects. We propose a new framework in which recognition performance for any category is the product of domain-general ability and category-specific experience. In Experiment 1, we show that the overlap between face and object recognition depends on experience with objects. In 256 subjects we measured face recognition, object recognition for eight categories, and self-reported experience with these categories. Experience predicted neither face recognition nor object recognition but moderated their relationship: Face recognition performance is increasingly similar to object recognition performance with increasing object experience. If a subject has a lot of experience with objects and is found to perform poorly, they also prove to have a low ability with faces. In a follow-up survey, we explored the dimensions of experience with objects that may have contributed to self-reported experience in Experiment 1. Different dimensions of experience appear to be more salient for different categories, with general self-reports of expertise reflecting judgments of verbal knowledge about a category more than judgments of visual performance. The complexity of experience and current limitations in its measurement support the importance of aggregating across multiple categories. Our findings imply that both face and object recognition are supported by a common, domain-general ability expressed through experience with a category and best measured when accounting for experience. © 2014 ARVO.

  4. Object recognition based on Google's reverse image search and image similarity

    Science.gov (United States)

    Horváth, András.

    2015-12-01

    Image classification is one of the most challenging tasks in computer vision and a general multiclass classifier could solve many different tasks in image processing. Classification is usually done by shallow learning for predefined objects, which is a difficult task and very different from human vision, which is based on continuous learning of object classes and one requires years to learn a large taxonomy of objects which are not disjunct nor independent. In this paper I present a system based on Google image similarity algorithm and Google image database, which can classify a large set of different objects in a human like manner, identifying related classes and taxonomies.

  5. Recognition of Simple 3D Geometrical Objects under Partial Occlusion

    Science.gov (United States)

    Barchunova, Alexandra; Sommer, Gerald

    In this paper we present a novel procedure for contour-based recognition of partially occluded three-dimensional objects. In our approach we use images of real and rendered objects whose contours have been deformed by a restricted change of the viewpoint. The preparatory part consists of contour extraction, preprocessing, local structure analysis and feature extraction. The main part deals with an extended construction and functionality of the classifier ensemble Adaptive Occlusion Classifier (AOC). It relies on a hierarchical fragmenting algorithm to perform a local structure analysis which is essential when dealing with occlusions. In the experimental part of this paper we present classification results for five classes of simple geometrical figures: prism, cylinder, half cylinder, a cube, and a bridge. We compare classification results for three classical feature extractors: Fourier descriptors, pseudo Zernike and Zernike moments.

  6. Object Recognition Memory and the Rodent Hippocampus

    Science.gov (United States)

    Broadbent, Nicola J.; Gaskin, Stephane; Squire, Larry R.; Clark, Robert E.

    2010-01-01

    In rodents, the novel object recognition task (NOR) has become a benchmark task for assessing recognition memory. Yet, despite its widespread use, a consensus has not developed about which brain structures are important for task performance. We assessed both the anterograde and retrograde effects of hippocampal lesions on performance in the NOR…

  7. Sensor agnostic object recognition using a map seeking circuit

    Science.gov (United States)

    Overman, Timothy L.; Hart, Michael

    2012-05-01

    Automatic object recognition capabilities are traditionally tuned to exploit the specific sensing modality they were designed to. Their successes (and shortcomings) are tied to object segmentation from the background, they typically require highly skilled personnel to train them, and they become cumbersome with the introduction of new objects. In this paper we describe a sensor independent algorithm based on the biologically inspired technology of map seeking circuits (MSC) which overcomes many of these obstacles. In particular, the MSC concept offers transparency in object recognition from a common interface to all sensor types, analogous to a USB device. It also provides a common core framework that is independent of the sensor and expandable to support high dimensionality decision spaces. Ease in training is assured by using commercially available 3D models from the video game community. The search time remains linear no matter how many objects are introduced, ensuring rapid object recognition. Here, we report results of an MSC algorithm applied to object recognition and pose estimation from high range resolution radar (1D), electrooptical imagery (2D), and LIDAR point clouds (3D) separately. By abstracting the sensor phenomenology from the underlying a prior knowledge base, MSC shows promise as an easily adaptable tool for incorporating additional sensor inputs.

  8. Object similarity affects the perceptual strategy underlying invariant visual object recognition in rats

    Directory of Open Access Journals (Sweden)

    Federica Bianca Rosselli

    2015-03-01

    Full Text Available In recent years, a number of studies have explored the possible use of rats as models of high-level visual functions. One central question at the root of such an investigation is to understand whether rat object vision relies on the processing of visual shape features or, rather, on lower-order image properties (e.g., overall brightness. In a recent study, we have shown that rats are capable of extracting multiple features of an object that are diagnostic of its identity, at least when those features are, structure-wise, distinct enough to be parsed by the rat visual system. In the present study, we have assessed the impact of object structure on rat perceptual strategy. We trained rats to discriminate between two structurally similar objects, and compared their recognition strategies with those reported in our previous study. We found that, under conditions of lower stimulus discriminability, rat visual discrimination strategy becomes more view-dependent and subject-dependent. Rats were still able to recognize the target objects, in a way that was largely tolerant (i.e., invariant to object transformation; however, the larger structural and pixel-wise similarity affected the way objects were processed. Compared to the findings of our previous study, the patterns of diagnostic features were: i smaller and more scattered; ii only partially preserved across object views; and iii only partially reproducible across rats. On the other hand, rats were still found to adopt a multi-featural processing strategy and to make use of part of the optimal discriminatory information afforded by the two objects. Our findings suggest that, as in humans, rat invariant recognition can flexibly rely on either view-invariant representations of distinctive object features or view-specific object representations, acquired through learning.

  9. Real object recognition using moment invariants

    Indian Academy of Sciences (India)

    are taken from different angles of view are the main features leading us to our objective. ... Two-dimensional moments of a digitally sampled M × M image that has gray function f (x, y), (x, .... in this paper. Information about the original colours of the objects is not used. .... multi-dimensional changes and recognition. Table 1.

  10. Three-dimensional object recognition using similar triangles and decision trees

    Science.gov (United States)

    Spirkovska, Lilly

    1993-01-01

    A system, TRIDEC, that is capable of distinguishing between a set of objects despite changes in the objects' positions in the input field, their size, or their rotational orientation in 3D space is described. TRIDEC combines very simple yet effective features with the classification capabilities of inductive decision tree methods. The feature vector is a list of all similar triangles defined by connecting all combinations of three pixels in a coarse coded 127 x 127 pixel input field. The classification is accomplished by building a decision tree using the information provided from a limited number of translated, scaled, and rotated samples. Simulation results are presented which show that TRIDEC achieves 94 percent recognition accuracy in the 2D invariant object recognition domain and 98 percent recognition accuracy in the 3D invariant object recognition domain after training on only a small sample of transformed views of the objects.

  11. Distinct roles of basal forebrain cholinergic neurons in spatial and object recognition memory

    OpenAIRE

    Kana Okada; Kayo Nishizawa; Tomoko Kobayashi; Shogo Sakata; Kazuto Kobayashi

    2015-01-01

    Recognition memory requires processing of various types of information such as objects and locations. Impairment in recognition memory is a prominent feature of amnesia and a symptom of Alzheimer?s disease (AD). Basal forebrain cholinergic neurons contain two major groups, one localized in the medial septum (MS)/vertical diagonal band of Broca (vDB), and the other in the nucleus basalis magnocellularis (NBM). The roles of these cell groups in recognition memory have been debated, and it remai...

  12. An ERP Study on Self-Relevant Object Recognition

    Science.gov (United States)

    Miyakoshi, Makoto; Nomura, Michio; Ohira, Hideki

    2007-01-01

    We performed an event-related potential study to investigate the self-relevance effect in object recognition. Three stimulus categories were prepared: SELF (participant's own objects), FAMILIAR (disposable and public objects, defined as objects with less-self-relevant familiarity), and UNFAMILIAR (others' objects). The participants' task was to…

  13. Class Energy Image Analysis for Video Sensor-Based Gait Recognition: A Review

    Directory of Open Access Journals (Sweden)

    Zhuowen Lv

    2015-01-01

    Full Text Available Gait is a unique perceptible biometric feature at larger distances, and the gait representation approach plays a key role in a video sensor-based gait recognition system. Class Energy Image is one of the most important gait representation methods based on appearance, which has received lots of attentions. In this paper, we reviewed the expressions and meanings of various Class Energy Image approaches, and analyzed the information in the Class Energy Images. Furthermore, the effectiveness and robustness of these approaches were compared on the benchmark gait databases. We outlined the research challenges and provided promising future directions for the field. To the best of our knowledge, this is the first review that focuses on Class Energy Image. It can provide a useful reference in the literature of video sensor-based gait representation approach.

  14. Early age-dependent impairments of context-dependent extinction learning, object recognition, and object-place learning occur in rats.

    Science.gov (United States)

    Wiescholleck, Valentina; Emma André, Marion Agnès; Manahan-Vaughan, Denise

    2014-03-01

    The hippocampus is vulnerable to age-dependent memory decline. Multiple forms of memory depend on adequate hippocampal function. Extinction learning comprises active inhibition of no longer relevant learned information concurrent with suppression of a previously learned reaction. It is highly dependent on context, and evidence exists that it requires hippocampal activation. In this study, we addressed whether context-based extinction as well as hippocampus-dependent tasks, such as object recognition and object-place recognition, are equally affected by moderate aging. Young (7-8 week old) and older (7-8 month old) Wistar rats were used. For the extinction study, animals learned that a particular floor context indicated that they should turn into one specific arm (e.g., left) to receive a food reward. On the day after reaching the learning criterion of 80% correct choices, the floor context was changed, no reward was given and animals were expected to extinguish the learned response. Both, young and older rats managed this first extinction trial in the new context with older rats showing a faster extinction performance. One day later, animals were returned to the T-maze with the original floor context and renewal effects were assessed. In this case, only young but not older rats showed the expected renewal effect (lower extinction ratio as compared to the day before). To assess general memory abilities, animals were tested in the standard object recognition and object-place memory tasks. Evaluations were made at 5 min, 1 h and 7 day intervals. Object recognition memory was poor at short-term and intermediate time-points in older but not young rats. Object-place memory performance was unaffected at 5 min, but impaired at 1 h in older but not young rats. Both groups were impaired at 7 days. These findings support that not only aspects of general memory, but also context-dependent extinction learning, are affected by moderate aging. This may reflect less flexibility in

  15. First-Class Object Sets

    DEFF Research Database (Denmark)

    Ernst, Erik

    Typically, objects are monolithic entities with a fixed interface. To increase the flexibility in this area, this paper presents first-class object sets as a language construct. An object set offers an interface which is a disjoint union of the interfaces of its member objects. It may also be used...... for a special kind of method invocation involving multiple objects in a dynamic lookup process. With support for feature access and late-bound method calls object sets are similar to ordinary objects, only more flexible. The approach is made precise by means of a small calculus, and the soundness of its type...

  16. Dopamine D1 receptor activation leads to object recognition memory in a coral reef fish.

    Science.gov (United States)

    Hamilton, Trevor J; Tresguerres, Martin; Kline, David I

    2017-07-01

    Object recognition memory is the ability to identify previously seen objects and is an adaptive mechanism that increases survival for many species throughout the animal kingdom. Previously believed to be possessed by only the highest order mammals, it is now becoming clear that fish are also capable of this type of memory formation. Similar to the mammalian hippocampus, the dorsolateral pallium regulates distinct memory processes and is modulated by neurotransmitters such as dopamine. Caribbean bicolour damselfish ( Stegastes partitus ) live in complex environments dominated by coral reef structures and thus likely possess many types of complex memory abilities including object recognition. This study used a novel object recognition test in which fish were first presented two identical objects, then after a retention interval of 10 min with no objects, the fish were presented with a novel object and one of the objects they had previously encountered in the first trial. We demonstrate that the dopamine D 1 -receptor agonist (SKF 38393) induces the formation of object recognition memories in these fish. Thus, our results suggest that dopamine-receptor mediated enhancement of spatial memory formation in fish represents an evolutionarily conserved mechanism in vertebrates. © 2017 The Author(s).

  17. On the relation between face and object recognition in developmental prosopagnosia

    DEFF Research Database (Denmark)

    Gerlach, Christian; Klargaard, Solja K.; Starrfelt, Randi

    2016-01-01

    There is an ongoing debate about whether face recognition and object recognition constitute separate domains. Clarification of this issue can have important theoretical implications as face recognition is often used as a prime example of domain-specificity in mind and brain. An important source...... of input to this debate comes from studies of individuals with developmental prosopagnosia, suggesting that face recognition can be selectively impaired. We put the selectivity hypothesis to test by assessing the performance of 10 individuals with developmental prosopagnosia on demanding tests of visual...... object processing involving both regular and degraded drawings. None of the individuals exhibited a clear dissociation between face and object recognition, and as a group they were significantly more affected by degradation of objects than control participants. Importantly, we also find positive...

  18. Exploring objects for recognition in the real world

    NARCIS (Netherlands)

    Kootstra, Gert; Ypma, Jelmer; de Boer, Bart

    2007-01-01

    Perception in natural systems is a highly active process. In this paper, we adopt the strategy of natural systems to explore objects for 3D object recognition using robots. The exploration of objects enables the system to learn objects from different viewpoints, which is essential for 3D object

  19. Object recognition - Convergence of vision, audition, and touch

    DEFF Research Database (Denmark)

    Kassuba, Tanja

    of object information across audition and touch or across all thee senses. Further, even though object recognition within different senses is to some degree redundant, the different senses differ with respect to their intrinsic efficiency in extracting types of information (Lederman & Klatzky, 2009...... magnetic resonance imaging (fMRI), diffusion tensor imaging (DTI), and repetitive transcranial magnetic stimulation (rTMS). The following research questions were addressed: 1. Where in the human brain does object recognition converge across vision, audition, and touch? 2. How is audio-haptic object......-match-to-sample task was applied in which participants had to match a target object with a previously presented sample object within and across audition and touch in both directions (auditory─haptic and haptic─auditory). As a coherence in content is an important binding cue (Laurienti et al., 2004), semantic...

  20. Comparison of Object Recognition Behavior in Human and Monkey

    Science.gov (United States)

    Rajalingham, Rishi; Schmidt, Kailyn

    2015-01-01

    Although the rhesus monkey is used widely as an animal model of human visual processing, it is not known whether invariant visual object recognition behavior is quantitatively comparable across monkeys and humans. To address this question, we systematically compared the core object recognition behavior of two monkeys with that of human subjects. To test true object recognition behavior (rather than image matching), we generated several thousand naturalistic synthetic images of 24 basic-level objects with high variation in viewing parameters and image background. Monkeys were trained to perform binary object recognition tasks on a match-to-sample paradigm. Data from 605 human subjects performing the same tasks on Mechanical Turk were aggregated to characterize “pooled human” object recognition behavior, as well as 33 separate Mechanical Turk subjects to characterize individual human subject behavior. Our results show that monkeys learn each new object in a few days, after which they not only match mean human performance but show a pattern of object confusion that is highly correlated with pooled human confusion patterns and is statistically indistinguishable from individual human subjects. Importantly, this shared human and monkey pattern of 3D object confusion is not shared with low-level visual representations (pixels, V1+; models of the retina and primary visual cortex) but is shared with a state-of-the-art computer vision feature representation. Together, these results are consistent with the hypothesis that rhesus monkeys and humans share a common neural shape representation that directly supports object perception. SIGNIFICANCE STATEMENT To date, several mammalian species have shown promise as animal models for studying the neural mechanisms underlying high-level visual processing in humans. In light of this diversity, making tight comparisons between nonhuman and human primates is particularly critical in determining the best use of nonhuman primates to

  1. PROBABILISTIC APPROACH TO OBJECT DETECTION AND RECOGNITION FOR VIDEOSTREAM PROCESSING

    Directory of Open Access Journals (Sweden)

    Volodymyr Kharchenko

    2017-07-01

    Full Text Available Purpose: The represented research results are aimed to improve theoretical basics of computer vision and artificial intelligence of dynamical system. Proposed approach of object detection and recognition is based on probabilistic fundamentals to ensure the required level of correct object recognition. Methods: Presented approach is grounded at probabilistic methods, statistical methods of probability density estimation and computer-based simulation at verification stage of development. Results: Proposed approach for object detection and recognition for video stream data processing has shown several advantages in comparison with existing methods due to its simple realization and small time of data processing. Presented results of experimental verification look plausible for object detection and recognition in video stream. Discussion: The approach can be implemented in dynamical system within changeable environment such as remotely piloted aircraft systems and can be a part of artificial intelligence in navigation and control systems.

  2. Perceptual Plasticity for Auditory Object Recognition

    Science.gov (United States)

    Heald, Shannon L. M.; Van Hedger, Stephen C.; Nusbaum, Howard C.

    2017-01-01

    In our auditory environment, we rarely experience the exact acoustic waveform twice. This is especially true for communicative signals that have meaning for listeners. In speech and music, the acoustic signal changes as a function of the talker (or instrument), speaking (or playing) rate, and room acoustics, to name a few factors. Yet, despite this acoustic variability, we are able to recognize a sentence or melody as the same across various kinds of acoustic inputs and determine meaning based on listening goals, expectations, context, and experience. The recognition process relates acoustic signals to prior experience despite variability in signal-relevant and signal-irrelevant acoustic properties, some of which could be considered as “noise” in service of a recognition goal. However, some acoustic variability, if systematic, is lawful and can be exploited by listeners to aid in recognition. Perceivable changes in systematic variability can herald a need for listeners to reorganize perception and reorient their attention to more immediately signal-relevant cues. This view is not incorporated currently in many extant theories of auditory perception, which traditionally reduce psychological or neural representations of perceptual objects and the processes that act on them to static entities. While this reduction is likely done for the sake of empirical tractability, such a reduction may seriously distort the perceptual process to be modeled. We argue that perceptual representations, as well as the processes underlying perception, are dynamically determined by an interaction between the uncertainty of the auditory signal and constraints of context. This suggests that the process of auditory recognition is highly context-dependent in that the identity of a given auditory object may be intrinsically tied to its preceding context. To argue for the flexible neural and psychological updating of sound-to-meaning mappings across speech and music, we draw upon examples

  3. Partially Supervised Approach in Signal Recognition

    Directory of Open Access Journals (Sweden)

    Catalina COCIANU

    2009-01-01

    Full Text Available The paper focuses on the potential of principal directions based approaches in signal classification and recognition. In probabilistic models, the classes are represented in terms of multivariate density functions, and an object coming from a certain class is modeled as a random vector whose repartition has the density function corresponding to this class. In cases when there is no statistical information concerning the set of density functions corresponding to the classes involved in the recognition process, usually estimates based on the information extracted from available data are used instead. In the proposed methodology, the characteristics of a class are given by a set of eigen vectors of the sample covariance matrix. The overall dissimilarity of an object X with a given class C is computed as the disturbance of the structure of C, when X is allotted to C. A series of tests concerning the behavior of the proposed recognition algorithm are reported in the final section of the paper.

  4. Exploiting core knowledge for visual object recognition.

    Science.gov (United States)

    Schurgin, Mark W; Flombaum, Jonathan I

    2017-03-01

    Humans recognize thousands of objects, and with relative tolerance to variable retinal inputs. The acquisition of this ability is not fully understood, and it remains an area in which artificial systems have yet to surpass people. We sought to investigate the memory process that supports object recognition. Specifically, we investigated the association of inputs that co-occur over short periods of time. We tested the hypothesis that human perception exploits expectations about object kinematics to limit the scope of association to inputs that are likely to have the same token as a source. In several experiments we exposed participants to images of objects, and we then tested recognition sensitivity. Using motion, we manipulated whether successive encounters with an image took place through kinematics that implied the same or a different token as the source of those encounters. Images were injected with noise, or shown at varying orientations, and we included 2 manipulations of motion kinematics. Across all experiments, memory performance was better for images that had been previously encountered with kinematics that implied a single token. A model-based analysis similarly showed greater memory strength when images were shown via kinematics that implied a single token. These results suggest that constraints from physics are built into the mechanisms that support memory about objects. Such constraints-often characterized as 'Core Knowledge'-are known to support perception and cognition broadly, even in young infants. But they have never been considered as a mechanism for memory with respect to recognition. (PsycINFO Database Record (c) 2017 APA, all rights reserved).

  5. Training facilitates object recognition in cubist paintings

    Directory of Open Access Journals (Sweden)

    Martin Wiesmann

    2010-03-01

    Full Text Available To the naïve observer, cubist paintings contain geometrical forms in which familiar objects are hardly recognizable, even in the presence of a meaningful title. We used fMRI to test whether a short training session about Cubism would facilitate object recognition in paintings by Picasso, Braque and Gris. Subjects, who had no formal art education, were presented with titled or untitled cubist paintings and scrambled images, and performed object recognition tasks. Relative to the control group, trained subjects recognized more objects in the paintings, their response latencies were significantly shorter, and they showed enhanced activation in the parahippocampal cortex, with a parametric increase in the amplitude of the fMRI signal as a function of the number of recognized objects. Moreover, trained subjects were slower to report not recognizing any familiar objects in the paintings and these longer response latencies were correlated with activation in a fronto-parietal network. These findings suggest that trained subjects adopted a visual search strategy and used contextual associations to perform the tasks. Our study supports the proactive brain framework, according to which the brain uses associations to generate predictions.

  6. It takes two-skilled recognition of objects engages lateral areas in both hemispheres.

    Directory of Open Access Journals (Sweden)

    Merim Bilalić

    Full Text Available Our object recognition abilities, a direct product of our experience with objects, are fine-tuned to perfection. Left temporal and lateral areas along the dorsal, action related stream, as well as left infero-temporal areas along the ventral, object related stream are engaged in object recognition. Here we show that expertise modulates the activity of dorsal areas in the recognition of man-made objects with clearly specified functions. Expert chess players were faster than chess novices in identifying chess objects and their functional relations. Experts' advantage was domain-specific as there were no differences between groups in a control task featuring geometrical shapes. The pattern of eye movements supported the notion that experts' extensive knowledge about domain objects and their functions enabled superior recognition even when experts were not directly fixating the objects of interest. Functional magnetic resonance imaging (fMRI related exclusively the areas along the dorsal stream to chess specific object recognition. Besides the commonly involved left temporal and parietal lateral brain areas, we found that only in experts homologous areas on the right hemisphere were also engaged in chess specific object recognition. Based on these results, we discuss whether skilled object recognition does not only involve a more efficient version of the processes found in non-skilled recognition, but also qualitatively different cognitive processes which engage additional brain areas.

  7. Hippocampal NMDA receptors are involved in rats' spontaneous object recognition only under high memory load condition.

    Science.gov (United States)

    Sugita, Manami; Yamada, Kazuo; Iguchi, Natsumi; Ichitani, Yukio

    2015-10-22

    The possible involvement of hippocampal N-methyl-D-aspartate (NMDA) receptors in spontaneous object recognition was investigated in rats under different memory load conditions. We first estimated rats' object memory span using 3-5 objects in "Different Objects Task (DOT)" in order to confirm the highest memory load condition in object recognition memory. Rats were allowed to explore a field in which 3 (3-DOT), 4 (4-DOT), or 5 (5-DOT) different objects were presented. After a delay period, they were placed again in the same field in which one of the sample objects was replaced by another object, and their object exploration behavior was analyzed. Rats could differentiate the novel object from the familiar ones in 3-DOT and 4-DOT but not in 5-DOT, suggesting that rats' object memory span was about 4. Then, we examined the effects of hippocampal AP5 infusion on performance in both 2-DOT (2 different objects were used) and 4-DOT. The drug treatment before the sample phase impaired performance only in 4-DOT. These results suggest that hippocampal NMDA receptors play a critical role in spontaneous object recognition only when the memory load is high. Copyright © 2015 Elsevier B.V. All rights reserved.

  8. Involvement of hippocampal NMDA receptors in retrieval of spontaneous object recognition memory in rats.

    Science.gov (United States)

    Iwamura, Etsushi; Yamada, Kazuo; Ichitani, Yukio

    2016-07-01

    The involvement of hippocampal N-methyl-d-aspartate (NMDA) receptors in the retrieval process of spontaneous object recognition memory was investigated. The spontaneous object recognition test consisted of three phases. In the sample phase, rats were exposed to two identical objects several (2-5) times in the arena. After the sample phase, various lengths of delay intervals (24h-6 weeks) were inserted (delay phase). In the test phase in which both the familiar and the novel objects were placed in the arena, rats' novel object exploration behavior under the hippocampal treatment of NMDA receptor antagonist, AP5, or vehicle was observed. With 5 exposure sessions in the sample phase (experiment 1), AP5 treatment in the test phase significantly decreased discrimination ratio when the delay was 3 weeks but not when it was one week. On the other hand, with 2 exposure sessions in the sample phase (experiment 2) in which even vehicle-injected control animals could not discriminate the novel object from the familiar one with a 3 week delay, AP5 treatment significantly decreased discrimination ratio when the delay was one week, but not when it was 24h. Additional experiment (experiment 3) showed that the hippocampal treatment of an α-amino-3-hydroxy-5-methyl-4-isoxazolepropionic acid (AMPA) receptor antagonist, NBQX, decreased discrimination ratio with all delay intervals tested (24h-3 weeks). Results suggest that hippocampal NMDA receptors play an important role in the retrieval of spontaneous object recognition memory especially when the memory trace weakens. Copyright © 2016. Published by Elsevier B.V.

  9. Perceptual differentiation and category effects in normal object recognition

    DEFF Research Database (Denmark)

    Gerlach, Christian; Law, I; Gade, A

    1999-01-01

    The purpose of the present PET study was (i) to investigate the neural correlates of object recognition, i.e. the matching of visual forms to memory, and (ii) to test the hypothesis that this process is more difficult for natural objects than for artefacts. This was done by using object decision...... tasks where subjects decided whether pictures represented real objects or non-objects. The object decision tasks differed in their difficulty (the degree of perceptual differentiation needed to perform them) and in the category of the real objects used (natural objects versus artefacts). A clear effect...... be the neural correlate of matching visual forms to memory, and the amount of activation in these regions may correspond to the degree of perceptual differentiation required for recognition to occur. With respect to behaviour, it took significantly longer to make object decisions on natural objects than...

  10. Combining heterogenous features for 3D hand-held object recognition

    Science.gov (United States)

    Lv, Xiong; Wang, Shuang; Li, Xiangyang; Jiang, Shuqiang

    2014-10-01

    Object recognition has wide applications in the area of human-machine interaction and multimedia retrieval. However, due to the problem of visual polysemous and concept polymorphism, it is still a great challenge to obtain reliable recognition result for the 2D images. Recently, with the emergence and easy availability of RGB-D equipment such as Kinect, this challenge could be relieved because the depth channel could bring more information. A very special and important case of object recognition is hand-held object recognition, as hand is a straight and natural way for both human-human interaction and human-machine interaction. In this paper, we study the problem of 3D object recognition by combining heterogenous features with different modalities and extraction techniques. For hand-craft feature, although it reserves the low-level information such as shape and color, it has shown weakness in representing hiconvolutionalgh-level semantic information compared with the automatic learned feature, especially deep feature. Deep feature has shown its great advantages in large scale dataset recognition but is not always robust to rotation or scale variance compared with hand-craft feature. In this paper, we propose a method to combine hand-craft point cloud features and deep learned features in RGB and depth channle. First, hand-held object segmentation is implemented by using depth cues and human skeleton information. Second, we combine the extracted hetegerogenous 3D features in different stages using linear concatenation and multiple kernel learning (MKL). Then a training model is used to recognize 3D handheld objects. Experimental results validate the effectiveness and gerneralization ability of the proposed method.

  11. A Patient with Difficulty of Object Recognition: Semantic Amnesia for Manipulable Objects

    Directory of Open Access Journals (Sweden)

    A. Yamadori

    1992-01-01

    Full Text Available We studied a patient who had recognition difficulty for manipulable objects. MRI showed a lesion in the left occipito-parietotemporal area. Differential diagnosis of agnosia, aphasia and apraxia is discussed. We believe this “object meaning amnesia” constitutes a distinct subtype of semantic amnesia.

  12. Leveraging Cognitive Context for Object Recognition

    Science.gov (United States)

    2014-06-01

    established, links have an associated strength value which affects how much activation is passed along the link from chunk j to chunk i. Link strengths ... strength is updated iteratively whenever the model thinks about chunks i context suggests that an apple is most likely to be seen next (since it primes...1998. 1, 4 [3] M. E. Auckland , K. R. Cave, and N. Donnelly. Non- target objects can influence perceptual processes dur- ing object recognition

  13. An Innovative SIFT-Based Method for Rigid Video Object Recognition

    Directory of Open Access Journals (Sweden)

    Jie Yu

    2014-01-01

    Full Text Available This paper presents an innovative SIFT-based method for rigid video object recognition (hereafter called RVO-SIFT. Just like what happens in the vision system of human being, this method makes the object recognition and feature updating process organically unify together, using both trajectory and feature matching, and thereby it can learn new features not only in the training stage but also in the recognition stage, which can improve greatly the completeness of the video object’s features automatically and, in turn, increases the ratio of correct recognition drastically. The experimental results on real video sequences demonstrate its surprising robustness and efficiency.

  14. Dorsal stream involvement in recognition of objects with transient onset but not with ramped onset

    Directory of Open Access Journals (Sweden)

    Lourenco Tomas

    2011-08-01

    Full Text Available Abstract Background Although the ventral visual stream is understood to be responsible for object recognition, it has been proposed that the dorsal stream may contribute to object recognition by rapidly activating parietal attention mechanisms, prior to ventral stream object processing. Methods To investigate the relative contribution of the dorsal visual stream to object recognition a group of tertiary students were divided into good and poor motion coherence groups and assessed on tasks classically assumed to rely on ventral stream processing. Participants were required to identify simple line drawings in two tasks, one where objects were presented abruptly for 50 ms followed by a white-noise mask, the other where contrast was linearly ramped on and off over 325 ms and replaced with a mask. Results Although both groups only differed in motion coherence performance (a dorsal stream measure, the good motion coherence group showed superior contrast sensitivity for object recognition on the abrupt, but not the ramped presentation tasks. Conclusions We propose that abrupt presentation of objects activated attention mechanisms fed by the dorsal stream, whereas the ramped presentation had reduced transience and thus did not activate dorsal attention mechanisms as well. The results suggest that rapid dorsal stream activation may be required to assist with ventral stream object processing.

  15. What are the visual features underlying rapid object recognition?

    Directory of Open Access Journals (Sweden)

    Sébastien M Crouzet

    2011-11-01

    Full Text Available Research progress in machine vision has been very significant in recent years. Robust face detection and identification algorithms are already readily available to consumers, and modern computer vision algorithms for generic object recognition are now coping with the richness and complexity of natural visual scenes. Unlike early vision models of object recognition that emphasized the role of figure-ground segmentation and spatial information between parts, recent successful approaches are based on the computation of loose collections of image features without prior segmentation or any explicit encoding of spatial relations. While these models remain simplistic models of visual processing, they suggest that, in principle, bottom-up activation of a loose collection of image features could support the rapid recognition of natural object categories and provide an initial coarse visual representation before more complex visual routines and attentional mechanisms take place. Focusing on biologically-plausible computational models of (bottom-up pre-attentive visual recognition, we review some of the key visual features that have been described in the literature. We discuss the consistency of these feature-based representations with classical theories from visual psychology and test their ability to account for human performance on a rapid object categorization task.

  16. Object Recognition System in Remote Controlled Weapon Station using SIFT and SURF Methods

    Directory of Open Access Journals (Sweden)

    Midriem Mirdanies

    2013-12-01

    Full Text Available Object recognition system using computer vision that is implemented on Remote Controlled Weapon Station (RCWS is discussed. This system will make it easier to identify and shoot targeted object automatically. Algorithm was created to recognize real time multiple objects using two methods i.e. Scale Invariant Feature Transform (SIFT and Speeded Up Robust Features (SURF combined with K-Nearest Neighbors (KNN and Random Sample Consensus (RANSAC for verification. The algorithm is designed to improve object detection to be more robust and to minimize the processing time required. Objects are registered on the system consisting of the armored personnel carrier, tanks, bus, sedan, big foot, and police jeep. In addition, object selection can use mouse to shoot another object that has not been registered on the system. Kinect™ is used to capture RGB images and to find the coordinates x, y, and z of the object. The programming language used is C with visual studio IDE 2010 and opencv libraries. Object recognition program is divided into three parts: 1 reading image from kinect™ and simulation results, 2 object recognition process, and 3 transfer of the object data to the ballistic computer. Communication between programs is performed using shared memory. The detected object data is sent to the ballistic computer via Local Area Network (LAN using winsock for ballistic calculation, and then the motor control system moves the direction of the weapon model to the desired object. The experimental results show that the SIFT method is more suitable because more accurate and faster than SURF with the average processing time to detect one object is 430.2 ms, two object is 618.4 ms, three objects is 682.4 ms, and four objects is 756.2 ms. Object recognition program is able to recognize multi-objects and the data of the identified object can be processed by the ballistic computer in realtime.

  17. Modular Adaptive System Based on a Multi-Stage Neural Structure for Recognition of 2D Objects of Discontinuous Production

    Directory of Open Access Journals (Sweden)

    I. Topalova

    2005-03-01

    Full Text Available This is a presentation of a new system for invariant recognition of 2D objects with overlapping classes, that can not be effectively recognized with the traditional methods. The translation, scale and partial rotation invariant contour object description is transformed in a DCT spectrum space. The obtained frequency spectrums are decomposed into frequency bands in order to feed different BPG neural nets (NNs. The NNs are structured in three stages - filtering and full rotation invariance; partial recognition; general classification. The designed multi-stage BPG Neural Structure shows very good accuracy and flexibility when tested with 2D objects used in the discontinuous production. The reached speed and the opportunuty for an easy restructuring and reprogramming of the system makes it suitable for application in different applied systems for real time work.

  18. Modular Adaptive System Based on a Multi-Stage Neural Structure for Recognition of 2D Objects of Discontinuous Production

    Directory of Open Access Journals (Sweden)

    I. Topalova

    2008-11-01

    Full Text Available This is a presentation of a new system for invariant recognition of 2D objects with overlapping classes, that can not be effectively recognized with the traditional methods. The translation, scale and partial rotation invariant contour object description is transformed in a DCT spectrum space. The obtained frequency spectrums are decomposed into frequency bands in order to feed different BPG neural nets (NNs. The NNs are structured in three stages - filtering and full rotation invariance; partial recognition; general classification. The designed multi-stage BPG Neural Structure shows very good accuracy and flexibility when tested with 2D objects used in the discontinuous production. The reached speed and the opportunuty for an easy restructuring and reprogramming of the system makes it suitable for application in different applied systems for real time work.

  19. Effects of Acute Administration of Urtica dioica on the Novel Object-Recognition Task in Mice

    Directory of Open Access Journals (Sweden)

    Hashemi-Firouzi

    2015-08-01

    Full Text Available Background Urtica dioica (nettle has a variety of uses in traditional medicine for the treatment of certain urogenital problems, gastrointestinal disorders, and diabetes. Objectives Recent studies have implicated the effect of U. dioica on brain functions such as pain and memory. However, there is no direct evidence of the acute effects of this plant on cognition. The aim of the present study was to evaluate the effect of U. dioica aqueous extract on the novel object-recognition task (NOR in mice. Materials and Methods First, U. dioica aqueous extract was prepared, then adult male mice were randomly divided into four experimental groups. During the training session, the mice were placed in a box and given 5 minutes to explore two identical objects. The next day, they were again placed in the box and allowed to explore one familiar and one novel object. They received intraperitoneal injections of saline or U. dioica aqueous extract (100 mg/kg before or immediately after the training session or before the test session of the NOR task. Results The results showed that there was a preference for the novel object compared to the familiar one in each of the experimental groups. The object-recognition discrimination index in the group of mice that received U. dioica before training was significantly less than in the other experimental groups. There was no significant difference in the discrimination index between the other groups. U. dioica did not decrease the time spent exploring familiar and unfamiliar objects, or the total time spent exploring both objects. Conclusions Acute administration of U. dioica impairs the object-recognition task if it is used only before the training session. This may be due to its modulation on the acquisition processing of object-recognition. U. dioica has no significant effects on the consolidation or retrieval processing stages of the NOR task. These results emphasize the unfavorable effect on cognitive function of pre

  20. Representations and Techniques for 3D Object Recognition and Scene Interpretation

    CERN Document Server

    Hoiem, Derek

    2011-01-01

    One of the grand challenges of artificial intelligence is to enable computers to interpret 3D scenes and objects from imagery. This book organizes and introduces major concepts in 3D scene and object representation and inference from still images, with a focus on recent efforts to fuse models of geometry and perspective with statistical machine learning. The book is organized into three sections: (1) Interpretation of Physical Space; (2) Recognition of 3D Objects; and (3) Integrated 3D Scene Interpretation. The first discusses representations of spatial layout and techniques to interpret physi

  1. Object and event recognition for stroke rehabilitation

    Science.gov (United States)

    Ghali, Ahmed; Cunningham, Andrew S.; Pridmore, Tony P.

    2003-06-01

    Stroke is a major cause of disability and health care expenditure around the world. Existing stroke rehabilitation methods can be effective but are costly and need to be improved. Even modest improvements in the effectiveness of rehabilitation techniques could produce large benefits in terms of quality of life. The work reported here is part of an ongoing effort to integrate virtual reality and machine vision technologies to produce innovative stroke rehabilitation methods. We describe a combined object recognition and event detection system that provides real time feedback to stroke patients performing everyday kitchen tasks necessary for independent living, e.g. making a cup of coffee. The image plane position of each object, including the patient"s hand, is monitored using histogram-based recognition methods. The relative positions of hand and objects are then reported to a task monitor that compares the patient"s actions against a model of the target task. A prototype system has been constructed and is currently undergoing technical and clinical evaluation.

  2. The role of nitric oxide in the object recognition memory.

    Science.gov (United States)

    Pitsikas, Nikolaos

    2015-05-15

    The novel object recognition task (NORT) assesses recognition memory in animals. It is a non-rewarded paradigm that it is based on spontaneous exploratory behavior in rodents. This procedure is widely used for testing the effects of compounds on recognition memory. Recognition memory is a type of memory severely compromised in schizophrenic and Alzheimer's disease patients. Nitric oxide (NO) is sought to be an intra- and inter-cellular messenger in the central nervous system and its implication in learning and memory is well documented. Here I intended to critically review the role of NO-related compounds on different aspects of recognition memory. Current analysis shows that both NO donors and NO synthase (NOS) inhibitors are involved in object recognition memory and suggests that NO might be a promising target for cognition impairments. However, the potential neurotoxicity of NO would add a note of caution in this context. Copyright © 2014 Elsevier B.V. All rights reserved.

  3. Single prolonged stress impairs social and object novelty recognition in rats.

    Science.gov (United States)

    Eagle, Andrew L; Fitzpatrick, Chris J; Perrine, Shane A

    2013-11-01

    Posttraumatic stress disorder (PTSD) results from exposure to a traumatic event and manifests as re-experiencing, arousal, avoidance, and negative cognition/mood symptoms. Avoidant symptoms, as well as the newly defined negative cognitions/mood, are a serious complication leading to diminished interest in once important or positive activities, such as social interaction; however, the basis of these symptoms remains poorly understood. PTSD patients also exhibit impaired object and social recognition, which may underlie the avoidance and symptoms of negative cognition, such as social estrangement or diminished interest in activities. Previous studies have demonstrated that single prolonged stress (SPS), models PTSD phenotypes, including impairments in learning and memory. Therefore, it was hypothesized that SPS would impair social and object recognition memory. Male Sprague Dawley rats were exposed to SPS then tested in the social choice test (SCT) or novel object recognition test (NOR). These tests measure recognition of novelty over familiarity, a natural preference of rodents. Results show that SPS impaired preference for both social and object novelty. In addition, SPS impairment in social recognition may be caused by impaired behavioral flexibility, or an inability to shift behavior during the SCT. These results demonstrate that traumatic stress can impair social and object recognition memory, which may underlie certain avoidant symptoms or negative cognition in PTSD and be related to impaired behavioral flexibility. Copyright © 2013 Elsevier B.V. All rights reserved.

  4. Electrophysiological evidence for effects of color knowledge in object recognition.

    Science.gov (United States)

    Lu, Aitao; Xu, Guiping; Jin, Hua; Mo, Lei; Zhang, Jijia; Zhang, John X

    2010-01-29

    Knowledge about the typical colors associated with familiar everyday objects (i.e., strawberries are red) is well-known to be represented in the conceptual semantic system. Evidence that such knowledge may also play a role in early perceptual processes for object recognition is scant. In the present ERP study, participants viewed a list of object pictures and detected infrequent stimulus repetitions. Results show that shortly after stimulus onset, ERP components indexing early perceptual processes, including N1, P2, and N2, differentiated between objects in their appropriate or congruent color from these objects in an inappropriate or incongruent color. Such congruence effect also occurred in N3 associated with semantic processing of pictures but not in N4 for domain-general semantic processing. Our results demonstrate a clear effect of color knowledge in early object recognition stages and support the following proposal-color as a surface property is stored in a multiple-memory system where pre-semantic perceptual and semantic conceptual representations interact during object recognition. (c) 2009 Elsevier Ireland Ltd. All rights reserved.

  5. First-Class Object Sets

    DEFF Research Database (Denmark)

    Ernst, Erik

    2009-01-01

    Typically, an object is a monolithic entity with a fixed interface.  To increase flexibility in this area, this paper presents first-class object sets as a language construct.  An object set offers an interface which is a disjoint union of the interfaces of its member objects.  It may also be use...... to a mainstream virtual machine in order to improve on the support for family polymorphism.  The approach is made precise by means of a small calculus, and the soundness of its type system has been shown by a mechanically checked proof in Coq....

  6. Recurrent Convolutional Neural Networks: A Better Model of Biological Object Recognition.

    Science.gov (United States)

    Spoerer, Courtney J; McClure, Patrick; Kriegeskorte, Nikolaus

    2017-01-01

    Feedforward neural networks provide the dominant model of how the brain performs visual object recognition. However, these networks lack the lateral and feedback connections, and the resulting recurrent neuronal dynamics, of the ventral visual pathway in the human and non-human primate brain. Here we investigate recurrent convolutional neural networks with bottom-up (B), lateral (L), and top-down (T) connections. Combining these types of connections yields four architectures (B, BT, BL, and BLT), which we systematically test and compare. We hypothesized that recurrent dynamics might improve recognition performance in the challenging scenario of partial occlusion. We introduce two novel occluded object recognition tasks to test the efficacy of the models, digit clutter (where multiple target digits occlude one another) and digit debris (where target digits are occluded by digit fragments). We find that recurrent neural networks outperform feedforward control models (approximately matched in parametric complexity) at recognizing objects, both in the absence of occlusion and in all occlusion conditions. Recurrent networks were also found to be more robust to the inclusion of additive Gaussian noise. Recurrent neural networks are better in two respects: (1) they are more neurobiologically realistic than their feedforward counterparts; (2) they are better in terms of their ability to recognize objects, especially under challenging conditions. This work shows that computer vision can benefit from using recurrent convolutional architectures and suggests that the ubiquitous recurrent connections in biological brains are essential for task performance.

  7. Improving package structure of object-oriented software using multi-objective optimization and weighted class connections

    Directory of Open Access Journals (Sweden)

    Amarjeet

    2017-07-01

    Full Text Available The software maintenance activities performed without following the original design decisions about the package structure usually deteriorate the quality of software modularization, leading to decay of the quality of the system. One of the main reasons for such structural deterioration is inappropriate grouping of source code classes in software packages. To improve such grouping/modular-structure, previous researchers formulated the software remodularization problem as an optimization problem and solved it using search-based meta-heuristic techniques. These optimization approaches aimed at improving the quality metrics values of the structure without considering the original package design decisions, often resulting into a totally new software modularization. The entirely changed software modularization becomes costly to realize as well as difficult to understand for the developers/maintainers. To alleviate this issue, we propose a multi-objective optimization approach to improve the modularization quality of an object-oriented system with minimum possible movement of classes between existing packages of original software modularization. The optimization is performed using NSGA-II, a widely-accepted multi-objective evolutionary algorithm. In order to ensure minimum modification of original package structure, a new approach of computing class relations using weighted strengths has been proposed here. The weights of relations among different classes are computed on the basis of the original package structure. A new objective function has been formulated using these weighted class relations. This objective function drives the optimization process toward better modularization quality simultaneously ensuring preservation of original structure. To evaluate the results of the proposed approach, a series of experiments are conducted over four real-worlds and two random software applications. The experimental results clearly indicate the effectiveness

  8. Deformation-specific and deformation-invariant visual object recognition: pose vs identity recognition of people and deforming objects

    Directory of Open Access Journals (Sweden)

    Tristan J Webb

    2014-04-01

    Full Text Available When we see a human sitting down, standing up, or walking, we can recognise one of these poses independently of the individual, or we can recognise the individual person, independently of the pose. The same issues arise for deforming objects. For example, if we see a flag deformed by the wind, either blowing out or hanging languidly, we can usually recognise the flag, independently of its deformation; or we can recognise the deformation independently of the identity of the flag. We hypothesize that these types of recognition can be implemented by the primate visual system using temporo-spatial continuity as objects transform as a learning principle. In particular, we hypothesize that pose or deformation can be learned under conditions in which large numbers of different people are successively seen in the same pose, or objects in the same deformation. We also hypothesize that person-specific representations that are independent of pose, and object-specific representations that are independent of deformation and view, could be built, when individual people or objects are observed successively transforming from one pose or deformation and view to another. These hypotheses were tested in a simulation of the ventral visual system, VisNet, that uses temporal continuity, implemented in a synaptic learning rule with a short-term memory trace of previous neuronal activity, to learn invariant representations. It was found that depending on the statistics of the visual input, either pose-specific or deformation-specific representations could be built that were invariant with respect to individual and view; or that identity-specific representations could be built that were invariant with respect to pose or deformation and view. We propose that this is how pose-specific and pose-invariant, and deformation-specific and deformation-invariant, perceptual representations are built in the brain.

  9. Learning Low-Rank Class-Specific Dictionary and Sparse Intra-Class Variant Dictionary for Face Recognition

    Science.gov (United States)

    Tang, Xin; Feng, Guo-can; Li, Xiao-xin; Cai, Jia-xin

    2015-01-01

    Face recognition is challenging especially when the images from different persons are similar to each other due to variations in illumination, expression, and occlusion. If we have sufficient training images of each person which can span the facial variations of that person under testing conditions, sparse representation based classification (SRC) achieves very promising results. However, in many applications, face recognition often encounters the small sample size problem arising from the small number of available training images for each person. In this paper, we present a novel face recognition framework by utilizing low-rank and sparse error matrix decomposition, and sparse coding techniques (LRSE+SC). Firstly, the low-rank matrix recovery technique is applied to decompose the face images per class into a low-rank matrix and a sparse error matrix. The low-rank matrix of each individual is a class-specific dictionary and it captures the discriminative feature of this individual. The sparse error matrix represents the intra-class variations, such as illumination, expression changes. Secondly, we combine the low-rank part (representative basis) of each person into a supervised dictionary and integrate all the sparse error matrix of each individual into a within-individual variant dictionary which can be applied to represent the possible variations between the testing and training images. Then these two dictionaries are used to code the query image. The within-individual variant dictionary can be shared by all the subjects and only contribute to explain the lighting conditions, expressions, and occlusions of the query image rather than discrimination. At last, a reconstruction-based scheme is adopted for face recognition. Since the within-individual dictionary is introduced, LRSE+SC can handle the problem of the corrupted training data and the situation that not all subjects have enough samples for training. Experimental results show that our method achieves the

  10. Learning Low-Rank Class-Specific Dictionary and Sparse Intra-Class Variant Dictionary for Face Recognition.

    Science.gov (United States)

    Tang, Xin; Feng, Guo-Can; Li, Xiao-Xin; Cai, Jia-Xin

    2015-01-01

    Face recognition is challenging especially when the images from different persons are similar to each other due to variations in illumination, expression, and occlusion. If we have sufficient training images of each person which can span the facial variations of that person under testing conditions, sparse representation based classification (SRC) achieves very promising results. However, in many applications, face recognition often encounters the small sample size problem arising from the small number of available training images for each person. In this paper, we present a novel face recognition framework by utilizing low-rank and sparse error matrix decomposition, and sparse coding techniques (LRSE+SC). Firstly, the low-rank matrix recovery technique is applied to decompose the face images per class into a low-rank matrix and a sparse error matrix. The low-rank matrix of each individual is a class-specific dictionary and it captures the discriminative feature of this individual. The sparse error matrix represents the intra-class variations, such as illumination, expression changes. Secondly, we combine the low-rank part (representative basis) of each person into a supervised dictionary and integrate all the sparse error matrix of each individual into a within-individual variant dictionary which can be applied to represent the possible variations between the testing and training images. Then these two dictionaries are used to code the query image. The within-individual variant dictionary can be shared by all the subjects and only contribute to explain the lighting conditions, expressions, and occlusions of the query image rather than discrimination. At last, a reconstruction-based scheme is adopted for face recognition. Since the within-individual dictionary is introduced, LRSE+SC can handle the problem of the corrupted training data and the situation that not all subjects have enough samples for training. Experimental results show that our method achieves the

  11. Learning Low-Rank Class-Specific Dictionary and Sparse Intra-Class Variant Dictionary for Face Recognition.

    Directory of Open Access Journals (Sweden)

    Xin Tang

    Full Text Available Face recognition is challenging especially when the images from different persons are similar to each other due to variations in illumination, expression, and occlusion. If we have sufficient training images of each person which can span the facial variations of that person under testing conditions, sparse representation based classification (SRC achieves very promising results. However, in many applications, face recognition often encounters the small sample size problem arising from the small number of available training images for each person. In this paper, we present a novel face recognition framework by utilizing low-rank and sparse error matrix decomposition, and sparse coding techniques (LRSE+SC. Firstly, the low-rank matrix recovery technique is applied to decompose the face images per class into a low-rank matrix and a sparse error matrix. The low-rank matrix of each individual is a class-specific dictionary and it captures the discriminative feature of this individual. The sparse error matrix represents the intra-class variations, such as illumination, expression changes. Secondly, we combine the low-rank part (representative basis of each person into a supervised dictionary and integrate all the sparse error matrix of each individual into a within-individual variant dictionary which can be applied to represent the possible variations between the testing and training images. Then these two dictionaries are used to code the query image. The within-individual variant dictionary can be shared by all the subjects and only contribute to explain the lighting conditions, expressions, and occlusions of the query image rather than discrimination. At last, a reconstruction-based scheme is adopted for face recognition. Since the within-individual dictionary is introduced, LRSE+SC can handle the problem of the corrupted training data and the situation that not all subjects have enough samples for training. Experimental results show that our

  12. A method of neighbor classes based SVM classification for optical printed Chinese character recognition.

    Science.gov (United States)

    Zhang, Jie; Wu, Xiaohong; Yu, Yanmei; Luo, Daisheng

    2013-01-01

    In optical printed Chinese character recognition (OPCCR), many classifiers have been proposed for the recognition. Among the classifiers, support vector machine (SVM) might be the best classifier. However, SVM is a classifier for two classes. When it is used for multi-classes in OPCCR, its computation is time-consuming. Thus, we propose a neighbor classes based SVM (NC-SVM) to reduce the computation consumption of SVM. Experiments of NC-SVM classification for OPCCR have been done. The results of the experiments have shown that the NC-SVM we proposed can effectively reduce the computation time in OPCCR.

  13. Virtual classes: a powerful mechanism in object-oriented programming

    DEFF Research Database (Denmark)

    Madsen, Ole Lehrmann; Møller-Pedersen, Birger

    1989-01-01

    The notions of class, subclass and virtual procedure are fairly well understood and recognized as some of the key concepts in object-oriented programming. The possibility of modifying a virtual procedure in a subclass is a powerful technique for specializing the general properties of the superclass....... In most object-oriented languages, the attributes of an object may be references to objects and (virtual) procedures. In Simula and BETA it is also possible to have class attributes. The power of class attributes has not yet been widely recognized. In BETA a class may also have virtual class attributes...

  14. Category-specificity in visual object recognition

    DEFF Research Database (Denmark)

    Gerlach, Christian

    2009-01-01

    Are all categories of objects recognized in the same manner visually? Evidence from neuropsychology suggests they are not: some brain damaged patients are more impaired in recognizing natural objects than artefacts whereas others show the opposite impairment. Category-effects have also been...... demonstrated in neurologically intact subjects, but the findings are contradictory and there is no agreement as to why category-effects arise. This article presents a Pre-semantic Account of Category Effects (PACE) in visual object recognition. PACE assumes two processing stages: shape configuration (the...... binding of shape elements into elaborate shape descriptions) and selection (among competing representations in visual long-term memory), which are held to be differentially affected by the structural similarity between objects. Drawing on evidence from clinical studies, experimental studies...

  15. Experimental acquisition of long-range portraits of objects and their recognition

    International Nuclear Information System (INIS)

    Buryi, E V; Kosykh, A E

    1998-01-01

    An experimental investigation was made of recognition of the perspectives of model objects on the basis of the shape of the envelope of a scattered laser pulse. Stable recognition of various perspectives of an object was found to be possible even for high ratios of the probe pulse duration to the time of its propagation along the object surface. (laser applications and other topics in quantum electronics)

  16. Superior voice recognition in a patient with acquired prosopagnosia and object agnosia.

    Science.gov (United States)

    Hoover, Adria E N; Démonet, Jean-François; Steeves, Jennifer K E

    2010-11-01

    Anecdotally, it has been reported that individuals with acquired prosopagnosia compensate for their inability to recognize faces by using other person identity cues such as hair, gait or the voice. Are they therefore superior at the use of non-face cues, specifically voices, to person identity? Here, we empirically measure person and object identity recognition in a patient with acquired prosopagnosia and object agnosia. We quantify person identity (face and voice) and object identity (car and horn) recognition for visual, auditory, and bimodal (visual and auditory) stimuli. The patient is unable to recognize faces or cars, consistent with his prosopagnosia and object agnosia, respectively. He is perfectly able to recognize people's voices and car horns and bimodal stimuli. These data show a reverse shift in the typical weighting of visual over auditory information for audiovisual stimuli in a compromised visual recognition system. Moreover, the patient shows selectively superior voice recognition compared to the controls revealing that two different stimulus domains, persons and objects, may not be equally affected by sensory adaptation effects. This also implies that person and object identity recognition are processed in separate pathways. These data demonstrate that an individual with acquired prosopagnosia and object agnosia can compensate for the visual impairment and become quite skilled at using spared aspects of sensory processing. In the case of acquired prosopagnosia it is advantageous to develop a superior use of voices for person identity recognition in everyday life. Copyright © 2010 Elsevier Ltd. All rights reserved.

  17. Sub-OBB based object recognition and localization algorithm using range images

    International Nuclear Information System (INIS)

    Hoang, Dinh-Cuong; Chen, Liang-Chia; Nguyen, Thanh-Hung

    2017-01-01

    This paper presents a novel approach to recognize and estimate pose of the 3D objects in cluttered range images. The key technical breakthrough of the developed approach can enable robust object recognition and localization under undesirable condition such as environmental illumination variation as well as optical occlusion to viewing the object partially. First, the acquired point clouds are segmented into individual object point clouds based on the developed 3D object segmentation for randomly stacked objects. Second, an efficient shape-matching algorithm called Sub-OBB based object recognition by using the proposed oriented bounding box (OBB) regional area-based descriptor is performed to reliably recognize the object. Then, the 3D position and orientation of the object can be roughly estimated by aligning the OBB of segmented object point cloud with OBB of matched point cloud in a database generated from CAD model and 3D virtual camera. To detect accurate pose of the object, the iterative closest point (ICP) algorithm is used to match the object model with the segmented point clouds. From the feasibility test of several scenarios, the developed approach is verified to be feasible for object pose recognition and localization. (paper)

  18. On the relation between face and object recognition in developmental prosopagnosia

    DEFF Research Database (Denmark)

    Gerlach, Christian; Klargaard, Solja; Starrfelt, Randi

    2016-01-01

    There is an ongoing debate about whether face recognition and object recognition constitute separate cognitive domains. Clarification of this issue can have important theoretical consequences as face recognition is often used as a prime example of domain-specificity in mind and brain. An importan...

  19. Central administration of angiotensin IV rapidly enhances novel object recognition among mice.

    Science.gov (United States)

    Paris, Jason J; Eans, Shainnel O; Mizrachi, Elisa; Reilley, Kate J; Ganno, Michelle L; McLaughlin, Jay P

    2013-07-01

    Angiotensin IV (Val(1)-Tyr(2)-Ile(3)-His(4)-Pro(5)-Phe(6)) has demonstrated potential cognitive-enhancing effects. The present investigation assessed and characterized: (1) dose-dependency of angiotensin IV's cognitive enhancement in a C57BL/6J mouse model of novel object recognition, (2) the time-course for these effects, (3) the identity of residues in the hexapeptide important to these effects and (4) the necessity of actions at angiotensin IV receptors for procognitive activity. Assessment of C57BL/6J mice in a novel object recognition task demonstrated that prior administration of angiotensin IV (0.1, 1.0, or 10.0, but not 0.01 nmol, i.c.v.) significantly enhanced novel object recognition in a dose-dependent manner. These effects were time dependent, with improved novel object recognition observed when angiotensin IV (0.1 nmol, i.c.v.) was administered 10 or 20, but not 30 min prior to the onset of the novel object recognition testing. An alanine scan of the angiotensin IV peptide revealed that replacement of the Val(1), Ile(3), His(4), or Phe(6) residues with Ala attenuated peptide-induced improvements in novel object recognition, whereas Tyr(2) or Pro(5) replacement did not significantly affect performance. Administration of the angiotensin IV receptor antagonist, divalinal-Ang IV (20 nmol, i.c.v.), reduced (but did not abolish) novel object recognition; however, this antagonist completely blocked the procognitive effects of angiotensin IV (0.1 nmol, i.c.v.) in this task. Rotorod testing demonstrated no locomotor effects with any angiotensin IV or divalinal-Ang IV dose tested. These data demonstrate that angiotensin IV produces a rapid enhancement of associative learning and memory performance in a mouse model that was dependent on the angiotensin IV receptor. Copyright © 2013 Elsevier Ltd. All rights reserved.

  20. The relationship between protein synthesis and protein degradation in object recognition memory.

    Science.gov (United States)

    Furini, Cristiane R G; Myskiw, Jociane de C; Schmidt, Bianca E; Zinn, Carolina G; Peixoto, Patricia B; Pereira, Luiza D; Izquierdo, Ivan

    2015-11-01

    For decades there has been a consensus that de novo protein synthesis is necessary for long-term memory. A second round of protein synthesis has been described for both extinction and reconsolidation following an unreinforced test session. Recently, it was shown that consolidation and reconsolidation depend not only on protein synthesis but also on protein degradation by the ubiquitin-proteasome system (UPS), a major mechanism responsible for protein turnover. However, the involvement of UPS on consolidation and reconsolidation of object recognition memory remains unknown. Here we investigate in the CA1 region of the dorsal hippocampus the involvement of UPS-mediated protein degradation in consolidation and reconsolidation of object recognition memory. Animals with infusion cannulae stereotaxically implanted in the CA1 region of the dorsal hippocampus, were exposed to an object recognition task. The UPS inhibitor β-Lactacystin did not affect the consolidation and the reconsolidation of object recognition memory at doses known to affect other forms of memory (inhibitory avoidance, spatial learning in a water maze) while the protein synthesis inhibitor anisomycin impaired the consolidation and the reconsolidation of the object recognition memory. However, β-Lactacystin was able to reverse the impairment caused by anisomycin on the reconsolidation process in the CA1 region of the hippocampus. Therefore, it is possible to postulate a direct link between protein degradation and protein synthesis during the reconsolidation of the object recognition memory. Copyright © 2015 Elsevier B.V. All rights reserved.

  1. The Functional Architecture of Visual Object Recognition

    Science.gov (United States)

    1991-07-01

    different forms of agnosia can provide clues to the representations underlying normal object recognition (Farah, 1990). For example, the pair-wise...patterns of deficit and sparing occur. In a review of 99 published cases of agnosia , the observed patterns of co- occurrence implicated two underlying

  2. Neurocomputational bases of object and face recognition.

    OpenAIRE

    Biederman, I; Kalocsai, P

    1997-01-01

    A number of behavioural phenomena distinguish the recognition of faces and objects, even when members of a set of objects are highly similar. Because faces have the same parts in approximately the same relations, individuation of faces typically requires specification of the metric variation in a holistic and integral representation of the facial surface. The direct mapping of a hypercolumn-like pattern of activation onto a representation layer that preserves relative spatial filter values in...

  3. Motor cortical processing is causally involved in object recognition.

    Science.gov (United States)

    Decloe, Rebecca; Obhi, Sukhvinder S

    2013-12-14

    Motor activity during vicarious experience of actions is a widely reported and studied phenomenon, and motor system activity also accompanies observation of graspable objects in the absence of any actions. Such motor activity is thought to reflect simulation of the observed action, or preparation to interact with the object, respectively. Here, in an initial exploratory study, we ask whether motor activity during observation of object directed actions is involved in processes related to recognition of the object after initial exposure. Single pulse Transcranial Magnetic Stimulation (TMS) was applied over the thumb representation of the motor cortex, or over the vertex, during observation of a model thumb typing on a cell-phone, and performance on a phone recognition task at the end of the trial was assessed. Disrupting motor processing over the thumb representation 100 ms after the onset of the typing video impaired the ability to recognize the phone in the recognition test, whereas there was no such effect for TMS applied over the vertex and no TMS trials. Furthermore, this effect only manifested for videos observed from the first person perspective. In an additional control condition, there was no evidence for any effects of TMS to the thumb representation or vertex when observing and recognizing non-action related shape stimuli. Overall, these data provide evidence that motor cortical processing during observation of object-directed actions from a first person perspective is causally linked to the formation of enduring representations of objects-of-action.

  4. Properties of mathematical objects (Goedel on classes, properties and concepts)

    International Nuclear Information System (INIS)

    Materna, Pavel

    2007-01-01

    In terms of a sufficiently fine-grained theory we should distinguish between classes, properties and concepts. Since properties are best modeled as a kind of non-trivial intensions while mathematical objects are never non-trivial intensions we should not speak about properties of mathematical objects. When we do use the term property in mathematics (as Goedel did) we either mean classes, or the more fine-grained entities to be called concepts. In the latter case concepts have to be defined so that various distinct concepts could identify one and the same object. The notion of construction in transparent intensional logic makes it possible to construe concepts as abstract procedures. At the same time we have to distinguish between this notion and the notion of construction in constructivist systems: the former - unlike the latter - are objective and, therefore, acceptable for a realist

  5. Spontaneous object recognition: a promising approach to the comparative study of memory

    Directory of Open Access Journals (Sweden)

    Rachel eBlaser

    2015-07-01

    Full Text Available Spontaneous recognition of a novel object is a popular measure of exploratory behavior, perception and recognition memory in rodent models. Because of its relative simplicity and speed of testing, the variety of stimuli that can be used, and its ecological validity across species, it is also an attractive task for comparative research. To date, variants of this test have been used with vertebrate and invertebrate species, but the methods have seldom been sufficiently standardized to allow cross-species comparison. Here, we review the methods necessary for the study of novel object recognition in mammalian and non-mammalian models, as well as the results of these experiments. Critical to the use of this test is an understanding of the organism’s initial response to a novel object, the modulation of exploration by context, and species differences in object perception and exploratory behaviors. We argue that with appropriate consideration of species differences in perception, object affordances, and natural exploratory behaviors, the spontaneous object recognition test can be a valid and versatile tool for translational research with non-mammalian models.

  6. Object Recognition In HADOOP Using HIPI

    Directory of Open Access Journals (Sweden)

    Ankit Kumar Agrawal

    2015-07-01

    Full Text Available Abstract The amount of images and videos being shared by the user is exponentially increasing but applications that perform video analytics is severely lacking or work on limited set of data. It is also challenging to perform analytics with less time complexity. Object recognition is the primary step in video analytics. We implement a robust method to extract objects from the data which is in unstructured format and cannot be processed directly by relational databases. In this study we present our report with results after performance evaluation and compare them with results of MATLAB.

  7. Improving a Deep Learning based RGB-D Object Recognition Model by Ensemble Learning

    DEFF Research Database (Denmark)

    Aakerberg, Andreas; Nasrollahi, Kamal; Heder, Thomas

    2018-01-01

    Augmenting RGB images with depth information is a well-known method to significantly improve the recognition accuracy of object recognition models. Another method to im- prove the performance of visual recognition models is ensemble learning. However, this method has not been widely explored...... in combination with deep convolutional neural network based RGB-D object recognition models. Hence, in this paper, we form different ensembles of complementary deep convolutional neural network models, and show that this can be used to increase the recognition performance beyond existing limits. Experiments...

  8. Higher-order neural network software for distortion invariant object recognition

    Science.gov (United States)

    Reid, Max B.; Spirkovska, Lilly

    1991-01-01

    The state-of-the-art in pattern recognition for such applications as automatic target recognition and industrial robotic vision relies on digital image processing. We present a higher-order neural network model and software which performs the complete feature extraction-pattern classification paradigm required for automatic pattern recognition. Using a third-order neural network, we demonstrate complete, 100 percent accurate invariance to distortions of scale, position, and in-plate rotation. In a higher-order neural network, feature extraction is built into the network, and does not have to be learned. Only the relatively simple classification step must be learned. This is key to achieving very rapid training. The training set is much smaller than with standard neural network software because the higher-order network only has to be shown one view of each object to be learned, not every possible view. The software and graphical user interface run on any Sun workstation. Results of the use of the neural software in autonomous robotic vision systems are presented. Such a system could have extensive application in robotic manufacturing.

  9. Global precedence effects account for individual differences in both face and object recognition performance

    DEFF Research Database (Denmark)

    Gerlach, Christian; Starrfelt, Randi

    2018-01-01

    examine whether global precedence effects, measured by means of non-face stimuli in Navon's paradigm, can also account for individual differences in face recognition and, if so, whether the effect is of similar magnitude for faces and objects. We find evidence that global precedence effects facilitate...... both face and object recognition, and to a similar extent. Our results suggest that both face and object recognition are characterized by a coarse-to-fine temporal dynamic, where global shape information is derived prior to local shape information, and that the efficiency of face and object recognition...

  10. Implementation of CT and IHT Processors for Invariant Object Recognition System

    Directory of Open Access Journals (Sweden)

    J. Turan jr.

    2004-12-01

    Full Text Available This paper presents PDL or ASIC implementation of key modules ofinvariant object recognition system based on the combination of theIncremental Hough transform (IHT, correlation and rapid transform(RT. The invariant object recognition system was represented partiallyin C++ language for general-purpose processor on personal computer andpartially described in VHDL code for implementation in PLD or ASIC.

  11. Probabilistic object and viewpoint models for active object recognition

    CSIR Research Space (South Africa)

    Govender, N

    2013-09-01

    Full Text Available ,θ′(f occ). V. EXPERIMENTS A. Dataset For our experiments, we use the active recognition dataset introduced by [12]. The training data consists of everyday objects such as cereal boxes, ornaments, spice bottle, etc. Images were captured every 20 degrees... are to be verified TABLE I CONFUSION MATRIX FOR BINARY A MODEL Obscured Obscured Obscured Obscured Obscured Obscured Obscured Obscured Obscured Obscured Cereal Battery Curry box Elephant Handbag MrMin Salad Bottle Spice Bottle Spray Can Spray Can 1 Cereal 0.9800 0...

  12. Post-Training Reversible Inactivation of the Hippocampus Enhances Novel Object Recognition Memory

    Science.gov (United States)

    Oliveira, Ana M. M.; Hawk, Joshua D.; Abel, Ted; Havekes, Robbert

    2010-01-01

    Research on the role of the hippocampus in object recognition memory has produced conflicting results. Previous studies have used permanent hippocampal lesions to assess the requirement for the hippocampus in the object recognition task. However, permanent hippocampal lesions may impact performance through effects on processes besides memory…

  13. Motor cortical processing is causally involved in object recognition

    Science.gov (United States)

    2013-01-01

    Background Motor activity during vicarious experience of actions is a widely reported and studied phenomenon, and motor system activity also accompanies observation of graspable objects in the absence of any actions. Such motor activity is thought to reflect simulation of the observed action, or preparation to interact with the object, respectively. Results Here, in an initial exploratory study, we ask whether motor activity during observation of object directed actions is involved in processes related to recognition of the object after initial exposure. Single pulse Transcranial Magnetic Stimulation (TMS) was applied over the thumb representation of the motor cortex, or over the vertex, during observation of a model thumb typing on a cell-phone, and performance on a phone recognition task at the end of the trial was assessed. Disrupting motor processing over the thumb representation 100 ms after the onset of the typing video impaired the ability to recognize the phone in the recognition test, whereas there was no such effect for TMS applied over the vertex and no TMS trials. Furthermore, this effect only manifested for videos observed from the first person perspective. In an additional control condition, there was no evidence for any effects of TMS to the thumb representation or vertex when observing and recognizing non-action related shape stimuli. Conclusion Overall, these data provide evidence that motor cortical processing during observation of object-directed actions from a first person perspective is causally linked to the formation of enduring representations of objects-of-action. PMID:24330638

  14. Figure-ground organization and object recognition processes: an interactive account.

    Science.gov (United States)

    Vecera, S P; O'Reilly, R C

    1998-04-01

    Traditional bottom-up models of visual processing assume that figure-ground organization precedes object recognition. This assumption seems logically necessary: How can object recognition occur before a region is labeled as figure? However, some behavioral studies find that familiar regions are more likely to be labeled figure than less familiar regions, a problematic finding for bottom-up models. An interactive account is proposed in which figure-ground processes receive top-down input from object representations in a hierarchical system. A graded, interactive computational model is presented that accounts for behavioral results in which familiarity effects are found. The interactive model offers an alternative conception of visual processing to bottom-up models.

  15. Short-term blueberry-enriched antioxidant diet prevents and reverses object recognition memory loss in aged rats

    Science.gov (United States)

    Objective Previously, four months of a blueberry-enriched (BB) antioxidant diet prevented impaired object recognition memory in aged rats. Experiment 1 determined whether one and two-month BB diets would have a similar effect and whether the benefits would disappear promptly after terminating the d...

  16. Dopamine D1 receptor stimulation modulates the formation and retrieval of novel object recognition memory: Role of the prelimbic cortex.

    Science.gov (United States)

    Pezze, Marie A; Marshall, Hayley J; Fone, Kevin C F; Cassaday, Helen J

    2015-11-01

    Previous studies have shown that dopamine D1 receptor antagonists impair novel object recognition memory but the effects of dopamine D1 receptor stimulation remain to be determined. This study investigated the effects of the selective dopamine D1 receptor agonist SKF81297 on acquisition and retrieval in the novel object recognition task in male Wistar rats. SKF81297 (0.4 and 0.8 mg/kg s.c.) given 15 min before the sampling phase impaired novel object recognition evaluated 10 min or 24 h later. The same treatments also reduced novel object recognition memory tested 24 h after the sampling phase and when given 15 min before the choice session. These data indicate that D1 receptor stimulation modulates both the encoding and retrieval of object recognition memory. Microinfusion of SKF81297 (0.025 or 0.05 μg/side) into the prelimbic sub-region of the medial prefrontal cortex (mPFC) in this case 10 min before the sampling phase also impaired novel object recognition memory, suggesting that the mPFC is one important site mediating the effects of D1 receptor stimulation on visual recognition memory. Copyright © 2015 The Authors. Published by Elsevier B.V. All rights reserved.

  17. HONTIOR - HIGHER-ORDER NEURAL NETWORK FOR TRANSFORMATION INVARIANT OBJECT RECOGNITION

    Science.gov (United States)

    Spirkovska, L.

    1994-01-01

    Neural networks have been applied in numerous fields, including transformation invariant object recognition, wherein an object is recognized despite changes in the object's position in the input field, size, or rotation. One of the more successful neural network methods used in invariant object recognition is the higher-order neural network (HONN) method. With a HONN, known relationships are exploited and the desired invariances are built directly into the architecture of the network, eliminating the need for the network to learn invariance to transformations. This results in a significant reduction in the training time required, since the network needs to be trained on only one view of each object, not on numerous transformed views. Moreover, one hundred percent accuracy is guaranteed for images characterized by the built-in distortions, providing noise is not introduced through pixelation. The program HONTIOR implements a third-order neural network having invariance to translation, scale, and in-plane rotation built directly into the architecture, Thus, for 2-D transformation invariance, the network needs only to be trained on just one view of each object. HONTIOR can also be used for 3-D transformation invariant object recognition by training the network only on a set of out-of-plane rotated views. Historically, the major drawback of HONNs has been that the size of the input field was limited to the memory required for the large number of interconnections in a fully connected network. HONTIOR solves this problem by coarse coding the input images (coding an image as a set of overlapping but offset coarser images). Using this scheme, large input fields (4096 x 4096 pixels) can easily be represented using very little virtual memory (30Mb). The HONTIOR distribution consists of three main programs. The first program contains the training and testing routines for a third-order neural network. The second program contains the same training and testing procedures as the

  18. Modeling guidance and recognition in categorical search: bridging human and computer object detection.

    Science.gov (United States)

    Zelinsky, Gregory J; Peng, Yifan; Berg, Alexander C; Samaras, Dimitris

    2013-10-08

    Search is commonly described as a repeating cycle of guidance to target-like objects, followed by the recognition of these objects as targets or distractors. Are these indeed separate processes using different visual features? We addressed this question by comparing observer behavior to that of support vector machine (SVM) models trained on guidance and recognition tasks. Observers searched for a categorically defined teddy bear target in four-object arrays. Target-absent trials consisted of random category distractors rated in their visual similarity to teddy bears. Guidance, quantified as first-fixated objects during search, was strongest for targets, followed by target-similar, medium-similarity, and target-dissimilar distractors. False positive errors to first-fixated distractors also decreased with increasing dissimilarity to the target category. To model guidance, nine teddy bear detectors, using features ranging in biological plausibility, were trained on unblurred bears then tested on blurred versions of the same objects appearing in each search display. Guidance estimates were based on target probabilities obtained from these detectors. To model recognition, nine bear/nonbear classifiers, trained and tested on unblurred objects, were used to classify the object that would be fixated first (based on the detector estimates) as a teddy bear or a distractor. Patterns of categorical guidance and recognition accuracy were modeled almost perfectly by an HMAX model in combination with a color histogram feature. We conclude that guidance and recognition in the context of search are not separate processes mediated by different features, and that what the literature knows as guidance is really recognition performed on blurred objects viewed in the visual periphery.

  19. Differential cortical c-Fos and Zif-268 expression after object and spatial memory processing in a standard or episodic-like object recognition task

    Directory of Open Access Journals (Sweden)

    Flávio F Barbosa

    2013-08-01

    Full Text Available Episodic memory reflects the capacity to recollect what, where and when a specific event happened in an integrative manner. Animal studies have suggested that the medial temporal lobe and the medial pre-frontal cortex are important for episodic-like memory formation. The goal of present study was to evaluate whether there are different patterns of expression of the immediate early genes c-Fos and Zif-268 in these cortical areas after rats are exposed to object recognition tasks with different cognitive demands. Male rats were randomly assigned to five groups: home cage control (CTR-HC, empty open field (CTR-OF, open field with one object (CTR-OF + Obj, novel object recognition task (OR and episodic-like memory task (ELM and were killed one hour after the last behavioral procedure. Rats were able to discriminate the objects in the OR task. In the ELM task, rats showed spatial (but not temporal discrimination of the objects. We found an increase in the c-Fos expression in the dorsal dentate gyrus (DG and in the perirhinal cortex (PRh in the OR and ELM groups. The OR group also presented an increase of c-Fos expression in the medial prefrontal cortex (mPFC. Additionally, the OR and ELM groups had increased expression of Zif-268 in the mPFC. Moreover, Zif-268 was increased in the dorsal CA1 and perirhinal cortex only in the ELM group. In conclusion, the pattern of activation was different in tasks with different cognitive demands. Accordingly, correlation tests suggest the engagement of different neural networks in the object recognition tasks used. Specifically, perirhinal-dentate gyrus co-activation was detected after the what-where memory retrieval, but not after the novel object recognition task. Both regions correlated with the respective behavioral outcome. These findings can be helpful in the understanding of the neural networks underlying memory tasks with different cognitive demands.

  20. Development of visuo-haptic transfer for object recognition in typical preschool and school-aged children.

    Science.gov (United States)

    Purpura, Giulia; Cioni, Giovanni; Tinelli, Francesca

    2018-07-01

    Object recognition is a long and complex adaptive process and its full maturation requires combination of many different sensory experiences as well as cognitive abilities to manipulate previous experiences in order to develop new percepts and subsequently to learn from the environment. It is well recognized that the transfer of visual and haptic information facilitates object recognition in adults, but less is known about development of this ability. In this study, we explored the developmental course of object recognition capacity in children using unimodal visual information, unimodal haptic information, and visuo-haptic information transfer in children from 4 years to 10 years and 11 months of age. Participants were tested through a clinical protocol, involving visual exploration of black-and-white photographs of common objects, haptic exploration of real objects, and visuo-haptic transfer of these two types of information. Results show an age-dependent development of object recognition abilities for visual, haptic, and visuo-haptic modalities. A significant effect of time on development of unimodal and crossmodal recognition skills was found. Moreover, our data suggest that multisensory processes for common object recognition are active at 4 years of age. They facilitate recognition of common objects, and, although not fully mature, are significant in adaptive behavior from the first years of age. The study of typical development of visuo-haptic processes in childhood is a starting point for future studies regarding object recognition in impaired populations.

  1. Object Recognition in Clutter: Cortical Responses Depend on the Type of Learning

    Directory of Open Access Journals (Sweden)

    Jay eHegdé

    2012-06-01

    Full Text Available Theoretical studies suggest that the visual system uses prior knowledge of visual objects to recognize them in visual clutter, and posit that the strategies for recognizing objects in clutter may differ depending on whether or not the object was learned in clutter to begin with. We tested this hypothesis using functional magnetic resonance imaging (fMRI of human subjects. We trained subjects to recognize naturalistic, yet novel objects in strong or weak clutter. We then tested subjects’ recognition performance for both sets of objects in strong clutter. We found many brain regions that were differentially responsive to objects during object recognition depending on whether they were learned in strong or weak clutter. In particular, the responses of the left fusiform gyrus reliably reflected, on a trial-to-trial basis, subjects’ object recognition performance for objects learned in the presence of strong clutter. These results indicate that the visual system does not use a single, general-purpose mechanism to cope with clutter. Instead, there are two distinct spatial patterns of activation whose responses are attributable not to the visual context in which the objects were seen, but to the context in which the objects were learned.

  2. Using Markov Chains and Multi-Objective Optimization for Energy-Efficient Context Recognition

    Directory of Open Access Journals (Sweden)

    Vito Janko

    2017-12-01

    Full Text Available The recognition of the user’s context with wearable sensing systems is a common problem in ubiquitous computing. However, the typically small battery of such systems often makes continuous recognition impractical. The strain on the battery can be reduced if the sensor setting is adapted to each context. We propose a method that efficiently finds near-optimal sensor settings for each context. It uses Markov chains to simulate the behavior of the system in different configurations and the multi-objective genetic algorithm to find a set of good non-dominated configurations. The method was evaluated on three real-life datasets and found good trade-offs between the system’s energy expenditure and the system’s accuracy. One of the solutions, for example, consumed five-times less energy than the default one, while sacrificing only two percentage points of accuracy.

  3. Using Markov Chains and Multi-Objective Optimization for Energy-Efficient Context Recognition.

    Science.gov (United States)

    Janko, Vito; Luštrek, Mitja

    2017-12-29

    The recognition of the user's context with wearable sensing systems is a common problem in ubiquitous computing. However, the typically small battery of such systems often makes continuous recognition impractical. The strain on the battery can be reduced if the sensor setting is adapted to each context. We propose a method that efficiently finds near-optimal sensor settings for each context. It uses Markov chains to simulate the behavior of the system in different configurations and the multi-objective genetic algorithm to find a set of good non-dominated configurations. The method was evaluated on three real-life datasets and found good trade-offs between the system's energy expenditure and the system's accuracy. One of the solutions, for example, consumed five-times less energy than the default one, while sacrificing only two percentage points of accuracy.

  4. Probabilistic Open Set Recognition

    Science.gov (United States)

    Jain, Lalit Prithviraj

    Real-world tasks in computer vision, pattern recognition and machine learning often touch upon the open set recognition problem: multi-class recognition with incomplete knowledge of the world and many unknown inputs. An obvious way to approach such problems is to develop a recognition system that thresholds probabilities to reject unknown classes. Traditional rejection techniques are not about the unknown; they are about the uncertain boundary and rejection around that boundary. Thus traditional techniques only represent the "known unknowns". However, a proper open set recognition algorithm is needed to reduce the risk from the "unknown unknowns". This dissertation examines this concept and finds existing probabilistic multi-class recognition approaches are ineffective for true open set recognition. We hypothesize the cause is due to weak adhoc assumptions combined with closed-world assumptions made by existing calibration techniques. Intuitively, if we could accurately model just the positive data for any known class without overfitting, we could reject the large set of unknown classes even under this assumption of incomplete class knowledge. For this, we formulate the problem as one of modeling positive training data by invoking statistical extreme value theory (EVT) near the decision boundary of positive data with respect to negative data. We provide a new algorithm called the PI-SVM for estimating the unnormalized posterior probability of class inclusion. This dissertation also introduces a new open set recognition model called Compact Abating Probability (CAP), where the probability of class membership decreases in value (abates) as points move from known data toward open space. We show that CAP models improve open set recognition for multiple algorithms. Leveraging the CAP formulation, we go on to describe the novel Weibull-calibrated SVM (W-SVM) algorithm, which combines the useful properties of statistical EVT for score calibration with one-class and binary

  5. Visual object recognition and category-specificity

    DEFF Research Database (Denmark)

    Gerlach, Christian

    This thesis is based on seven published papers. The majority of the papers address two topics in visual object recognition: (i) category-effects at pre-semantic stages, and (ii) the integration of visual elements into elaborate shape descriptions corresponding to whole objects or large object parts...... (shape configuration). In the early writings these two topics were examined more or less independently. In later works, findings concerning category-effects and shape configuration merge into an integrated model, termed RACE, advanced to explain category-effects arising at pre-semantic stages in visual...... in visual long-term memory. In the thesis it is described how this simple model can account for a wide range of findings on category-specificity in both patients with brain damage and normal subjects. Finally, two hypotheses regarding the neural substrates of the model's components - and how activation...

  6. An Intelligent Systems Approach to Automated Object Recognition: A Preliminary Study

    Science.gov (United States)

    Maddox, Brian G.; Swadley, Casey L.

    2002-01-01

    Attempts at fully automated object recognition systems have met with varying levels of success over the years. However, none of the systems have achieved high enough accuracy rates to be run unattended. One of the reasons for this may be that they are designed from the computer's point of view and rely mainly on image-processing methods. A better solution to this problem may be to make use of modern advances in computational intelligence and distributed processing to try to mimic how the human brain is thought to recognize objects. As humans combine cognitive processes with detection techniques, such a system would combine traditional image-processing techniques with computer-based intelligence to determine the identity of various objects in a scene.

  7. Industrial robots with sensors and object recognition systems

    International Nuclear Information System (INIS)

    Koehler, G.W.

    1978-01-01

    The previous development and the present status of industrial robots equipped with sensors and object recognition systems are described. This type of equipment allows flexible automation of many work stations in which industrial robots of the first generation, which are unable to react to changes in their respective environments automatically, apart from their being linked to other machines, could not be used because of the prevailing boundary conditions. A classification system facilitates an overview of the large number of technical solutions now available. The manifold possibilities of application of this equipment are demonstrated by a number of examples. As a result of the present state of development of the components required, and in view also of economic reasons, there is a trend towards special designs for a small number of specific purposes and towards stripped-down object recognition. systems with limited applications. A fitting description is offered of the term 'robot', which is now being used in various contexts, and an indication is made of the capabilities and components a machine to be called robot should have as a minimum. Finally, reference is made to some potential lines of development serving to reduce expediture and accelerate recognition processes. (orig.) [de

  8. Evaluating Color Descriptors for Object and Scene Recognition

    NARCIS (Netherlands)

    van de Sande, K.E.A.; Gevers, T.; Snoek, C.G.M.

    2010-01-01

    Image category recognition is important to access visual information on the level of objects and scene types. So far, intensity-based descriptors have been widely used for feature extraction at salient points. To increase illumination invariance and discriminative power, color descriptors have been

  9. Linguistic approach to object recognition by grasping

    Energy Technology Data Exchange (ETDEWEB)

    Marik, V

    1982-01-01

    A method for recognizing both the three-dimensional object shapes and their sizes by grasping them with an antropomorphic five-finger artificial hand is described. The hand is equipped with position sensing elements in the joints of the fingers and with a tactile transducer net on the palm surface. The linguistic method uses formal grammars and languages for the pattern description. The recognition is hierarchically arranged, every level being different from the others by a formal language which has been used. On every level the pattern description is generated and verified from the symmetrical and semantical points of view. The results of the implementation of the recognition of cones, pyramides, spheres, prisms and cylinders are presented and discussed. 8 references.

  10. A biologically inspired neural network model to transformation invariant object recognition

    Science.gov (United States)

    Iftekharuddin, Khan M.; Li, Yaqin; Siddiqui, Faraz

    2007-09-01

    Transformation invariant image recognition has been an active research area due to its widespread applications in a variety of fields such as military operations, robotics, medical practices, geographic scene analysis, and many others. The primary goal for this research is detection of objects in the presence of image transformations such as changes in resolution, rotation, translation, scale and occlusion. We investigate a biologically-inspired neural network (NN) model for such transformation-invariant object recognition. In a classical training-testing setup for NN, the performance is largely dependent on the range of transformation or orientation involved in training. However, an even more serious dilemma is that there may not be enough training data available for successful learning or even no training data at all. To alleviate this problem, a biologically inspired reinforcement learning (RL) approach is proposed. In this paper, the RL approach is explored for object recognition with different types of transformations such as changes in scale, size, resolution and rotation. The RL is implemented in an adaptive critic design (ACD) framework, which approximates the neuro-dynamic programming of an action network and a critic network, respectively. Two ACD algorithms such as Heuristic Dynamic Programming (HDP) and Dual Heuristic dynamic Programming (DHP) are investigated to obtain transformation invariant object recognition. The two learning algorithms are evaluated statistically using simulated transformations in images as well as with a large-scale UMIST face database with pose variations. In the face database authentication case, the 90° out-of-plane rotation of faces from 20 different subjects in the UMIST database is used. Our simulations show promising results for both designs for transformation-invariant object recognition and authentication of faces. Comparing the two algorithms, DHP outperforms HDP in learning capability, as DHP takes fewer steps to

  11. Deletion of the GluA1 AMPA receptor subunit impairs recency-dependent object recognition memory

    Science.gov (United States)

    Sanderson, David J.; Hindley, Emma; Smeaton, Emily; Denny, Nick; Taylor, Amy; Barkus, Chris; Sprengel, Rolf; Seeburg, Peter H.; Bannerman, David M.

    2011-01-01

    Deletion of the GluA1 AMPA receptor subunit impairs short-term spatial recognition memory. It has been suggested that short-term recognition depends upon memory caused by the recent presentation of a stimulus that is independent of contextual–retrieval processes. The aim of the present set of experiments was to test whether the role of GluA1 extends to nonspatial recognition memory. Wild-type and GluA1 knockout mice were tested on the standard object recognition task and a context-independent recognition task that required recency-dependent memory. In a first set of experiments it was found that GluA1 deletion failed to impair performance on either of the object recognition or recency-dependent tasks. However, GluA1 knockout mice displayed increased levels of exploration of the objects in both the sample and test phases compared to controls. In contrast, when the time that GluA1 knockout mice spent exploring the objects was yoked to control mice during the sample phase, it was found that GluA1 deletion now impaired performance on both the object recognition and the recency-dependent tasks. GluA1 deletion failed to impair performance on a context-dependent recognition task regardless of whether object exposure in knockout mice was yoked to controls or not. These results demonstrate that GluA1 is necessary for nonspatial as well as spatial recognition memory and plays an important role in recency-dependent memory processes. PMID:21378100

  12. Global precedence effects account for individual differences in both face and object recognition performance.

    Science.gov (United States)

    Gerlach, Christian; Starrfelt, Randi

    2018-03-20

    There has been an increase in studies adopting an individual difference approach to examine visual cognition and in particular in studies trying to relate face recognition performance with measures of holistic processing (the face composite effect and the part-whole effect). In the present study we examine whether global precedence effects, measured by means of non-face stimuli in Navon's paradigm, can also account for individual differences in face recognition and, if so, whether the effect is of similar magnitude for faces and objects. We find evidence that global precedence effects facilitate both face and object recognition, and to a similar extent. Our results suggest that both face and object recognition are characterized by a coarse-to-fine temporal dynamic, where global shape information is derived prior to local shape information, and that the efficiency of face and object recognition is related to the magnitude of the global precedence effect.

  13. The interplay between perceptual organization and object recognition: Temporal dynamics and neuropsychology

    OpenAIRE

    Torfs, Katrien

    2012-01-01

    The ease and efficiency with which we perceive objects in daily life masks the complexity of the processes involved. The main goal of my doctoral research was to enhance our understanding of the complex interplay between perceptual organization and object recognition. To this end, we investigated the dynamic interplay between different component processes of object recognition, and their temporal dynamics. In the first part of this thesis, I present three behavioral studies focusing on the ro...

  14. Recurrent processing during object recognition

    Directory of Open Access Journals (Sweden)

    Randall C. O'Reilly

    2013-04-01

    Full Text Available How does the brain learn to recognize objects visually, and perform this difficult feat robustly in the face of many sources of ambiguity and variability? We present a computational model based on the biology of the relevant visual pathways that learns to reliably recognize 100 different object categories in the face of of naturally-occurring variability in location, rotation, size, and lighting. The model exhibits robustness to highly ambiguous, partially occluded inputs. Both the unified, biologically plausible learning mechanism and the robustness to occlusion derive from the role that recurrent connectivity and recurrent processing mechanisms play in the model. Furthermore, this interaction of recurrent connectivity and learning predicts that high-level visual representations should be shaped by error signals from nearby, associated brain areas over the course of visual learning. Consistent with this prediction, we show how semantic knowledge about object categories changes the nature of their learned visual representations, as well as how this representational shift supports the mapping between perceptual and conceptual knowledge. Altogether, these findings support the potential importance of ongoing recurrent processing throughout the brain's visual system and suggest ways in which object recognition can be understood in terms of interactions within and between processes over time.

  15. A Large-Scale 3D Object Recognition dataset

    DEFF Research Database (Denmark)

    Sølund, Thomas; Glent Buch, Anders; Krüger, Norbert

    2016-01-01

    geometric groups; concave, convex, cylindrical and flat 3D object models. The object models have varying amount of local geometric features to challenge existing local shape feature descriptors in terms of descriptiveness and robustness. The dataset is validated in a benchmark which evaluates the matching...... performance of 7 different state-of-the-art local shape descriptors. Further, we validate the dataset in a 3D object recognition pipeline. Our benchmark shows as expected that local shape feature descriptors without any global point relation across the surface have a poor matching performance with flat...

  16. Lateral septal vasopressin in rats : Role in social and object recognition?

    NARCIS (Netherlands)

    Everts, H.G J; Koolhaas, J.M.

    1997-01-01

    The capacity of male rats to remember familiar conspecifics is called social recognition. It is a form of short-term memory modulated by lateral septal (LS) vasopressin (VP). The specificity of this phenomenon was studied by examining whether recognition of previously investigated objects is also

  17. Standardization of transportation classes for object-oriented deployment simulations.

    Energy Technology Data Exchange (ETDEWEB)

    Burke, J. F., Jr.; Howard, D. L.; Jackson, J.; Macal, C. M.; Nevins, M. R.; Van Groningen, C. N.

    1999-07-30

    Many recent efforts to integrate transportation and deployment simulations, although beneficial, have lacked a feature vital for seamless integration: a common data class representation. It is an objective of the Department of Defense (DoD) to standardize all classes used in object-oriented deployment simulations by developing a standard class attribute representation and behavior for all deployment simulations that rely on an underlying class representation. The Extensive Hierarchy and Object Representation for Transportation Simulations (EXHORT) is a collection of three hierarchies that together will constitute a standard and consistent class attribute representation and behavior that could be used directly by a large set of deployment simulations. The first hierarchy is the Transportation Class Hierarchy (TCH), which describes a significant portion of the defense transportation system; the other two deal with infrastructure and resource classes. EXHORT will allow deployment simulations to use the same set of underlying class data, ensure transparent exchanges, reduce the effort needed to integrate simulations, and permit a detailed analysis of the defense transportation system. This paper describes EXHORT's first hierarchy, the TCH, and provides a rationale for why it is a helpful tool for modeling major portions of the defense transportation system.

  18. Noradrenergic activation of the basolateral amygdala modulates the consolidation of object-in-context recognition memory

    Directory of Open Access Journals (Sweden)

    Areg eBarsegyan

    2014-05-01

    Full Text Available Noradrenergic activation of the basolateral complex of the amygdala (BLA is well known to enhance the consolidation of long-term memory of highly emotionally arousing training experiences. The present study investigated whether such noradrenergic activation of the BLA also influences the consolidation of object-in-context recognition memory, a low-arousing training task assessing episodic-like memory. Male Sprague–Dawley rats were exposed to two identical objects in one context for either 3 or 10 min, immediately followed by exposure to two other identical objects in a distinctly different context. Immediately after the training they received bilateral intra-BLA infusions of norepinephrine (0.3, 1.0 or 3.0 μg or the β-adrenoceptor antagonist propranolol (0.1, 0.3 or 1.0 μg. On the 24-h retention test, rats were placed back into one of the training contexts with one copy of each of the two training objects. Thus, although both objects were familiar, one of the objects had not previously been encountered in this particular test context. Hence, if the animal generated a long-term memory for the association between an object and its context, it would spend significantly more time exploring the object that was not previously experienced in this context. Saline-infused control rats exhibited poor 24-h retention when given 3 min of training and good retention when given 10 min of training. Norepinephrine administered after 3 min of object-in-context training induced a dose-dependent memory enhancement, whereas propranolol administered after 10 min of training produced memory impairment. These findings provide evidence that posttraining noradrenergic activation of the BLA also enhances the consolidation of memory of object-in-context recognition training, enabling accuracy of episodic-like memories.

  19. Ear recognition from one sample per person.

    Directory of Open Access Journals (Sweden)

    Long Chen

    Full Text Available Biometrics has the advantages of efficiency and convenience in identity authentication. As one of the most promising biometric-based methods, ear recognition has received broad attention and research. Previous studies have achieved remarkable performance with multiple samples per person (MSPP in the gallery. However, most conventional methods are insufficient when there is only one sample per person (OSPP available in the gallery. To solve the OSPP problem by maximizing the use of a single sample, this paper proposes a hybrid multi-keypoint descriptor sparse representation-based classification (MKD-SRC ear recognition approach based on 2D and 3D information. Because most 3D sensors capture 3D data accessorizing the corresponding 2D data, it is sensible to use both types of information. First, the ear region is extracted from the profile. Second, keypoints are detected and described for both the 2D texture image and 3D range image. Then, the hybrid MKD-SRC algorithm is used to complete the recognition with only OSPP in the gallery. Experimental results on a benchmark dataset have demonstrated the feasibility and effectiveness of the proposed method in resolving the OSPP problem. A Rank-one recognition rate of 96.4% is achieved for a gallery of 415 subjects, and the time involved in the computation is satisfactory compared to conventional methods.

  20. Ear recognition from one sample per person.

    Science.gov (United States)

    Chen, Long; Mu, Zhichun; Zhang, Baoqing; Zhang, Yi

    2015-01-01

    Biometrics has the advantages of efficiency and convenience in identity authentication. As one of the most promising biometric-based methods, ear recognition has received broad attention and research. Previous studies have achieved remarkable performance with multiple samples per person (MSPP) in the gallery. However, most conventional methods are insufficient when there is only one sample per person (OSPP) available in the gallery. To solve the OSPP problem by maximizing the use of a single sample, this paper proposes a hybrid multi-keypoint descriptor sparse representation-based classification (MKD-SRC) ear recognition approach based on 2D and 3D information. Because most 3D sensors capture 3D data accessorizing the corresponding 2D data, it is sensible to use both types of information. First, the ear region is extracted from the profile. Second, keypoints are detected and described for both the 2D texture image and 3D range image. Then, the hybrid MKD-SRC algorithm is used to complete the recognition with only OSPP in the gallery. Experimental results on a benchmark dataset have demonstrated the feasibility and effectiveness of the proposed method in resolving the OSPP problem. A Rank-one recognition rate of 96.4% is achieved for a gallery of 415 subjects, and the time involved in the computation is satisfactory compared to conventional methods.

  1. Speckle-learning-based object recognition through scattering media.

    Science.gov (United States)

    Ando, Takamasa; Horisaki, Ryoichi; Tanida, Jun

    2015-12-28

    We experimentally demonstrated object recognition through scattering media based on direct machine learning of a number of speckle intensity images. In the experiments, speckle intensity images of amplitude or phase objects on a spatial light modulator between scattering plates were captured by a camera. We used the support vector machine for binary classification of the captured speckle intensity images of face and non-face data. The experimental results showed that speckles are sufficient for machine learning.

  2. Online Feature Transformation Learning for Cross-Domain Object Category Recognition.

    Science.gov (United States)

    Zhang, Xuesong; Zhuang, Yan; Wang, Wei; Pedrycz, Witold

    2017-06-09

    In this paper, we introduce a new research problem termed online feature transformation learning in the context of multiclass object category recognition. The learning of a feature transformation is viewed as learning a global similarity metric function in an online manner. We first consider the problem of online learning a feature transformation matrix expressed in the original feature space and propose an online passive aggressive feature transformation algorithm. Then these original features are mapped to kernel space and an online single kernel feature transformation (OSKFT) algorithm is developed to learn a nonlinear feature transformation. Based on the OSKFT and the existing Hedge algorithm, a novel online multiple kernel feature transformation algorithm is also proposed, which can further improve the performance of online feature transformation learning in large-scale application. The classifier is trained with k nearest neighbor algorithm together with the learned similarity metric function. Finally, we experimentally examined the effect of setting different parameter values in the proposed algorithms and evaluate the model performance on several multiclass object recognition data sets. The experimental results demonstrate the validity and good performance of our methods on cross-domain and multiclass object recognition application.

  3. Critical object recognition in millimeter-wave images with robustness to rotation and scale.

    Science.gov (United States)

    Mohammadzade, Hoda; Ghojogh, Benyamin; Faezi, Sina; Shabany, Mahdi

    2017-06-01

    Locating critical objects is crucial in various security applications and industries. For example, in security applications, such as in airports, these objects might be hidden or covered under shields or secret sheaths. Millimeter-wave images can be utilized to discover and recognize the critical objects out of the hidden cases without any health risk due to their non-ionizing features. However, millimeter-wave images usually have waves in and around the detected objects, making object recognition difficult. Thus, regular image processing and classification methods cannot be used for these images and additional pre-processings and classification methods should be introduced. This paper proposes a novel pre-processing method for canceling rotation and scale using principal component analysis. In addition, a two-layer classification method is introduced and utilized for recognition. Moreover, a large dataset of millimeter-wave images is collected and created for experiments. Experimental results show that a typical classification method such as support vector machines can recognize 45.5% of a type of critical objects at 34.2% false alarm rate (FAR), which is a drastically poor recognition. The same method within the proposed recognition framework achieves 92.9% recognition rate at 0.43% FAR, which indicates a highly significant improvement. The significant contribution of this work is to introduce a new method for analyzing millimeter-wave images based on machine vision and learning approaches, which is not yet widely noted in the field of millimeter-wave image analysis.

  4. Object recognition in images via a factor graph model

    Science.gov (United States)

    He, Yong; Wang, Long; Wu, Zhaolin; Zhang, Haisu

    2018-04-01

    Object recognition in images suffered from huge search space and uncertain object profile. Recently, the Bag-of- Words methods are utilized to solve these problems, especially the 2-dimension CRF(Conditional Random Field) model. In this paper we suggest the method based on a general and flexible fact graph model, which can catch the long-range correlation in Bag-of-Words by constructing a network learning framework contrasted from lattice in CRF. Furthermore, we explore a parameter learning algorithm based on the gradient descent and Loopy Sum-Product algorithms for the factor graph model. Experimental results on Graz 02 dataset show that, the recognition performance of our method in precision and recall is better than a state-of-art method and the original CRF model, demonstrating the effectiveness of the proposed method.

  5. Reliable Recognition of Partially Occluded Objects with Correlation Filters

    Directory of Open Access Journals (Sweden)

    Alexey Ruchay

    2018-01-01

    Full Text Available Design of conventional correlation filters requires explicit knowledge of the appearance and shape of a target object, so the performance of correlation filters is significantly affected by changes in the appearance of the object in the input scene. In particular, the performance of correlation filters worsens when objects to be recognized are partially occluded by other objects, and the input scene contains a cluttered background and noise. In this paper, we propose a new algorithm for the design of a system consisting of a set of adaptive correlation filters for recognition of partially occluded objects in noisy scenes. Since the input scene may contain different fragments of the target, false objects, and background to be rejected, the system is designed in such a manner to guarantee equally high correlation peaks corresponding to parts of the target in the scenes. The key points of the system are as follows: (i it consists of a bank of composite optimum filters, which yield the best performance for different parts of the target; (ii it includes a fragmentation of the target into a given number of parts in the training stage to provide equal intensity responses of the system for each part of the target. With the help of computer simulation, the performance of the proposed algorithm for recognition partially occluded objects is compared with that of common algorithms in terms of objective metrics.

  6. Three-dimensional model-based object recognition and segmentation in cluttered scenes.

    Science.gov (United States)

    Mian, Ajmal S; Bennamoun, Mohammed; Owens, Robyn

    2006-10-01

    Viewpoint independent recognition of free-form objects and their segmentation in the presence of clutter and occlusions is a challenging task. We present a novel 3D model-based algorithm which performs this task automatically and efficiently. A 3D model of an object is automatically constructed offline from its multiple unordered range images (views). These views are converted into multidimensional table representations (which we refer to as tensors). Correspondences are automatically established between these views by simultaneously matching the tensors of a view with those of the remaining views using a hash table-based voting scheme. This results in a graph of relative transformations used to register the views before they are integrated into a seamless 3D model. These models and their tensor representations constitute the model library. During online recognition, a tensor from the scene is simultaneously matched with those in the library by casting votes. Similarity measures are calculated for the model tensors which receive the most votes. The model with the highest similarity is transformed to the scene and, if it aligns accurately with an object in the scene, that object is declared as recognized and is segmented. This process is repeated until the scene is completely segmented. Experiments were performed on real and synthetic data comprised of 55 models and 610 scenes and an overall recognition rate of 95 percent was achieved. Comparison with the spin images revealed that our algorithm is superior in terms of recognition rate and efficiency.

  7. Using Markov Chains and Multi-Objective Optimization for Energy-Efficient Context Recognition

    Science.gov (United States)

    Janko, Vito

    2017-01-01

    The recognition of the user’s context with wearable sensing systems is a common problem in ubiquitous computing. However, the typically small battery of such systems often makes continuous recognition impractical. The strain on the battery can be reduced if the sensor setting is adapted to each context. We propose a method that efficiently finds near-optimal sensor settings for each context. It uses Markov chains to simulate the behavior of the system in different configurations and the multi-objective genetic algorithm to find a set of good non-dominated configurations. The method was evaluated on three real-life datasets and found good trade-offs between the system’s energy expenditure and the system’s accuracy. One of the solutions, for example, consumed five-times less energy than the default one, while sacrificing only two percentage points of accuracy. PMID:29286301

  8. Neurophysiological indices of perceptual object priming in the absence of explicit recognition memory.

    Science.gov (United States)

    Harris, Jill D; Cutmore, Tim R H; O'Gorman, John; Finnigan, Simon; Shum, David

    2009-02-01

    The aim of this study was to identify ERP correlates of perceptual object priming that are insensitive to factors affecting explicit, episodic memory. EEG was recorded from 21 participants while they performed a visual object recognition test on a combination of unstudied items and old items that were previously encountered during either a 'deep' or 'shallow' levels-of-processing (LOP) study task. The results demonstrated a midline P150 old/new effect which was sensitive only to objects' old/new status and not to the accuracy of recognition responses to old items, or to the LOP manipulation. Similar outcomes were observed for the subsequent P200 and N400 effects, the former of which had a parietal scalp maximum and the latter, a broadly distributed topography. In addition an LPC old/new effect typical of those reported in past ERP recognition studies was observed. These outcomes support the proposal that the P150 effect is reflective of perceptual object priming and moreover, provide novel evidence that this and the P200 effect are independent of explicit recognition memory process(es).

  9. Category-Specific Visual Recognition and Aging from the PACE Theory Perspective: Evidence for a Presemantic Deficit in Aging Object Recognition

    DEFF Research Database (Denmark)

    Bordaberry, Pierre; Gerlach, Christian; Lenoble, Quentin

    2016-01-01

    Background/Study Context: The objective of this study was to investigate the object recognition deficit in aging. Age-related declines were examined from the presemantic account of category effects (PACE) theory perspective (Gerlach, 2009, Cognition, 111, 281–301). This view assumes that the stru......Background/Study Context: The objective of this study was to investigate the object recognition deficit in aging. Age-related declines were examined from the presemantic account of category effects (PACE) theory perspective (Gerlach, 2009, Cognition, 111, 281–301). This view assumes...... that the structural similarity/dissimilarity inherent in living and nonliving objects, respectively, can account for a wide range of category-specific effects. Methods: In two experiments on object recognition, young (36 participants, 18–27 years) and older (36 participants, 53–69 years) adult participants...... in the selection stage of the PACE theory (visual long-term memory matching) could be responsible for these impairments. Indeed, the older group showed a deficit when this stage was most relevant. This article emphasize on the critical need for taking into account structural component of the stimuli and type...

  10. Detection, information fusion, and temporal processing for intelligence in recognition

    Energy Technology Data Exchange (ETDEWEB)

    Casasent, D. [Carnegie Mellon Univ., Pittsburgh, PA (United States)

    1996-12-31

    The use of intelligence in vision recognition uses many different techniques or tools. This presentation discusses several of these techniques for recognition. The recognition process is generally separated into several steps or stages when implemented in hardware, e.g. detection, segmentation and enhancement, and recognition. Several new distortion-invariant filters, biologically-inspired Gabor wavelet filter techniques, and morphological operations that have been found very useful for detection and clutter rejection are discussed. These are all shift-invariant operations that allow multiple object regions of interest in a scene to be located in parallel. We also discuss new algorithm fusion concepts by which the results from different detection algorithms are combined to reduce detection false alarms; these fusion methods utilize hierarchical processing and fuzzy logic concepts. We have found this to be most necessary, since no single detection algorithm is best for all cases. For the final recognition stage, we describe a new method of representing all distorted versions of different classes of objects and determining the object class and pose that most closely matches that of a given input. Besides being efficient in terms of storage and on-line computations required, it overcomes many of the problems that other classifiers have in terms of the required training set size, poor generalization with many hidden layer neurons, etc. It is also attractive in its ability to reject input regions as clutter (non-objects) and to learn new object descriptions. We also discuss its use in processing a temporal sequence of input images of the contents of each local region of interest. We note how this leads to robust results in which estimation efforts in individual frames can be overcome. This seems very practical, since in many scenarios a decision need not be made after only one frame of data, since subsequent frames of data enter immediately in sequence.

  11. Modeling guidance and recognition in categorical search: Bridging human and computer object detection

    OpenAIRE

    Zelinsky, Gregory J.; Peng, Yifan; Berg, Alexander C.; Samaras, Dimitris

    2013-01-01

    Search is commonly described as a repeating cycle of guidance to target-like objects, followed by the recognition of these objects as targets or distractors. Are these indeed separate processes using different visual features? We addressed this question by comparing observer behavior to that of support vector machine (SVM) models trained on guidance and recognition tasks. Observers searched for a categorically defined teddy bear target in four-object arrays. Target-absent trials consisted of ...

  12. Human Activity Recognition from Smart-Phone Sensor Data using a Multi-Class Ensemble Learning in Home Monitoring.

    Science.gov (United States)

    Ghose, Soumya; Mitra, Jhimli; Karunanithi, Mohan; Dowling, Jason

    2015-01-01

    Home monitoring of chronically ill or elderly patient can reduce frequent hospitalisations and hence provide improved quality of care at a reduced cost to the community, therefore reducing the burden on the healthcare system. Activity recognition of such patients is of high importance in such a design. In this work, a system for automatic human physical activity recognition from smart-phone inertial sensors data is proposed. An ensemble of decision trees framework is adopted to train and predict the multi-class human activity system. A comparison of our proposed method with a multi-class traditional support vector machine shows significant improvement in activity recognition accuracies.

  13. Development of novel tasks for studying view-invariant object recognition in rodents: Sensitivity to scopolamine.

    Science.gov (United States)

    Mitchnick, Krista A; Wideman, Cassidy E; Huff, Andrew E; Palmer, Daniel; McNaughton, Bruce L; Winters, Boyer D

    2018-05-15

    The capacity to recognize objects from different view-points or angles, referred to as view-invariance, is an essential process that humans engage in daily. Currently, the ability to investigate the neurobiological underpinnings of this phenomenon is limited, as few ethologically valid view-invariant object recognition tasks exist for rodents. Here, we report two complementary, novel view-invariant object recognition tasks in which rodents physically interact with three-dimensional objects. Prior to experimentation, rats and mice were given extensive experience with a set of 'pre-exposure' objects. In a variant of the spontaneous object recognition task, novelty preference for pre-exposed or new objects was assessed at various angles of rotation (45°, 90° or 180°); unlike control rodents, for whom the objects were novel, rats and mice tested with pre-exposed objects did not discriminate between rotated and un-rotated objects in the choice phase, indicating substantial view-invariant object recognition. Secondly, using automated operant touchscreen chambers, rats were tested on pre-exposed or novel objects in a pairwise discrimination task, where the rewarded stimulus (S+) was rotated (180°) once rats had reached acquisition criterion; rats tested with pre-exposed objects re-acquired the pairwise discrimination following S+ rotation more effectively than those tested with new objects. Systemic scopolamine impaired performance on both tasks, suggesting involvement of acetylcholine at muscarinic receptors in view-invariant object processing. These tasks present novel means of studying the behavioral and neural bases of view-invariant object recognition in rodents. Copyright © 2018 Elsevier B.V. All rights reserved.

  14. Standard object recognition memory and "what" and "where" components: Improvement by post-training epinephrine in highly habituated rats.

    Science.gov (United States)

    Jurado-Berbel, Patricia; Costa-Miserachs, David; Torras-Garcia, Meritxell; Coll-Andreu, Margalida; Portell-Cortés, Isabel

    2010-02-11

    The present work examined whether post-training systemic epinephrine (EPI) is able to modulate short-term (3h) and long-term (24 h and 48 h) memory of standard object recognition, as well as long-term (24 h) memory of separate "what" (object identity) and "where" (object location) components of object recognition. Although object recognition training is associated to low arousal levels, all the animals received habituation to the training box in order to further reduce emotional arousal. Post-training EPI improved long-term (24 h and 48 h), but not short-term (3 h), memory in the standard object recognition task, as well as 24 h memory for both object identity and object location. These data indicate that post-training epinephrine: (1) facilitates long-term memory for standard object recognition; (2) exerts separate facilitatory effects on "what" (object identity) and "where" (object location) components of object recognition; and (3) is capable of improving memory for a low arousing task even in highly habituated rats.

  15. Dopamine D4 receptor stimulation contributes to novel object recognition: Relevance to cognitive impairment in schizophrenia.

    Science.gov (United States)

    Miyauchi, Masanori; Neugebauer, Nichole M; Meltzer, Herbert Y

    2017-04-01

    Several atypical antipsychotic drugs (APDs) have high affinity for the dopamine (DA) D 4 receptor, but the relevance to the efficacy for the treatment of cognitive impairment associated with schizophrenia (CIAS) is poorly understood. The aim of this study was to investigate the effects of D 4 receptor stimulation or blockade on novel object recognition (NOR) in normal rats and on the sub-chronic phencyclidine (PCP)-induced novel object recognition deficit. The effect of the D 4 agonist, PD168077, and the D 4 antagonist, L-745,870, were studied alone, and in combination with clozapine and lurasidone. In normal rats, L-745,870 impaired novel object recognition, whereas PD168077 had no effect. PD168077 acutely reversed the sub-chronic phencyclidine-induced novel object recognition deficit. Co-administration of a sub-effective dose (SED) of PD168077 with a sub-effective dose of lurasidone also reversed this deficit, but a sub-effective dose of PD168077 with a sub-effective dose of clozapine, a more potent D 4 antagonist than lurasidone, did not reverse the sub-chronic phencyclidine-induced novel object recognition deficit. At a dose that did not induce a novel object recognition deficit, L-745,870 blocked the ability of clozapine, but not lurasidone, to reverse the novel object recognition deficit. D 4 receptor agonism has a beneficial effect on novel object recognition in sub-chronic PCP-treated rats and augments the cognitive enhancing efficacy of an atypical antipsychotic drug that lacks affinity for the D 4 receptor, lurasidone.

  16. Object recognition using deep convolutional neural networks with complete transfer and partial frozen layers

    NARCIS (Netherlands)

    Kruithof, M.C.; Bouma, H.; Fischer, N.M.; Schutte, K.

    2016-01-01

    Object recognition is important to understand the content of video and allow flexible querying in a large number of cameras, especially for security applications. Recent benchmarks show that deep convolutional neural networks are excellent approaches for object recognition. This paper describes an

  17. A C++ Class for Rule-Base Objects

    Directory of Open Access Journals (Sweden)

    William J. Grenney

    1992-01-01

    Full Text Available A C++ class, called Tripod, was created as a tool to assist with the development of rule-base decision support systems. The Tripod class contains data structures for the rule-base and member functions for operating on the data. The rule-base is defined by three ASCII files. These files are translated by a preprocessor into a single file that is located when a rule-base object is instantiated. The Tripod class was tested as part of a proto-type decision support system (DSS for winter highway maintenance in the Intermountain West. The DSS is composed of two principal modules: the main program, called the wrapper, and a Tripod rule-base object. The wrapper is a procedural module that interfaces with remote sensors and an external meterological database. The rule-base contains the logic for advising an inexperienced user and for assisting with the decision making process.

  18. It's all connected: Pathways in visual object recognition and early noun learning.

    Science.gov (United States)

    Smith, Linda B

    2013-11-01

    A developmental pathway may be defined as the route, or chain of events, through which a new structure or function forms. For many human behaviors, including object name learning and visual object recognition, these pathways are often complex and multicausal and include unexpected dependencies. This article presents three principles of development that suggest the value of a developmental psychology that explicitly seeks to trace these pathways and uses empirical evidence on developmental dependencies among motor development, action on objects, visual object recognition, and object name learning in 12- to 24-month-old infants to make the case. The article concludes with a consideration of the theoretical implications of this approach. (PsycINFO Database Record (c) 2013 APA, all rights reserved).

  19. Multi-sensor Object Recognition: The Case of Electronics Recycling

    NARCIS (Netherlands)

    van Dop, E.R.

    1999-01-01

    In automated object recognition systems, measurements from a single source of information do not always suffice for the reconstruction of the underlying scene. Incompleteness, inaccuracy and unreliability of the information often leaves room for multiple interpretations of the world which are

  20. Action Recognition Using 3D Histograms of Texture and A Multi-Class Boosting Classifier.

    Science.gov (United States)

    Zhang, Baochang; Yang, Yun; Chen, Chen; Yang, Linlin; Han, Jungong; Shao, Ling

    2017-10-01

    Human action recognition is an important yet challenging task. This paper presents a low-cost descriptor called 3D histograms of texture (3DHoTs) to extract discriminant features from a sequence of depth maps. 3DHoTs are derived from projecting depth frames onto three orthogonal Cartesian planes, i.e., the frontal, side, and top planes, and thus compactly characterize the salient information of a specific action, on which texture features are calculated to represent the action. Besides this fast feature descriptor, a new multi-class boosting classifier (MBC) is also proposed to efficiently exploit different kinds of features in a unified framework for action classification. Compared with the existing boosting frameworks, we add a new multi-class constraint into the objective function, which helps to maintain a better margin distribution by maximizing the mean of margin, whereas still minimizing the variance of margin. Experiments on the MSRAction3D, MSRGesture3D, MSRActivity3D, and UTD-MHAD data sets demonstrate that the proposed system combining 3DHoTs and MBC is superior to the state of the art.

  1. The subjective experience of object recognition: comparing metacognition for object detection and object categorization.

    Science.gov (United States)

    Meuwese, Julia D I; van Loon, Anouk M; Lamme, Victor A F; Fahrenfort, Johannes J

    2014-05-01

    Perceptual decisions seem to be made automatically and almost instantly. Constructing a unitary subjective conscious experience takes more time. For example, when trying to avoid a collision with a car on a foggy road you brake or steer away in a reflex, before realizing you were in a near accident. This subjective aspect of object recognition has been given little attention. We used metacognition (assessed with confidence ratings) to measure subjective experience during object detection and object categorization for degraded and masked objects, while objective performance was matched. Metacognition was equal for degraded and masked objects, but categorization led to higher metacognition than did detection. This effect turned out to be driven by a difference in metacognition for correct rejection trials, which seemed to be caused by an asymmetry of the distractor stimulus: It does not contain object-related information in the detection task, whereas it does contain such information in the categorization task. Strikingly, this asymmetry selectively impacted metacognitive ability when objective performance was matched. This finding reveals a fundamental difference in how humans reflect versus act on information: When matching the amount of information required to perform two tasks at some objective level of accuracy (acting), metacognitive ability (reflecting) is still better in tasks that rely on positive evidence (categorization) than in tasks that rely more strongly on an absence of evidence (detection).

  2. Spontaneous Object Recognition Memory in Aged Rats: Complexity versus Similarity

    Science.gov (United States)

    Gamiz, Fernando; Gallo, Milagros

    2012-01-01

    Previous work on the effect of aging on spontaneous object recognition (SOR) memory tasks in rats has yielded controversial results. Although the results at long-retention intervals are consistent, conflicting results have been reported at shorter delays. We have assessed the potential relevance of the type of object used in the performance of…

  3. Selective attention affects conceptual object priming and recognition: a study with young and older adults.

    Science.gov (United States)

    Ballesteros, Soledad; Mayas, Julia

    2014-01-01

    In the present study, we investigated the effects of selective attention at encoding on conceptual object priming (Experiment 1) and old-new recognition memory (Experiment 2) tasks in young and older adults. The procedures of both experiments included encoding and memory test phases separated by a short delay. At encoding, the picture outlines of two familiar objects, one in blue and the other in green, were presented to the left and to the right of fixation. In Experiment 1, participants were instructed to attend to the picture outline of a certain color and to classify the object as natural or artificial. After a short delay, participants performed a natural/artificial speeded conceptual classification task with repeated attended, repeated unattended, and new pictures. In Experiment 2, participants at encoding memorized the attended pictures and classify them as natural or artificial. After the encoding phase, they performed an old-new recognition memory task. Consistent with previous findings with perceptual priming tasks, we found that conceptual object priming, like explicit memory, required attention at encoding. Significant priming was obtained in both age groups, but only for those pictures that were attended at encoding. Although older adults were slower than young adults, both groups showed facilitation for attended pictures. In line with previous studies, young adults had better recognition memory than older adults.

  4. Selective attention affects conceptual object priming and recognition: A study with young and older adults

    Directory of Open Access Journals (Sweden)

    Soledad eBallesteros

    2015-01-01

    Full Text Available In the present study, we investigated the effects of selective attention at encoding on conceptual object priming (Experiment 1 and old-new recognition memory (Experiment 2 tasks in young and older adults. The procedures of both experiments included encoding and memory test phases separated by a short delay. At encoding, the picture outlines of two familiar objects, one in blue and the other in green, were presented to the left and to the right of fixation. In Experiment 1, participants were instructed to attend to the picture outline of a certain color and to classify the object as natural or artificial. After a short delay, participants performed a natural/ artificial speeded conceptual classification task with repeated attended, repeated unattended and new pictures. In Experiment 2, participants at encoding memorized the attended pictures and classified them as natural or artificial. After the encoding phase, they performed an old-new recognition memory task. Consistent with previous findings with perceptual priming tasks, we found that conceptual object priming, like explicit memory, required attention at encoding. Significant priming was obtained in both age groups, but only for those pictures that were attended at encoding. Although older adults were slower than young adults, both groups showed facilitation for attended pictures. In line with previous studies, young adults had better recognition memory than older adults.

  5. Asymmetric Functional Connectivity of the Contra- and Ipsilateral Secondary Somatosensory Cortex during Tactile Object Recognition

    Directory of Open Access Journals (Sweden)

    Yinghua Yu

    2018-01-01

    Full Text Available In the somatosensory system, it is well known that the bilateral secondary somatosensory cortex (SII receives projections from the unilateral primary somatosensory cortex (SI, and the SII, in turn, sends feedback projections to SI. Most neuroimaging studies have clearly shown bilateral SII activation using only unilateral stimulation for both anatomical and functional connectivity across SII subregions. However, no study has unveiled differences in the functional connectivity of the contra- and ipsilateral SII network that relates to frontoparietal areas during tactile object recognition. Therefore, we used event-related functional magnetic resonance imaging (fMRI and a delayed match-to-sample (DMS task to investigate the contributions of bilateral SII during tactile object recognition. In the fMRI experiment, 14 healthy subjects were presented with tactile angle stimuli on their right index finger and asked to encode three sample stimuli during the encoding phase and one test stimulus during the recognition phase. Then, the subjects indicated whether the angle of test stimulus was presented during the encoding phase. The results showed that contralateral (left SII activity was greater than ipsilateral (right SII activity during the encoding phase, but there was no difference during the recognition phase. A subsequent psycho-physiological interaction (PPI analysis revealed distinct connectivity from the contra- and ipsilateral SII to other regions. The left SII functionally connected to the left SI and right primary and premotor cortex, while the right SII functionally connected to the left posterior parietal cortex (PPC. Our findings suggest that in situations involving unilateral tactile object recognition, contra- and ipsilateral SII will induce an asymmetrical functional connectivity to other brain areas, which may occur by the hand contralateral effect of SII.

  6. Noradrenergic activation of the basolateral amygdala modulates the consolidation of object-in-context recognition memory

    OpenAIRE

    Barsegyan, Areg; McGaugh, James L.; Roozendaal, Benno

    2014-01-01

    Noradrenergic activation of the basolateral complex of the amygdala (BLA) is well known to enhance the consolidation of long-term memory of highly emotionally arousing training experiences. The present study investigated whether such noradrenergic activation of the BLA also influences the consolidation of object-in-context recognition memory, a low-arousing training task assessing episodic-like memory. Male Sprague-Dawley rats were exposed to two identical objects in one context for either 3 ...

  7. Novel Mahalanobis-based feature selection improves one-class classification of early hepatocellular carcinoma.

    Science.gov (United States)

    Thomaz, Ricardo de Lima; Carneiro, Pedro Cunha; Bonin, João Eliton; Macedo, Túlio Augusto Alves; Patrocinio, Ana Claudia; Soares, Alcimar Barbosa

    2018-05-01

    Detection of early hepatocellular carcinoma (HCC) is responsible for increasing survival rates in up to 40%. One-class classifiers can be used for modeling early HCC in multidetector computed tomography (MDCT), but demand the specific knowledge pertaining to the set of features that best describes the target class. Although the literature outlines several features for characterizing liver lesions, it is unclear which is most relevant for describing early HCC. In this paper, we introduce an unconstrained GA feature selection algorithm based on a multi-objective Mahalanobis fitness function to improve the classification performance for early HCC. We compared our approach to a constrained Mahalanobis function and two other unconstrained functions using Welch's t-test and Gaussian Data Descriptors. The performance of each fitness function was evaluated by cross-validating a one-class SVM. The results show that the proposed multi-objective Mahalanobis fitness function is capable of significantly reducing data dimensionality (96.4%) and improving one-class classification of early HCC (0.84 AUC). Furthermore, the results provide strong evidence that intensity features extracted at the arterial to portal and arterial to equilibrium phases are important for classifying early HCC.

  8. Neuropeptide S interacts with the basolateral amygdala noradrenergic system in facilitating object recognition memory consolidation.

    Science.gov (United States)

    Han, Ren-Wen; Xu, Hong-Jiao; Zhang, Rui-San; Wang, Pei; Chang, Min; Peng, Ya-Li; Deng, Ke-Yu; Wang, Rui

    2014-01-01

    The noradrenergic activity in the basolateral amygdala (BLA) was reported to be involved in the regulation of object recognition memory. As the BLA expresses high density of receptors for Neuropeptide S (NPS), we investigated whether the BLA is involved in mediating NPS's effects on object recognition memory consolidation and whether such effects require noradrenergic activity. Intracerebroventricular infusion of NPS (1nmol) post training facilitated 24-h memory in a mouse novel object recognition task. The memory-enhancing effect of NPS could be blocked by the β-adrenoceptor antagonist propranolol. Furthermore, post-training intra-BLA infusions of NPS (0.5nmol/side) improved 24-h memory for objects, which was impaired by co-administration of propranolol (0.5μg/side). Taken together, these results indicate that NPS interacts with the BLA noradrenergic system in improving object recognition memory during consolidation. Copyright © 2013 Elsevier Inc. All rights reserved.

  9. A General Polygon-based Deformable Model for Object Recognition

    DEFF Research Database (Denmark)

    Jensen, Rune Fisker; Carstensen, Jens Michael

    1999-01-01

    We propose a general scheme for object localization and recognition based on a deformable model. The model combines shape and image properties by warping a arbitrary prototype intensity template according to the deformation in shape. The shape deformations are constrained by a probabilistic distr...

  10. Enriched environment effects on remote object recognition memory.

    Science.gov (United States)

    Melani, Riccardo; Chelini, Gabriele; Cenni, Maria Cristina; Berardi, Nicoletta

    2017-06-03

    Since Ebbinghaus' classical work on oblivion and saving effects, we know that declarative memories may become at first spontaneously irretrievable and only subsequently completely extinguished. Recently, this time-dependent path toward memory-trace loss has been shown to correlate with different patterns of brain activation. Environmental enrichment (EE) enhances learning and memory and affects system memory consolidation. However, there is no evidence on whether and how EE could affect the time-dependent path toward oblivion. We used Object Recognition Test (ORT) to assess in adult mice put in EE for 40days (EE mice) or left in standard condition (SC mice) memory retrieval of the familiar objects 9 and 21days after learning with or without a brief retraining performed the day before. We found that SC mice show preferential exploration of new object at day 9 only with retraining, while EE mice do it even without. At day 21 SC mice do not show preferential exploration of novel object, irrespective of the retraining, while EE mice are still capable to benefit from retraining, even if they were not able to spontaneously recover the trace. Analysis of c-fos expression 20days after learning shows a different pattern of active brain areas in response to the retraining session in EE and SC mice, with SC mice recruiting the same brain network as naïve SC or EE mice following de novo learning. This suggests that EE promotes formation of longer lasting object recognition memory, allowing a longer time window during which saving is present. Copyright © 2017 IBRO. Published by Elsevier Ltd. All rights reserved.

  11. An Approach to Object Recognition: Aligning Pictorial Descriptions.

    Science.gov (United States)

    1986-12-01

    PERFORMING 0RGANIZATION NAMIE ANDORS IS551. PROGRAM ELEMENT. PROJECT. TASK Artificial Inteligence Laboratory AREKA A WORK UNIT NUMBERS ( 545 Technology... ARTIFICIAL INTELLIGENCE LABORATORY A.I. Memo No. 931 December, 1986 AN APPROACH TO OBJECT RECOGNITION: ALIGNING PICTORIAL DESCRIPTIONS Shimon Ullman...within the Artificial Intelligence Laboratory at the Massachusetts Institute of Technology. Support for the A.I. Laboratory’s artificial intelligence

  12. Attentional Selection for Object Recognition - A Gentle Way

    National Research Council Canada - National Science Library

    Walther, Dirk; Itti, Laurent; Riesenhuber, Maximilian; Poggio, Tomaso; Koch, Christof

    2002-01-01

    ...% at a high level is sufficient to recognize multiple objects. To determine the size and shape of the region to be modulated, a rough segmentation is performed, based on pre-attentive features already computed to guide attention. Testing with synthetic and natural stimuli demonstrates that our new approach to attentional selection for recognition yields encouraging results in addition to being biologically plausible.

  13. Deficits in long-term recognition memory reveal dissociated subtypes in congenital prosopagnosia.

    Directory of Open Access Journals (Sweden)

    Rainer Stollhoff

    Full Text Available The study investigates long-term recognition memory in congenital prosopagnosia (CP, a lifelong impairment in face identification that is present from birth. Previous investigations of processing deficits in CP have mostly relied on short-term recognition tests to estimate the scope and severity of individual deficits. We firstly report on a controlled test of long-term (one year recognition memory for faces and objects conducted with a large group of participants with CP. Long-term recognition memory is significantly impaired in eight CP participants (CPs. In all but one case, this deficit was selective to faces and didn't extend to intra-class recognition of object stimuli. In a test of famous face recognition, long-term recognition deficits were less pronounced, even after accounting for differences in media consumption between controls and CPs. Secondly, we combined test results on long-term and short-term recognition of faces and objects, and found a large heterogeneity in severity and scope of individual deficits. Analysis of the observed heterogeneity revealed a dissociation of CP into subtypes with a homogeneous phenotypical profile. Thirdly, we found that among CPs self-assessment of real-life difficulties, based on a standardized questionnaire, and experimentally assessed face recognition deficits are strongly correlated. Our results demonstrate that controlled tests of long-term recognition memory are needed to fully assess face recognition deficits in CP. Based on controlled and comprehensive experimental testing, CP can be dissociated into subtypes with a homogeneous phenotypical profile. The CP subtypes identified align with those found in prosopagnosia caused by cortical lesions; they can be interpreted with respect to a hierarchical neural system for face perception.

  14. Deficits in long-term recognition memory reveal dissociated subtypes in congenital prosopagnosia.

    Science.gov (United States)

    Stollhoff, Rainer; Jost, Jürgen; Elze, Tobias; Kennerknecht, Ingo

    2011-01-25

    The study investigates long-term recognition memory in congenital prosopagnosia (CP), a lifelong impairment in face identification that is present from birth. Previous investigations of processing deficits in CP have mostly relied on short-term recognition tests to estimate the scope and severity of individual deficits. We firstly report on a controlled test of long-term (one year) recognition memory for faces and objects conducted with a large group of participants with CP. Long-term recognition memory is significantly impaired in eight CP participants (CPs). In all but one case, this deficit was selective to faces and didn't extend to intra-class recognition of object stimuli. In a test of famous face recognition, long-term recognition deficits were less pronounced, even after accounting for differences in media consumption between controls and CPs. Secondly, we combined test results on long-term and short-term recognition of faces and objects, and found a large heterogeneity in severity and scope of individual deficits. Analysis of the observed heterogeneity revealed a dissociation of CP into subtypes with a homogeneous phenotypical profile. Thirdly, we found that among CPs self-assessment of real-life difficulties, based on a standardized questionnaire, and experimentally assessed face recognition deficits are strongly correlated. Our results demonstrate that controlled tests of long-term recognition memory are needed to fully assess face recognition deficits in CP. Based on controlled and comprehensive experimental testing, CP can be dissociated into subtypes with a homogeneous phenotypical profile. The CP subtypes identified align with those found in prosopagnosia caused by cortical lesions; they can be interpreted with respect to a hierarchical neural system for face perception.

  15. Effects of physical exercise on object recognition memory in adult rats of postnatal isoflurane exposures

    Directory of Open Access Journals (Sweden)

    Xiao-yan FANG

    2017-08-01

    Full Text Available Objective To investigate effects of physical exercise (PE on object recognition memory in adult rats of postnatal isoflurane (Iso exposures. Methods One hundred and ten postnatal 7-day SD rats (P7 were randomly divided into four groups: normal control group (Naive, Naive+PE group (received physical exercise in P21: a treadmill exercise 30min each day, 5 times/week, for 6 weeks, Iso group (three times of 2-hour Iso exposure in P7, P9, and P11, and Iso+PE group (received PE in P21 after postnatal Iso exposures. In P67, behavioral testing was conducted including open field and object recognition task (ORT, recording the time (Discrimination Ratios, DR that rats spent on exploring each object, evaluating effects of PE on object recognition memory. Results There was no significant difference in influence of PE on open field testing in all of the groups (P>0.05. Compared with Naive, there was no group difference in DR (P>0.05 for all groups, but the DR of Iso male rats was significantly higher than that of Naive female rats in P67, with significant difference (P=0.034. Compared with non-PE groups, whether or not postnatal Iso exposures, the DR of PE male groups was significantly higher (compared with Naive and Iso group: P67, P=0.050, P=0.017; P95, P=0.037, P=0.019; in female rats, the DR for ISO+PE group was lower than that of Iso group in P67 (P=0.036, but the DR of Naive+PE group was higher than that of Naive group in P95 (P=0.004. Compared with male rats, the DR of non-PE female rats was significantly higher in P67 (vis. Naive and Iso group: P=0.022, P=0.011; but in P95, the DR of non- Iso female groups was significantly higher than that of male groups (vis. Naive and Naive+PE: P=0.008, P=0.017. Conclusions There is no obvious impact of postnatal Iso exposures on object recognition memory of adult rats. These results also indicate that postnatal PE could improve object recognition memory of non-spatial learning in adult rats. In addition, exercise

  16. A class Hierarchical, object-oriented approach to virtual memory management

    Science.gov (United States)

    Russo, Vincent F.; Campbell, Roy H.; Johnston, Gary M.

    1989-01-01

    The Choices family of operating systems exploits class hierarchies and object-oriented programming to facilitate the construction of customized operating systems for shared memory and networked multiprocessors. The software is being used in the Tapestry laboratory to study the performance of algorithms, mechanisms, and policies for parallel systems. Described here are the architectural design and class hierarchy of the Choices virtual memory management system. The software and hardware mechanisms and policies of a virtual memory system implement a memory hierarchy that exploits the trade-off between response times and storage capacities. In Choices, the notion of a memory hierarchy is captured by abstract classes. Concrete subclasses of those abstractions implement a virtual address space, segmentation, paging, physical memory management, secondary storage, and remote (that is, networked) storage. Captured in the notion of a memory hierarchy are classes that represent memory objects. These classes provide a storage mechanism that contains encapsulated data and have methods to read or write the memory object. Each of these classes provides specializations to represent the memory hierarchy.

  17. Hierarchical object class representation using holes and notches

    Energy Technology Data Exchange (ETDEWEB)

    Osbourn, G.C.

    1989-01-01

    A general representation approach is described which employs a hierarchy of holes and notches. A matching procedure is also described which allows non-ideal image hierarchies to be matched to class representations. The representation and matching methods are demonstrated on a set of handgun photographs. Examples of handguns which are different in detail are shown to exhibit the same class characteristics, while other similarly shaped objects are correctly distinguished from the handgun class. 6 refs., 8 figs.

  18. Towards an Artificial Space Object Taxonomy

    Science.gov (United States)

    Wilkins, M.; Schumacher, P.; Jah, M.; Pfeffer, A.

    2013-09-01

    Object recognition is the first step in positively identifying a resident space object (RSO), i.e. assigning an RSO to a category such as GPS satellite or space debris. Object identification is the process of deciding that two RSOs are in fact one and the same. Provided we have appropriately defined a satellite taxonomy that allows us to place a given RSO into a particular class of object without any ambiguity, one can assess the probability of assignment to a particular class by determining how well the object satisfies the unique criteria of belonging to that class. Ultimately, tree-based taxonomies delineate unique signatures by defining the minimum amount of information required to positively identify a RSO. Therefore, taxonomic trees can be used to depict hypotheses in a Bayesian object recognition and identification process. This work describes a new RSO taxonomy along with specific reasoning behind the choice of groupings. An alternative taxonomy was recently presented at the Sixth Conference on Space Debris in Darmstadt, Germany. [1] The best example of a taxonomy that enjoys almost universal scientific acceptance is the classical Linnaean biological taxonomy. A strength of Linnaean taxonomy is that it can be used to organize the different kinds of living organisms, simply and practically. Every species can be given a unique name. This uniqueness and stability are a result of the acceptance by biologists specializing in taxonomy, not merely of the binomial names themselves. Fundamentally, the taxonomy is governed by rules for the use of these names, and these are laid down in formal Nomenclature Codes. We seek to provide a similar formal nomenclature system for RSOs through a defined tree-based taxonomy structure. Each categorization, beginning with the most general or inclusive, at any level is called a taxon. Taxon names are defined by a type, which can be a specimen or a taxon of lower rank, and a diagnosis, a statement intended to supply characters that

  19. Selective attention affects conceptual object priming and recognition: A study with young and older adults

    OpenAIRE

    Soledad eBallesteros; Julia eMayas

    2015-01-01

    In the present study, we investigated the effects of selective attention at encoding on conceptual object priming (Experiment 1) and old–new recognition memory (Experiment 2) tasks in young and older adults. The procedures of both experiments included encoding and memory test phases separated by a short delay. At encoding, the picture outlines of two familiar objects, one in blue and the other in green, were presented to the left and to the right of fixation. In Experiment 1, participants wer...

  20. Understanding Intra-Class Knowledge Inside CNN

    OpenAIRE

    Wei, Donglai; Zhou, Bolei; Torrabla, Antonio; Freeman, William

    2015-01-01

    Convolutional Neural Network (CNN) has been successful in image recognition tasks, and recent works shed lights on how CNN separates different classes with the learned inter-class knowledge through visualization. In this work, we instead visualize the intra-class knowledge inside CNN to better understand how an object class is represented in the fully-connected layers. To invert the intra-class knowledge into more interpretable images, we propose a non-parametric patch prior upon previous CNN...

  1. Computing with Connections in Visual Recognition of Origami Objects.

    Science.gov (United States)

    Sabbah, Daniel

    1985-01-01

    Summarizes an initial foray in tackling artificial intelligence problems using a connectionist approach. The task chosen is visual recognition of Origami objects, and the questions answered are how to construct a connectionist network to represent and recognize projected Origami line drawings and the advantages such an approach would have. (30…

  2. Visual object recognition for automatic micropropagation of plants

    Science.gov (United States)

    Brendel, Thorsten; Schwanke, Joerg; Jensch, Peter F.

    1994-11-01

    Micropropagation of plants is done by cutting juvenile plants and placing them into special container-boxes with nutrient-solution where the pieces can grow up and be cut again several times. To produce high amounts of biomass it is necessary to do plant micropropagation by a robotic system. In this paper we describe parts of the vision system that recognizes plants and their particular cutting points. Therefore, it is necessary to extract elements of the plants and relations between these elements (for example root, stem, leaf). Different species vary in their morphological appearance, variation is also immanent in plants of the same species. Therefore, we introduce several morphological classes of plants from that we expect same recognition methods.

  3. HD-MTL: Hierarchical Deep Multi-Task Learning for Large-Scale Visual Recognition.

    Science.gov (United States)

    Fan, Jianping; Zhao, Tianyi; Kuang, Zhenzhong; Zheng, Yu; Zhang, Ji; Yu, Jun; Peng, Jinye

    2017-02-09

    In this paper, a hierarchical deep multi-task learning (HD-MTL) algorithm is developed to support large-scale visual recognition (e.g., recognizing thousands or even tens of thousands of atomic object classes automatically). First, multiple sets of multi-level deep features are extracted from different layers of deep convolutional neural networks (deep CNNs), and they are used to achieve more effective accomplishment of the coarseto- fine tasks for hierarchical visual recognition. A visual tree is then learned by assigning the visually-similar atomic object classes with similar learning complexities into the same group, which can provide a good environment for determining the interrelated learning tasks automatically. By leveraging the inter-task relatedness (inter-class similarities) to learn more discriminative group-specific deep representations, our deep multi-task learning algorithm can train more discriminative node classifiers for distinguishing the visually-similar atomic object classes effectively. Our hierarchical deep multi-task learning (HD-MTL) algorithm can integrate two discriminative regularization terms to control the inter-level error propagation effectively, and it can provide an end-to-end approach for jointly learning more representative deep CNNs (for image representation) and more discriminative tree classifier (for large-scale visual recognition) and updating them simultaneously. Our incremental deep learning algorithms can effectively adapt both the deep CNNs and the tree classifier to the new training images and the new object classes. Our experimental results have demonstrated that our HD-MTL algorithm can achieve very competitive results on improving the accuracy rates for large-scale visual recognition.

  4. Neural network application for thermal image recognition of low-resolution objects

    Science.gov (United States)

    Fang, Yi-Chin; Wu, Bo-Wen

    2007-02-01

    In the ever-changing situation on a battle field, accurate recognition of a distant object is critical to a commander's decision-making and the general public's safety. Efficiently distinguishing between an enemy's armoured vehicles and ordinary civilian houses under all weather conditions has become an important research topic. This study presents a system for recognizing an armoured vehicle by distinguishing marks and contours. The characteristics of 12 different shapes and 12 characters are used to explore thermal image recognition under the circumstance of long distance and low resolution. Although the recognition capability of human eyes is superior to that of artificial intelligence under normal conditions, it tends to deteriorate substantially under long-distance and low-resolution scenarios. This study presents an effective method for choosing features and processing images. The artificial neural network technique is applied to further improve the probability of accurate recognition well beyond the limit of the recognition capability of human eyes.

  5. A Scientific Workflow Platform for Generic and Scalable Object Recognition on Medical Images

    Science.gov (United States)

    Möller, Manuel; Tuot, Christopher; Sintek, Michael

    In the research project THESEUS MEDICO we aim at a system combining medical image information with semantic background knowledge from ontologies to give clinicians fully cross-modal access to biomedical image repositories. Therefore joint efforts have to be made in more than one dimension: Object detection processes have to be specified in which an abstraction is performed starting from low-level image features across landmark detection utilizing abstract domain knowledge up to high-level object recognition. We propose a system based on a client-server extension of the scientific workflow platform Kepler that assists the collaboration of medical experts and computer scientists during development and parameter learning.

  6. The Consolidation of Object and Context Recognition Memory Involve Different Regions of the Temporal Lobe

    Science.gov (United States)

    Balderas, Israela; Rodriguez-Ortiz, Carlos J.; Salgado-Tonda, Paloma; Chavez-Hurtado, Julio; McGaugh, James L.; Bermudez-Rattoni, Federico

    2008-01-01

    These experiments investigated the involvement of several temporal lobe regions in consolidation of recognition memory. Anisomycin, a protein synthesis inhibitor, was infused into the hippocampus, perirhinal cortex, insular cortex, or basolateral amygdala of rats immediately after the sample phase of object or object-in-context recognition memory…

  7. Metric invariance in object recognition: a review and further evidence.

    Science.gov (United States)

    Cooper, E E; Biederman, I; Hummel, J E

    1992-06-01

    Phenomenologically, human shape recognition appears to be invariant with changes of orientation in depth (up to parts occlusion), position in the visual field, and size. Recent versions of template theories (e.g., Ullman, 1989; Lowe, 1987) assume that these invariances are achieved through the application of transformations such as rotation, translation, and scaling of the image so that it can be matched metrically to a stored template. Presumably, such transformations would require time for their execution. We describe recent priming experiments in which the effects of a prior brief presentation of an image on its subsequent recognition are assessed. The results of these experiments indicate that the invariance is complete: The magnitude of visual priming (as distinct from name or basic level concept priming) is not affected by a change in position, size, orientation in depth, or the particular lines and vertices present in the image, as long as representations of the same components can be activated. An implemented seven layer neural network model (Hummel & Biederman, 1992) that captures these fundamental properties of human object recognition is described. Given a line drawing of an object, the model activates a viewpoint-invariant structural description of the object, specifying its parts and their interrelations. Visual priming is interpreted as a change in the connection weights for the activation of: a) cells, termed geon feature assemblies (GFAs), that conjoin the output of units that represent invariant, independent properties of a single geon and its relations (such as its type, aspect ratio, relations to other geons), or b) a change in the connection weights by which several GFAs activate a cell representing an object.

  8. Glucocorticoid effects on object recognition memory require training-associated emotional arousal.

    Science.gov (United States)

    Okuda, Shoki; Roozendaal, Benno; McGaugh, James L

    2004-01-20

    Considerable evidence implicates glucocorticoid hormones in the regulation of memory consolidation and memory retrieval. The present experiments investigated whether the influence of these hormones on memory depends on the level of emotional arousal induced by the training experience. We investigated this issue in male Sprague-Dawley rats by examining the effects of immediate posttraining systemic injections of the glucocorticoid corticosterone on object recognition memory under two conditions that differed in their training-associated emotional arousal. In rats that were not previously habituated to the experimental context, corticosterone (0.3, 1.0, or 3.0 mg/kg, s.c.) administered immediately after a 3-min training trial enhanced 24-hr retention performance in an inverted-U shaped dose-response relationship. In contrast, corticosterone did not affect 24-hr retention of rats that received extensive prior habituation to the experimental context and, thus, had decreased novelty-induced emotional arousal during training. Additionally, immediate posttraining administration of corticosterone to nonhabituated rats, in doses that enhanced 24-hr retention, impaired object recognition performance at a 1-hr retention interval whereas corticosterone administered after training to well-habituated rats did not impair 1-hr retention. Thus, the present findings suggest that training-induced emotional arousal may be essential for glucocorticoid effects on object recognition memory.

  9. Priming Contour-Deleted Images: Evidence for Immediate Representations in Visual Object Recognition.

    Science.gov (United States)

    Biederman, Irving; Cooper, Eric E.

    1991-01-01

    Speed and accuracy of identification of pictures of objects are facilitated by prior viewing. Contributions of image features, convex or concave components, and object models in a repetition priming task were explored in 2 studies involving 96 college students. Results provide evidence of intermediate representations in visual object recognition.…

  10. Activity recognition from minimal distinguishing subsequence mining

    Science.gov (United States)

    Iqbal, Mohammad; Pao, Hsing-Kuo

    2017-08-01

    Human activity recognition is one of the most important research topics in the era of Internet of Things. To separate different activities given sensory data, we utilize a Minimal Distinguishing Subsequence (MDS) mining approach to efficiently find distinguishing patterns among different activities. We first transform the sensory data into a series of sensor triggering events and operate the MDS mining procedure afterwards. The gap constraints are also considered in the MDS mining. Given the multi-class nature of most activity recognition tasks, we modify the MDS mining approach from a binary case to a multi-class one to fit the need for multiple activity recognition. We also study how to select the best parameter set including the minimal and the maximal support thresholds in finding the MDSs for effective activity recognition. Overall, the prediction accuracy is 86.59% on the van Kasteren dataset which consists of four different activities for recognition.

  11. Object class hierarchy for an incremental hypertext editor

    Directory of Open Access Journals (Sweden)

    A. Colesnicov

    1995-02-01

    Full Text Available The object class hierarchy design is considered due to a hypertext editor implementation. The following basic classes were selected: the editor's coordinate system, the memory manager, the text buffer executing basic editing operations, the inherited hypertext buffer, the edit window, the multi-window shell. Special hypertext editing features, the incremental hypertext creation support and further generalizations are discussed.

  12. Discovery of M class objects among the near-earth asteroid population

    Science.gov (United States)

    Tedesco, Edward F.; Gradie, Jonathan

    1987-01-01

    Broadband colorimetry, visual photometry, near-infrared photometry, and 10 and 20 micron radiometry of the near-earth asteroids (NEAs) 1986 DA and 1986 EB are used to show that these objects belong to the M class of asteroids. The similarity among the distributions of taxonomic classes among the 38 NEAs to the abundances found in the inner astoroid belt between the 3:1 and 5:2 resonances suggests that NEAs have their origins among asteroids in the vicinity of these resonances. The implied mineralogy of 1986 DA and 1986 EB is mostly nickel-iron metal; if this is indeed the case, then current models for meteorite production based on strength-related collisional processes on asteroidal surfaces predict that these two objects alone should produce about one percent of all meteorite falls. Iron meteorites derived from these near-earth asteroids should have low cosmic-ray exposure ages.

  13. a Two-Step Classification Approach to Distinguishing Similar Objects in Mobile LIDAR Point Clouds

    Science.gov (United States)

    He, H.; Khoshelham, K.; Fraser, C.

    2017-09-01

    Nowadays, lidar is widely used in cultural heritage documentation, urban modeling, and driverless car technology for its fast and accurate 3D scanning ability. However, full exploitation of the potential of point cloud data for efficient and automatic object recognition remains elusive. Recently, feature-based methods have become very popular in object recognition on account of their good performance in capturing object details. Compared with global features describing the whole shape of the object, local features recording the fractional details are more discriminative and are applicable for object classes with considerable similarity. In this paper, we propose a two-step classification approach based on point feature histograms and the bag-of-features method for automatic recognition of similar objects in mobile lidar point clouds. Lamp post, street light and traffic sign are grouped as one category in the first-step classification for their inter similarity compared with tree and vehicle. A finer classification of the lamp post, street light and traffic sign based on the result of the first-step classification is implemented in the second step. The proposed two-step classification approach is shown to yield a considerable improvement over the conventional one-step classification approach.

  14. Supervised linear dimensionality reduction with robust margins for object recognition

    Science.gov (United States)

    Dornaika, F.; Assoum, A.

    2013-01-01

    Linear Dimensionality Reduction (LDR) techniques have been increasingly important in computer vision and pattern recognition since they permit a relatively simple mapping of data onto a lower dimensional subspace, leading to simple and computationally efficient classification strategies. Recently, many linear discriminant methods have been developed in order to reduce the dimensionality of visual data and to enhance the discrimination between different groups or classes. Many existing linear embedding techniques relied on the use of local margins in order to get a good discrimination performance. However, dealing with outliers and within-class diversity has not been addressed by margin-based embedding method. In this paper, we explored the use of different margin-based linear embedding methods. More precisely, we propose to use the concepts of Median miss and Median hit for building robust margin-based criteria. Based on such margins, we seek the projection directions (linear embedding) such that the sum of local margins is maximized. Our proposed approach has been applied to the problem of appearance-based face recognition. Experiments performed on four public face databases show that the proposed approach can give better generalization performance than the classic Average Neighborhood Margin Maximization (ANMM). Moreover, thanks to the use of robust margins, the proposed method down-grades gracefully when label outliers contaminate the training data set. In particular, we show that the concept of Median hit was crucial in order to get robust performance in the presence of outliers.

  15. The effect of subjective and objective social class on health-related quality of life: new paradigm using longitudinal analysis.

    Science.gov (United States)

    Choi, Young; Kim, Jae-Hyun; Park, Eun-Cheol

    2015-08-08

    To investigate the impact of the gap between subjective and objective social status on health-related quality of life. We analyzed data from 12,350 participants aged ≥ 18 years in the Korean Health Panel Survey. Health-related quality of life was measured by EuroQol-Visual analogue scale. Objective (income and education) and subjective social class (measured by MacArthur scale) was classified into three groups (High, Middle, Low). In terms of a gap between objective and subjective social class, social class was grouped into nine categories ranging from High-High to Low-Low. A linear mixed model was used to investigate the association between the combined social class and health-related quality of life. The impact of the gap between objective and subjective status on Health-related quality of life varied according to the type of gap. Namely, at any given subjective social class, an individual's quality of life declined with a decrease in the objective social class. At any given objective social class (e.g., HH, HM, HL; in terms of both education and income), an individual's quality of life declined with a one-level decrease in subjective social class. Our results suggest that studies of the relationship between social class and health outcomes may consider the multidimensional nature of social status.

  16. A rat in the sewer: How mental imagery interacts with object recognition.

    Science.gov (United States)

    Karimpur, Harun; Hamburger, Kai

    2018-01-01

    The role of mental imagery has been puzzling researchers for more than two millennia. Both positive and negative effects of mental imagery on information processing have been discussed. The aim of this work was to examine how mental imagery affects object recognition and associative learning. Based on different perceptual and cognitive accounts we tested our imagery-induced interaction hypothesis in a series of two experiments. According to that, mental imagery could lead to (1) a superior performance in object recognition and associative learning if these objects are imagery-congruent (semantically) and to (2) an inferior performance if these objects are imagery-incongruent. In the first experiment, we used a static environment and tested associative learning. In the second experiment, subjects encoded object information in a dynamic environment by means of a virtual sewer system. Our results demonstrate that subjects who received a role adoption task (by means of guided mental imagery) performed better when imagery-congruent objects were used and worse when imagery-incongruent objects were used. We finally discuss our findings also with respect to alternative accounts and plead for a multi-methodological approach for future research in order to solve this issue.

  17. A Neural Model Combining Attentional Orienting to Object Recognition: Preliminary Explorations on the Interplay Between Where and What

    National Research Council Canada - National Science Library

    Miau, Florence

    2001-01-01

    ... ("where") pathway and an object recognition ("what") pathway. The fast visual attention front-end rapidly selects the few most conspicuous image locations, and the slower object recognition back-end identifies objects at the selected locations...

  18. Single-Pol Synthetic Aperture Radar Terrain Classification using Multiclass Confidence for One-Class Classifiers

    Energy Technology Data Exchange (ETDEWEB)

    Koch, Mark William [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Steinbach, Ryan Matthew [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Moya, Mary M [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

    2015-10-01

    Except in the most extreme conditions, Synthetic aperture radar (SAR) is a remote sensing technology that can operate day or night. A SAR can provide surveillance over a long time period by making multiple passes over a wide area. For object-based intelligence it is convenient to segment and classify the SAR images into objects that identify various terrains and man-made structures that we call “static features.” In this paper we introduce a novel SAR image product that captures how different regions decorrelate at different rates. Using superpixels and their first two moments we develop a series of one-class classification algorithms using a goodness-of-fit metric. P-value fusion is used to combine the results from different classes. We also show how to combine multiple one-class classifiers to get a confidence about a classification. This can be used by downstream algorithms such as a conditional random field to enforce spatial constraints.

  19. Discriminative kernel feature extraction and learning for object recognition and detection

    DEFF Research Database (Denmark)

    Pan, Hong; Olsen, Søren Ingvor; Zhu, Yaping

    2015-01-01

    Feature extraction and learning is critical for object recognition and detection. By embedding context cue of image attributes into the kernel descriptors, we propose a set of novel kernel descriptors called context kernel descriptors (CKD). The motivation of CKD is to use the spatial consistency...... even in high-dimensional space. In addition, the latent connection between Rényi quadratic entropy and the mapping data in kernel feature space further facilitates us to capture the geometric structure as well as the information about the underlying labels of the CKD using CSQMI. Thus the resulting...... codebook and reduced CKD are discriminative. We report superior performance of our algorithm for object recognition on benchmark datasets like Caltech-101 and CIFAR-10, as well as for detection on a challenging chicken feet dataset....

  20. Dentate gyrus supports slope recognition memory, shades of grey-context pattern separation and recognition memory, and CA3 supports pattern completion for object memory.

    Science.gov (United States)

    Kesner, Raymond P; Kirk, Ryan A; Yu, Zhenghui; Polansky, Caitlin; Musso, Nick D

    2016-03-01

    In order to examine the role of the dorsal dentate gyrus (dDG) in slope (vertical space) recognition and possible pattern separation, various slope (vertical space) degrees were used in a novel exploratory paradigm to measure novelty detection for changes in slope (vertical space) recognition memory and slope memory pattern separation in Experiment 1. The results of the experiment indicate that control rats displayed a slope recognition memory function with a pattern separation process for slope memory that is dependent upon the magnitude of change in slope between study and test phases. In contrast, the dDG lesioned rats displayed an impairment in slope recognition memory, though because there was no significant interaction between the two groups and slope memory, a reliable pattern separation impairment for slope could not be firmly established in the DG lesioned rats. In Experiment 2, in order to determine whether, the dDG plays a role in shades of grey spatial context recognition and possible pattern separation, shades of grey were used in a novel exploratory paradigm to measure novelty detection for changes in the shades of grey context environment. The results of the experiment indicate that control rats displayed a shades of grey-context pattern separation effect across levels of separation of context (shades of grey). In contrast, the DG lesioned rats displayed a significant interaction between the two groups and levels of shades of grey suggesting impairment in a pattern separation function for levels of shades of grey. In Experiment 3 in order to determine whether the dorsal CA3 (dCA3) plays a role in object pattern completion, a new task requiring less training and using a choice that was based on choosing the correct set of objects on a two-choice discrimination task was used. The results indicated that control rats displayed a pattern completion function based on the availability of one, two, three or four cues. In contrast, the dCA3 lesioned rats

  1. Crowded and Sparse Domains in Object Recognition: Consequences for Categorization and Naming

    Science.gov (United States)

    Gale, Tim M.; Laws, Keith R.; Foley, Kerry

    2006-01-01

    Some models of object recognition propose that items from structurally crowded categories (e.g., living things) permit faster access to superordinate semantic information than structurally dissimilar categories (e.g., nonliving things), but slower access to individual object information when naming items. We present four experiments that utilize…

  2. Visual object recognition and tracking

    Science.gov (United States)

    Chang, Chu-Yin (Inventor); English, James D. (Inventor); Tardella, Neil M. (Inventor)

    2010-01-01

    This invention describes a method for identifying and tracking an object from two-dimensional data pictorially representing said object by an object-tracking system through processing said two-dimensional data using at least one tracker-identifier belonging to the object-tracking system for providing an output signal containing: a) a type of the object, and/or b) a position or an orientation of the object in three-dimensions, and/or c) an articulation or a shape change of said object in said three dimensions.

  3. Exploring social class differences at work

    OpenAIRE

    Evans, Samantha

    2016-01-01

    This paper is part of a wider project that investigates how organisational and individual factors within the workplace contribute to social class differences and inequality by examining the relative impact of objective and subjective indicators of social class on explicit (e.g. salary, promotions) and implicit (e.g. career satisfaction, quality of working life, stress and well-being) career and work outcomes. \\ud There is increasing recognition that social class differences play a crucial rol...

  4. Visual recognition and tracking of objects for robot sensing

    International Nuclear Information System (INIS)

    Lowe, D.G.

    1994-01-01

    An overview is presented of a number of techniques used for recognition and motion tracking of articulated 3-D objects. With recent advances in robust methods for model-based vision and improved performance of computer systems, it will soon be possible to build low-cost, high-reliability systems for model-based motion tracking. Such systems can be expected to open up a wide range of applications in robotics by providing machines with real-time information about their environment. This paper describes a number of techniques for efficiently matching parameterized 3-D models to image features. The matching methods are robust with respect to missing and ambiguous features as well as measurement errors. Unlike most previous work on model-based motion tracking, this system provides for the integrated treatment of matching and measurement errors during motion tracking. The initial application is in a system for real-time motion tracking of articulated 3-D objects. With the future addition of an indexing component, these same techniques can also be used for general model-based recognition. The current real-time implementation is based on matching straight line segments, but some preliminary experiments on matching arbitrary curves are also described. (author)

  5. Face Recognition Is Affected by Similarity in Spatial Frequency Range to a Greater Degree Than Within-Category Object Recognition

    Science.gov (United States)

    Collin, Charles A.; Liu, Chang Hong; Troje, Nikolaus F.; McMullen, Patricia A.; Chaudhuri, Avi

    2004-01-01

    Previous studies have suggested that face identification is more sensitive to variations in spatial frequency content than object recognition, but none have compared how sensitive the 2 processes are to variations in spatial frequency overlap (SFO). The authors tested face and object matching accuracy under varying SFO conditions. Their results…

  6. Biometric correspondence between reface computerized facial approximations and CT-derived ground truth skin surface models objectively examined using an automated facial recognition system.

    Science.gov (United States)

    Parks, Connie L; Monson, Keith L

    2018-05-01

    This study employed an automated facial recognition system as a means of objectively evaluating biometric correspondence between a ReFace facial approximation and the computed tomography (CT) derived ground truth skin surface of the same individual. High rates of biometric correspondence were observed, irrespective of rank class (R k ) or demographic cohort examined. Overall, 48% of the test subjects' ReFace approximation probes (n=96) were matched to his or her corresponding ground truth skin surface image at R 1 , a rank indicating a high degree of biometric correspondence and a potential positive identification. Identification rates improved with each successively broader rank class (R 10 =85%, R 25 =96%, and R 50 =99%), with 100% identification by R 57 . A sharp increase (39% mean increase) in identification rates was observed between R 1 and R 10 across most rank classes and demographic cohorts. In contrast, significantly lower (p0.05) performance differences were observed across demographic cohorts or CT scan protocols. Performance measures observed in this research suggest that ReFace approximations are biometrically similar to the actual faces of the approximated individuals and, therefore, may have potential operational utility in contexts in which computerized approximations are utilized as probes in automated facial recognition systems. Copyright © 2018. Published by Elsevier B.V.

  7. A Latent Class Multidimensional Scaling Model for Two-Way One-Mode Continuous Rating Dissimilarity Data

    Science.gov (United States)

    Vera, J. Fernando; Macias, Rodrigo; Heiser, Willem J.

    2009-01-01

    In this paper, we propose a cluster-MDS model for two-way one-mode continuous rating dissimilarity data. The model aims at partitioning the objects into classes and simultaneously representing the cluster centers in a low-dimensional space. Under the normal distribution assumption, a latent class model is developed in terms of the set of…

  8. Distinct roles of the hippocampus and perirhinal cortex in GABAA receptor blockade-induced enhancement of object recognition memory.

    Science.gov (United States)

    Kim, Jong Min; Kim, Dong Hyun; Lee, Younghwan; Park, Se Jin; Ryu, Jong Hoon

    2014-03-13

    It is well known that the hippocampus plays a role in spatial and contextual memory, and that spatial information is tightly regulated by the hippocampus. However, it is still highly controversial whether the hippocampus plays a role in object recognition memory. In a pilot study, the administration of bicuculline, a GABAA receptor antagonist, enhanced memory in the passive avoidance task, but not in the novel object recognition task. In the present study, we hypothesized that these different results are related to the characteristics of each task and the different roles of hippocampus and perirhinal cortex. A region-specific drug-treatment model was employed to clarify the role of the hippocampus and perirhinal cortex in object recognition memory. After a single habituation in the novel object recognition task, intra-perirhinal cortical injection of bicuculline increased and intra-hippocampal injection decreased the exploration time ratio to novel object. In addition, when animals were repeatedly habituated to the context, intra-perirhinal cortical administration of bicuculline still increased exploration time ratio to novel object, but the effect of intra-hippocampal administration disappeared. Concurrent increases of c-Fos expression and ERK phosphorylation were observed in the perirhinal cortex of the object with context-exposed group either after single or repeated habituation to the context, but no changes were noted in the hippocampus. Altogether, these results suggest that object recognition memory formation requires the perirhinal cortex but not the hippocampus, and that hippocampal activation interferes with object recognition memory by the information encoding of unfamiliar environment. Copyright © 2014 Elsevier B.V. All rights reserved.

  9. The Effect of Training Data Selection on Face Recognition in Surveillance Application

    Directory of Open Access Journals (Sweden)

    Jamal Ahmad DARGHAM

    2014-12-01

    Full Text Available Face recognition is an important biometric method because of its potential applications in many fields, such as access control and surveillance. In surveillance applications, the distance between the subject and the camera is changing. Thus, in this paper, the effect of the distance between the subject and the camera, distance class, the effect of the number of images per class, and also the effect of session used to acquire the images have been investigated. Three sessions are used to acquire the images in the database. The images in each session were equally divided into three distance classes: CLOSE, MEDIUM, and FAR, according to the distance of the subject from the camera. It was found that using images from the MEDIUM class for training gives better performance than using either the FAR or the CLOSE class. In addition, it was also found that using one image from each class for training gives the same recognition performance as using three images from the MEDIUM class for training. It was also found that as the number of images per class increases, the recognition performance also increases. Lastly, it was found that by using one image per class from all the available database sessions gives the best recognition performance.

  10. A TWO-STEP CLASSIFICATION APPROACH TO DISTINGUISHING SIMILAR OBJECTS IN MOBILE LIDAR POINT CLOUDS

    Directory of Open Access Journals (Sweden)

    H. He

    2017-09-01

    Full Text Available Nowadays, lidar is widely used in cultural heritage documentation, urban modeling, and driverless car technology for its fast and accurate 3D scanning ability. However, full exploitation of the potential of point cloud data for efficient and automatic object recognition remains elusive. Recently, feature-based methods have become very popular in object recognition on account of their good performance in capturing object details. Compared with global features describing the whole shape of the object, local features recording the fractional details are more discriminative and are applicable for object classes with considerable similarity. In this paper, we propose a two-step classification approach based on point feature histograms and the bag-of-features method for automatic recognition of similar objects in mobile lidar point clouds. Lamp post, street light and traffic sign are grouped as one category in the first-step classification for their inter similarity compared with tree and vehicle. A finer classification of the lamp post, street light and traffic sign based on the result of the first-step classification is implemented in the second step. The proposed two-step classification approach is shown to yield a considerable improvement over the conventional one-step classification approach.

  11. Image processing and recognition for biological images.

    Science.gov (United States)

    Uchida, Seiichi

    2013-05-01

    This paper reviews image processing and pattern recognition techniques, which will be useful to analyze bioimages. Although this paper does not provide their technical details, it will be possible to grasp their main tasks and typical tools to handle the tasks. Image processing is a large research area to improve the visibility of an input image and acquire some valuable information from it. As the main tasks of image processing, this paper introduces gray-level transformation, binarization, image filtering, image segmentation, visual object tracking, optical flow and image registration. Image pattern recognition is the technique to classify an input image into one of the predefined classes and also has a large research area. This paper overviews its two main modules, that is, feature extraction module and classification module. Throughout the paper, it will be emphasized that bioimage is a very difficult target for even state-of-the-art image processing and pattern recognition techniques due to noises, deformations, etc. This paper is expected to be one tutorial guide to bridge biology and image processing researchers for their further collaboration to tackle such a difficult target. © 2013 The Author Development, Growth & Differentiation © 2013 Japanese Society of Developmental Biologists.

  12. Anomaly detection in forward looking infrared imaging using one-class classifiers

    Science.gov (United States)

    Popescu, Mihail; Stone, Kevin; Havens, Timothy; Ho, Dominic; Keller, James

    2010-04-01

    In this paper we describe a method for generating cues of possible abnormal objects present in the field of view of an infrared (IR) camera installed on a moving vehicle. The proposed method has two steps. In the first step, for each frame, we generate a set of possible points of interest using a corner detection algorithm. In the second step, the points related to the background are discarded from the point set using an one class classifier (OCC) trained on features extracted from a local neighborhood of each point. The advantage of using an OCC is that we do not need examples from the "abnormal object" class to train the classifier. Instead, OCC is trained using corner points from images known to be abnormal object free, i.e., that contain only background scenes. To further reduce the number of false alarms we use a temporal fusion procedure: a region has to be detected as "interesting" in m out of n, mGM). The comparison is performed using a set of about 900 background point neighborhoods for training and 400 for testing. The best performing OCC is then used to detect abnormal objects in a set of IR video sequences obtained on a 1 mile long country road.

  13. Image object recognition based on the Zernike moment and neural networks

    Science.gov (United States)

    Wan, Jianwei; Wang, Ling; Huang, Fukan; Zhou, Liangzhu

    1998-03-01

    This paper first give a comprehensive discussion about the concept of artificial neural network its research methods and the relations with information processing. On the basis of such a discussion, we expound the mathematical similarity of artificial neural network and information processing. Then, the paper presents a new method of image recognition based on invariant features and neural network by using image Zernike transform. The method not only has the invariant properties for rotation, shift and scale of image object, but also has good fault tolerance and robustness. Meanwhile, it is also compared with statistical classifier and invariant moments recognition method.

  14. Where vision meets memory: prefrontal-posterior networks for visual object constancy during categorization and recognition.

    Science.gov (United States)

    Schendan, Haline E; Stern, Chantal E

    2008-07-01

    Objects seen from unusual relative to more canonical views require more time to categorize and recognize, and, according to object model verification theories, additionally recruit prefrontal processes for cognitive control that interact with parietal processes for mental rotation. To test this using functional magnetic resonance imaging, people categorized and recognized known objects from unusual and canonical views. Canonical views activated some components of a default network more on categorization than recognition. Activation to unusual views showed that both ventral and dorsal visual pathways, and prefrontal cortex, have key roles in visual object constancy. Unusual views activated object-sensitive and mental rotation (and not saccade) regions in ventrocaudal intraparietal, transverse occipital, and inferotemporal sulci, and ventral premotor cortex for verification processes of model testing on any task. A collateral-lingual sulci "place" area activated for mental rotation, working memory, and unusual views on correct recognition and categorization trials to accomplish detailed spatial matching. Ventrolateral prefrontal cortex and object-sensitive lateral occipital sulcus activated for mental rotation and unusual views on categorization more than recognition, supporting verification processes of model prediction. This visual knowledge framework integrates vision and memory theories to explain how distinct prefrontal-posterior networks enable meaningful interactions with objects in diverse situations.

  15. Hierarchical Context Modeling for Video Event Recognition.

    Science.gov (United States)

    Wang, Xiaoyang; Ji, Qiang

    2016-10-11

    Current video event recognition research remains largely target-centered. For real-world surveillance videos, targetcentered event recognition faces great challenges due to large intra-class target variation, limited image resolution, and poor detection and tracking results. To mitigate these challenges, we introduced a context-augmented video event recognition approach. Specifically, we explicitly capture different types of contexts from three levels including image level, semantic level, and prior level. At the image level, we introduce two types of contextual features including the appearance context features and interaction context features to capture the appearance of context objects and their interactions with the target objects. At the semantic level, we propose a deep model based on deep Boltzmann machine to learn event object representations and their interactions. At the prior level, we utilize two types of prior-level contexts including scene priming and dynamic cueing. Finally, we introduce a hierarchical context model that systematically integrates the contextual information at different levels. Through the hierarchical context model, contexts at different levels jointly contribute to the event recognition. We evaluate the hierarchical context model for event recognition on benchmark surveillance video datasets. Results show that incorporating contexts in each level can improve event recognition performance, and jointly integrating three levels of contexts through our hierarchical model achieves the best performance.

  16. Are Face and Object Recognition Independent? A Neurocomputational Modeling Exploration.

    Science.gov (United States)

    Wang, Panqu; Gauthier, Isabel; Cottrell, Garrison

    2016-04-01

    Are face and object recognition abilities independent? Although it is commonly believed that they are, Gauthier et al. [Gauthier, I., McGugin, R. W., Richler, J. J., Herzmann, G., Speegle, M., & VanGulick, A. E. Experience moderates overlap between object and face recognition, suggesting a common ability. Journal of Vision, 14, 7, 2014] recently showed that these abilities become more correlated as experience with nonface categories increases. They argued that there is a single underlying visual ability, v, that is expressed in performance with both face and nonface categories as experience grows. Using the Cambridge Face Memory Test and the Vanderbilt Expertise Test, they showed that the shared variance between Cambridge Face Memory Test and Vanderbilt Expertise Test performance increases monotonically as experience increases. Here, we address why a shared resource across different visual domains does not lead to competition and to an inverse correlation in abilities? We explain this conundrum using our neurocomputational model of face and object processing ["The Model", TM, Cottrell, G. W., & Hsiao, J. H. Neurocomputational models of face processing. In A. J. Calder, G. Rhodes, M. Johnson, & J. Haxby (Eds.), The Oxford handbook of face perception. Oxford, UK: Oxford University Press, 2011]. We model the domain general ability v as the available computational resources (number of hidden units) in the mapping from input to label and experience as the frequency of individual exemplars in an object category appearing during network training. Our results show that, as in the behavioral data, the correlation between subordinate level face and object recognition accuracy increases as experience grows. We suggest that different domains do not compete for resources because the relevant features are shared between faces and objects. The essential power of experience is to generate a "spreading transform" for faces (separating them in representational space) that

  17. [Recognition of visual objects under forward masking. Effects of cathegorial similarity of test and masking stimuli].

    Science.gov (United States)

    Gerasimenko, N Iu; Slavutskaia, A V; Kalinin, S A; Kulikov, M A; Mikhaĭlova, E S

    2013-01-01

    In 38 healthy subjects accuracy and response time were examined during recognition of two categories of images--animals andnonliving objects--under forward masking. We revealed new data that masking effects depended of categorical similarity of target and masking stimuli. The recognition accuracy was the lowest and the response time was the most slow, when the target and masking stimuli belongs to the same category, that was combined with high dispersion of response times. The revealed effects were more clear in the task of animal recognition in comparison with the recognition of nonliving objects. We supposed that the revealed effects connected with interference between cortical representations of the target and masking stimuli and discussed our results in context of cortical interference and negative priming.

  18. Recognition of abstract objects via neural oscillators: interaction among topological organization, associative memory and gamma band synchronization.

    Science.gov (United States)

    Ursino, Mauro; Magosso, Elisa; Cuppini, Cristiano

    2009-02-01

    Synchronization of neural activity in the gamma band is assumed to play a significant role not only in perceptual processing, but also in higher cognitive functions. Here, we propose a neural network of Wilson-Cowan oscillators to simulate recognition of abstract objects, each represented as a collection of four features. Features are ordered in topological maps of oscillators connected via excitatory lateral synapses, to implement a similarity principle. Experience on previous objects is stored in long-range synapses connecting the different topological maps, and trained via timing dependent Hebbian learning (previous knowledge principle). Finally, a downstream decision network detects the presence of a reliable object representation, when all features are oscillating in synchrony. Simulations performed giving various simultaneous objects to the network (from 1 to 4), with some missing and/or modified properties suggest that the network can reconstruct objects, and segment them from the other simultaneously present objects, even in case of deteriorated information, noise, and moderate correlation among the inputs (one common feature). The balance between sensitivity and specificity depends on the strength of the Hebbian learning. Achieving a correct reconstruction in all cases, however, requires ad hoc selection of the oscillation frequency. The model represents an attempt to investigate the interactions among topological maps, autoassociative memory, and gamma-band synchronization, for recognition of abstract objects.

  19. A comparison of feature detectors and descriptors for object class matching

    DEFF Research Database (Denmark)

    Hietanen, Antti; Lankinen, Jukka; Kämäräinen, Joni-Kristian

    2016-01-01

    appearance variation can be large. We extend the benchmarks to the class matching setting and evaluate state-of-the-art detectors and descriptors with Caltech and ImageNet classes. Our experiments provide important findings with regard to object class matching: (1) the original SIFT is still the best...

  20. Field of attention for instantaneous object recognition.

    Directory of Open Access Journals (Sweden)

    Jian-Gao Yao

    Full Text Available BACKGROUND: Instantaneous object discrimination and categorization are fundamental cognitive capacities performed with the guidance of visual attention. Visual attention enables selection of a salient object within a limited area of the visual field; we referred to as "field of attention" (FA. Though there is some evidence concerning the spatial extent of object recognition, the following questions still remain unknown: (a how large is the FA for rapid object categorization, (b how accuracy of attention is distributed over the FA, and (c how fast complex objects can be categorized when presented against backgrounds formed by natural scenes. METHODOLOGY/PRINCIPAL FINDINGS: To answer these questions, we used a visual perceptual task in which subjects were asked to focus their attention on a point while being required to categorize briefly flashed (20 ms photographs of natural scenes by indicating whether or not these contained an animal. By measuring the accuracy of categorization at different eccentricities from the fixation point, we were able to determine the spatial extent and the distribution of accuracy over the FA, as well as the speed of categorizing objects using stimulus onset asynchrony (SOA. Our results revealed that subjects are able to rapidly categorize complex natural images within about 0.1 s without eye movement, and showed that the FA for instantaneous image categorization covers a visual field extending 20° × 24°, and accuracy was highest (>90% at the center of FA and declined with increasing eccentricity. CONCLUSIONS/SIGNIFICANCE: In conclusion, human beings are able to categorize complex natural images at a glance over a large extent of the visual field without eye movement.

  1. 3-D OBJECT RECOGNITION FROM POINT CLOUD DATA

    Directory of Open Access Journals (Sweden)

    W. Smith

    2012-09-01

    Full Text Available The market for real-time 3-D mapping includes not only traditional geospatial applications but also navigation of unmanned autonomous vehicles (UAVs. Massively parallel processes such as graphics processing unit (GPU computing make real-time 3-D object recognition and mapping achievable. Geospatial technologies such as digital photogrammetry and GIS offer advanced capabilities to produce 2-D and 3-D static maps using UAV data. The goal is to develop real-time UAV navigation through increased automation. It is challenging for a computer to identify a 3-D object such as a car, a tree or a house, yet automatic 3-D object recognition is essential to increasing the productivity of geospatial data such as 3-D city site models. In the past three decades, researchers have used radiometric properties to identify objects in digital imagery with limited success, because these properties vary considerably from image to image. Consequently, our team has developed software that recognizes certain types of 3-D objects within 3-D point clouds. Although our software is developed for modeling, simulation and visualization, it has the potential to be valuable in robotics and UAV applications. The locations and shapes of 3-D objects such as buildings and trees are easily recognizable by a human from a brief glance at a representation of a point cloud such as terrain-shaded relief. The algorithms to extract these objects have been developed and require only the point cloud and minimal human inputs such as a set of limits on building size and a request to turn on a squaring option. The algorithms use both digital surface model (DSM and digital elevation model (DEM, so software has also been developed to derive the latter from the former. The process continues through the following steps: identify and group 3-D object points into regions; separate buildings and houses from trees; trace region boundaries; regularize and simplify boundary polygons; construct complex

  2. 3-D Object Recognition from Point Cloud Data

    Science.gov (United States)

    Smith, W.; Walker, A. S.; Zhang, B.

    2011-09-01

    The market for real-time 3-D mapping includes not only traditional geospatial applications but also navigation of unmanned autonomous vehicles (UAVs). Massively parallel processes such as graphics processing unit (GPU) computing make real-time 3-D object recognition and mapping achievable. Geospatial technologies such as digital photogrammetry and GIS offer advanced capabilities to produce 2-D and 3-D static maps using UAV data. The goal is to develop real-time UAV navigation through increased automation. It is challenging for a computer to identify a 3-D object such as a car, a tree or a house, yet automatic 3-D object recognition is essential to increasing the productivity of geospatial data such as 3-D city site models. In the past three decades, researchers have used radiometric properties to identify objects in digital imagery with limited success, because these properties vary considerably from image to image. Consequently, our team has developed software that recognizes certain types of 3-D objects within 3-D point clouds. Although our software is developed for modeling, simulation and visualization, it has the potential to be valuable in robotics and UAV applications. The locations and shapes of 3-D objects such as buildings and trees are easily recognizable by a human from a brief glance at a representation of a point cloud such as terrain-shaded relief. The algorithms to extract these objects have been developed and require only the point cloud and minimal human inputs such as a set of limits on building size and a request to turn on a squaring option. The algorithms use both digital surface model (DSM) and digital elevation model (DEM), so software has also been developed to derive the latter from the former. The process continues through the following steps: identify and group 3-D object points into regions; separate buildings and houses from trees; trace region boundaries; regularize and simplify boundary polygons; construct complex roofs. Several case

  3. Short-term plasticity of visuo-haptic object recognition

    DEFF Research Database (Denmark)

    Kassuba, Tanja; Klinge, Corinna; Hölig, Cordula

    2014-01-01

    , the same stimulation gave rise to relative increases in activation during S2 processing in the right LO, left FG, bilateral IPS, and other regions previously associated with object recognition. Critically, the modality of S2 determined which regions were recruited after rTMS. Relative to sham rTMS, real r......TMS induced increased activations during crossmodal congruent matching in the left FG for haptic S2 and the temporal pole for visual S2. In addition, we found stronger activations for incongruent than congruent matching in the right anterior parahippocampus and middle frontal gyrus for crossmodal matching......Functional magnetic resonance imaging (fMRI) studies have provided ample evidence for the involvement of the lateral occipital cortex (LO), fusiform gyrus (FG), and intraparietal sulcus (IPS) in visuo-haptic object integration. Here we applied 30 min of sham (non-effective) or real offline 1 Hz...

  4. Fast and efficient indexing approach for object recognition

    Science.gov (United States)

    Hefnawy, Alaa; Mashali, Samia A.; Rashwan, Mohsen; Fikri, Magdi

    1999-08-01

    This paper introduces a fast and efficient indexing approach for both 2D and 3D model-based object recognition in the presence of rotation, translation, and scale variations of objects. The indexing entries are computed after preprocessing the data by Haar wavelet decomposition. The scheme is based on a unified image feature detection approach based on Zernike moments. A set of low level features, e.g. high precision edges, gray level corners, are estimated by a set of orthogonal Zernike moments, calculated locally around every image point. A high dimensional, highly descriptive indexing entries are then calculated based on the correlation of these local features and employed for fast access to the model database to generate hypotheses. A list of the most candidate models is then presented by evaluating the hypotheses. Experimental results are included to demonstrate the effectiveness of the proposed indexing approach.

  5. Flipping a Calculus Class: One Instructor's Experience

    Science.gov (United States)

    Palmer, Katrina

    2015-01-01

    This paper describes one instructor's experiences during a year of flipping four calculus classes. The first exploration attempts to understand student expectations of a math class and their preference towards a flipped classroom. The second examines success of students from a flipped classroom, and the last investigates relationships with student…

  6. Invariant recognition drives neural representations of action sequences.

    Directory of Open Access Journals (Sweden)

    Andrea Tacchetti

    2017-12-01

    Full Text Available Recognizing the actions of others from visual stimuli is a crucial aspect of human perception that allows individuals to respond to social cues. Humans are able to discriminate between similar actions despite transformations, like changes in viewpoint or actor, that substantially alter the visual appearance of a scene. This ability to generalize across complex transformations is a hallmark of human visual intelligence. Advances in understanding action recognition at the neural level have not always translated into precise accounts of the computational principles underlying what representations of action sequences are constructed by human visual cortex. Here we test the hypothesis that invariant action discrimination might fill this gap. Recently, the study of artificial systems for static object perception has produced models, Convolutional Neural Networks (CNNs, that achieve human level performance in complex discriminative tasks. Within this class, architectures that better support invariant object recognition also produce image representations that better match those implied by human and primate neural data. However, whether these models produce representations of action sequences that support recognition across complex transformations and closely follow neural representations of actions remains unknown. Here we show that spatiotemporal CNNs accurately categorize video stimuli into action classes, and that deliberate model modifications that improve performance on an invariant action recognition task lead to data representations that better match human neural recordings. Our results support our hypothesis that performance on invariant discrimination dictates the neural representations of actions computed in the brain. These results broaden the scope of the invariant recognition framework for understanding visual intelligence from perception of inanimate objects and faces in static images to the study of human perception of action sequences.

  7. Caffeine improves adult mice performance in the object recognition task and increases BDNF and TrkB independent on phospho-CREB immunocontent in the hippocampus.

    Science.gov (United States)

    Costa, Marcelo S; Botton, Paulo H; Mioranzza, Sabrina; Ardais, Ana Paula; Moreira, Julia D; Souza, Diogo O; Porciúncula, Lisiane O

    2008-09-01

    Caffeine is one of the most psychostimulants consumed all over the world that usually presents positive effects on cognition. In this study, effects of caffeine on mice performance in the object recognition task were tested in different intertrial intervals. In addition, it was analyzed the effects of caffeine on brain derived neurotrophic factor (BDNF) and its receptor, TrkB, immunocontent to try to establish a connection between the behavioral finding and BDNF, one of the neurotrophins strictly involved in memory and learning process. CF1 mice were treated during 4 consecutive days with saline (0.9g%, i.p.) or caffeine (10mg/kg, i.p., equivalent dose corresponding to 2-3 cups of coffee). Caffeine treatment was interrupted 24h before the object recognition task analysis. In the test session performed 15min after training session, caffeine-treated mice recognized more efficiently both the familiar and the novel object. In the test session performed 90min and 24h after training session, caffeine did not change the time spent in the familiar object but increased the object recognition index, when compared to control group. Western blotting analysis of hippocampus from caffeine-treated mice revealed an increase in BDNF and TrkB immunocontent, compared to their saline-matched controls. Phospho-CREB immunocontent did not change with caffeine treatment. Our results suggest that acute treatment with caffeine improves recognition memory, and this effect may be related to an increase of the BDNF and TrkB immunocontent in the hippocampus.

  8. The Role of Sensory-Motor Information in Object Recognition: Evidence from Category-Specific Visual Agnosia

    Science.gov (United States)

    Wolk, D.A.; Coslett, H.B.; Glosser, G.

    2005-01-01

    The role of sensory-motor representations in object recognition was investigated in experiments involving AD, a patient with mild visual agnosia who was impaired in the recognition of visually presented living as compared to non-living entities. AD named visually presented items for which sensory-motor information was available significantly more…

  9. Vision holds a greater share in visuo-haptic object recognition than touch

    DEFF Research Database (Denmark)

    Kassuba, Tanja; Klinge, Corinna; Hölig, Cordula

    2013-01-01

    approach of multisensory integration would predict that haptics as the less efficient sense for object recognition gains more from integrating additional visual information than vice versa. To test for asymmetries between vision and touch in visuo-haptic interactions, we measured regional changes in brain...... processed the target object, being more pronounced for haptic than visual targets. This preferential response of visuo-haptic regions indicates a modality-specific asymmetry in crossmodal matching of visual and haptic object features, suggesting a functional primacy of vision over touch in visuo...

  10. Nicotine enhances the reconsolidation of novel object recognition memory in rats.

    Science.gov (United States)

    Tian, Shaowen; Pan, Si; You, Yong

    2015-02-01

    There is increasing evidence that nicotine is involved in learning and memory. However, there are only few studies that have evaluated the relationship between nicotine and memory reconsolidation. In this study, we investigated the effects of nicotine on the reconsolidation of novel object recognition memory in rats. Behavior procedure involved four training phases: habituation (Days 1 and 2), sample (Day 3), reactivation (Day 4) and test (Day 6). Rats were injected with saline or nicotine (0.1, 0.2 and 0.4 mg/kg) immediately or 6h after reactivation. The discrimination index was used to assess memory performance and calculated as the difference in time exploring on the novel and familiar objects. Results showed that nicotine administration immediately but not 6 h after reactivation significantly enhanced memory performance of rats. Further results showed that the enhancing effect of nicotine on memory performance was dependent on memory reactivation, and was not attributed to the changes of the nonspecific responses (locomotor activity and anxiety level) 48 h after nicotine administration. The results suggest that post-reactivation nicotine administration enhances the reconsolidation of novel object recognition memory. Our present finding extends previous research on the nicotinic effects on learning and memory. Copyright © 2014 Elsevier Inc. All rights reserved.

  11. Rapid eye movement sleep deprivation disrupts consolidation but not reconsolidation of novel object recognition memory in rats.

    Science.gov (United States)

    Chen, Lin; Tian, Shaowen; Ke, Jie

    2014-03-20

    There is increasing evidence that sleep plays a critical role in memory consolidation. However, there are comparatively few studies that have assessed the relationship between sleep and memory reconsolidation. In the present study, we explored the effects of rapid eye movement sleep deprivation (RSD) on the consolidation (experiment 1) and reconsolidation (experiment 2) of novel object recognition memory in rats. In experiment 1 behavioral procedure involved two training phases: sample and test. Rats were subjected to 6h RSD starting either immediately after sample (exposed to 2 objects) or 6h later. In experiment 2 behavioral procedure involved three training phases: sample, reactivation and test. Rats were subjected to 6h RSD starting either immediately after reactivation (exposed to the same 2 sample objects to reactivate the memory trace) or 6h later. Results from experiment 1 showed that post-sample RSD from 0 to 6h but not 6 to 12h disrupted novel object recognition memory consolidation. However, we found that post-reactivation RSD whether from 0 to 6h or 6 to 12h had no effect on novel object recognition memory reconsolidation in experiment 2. The results indicated that RSD selectively disrupted consolidation of novel object recognition memory, suggesting a dissociation effect of RSD on consolidation and reconsolidation. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.

  12. Why does brain damage impair memory? A connectionist model of object recognition memory in perirhinal cortex.

    Science.gov (United States)

    Cowell, Rosemary A; Bussey, Timothy J; Saksida, Lisa M

    2006-11-22

    Object recognition is the canonical test of declarative memory, the type of memory putatively impaired after damage to the temporal lobes. Studies of object recognition memory have helped elucidate the anatomical structures involved in declarative memory, indicating a critical role for perirhinal cortex. We offer a mechanistic account of the effects of perirhinal cortex damage on object recognition memory, based on the assumption that perirhinal cortex stores representations of the conjunctions of visual features possessed by complex objects. Such representations are proposed to play an important role in memory when it is difficult to solve a task using representations of only individual visual features of stimuli, thought to be stored in regions of the ventral visual stream caudal to perirhinal cortex. The account is instantiated in a connectionist model, in which development of object representations with visual experience provides a mechanism for judgment of previous occurrence. We present simulations addressing the following empirical findings: (1) that impairments after damage to perirhinal cortex (modeled by removing the "perirhinal cortex" layer of the network) are exacerbated by lengthening the delay between presentation of to-be-remembered items and test, (2) that such impairments are also exacerbated by lengthening the list of to-be-remembered items, and (3) that impairments are revealed only when stimuli are trial unique rather than repeatedly presented. This study shows that it may be possible to account for object recognition impairments after damage to perirhinal cortex within a hierarchical, representational framework, in which complex conjunctive representations in perirhinal cortex play a critical role.

  13. Face Memory and Object Recognition in Children with High-Functioning Autism or Asperger Syndrome and in Their Parents

    Science.gov (United States)

    Kuusikko-Gauffin, Sanna; Jansson-Verkasalo, Eira; Carter, Alice; Pollock-Wurman, Rachel; Jussila, Katja; Mattila, Marja-Leena; Rahko, Jukka; Ebeling, Hanna; Pauls, David; Moilanen, Irma

    2011-01-01

    Children with Autism Spectrum Disorders (ASDs) have reported to have impairments in face, recognition and face memory, but intact object recognition and object memory. Potential abnormalities, in these fields at the family level of high-functioning children with ASD remains understudied despite, the ever-mounting evidence that ASDs are genetic and…

  14. Deep neural networks rival the representation of primate IT cortex for core visual object recognition.

    Directory of Open Access Journals (Sweden)

    Charles F Cadieu

    2014-12-01

    Full Text Available The primate visual system achieves remarkable visual object recognition performance even in brief presentations, and under changes to object exemplar, geometric transformations, and background variation (a.k.a. core visual object recognition. This remarkable performance is mediated by the representation formed in inferior temporal (IT cortex. In parallel, recent advances in machine learning have led to ever higher performing models of object recognition using artificial deep neural networks (DNNs. It remains unclear, however, whether the representational performance of DNNs rivals that of the brain. To accurately produce such a comparison, a major difficulty has been a unifying metric that accounts for experimental limitations, such as the amount of noise, the number of neural recording sites, and the number of trials, and computational limitations, such as the complexity of the decoding classifier and the number of classifier training examples. In this work, we perform a direct comparison that corrects for these experimental limitations and computational considerations. As part of our methodology, we propose an extension of "kernel analysis" that measures the generalization accuracy as a function of representational complexity. Our evaluations show that, unlike previous bio-inspired models, the latest DNNs rival the representational performance of IT cortex on this visual object recognition task. Furthermore, we show that models that perform well on measures of representational performance also perform well on measures of representational similarity to IT, and on measures of predicting individual IT multi-unit responses. Whether these DNNs rely on computational mechanisms similar to the primate visual system is yet to be determined, but, unlike all previous bio-inspired models, that possibility cannot be ruled out merely on representational performance grounds.

  15. Deteksi Penyakit Dengue Hemorrhagic Fever dengan Pendekatan One Class Classification

    Directory of Open Access Journals (Sweden)

    Zida Ziyan Azkiya

    2017-10-01

    Full Text Available Two class classification problem maps input into two target classes. In certain cases, training data is available only in the form of a single class, as in the case of Dengue Hemorrhagic Fever (DHF patients, where only data of positive patients is available. In this paper, we report our experiment in building a classification model for detecting DHF infection using One Class Classification (OCC approach. Data from this study is sourced from laboratory tests of patients with dengue fever. The OCC methods compared are One-Class Support Vector Machine and One-Class K-Means. The result shows SVM method obtained precision value = 1.0, recall = 0.993, f-1 score = 0.997, and accuracy of 99.7% while the K-Means method obtained precision value = 0.901, recall = 0.973, f- 1 score = 0.936, and accuracy of 93.3%. This indicates that the SVM method is slightly superior to K-Means for One-Class Classification of DHF patients.

  16. Mice deficient for striatal Vesicular Acetylcholine Transporter (VAChT) display impaired short-term but normal long-term object recognition memory.

    Science.gov (United States)

    Palmer, Daniel; Creighton, Samantha; Prado, Vania F; Prado, Marco A M; Choleris, Elena; Winters, Boyer D

    2016-09-15

    Substantial evidence implicates Acetylcholine (ACh) in the acquisition of object memories. While most research has focused on the role of the cholinergic basal forebrain and its cortical targets, there are additional cholinergic networks that may contribute to object recognition. The striatum contains an independent cholinergic network comprised of interneurons. In the current study, we investigated the role of this cholinergic signalling in object recognition using mice deficient for Vesicular Acetylcholine Transporter (VAChT) within interneurons of the striatum. We tested whether these striatal VAChT(D2-Cre-flox/flox) mice would display normal short-term (5 or 15min retention delay) and long-term (3h retention delay) object recognition memory. In a home cage object recognition task, male and female VAChT(D2-Cre-flox/flox) mice were impaired selectively with a 15min retention delay. When tested on an object location task, VAChT(D2-Cre-flox/flox) mice displayed intact spatial memory. Finally, when object recognition was tested in a Y-shaped apparatus, designed to minimize the influence of spatial and contextual cues, only females displayed impaired recognition with a 5min retention delay, but when males were challenged with a 15min retention delay, they were also impaired; neither males nor females were impaired with the 3h delay. The pattern of results suggests that striatal cholinergic transmission plays a role in the short-term memory for object features, but not spatial location. Copyright © 2016 Elsevier B.V. All rights reserved.

  17. The Role of Fixation and Visual Attention in Object Recognition.

    Science.gov (United States)

    1995-01-01

    computers", Technical Report, Aritificial Intelligence Lab, M.I. T., AI-Memo-915, June 1986. [29] D.P. Huttenlocher and S.Ullman, "Object Recognition Using...attention", Technical Report, Aritificial Intelligence Lab, M.I. T., AI-memo-770, Jan 1984. [35] E.Krotkov, K. Henriksen and R. Kories, "Stereo...MIT Artificial Intelligence Laboratory [ PCTBTBimON STATEMENT X \\ Afipioved tor puciic reieo*«* \\ »?*•;.., jDi*tiibutK» U»lisut»d* 19951004

  18. Episodic Short-Term Recognition Requires Encoding into Visual Working Memory: Evidence from Probe Recognition after Letter Report.

    Science.gov (United States)

    Poth, Christian H; Schneider, Werner X

    2016-01-01

    Human vision is organized in discrete processing episodes (e.g., eye fixations or task-steps). Object information must be transmitted across episodes to enable episodic short-term recognition: recognizing whether a current object has been seen in a previous episode. We ask whether episodic short-term recognition presupposes that objects have been encoded into capacity-limited visual working memory (VWM), which retains visual information for report. Alternatively, it could rely on the activation of visual features or categories that occurs before encoding into VWM. We assessed the dependence of episodic short-term recognition on VWM by a new paradigm combining letter report and probe recognition. Participants viewed displays of 10 letters and reported as many as possible after a retention interval (whole report). Next, participants viewed a probe letter and indicated whether it had been one of the 10 letters (probe recognition). In Experiment 1, probe recognition was more accurate for letters that had been encoded into VWM (reported letters) compared with non-encoded letters (non-reported letters). Interestingly, those letters that participants reported in their whole report had been near to one another within the letter displays. This suggests that the encoding into VWM proceeded in a spatially clustered manner. In Experiment 2, participants reported only one of 10 letters (partial report) and probes either referred to this letter, to letters that had been near to it, or far from it. Probe recognition was more accurate for near than for far letters, although none of these letters had to be reported. These findings indicate that episodic short-term recognition is constrained to a small number of simultaneously presented objects that have been encoded into VWM.

  19. Episodic Short-Term Recognition Requires Encoding into Visual Working Memory: Evidence from Probe Recognition after Letter Report

    Directory of Open Access Journals (Sweden)

    Christian H. Poth

    2016-09-01

    Full Text Available Human vision is organized in discrete processing episodes (e.g. eye fixations or task-steps. Object information must be transmitted across episodes to enable episodic short-term recognition: recognizing whether a current object has been seen in a previous episode. We ask whether episodic short-term recognition presupposes that objects have been encoded into capacity-limited visual working memory (VWM, which retains visual information for report. Alternatively, it could rely on the activation of visual features or categories that occurs before encoding into VWM. We assessed the dependence of episodic short-term recognition on VWM by a new paradigm combining letter report and probe recognition. Participants viewed displays of ten letters and reported as many as possible after a retention interval (whole report. Next, participants viewed a probe letter and indicated whether it had been one of the ten letters (probe recognition. In Experiment 1, probe recognition was more accurate for letters that had been encoded into VWM (reported letters compared with non-encoded letters (non-reported letters. Interestingly, those letters that participants reported in their whole report had been near to one another within the letter displays. This suggests that the encoding into VWM proceeded in a spatially clustered manner. In Experiment 2 participants reported only one of ten letters (partial report and probes either referred to this letter, to letters that had been near to it, or far from it. Probe recognition was more accurate for near than for far letters, although none of these letters had to be reported. These findings indicate that episodic short-term recognition is constrained to a small number of simultaneously presented objects that have been encoded into VWM.

  20. Modelling of anisotropic compact stars of embedding class one

    Energy Technology Data Exchange (ETDEWEB)

    Bhar, Piyali [Government General Degree College, Department of Mathematics, Singur, Hooghly, West Bengal (India); Maurya, S.K. [University of Nizwa, Department of Mathematical and Physical Sciences, College of Arts and Science, Nizwa (Oman); Gupta, Y.K. [Raj Kumar Goel Institute of Technology, Department of Mathematics, Ghaziabad, U.P. (India); Manna, Tuhina [St. Xavier' s College, Department of Commerce (Evening), Kolkata, West Bengal (India)

    2016-10-15

    In the present article, we have constructed static anisotropic compact star models of Einstein field equations for the spherical symmetric metric of embedding class one. By assuming the particular form of the metric function ν, we have solved the Einstein field equations for anisotropic matter distribution. The anisotropic models represent the realistic compact objects such as SAX J 1808.4-3658 (SS1), Her X-1, Vela X-12, PSR J1614-2230 and Cen X-3. We have reported our results in details for the compact star Her X-1 on the ground of physical properties such as pressure, density, velocity of sound, energy conditions, TOV equation and red-shift etc. Along with these, we have also discussed about the stability of the compact star models. Finally we made a comparison between our anisotropic stars with the realistic objects on the key aspects as central density, central pressure, compactness and surface red-shift. (orig.)

  1. Creating Objects and Object Categories for Studying Perception and Perceptual Learning

    Science.gov (United States)

    Hauffen, Karin; Bart, Eugene; Brady, Mark; Kersten, Daniel; Hegdé, Jay

    2012-01-01

    In order to quantitatively study object perception, be it perception by biological systems or by machines, one needs to create objects and object categories with precisely definable, preferably naturalistic, properties1. Furthermore, for studies on perceptual learning, it is useful to create novel objects and object categories (or object classes) with such properties2. Many innovative and useful methods currently exist for creating novel objects and object categories3-6 (also see refs. 7,8). However, generally speaking, the existing methods have three broad types of shortcomings. First, shape variations are generally imposed by the experimenter5,9,10, and may therefore be different from the variability in natural categories, and optimized for a particular recognition algorithm. It would be desirable to have the variations arise independently of the externally imposed constraints. Second, the existing methods have difficulty capturing the shape complexity of natural objects11-13. If the goal is to study natural object perception, it is desirable for objects and object categories to be naturalistic, so as to avoid possible confounds and special cases. Third, it is generally hard to quantitatively measure the available information in the stimuli created by conventional methods. It would be desirable to create objects and object categories where the available information can be precisely measured and, where necessary, systematically manipulated (or 'tuned'). This allows one to formulate the underlying object recognition tasks in quantitative terms. Here we describe a set of algorithms, or methods, that meet all three of the above criteria. Virtual morphogenesis (VM) creates novel, naturalistic virtual 3-D objects called 'digital embryos' by simulating the biological process of embryogenesis14. Virtual phylogenesis (VP) creates novel, naturalistic object categories by simulating the evolutionary process of natural selection9,12,13. Objects and object categories created

  2. Bayesian feature weighting for unsupervised learning, with application to object recognition

    OpenAIRE

    Carbonetto , Peter; De Freitas , Nando; Gustafson , Paul; Thompson , Natalie

    2003-01-01

    International audience; We present a method for variable selection/weighting in an unsupervised learning context using Bayesian shrinkage. The basis for the model parameters and cluster assignments can be computed simultaneous using an efficient EM algorithm. Applying our Bayesian shrinkage model to a complex problem in object recognition (Duygulu, Barnard, de Freitas and Forsyth 2002), our experiments yied good results.

  3. Extracting UML Class Diagrams from Object-Oriented Fortran: ForUML

    Directory of Open Access Journals (Sweden)

    Aziz Nanthaamornphong

    2015-01-01

    Full Text Available Many scientists who implement computational science and engineering software have adopted the object-oriented (OO Fortran paradigm. One of the challenges faced by OO Fortran developers is the inability to obtain high level software design descriptions of existing applications. Knowledge of the overall software design is not only valuable in the absence of documentation, it can also serve to assist developers with accomplishing different tasks during the software development process, especially maintenance and refactoring. The software engineering community commonly uses reverse engineering techniques to deal with this challenge. A number of reverse engineering-based tools have been proposed, but few of them can be applied to OO Fortran applications. In this paper, we propose a software tool to extract unified modeling language (UML class diagrams from Fortran code. The UML class diagram facilitates the developers' ability to examine the entities and their relationships in the software system. The extracted diagrams enhance software maintenance and evolution. The experiments carried out to evaluate the proposed tool show its accuracy and a few of the limitations.

  4. Marked Object Recognition Multitouch Screen Printed Touchpad for Interactive Applications.

    Science.gov (United States)

    Nunes, Jivago Serrado; Castro, Nelson; Gonçalves, Sergio; Pereira, Nélson; Correia, Vitor; Lanceros-Mendez, Senentxu

    2017-12-01

    The market for interactive platforms is rapidly growing, and touchscreens have been incorporated in an increasing number of devices. Thus, the area of smart objects and devices is strongly increasing by adding interactive touch and multimedia content, leading to new uses and capabilities. In this work, a flexible screen printed sensor matrix is fabricated based on silver ink in a polyethylene terephthalate (PET) substrate. Diamond shaped capacitive electrodes coupled with conventional capacitive reading electronics enables fabrication of a highly functional capacitive touchpad, and also allows for the identification of marked objects. For the latter, the capacitive signatures are identified by intersecting points and distances between them. Thus, this work demonstrates the applicability of a low cost method using royalty-free geometries and technologies for the development of flexible multitouch touchpads for the implementation of interactive and object recognition applications.

  5. Marked Object Recognition Multitouch Screen Printed Touchpad for Interactive Applications

    Directory of Open Access Journals (Sweden)

    Jivago Serrado Nunes

    2017-12-01

    Full Text Available The market for interactive platforms is rapidly growing, and touchscreens have been incorporated in an increasing number of devices. Thus, the area of smart objects and devices is strongly increasing by adding interactive touch and multimedia content, leading to new uses and capabilities. In this work, a flexible screen printed sensor matrix is fabricated based on silver ink in a polyethylene terephthalate (PET substrate. Diamond shaped capacitive electrodes coupled with conventional capacitive reading electronics enables fabrication of a highly functional capacitive touchpad, and also allows for the identification of marked objects. For the latter, the capacitive signatures are identified by intersecting points and distances between them. Thus, this work demonstrates the applicability of a low cost method using royalty-free geometries and technologies for the development of flexible multitouch touchpads for the implementation of interactive and object recognition applications.

  6. The active blind spot camera: hard real-time recognition of moving objects from a moving camera

    OpenAIRE

    Van Beeck, Kristof; Goedemé, Toon; Tuytelaars, Tinne

    2014-01-01

    This PhD research focuses on visual object recognition under specific demanding conditions. The object to be recognized as well as the camera move, and the time available for the recognition task is extremely short. This generic problem is applied here on a specific problem: the active blind spot camera. Statistics show a large number of accidents with trucks are related to the so-called blind spot, the area around the vehicle in which vulnerable road users are hard to perceive by the truck d...

  7. Invariant object recognition based on the generalized discrete radon transform

    Science.gov (United States)

    Easley, Glenn R.; Colonna, Flavia

    2004-04-01

    We introduce a method for classifying objects based on special cases of the generalized discrete Radon transform. We adjust the transform and the corresponding ridgelet transform by means of circular shifting and a singular value decomposition (SVD) to obtain a translation, rotation and scaling invariant set of feature vectors. We then use a back-propagation neural network to classify the input feature vectors. We conclude with experimental results and compare these with other invariant recognition methods.

  8. Dependent Classes

    DEFF Research Database (Denmark)

    Gasiunas, Vaidas; Mezini, Mira; Ostermann, Klaus

    2007-01-01

    of dependent classes and a machine-checked type soundness proof in Isabelle/HOL [29], the first of this kind for a language with virtual classes and path-dependent types. [29] T.Nipkow, L.C. Poulson, and M. Wenzel. Isabelle/HOL -- A Proof Assistant for Higher-Order Logic, volume 2283 of LNCS, Springer, 2002......Virtual classes allow nested classes to be refined in subclasses. In this way nested classes can be seen as dependent abstractions of the objects of the enclosing classes. Expressing dependency via nesting, however, has two limitations: Abstractions that depend on more than one object cannot...... be modeled and a class must know all classes that depend on its objects. This paper presents dependent classes, a generalization of virtual classes that expresses similar semantics by parameterization rather than by nesting. This increases expressivity of class variations as well as the flexibility...

  9. Classifying objects in LWIR imagery via CNNs

    Science.gov (United States)

    Rodger, Iain; Connor, Barry; Robertson, Neil M.

    2016-10-01

    The aim of the presented work is to demonstrate enhanced target recognition and improved false alarm rates for a mid to long range detection system, utilising a Long Wave Infrared (LWIR) sensor. By exploiting high quality thermal image data and recent techniques in machine learning, the system can provide automatic target recognition capabilities. A Convolutional Neural Network (CNN) is trained and the classifier achieves an overall accuracy of > 95% for 6 object classes related to land defence. While the highly accurate CNN struggles to recognise long range target classes, due to low signal quality, robust target discrimination is achieved for challenging candidates. The overall performance of the methodology presented is assessed using human ground truth information, generating classifier evaluation metrics for thermal image sequences.

  10. Glucocorticoid effects on object recognition memory require training-associated emotional arousal

    OpenAIRE

    Okuda, Shoki; Roozendaal, Benno; McGaugh, James L.

    2004-01-01

    Considerable evidence implicates glucocorticoid hormones in the regulation of memory consolidation and memory retrieval. The present experiments investigated whether the influence of these hormones on memory depends on the level of emotional arousal induced by the training experience. We investigated this issue in male Sprague–Dawley rats by examining the effects of immediate posttraining systemic injections of the glucocorticoid corticosterone on object recognition memory under two condition...

  11. Visual recognition of age class and preference for infantile features: implications for species-specific vs universal cognitive traits in primates.

    Directory of Open Access Journals (Sweden)

    Anna Sato

    Full Text Available Despite not knowing the exact age of individuals, humans can estimate their rough age using age-related physical features. Nonhuman primates show some age-related physical features; however, the cognitive traits underlying their recognition of age class have not been revealed. Here, we tested the ability of two species of Old World monkey, Japanese macaques (JM and Campbell's monkeys (CM, to spontaneously discriminate age classes using visual paired comparison (VPC tasks based on the two distinct categories of infant and adult images. First, VPCs were conducted in JM subjects using conspecific JM stimuli. When analyzing the side of the first look, JM subjects significantly looked more often at novel images. Based on analyses of total looking durations, JM subjects looked at a novel infant image longer than they looked at a familiar adult image, suggesting the ability to spontaneously discriminate between the two age classes and a preference for infant over adult images. Next, VPCs were tested in CM subjects using heterospecific JM stimuli. CM subjects showed no difference in the side of their first look, but looked at infant JM images longer than they looked at adult images; the fact that CMs were totally naïve to JMs suggested that the attractiveness of infant images transcends species differences. This is the first report of visual age class recognition and a preference for infant over adult images in nonhuman primates. Our results suggest not only species-specific processing for age class recognition but also the evolutionary origins of the instinctive human perception of baby cuteness schema, proposed by the ethologist Konrad Lorenz.

  12. Intracellular Zn(2+) signaling in the dentate gyrus is required for object recognition memory.

    Science.gov (United States)

    Takeda, Atsushi; Tamano, Haruna; Ogawa, Taisuke; Takada, Shunsuke; Nakamura, Masatoshi; Fujii, Hiroaki; Ando, Masaki

    2014-11-01

    The role of perforant pathway-dentate granule cell synapses in cognitive behavior was examined focusing on synaptic Zn(2+) signaling in the dentate gyrus. Object recognition memory was transiently impaired when extracellular Zn(2+) levels were decreased by injection of clioquinol and N,N,N',N'-tetrakis-(2-pyridylmethyl) ethylendediamine. To pursue the effect of the loss and/or blockade of Zn(2+) signaling in dentate granule cells, ZnAF-2DA (100 pmol, 0.1 mM/1 µl), an intracellular Zn(2+) chelator, was locally injected into the dentate molecular layer of rats. ZnAF-2DA injection, which was estimated to chelate intracellular Zn(2+) signaling only in the dentate gyrus, affected object recognition memory 1 h after training without affecting intracellular Ca(2+) signaling in the dentate molecular layer. In vivo dentate gyrus long-term potentiation (LTP) was affected under the local perfusion of the recording region (the dentate granule cell layer) with 0.1 mM ZnAF-2DA, but not with 1-10 mM CaEDTA, an extracellular Zn(2+) chelator, suggesting that the blockade of intracellular Zn(2+) signaling in dentate granule cells affects dentate gyrus LTP. The present study demonstrates that intracellular Zn(2+) signaling in the dentate gyrus is required for object recognition memory, probably via dentate gyrus LTP expression. Copyright © 2014 Wiley Periodicals, Inc.

  13. Chronic prenatal caffeine exposure impairs novel object recognition and radial arm maze behaviors in adult rats.

    Science.gov (United States)

    Soellner, Deborah E; Grandys, Theresa; Nuñez, Joseph L

    2009-12-14

    In this report, we demonstrate that chronic prenatal exposure to a moderate dose of caffeine disrupts novel object recognition and radial arm maze behaviors in adult male and female rats. Pregnant dams were administered either tap water or 75 mg/L caffeinated tap water throughout gestation. Oral self-administration in the drinking water led to an approximate maternal intake of 10mg/kg/day, equivalent to 2-3 cups of coffee/day in humans based on a metabolic body weight conversion. In adulthood, the offspring underwent testing on novel object recognition, radial arm maze, and Morris water maze tasks. Prenatal caffeine exposure was found to impair 24-h memory retention in the novel object recognition task and impair both working and reference memory in the radial arm maze. However, prenatal caffeine exposure did not alter Morris water maze performance in either a simple water maze procedure or in an advanced water maze procedure that included reversal and working memory paradigms. These findings demonstrate that chronic oral intake of caffeine throughout gestation can alter adult cognitive behaviors in rats.

  14. Biased figure-ground assignment affects conscious object recognition in spatial neglect.

    Science.gov (United States)

    Eramudugolla, Ranmalee; Driver, Jon; Mattingley, Jason B

    2010-09-01

    Unilateral spatial neglect is a disorder of attention and spatial representation, in which early visual processes such as figure-ground segmentation have been assumed to be largely intact. There is evidence, however, that the spatial attention bias underlying neglect can bias the segmentation of a figural region from its background. Relatively few studies have explicitly examined the effect of spatial neglect on processing the figures that result from such scene segmentation. Here, we show that a neglect patient's bias in figure-ground segmentation directly influences his conscious recognition of these figures. By varying the relative salience of figural and background regions in static, two-dimensional displays, we show that competition between elements in such displays can modulate a neglect patient's ability to recognise parsed figures in a scene. The findings provide insight into the interaction between scene segmentation, explicit object recognition, and attention.

  15. Humans and Deep Networks Largely Agree on Which Kinds of Variation Make Object Recognition Harder.

    Science.gov (United States)

    Kheradpisheh, Saeed R; Ghodrati, Masoud; Ganjtabesh, Mohammad; Masquelier, Timothée

    2016-01-01

    View-invariant object recognition is a challenging problem that has attracted much attention among the psychology, neuroscience, and computer vision communities. Humans are notoriously good at it, even if some variations are presumably more difficult to handle than others (e.g., 3D rotations). Humans are thought to solve the problem through hierarchical processing along the ventral stream, which progressively extracts more and more invariant visual features. This feed-forward architecture has inspired a new generation of bio-inspired computer vision systems called deep convolutional neural networks (DCNN), which are currently the best models for object recognition in natural images. Here, for the first time, we systematically compared human feed-forward vision and DCNNs at view-invariant object recognition task using the same set of images and controlling the kinds of transformation (position, scale, rotation in plane, and rotation in depth) as well as their magnitude, which we call "variation level." We used four object categories: car, ship, motorcycle, and animal. In total, 89 human subjects participated in 10 experiments in which they had to discriminate between two or four categories after rapid presentation with backward masking. We also tested two recent DCNNs (proposed respectively by Hinton's group and Zisserman's group) on the same tasks. We found that humans and DCNNs largely agreed on the relative difficulties of each kind of variation: rotation in depth is by far the hardest transformation to handle, followed by scale, then rotation in plane, and finally position (much easier). This suggests that DCNNs would be reasonable models of human feed-forward vision. In addition, our results show that the variation levels in rotation in depth and scale strongly modulate both humans' and DCNNs' recognition performances. We thus argue that these variations should be controlled in the image datasets used in vision research.

  16. Humans and deep networks largely agree on which kinds of variation make object recognition harder

    Directory of Open Access Journals (Sweden)

    Saeed Reza Kheradpisheh

    2016-08-01

    Full Text Available View-invariant object recognition is a challenging problem that has attracted much attention among the psychology, neuroscience, and computer vision communities. Humans are notoriously good at it, even if some variations are presumably more difficult to handle than others (e.g. 3D rotations. Humans are thought to solve the problem through hierarchical processing along the ventral stream, which progressively extracts more and more invariant visual features. This feed-forward architecture has inspired a new generation of bio-inspired computer vision systems called deep convolutional neural networks (DCNN, which are currently the best models for object recognition in natural images. Here, for the first time, we systematically compared human feed-forward vision and DCNNs at view-invariant object recognition task using the same set of images and controlling the kinds of transformation (position, scale, rotation in plane, and rotation in depth as well as their magnitude, which we call variation level. We used four object categories: car, ship, motorcycle, and animal. In total, 89 human subjects participated in 10 experiments in which they had to discriminate between two or four categories after rapid presentation with backward masking. We also tested two recent DCNNs (proposed respectively by Hinton's group and Zisserman's group on the same tasks. We found that humans and DCNNs largely agreed on the relative difficulties of each kind of variation: rotation in depth is by far the hardest transformation to handle, followed by scale, then rotation in plane, and finally position (much easier. This suggests that DCNNs would be reasonable models of human feed-forward vision. In addition, our results show that the variation levels in rotation in depth and scale strongly modulate both humans' and DCNNs' recognition performances. We thus argue that these variations should be controlled in the image datasets used in vision research.

  17. Object detection and recognition in digital images theory and practice

    CERN Document Server

    Cyganek, Boguslaw

    2013-01-01

    Object detection, tracking and recognition in images are key problems in computer vision. This book provides the reader with a balanced treatment between the theory and practice of selected methods in these areas to make the book accessible to a range of researchers, engineers, developers and postgraduate students working in computer vision and related fields. Key features: Explains the main theoretical ideas behind each method (which are augmented with a rigorous mathematical derivation of the formulas), their implementation (in C++) and demonstrated working in real applications.

  18. Remembering the object you fear: brain potentials during recognition of spiders in spider-fearful individuals.

    Science.gov (United States)

    Michalowski, Jaroslaw M; Weymar, Mathias; Hamm, Alfons O

    2014-01-01

    In the present study we investigated long-term memory for unpleasant, neutral and spider pictures in 15 spider-fearful and 15 non-fearful control individuals using behavioral and electrophysiological measures. During the initial (incidental) encoding, pictures were passively viewed in three separate blocks and were subsequently rated for valence and arousal. A recognition memory task was performed one week later in which old and new unpleasant, neutral and spider pictures were presented. Replicating previous results, we found enhanced memory performance and higher confidence ratings for unpleasant when compared to neutral materials in both animal fearful individuals and controls. When compared to controls high animal fearful individuals also showed a tendency towards better memory accuracy and significantly higher confidence during recognition of spider pictures, suggesting that memory of objects prompting specific fear is also facilitated in fearful individuals. In line, spider-fearful but not control participants responded with larger ERP positivity for correctly recognized old when compared to correctly rejected new spider pictures, thus showing the same effects in the neural signature of emotional memory for feared objects that were already discovered for other emotional materials. The increased fear memory for phobic materials observed in the present study in spider-fearful individuals might result in an enhanced fear response and reinforce negative beliefs aggravating anxiety symptomatology and hindering recovery.

  19. Short- and long-term effects of nicotine and the histone deacetylase inhibitor phenylbutyrate on novel object recognition in zebrafish.

    Science.gov (United States)

    Faillace, M P; Pisera-Fuster, A; Medrano, M P; Bejarano, A C; Bernabeu, R O

    2017-03-01

    Zebrafish have a sophisticated color- and shape-sensitive visual system, so we examined color cue-based novel object recognition in zebrafish. We evaluated preference in the absence or presence of drugs that affect attention and memory retention in rodents: nicotine and the histone deacetylase inhibitor (HDACi) phenylbutyrate (PhB). The objective of this study was to evaluate whether nicotine and PhB affect innate preferences of zebrafish for familiar and novel objects after short- and long-retention intervals. We developed modified object recognition (OR) tasks using neutral novel and familiar objects in different colors. We also tested objects which differed with respect to the exploratory behavior they elicited from naïve zebrafish. Zebrafish showed an innate preference for exploring red or green objects rather than yellow or blue objects. Zebrafish were better at discriminating color changes than changes in object shape or size. Nicotine significantly enhanced or changed short-term innate novel object preference whereas PhB had similar effects when preference was assessed 24 h after training. Analysis of other zebrafish behaviors corroborated these results. Zebrafish were innately reluctant or prone to explore colored novel objects, so drug effects on innate preference for objects can be evaluated changing the color of objects with a simple geometry. Zebrafish exhibited recognition memory for novel objects with similar innate significance. Interestingly, nicotine and PhB significantly modified innate object preference.

  20. Depth Value Pre-Processing for Accurate Transfer Learning Based RGB-D Object Recognition

    DEFF Research Database (Denmark)

    Aakerberg, Andreas; Nasrollahi, Kamal; Rasmussen, Christoffer Bøgelund

    2017-01-01

    of an existing deeplearning based RGB-D object recognition model, namely the FusionNet proposed by Eitel et al. First, we showthat encoding the depth values as colorized surface normals is beneficial, when the model is initialized withweights learned from training on ImageNet data. Additionally, we show...

  1. Improving protein fold recognition and structural class prediction accuracies using physicochemical properties of amino acids.

    Science.gov (United States)

    Raicar, Gaurav; Saini, Harsh; Dehzangi, Abdollah; Lal, Sunil; Sharma, Alok

    2016-08-07

    Predicting the three-dimensional (3-D) structure of a protein is an important task in the field of bioinformatics and biological sciences. However, directly predicting the 3-D structure from the primary structure is hard to achieve. Therefore, predicting the fold or structural class of a protein sequence is generally used as an intermediate step in determining the protein's 3-D structure. For protein fold recognition (PFR) and structural class prediction (SCP), two steps are required - feature extraction step and classification step. Feature extraction techniques generally utilize syntactical-based information, evolutionary-based information and physicochemical-based information to extract features. In this study, we explore the importance of utilizing the physicochemical properties of amino acids for improving PFR and SCP accuracies. For this, we propose a Forward Consecutive Search (FCS) scheme which aims to strategically select physicochemical attributes that will supplement the existing feature extraction techniques for PFR and SCP. An exhaustive search is conducted on all the existing 544 physicochemical attributes using the proposed FCS scheme and a subset of physicochemical attributes is identified. Features extracted from these selected attributes are then combined with existing syntactical-based and evolutionary-based features, to show an improvement in the recognition and prediction performance on benchmark datasets. Copyright © 2016 Elsevier Ltd. All rights reserved.

  2. Brain dynamics of upstream perceptual processes leading to visual object recognition: a high density ERP topographic mapping study.

    Science.gov (United States)

    Schettino, Antonio; Loeys, Tom; Delplanque, Sylvain; Pourtois, Gilles

    2011-04-01

    Recent studies suggest that visual object recognition is a proactive process through which perceptual evidence accumulates over time before a decision can be made about the object. However, the exact electrophysiological correlates and time-course of this complex process remain unclear. In addition, the potential influence of emotion on this process has not been investigated yet. We recorded high density EEG in healthy adult participants performing a novel perceptual recognition task. For each trial, an initial blurred visual scene was first shown, before the actual content of the stimulus was gradually revealed by progressively adding diagnostic high spatial frequency information. Participants were asked to stop this stimulus sequence as soon as they could correctly perform an animacy judgment task. Behavioral results showed that participants reliably gathered perceptual evidence before recognition. Furthermore, prolonged exploration times were observed for pleasant, relative to either neutral or unpleasant scenes. ERP results showed distinct effects starting at 280 ms post-stimulus onset in distant brain regions during stimulus processing, mainly characterized by: (i) a monotonic accumulation of evidence, involving regions of the posterior cingulate cortex/parahippocampal gyrus, and (ii) true categorical recognition effects in medial frontal regions, including the dorsal anterior cingulate cortex. These findings provide evidence for the early involvement, following stimulus onset, of non-overlapping brain networks during proactive processes eventually leading to visual object recognition. Copyright © 2011 Elsevier Inc. All rights reserved.

  3. Differential Roles for "Nr4a1" and "Nr4a2" in Object Location vs. Object Recognition Long-Term Memory

    Science.gov (United States)

    McNulty, Susan E.; Barrett, Ruth M.; Vogel-Ciernia, Annie; Malvaez, Melissa; Hernandez, Nicole; Davatolhagh, M. Felicia; Matheos, Dina P.; Schiffman, Aaron; Wood, Marcelo A.

    2012-01-01

    "Nr4a1" and "Nr4a2" are transcription factors and immediate early genes belonging to the nuclear receptor Nr4a family. In this study, we examine their role in long-term memory formation for object location and object recognition. Using siRNA to block expression of either "Nr4a1" or "Nr4a2", we found that "Nr4a2" is necessary for both long-term…

  4. Perirhinal Cortex Resolves Feature Ambiguity in Configural Object Recognition and Perceptual Oddity Tasks

    Science.gov (United States)

    Bartko, Susan J.; Winters, Boyer D.; Cowell, Rosemary A.; Saksida, Lisa M.; Bussey, Timothy J.

    2007-01-01

    The perirhinal cortex (PRh) has a well-established role in object recognition memory. More recent studies suggest that PRh is also important for two-choice visual discrimination tasks. Specifically, it has been suggested that PRh contains conjunctive representations that help resolve feature ambiguity, which occurs when a task cannot easily be…

  5. Coarse-coded higher-order neural networks for PSRI object recognition. [position, scale, and rotation invariant

    Science.gov (United States)

    Spirkovska, Lilly; Reid, Max B.

    1993-01-01

    A higher-order neural network (HONN) can be designed to be invariant to changes in scale, translation, and inplane rotation. Invariances are built directly into the architecture of a HONN and do not need to be learned. Consequently, fewer training passes and a smaller training set are required to learn to distinguish between objects. The size of the input field is limited, however, because of the memory required for the large number of interconnections in a fully connected HONN. By coarse coding the input image, the input field size can be increased to allow the larger input scenes required for practical object recognition problems. We describe a coarse coding technique and present simulation results illustrating its usefulness and its limitations. Our simulations show that a third-order neural network can be trained to distinguish between two objects in a 4096 x 4096 pixel input field independent of transformations in translation, in-plane rotation, and scale in less than ten passes through the training set. Furthermore, we empirically determine the limits of the coarse coding technique in the object recognition domain.

  6. The medial prefrontal cortex-lateral entorhinal cortex circuit is essential for episodic-like memory and associative object-recognition.

    Science.gov (United States)

    Chao, Owen Y; Huston, Joseph P; Li, Jay-Shake; Wang, An-Li; de Souza Silva, Maria A

    2016-05-01

    The prefrontal cortex directly projects to the lateral entorhinal cortex (LEC), an important substrate for engaging item-associated information and relaying the information to the hippocampus. Here we ask to what extent the communication between the prefrontal cortex and LEC is critically involved in the processing of episodic-like memory. We applied a disconnection procedure to test whether the interaction between the medial prefrontal cortex (mPFC) and LEC is essential for the expression of recognition memory. It was found that male rats that received unilateral NMDA lesions of the mPFC and LEC in the same hemisphere, exhibited intact episodic-like (what-where-when) and object-recognition memories. When these lesions were placed in the opposite hemispheres (disconnection), episodic-like and associative memories for object identity, location and context were impaired. However, the disconnection did not impair the components of episodic memory, namely memory for novel object (what), object place (where) and temporal order (when), per se. Thus, the present findings suggest that the mPFC and LEC are a critical part of a neural circuit that underlies episodic-like and associative object-recognition memory. © 2015 Wiley Periodicals, Inc.

  7. DATA Act File B Object Class and Program Activity - Social Security

    Data.gov (United States)

    Social Security Administration — The DATA Act Information Model Schema Reporting Submission Specification File B. File B includes the agency object class and program activity detail obligation and...

  8. Authentication of bee pollen grains in bright-field microscopy by combining one-class classification techniques and image processing.

    Science.gov (United States)

    Chica, Manuel

    2012-11-01

    A novel method for authenticating pollen grains in bright-field microscopic images is presented in this work. The usage of this new method is clear in many application fields such as bee-keeping sector, where laboratory experts need to identify fraudulent bee pollen samples against local known pollen types. Our system is based on image processing and one-class classification to reject unknown pollen grain objects. The latter classification technique allows us to tackle the major difficulty of the problem, the existence of many possible fraudulent pollen types, and the impossibility of modeling all of them. Different one-class classification paradigms are compared to study the most suitable technique for solving the problem. In addition, feature selection algorithms are applied to reduce the complexity and increase the accuracy of the models. For each local pollen type, a one-class classifier is trained and aggregated into a multiclassifier model. This multiclassification scheme combines the output of all the one-class classifiers in a unique final response. The proposed method is validated by authenticating pollen grains belonging to different Spanish bee pollen types. The overall accuracy of the system on classifying fraudulent microscopic pollen grain objects is 92.3%. The system is able to rapidly reject pollen grains, which belong to nonlocal pollen types, reducing the laboratory work and effort. The number of possible applications of this authentication method in the microscopy research field is unlimited. Copyright © 2012 Wiley Periodicals, Inc.

  9. The use of the Emotional-Object Recognition as an assay to assess learning and memory associated to an aversive stimulus in rodents.

    Science.gov (United States)

    Brancato, Anna; Lavanco, Gianluca; Cavallaro, Angela; Plescia, Fulvio; Cannizzaro, Carla

    2016-12-01

    Emotionally salient experiences induce the formation of explicit memory traces, besides eliciting automatic or implicit emotional memory in rodents. This study aims at investigating the implementation of a novel task for studying the formation of limbic memory engrams as a result of the acquisition- and retrieval- of fear-conditioning - biased declarative memory traces, measured by animal discrimination of an "emotional-object". Moreover, by using this new method we investigated the potential interactions between stimulation of cannabinoid transmission and integration of emotional information and cognitive functioning. The Emotional-Object Recognition task is composed of 3 following sessions: habituation; cued fear-conditioned learning; emotional recognition. Rats are exposed to Context "B chamber" for habituation and cued fear-conditioning, and tested in Context "A chamber" for emotional-object recognition. Cued fear-conditioning induces a reduction in emotional-object exploration time during the Emotional-Object Recognition task in controls. The activation of cannabinoid signalling impairs limbic memory formation, with respect to vehicle. The Emotional-Object Recognition test overcomes several limitations of commonly employed methods that explore declarative-, spatial memory and fear-conditioning in a non-integrated manner. It allows the assessment of unbiased cognitive indicators of emotional learning and memory. The Emotional-Object Recognition task is a valuable tool for investigating whether, and at what extent, specific drugs or pathological conditions that interfere with the individual affective/emotional homeostasis, can modulate the formation of emotionally salient explicit memory traces, thus jeopardizing control and regulation of animal behavioural strategy. Copyright © 2016 Elsevier B.V. All rights reserved.

  10. Automatic radar target recognition of objects falling on railway tracks

    International Nuclear Information System (INIS)

    Mroué, A; Heddebaut, M; Elbahhar, F; Rivenq, A; Rouvaen, J-M

    2012-01-01

    This paper presents an automatic radar target recognition procedure based on complex resonances using the signals provided by ultra-wideband radar. This procedure is dedicated to detection and identification of objects lying on railway tracks. For an efficient complex resonance extraction, a comparison between several pole extraction methods is illustrated. Therefore, preprocessing methods are presented aiming to remove most of the erroneous poles interfering with the discrimination scheme. Once physical poles are determined, a specific discrimination technique is introduced based on the Euclidean distances. Both simulation and experimental results are depicted showing an efficient discrimination of different targets including guided transport passengers

  11. Object location and object recognition memory impairments, motivation deficits and depression in a model of Gulf War illness.

    Science.gov (United States)

    Hattiangady, Bharathi; Mishra, Vikas; Kodali, Maheedhar; Shuai, Bing; Rao, Xiolan; Shetty, Ashok K

    2014-01-01

    Memory and mood deficits are the enduring brain-related symptoms in Gulf War illness (GWI). Both animal model and epidemiological investigations have indicated that these impairments in a majority of GW veterans are linked to exposures to chemicals such as pyridostigmine bromide (PB, an antinerve gas drug), permethrin (PM, an insecticide) and DEET (a mosquito repellant) encountered during the Persian Gulf War-1. Our previous study in a rat model has shown that combined exposures to low doses of GWI-related (GWIR) chemicals PB, PM, and DEET with or without 5-min of restraint stress (a mild stress paradigm) causes hippocampus-dependent spatial memory dysfunction in a water maze test (WMT) and increased depressive-like behavior in a forced swim test (FST). In this study, using a larger cohort of rats exposed to GWIR-chemicals and stress, we investigated whether the memory deficiency identified earlier in a WMT is reproducible with an alternative and stress free hippocampus-dependent memory test such as the object location test (OLT). We also ascertained the possible co-existence of hippocampus-independent memory dysfunction using a novel object recognition test (NORT), and alterations in mood function with additional tests for motivation and depression. Our results provide new evidence that exposure to low doses of GWIR-chemicals and mild stress for 4 weeks causes deficits in hippocampus-dependent object location memory and perirhinal cortex-dependent novel object recognition memory. An open field test performed prior to other behavioral analyses revealed that memory impairments were not associated with increased anxiety or deficits in general motor ability. However, behavioral tests for mood function such as a voluntary physical exercise paradigm and a novelty suppressed feeding test (NSFT) demonstrated decreased motivation levels and depression. Thus, exposure to GWIR-chemicals and stress causes both hippocampus-dependent and hippocampus-independent memory

  12. Blockade of intracellular Zn2+ signaling in the basolateral amygdala affects object recognition memory via attenuation of dentate gyrus LTP.

    Science.gov (United States)

    Fujise, Yuki; Kubota, Mitsuyasu; Suzuki, Miki; Tamano, Haruna; Takeda, Atsushi

    2017-09-01

    Hippocampus-dependent memory is modulated by the amygdala. However, it is unknown whether intracellular Zn 2+ signaling in the amygdala is involved in hippocampus-dependent memory. On the basis of the evidence that intracellular Zn 2+ signaling in dentate granule cells (DGC) is necessary for object recognition memory via LTP at medial perforant pathway (PP)-DGC synapses, the present study examined whether intracellular Zn 2+ signaling in the amygdala influences object recognition memory via modulation of LTP at medial PP-DGC synapses. When ZnAF-2DA (100 μM, 2 μl) was injected into the basolateral amygdala (BLA), intracellular ZnAF-2 locally chelated intracellular Zn 2+ in the amygdala. Recognition memory was affected when training of object recognition test was performed 20 min after ZnAF-2DA injection into the BLA. Twenty minutes after injection of ZnAF-2DA into the BLA, LTP induction at medial PP-DGC synapses was attenuated, while LTP induction at PP-BLA synapses was potentiated and LTP induction at BLA-DGC synapses was attenuated. These results suggest that intracellular Zn 2+ signaling in the BLA is involved in BLA-associated LTP and modulates LTP at medial PP-DGC synapses, followed by modulation of object recognition memory. Copyright © 2017 Elsevier Ltd. All rights reserved.

  13. Cross-sensor iris recognition through kernel learning.

    Science.gov (United States)

    Pillai, Jaishanker K; Puertas, Maria; Chellappa, Rama

    2014-01-01

    Due to the increasing popularity of iris biometrics, new sensors are being developed for acquiring iris images and existing ones are being continuously upgraded. Re-enrolling users every time a new sensor is deployed is expensive and time-consuming, especially in applications with a large number of enrolled users. However, recent studies show that cross-sensor matching, where the test samples are verified using data enrolled with a different sensor, often lead to reduced performance. In this paper, we propose a machine learning technique to mitigate the cross-sensor performance degradation by adapting the iris samples from one sensor to another. We first present a novel optimization framework for learning transformations on iris biometrics. We then utilize this framework for sensor adaptation, by reducing the distance between samples of the same class, and increasing it between samples of different classes, irrespective of the sensors acquiring them. Extensive evaluations on iris data from multiple sensors demonstrate that the proposed method leads to improvement in cross-sensor recognition accuracy. Furthermore, since the proposed technique requires minimal changes to the iris recognition pipeline, it can easily be incorporated into existing iris recognition systems.

  14. Visualization of the ROOT 3D class objects with openInventor-like viewers

    CERN Document Server

    Fine, V; Kulikova, A; Panebrattsev, M

    2004-01-01

    The class library for conversion of the ROOT 3D class objects to the iv format for 3D image viewers is described in this paper. At present the library was tested using the STAR and ATLAS detector geometry without any changes and revision for concrete detector.

  15. Chronic methylphenidate-effects over circadian cycle of young and adult rats submitted to open-field and object recognition tests.

    Science.gov (United States)

    Gomes, Karin M; Souza, Renan P; Valvassori, Samira S; Réus, Gislaine Z; Inácio, Cecília G; Martins, Márcio R; Comim, Clarissa M; Quevedo, João

    2009-11-01

    In this study age-, circadian rhythm- and methylphenidate administration- effect on open field habituation and object recognition were analyzed. Young and adult male Wistar rats were treated with saline or methylphenidate 2.0 mg/kg for 28 days. Experiments were performed during the light and the dark cycle. Locomotor activity was significantly altered by circadian cycle and methylphenidate treatment during the training session and by drug treatment during the testing session. Exploratory activity was significantly modulated by age during the training session and by age and drug treatment during the testing session. Object recognition memory was altered by cycle at the training session; by age 1.5 h later and by cycle and age 24 h after the training session. These results show that methylphenidate treatment was the major modulator factor on open-field test while cycle and age had an important effect on object recognition experiment.

  16. Object instance recognition using motion cues and instance specific appearance models

    Science.gov (United States)

    Schumann, Arne

    2014-03-01

    In this paper we present an object instance retrieval approach. The baseline approach consists of a pool of image features which are computed on the bounding boxes of a query object track and compared to a database of tracks in order to find additional appearances of the same object instance. We improve over this simple baseline approach in multiple ways: 1) we include motion cues to achieve improved robustness to viewpoint and rotation changes, 2) we include operator feedback to iteratively re-rank the resulting retrieval lists and 3) we use operator feedback and location constraints to train classifiers and learn an instance specific appearance model. We use these classifiers to further improve the retrieval results. The approach is evaluated on two popular public datasets for two different applications. We evaluate person re-identification on the CAVIAR shopping mall surveillance dataset and vehicle instance recognition on the VIVID aerial dataset and achieve significant improvements over our baseline results.

  17. Mechanisms and Neural Basis of Object and Pattern Recognition: A Study with Chess Experts

    Science.gov (United States)

    Bilalic, Merim; Langner, Robert; Erb, Michael; Grodd, Wolfgang

    2010-01-01

    Comparing experts with novices offers unique insights into the functioning of cognition, based on the maximization of individual differences. Here we used this expertise approach to disentangle the mechanisms and neural basis behind two processes that contribute to everyday expertise: object and pattern recognition. We compared chess experts and…

  18. Visual language recognition with a feed-forward network of spiking neurons

    Energy Technology Data Exchange (ETDEWEB)

    Rasmussen, Craig E [Los Alamos National Laboratory; Garrett, Kenyan [Los Alamos National Laboratory; Sottile, Matthew [GALOIS; Shreyas, Ns [INDIANA UNIV.

    2010-01-01

    An analogy is made and exploited between the recognition of visual objects and language parsing. A subset of regular languages is used to define a one-dimensional 'visual' language, in which the words are translational and scale invariant. This allows an exploration of the viewpoint invariant languages that can be solved by a network of concurrent, hierarchically connected processors. A language family is defined that is hierarchically tiling system recognizable (HREC). As inspired by nature, an algorithm is presented that constructs a cellular automaton that recognizes strings from a language in the HREC family. It is demonstrated how a language recognizer can be implemented from the cellular automaton using a feed-forward network of spiking neurons. This parser recognizes fixed-length strings from the language in parallel and as the computation is pipelined, a new string can be parsed in each new interval of time. The analogy with formal language theory allows inferences to be drawn regarding what class of objects can be recognized by visual cortex operating in purely feed-forward fashion and what class of objects requires a more complicated network architecture.

  19. The Initial Development of Object Knowledge by a Learning Robot.

    Science.gov (United States)

    Modayil, Joseph; Kuipers, Benjamin

    2008-11-30

    We describe how a robot can develop knowledge of the objects in its environment directly from unsupervised sensorimotor experience. The object knowledge consists of multiple integrated representations: trackers that form spatio-temporal clusters of sensory experience, percepts that represent properties for the tracked objects, classes that support efficient generalization from past experience, and actions that reliably change object percepts. We evaluate how well this intrinsically acquired object knowledge can be used to solve externally specified tasks including object recognition and achieving goals that require both planning and continuous control.

  20. A new exact anisotropic solution of embedding class one

    Energy Technology Data Exchange (ETDEWEB)

    Maurya, S.K.; Smitha, T.T. [University of Nizwa, Department of Mathematical and Physical Sciences, College of Arts and Science, Nizwa (Oman); Gupta, Y.K. [Raj Kumar Goel Institute of Technology, Department of Mathematics, Ghaziabad (India); Rahaman, Farook [Jadavpur University, Department of Mathematics, Kolkata, West Bengal (India)

    2016-07-15

    We have presented a new anisotropic solution of Einstein's field equations for compact-star models. Einstein's field equations are solved by using the class-one condition (S.N. Pandey, S.P. Sharma, Gen. Relativ. Gravit. 14, 113 (1982)). We constructed the expression for the anisotropy factor (Δ) by using the pressure anisotropy condition and thereafter we obtained the physical parameters like energy density, radial and transverse pressure. These models parameters are well-behaved inside the star and satisfy all the required physical conditions. Also we observed the very interesting result that all physical parameters depend upon the anisotropy factor (Δ). The mass and radius of the present compact-star models are quite compatible with the observational astrophysical compact stellar objects like Her X-1, RXJ 1856-37, SAX J1808.4-3658(SS1), SAX J1808.4-3658(SS2). (orig.)

  1. Online Least Squares One-Class Support Vector Machines-Based Abnormal Visual Event Detection

    Directory of Open Access Journals (Sweden)

    Tian Wang

    2013-12-01

    Full Text Available The abnormal event detection problem is an important subject in real-time video surveillance. In this paper, we propose a novel online one-class classification algorithm, online least squares one-class support vector machine (online LS-OC-SVM, combined with its sparsified version (sparse online LS-OC-SVM. LS-OC-SVM extracts a hyperplane as an optimal description of training objects in a regularized least squares sense. The online LS-OC-SVM learns a training set with a limited number of samples to provide a basic normal model, then updates the model through remaining data. In the sparse online scheme, the model complexity is controlled by the coherence criterion. The online LS-OC-SVM is adopted to handle the abnormal event detection problem. Each frame of the video is characterized by the covariance matrix descriptor encoding the moving information, then is classified into a normal or an abnormal frame. Experiments are conducted, on a two-dimensional synthetic distribution dataset and a benchmark video surveillance dataset, to demonstrate the promising results of the proposed online LS-OC-SVM method.

  2. Learning to recognise : A study on one-class classification and active learning

    NARCIS (Netherlands)

    Juszczak, P.

    2006-01-01

    The thesis treats classification problems which are undersampled or where there exist an unbalance between classes in the sampling. The thesis is divided into three parts. The first two parts treat the problem of one-class classification. In the one-class classification problem, it is assumed that

  3. On hierarchical models for visual recognition and learning of objects, scenes, and activities

    CERN Document Server

    Spehr, Jens

    2015-01-01

    In many computer vision applications, objects have to be learned and recognized in images or image sequences. This book presents new probabilistic hierarchical models that allow an efficient representation of multiple objects of different categories, scales, rotations, and views. The idea is to exploit similarities between objects and object parts in order to share calculations and avoid redundant information. Furthermore inference approaches for fast and robust detection are presented. These new approaches combine the idea of compositional and similarity hierarchies and overcome limitations of previous methods. Besides classical object recognition the book shows the use for detection of human poses in a project for gait analysis. The use of activity detection is presented for the design of environments for ageing, to identify activities and behavior patterns in smart homes. In a presented project for parking spot detection using an intelligent vehicle, the proposed approaches are used to hierarchically model...

  4. Novel object recognition ability in female mice following exposure to nanoparticle-rich diesel exhaust

    Energy Technology Data Exchange (ETDEWEB)

    Win-Shwe, Tin-Tin, E-mail: tin.tin.win.shwe@nies.go.jp [Center for Environmental Health Sciences, National Institute for Environmental Studies, 16‐2 Onogawa, Tsukuba, Ibaraki 305‐8506 (Japan); Fujimaki, Hidekazu; Fujitani, Yuji; Hirano, Seishiro [Center for Environmental Risk Research, National Institute for Environmental Studies, 16‐2 Onogawa, Tsukuba, Ibaraki 305‐8506 (Japan)

    2012-08-01

    Recently, our laboratory reported that exposure to nanoparticle-rich diesel exhaust (NRDE) for 3 months impaired hippocampus-dependent spatial learning ability and up-regulated the expressions of memory function-related genes in the hippocampus of female mice. However, whether NRDE affects the hippocampus-dependent non-spatial learning ability and the mechanism of NRDE-induced neurotoxicity was unknown. Female BALB/c mice were exposed to clean air, middle-dose NRDE (M-NRDE, 47 μg/m{sup 3}), high-dose NRDE (H-NRDE, 129 μg/m{sup 3}), or filtered H-NRDE (F-DE) for 3 months. We then investigated the effect of NRDE exposure on non-spatial learning ability and the expression of genes related to glutamate neurotransmission using a novel object recognition test and a real-time RT-PCR analysis, respectively. We also examined microglia marker Iba1 immunoreactivity in the hippocampus using immunohistochemical analyses. Mice exposed to H-NRDE or F-DE could not discriminate between familiar and novel objects. The control and M-NRDE-exposed groups showed a significantly increased discrimination index, compared to the H-NRDE-exposed group. Although no significant changes in the expression levels of the NMDA receptor subunits were observed, the expression of glutamate transporter EAAT4 was decreased and that of glutamic acid decarboxylase GAD65 was increased in the hippocampus of H-NRDE-exposed mice, compared with the expression levels in control mice. We also found that microglia activation was prominent in the hippocampal area of the H-NRDE-exposed mice, compared with the other groups. These results indicated that exposure to NRDE for 3 months impaired the novel object recognition ability. The present study suggests that genes related to glutamate metabolism may be involved in the NRDE-induced neurotoxicity observed in the present mouse model. -- Highlights: ► The effects of nanoparticle-induced neurotoxicity remain unclear. ► We investigated the effect of exposure to

  5. Novel object recognition ability in female mice following exposure to nanoparticle-rich diesel exhaust

    International Nuclear Information System (INIS)

    Win-Shwe, Tin-Tin; Fujimaki, Hidekazu; Fujitani, Yuji; Hirano, Seishiro

    2012-01-01

    Recently, our laboratory reported that exposure to nanoparticle-rich diesel exhaust (NRDE) for 3 months impaired hippocampus-dependent spatial learning ability and up-regulated the expressions of memory function-related genes in the hippocampus of female mice. However, whether NRDE affects the hippocampus-dependent non-spatial learning ability and the mechanism of NRDE-induced neurotoxicity was unknown. Female BALB/c mice were exposed to clean air, middle-dose NRDE (M-NRDE, 47 μg/m 3 ), high-dose NRDE (H-NRDE, 129 μg/m 3 ), or filtered H-NRDE (F-DE) for 3 months. We then investigated the effect of NRDE exposure on non-spatial learning ability and the expression of genes related to glutamate neurotransmission using a novel object recognition test and a real-time RT-PCR analysis, respectively. We also examined microglia marker Iba1 immunoreactivity in the hippocampus using immunohistochemical analyses. Mice exposed to H-NRDE or F-DE could not discriminate between familiar and novel objects. The control and M-NRDE-exposed groups showed a significantly increased discrimination index, compared to the H-NRDE-exposed group. Although no significant changes in the expression levels of the NMDA receptor subunits were observed, the expression of glutamate transporter EAAT4 was decreased and that of glutamic acid decarboxylase GAD65 was increased in the hippocampus of H-NRDE-exposed mice, compared with the expression levels in control mice. We also found that microglia activation was prominent in the hippocampal area of the H-NRDE-exposed mice, compared with the other groups. These results indicated that exposure to NRDE for 3 months impaired the novel object recognition ability. The present study suggests that genes related to glutamate metabolism may be involved in the NRDE-induced neurotoxicity observed in the present mouse model. -- Highlights: ► The effects of nanoparticle-induced neurotoxicity remain unclear. ► We investigated the effect of exposure to

  6. Infliximab ameliorates AD-associated object recognition memory impairment.

    Science.gov (United States)

    Kim, Dong Hyun; Choi, Seong-Min; Jho, Jihoon; Park, Man-Seok; Kang, Jisu; Park, Se Jin; Ryu, Jong Hoon; Jo, Jihoon; Kim, Hyun Hee; Kim, Byeong C

    2016-09-15

    Dysfunctions in the perirhinal cortex (PRh) are associated with visual recognition memory deficit, which is frequently detected in the early stage of Alzheimer's disease. Muscarinic acetylcholine receptor-dependent long-term depression (mAChR-LTD) of synaptic transmission is known as a key pathway in eliciting this type of memory, and Tg2576 mice expressing enhanced levels of Aβ oligomers are found to have impaired mAChR-LTD in this brain area at as early as 3 months of age. We found that the administration of Aβ oligomers in young normal mice also induced visual recognition memory impairment and perturbed mAChR-LTD in mouse PRh slices. In addition, when mice were treated with infliximab, a monoclonal antibody against TNF-α, visual recognition memory impaired by pre-administered Aβ oligomers dramatically improved and the detrimental Aβ effect on mAChR-LTD was annulled. Taken together, these findings suggest that Aβ-induced inflammation is mediated through TNF-α signaling cascades, disturbing synaptic transmission in the PRh, and leading to visual recognition memory deficits. Copyright © 2016 Elsevier B.V. All rights reserved.

  7. Recognition of explosives fingerprints on objects for courier services using machine learning methods and laser-induced breakdown spectroscopy.

    Science.gov (United States)

    Moros, J; Serrano, J; Gallego, F J; Macías, J; Laserna, J J

    2013-06-15

    During recent years laser-induced breakdown spectroscopy (LIBS) has been considered one of the techniques with larger ability for trace detection of explosives. However, despite of the high sensitivity exhibited for this application, LIBS suffers from a limited selectivity due to difficulties in assigning the molecular origin of the spectral emissions observed. This circumstance makes the recognition of fingerprints a latent challenging problem. In the present manuscript the sorting of six explosives (chloratite, ammonal, DNT, TNT, RDX and PETN) against a broad list of potential harmless interferents (butter, fuel oil, hand cream, olive oil, …), all of them in the form of fingerprints deposited on the surfaces of objects for courier services, has been carried out. When LIBS information is processed through a multi-stage architecture algorithm built from a suitable combination of 3 learning classifiers, an unknown fingerprint may be labeled into a particular class. Neural network classifiers trained by the Levenberg-Marquardt rule were decided within 3D scatter plots projected onto the subspace of the most useful features extracted from the LIBS spectra. Experimental results demonstrate that the presented algorithm sorts fingerprints according to their hazardous character, although its spectral information is virtually identical in appearance, with rates of false negatives and false positives not beyond of 10%. These reported achievements mean a step forward in the technology readiness level of LIBS for this complex application related to defense, homeland security and force protection. Copyright © 2013 Elsevier B.V. All rights reserved.

  8. Short-term blueberry-enriched diet prevents and reverses object recognition memory loss in aging rats.

    Science.gov (United States)

    Malin, David H; Lee, David R; Goyarzu, Pilar; Chang, Yu-Hsuan; Ennis, Lalanya J; Beckett, Elizabeth; Shukitt-Hale, Barbara; Joseph, James A

    2011-03-01

    Previously, 4 mo of a blueberry-enriched (BB) antioxidant diet prevented impaired object recognition memory in aging rats. Experiment 1 determined whether 1- and 2-mo BB diets would have a similar effect and whether the benefits would disappear promptly after terminating the diets. Experiment 2 determined whether a 1-mo BB diet could subsequently reverse existing object memory impairment in aging rats. In experiment 1, Fischer-344 rats were maintained on an appropriate control diet or on 1 or 2 mo of the BB diet before testing object memory at 19 mo postnatally. In experiment 2, rats were tested for object recognition memory at 19 mo and again at 20 mo after 1 mo of maintenance on a 2% BB or control diet. In experiment 1, the control group performed no better than chance, whereas the 1- and 2-mo BB diet groups performed similarly and significantly better than controls. The 2-mo BB-diet group, but not the 1-mo group, maintained its performance over a subsequent month on a standard laboratory diet. In experiment 2, the 19-mo-old rats performed near chance. At 20 mo of age, the rats subsequently maintained on the BB diet significantly increased their object memory scores, whereas the control diet group exhibited a non-significant decline. The change in object memory scores differed significantly between the two diet groups. These results suggest that a considerable degree of age-related object memory decline can be prevented and reversed by brief maintenance on BB diets. Copyright © 2011 Elsevier Inc. All rights reserved.

  9. Category Specificity in Normal Episodic Learning: Applications to Object Recognition and Category-Specific Agnosia

    Science.gov (United States)

    Bukach, Cindy M.; Bub, Daniel N.; Masson, Michael E. J.; Lindsay, D. Stephen

    2004-01-01

    Studies of patients with category-specific agnosia (CSA) have given rise to multiple theories of object recognition, most of which assume the existence of a stable, abstract semantic memory system. We applied an episodic view of memory to questions raised by CSA in a series of studies examining normal observers' recall of newly learned attributes…

  10. Divergent short- and long-term effects of acute stress in object recognition memory are mediated by endogenous opioid system activation.

    Science.gov (United States)

    Nava-Mesa, Mauricio O; Lamprea, Marisol R; Múnera, Alejandro

    2013-11-01

    Acute stress induces short-term object recognition memory impairment and elicits endogenous opioid system activation. The aim of this study was thus to evaluate whether opiate system activation mediates the acute stress-induced object recognition memory changes. Adult male Wistar rats were trained in an object recognition task designed to test both short- and long-term memory. Subjects were randomly assigned to receive an intraperitoneal injection of saline, 1 mg/kg naltrexone or 3 mg/kg naltrexone, four and a half hours before the sample trial. Five minutes after the injection, half the subjects were submitted to movement restraint during four hours while the other half remained in their home cages. Non-stressed subjects receiving saline (control) performed adequately during the short-term memory test, while stressed subjects receiving saline displayed impaired performance. Naltrexone prevented such deleterious effect, in spite of the fact that it had no intrinsic effect on short-term object recognition memory. Stressed subjects receiving saline and non-stressed subjects receiving naltrexone performed adequately during the long-term memory test; however, control subjects as well as stressed subjects receiving a high dose of naltrexone performed poorly. Control subjects' dissociated performance during both memory tests suggests that the short-term memory test induced a retroactive interference effect mediated through light opioid system activation; such effect was prevented either by low dose naltrexone administration or by strongly activating the opioid system through acute stress. Both short-term memory retrieval impairment and long-term memory improvement observed in stressed subjects may have been mediated through strong opioid system activation, since they were prevented by high dose naltrexone administration. Therefore, the activation of the opioid system plays a dual modulating role in object recognition memory. Copyright © 2013 Elsevier Inc. All rights

  11. Target recognition based on convolutional neural network

    Science.gov (United States)

    Wang, Liqiang; Wang, Xin; Xi, Fubiao; Dong, Jian

    2017-11-01

    One of the important part of object target recognition is the feature extraction, which can be classified into feature extraction and automatic feature extraction. The traditional neural network is one of the automatic feature extraction methods, while it causes high possibility of over-fitting due to the global connection. The deep learning algorithm used in this paper is a hierarchical automatic feature extraction method, trained with the layer-by-layer convolutional neural network (CNN), which can extract the features from lower layers to higher layers. The features are more discriminative and it is beneficial to the object target recognition.

  12. Heterozygous Che-1 KO mice show deficiencies in object recognition memory persistence.

    Science.gov (United States)

    Zalcman, Gisela; Corbi, Nicoletta; Di Certo, Maria Grazia; Mattei, Elisabetta; Federman, Noel; Romano, Arturo

    2016-10-06

    Transcriptional regulation is a key process in the formation of long-term memories. Che-1 is a protein involved in the regulation of gene transcription that has recently been proved to bind the transcription factor NF-κB, which is known to be involved in many memory-related molecular events. This evidence prompted us to investigate the putative role of Che-1 in memory processes. For this study we newly generated a line of Che-1(+/-) heterozygous mice. Che-1 homozygous KO mouse is lethal during development, but Che-1(+/-) heterozygous mouse is normal in its general anatomical and physiological characteristics. We analyzed the behavioral characteristic and memory performance of Che-1(+/-) mice in two NF-κB dependent types of memory. We found that Che-1(+/-) mice show similar locomotor activity and thigmotactic behavior than wild type (WT) mice in an open field. In a similar way, no differences were found in anxiety-like behavior between Che-1(+/-) and WT mice in an elevated plus maze as well as in fear response in a contextual fear conditioning (CFC) and object exploration in a novel object recognition (NOR) task. No differences were found between WT and Che-1(+/-) mice performance in CFC training and when tested at 24h or 7days after training. Similar performance was found between groups in NOR task, both in training and 24h testing performance. However, we found that object recognition memory persistence at 7days was impaired in Che-1(+/-) heterozygous mice. This is the first evidence showing that Che-1 is involved in memory processes. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

  13. Noradrenergic Activation of the Basolateral Amygdala Enhances Object Recognition Memory and Induces Chromatin Remodeling in the Insular Cortex

    Directory of Open Access Journals (Sweden)

    Hassiba eBeldjoud

    2015-04-01

    Full Text Available It is well established that arousal-induced memory enhancement requires noradrenergic activation of the basolateral complex of the amygdala (BLA and modulatory influences on information storage processes in its many target regions. While this concept is well accepted, the molecular basis of such BLA effects on neural plasticity changes within other brain regions remains to be elucidated. The present study investigated whether noradrenergic activation of the BLA after object recognition training induces chromatin remodeling through histone post-translational modifications in the insular cortex (IC, a brain region that is importantly involved in object recognition memory. Male Sprague–Dawley rats were trained on an object recognition task, followed immediately by bilateral microinfusions of norepinephrine (1.0 µg or saline administered into the BLA. Saline-treated control rats exhibited poor 24-h retention, whereas norepinephrine treatment induced robust 24-h object recognition memory. Most importantly, this memory-enhancing dose of norepinephrine induced a global reduction in the acetylation levels of histone H3 at lysine 14, H2B and H4 in the IC 1 h later, whereas it had no effect on the phosphorylation of histone H3 at serine 10 or tri-methylation of histone H3 at lysine 27. Norepinephrine administered into the BLA of non-trained control rats did not induce any changes in the histone marks investigated in this study. These findings indicate that noradrenergic activation of the BLA induces training-specific effects on chromatin remodeling mechanisms, and presumably gene transcription, in its target regions, which may contribute to the understanding of the molecular mechanisms of stress and emotional arousal effects on memory consolidation.

  14. Channels as Objects in Concurrent Object-Oriented Programming

    Directory of Open Access Journals (Sweden)

    Joana Campos

    2011-10-01

    Full Text Available There is often a sort of a protocol associated to each class, stating when and how certain methods should be called. Given that this protocol is, if at all, described in the documentation accompanying the class, current mainstream object-oriented languages cannot provide for the verification of client code adherence against the sought class behaviour. We have defined a class-based concurrent object-oriented language that formalises such protocols in the form of usage types. Usage types are attached to class definitions, allowing for the specification of (1 the available methods, (2 the tests clients must perform on the result of methods, and (3 the object status - linear or shared - all of which depend on the object's state. Our work extends the recent approach on modular session types by eliminating channel operations, and defining the method call as the single communication primitive in both sequential and concurrent settings. In contrast to previous works, we define a single category for objects, instead of distinct categories for linear and for shared objects, and let linear objects evolve into shared ones. We introduce a standard sync qualifier to prevent thread interference in certain operations on shared objects. We formalise the language syntax, the operational semantics, and a type system that enforces by static typing that methods are called only when available, and by a single client if so specified in the usage type. We illustrate the language via a complete example.

  15. Predicting peptides binding to MHC class II molecules using multi-objective evolutionary algorithms

    Directory of Open Access Journals (Sweden)

    Feng Lin

    2007-11-01

    Full Text Available Abstract Background Peptides binding to Major Histocompatibility Complex (MHC class II molecules are crucial for initiation and regulation of immune responses. Predicting peptides that bind to a specific MHC molecule plays an important role in determining potential candidates for vaccines. The binding groove in class II MHC is open at both ends, allowing peptides longer than 9-mer to bind. Finding the consensus motif facilitating the binding of peptides to a MHC class II molecule is difficult because of different lengths of binding peptides and varying location of 9-mer binding core. The level of difficulty increases when the molecule is promiscuous and binds to a large number of low affinity peptides. In this paper, we propose two approaches using multi-objective evolutionary algorithms (MOEA for predicting peptides binding to MHC class II molecules. One uses the information from both binders and non-binders for self-discovery of motifs. The other, in addition, uses information from experimentally determined motifs for guided-discovery of motifs. Results The proposed methods are intended for finding peptides binding to MHC class II I-Ag7 molecule – a promiscuous binder to a large number of low affinity peptides. Cross-validation results across experiments on two motifs derived for I-Ag7 datasets demonstrate better generalization abilities and accuracies of the present method over earlier approaches. Further, the proposed method was validated and compared on two publicly available benchmark datasets: (1 an ensemble of qualitative HLA-DRB1*0401 peptide data obtained from five different sources, and (2 quantitative peptide data obtained for sixteen different alleles comprising of three mouse alleles and thirteen HLA alleles. The proposed method outperformed earlier methods on most datasets, indicating that it is well suited for finding peptides binding to MHC class II molecules. Conclusion We present two MOEA-based algorithms for finding motifs

  16. MHC class I molecules with superenhanced CD8 binding properties bypass the requirement for cognate TCR recognition and nonspecifically activate CTLs

    NARCIS (Netherlands)

    L. Wooldridge (Linda); M. Clement (Mathew); A. Lissina (Anna); E.S.J. Edwards (Emily); K. Ladell (Kristin); J. Ekeruche (Julia); R.E. Hewitt (Rachel); B. Laugel (Bruno); E. Gostick (Emma); D.K. Cole (David); J.E.M.A. Debets (Reno); C.A. Berrevoets (Cor); J.J. Miles (John); S.R. Burrows (Scott); D.A. Price (David); A.K. Sewell (Andrew)

    2010-01-01

    textabstractCD8+CTLs are essential for effective immune defense against intracellular microbes and neoplasia. CTLs recognize short peptide fragments presented in association with MHC class I (MHCI) molecules on the surface of infected or dysregulated cells. Ag recognition involves the binding of

  17. The impact of differences between subjective and objective social class on life satisfaction among the Korean population in early old age: Analysis of Korean longitudinal study on aging.

    Science.gov (United States)

    Choi, Young; Kim, Jae-Hyun; Park, Eun-Cheol

    2016-01-01

    Several previous studies have established the relationship between the effects of socioeconomic status or subjective social strata on life satisfaction. However, no previous study has examined the relationship between social class and life satisfaction in terms of a disparity between subjective and objective social status. To investigate the relationship between differences in subjective and objective social class and life satisfaction. Data from the Korean Longitudinal Study of Aging with 8252 participants aged 45 or older was used. Life satisfaction was measured by the question, "How satisfied are you with your quality of life?" The main independent variable was differences in objective (income and education) and subjective social class, which was classified according to nine categories (ranging from high-high to low-low). This association was investigated by linear mixed model due to two waves data nested within individuals. Lower social class (income, education, subjective social class) was associated with dissatisfaction. The impact of objective and subjective social class on life satisfaction varied according to the level of differences in objective and subjective social class. Namely, an individual's life satisfaction declined as objective social classes decreased at the same level of subjective social class (i.e., HH, MH, LH). In both dimensions of objective social class (education and income), an individual's life satisfaction declined as subjective social class decreased by one level (i.e., HH, HM, HL). Our findings indicated that social supports is needed to improve the life satisfaction among the population aged 45 or more with low social class. The government should place increased focus on policies that encourage not only the life satisfaction of the Korean elderly with low objective social class, but also subjective social class. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

  18. Investigations into the involvement of NMDA mechanisms in recognition memory.

    Science.gov (United States)

    Warburton, E Clea; Barker, Gareth R I; Brown, Malcom W

    2013-11-01

    This review will focus on evidence showing that NMDA receptor neurotransmission is critical for synaptic plasticity processes within brain regions known to be necessary for the formation of object recognition memories. The aim will be to provide evidence concerning NMDA mechanisms related to recognition memory processes and show that recognition memory for objects, places or associations between objects and places depends on NMDA neurotransmission within the perirhinal cortex, temporal association cortex medial prefrontal cortex and hippocampus. Administration of the NMDA antagonist AP5, selectively into each of these brain regions has revealed that the extent of the involvement NMDA receptors appears dependent on the type of information required to solve the recognition memory task; thus NMDA receptors in the perirhinal cortex are crucial for the encoding of long-term recognition memory for objects, and object-in-place associations, but not for short-term recognition memory or for retrieval. In contrast the hippocampus and medial prefrontal cortex are required for both long-term and short-term recognition memory for places or associations between objects and places, or for recognition memory tasks that have a temporal component. Such studies have therefore confirmed that the multiple brain regions make distinct contributions to recognition memory but in addition that more than one synaptic plasticity process must be involved. This article is part of the Special Issue entitled 'Glutamate Receptor-Dependent Synaptic Plasticity'. Copyright © 2013 The Authors. Published by Elsevier Ltd.. All rights reserved.

  19. Improving human object recognition performance using video enhancement techniques

    Science.gov (United States)

    Whitman, Lucy S.; Lewis, Colin; Oakley, John P.

    2004-12-01

    Atmospheric scattering causes significant degradation in the quality of video images, particularly when imaging over long distances. The principle problem is the reduction in contrast due to scattered light. It is known that when the scattering particles are not too large compared with the imaging wavelength (i.e. Mie scattering) then high spatial resolution information may be contained within a low-contrast image. Unfortunately this information is not easily perceived by a human observer, particularly when using a standard video monitor. A secondary problem is the difficulty of achieving a sharp focus since automatic focus techniques tend to fail in such conditions. Recently several commercial colour video processing systems have become available. These systems use various techniques to improve image quality in low contrast conditions whilst retaining colour content. These systems produce improvements in subjective image quality in some situations, particularly in conditions of haze and light fog. There is also some evidence that video enhancement leads to improved ATR performance when used as a pre-processing stage. Psychological literature indicates that low contrast levels generally lead to a reduction in the performance of human observers in carrying out simple visual tasks. The aim of this paper is to present the results of an empirical study on object recognition in adverse viewing conditions. The chosen visual task was vehicle number plate recognition at long ranges (500 m and beyond). Two different commercial video enhancement systems are evaluated using the same protocol. The results show an increase in effective range with some differences between the different enhancement systems.

  20. Two diverse models of embedding class one

    Science.gov (United States)

    Kuhfittig, Peter K. F.

    2018-05-01

    Embedding theorems have continued to be a topic of interest in the general theory of relativity since these help connect the classical theory to higher-dimensional manifolds. This paper deals with spacetimes of embedding class one, i.e., spacetimes that can be embedded in a five-dimensional flat spacetime. These ideas are applied to two diverse models, a complete solution for a charged wormhole admitting a one-parameter group of conformal motions and a new model to explain the flat rotation curves in spiral galaxies without the need for dark matter.

  1. In-the-wild facial expression recognition in extreme poses

    Science.gov (United States)

    Yang, Fei; Zhang, Qian; Zheng, Chi; Qiu, Guoping

    2018-04-01

    In the computer research area, facial expression recognition is a hot research problem. Recent years, the research has moved from the lab environment to in-the-wild circumstances. It is challenging, especially under extreme poses. But current expression detection systems are trying to avoid the pose effects and gain the general applicable ability. In this work, we solve the problem in the opposite approach. We consider the head poses and detect the expressions within special head poses. Our work includes two parts: detect the head pose and group it into one pre-defined head pose class; do facial expression recognize within each pose class. Our experiments show that the recognition results with pose class grouping are much better than that of direct recognition without considering poses. We combine the hand-crafted features, SIFT, LBP and geometric feature, with deep learning feature as the representation of the expressions. The handcrafted features are added into the deep learning framework along with the high level deep learning features. As a comparison, we implement SVM and random forest to as the prediction models. To train and test our methodology, we labeled the face dataset with 6 basic expressions.

  2. Visual Object Recognition with 3D-Aware Features in KITTI Urban Scenes.

    Science.gov (United States)

    Yebes, J Javier; Bergasa, Luis M; García-Garrido, Miguel Ángel

    2015-04-20

    Driver assistance systems and autonomous robotics rely on the deployment of several sensors for environment perception. Compared to LiDAR systems, the inexpensive vision sensors can capture the 3D scene as perceived by a driver in terms of appearance and depth cues. Indeed, providing 3D image understanding capabilities to vehicles is an essential target in order to infer scene semantics in urban environments. One of the challenges that arises from the navigation task in naturalistic urban scenarios is the detection of road participants (e.g., cyclists, pedestrians and vehicles). In this regard, this paper tackles the detection and orientation estimation of cars, pedestrians and cyclists, employing the challenging and naturalistic KITTI images. This work proposes 3D-aware features computed from stereo color images in order to capture the appearance and depth peculiarities of the objects in road scenes. The successful part-based object detector, known as DPM, is extended to learn richer models from the 2.5D data (color and disparity), while also carrying out a detailed analysis of the training pipeline. A large set of experiments evaluate the proposals, and the best performing approach is ranked on the KITTI website. Indeed, this is the first work that reports results with stereo data for the KITTI object challenge, achieving increased detection ratios for the classes car and cyclist compared to a baseline DPM.

  3. Visual Object Recognition with 3D-Aware Features in KITTI Urban Scenes

    Directory of Open Access Journals (Sweden)

    J. Javier Yebes

    2015-04-01

    Full Text Available Driver assistance systems and autonomous robotics rely on the deployment of several sensors for environment perception. Compared to LiDAR systems, the inexpensive vision sensors can capture the 3D scene as perceived by a driver in terms of appearance and depth cues. Indeed, providing 3D image understanding capabilities to vehicles is an essential target in order to infer scene semantics in urban environments. One of the challenges that arises from the navigation task in naturalistic urban scenarios is the detection of road participants (e.g., cyclists, pedestrians and vehicles. In this regard, this paper tackles the detection and orientation estimation of cars, pedestrians and cyclists, employing the challenging and naturalistic KITTI images. This work proposes 3D-aware features computed from stereo color images in order to capture the appearance and depth peculiarities of the objects in road scenes. The successful part-based object detector, known as DPM, is extended to learn richer models from the 2.5D data (color and disparity, while also carrying out a detailed analysis of the training pipeline. A large set of experiments evaluate the proposals, and the best performing approach is ranked on the KITTI website. Indeed, this is the first work that reports results with stereo data for the KITTI object challenge, achieving increased detection ratios for the classes car and cyclist compared to a baseline DPM.

  4. Memory consolidation and expression of object recognition are susceptible to retroactive interference.

    Science.gov (United States)

    Villar, María Eugenia; Martinez, María Cecilia; Lopes da Cunha, Pamela; Ballarini, Fabricio; Viola, Haydee

    2017-02-01

    With the aim of analyzing if object recognition long-term memory (OR-LTM) formation is susceptible to retroactive interference (RI), we submitted rats to sequential sample sessions using the same arena but changing the identity of a pair of objects placed in it. Separate groups of animals were tested in the arena in order to evaluate the LTM for these objects. Our results suggest that OR-LTM formation was retroactively interfered within a critical time window by the exploration of a new, but not familiar, object. This RI acted on the consolidation of the object explored in the first sample session because its OR-STM measured 3h after training was not affected, whereas the OR-LTM measured at 24h was impaired. This sample session also impaired the expression of OR memory when it took place before the test. Moreover, local inactivation of the dorsal Hippocampus (Hp) or the medial Prefrontal Cortex (mPFC) previous to the exploration of the second pair of objects impaired their consolidation restoring the LTM for the objects explored in the first session. This data suggests that both brain regions are involved in the processing of OR-memory and also that if those regions are engaged in another process before finishing the first consolidation process its LTM will be impaired by RI. Copyright © 2016 Elsevier Inc. All rights reserved.

  5. Anomaly detection for medical images based on a one-class classification

    Science.gov (United States)

    Wei, Qi; Ren, Yinhao; Hou, Rui; Shi, Bibo; Lo, Joseph Y.; Carin, Lawrence

    2018-02-01

    Detecting an anomaly such as a malignant tumor or a nodule from medical images including mammogram, CT or PET images is still an ongoing research problem drawing a lot of attention with applications in medical diagnosis. A conventional way to address this is to learn a discriminative model using training datasets of negative and positive samples. The learned model can be used to classify a testing sample into a positive or negative class. However, in medical applications, the high unbalance between negative and positive samples poses a difficulty for learning algorithms, as they will be biased towards the majority group, i.e., the negative one. To address this imbalanced data issue as well as leverage the huge amount of negative samples, i.e., normal medical images, we propose to learn an unsupervised model to characterize the negative class. To make the learned model more flexible and extendable for medical images of different scales, we have designed an autoencoder based on a deep neural network to characterize the negative patches decomposed from large medical images. A testing image is decomposed into patches and then fed into the learned autoencoder to reconstruct these patches themselves. The reconstruction error of one patch is used to classify this patch into a binary class, i.e., a positive or a negative one, leading to a one-class classifier. The positive patches highlight the suspicious areas containing anomalies in a large medical image. The proposed method has been tested on InBreast dataset and achieves an AUC of 0.84. The main contribution of our work can be summarized as follows. 1) The proposed one-class learning requires only data from one class, i.e., the negative data; 2) The patch-based learning makes the proposed method scalable to images of different sizes and helps avoid the large scale problem for medical images; 3) The training of the proposed deep convolutional neural network (DCNN) based auto-encoder is fast and stable.

  6. Attribute-based classification for zero-shot visual object categorization.

    Science.gov (United States)

    Lampert, Christoph H; Nickisch, Hannes; Harmeling, Stefan

    2014-03-01

    We study the problem of object recognition for categories for which we have no training examples, a task also called zero--data or zero-shot learning. This situation has hardly been studied in computer vision research, even though it occurs frequently; the world contains tens of thousands of different object classes, and image collections have been formed and suitably annotated for only a few of them. To tackle the problem, we introduce attribute-based classification: Objects are identified based on a high-level description that is phrased in terms of semantic attributes, such as the object's color or shape. Because the identification of each such property transcends the specific learning task at hand, the attribute classifiers can be prelearned independently, for example, from existing image data sets unrelated to the current task. Afterward, new classes can be detected based on their attribute representation, without the need for a new training phase. In this paper, we also introduce a new data set, Animals with Attributes, of over 30,000 images of 50 animal classes, annotated with 85 semantic attributes. Extensive experiments on this and two more data sets show that attribute-based classification indeed is able to categorize images without access to any training images of the target classes.

  7. Real-time object recognition in multidimensional images based on joined extended structural tensor and higher-order tensor decomposition methods

    Science.gov (United States)

    Cyganek, Boguslaw; Smolka, Bogdan

    2015-02-01

    In this paper a system for real-time recognition of objects in multidimensional video signals is proposed. Object recognition is done by pattern projection into the tensor subspaces obtained from the factorization of the signal tensors representing the input signal. However, instead of taking only the intensity signal the novelty of this paper is first to build the Extended Structural Tensor representation from the intensity signal that conveys information on signal intensities, as well as on higher-order statistics of the input signals. This way the higher-order input pattern tensors are built from the training samples. Then, the tensor subspaces are built based on the Higher-Order Singular Value Decomposition of the prototype pattern tensors. Finally, recognition relies on measurements of the distance of a test pattern projected into the tensor subspaces obtained from the training tensors. Due to high-dimensionality of the input data, tensor based methods require high memory and computational resources. However, recent achievements in the technology of the multi-core microprocessors and graphic cards allows real-time operation of the multidimensional methods as is shown and analyzed in this paper based on real examples of object detection in digital images.

  8. Impairment of object recognition memory by maternal bisphenol A exposure is associated with inhibition of Akt and ERK/CREB/BDNF pathway in the male offspring hippocampus.

    Science.gov (United States)

    Wang, Chong; Li, Zhihui; Han, Haijun; Luo, Guangying; Zhou, Bingrui; Wang, Shaolin; Wang, Jundong

    2016-02-03

    Bisphenol A (BPA) is a commonly used endocrine-disrupting chemical used as a component of polycarbonates plastics that has potential adverse effects on human health. Exposure to BPA during development has been implicated in memory deficits, but the mechanism of action underlying the effect is not fully understood. In this study, we investigated the effect of maternal exposure to BPA on object recognition memory and the expressions of proteins important for memory, especially focusing on the ERK/CREB/BDNF pathway. Pregnant Sprague-Dawley female rats were orally treated with either vehicle or BPA (0.05, 0.5, 5 or 50 mg/kg BW/day) during days 9-20 of gestation. Male offspring were tested on postnatal day 21 with the object recognition task. Recognition memory was assessed using the object recognition index (index=the time spent exploring the novel object/(the time spent exploring the novel object+the time spent exploring the familiar object)). In the test session performed 90 min after the training session, BPA-exposed male offspring not only spent more time in exploring the familiar object at the highest dose than the control, but also displayed a significantly decreased the object recognition index at the doses of 0.5, 5 and 50 mg/kg BW/day. During the test session performed 24h after the training session, BPA-treated males did not change the time spent exploring the familiar object, but had a decreased object recognition index at 5 and 50 mg/kg BW/day, when compared to control group. These findings indicate that object recognition memory was susceptible to maternal BPA exposure. Western blot analysis of hippocampi from BPA-treated male offspring revealed a decrease in Akt, phospho-Akt, p44/42 MAPK and phospho-p44/42 MAPK protein levels, compared to controls. In addition, BPA significantly inhibited the levels of phosphorylation of CREB and BDNF in the hippocampus. Our results show that maternal BPA exposure may full impair object recognition memory, and that

  9. Bidirectional Modulation of Recognition Memory.

    Science.gov (United States)

    Ho, Jonathan W; Poeta, Devon L; Jacobson, Tara K; Zolnik, Timothy A; Neske, Garrett T; Connors, Barry W; Burwell, Rebecca D

    2015-09-30

    Perirhinal cortex (PER) has a well established role in the familiarity-based recognition of individual items and objects. For example, animals and humans with perirhinal damage are unable to distinguish familiar from novel objects in recognition memory tasks. In the normal brain, perirhinal neurons respond to novelty and familiarity by increasing or decreasing firing rates. Recent work also implicates oscillatory activity in the low-beta and low-gamma frequency bands in sensory detection, perception, and recognition. Using optogenetic methods in a spontaneous object exploration (SOR) task, we altered recognition memory performance in rats. In the SOR task, normal rats preferentially explore novel images over familiar ones. We modulated exploratory behavior in this task by optically stimulating channelrhodopsin-expressing perirhinal neurons at various frequencies while rats looked at novel or familiar 2D images. Stimulation at 30-40 Hz during looking caused rats to treat a familiar image as if it were novel by increasing time looking at the image. Stimulation at 30-40 Hz was not effective in increasing exploration of novel images. Stimulation at 10-15 Hz caused animals to treat a novel image as familiar by decreasing time looking at the image, but did not affect looking times for images that were already familiar. We conclude that optical stimulation of PER at different frequencies can alter visual recognition memory bidirectionally. Significance statement: Recognition of novelty and familiarity are important for learning, memory, and decision making. Perirhinal cortex (PER) has a well established role in the familiarity-based recognition of individual items and objects, but how novelty and familiarity are encoded and transmitted in the brain is not known. Perirhinal neurons respond to novelty and familiarity by changing firing rates, but recent work suggests that brain oscillations may also be important for recognition. In this study, we showed that stimulation of

  10. Objective Prediction of Hearing Aid Benefit Across Listener Groups Using Machine Learning: Speech Recognition Performance With Binaural Noise-Reduction Algorithms.

    Science.gov (United States)

    Schädler, Marc R; Warzybok, Anna; Kollmeier, Birger

    2018-01-01

    The simulation framework for auditory discrimination experiments (FADE) was adopted and validated to predict the individual speech-in-noise recognition performance of listeners with normal and impaired hearing with and without a given hearing-aid algorithm. FADE uses a simple automatic speech recognizer (ASR) to estimate the lowest achievable speech reception thresholds (SRTs) from simulated speech recognition experiments in an objective way, independent from any empirical reference data. Empirical data from the literature were used to evaluate the model in terms of predicted SRTs and benefits in SRT with the German matrix sentence recognition test when using eight single- and multichannel binaural noise-reduction algorithms. To allow individual predictions of SRTs in binaural conditions, the model was extended with a simple better ear approach and individualized by taking audiograms into account. In a realistic binaural cafeteria condition, FADE explained about 90% of the variance of the empirical SRTs for a group of normal-hearing listeners and predicted the corresponding benefits with a root-mean-square prediction error of 0.6 dB. This highlights the potential of the approach for the objective assessment of benefits in SRT without prior knowledge about the empirical data. The predictions for the group of listeners with impaired hearing explained 75% of the empirical variance, while the individual predictions explained less than 25%. Possibly, additional individual factors should be considered for more accurate predictions with impaired hearing. A competing talker condition clearly showed one limitation of current ASR technology, as the empirical performance with SRTs lower than -20 dB could not be predicted.

  11. Geometric Edge Description and Classification in Point Cloud Data with Application to 3D Object Recognition

    DEFF Research Database (Denmark)

    Jørgensen, Troels Bo; Buch, Anders Glent; Kraft, Dirk

    2015-01-01

    descriptor allows for both fast computation and fast processing by having a low dimension, while still producing highly reliable edge detections. Lastly, we use our features in a 3D object recognition application using a well-established benchmark. We show that our edge features allow for significant...

  12. People's Risk Recognition Preceding Evacuation and Its Role in Demand Modeling and Planning.

    Science.gov (United States)

    Urata, Junji; Pel, Adam J

    2018-05-01

    Evacuation planning and management involves estimating the travel demand in the event that such action is required. This is usually done as a function of people's decision to evacuate, which we show is strongly linked to their risk awareness. We use an empirical data set, which shows tsunami evacuation behavior, to demonstrate that risk recognition is not synonymous with objective risk, but is instead determined by a combination of factors including risk education, information, and sociodemographics, and that it changes dynamically over time. Based on these findings, we formulate an ordered logit model to describe risk recognition combined with a latent class model to describe evacuation choices. Our proposed evacuation choice model along with a risk recognition class can evaluate quantitatively the influence of disaster mitigation measures, risk education, and risk information. The results obtained from the risk recognition model show that risk information has a greater impact in the sense that people recognize their high risk. The results of the evacuation choice model show that people who are unaware of their risk take a longer time to evacuate. © 2017 Society for Risk Analysis.

  13. An object-oriented class design for the generalized finite element method programming

    Directory of Open Access Journals (Sweden)

    Dorival Piedade Neto

    Full Text Available The Generalized Finite Element Method (GFEM is a numerical method based on the Finite Element Method (FEM, presenting as its main feature the possibility of improving the solution by means of local enrichment functions. In spite of its advantages, the method demands a complex data structure, which can be especially benefited by the Object-Oriented Programming (OOP. Even though the OOP for the traditional FEM has been extensively described in the technical literature, specific design issues related to the GFEM are yet little discussed and not clearly defined. In the present article it is described an Object-Oriented (OO class design for the GFEM, aiming to achieve a computational code that presents a flexible class structure, circumventing the difficulties associated to the method characteristics. The proposed design is evaluated by means of some numerical examples, computed using a code implemented in Python programming language.

  14. Teaching Object Permanence: An Action Research Study

    Science.gov (United States)

    Bruce, Susan M.; Vargas, Claudia

    2013-01-01

    "Object permanence," also known as "object concept" in the field of visual impairment, is one of the most important early developmental milestones. The achievement of object permanence is associated with the onset of representational thought and language. Object permanence is important to orientation, including the recognition of landmarks.…

  15. Why recognition is rational

    Directory of Open Access Journals (Sweden)

    Clintin P. Davis-Stober

    2010-07-01

    Full Text Available The Recognition Heuristic (Gigerenzer and Goldstein, 1996; Goldstein and Gigerenzer, 2002 makes the counter-intuitive prediction that a decision maker utilizing less information may do as well as, or outperform, an idealized decision maker utilizing more information. We lay a theoretical foundation for the use of single-variable heuristics such as the Recognition Heuristic as an optimal decision strategy within a linear modeling framework. We identify conditions under which over-weighting a single predictor is a mini-max strategy among a class of a priori chosen weights based on decision heuristics with respect to a measure of statistical lack of fit we call ``risk''. These strategies, in turn, outperform standard multiple regression as long as the amount of data available is limited. We also show that, under related conditions, weighting only one variable and ignoring all others produces the same risk as ignoring the single variable and weighting all others. This approach has the advantage of generalizing beyond the original environment of the Recognition Heuristic to situations with more than two choice options, binary or continuous representations of recognition, and to other single variable heuristics. We analyze the structure of data used in some prior recognition tasks and find that it matches the sufficient conditions for optimality in our results. Rather than being a poor or adequate substitute for a compensatory model, the Recognition Heuristic closely approximates an optimal strategy when a decision maker has finite data about the world.

  16. The role of the hippocampus in recognition memory.

    Science.gov (United States)

    Bird, Chris M

    2017-08-01

    Many theories of declarative memory propose that it is supported by partially separable processes underpinned by different brain structures. The hippocampus plays a critical role in binding together item and contextual information together and processing the relationships between individual items. By contrast, the processing of individual items and their later recognition can be supported by extrahippocampal regions of the medial temporal lobes (MTL), particularly when recognition is based on feelings of familiarity without the retrieval of any associated information. These theories are domain-general in that "items" might be words, faces, objects, scenes, etc. However, there is mixed evidence that item recognition does not require the hippocampus, or that familiarity-based recognition can be supported by extrahippocampal regions. By contrast, there is compelling evidence that in humans, hippocampal damage does not affect recognition memory for unfamiliar faces, whilst recognition memory for several other stimulus classes is impaired. I propose that regions outside of the hippocampus can support recognition of unfamiliar faces because they are perceived as discrete items and have no prior conceptual associations. Conversely, extrahippocampal processes are inadequate for recognition of items which (a) have been previously experienced, (b) are conceptually meaningful, or (c) are perceived as being comprised of individual elements. This account reconciles findings from primate and human studies of recognition memory. Furthermore, it suggests that while the hippocampus is critical for binding and relational processing, these processes are required for item recognition memory in most situations. Copyright © 2017 Elsevier Ltd. All rights reserved.

  17. hemaClass.org: Online One-By-One Microarray Normalization and Classification of Hematological Cancers for Precision Medicine.

    Science.gov (United States)

    Falgreen, Steffen; Ellern Bilgrau, Anders; Brøndum, Rasmus Froberg; Hjort Jakobsen, Lasse; Have, Jonas; Lindblad Nielsen, Kasper; El-Galaly, Tarec Christoffer; Bødker, Julie Støve; Schmitz, Alexander; H Young, Ken; Johnsen, Hans Erik; Dybkær, Karen; Bøgsted, Martin

    2016-01-01

    Dozens of omics based cancer classification systems have been introduced with prognostic, diagnostic, and predictive capabilities. However, they often employ complex algorithms and are only applicable on whole cohorts of patients, making them difficult to apply in a personalized clinical setting. This prompted us to create hemaClass.org, an online web application providing an easy interface to one-by-one RMA normalization of microarrays and subsequent risk classifications of diffuse large B-cell lymphoma (DLBCL) into cell-of-origin and chemotherapeutic sensitivity classes. Classification results for one-by-one array pre-processing with and without a laboratory specific RMA reference dataset were compared to cohort based classifiers in 4 publicly available datasets. Classifications showed high agreement between one-by-one and whole cohort pre-processsed data when a laboratory specific reference set was supplied. The website is essentially the R-package hemaClass accompanied by a Shiny web application. The well-documented package can be used to run the website locally or to use the developed methods programmatically. The website and R-package is relevant for biological and clinical lymphoma researchers using affymetrix U-133 Plus 2 arrays, as it provides reliable and swift methods for calculation of disease subclasses. The proposed one-by-one pre-processing method is relevant for all researchers using microarrays.

  18. Optical Pattern Recognition

    Science.gov (United States)

    Yu, Francis T. S.; Jutamulia, Suganda

    2008-10-01

    Contributors; Preface; 1. Pattern recognition with optics Francis T. S. Yu and Don A. Gregory; 2. Hybrid neural networks for nonlinear pattern recognition Taiwei Lu; 3. Wavelets, optics, and pattern recognition Yao Li and Yunglong Sheng; 4. Applications of the fractional Fourier transform to optical pattern recognition David Mendlovic, Zeev Zalesky and Haldum M. Oxaktas; 5. Optical implementation of mathematical morphology Tien-Hsin Chao; 6. Nonlinear optical correlators with improved discrimination capability for object location and recognition Leonid P. Yaroslavsky; 7. Distortion-invariant quadratic filters Gregory Gheen; 8. Composite filter synthesis as applied to pattern recognition Shizhou Yin and Guowen Lu; 9. Iterative procedures in electro-optical pattern recognition Joseph Shamir; 10. Optoelectronic hybrid system for three-dimensional object pattern recognition Guoguang Mu, Mingzhe Lu and Ying Sun; 11. Applications of photrefractive devices in optical pattern recognition Ziangyang Yang; 12. Optical pattern recognition with microlasers Eung-Gi Paek; 13. Optical properties and applications of bacteriorhodopsin Q. Wang Song and Yu-He Zhang; 14. Liquid-crystal spatial light modulators Aris Tanone and Suganda Jutamulia; 15. Representations of fully complex functions on real-time spatial light modulators Robert W. Cohn and Laurence G. Hassbrook; Index.

  19. A new kernel discriminant analysis framework for electronic nose recognition

    International Nuclear Information System (INIS)

    Zhang, Lei; Tian, Feng-Chun

    2014-01-01

    Graphical abstract: - Highlights: • This paper proposes a new discriminant analysis framework for feature extraction and recognition. • The principle of the proposed NDA is derived mathematically. • The NDA framework is coupled with kernel PCA for classification. • The proposed KNDA is compared with state of the art e-Nose recognition methods. • The proposed KNDA shows the best performance in e-Nose experiments. - Abstract: Electronic nose (e-Nose) technology based on metal oxide semiconductor gas sensor array is widely studied for detection of gas components. This paper proposes a new discriminant analysis framework (NDA) for dimension reduction and e-Nose recognition. In a NDA, the between-class and the within-class Laplacian scatter matrix are designed from sample to sample, respectively, to characterize the between-class separability and the within-class compactness by seeking for discriminant matrix to simultaneously maximize the between-class Laplacian scatter and minimize the within-class Laplacian scatter. In terms of the linear separability in high dimensional kernel mapping space and the dimension reduction of principal component analysis (PCA), an effective kernel PCA plus NDA method (KNDA) is proposed for rapid detection of gas mixture components by an e-Nose. The NDA framework is derived in this paper as well as the specific implementations of the proposed KNDA method in training and recognition process. The KNDA is examined on the e-Nose datasets of six kinds of gas components, and compared with state of the art e-Nose classification methods. Experimental results demonstrate that the proposed KNDA method shows the best performance with average recognition rate and total recognition rate as 94.14% and 95.06% which leads to a promising feature extraction and multi-class recognition in e-Nose

  20. Multi-class geospatial object detection based on a position-sensitive balancing framework for high spatial resolution remote sensing imagery

    Science.gov (United States)

    Zhong, Yanfei; Han, Xiaobing; Zhang, Liangpei

    2018-04-01

    Multi-class geospatial object detection from high spatial resolution (HSR) remote sensing imagery is attracting increasing attention in a wide range of object-related civil and engineering applications. However, the distribution of objects in HSR remote sensing imagery is location-variable and complicated, and how to accurately detect the objects in HSR remote sensing imagery is a critical problem. Due to the powerful feature extraction and representation capability of deep learning, the deep learning based region proposal generation and object detection integrated framework has greatly promoted the performance of multi-class geospatial object detection for HSR remote sensing imagery. However, due to the translation caused by the convolution operation in the convolutional neural network (CNN), although the performance of the classification stage is seldom influenced, the localization accuracies of the predicted bounding boxes in the detection stage are easily influenced. The dilemma between translation-invariance in the classification stage and translation-variance in the object detection stage has not been addressed for HSR remote sensing imagery, and causes position accuracy problems for multi-class geospatial object detection with region proposal generation and object detection. In order to further improve the performance of the region proposal generation and object detection integrated framework for HSR remote sensing imagery object detection, a position-sensitive balancing (PSB) framework is proposed in this paper for multi-class geospatial object detection from HSR remote sensing imagery. The proposed PSB framework takes full advantage of the fully convolutional network (FCN), on the basis of a residual network, and adopts the PSB framework to solve the dilemma between translation-invariance in the classification stage and translation-variance in the object detection stage. In addition, a pre-training mechanism is utilized to accelerate the training procedure

  1. Hidden neural networks: application to speech recognition

    DEFF Research Database (Denmark)

    Riis, Søren Kamaric

    1998-01-01

    We evaluate the hidden neural network HMM/NN hybrid on two speech recognition benchmark tasks; (1) task independent isolated word recognition on the Phonebook database, and (2) recognition of broad phoneme classes in continuous speech from the TIMIT database. It is shown how hidden neural networks...

  2. A contextual classifier that only requires one prototype pixel for each class

    DEFF Research Database (Denmark)

    Maletti, Gabriela Mariel; Ersbøll, Bjarne Kjær; Conradsen, Knut

    2001-01-01

    constructed with experimental data is used in this stage. The algorithm was tested with the Kappa coefficient k on synthetical images and compared with K-means (k~=0.41) and a similar scheme that uses spectral means (k~=0.75) instead of histograms (k~=0.90). Results are shown on a dermatological image......A three stage scheme for classification of multi-spectral images is proposed. In each stage, statistics of each class present in the image are estimated. The user is required to provide only one prototype pixel for each class to be seeded into a homogeneous region. The algorithm starts...... by generating optimum initial training sets, one for each class, maximizing the redundancy in the data sets. These sets are the realizations of the maximal discs centered on the prototype pixels for which it is true that all the elements belong to the same class as the center one. Afterwards a region growing...

  3. A Contextual Classifier That Only Requires One Prototype Pixel for Each Class

    DEFF Research Database (Denmark)

    Maletti, Gabriela Mariel; Ersbøll, Bjarne Kjær; Conradsen, Knut

    2002-01-01

    constructed with experimental data is used in this stage. The algorithm was tested with the Kappa coefficient κ on synthetic images and compared with K-means (κ~=0.41) and a similar scheme that uses spectral means (κ~=0.75) instead of histograms (κ~=0.90). The results are shown on a dermatological image......A three-stage scheme for the classification of multispectral images is proposed. In each stage, the statistics of each class present in the image are estimated. The user is required to provide only one prototype pixel for each class to be seeded into a homogeneous region. The algorithm starts...... by generating optimum initial training sets, one for each class, maximizing the redundancy in the data sets. These sets are the realizations of the maximal discs centered on the prototype pixels for which it is true that all the elements belong to the same class as the center one. Afterwards, a region...

  4. New automated procedure to assess context recognition memory in mice.

    Science.gov (United States)

    Reiss, David; Walter, Ondine; Bourgoin, Lucie; Kieffer, Brigitte L; Ouagazzal, Abdel-Mouttalib

    2014-11-01

    Recognition memory is an important aspect of human declarative memory and is one of the routine memory abilities altered in patients with amnestic syndrome and Alzheimer's disease. In rodents, recognition memory has been most widely assessed using the novel object preference paradigm, which exploits the spontaneous preference that animals display for novel objects. Here, we used nose-poke units instead of objects to design a simple automated method for assessing context recognition memory in mice. In the acquisition trial, mice are exposed for the first time to an operant chamber with one blinking nose-poke unit. In the choice session, a novel nonblinking nose-poke unit is inserted into an empty spatial location and the number of nose poking dedicated to each set of nose-poke unit is used as an index of recognition memory. We report that recognition performance varies as a function of the length of the acquisition period and the retention delay and is sensitive to conventional amnestic treatments. By manipulating the features of the operant chamber during a brief retrieval episode (3-min long), we further demonstrate that reconsolidation of the original contextual memory depends on the magnitude and the type of environmental changes introduced into the familiar spatial environment. These results show that the nose-poke recognition task provides a rapid and reliable way for assessing context recognition memory in mice and offers new possibilities for the deciphering of the brain mechanisms governing the reconsolidation process.

  5. Computationally efficient SVM multi-class image recognition with confidence measures

    International Nuclear Information System (INIS)

    Makili, Lazaro; Vega, Jesus; Dormido-Canto, Sebastian; Pastor, Ignacio; Murari, Andrea

    2011-01-01

    Typically, machine learning methods produce non-qualified estimates, i.e. the accuracy and reliability of the predictions are not provided. Transductive predictors are very recent classifiers able to provide, simultaneously with the prediction, a couple of values (confidence and credibility) to reflect the quality of the prediction. Usually, a drawback of the transductive techniques for huge datasets and large dimensionality is the high computational time. To overcome this issue, a more efficient classifier has been used in a multi-class image classification problem in the TJ-II stellarator database. It is based on the creation of a hash function to generate several 'one versus the rest' classifiers for every class. By using Support Vector Machines as the underlying classifier, a comparison between the pure transductive approach and the new method has been performed. In both cases, the success rates are high and the computation time with the new method is up to 0.4 times the old one.

  6. Activity and function recognition for moving and static objects in urban environments from wide-area persistent surveillance inputs

    Science.gov (United States)

    Levchuk, Georgiy; Bobick, Aaron; Jones, Eric

    2010-04-01

    In this paper, we describe results from experimental analysis of a model designed to recognize activities and functions of moving and static objects from low-resolution wide-area video inputs. Our model is based on representing the activities and functions using three variables: (i) time; (ii) space; and (iii) structures. The activity and function recognition is achieved by imposing lexical, syntactic, and semantic constraints on the lower-level event sequences. In the reported research, we have evaluated the utility and sensitivity of several algorithms derived from natural language processing and pattern recognition domains. We achieved high recognition accuracy for a wide range of activity and function types in the experiments using Electro-Optical (EO) imagery collected by Wide Area Airborne Surveillance (WAAS) platform.

  7. Incremental Nonnegative Matrix Factorization for Face Recognition

    Directory of Open Access Journals (Sweden)

    Wen-Sheng Chen

    2008-01-01

    Full Text Available Nonnegative matrix factorization (NMF is a promising approach for local feature extraction in face recognition tasks. However, there are two major drawbacks in almost all existing NMF-based methods. One shortcoming is that the computational cost is expensive for large matrix decomposition. The other is that it must conduct repetitive learning, when the training samples or classes are updated. To overcome these two limitations, this paper proposes a novel incremental nonnegative matrix factorization (INMF for face representation and recognition. The proposed INMF approach is based on a novel constraint criterion and our previous block strategy. It thus has some good properties, such as low computational complexity, sparse coefficient matrix. Also, the coefficient column vectors between different classes are orthogonal. In particular, it can be applied to incremental learning. Two face databases, namely FERET and CMU PIE face databases, are selected for evaluation. Compared with PCA and some state-of-the-art NMF-based methods, our INMF approach gives the best performance.

  8. On CSM classes via Chern-Fulton classes of f-schemes

    OpenAIRE

    Fullwood, James; Wang, Dongxu

    2015-01-01

    The Chern-Fulton class is a generalization of Chern class to the realm of arbitrary embeddable schemes. While Chern-Fulton classes are sensitive to non-reduced scheme structure, they are not sensitive to possible singularities of the underlying support, thus at first glance are not interesting from a singularity theory viewpoint. However, we introduce a class of formal objects which we think of as `fractional schemes', or f-schemes for short, and then show that when one broadens the domain of...

  9. Objective and subjective indicators of happiness in Brazil: the mediating role of social class.

    Science.gov (United States)

    Islam, Gazi; Wills-Herrera, Eduardo; Hamilton, Marilyn

    2009-04-01

    The authors tested the proposition that monetary household income affects subjective well-being (E. Deiner, E. M. Suh, R. E. Lucas, & H. L. Smith, 1999) through the mediating mechanisms of objective and subjective social classes. The present authors drew a representative sample in a door-to-door survey format from a Brazilian urban center. Using a back-translated version of E. Diener, R. A. Emmons, R. J. Larson, and S. Griffin's (1985) Satisfaction With Life Scale, the present authors demonstrated a significant relation with income. However, this effect was mediated by objectively and subjectively measured social classes. These effects reinforce, extend, and internationally generalize the Person x Situation perspective elaborated by E. Diener et al. (1999).

  10. Stability-class determination: a comparison for one site

    International Nuclear Information System (INIS)

    Bowen, B.M.; Dewart, J.M.; Chen, A.I.

    1983-01-01

    The Pasquill method of determining stability class at a site with irregular terrain with other commonly used methods: vertical temperature difference (#betta#T); Richardson number (Ri) and Bulk Richardson number (Ri/sub B/); and horizontal standard deviation of wind and vertical standard deviation of wind. Also, the indirect methods of measuring turbulence, such as the Pasquill method, are compared to direct measures of turbulence. The various methods for determining stability class are analyzed and compared with the Pasquill classification scheme at 2 sites with irregular terrain. The Pasquill categories were estimated objectively and compared with other stability indicators for 15-minute periods over a year. The results show that near-surface #betta#T distinguishes the neutral category very well. However, it does not differentiate the specific stable and unstable categories very well. Both the Ri and Ri/sub B/, indicators of both thermal and mechanical turbulence, correlate very well with and distinguish the different stability categories. Due to the irregular terrain, the various methods of determining stability may be even better indicators of turbulence and diffusion if the wind direction were taken into account. It is suggested that further study investigate the methods by wind direction

  11. Impulsivity and novel object recognition test of rat model for vascular cognitive impairment after antipsychotics treatment

    Directory of Open Access Journals (Sweden)

    Ronny T Wirasto

    2016-12-01

    Full Text Available ABSTRACT Vascular cognitive impairment (VCI is a common condition in which no standard treatment has been approved. VCI is often accompanied by behavioral problems which require psychiatric interventions. The common therapeutic agent used for the acute management is antipsychotic injections. Current findings showed that atypical antipsychotic possess better safety profile for treating behavioral problems related to VCI compared to typical antipsychotic. In this study, we induced VCI in Sprague Dawley rats between 6-8 weeks old using bilateral carotid communist artery occlusion technique. The subjects were divided into 4 treatment groups: sham, olanzapine, haloperidol, and risperidone groups. Subjects received intramuscular injections of subsequent drugs for 3 days post VCI induction. Impulsive behavior and object recognition were examined using cliff jumping test and novel object recognition test. The analyses results showed that impulsive behavior was lower in the olanzapine and haloperidol groups compared to sham group, although it was not statistically significant (p = 0.651. The results also showed that there were no significant differences in the time spent exploring old and novel objects in all groups (p = 0.945;0.637 respectively. In conclusion, antipsychotic injection might not be effective to control impulsive behavior post VCI induction.

  12. Objective Prediction of Hearing Aid Benefit Across Listener Groups Using Machine Learning: Speech Recognition Performance With Binaural Noise-Reduction Algorithms

    Science.gov (United States)

    Schädler, Marc R.; Warzybok, Anna; Kollmeier, Birger

    2018-01-01

    The simulation framework for auditory discrimination experiments (FADE) was adopted and validated to predict the individual speech-in-noise recognition performance of listeners with normal and impaired hearing with and without a given hearing-aid algorithm. FADE uses a simple automatic speech recognizer (ASR) to estimate the lowest achievable speech reception thresholds (SRTs) from simulated speech recognition experiments in an objective way, independent from any empirical reference data. Empirical data from the literature were used to evaluate the model in terms of predicted SRTs and benefits in SRT with the German matrix sentence recognition test when using eight single- and multichannel binaural noise-reduction algorithms. To allow individual predictions of SRTs in binaural conditions, the model was extended with a simple better ear approach and individualized by taking audiograms into account. In a realistic binaural cafeteria condition, FADE explained about 90% of the variance of the empirical SRTs for a group of normal-hearing listeners and predicted the corresponding benefits with a root-mean-square prediction error of 0.6 dB. This highlights the potential of the approach for the objective assessment of benefits in SRT without prior knowledge about the empirical data. The predictions for the group of listeners with impaired hearing explained 75% of the empirical variance, while the individual predictions explained less than 25%. Possibly, additional individual factors should be considered for more accurate predictions with impaired hearing. A competing talker condition clearly showed one limitation of current ASR technology, as the empirical performance with SRTs lower than −20 dB could not be predicted. PMID:29692200

  13. STDP-based spiking deep convolutional neural networks for object recognition.

    Science.gov (United States)

    Kheradpisheh, Saeed Reza; Ganjtabesh, Mohammad; Thorpe, Simon J; Masquelier, Timothée

    2018-03-01

    Previous studies have shown that spike-timing-dependent plasticity (STDP) can be used in spiking neural networks (SNN) to extract visual features of low or intermediate complexity in an unsupervised manner. These studies, however, used relatively shallow architectures, and only one layer was trainable. Another line of research has demonstrated - using rate-based neural networks trained with back-propagation - that having many layers increases the recognition robustness, an approach known as deep learning. We thus designed a deep SNN, comprising several convolutional (trainable with STDP) and pooling layers. We used a temporal coding scheme where the most strongly activated neurons fire first, and less activated neurons fire later or not at all. The network was exposed to natural images. Thanks to STDP, neurons progressively learned features corresponding to prototypical patterns that were both salient and frequent. Only a few tens of examples per category were required and no label was needed. After learning, the complexity of the extracted features increased along the hierarchy, from edge detectors in the first layer to object prototypes in the last layer. Coding was very sparse, with only a few thousands spikes per image, and in some cases the object category could be reasonably well inferred from the activity of a single higher-order neuron. More generally, the activity of a few hundreds of such neurons contained robust category information, as demonstrated using a classifier on Caltech 101, ETH-80, and MNIST databases. We also demonstrate the superiority of STDP over other unsupervised techniques such as random crops (HMAX) or auto-encoders. Taken together, our results suggest that the combination of STDP with latency coding may be a key to understanding the way that the primate visual system learns, its remarkable processing speed and its low energy consumption. These mechanisms are also interesting for artificial vision systems, particularly for hardware

  14. Automatic target recognition using a feature-based optical neural network

    Science.gov (United States)

    Chao, Tien-Hsin

    1992-01-01

    An optical neural network based upon the Neocognitron paradigm (K. Fukushima et al. 1983) is introduced. A novel aspect of the architectural design is shift-invariant multichannel Fourier optical correlation within each processing layer. Multilayer processing is achieved by iteratively feeding back the output of the feature correlator to the input spatial light modulator and updating the Fourier filters. By training the neural net with characteristic features extracted from the target images, successful pattern recognition with intra-class fault tolerance and inter-class discrimination is achieved. A detailed system description is provided. Experimental demonstration of a two-layer neural network for space objects discrimination is also presented.

  15. Robust Pedestrian Tracking and Recognition from FLIR Video: A Unified Approach via Sparse Coding

    Directory of Open Access Journals (Sweden)

    Xin Li

    2014-06-01

    Full Text Available Sparse coding is an emerging method that has been successfully applied to both robust object tracking and recognition in the vision literature. In this paper, we propose to explore a sparse coding-based approach toward joint object tracking-and-recognition and explore its potential in the analysis of forward-looking infrared (FLIR video to support nighttime machine vision systems. A key technical contribution of this work is to unify existing sparse coding-based approaches toward tracking and recognition under the same framework, so that they can benefit from each other in a closed-loop. On the one hand, tracking the same object through temporal frames allows us to achieve improved recognition performance through dynamical updating of template/dictionary and combining multiple recognition results; on the other hand, the recognition of individual objects facilitates the tracking of multiple objects (i.e., walking pedestrians, especially in the presence of occlusion within a crowded environment. We report experimental results on both the CASIAPedestrian Database and our own collected FLIR video database to demonstrate the effectiveness of the proposed joint tracking-and-recognition approach.

  16. Excess influx of Zn(2+) into dentate granule cells affects object recognition memory via attenuated LTP.

    Science.gov (United States)

    Suzuki, Miki; Fujise, Yuki; Tsuchiya, Yuka; Tamano, Haruna; Takeda, Atsushi

    2015-08-01

    The influx of extracellular Zn(2+) into dentate granule cells is nonessential for dentate gyrus long-term potentiation (LTP) and the physiological significance of extracellular Zn(2+) dynamics is unknown in the dentate gyrus. Excess increase in extracellular Zn(2+) in the hippocampal CA1, which is induced with excitation of zincergic neurons, induces memory deficit via excess influx of Zn(2+) into CA1 pyramidal cells. In the present study, it was examined whether extracellular Zn(2+) induces object recognition memory deficit via excess influx of Zn(2+) into dentate granule cells. KCl (100 mM, 2 µl) was locally injected into the dentate gyrus. The increase in intracellular Zn(2+) in dentate granule cells induced with high K(+) was blocked by co-injection of CaEDTA and CNQX, an extracellular Zn(2+) chelator and an AMPA receptor antagonist, respectively, suggesting that high K(+) increases the influx of Zn(2+) into dentate granule cells via AMPA receptor activation. Dentate gyrus LTP induction was attenuated 1 h after KCl injection into the dentate gyrus and also attenuated when KCl was injected 5 min after the induction. Memory deficit was induced when training of object recognition test was performed 1 h after KCl injection into the dentate gyrus and also induced when KCl was injected 5 min after the training. High K(+)-induced impairments of LTP and memory were rescued by co-injection of CaEDTA. These results indicate that excess influx of Zn(2+) into dentate granule cells via AMPA receptor activation affects object recognition memory via attenuated LTP induction. Even in the dentate gyrus where is scarcely innervated by zincergic neurons, it is likely that extracellular Zn(2+) homeostasis is strictly regulated for cognition. Copyright © 2015 Elsevier Ltd. All rights reserved.

  17. Emerging technologies with potential for objectively evaluating speech recognition skills.

    Science.gov (United States)

    Rawool, Vishakha Waman

    2016-01-01

    Work-related exposure to noise and other ototoxins can cause damage to the cochlea, synapses between the inner hair cells, the auditory nerve fibers, and higher auditory pathways, leading to difficulties in recognizing speech. Procedures designed to determine speech recognition scores (SRS) in an objective manner can be helpful in disability compensation cases where the worker claims to have poor speech perception due to exposure to noise or ototoxins. Such measures can also be helpful in determining SRS in individuals who cannot provide reliable responses to speech stimuli, including patients with Alzheimer's disease, traumatic brain injuries, and infants with and without hearing loss. Cost-effective neural monitoring hardware and software is being rapidly refined due to the high demand for neurogaming (games involving the use of brain-computer interfaces), health, and other applications. More specifically, two related advances in neuro-technology include relative ease in recording neural activity and availability of sophisticated analysing techniques. These techniques are reviewed in the current article and their applications for developing objective SRS procedures are proposed. Issues related to neuroaudioethics (ethics related to collection of neural data evoked by auditory stimuli including speech) and neurosecurity (preservation of a person's neural mechanisms and free will) are also discussed.

  18. Genetic Mapping in Mice Reveals the Involvement of Pcdh9 in Long-Term Social and Object Recognition and Sensorimotor Development.

    Science.gov (United States)

    Bruining, Hilgo; Matsui, Asuka; Oguro-Ando, Asami; Kahn, René S; Van't Spijker, Heleen M; Akkermans, Guus; Stiedl, Oliver; van Engeland, Herman; Koopmans, Bastijn; van Lith, Hein A; Oppelaar, Hugo; Tieland, Liselotte; Nonkes, Lourens J; Yagi, Takeshi; Kaneko, Ryosuke; Burbach, J Peter H; Yamamoto, Nobuhiko; Kas, Martien J

    2015-10-01

    Quantitative genetic analysis of basic mouse behaviors is a powerful tool to identify novel genetic phenotypes contributing to neurobehavioral disorders. Here, we analyzed genetic contributions to single-trial, long-term social and nonsocial recognition and subsequently studied the functional impact of an identified candidate gene on behavioral development. Genetic mapping of single-trial social recognition was performed in chromosome substitution strains, a sophisticated tool for detecting quantitative trait loci (QTL) of complex traits. Follow-up occurred by generating and testing knockout (KO) mice of a selected QTL candidate gene. Functional characterization of these mice was performed through behavioral and neurological assessments across developmental stages and analyses of gene expression and brain morphology. Chromosome substitution strain 14 mapping studies revealed an overlapping QTL related to long-term social and object recognition harboring Pcdh9, a cell-adhesion gene previously associated with autism spectrum disorder. Specific long-term social and object recognition deficits were confirmed in homozygous (KO) Pcdh9-deficient mice, while heterozygous mice only showed long-term social recognition impairment. The recognition deficits in KO mice were not associated with alterations in perception, multi-trial discrimination learning, sociability, behavioral flexibility, or fear memory. Rather, KO mice showed additional impairments in sensorimotor development reflected by early touch-evoked biting, rotarod performance, and sensory gating deficits. This profile emerged with structural changes in deep layers of sensory cortices, where Pcdh9 is selectively expressed. This behavior-to-gene study implicates Pcdh9 in cognitive functions required for long-term social and nonsocial recognition. This role is supported by the involvement of Pcdh9 in sensory cortex development and sensorimotor phenotypes. Copyright © 2015 Society of Biological Psychiatry. Published

  19. Two speed factors of visual recognition independently correlated with fluid intelligence.

    Science.gov (United States)

    Tachibana, Ryosuke; Namba, Yuri; Noguchi, Yasuki

    2014-01-01

    Growing evidence indicates a moderate but significant relationship between processing speed in visuo-cognitive tasks and general intelligence. On the other hand, findings from neuroscience proposed that the primate visual system consists of two major pathways, the ventral pathway for objects recognition and the dorsal pathway for spatial processing and attentive analysis. Previous studies seeking for visuo-cognitive factors of human intelligence indicated a significant correlation between fluid intelligence and the inspection time (IT), an index for a speed of object recognition performed in the ventral pathway. We thus presently examined a possibility that neural processing speed in the dorsal pathway also represented a factor of intelligence. Specifically, we used the mental rotation (MR) task, a popular psychometric measure for mental speed of spatial processing in the dorsal pathway. We found that the speed of MR was significantly correlated with intelligence scores, while it had no correlation with one's IT (recognition speed of visual objects). Our results support the new possibility that intelligence could be explained by two types of mental speed, one related to object recognition (IT) and another for manipulation of mental images (MR).

  20. Polyacene and a new class of quasi-one-dimensional conductors

    International Nuclear Information System (INIS)

    Kivelson, S.; Chapman, O.L.

    1983-01-01

    Most one-dimensional conductors are quite similar since the Fermi surface is a point and the electron energy dispersion relation near the Fermi surface is linear. It is pointed out that in polyacene the Fermi surface lies at the edge of the Brillouin zone, but that an accidental degeneracy between the valence and conduction bands makes it metallic nonetheless. The dispersion relation is therefore quadratic, and the density of states diverges at the Fermi surface. Thus, polyacene [(C 4 H 2 )/sub n/] and its possible derivatives represent a conceptually new class of quasi-one-dimensional conductors. Moreover, we find that this class of materials has the possibility of possessing interesting condensed phases including high-temperature superconductivity and ferromagnetism

  1. Supervised Object Class Colour Normalisation

    DEFF Research Database (Denmark)

    Riabchenko, Ekatarina; Lankinen, Jukka; Buch, Anders Glent

    2013-01-01

    . In this work, we develop a such colour normalisation technique, where true colours are not important per se but where examples of same classes have photometrically consistent appearance. This is achieved by supervised estimation of a class specic canonical colour space where the examples have minimal variation......Colour is an important cue in many applications of computer vision and image processing, but robust usage often requires estimation of the unknown illuminant colour. Usually, to obtain images invariant to the illumination conditions under which they were taken, color normalisation is used...... in their colours. We demonstrate the effectiveness of our method with qualitative and quantitative examples from the Caltech-101 data set and a real application of 3D pose estimation for robot grasping....

  2. Large-scale weakly supervised object localization via latent category learning.

    Science.gov (United States)

    Chong Wang; Kaiqi Huang; Weiqiang Ren; Junge Zhang; Maybank, Steve

    2015-04-01

    Localizing objects in cluttered backgrounds is challenging under large-scale weakly supervised conditions. Due to the cluttered image condition, objects usually have large ambiguity with backgrounds. Besides, there is also a lack of effective algorithm for large-scale weakly supervised localization in cluttered backgrounds. However, backgrounds contain useful latent information, e.g., the sky in the aeroplane class. If this latent information can be learned, object-background ambiguity can be largely reduced and background can be suppressed effectively. In this paper, we propose the latent category learning (LCL) in large-scale cluttered conditions. LCL is an unsupervised learning method which requires only image-level class labels. First, we use the latent semantic analysis with semantic object representation to learn the latent categories, which represent objects, object parts or backgrounds. Second, to determine which category contains the target object, we propose a category selection strategy by evaluating each category's discrimination. Finally, we propose the online LCL for use in large-scale conditions. Evaluation on the challenging PASCAL Visual Object Class (VOC) 2007 and the large-scale imagenet large-scale visual recognition challenge 2013 detection data sets shows that the method can improve the annotation precision by 10% over previous methods. More importantly, we achieve the detection precision which outperforms previous results by a large margin and can be competitive to the supervised deformable part model 5.0 baseline on both data sets.

  3. Static Members of Classes in C#

    Directory of Open Access Journals (Sweden)

    Adrian LUPASC

    2017-12-01

    Full Text Available The C# language is object-oriented, which is why the declared member data must be part of a class. Thus, there is no possibility to declare certain variables that can be accessed from anywhere within the application, as it happens, for example, with global variables at the C language level. Making this work in C# is possible through static members of the class. Declaring a class implies defining some of its member data that later receive values when creating each object. A static member of the class can be interpreted as belonging only to the class, not to the objects subsequently created, which means that for the non-static data, there are as many children as there were objects created, while for the static ones there is only one copy, regardless of the number of created objects. In this regard, this paper presents the main aspects that characterize these abstract concepts of object oriented programming in general and C# language in particular, detailing how to develop an application that includes both static and non-static members. At the same time, particularities in the mirror for the two types of data, restrictions on use and potential limitations are presented.

  4. Fine-grained recognition of plants from images.

    Science.gov (United States)

    Šulc, Milan; Matas, Jiří

    2017-01-01

    Fine-grained recognition of plants from images is a challenging computer vision task, due to the diverse appearance and complex structure of plants, high intra-class variability and small inter-class differences. We review the state-of-the-art and discuss plant recognition tasks, from identification of plants from specific plant organs to general plant recognition "in the wild". We propose texture analysis and deep learning methods for different plant recognition tasks. The methods are evaluated and compared them to the state-of-the-art. Texture analysis is only applied to images with unambiguous segmentation (bark and leaf recognition), whereas CNNs are only applied when sufficiently large datasets are available. The results provide an insight in the complexity of different plant recognition tasks. The proposed methods outperform the state-of-the-art in leaf and bark classification and achieve very competitive results in plant recognition "in the wild". The results suggest that recognition of segmented leaves is practically a solved problem, when high volumes of training data are available. The generality and higher capacity of state-of-the-art CNNs makes them suitable for plant recognition "in the wild" where the views on plant organs or plants vary significantly and the difficulty is increased by occlusions and background clutter.

  5. Reader error, object recognition, and visual search

    Science.gov (United States)

    Kundel, Harold L.

    2004-05-01

    Small abnormalities such as hairline fractures, lung nodules and breast tumors are missed by competent radiologists with sufficient frequency to make them a matter of concern to the medical community; not only because they lead to litigation but also because they delay patient care. It is very easy to attribute misses to incompetence or inattention. To do so may be placing an unjustified stigma on the radiologists involved and may allow other radiologists to continue a false optimism that it can never happen to them. This review presents some of the fundamentals of visual system function that are relevant to understanding the search for and the recognition of small targets embedded in complicated but meaningful backgrounds like chests and mammograms. It presents a model for visual search that postulates a pre-attentive global analysis of the retinal image followed by foveal checking fixations and eventually discovery scanning. The model will be used to differentiate errors of search, recognition and decision making. The implications for computer aided diagnosis and for functional workstation design are discussed.

  6. Now you see it, now you don’t: The context dependent nature of category-effects in visual object recognition

    DEFF Research Database (Denmark)

    Gerlach, Christian; Toft, Kristian Olesen

    2011-01-01

    In two experiments, we test predictions regarding processing advantages/disadvantages for natural objects and artefacts in visual object recognition. Varying three important parameters*degree of perceptual differentiation, stimulus format, and stimulus exposure duration*we show how different......-effects are products of common operations which are differentially affected by the structural similarity among objects (with natural objects being more structurally similar than artefacts). The potentially most important aspect of the present study is the demonstration that category-effects are very context dependent...

  7. Tensor Rank Preserving Discriminant Analysis for Facial Recognition.

    Science.gov (United States)

    Tao, Dapeng; Guo, Yanan; Li, Yaotang; Gao, Xinbo

    2017-10-12

    Facial recognition, one of the basic topics in computer vision and pattern recognition, has received substantial attention in recent years. However, for those traditional facial recognition algorithms, the facial images are reshaped to a long vector, thereby losing part of the original spatial constraints of each pixel. In this paper, a new tensor-based feature extraction algorithm termed tensor rank preserving discriminant analysis (TRPDA) for facial image recognition is proposed; the proposed method involves two stages: in the first stage, the low-dimensional tensor subspace of the original input tensor samples was obtained; in the second stage, discriminative locality alignment was utilized to obtain the ultimate vector feature representation for subsequent facial recognition. On the one hand, the proposed TRPDA algorithm fully utilizes the natural structure of the input samples, and it applies an optimization criterion that can directly handle the tensor spectral analysis problem, thereby decreasing the computation cost compared those traditional tensor-based feature selection algorithms. On the other hand, the proposed TRPDA algorithm extracts feature by finding a tensor subspace that preserves most of the rank order information of the intra-class input samples. Experiments on the three facial databases are performed here to determine the effectiveness of the proposed TRPDA algorithm.

  8. Conversion of short-term to long-term memory in the novel object recognition paradigm.

    Science.gov (United States)

    Moore, Shannon J; Deshpande, Kaivalya; Stinnett, Gwen S; Seasholtz, Audrey F; Murphy, Geoffrey G

    2013-10-01

    It is well-known that stress can significantly impact learning; however, whether this effect facilitates or impairs the resultant memory depends on the characteristics of the stressor. Investigation of these dynamics can be confounded by the role of the stressor in motivating performance in a task. Positing a cohesive model of the effect of stress on learning and memory necessitates elucidating the consequences of stressful stimuli independently from task-specific functions. Therefore, the goal of this study was to examine the effect of manipulating a task-independent stressor (elevated light level) on short-term and long-term memory in the novel object recognition paradigm. Short-term memory was elicited in both low light and high light conditions, but long-term memory specifically required high light conditions during the acquisition phase (familiarization trial) and was independent of the light level during retrieval (test trial). Additionally, long-term memory appeared to be independent of stress-mediated glucocorticoid release, as both low and high light produced similar levels of plasma corticosterone, which further did not correlate with subsequent memory performance. Finally, both short-term and long-term memory showed no savings between repeated experiments suggesting that this novel object recognition paradigm may be useful for longitudinal studies, particularly when investigating treatments to stabilize or enhance weak memories in neurodegenerative diseases or during age-related cognitive decline. Copyright © 2013 Elsevier Inc. All rights reserved.

  9. Structure and Evolution of Kuiper Belt Objects: The Case for Compositional Classes

    Science.gov (United States)

    McKinnon, William B.; Prialnik, D.; Stern, S. A.

    2007-10-01

    Kuiper belt objects (KBOs) accreted from a mélange of ices, carbonaceous matter, and rock of mixed interstellar and solar nebular provenance. The transneptunian region, where this accretion took place, was likely more radially compact than today. This and the influence of gas drag during the solar nebula epoch argue for more rapid KBO accretion than usually considered. Early evolution of KBOs was largely the result of radiogenic heating, with both short-term and long-term contributions being potentially important. Depending on rock content and porous conductivity, KBO interiors may have reached relatively high temperatures. Models suggest that KBOs likely lost very volatile ices during early evolution, whereas less volatile ices should be retained in cold, less altered subsurface layers; initially amorphous ice may have crystallized in the interior as well, releasing trapped volatiles. Generally, KBOs should be stratified in terms of composition and porosity, albeit subject to impact disruption and collisional stripping. KBOs are thus unlikely to be "the most pristine objects in the Solar System.” Large (dwarf planet) KBOs may be fully differentiated. KBO surface color and compositional classes are usually discussed in terms of "nature vs. nurture,” i.e., a generic primordial composition vs. surface processing, but the true nature of KBOs also depends on how they have evolved. The broad range of albedos now found in the Kuiper belt, deep water-ice absorptions on some objects, evidence for differentiation of Pluto and 2003 EL61, and a range of densities incompatible with a single, primordial composition and variable porosity strongly imply significant, intrinsic compositional differences among KBOs. The interplay of formation zone (accretion rate), body size, and dynamical (collisional) history may yield KBO compositional classes (and their spectral correlates) that recall the different classes of asteroids in the inner Solar System, but whose members are

  10. Performance improvement of multi-class detection using greedy algorithm for Viola-Jones cascade selection

    Science.gov (United States)

    Tereshin, Alexander A.; Usilin, Sergey A.; Arlazarov, Vladimir V.

    2018-04-01

    This paper aims to study the problem of multi-class object detection in video stream with Viola-Jones cascades. An adaptive algorithm for selecting Viola-Jones cascade based on greedy choice strategy in solution of the N-armed bandit problem is proposed. The efficiency of the algorithm on the problem of detection and recognition of the bank card logos in the video stream is shown. The proposed algorithm can be effectively used in documents localization and identification, recognition of road scene elements, localization and tracking of the lengthy objects , and for solving other problems of rigid object detection in a heterogeneous data flows. The computational efficiency of the algorithm makes it possible to use it both on personal computers and on mobile devices based on processors with low power consumption.

  11. Under what conditions is recognition spared relative to recall after selective hippocampal damage in humans?

    Science.gov (United States)

    Holdstock, J S; Mayes, A R; Roberts, N; Cezayirli, E; Isaac, C L; O'Reilly, R C; Norman, K A

    2002-01-01

    The claim that recognition memory is spared relative to recall after focal hippocampal damage has been disputed in the literature. We examined this claim by investigating object and object-location recall and recognition memory in a patient, YR, who has adult-onset selective hippocampal damage. Our aim was to identify the conditions under which recognition was spared relative to recall in this patient. She showed unimpaired forced-choice object recognition but clearly impaired recall, even when her control subjects found the object recognition task to be numerically harder than the object recall task. However, on two other recognition tests, YR's performance was not relatively spared. First, she was clearly impaired at an equivalently difficult yes/no object recognition task, but only when targets and foils were very similar. Second, YR was clearly impaired at forced-choice recognition of object-location associations. This impairment was also unrelated to difficulty because this task was no more difficult than the forced-choice object recognition task for control subjects. The clear impairment of yes/no, but not of forced-choice, object recognition after focal hippocampal damage, when targets and foils are very similar, is predicted by the neural network-based Complementary Learning Systems model of recognition. This model postulates that recognition is mediated by hippocampally dependent recollection and cortically dependent familiarity; thus hippocampal damage should not impair item familiarity. The model postulates that familiarity is ineffective when very similar targets and foils are shown one at a time and subjects have to identify which items are old (yes/no recognition). In contrast, familiarity is effective in discriminating which of similar targets and foils, seen together, is old (forced-choice recognition). Independent evidence from the remember/know procedure also indicates that YR's familiarity is normal. The Complementary Learning Systems model can

  12. Fast and flexible 3D object recognition solutions for machine vision applications

    Science.gov (United States)

    Effenberger, Ira; Kühnle, Jens; Verl, Alexander

    2013-03-01

    In automation and handling engineering, supplying work pieces between different stages along the production process chain is of special interest. Often the parts are stored unordered in bins or lattice boxes and hence have to be separated and ordered for feeding purposes. An alternative to complex and spacious mechanical systems such as bowl feeders or conveyor belts, which are typically adapted to the parts' geometry, is using a robot to grip the work pieces out of a bin or from a belt. Such applications are in need of reliable and precise computer-aided object detection and localization systems. For a restricted range of parts, there exists a variety of 2D image processing algorithms that solve the recognition problem. However, these methods are often not well suited for the localization of randomly stored parts. In this paper we present a fast and flexible 3D object recognizer that localizes objects by identifying primitive features within the objects. Since technical work pieces typically consist to a substantial degree of geometric primitives such as planes, cylinders and cones, such features usually carry enough information in order to determine the position of the entire object. Our algorithms use 3D best-fitting combined with an intelligent data pre-processing step. The capability and performance of this approach is shown by applying the algorithms to real data sets of different industrial test parts in a prototypical bin picking demonstration system.

  13. Constant Light Desynchronizes Olfactory versus Object and Visuospatial Recognition Memory Performance.

    Science.gov (United States)

    Tam, Shu K E; Hasan, Sibah; Choi, Harry M C; Brown, Laurence A; Jagannath, Aarti; Hughes, Steven; Hankins, Mark W; Foster, Russell G; Vyazovskiy, Vladyslav V; Bannerman, David M; Peirson, Stuart N

    2017-03-29

    Circadian rhythms optimize physiology and behavior to the varying demands of the 24 h day. The master circadian clock is located in the suprachiasmatic nuclei (SCN) of the hypothalamus and it regulates circadian oscillators in tissues throughout the body to prevent internal desynchrony. Here, we demonstrate for the first time that, under standard 12 h:12 h light/dark (LD) cycles, object, visuospatial, and olfactory recognition performance in C57BL/6J mice is consistently better at midday relative to midnight. However, under repeated exposure to constant light ( r LL), recognition performance becomes desynchronized, with object and visuospatial performance better at subjective midday and olfactory performance better at subjective midnight. This desynchrony in behavioral performance is mirrored by changes in expression of the canonical clock genes Period1 and Period2 ( Per1 and Per2 ), as well as the immediate-early gene Fos in the SCN, dorsal hippocampus, and olfactory bulb. Under r LL, rhythmic Per1 and Fos expression is attenuated in the SCN. In contrast, hippocampal gene expression remains rhythmic, mirroring object and visuospatial performance. Strikingly, Per1 and Fos expression in the olfactory bulb is reversed, mirroring the inverted olfactory performance. Temporal desynchrony among these regions does not result in arrhythmicity because core body temperature and exploratory activity rhythms persist under r LL. Our data provide the first demonstration that abnormal lighting conditions can give rise to temporal desynchrony between autonomous circadian oscillators in different regions, with different consequences for performance across different sensory domains. Such a dispersed network of dissociable circadian oscillators may provide greater flexibility when faced with conflicting environmental signals. SIGNIFICANCE STATEMENT A master circadian clock in the suprachiasmatic nuclei (SCN) of the hypothalamus regulates physiology and behavior across the 24 h day by

  14. Constant Light Desynchronizes Olfactory versus Object and Visuospatial Recognition Memory Performance

    Science.gov (United States)

    Tam, Shu K.E.; Hasan, Sibah; Brown, Laurence A.; Jagannath, Aarti; Hankins, Mark W.; Foster, Russell G.; Vyazovskiy, Vladyslav V.

    2017-01-01

    Circadian rhythms optimize physiology and behavior to the varying demands of the 24 h day. The master circadian clock is located in the suprachiasmatic nuclei (SCN) of the hypothalamus and it regulates circadian oscillators in tissues throughout the body to prevent internal desynchrony. Here, we demonstrate for the first time that, under standard 12 h:12 h light/dark (LD) cycles, object, visuospatial, and olfactory recognition performance in C57BL/6J mice is consistently better at midday relative to midnight. However, under repeated exposure to constant light (rLL), recognition performance becomes desynchronized, with object and visuospatial performance better at subjective midday and olfactory performance better at subjective midnight. This desynchrony in behavioral performance is mirrored by changes in expression of the canonical clock genes Period1 and Period2 (Per1 and Per2), as well as the immediate-early gene Fos in the SCN, dorsal hippocampus, and olfactory bulb. Under rLL, rhythmic Per1 and Fos expression is attenuated in the SCN. In contrast, hippocampal gene expression remains rhythmic, mirroring object and visuospatial performance. Strikingly, Per1 and Fos expression in the olfactory bulb is reversed, mirroring the inverted olfactory performance. Temporal desynchrony among these regions does not result in arrhythmicity because core body temperature and exploratory activity rhythms persist under rLL. Our data provide the first demonstration that abnormal lighting conditions can give rise to temporal desynchrony between autonomous circadian oscillators in different regions, with different consequences for performance across different sensory domains. Such a dispersed network of dissociable circadian oscillators may provide greater flexibility when faced with conflicting environmental signals. SIGNIFICANCE STATEMENT A master circadian clock in the suprachiasmatic nuclei (SCN) of the hypothalamus regulates physiology and behavior across the 24 h day by

  15. Translation Ambiguity but Not Word Class Predicts Translation Performance

    Science.gov (United States)

    Prior, Anat; Kroll, Judith F.; Macwhinney, Brian

    2013-01-01

    We investigated the influence of word class and translation ambiguity on cross-linguistic representation and processing. Bilingual speakers of English and Spanish performed translation production and translation recognition tasks on nouns and verbs in both languages. Words either had a single translation or more than one translation. Translation…

  16. A Temporally Distinct Role for Group I and Group II Metabotropic Glutamate Receptors in Object Recognition Memory

    Science.gov (United States)

    Brown, Malcolm Watson; Warburton, Elizabeth Clea; Barker, Gareth Robert Isaac; Bashir, Zafar Iqbal

    2006-01-01

    Recognition memory, involving the ability to discriminate between a novel and familiar object, depends on the integrity of the perirhinal cortex (PRH). Glutamate, the main excitatory neurotransmitter in the cortex, is essential for many types of memory processes. Of the subtypes of glutamate receptor, metabotropic receptors (mGluRs) have received…

  17. Object Oriented Programming in Director

    Directory of Open Access Journals (Sweden)

    Marian DARDALA

    2006-01-01

    Full Text Available Director is one of the most popular authoring software. As software for developing multimedia applications, Director is an object oriented programming environment. A very important issue to develop multimedia applications is the designing of their own classes. This paper presents the particular aspects concerning the available facilities offered by Lingo to design classes and to generate objects.

  18. Landsat TM band 431 combine on clustering analysis for pattern recognition land use using idrisi 4.2 software

    International Nuclear Information System (INIS)

    Wiweka, Arief H.; Izzawati, Tjahyaningsih A.

    1997-01-01

    The recognition of earth object's pattern which is recorded on remote sensing digital image can do by classification process based on the group of spectral pixel value. The spectral assessment on a spatial which represent the object characteristic can be helped through supervised or unsupervised. On certain case, there no media, such as maps, airborne, photo, the capability of field observation and the knowledge of object's location. Classification process can be done by clustering. The group of pixel based on the wide of the whole value interval of spectral image, then the class group base on the desired accuracy. The clustering method in Idris 4.2 software equipments are sequential method, statistic, iso data, and RGB. The clustering existence can help pre-process pattern recognition

  19. Support Vector Data Descriptions and k-Means Clustering: One Class?

    Science.gov (United States)

    Gornitz, Nico; Lima, Luiz Alberto; Muller, Klaus-Robert; Kloft, Marius; Nakajima, Shinichi

    2017-09-27

    We present ClusterSVDD, a methodology that unifies support vector data descriptions (SVDDs) and k-means clustering into a single formulation. This allows both methods to benefit from one another, i.e., by adding flexibility using multiple spheres for SVDDs and increasing anomaly resistance and flexibility through kernels to k-means. In particular, our approach leads to a new interpretation of k-means as a regularized mode seeking algorithm. The unifying formulation further allows for deriving new algorithms by transferring knowledge from one-class learning settings to clustering settings and vice versa. As a showcase, we derive a clustering method for structured data based on a one-class learning scenario. Additionally, our formulation can be solved via a particularly simple optimization scheme. We evaluate our approach empirically to highlight some of the proposed benefits on artificially generated data, as well as on real-world problems, and provide a Python software package comprising various implementations of primal and dual SVDD as well as our proposed ClusterSVDD.

  20. Three dimensional pattern recognition using feature-based indexing and rule-based search

    Science.gov (United States)

    Lee, Jae-Kyu

    In flexible automated manufacturing, robots can perform routine operations as well as recover from atypical events, provided that process-relevant information is available to the robot controller. Real time vision is among the most versatile sensing tools, yet the reliability of machine-based scene interpretation can be questionable. The effort described here is focused on the development of machine-based vision methods to support autonomous nuclear fuel manufacturing operations in hot cells. This thesis presents a method to efficiently recognize 3D objects from 2D images based on feature-based indexing. Object recognition is the identification of correspondences between parts of a current scene and stored views of known objects, using chains of segments or indexing vectors. To create indexed object models, characteristic model image features are extracted during preprocessing. Feature vectors representing model object contours are acquired from several points of view around each object and stored. Recognition is the process of matching stored views with features or patterns detected in a test scene. Two sets of algorithms were developed, one for preprocessing and indexed database creation, and one for pattern searching and matching during recognition. At recognition time, those indexing vectors with the highest match probability are retrieved from the model image database, using a nearest neighbor search algorithm. The nearest neighbor search predicts the best possible match candidates. Extended searches are guided by a search strategy that employs knowledge-base (KB) selection criteria. The knowledge-based system simplifies the recognition process and minimizes the number of iterations and memory usage. Novel contributions include the use of a feature-based indexing data structure together with a knowledge base. Both components improve the efficiency of the recognition process by improved structuring of the database of object features and reducing data base size

  1. Effects of heavy particle irradiation and diet on object recognition memory in rats

    Science.gov (United States)

    Rabin, Bernard M.; Carrihill-Knoll, Kirsty; Hinchman, Marie; Shukitt-Hale, Barbara; Joseph, James A.; Foster, Brian C.

    2009-04-01

    On long-duration missions to other planets astronauts will be exposed to types and doses of radiation that are not experienced in low earth orbit. Previous research using a ground-based model for exposure to cosmic rays has shown that exposure to heavy particles, such as 56Fe, disrupts spatial learning and memory measured using the Morris water maze. Maintaining rats on diets containing antioxidant phytochemicals for 2 weeks prior to irradiation ameliorated this deficit. The present experiments were designed to determine: (1) the generality of the particle-induced disruption of memory by examining the effects of exposure to 56Fe particles on object recognition memory; and (2) whether maintaining rats on these antioxidant diets for 2 weeks prior to irradiation would also ameliorate any potential deficit. The results showed that exposure to low doses of 56Fe particles does disrupt recognition memory and that maintaining rats on antioxidant diets containing blueberry and strawberry extract for only 2 weeks was effective in ameliorating the disruptive effects of irradiation. The results are discussed in terms of the mechanisms by which exposure to these particles may produce effects on neurocognitive performance.

  2. Generalized framework for the parallel semantic segmentation of multiple objects and posterior manipulation

    DEFF Research Database (Denmark)

    Llopart, Adrian; Ravn, Ole; Andersen, Nils Axel

    2017-01-01

    The end-to-end approach presented in this paper deals with the recognition, detection, segmentation and grasping of objects, assuming no prior knowledge of the environment nor objects. The proposed pipeline is as follows: 1) Usage of a trained Convolutional Neural Net (CNN) that recognizes up to 80...... different classes of objects in real time and generates bounding boxes around them. 2) An algorithm to derive in parallel the pointclouds of said regions of interest (ROI). 3) Eight different segmentation methods to remove background data and noise from the pointclouds and obtain a precise result...

  3. The Memory State Heuristic: A Formal Model Based on Repeated Recognition Judgments

    Science.gov (United States)

    Castela, Marta; Erdfelder, Edgar

    2017-01-01

    The recognition heuristic (RH) theory predicts that, in comparative judgment tasks, if one object is recognized and the other is not, the recognized one is chosen. The memory-state heuristic (MSH) extends the RH by assuming that choices are not affected by recognition judgments per se, but by the memory states underlying these judgments (i.e.,…

  4. A neuromorphic architecture for object recognition and motion anticipation using burst-STDP.

    Directory of Open Access Journals (Sweden)

    Andrew Nere

    Full Text Available In this work we investigate the possibilities offered by a minimal framework of artificial spiking neurons to be deployed in silico. Here we introduce a hierarchical network architecture of spiking neurons which learns to recognize moving objects in a visual environment and determine the correct motor output for each object. These tasks are learned through both supervised and unsupervised spike timing dependent plasticity (STDP. STDP is responsible for the strengthening (or weakening of synapses in relation to pre- and post-synaptic spike times and has been described as a Hebbian paradigm taking place both in vitro and in vivo. We utilize a variation of STDP learning, called burst-STDP, which is based on the notion that, since spikes are expensive in terms of energy consumption, then strong bursting activity carries more information than single (sparse spikes. Furthermore, this learning algorithm takes advantage of homeostatic renormalization, which has been hypothesized to promote memory consolidation during NREM sleep. Using this learning rule, we design a spiking neural network architecture capable of object recognition, motion detection, attention towards important objects, and motor control outputs. We demonstrate the abilities of our design in a simple environment with distractor objects, multiple objects moving concurrently, and in the presence of noise. Most importantly, we show how this neural network is capable of performing these tasks using a simple leaky-integrate-and-fire (LIF neuron model with binary synapses, making it fully compatible with state-of-the-art digital neuromorphic hardware designs. As such, the building blocks and learning rules presented in this paper appear promising for scalable fully neuromorphic systems to be implemented in hardware chips.

  5. Behavioral model of visual perception and recognition

    Science.gov (United States)

    Rybak, Ilya A.; Golovan, Alexander V.; Gusakova, Valentina I.

    1993-09-01

    In the processes of visual perception and recognition human eyes actively select essential information by way of successive fixations at the most informative points of the image. A behavioral program defining a scanpath of the image is formed at the stage of learning (object memorizing) and consists of sequential motor actions, which are shifts of attention from one to another point of fixation, and sensory signals expected to arrive in response to each shift of attention. In the modern view of the problem, invariant object recognition is provided by the following: (1) separated processing of `what' (object features) and `where' (spatial features) information at high levels of the visual system; (2) mechanisms of visual attention using `where' information; (3) representation of `what' information in an object-based frame of reference (OFR). However, most recent models of vision based on OFR have demonstrated the ability of invariant recognition of only simple objects like letters or binary objects without background, i.e. objects to which a frame of reference is easily attached. In contrast, we use not OFR, but a feature-based frame of reference (FFR), connected with the basic feature (edge) at the fixation point. This has provided for our model, the ability for invariant representation of complex objects in gray-level images, but demands realization of behavioral aspects of vision described above. The developed model contains a neural network subsystem of low-level vision which extracts a set of primary features (edges) in each fixation, and high- level subsystem consisting of `what' (Sensory Memory) and `where' (Motor Memory) modules. The resolution of primary features extraction decreases with distances from the point of fixation. FFR provides both the invariant representation of object features in Sensor Memory and shifts of attention in Motor Memory. Object recognition consists in successive recall (from Motor Memory) and execution of shifts of attention and

  6. Probing binding hot spots at protein-RNA recognition sites.

    Science.gov (United States)

    Barik, Amita; Nithin, Chandran; Karampudi, Naga Bhushana Rao; Mukherjee, Sunandan; Bahadur, Ranjit Prasad

    2016-01-29

    We use evolutionary conservation derived from structure alignment of polypeptide sequences along with structural and physicochemical attributes of protein-RNA interfaces to probe the binding hot spots at protein-RNA recognition sites. We find that the degree of conservation varies across the RNA binding proteins; some evolve rapidly compared to others. Additionally, irrespective of the structural class of the complexes, residues at the RNA binding sites are evolutionary better conserved than those at the solvent exposed surfaces. For recognitions involving duplex RNA, residues interacting with the major groove are better conserved than those interacting with the minor groove. We identify multi-interface residues participating simultaneously in protein-protein and protein-RNA interfaces in complexes where more than one polypeptide is involved in RNA recognition, and show that they are better conserved compared to any other RNA binding residues. We find that the residues at water preservation site are better conserved than those at hydrated or at dehydrated sites. Finally, we develop a Random Forests model using structural and physicochemical attributes for predicting binding hot spots. The model accurately predicts 80% of the instances of experimental ΔΔG values in a particular class, and provides a stepping-stone towards the engineering of protein-RNA recognition sites with desired affinity. © The Author(s) 2015. Published by Oxford University Press on behalf of Nucleic Acids Research.

  7. Role of the Anterior Cingulate Cortex in the Retrieval of Novel Object Recognition Memory after a Long Delay

    Science.gov (United States)

    Pezze, Marie A.; Marshall, Hayley J.; Fone, Kevin C. F.; Cassaday, Helen J.

    2017-01-01

    Previous in vivo electrophysiological studies suggest that the anterior cingulate cortex (ACgx) is an important substrate of novel object recognition (NOR) memory. However, intervention studies are needed to confirm this conclusion and permanent lesion studies cannot distinguish effects on encoding and retrieval. The interval between encoding and…

  8. Dissociation of Recognition and Recency Memory Judgments After Anterior Thalamic Nuclei Lesions in Rats

    Science.gov (United States)

    Dumont, Julie R.; Aggleton, John P.

    2013-01-01

    The anterior thalamic nuclei form part of a network for episodic memory in humans. The importance of these nuclei for recognition and recency judgments remains, however, unclear. Rats with anterior thalamic nuclei lesions and their controls were tested on object recognition, along with two types of recency judgment. The spontaneous discrimination of a novel object or a novel odor from a familiar counterpart (recognition memory) was not affected by anterior thalamic lesions when tested after retention delays of 1 and 60 min. To measure recency memory, rats were shown two familiar objects, one of which had been explored more recently. In one condition, rats were presented with two lists (List A, List B) of objects separated by a delay, thereby creating two distinct blocks of stimuli. After an additional delay, rats were presented with pairs of objects, one from List A and one from List B (between-block recency). No lesion-induced deficit was apparent for recency discriminations between objects from different lists, despite using three different levels of task difficulty. In contrast, rats with anterior thalamic lesions were significantly impaired when presented with a continuous list of objects and then tested on their ability to distinguish between those items early and late in the same list (within-block recency). The contrasting effects on recognition and recency support the notion that interlinked hippocampal–anterior thalamic interconnections support aspects of both spatial and nonspatial learning, although the role of the anterior thalamic nuclei may be restricted to a subclass of recency judgments (within-block). PMID:23731076

  9. HLA Class II Defects in Burkitt Lymphoma: Bryostatin-1-Induced 17 kDa Protein Restores CD4+ T-Cell Recognition

    Directory of Open Access Journals (Sweden)

    Azim Hossain

    2011-01-01

    Full Text Available While the defects in HLA class I-mediated Ag presentation by Burkitt lymphoma (BL have been well documented, CD4+ T-cells are also poorly stimulated by HLA class II Ag presentation, and the reasons underlying this defect(s have not yet been fully resolved. Here, we show that BL cells are deficient in their ability to optimally stimulate CD4+ T cells via the HLA class II pathway. The observed defect was not associated with low levels of BL-expressed costimulatory molecules, as addition of external co-stimulation failed to result in BL-mediated CD4+ T-cell activation. We further demonstrate that BL cells express the components of the class II pathway, and the defect was not caused by faulty Ag/class II interaction, because antigenic peptides bound with measurable affinity to BL-associated class II molecules. Treatment of BL with broystatin-1, a potent modulator of protein kinase C, led to significant improvement of functional class II Ag presentation in BL. The restoration of immune recognition appeared to be linked with an increased expression of a 17 kDa peptidylprolyl-like protein. These results demonstrate the presence of a specific defect in HLA class II-mediated Ag presentation in BL and reveal that treatment with bryostatin-1 could lead to enhanced immunogenicity.

  10. Landscape object-based analysis of wetland plant functional types: the effects of spatial scale, vegetation classes and classifier methods

    Science.gov (United States)

    Dronova, I.; Gong, P.; Wang, L.; Clinton, N.; Fu, W.; Qi, S.

    2011-12-01

    Remote sensing-based vegetation classifications representing plant function such as photosynthesis and productivity are challenging in wetlands with complex cover and difficult field access. Recent advances in object-based image analysis (OBIA) and machine-learning algorithms offer new classification tools; however, few comparisons of different algorithms and spatial scales have been discussed to date. We applied OBIA to delineate wetland plant functional types (PFTs) for Poyang Lake, the largest freshwater lake in China and Ramsar wetland conservation site, from 30-m Landsat TM scene at the peak of spring growing season. We targeted major PFTs (C3 grasses, C3 forbs and different types of C4 grasses and aquatic vegetation) that are both key players in system's biogeochemical cycles and critical providers of waterbird habitat. Classification results were compared among: a) several object segmentation scales (with average object sizes 900-9000 m2); b) several families of statistical classifiers (including Bayesian, Logistic, Neural Network, Decision Trees and Support Vector Machines) and c) two hierarchical levels of vegetation classification, a generalized 3-class set and more detailed 6-class set. We found that classification benefited from object-based approach which allowed including object shape, texture and context descriptors in classification. While a number of classifiers achieved high accuracy at the finest pixel-equivalent segmentation scale, the highest accuracies and best agreement among algorithms occurred at coarser object scales. No single classifier was consistently superior across all scales, although selected algorithms of Neural Network, Logistic and K-Nearest Neighbors families frequently provided the best discrimination of classes at different scales. The choice of vegetation categories also affected classification accuracy. The 6-class set allowed for higher individual class accuracies but lower overall accuracies than the 3-class set because

  11. The effect of Wi-Fi electromagnetic waves in unimodal and multimodal object recognition tasks in male rats.

    Science.gov (United States)

    Hassanshahi, Amin; Shafeie, Seyed Ali; Fatemi, Iman; Hassanshahi, Elham; Allahtavakoli, Mohammad; Shabani, Mohammad; Roohbakhsh, Ali; Shamsizadeh, Ali

    2017-06-01

    Wireless internet (Wi-Fi) electromagnetic waves (2.45 GHz) have widespread usage almost everywhere, especially in our homes. Considering the recent reports about some hazardous effects of Wi-Fi signals on the nervous system, this study aimed to investigate the effect of 2.4 GHz Wi-Fi radiation on multisensory integration in rats. This experimental study was done on 80 male Wistar rats that were allocated into exposure and sham groups. Wi-Fi exposure to 2.4 GHz microwaves [in Service Set Identifier mode (23.6 dBm and 3% for power and duty cycle, respectively)] was done for 30 days (12 h/day). Cross-modal visual-tactile object recognition (CMOR) task was performed by four variations of spontaneous object recognition (SOR) test including standard SOR, tactile SOR, visual SOR, and CMOR tests. A discrimination ratio was calculated to assess the preference of animal to the novel object. The expression levels of M1 and GAT1 mRNA in the hippocampus were assessed by quantitative real-time RT-PCR. Results demonstrated that rats in Wi-Fi exposure groups could not discriminate significantly between the novel and familiar objects in any of the standard SOR, tactile SOR, visual SOR, and CMOR tests. The expression of M1 receptors increased following Wi-Fi exposure. In conclusion, results of this study showed that chronic exposure to Wi-Fi electromagnetic waves might impair both unimodal and cross-modal encoding of information.

  12. The influence of object and background color manipulations on the electrophysiological indices of recognition memory.

    Science.gov (United States)

    Ecker, Ullrich K H; Zimmer, Hubert D; Groh-Bordin, Christian

    2007-12-14

    In a recognition memory experiment, the claim was tested that intrinsic object features contribute to familiarity, whereas extrinsic context features do not. We used the study-test manipulation of color to investigate the perceptual specificity of ERP old-new effects associated with familiarity and recollection. Color was either an intrinsic surface feature of the object or a feature of the surrounding context (a frame encasing the object); thus, the same feature was manipulated across intrinsic/extrinsic conditions. Subjects performed a threefold (same color/different color/new object) decision, making feature information task-relevant. Results suggest that the intrinsic manipulation of color affected the mid-frontal old-new effect associated with familiarity, while this effect was not influenced by extrinsic manipulation. This ERP pattern could not be explained by basic behavioral performance differences. It is concluded that familiarity can be perceptually specific with regard to intrinsic information belonging to the object. The putative electrophysiological signature of recollection - a late parietal old-new effect - was not present in the data, and reasons for this null effect are discussed.

  13. The memory state heuristic: A formal model based on repeated recognition judgments.

    Science.gov (United States)

    Castela, Marta; Erdfelder, Edgar

    2017-02-01

    The recognition heuristic (RH) theory predicts that, in comparative judgment tasks, if one object is recognized and the other is not, the recognized one is chosen. The memory-state heuristic (MSH) extends the RH by assuming that choices are not affected by recognition judgments per se, but by the memory states underlying these judgments (i.e., recognition certainty, uncertainty, or rejection certainty). Specifically, the larger the discrepancy between memory states, the larger the probability of choosing the object in the higher state. The typical RH paradigm does not allow estimation of the underlying memory states because it is unknown whether the objects were previously experienced or not. Therefore, we extended the paradigm by repeating the recognition task twice. In line with high threshold models of recognition, we assumed that inconsistent recognition judgments result from uncertainty whereas consistent judgments most likely result from memory certainty. In Experiment 1, we fitted 2 nested multinomial models to the data: an MSH model that formalizes the relation between memory states and binary choices explicitly and an approximate model that ignores the (unlikely) possibility of consistent guesses. Both models provided converging results. As predicted, reliance on recognition increased with the discrepancy in the underlying memory states. In Experiment 2, we replicated these results and found support for choice consistency predictions of the MSH. Additionally, recognition and choice latencies were in agreement with the MSH in both experiments. Finally, we validated critical parameters of our MSH model through a cross-validation method and a third experiment. (PsycINFO Database Record (c) 2017 APA, all rights reserved).

  14. Flipped Class - Making that One Hour Effective in a Resource Constrained Setting.

    Science.gov (United States)

    Zafar, Afsheen

    2016-09-01

    Flipped-class teaching has a great potential to replace traditional lectures in medical education. This study was designed to explore attitude of undergraduate medical students from Pakistan towards flipped-class. Five flipped classes were conducted in third year MBBS by a single teacher for a class of 100 students. Quantitative data was collected through a survey questionnaire to assess students' response to the new method. Afocused group discussion was then conducted with students who disliked the method and preferred traditional lectures. Asequential mixed methods approach was used for analysis. Seventy-one students participated in the survey, 84.5% students liked this method of teaching. Students identified fruitful interaction, better retention, better conceptualisation, prior knowledge, active learning, individual student attention, and application of knowledge as strengths of the class. Noise, limited time, lack of self-confidence, and presence of uninterested students were identified as problems for engaging in the class.

  15. Human Wearable Attribute Recognition Using Probability-Map-Based Decomposition of Thermal Infrared Images

    OpenAIRE

    KRESNARAMAN, Brahmastro; KAWANISHI, Yasutomo; DEGUCHI, Daisuke; TAKAHASHI, Tomokazu; MEKADA, Yoshito; IDE, Ichiro; MURASE, Hiroshi

    2017-01-01

    This paper addresses the attribute recognition problem, a field of research that is dominated by studies in the visible spectrum. Only a few works are available in the thermal spectrum, which is fundamentally different from the visible one. This research performs recognition specifically on wearable attributes, such as glasses and masks. Usually these attributes are relatively small in size when compared with the human body, on top of a large intra-class variation of the human body itself, th...

  16. Chronic cannabidiol treatment improves social and object recognition in double transgenic APPswe/PS1∆E9 mice.

    Science.gov (United States)

    Cheng, David; Low, Jac Kee; Logge, Warren; Garner, Brett; Karl, Tim

    2014-08-01

    Patients suffering from Alzheimer's disease (AD) exhibit a decline in cognitive abilities including an inability to recognise familiar faces. Hallmark pathological changes in AD include the aggregation of amyloid-β (Aβ), tau protein hyperphosphorylation as well as pronounced neurodegeneration, neuroinflammation, neurotoxicity and oxidative damage. The non-psychoactive phytocannabinoid cannabidiol (CBD) exerts neuroprotective, anti-oxidant and anti-inflammatory effects and promotes neurogenesis. CBD also reverses Aβ-induced spatial memory deficits in rodents. Thus we determined the therapeutic-like effects of chronic CBD treatment (20 mg/kg, daily intraperitoneal injections for 3 weeks) on the APPswe/PS1∆E9 (APPxPS1) transgenic mouse model for AD in a number of cognitive tests, including the social preference test, the novel object recognition task and the fear conditioning paradigm. We also analysed the impact of CBD on anxiety behaviours in the elevated plus maze. Vehicle-treated APPxPS1 mice demonstrated impairments in social recognition and novel object recognition compared to wild type-like mice. Chronic CBD treatment reversed these cognitive deficits in APPxPS1 mice without affecting anxiety-related behaviours. This is the first study to investigate the effect of chronic CBD treatment on cognition in an AD transgenic mouse model. Our findings suggest that CBD may have therapeutic potential for specific cognitive impairments associated with AD.

  17. Secondary iris recognition method based on local energy-orientation feature

    Science.gov (United States)

    Huo, Guang; Liu, Yuanning; Zhu, Xiaodong; Dong, Hongxing

    2015-01-01

    This paper proposes a secondary iris recognition based on local features. The application of the energy-orientation feature (EOF) by two-dimensional Gabor filter to the extraction of the iris goes before the first recognition by the threshold of similarity, which sets the whole iris database into two categories-a correctly recognized class and a class to be recognized. Therefore, the former are accepted and the latter are transformed by histogram to achieve an energy-orientation histogram feature (EOHF), which is followed by a second recognition with the chi-square distance. The experiment has proved that the proposed method, because of its higher correct recognition rate, could be designated as the most efficient and effective among its companion studies in iris recognition algorithms.

  18. Risperidone reverses the spatial object recognition impairment and hippocampal BDNF-TrkB signalling system alterations induced by acute MK-801 treatment

    Science.gov (United States)

    Chen, Guangdong; Lin, Xiaodong; Li, Gongying; Jiang, Diego; Lib, Zhiruo; Jiang, Ronghuan; Zhuo, Chuanjun

    2017-01-01

    The aim of the present study was to investigate the effects of a commonly-used atypical antipsychotic, risperidone, on alterations in spatial learning and in the hippocampal brain-derived neurotrophic factor (BDNF)-tyrosine receptor kinase B (TrkB) signalling system caused by acute dizocilpine maleate (MK-801) treatment. In experiment 1, adult male Sprague-Dawley rats subjected to acute treatment of either low-dose MK801 (0.1 mg/kg) or normal saline (vehicle) were tested for spatial object recognition and hippocampal expression levels of BDNF, TrkB and the phophorylation of TrkB (p-TrkB). We found that compared to the vehicle, MK-801 treatment impaired spatial object recognition of animals and downregulated the expression levels of p-TrkB. In experiment 2, MK-801- or vehicle-treated animals were further injected with risperidone (0.1 mg/kg) or vehicle before behavioural testing and sacrifice. Of note, we found that risperidone successfully reversed the deleterious effects of MK-801 on spatial object recognition and upregulated the hippocampal BDNF-TrkB signalling system. Collectively, the findings suggest that cognitive deficits from acute N-methyl-D-aspartate receptor blockade may be associated with the hypofunction of hippocampal BDNF-TrkB signalling system and that risperidone was able to reverse these alterations. PMID:28451387

  19. Real-world objects are more memorable than photographs of objects

    Directory of Open Access Journals (Sweden)

    Jacqueline C Snow

    2014-10-01

    Full Text Available Research studies in psychology typically use two-dimensional (2D images of objects as proxies for real-world three-dimensional (3D stimuli. There are, however, a number of important differences between real objects and images that could influence cognition and behavior. Although human memory has been studied extensively, only a handful of studies have used real objects in the context of memory and virtually none have directly compared memory for real objects versus their 2D counterparts. Here we examined whether or not episodic memory is influenced by the format in which objects are displayed. We conducted two experiments asking participants to freely recall, and to recognize, a set of 44 common household objects. Critically, the exemplars were displayed to observers in one of three viewing conditions: real-world objects, colored photographs, or black and white line drawings. Stimuli were closely matched across conditions for size, orientation, and illumination. Surprisingly, recall and recognition performance was significantly better for real objects compared to colored photographs or line drawings (for which memory performance was equivalent. We replicated this pattern in a second experiment comparing memory for real objects versus color photos, when the stimuli were matched for viewing angle across conditions. Again, recall and recognition performance was significantly better for the real objects than matched color photos of the same items. Taken together, our data suggest that real objects are more memorable than pictorial stimuli. Our results highlight the importance of studying real-world object cognition and raise the potential for applied use in developing effective strategies for education, marketing, and further research on object-related cognition.

  20. Optical-electronic shape recognition system based on synergetic associative memory

    Science.gov (United States)

    Gao, Jun; Bao, Jie; Chen, Dingguo; Yang, Youqing; Yang, Xuedong

    2001-04-01

    This paper presents a novel optical-electronic shape recognition system based on synergetic associative memory. Our shape recognition system is composed of two parts: the first one is feature extraction system; the second is synergetic pattern recognition system. Hough transform is proposed for feature extraction of unrecognized object, with the effects of reducing dimensions and filtering for object distortion and noise, synergetic neural network is proposed for realizing associative memory in order to eliminate spurious states. Then we adopt an approach of optical- electronic realization to our system that can satisfy the demands of real time, high speed and parallelism. In order to realize fast algorithm, we replace the dynamic evolution circuit with adjudge circuit according to the relationship between attention parameters and order parameters, then implement the recognition of some simple images and its validity is proved.

  1. The different faces of one's self: an fMRI study into the recognition of current and past self-facial appearances.

    Science.gov (United States)

    Apps, Matthew A J; Tajadura-Jiménez, Ana; Turley, Grainne; Tsakiris, Manos

    2012-11-15

    Mirror self-recognition is often considered as an index of self-awareness. Neuroimaging studies have identified a neural circuit specialised for the recognition of one's own current facial appearance. However, faces change considerably over a lifespan, highlighting the necessity for representations of one's face to continually be updated. We used fMRI to investigate the different neural circuits involved in the recognition of the childhood and current, adult, faces of one's self. Participants viewed images of either their own face as it currently looks morphed with the face of a familiar other or their childhood face morphed with the childhood face of the familiar other. Activity in areas which have a generalised selectivity for faces, including the inferior occipital gyrus, the superior parietal lobule and the inferior temporal gyrus, varied with the amount of current self in an image. Activity in areas involved in memory encoding and retrieval, including the hippocampus and the posterior cingulate gyrus, and areas involved in creating a sense of body ownership, including the temporo-parietal junction and the inferior parietal lobule, varied with the amount of childhood self in an image. We suggest that the recognition of one's own past or present face is underpinned by different cognitive processes in distinct neural circuits. Current self-recognition engages areas involved in perceptual face processing, whereas childhood self-recognition recruits networks involved in body ownership and memory processing. Copyright © 2012 Elsevier Inc. All rights reserved.

  2. Classical methods for interpreting objective function minimization as intelligent inference

    Energy Technology Data Exchange (ETDEWEB)

    Golden, R.M. [Univ. of Texas, Dallas, TX (United States)

    1996-12-31

    Most recognition algorithms and neural networks can be formally viewed as seeking a minimum value of an appropriate objective function during either classification or learning phases. The goal of this paper is to argue that in order to show a recognition algorithm is making intelligent inferences, it is not sufficient to show that the recognition algorithm is computing (or trying to compute) the global minimum of some objective function. One must explicitly define a {open_quotes}relational system{close_quotes} for the recognition algorithm or neural network which identifies the: (i) sample space, (ii) the relevant sigmafield of events generated by the sample space, and (iii) the {open_quotes}relation{close_quotes} for that relational system. Only when such a {open_quotes}relational system{close_quotes} is properly defined, is it possible to formally establish the sense in which computing the global minimum of an objective function is an intelligent, inference.

  3. Feature extraction for SAR target recognition based on supervised manifold learning

    International Nuclear Information System (INIS)

    Du, C; Zhou, S; Sun, J; Zhao, J

    2014-01-01

    On the basis of manifold learning theory, a new feature extraction method for Synthetic aperture radar (SAR) target recognition is proposed. First, the proposed algorithm estimates the within-class and between-class local neighbourhood surrounding each SAR sample. After computing the local tangent space for each neighbourhood, the proposed algorithm seeks for the optimal projecting matrix by preserving the local within-class property and simultaneously maximizing the local between-class separability. The use of uncorrelated constraint can also enhance the discriminating power of the optimal projecting matrix. Finally, the nearest neighbour classifier is applied to recognize SAR targets in the projected feature subspace. Experimental results on MSTAR datasets demonstrate that the proposed method can provide a higher recognition rate than traditional feature extraction algorithms in SAR target recognition

  4. The Effect of Inversion on 3- to 5-Year-Olds' Recognition of Face and Nonface Visual Objects

    Science.gov (United States)

    Picozzi, Marta; Cassia, Viola Macchi; Turati, Chiara; Vescovo, Elena

    2009-01-01

    This study compared the effect of stimulus inversion on 3- to 5-year-olds' recognition of faces and two nonface object categories matched with faces for a number of attributes: shoes (Experiment 1) and frontal images of cars (Experiments 2 and 3). The inversion effect was present for faces but not shoes at 3 years of age (Experiment 1). Analogous…

  5. The symmetric = ω -semi-classical orthogonal polynomials of class one

    Science.gov (United States)

    Maroni, P.; Mejri, M.

    2008-12-01

    We give the system of Laguerre-Freud equations associated with the = ω -semi-classical functionals of class one, where = ω is the divided difference operator. This system is solved in the symmetric case. There are essentially two canonical cases. The corresponding integral representations are given.

  6. Eye movement analysis for activity recognition using electrooculography.

    Science.gov (United States)

    Bulling, Andreas; Ward, Jamie A; Gellersen, Hans; Tröster, Gerhard

    2011-04-01

    In this work, we investigate eye movement analysis as a new sensing modality for activity recognition. Eye movement data were recorded using an electrooculography (EOG) system. We first describe and evaluate algorithms for detecting three eye movement characteristics from EOG signals-saccades, fixations, and blinks-and propose a method for assessing repetitive patterns of eye movements. We then devise 90 different features based on these characteristics and select a subset of them using minimum redundancy maximum relevance (mRMR) feature selection. We validate the method using an eight participant study in an office environment using an example set of five activity classes: copying a text, reading a printed paper, taking handwritten notes, watching a video, and browsing the Web. We also include periods with no specific activity (the NULL class). Using a support vector machine (SVM) classifier and person-independent (leave-one-person-out) training, we obtain an average precision of 76.1 percent and recall of 70.5 percent over all classes and participants. The work demonstrates the promise of eye-based activity recognition (EAR) and opens up discussion on the wider applicability of EAR to other activities that are difficult, or even impossible, to detect using common sensing modalities.

  7. Estradiol-Induced Object Recognition Memory Consolidation Is Dependent on Activation of mTOR Signaling in the Dorsal Hippocampus

    Science.gov (United States)

    Fortress, Ashley M.; Fan, Lu; Orr, Patrick T.; Zhao, Zaorui; Frick, Karyn M.

    2013-01-01

    The mammalian target of rapamycin (mTOR) signaling pathway is an important regulator of protein synthesis and is essential for various forms of hippocampal memory. Here, we asked whether the enhancement of object recognition memory consolidation produced by dorsal hippocampal infusion of 17[Beta]-estradiol (E[subscript 2]) is dependent on mTOR…

  8. A Longitudinal Study of Cognitive Representation in Symbolic Play, Self-recognition, and Object Permanence during the Second Year.

    Science.gov (United States)

    Chapman, Michael

    1987-01-01

    Explores development of cognitive representation in 20 infants 12 to 24 months of age with regard to (l) their understanding of agency in symbolic play (agent use), (2) recognition of their own mirror image, and (3) object permanence. Results were generally consistent with developmental sequences predicted by Fischer's Skill Theory for agent use…

  9. Color constancy in 3D-2D face recognition

    Science.gov (United States)

    Meyer, Manuel; Riess, Christian; Angelopoulou, Elli; Evangelopoulos, Georgios; Kakadiaris, Ioannis A.

    2013-05-01

    Face is one of the most popular biometric modalities. However, up to now, color is rarely actively used in face recognition. Yet, it is well-known that when a person recognizes a face, color cues can become as important as shape, especially when combined with the ability of people to identify the color of objects independent of illuminant color variations. In this paper, we examine the feasibility and effect of explicitly embedding illuminant color information in face recognition systems. We empirically examine the theoretical maximum gain of including known illuminant color to a 3D-2D face recognition system. We also investigate the impact of using computational color constancy methods for estimating the illuminant color, which is then incorporated into the face recognition framework. Our experiments show that under close-to-ideal illumination estimates, one can improve face recognition rates by 16%. When the illuminant color is algorithmically estimated, the improvement is approximately 5%. These results suggest that color constancy has a positive impact on face recognition, but the accuracy of the illuminant color estimate has a considerable effect on its benefits.

  10. Facial Emotions Recognition using Gabor Transform and Facial Animation Parameters with Neural Networks

    Science.gov (United States)

    Harit, Aditya; Joshi, J. C., Col; Gupta, K. K.

    2018-03-01

    The paper proposed an automatic facial emotion recognition algorithm which comprises of two main components: feature extraction and expression recognition. The algorithm uses a Gabor filter bank on fiducial points to find the facial expression features. The resulting magnitudes of Gabor transforms, along with 14 chosen FAPs (Facial Animation Parameters), compose the feature space. There are two stages: the training phase and the recognition phase. Firstly, for the present 6 different emotions, the system classifies all training expressions in 6 different classes (one for each emotion) in the training stage. In the recognition phase, it recognizes the emotion by applying the Gabor bank to a face image, then finds the fiducial points, and then feeds it to the trained neural architecture.

  11. A necessary and sufficient condition for a real quadratic extension to have class number one

    International Nuclear Information System (INIS)

    Alemu, Y.

    1990-02-01

    We give a necessary and sufficient condition for a real quadratic extension to have class number one and discuss the applicability of the result to find the class number one fields with small discriminant. 9 refs, 3 tabs

  12. Emotion and Object Processing in Parkinson's Disease

    Science.gov (United States)

    Cohen, Henri; Gagne, Marie-Helene; Hess, Ursula; Pourcher, Emmanuelle

    2010-01-01

    The neuropsychological literature on the processing of emotions in Parkinson's disease (PD) reveals conflicting evidence about the role of the basal ganglia in the recognition of facial emotions. Hence, the present study had two objectives. One was to determine the extent to which the visual processing of emotions and objects differs in PD. The…

  13. Feature Selection Has a Large Impact on One-Class Classification Accuracy for MicroRNAs in Plants.

    Science.gov (United States)

    Yousef, Malik; Saçar Demirci, Müşerref Duygu; Khalifa, Waleed; Allmer, Jens

    2016-01-01

    MicroRNAs (miRNAs) are short RNA sequences involved in posttranscriptional gene regulation. Their experimental analysis is complicated and, therefore, needs to be supplemented with computational miRNA detection. Currently computational miRNA detection is mainly performed using machine learning and in particular two-class classification. For machine learning, the miRNAs need to be parametrized and more than 700 features have been described. Positive training examples for machine learning are readily available, but negative data is hard to come by. Therefore, it seems prerogative to use one-class classification instead of two-class classification. Previously, we were able to almost reach two-class classification accuracy using one-class classifiers. In this work, we employ feature selection procedures in conjunction with one-class classification and show that there is up to 36% difference in accuracy among these feature selection methods. The best feature set allowed the training of a one-class classifier which achieved an average accuracy of ~95.6% thereby outperforming previous two-class-based plant miRNA detection approaches by about 0.5%. We believe that this can be improved upon in the future by rigorous filtering of the positive training examples and by improving current feature clustering algorithms to better target pre-miRNA feature selection.

  14. Guppies Show Behavioural but Not Cognitive Sex Differences in a Novel Object Recognition Test.

    Directory of Open Access Journals (Sweden)

    Tyrone Lucon-Xiccato

    Full Text Available The novel object recognition (NOR test is a widely-used paradigm to study learning and memory in rodents. NOR performance is typically measured as the preference to interact with a novel object over a familiar object based on spontaneous exploratory behaviour. In rats and mice, females usually have greater NOR ability than males. The NOR test is now available for a large number of species, including fish, but sex differences have not been properly tested outside of rodents. We compared male and female guppies (Poecilia reticulata in a NOR test to study whether sex differences exist also for fish. We focused on sex differences in both performance and behaviour of guppies during the test. In our experiment, adult guppies expressed a preference for the novel object as most rodents and other species do. When we looked at sex differences, we found the two sexes showed a similar preference for the novel object over the familiar object, suggesting that male and female guppies have similar NOR performances. Analysis of behaviour revealed that males were more inclined to swim in the proximity of the two objects than females. Further, males explored the novel object at the beginning of the experiment while females did so afterwards. These two behavioural differences are possibly due to sex differences in exploration. Even though NOR performance is not different between male and female guppies, the behavioural sex differences we found could affect the results of the experiments and should be carefully considered when assessing fish memory with the NOR test.

  15. Recognition for old Arabic manuscripts using spatial gray level dependence (SGLD

    Directory of Open Access Journals (Sweden)

    Ahmad M. Abd Al-Aziz

    2011-03-01

    Full Text Available Texture analysis forms the basis of object recognition and classification in several domains, one of these domains is historical document manuscripts because the manuscripts hold our culture heritage and also large numbers of undated manuscripts exist. This paper presents results for historical document classification of old Arabic manuscripts using texture analysis and a segmentation free approach. The main objective is to discriminate between historical documents of different writing styles to three different ages: Contemporary (Modern Age, Ottoman Age and Mamluk Age. This classification depends on a Spatial Gray-level Dependence (SGLD technique which provides eight distinct texture features for each sample document. We applied Stepwise Discriminant Analysis and Multiple discriminant analysis methods to decrease the dimensionality of features and extract training vector features from samples. To classify historical documents into three main historical age classes the decision tree classification is applied. The system has been tested on 48 Arabic historical manuscripts documents from the Dar Al-Kotob Al-Masria Library. Our results so far yield 95.83% correct classification for the historical Arabic documents.

  16. Face recognition based on two-dimensional discriminant sparse preserving projection

    Science.gov (United States)

    Zhang, Dawei; Zhu, Shanan

    2018-04-01

    In this paper, a supervised dimensionality reduction algorithm named two-dimensional discriminant sparse preserving projection (2DDSPP) is proposed for face recognition. In order to accurately model manifold structure of data, 2DDSPP constructs within-class affinity graph and between-class affinity graph by the constrained least squares (LS) and l1 norm minimization problem, respectively. Based on directly operating on image matrix, 2DDSPP integrates graph embedding (GE) with Fisher criterion. The obtained projection subspace preserves within-class neighborhood geometry structure of samples, while keeping away samples from different classes. The experimental results on the PIE and AR face databases show that 2DDSPP can achieve better recognition performance.

  17. Automatic anatomy recognition via multiobject oriented active shape models.

    Science.gov (United States)

    Chen, Xinjian; Udupa, Jayaram K; Alavi, Abass; Torigian, Drew A

    2010-12-01

    This paper studies the feasibility of developing an automatic anatomy recognition (AAR) system in clinical radiology and demonstrates its operation on clinical 2D images. The anatomy recognition method described here consists of two main components: (a) multiobject generalization of OASM and (b) object recognition strategies. The OASM algorithm is generalized to multiple objects by including a model for each object and assigning a cost structure specific to each object in the spirit of live wire. The delineation of multiobject boundaries is done in MOASM via a three level dynamic programming algorithm, wherein the first level is at pixel level which aims to find optimal oriented boundary segments between successive landmarks, the second level is at landmark level which aims to find optimal location for the landmarks, and the third level is at the object level which aims to find optimal arrangement of object boundaries over all objects. The object recognition strategy attempts to find that pose vector (consisting of translation, rotation, and scale component) for the multiobject model that yields the smallest total boundary cost for all objects. The delineation and recognition accuracies were evaluated separately utilizing routine clinical chest CT, abdominal CT, and foot MRI data sets. The delineation accuracy was evaluated in terms of true and false positive volume fractions (TPVF and FPVF). The recognition accuracy was assessed (1) in terms of the size of the space of the pose vectors for the model assembly that yielded high delineation accuracy, (2) as a function of the number of objects and objects' distribution and size in the model, (3) in terms of the interdependence between delineation and recognition, and (4) in terms of the closeness of the optimum recognition result to the global optimum. When multiple objects are included in the model, the delineation accuracy in terms of TPVF can be improved to 97%-98% with a low FPVF of 0.1%-0.2%. Typically, a

  18. Super-recognition in development: A case study of an adolescent with extraordinary face recognition skills.

    Science.gov (United States)

    Bennetts, Rachel J; Mole, Joseph; Bate, Sarah

    2017-09-01

    Face recognition abilities vary widely. While face recognition deficits have been reported in children, it is unclear whether superior face recognition skills can be encountered during development. This paper presents O.B., a 14-year-old female with extraordinary face recognition skills: a "super-recognizer" (SR). O.B. demonstrated exceptional face-processing skills across multiple tasks, with a level of performance that is comparable to adult SRs. Her superior abilities appear to be specific to face identity: She showed an exaggerated face inversion effect and her superior abilities did not extend to object processing or non-identity aspects of face recognition. Finally, an eye-movement task demonstrated that O.B. spent more time than controls examining the nose - a pattern previously reported in adult SRs. O.B. is therefore particularly skilled at extracting and using identity-specific facial cues, indicating that face and object recognition are dissociable during development, and that super recognition can be detected in adolescence.

  19. Products recognition on shop-racks from local scale-invariant features

    Science.gov (United States)

    Zawistowski, Jacek; Kurzejamski, Grzegorz; Garbat, Piotr; Naruniec, Jacek

    2016-04-01

    This paper presents a system designed for the multi-object detection purposes and adjusted for the application of product search on the market shelves. System uses well known binary keypoint detection algorithms for finding characteristic points in the image. One of the main idea is object recognition based on Implicit Shape Model method. Authors of the article proposed many improvements of the algorithm. Originally fiducial points are matched with a very simple function. This leads to the limitations in the number of objects parts being success- fully separated, while various methods of classification may be validated in order to achieve higher performance. Such an extension implies research on training procedure able to deal with many objects categories. Proposed solution opens a new possibilities for many algorithms demanding fast and robust multi-object recognition.

  20. Self-Recognition in Autistic Children.

    Science.gov (United States)

    Dawson, Geraldine; McKissick, Fawn Celeste

    1984-01-01

    Fifteen autistic children (four to six years old) were assessed for visual self-recognition ability, as well as for object permanence and gestural imitation. It was found that 13 of 15 autistic children showed evidence of self-recognition. Consistent relationships were suggested between self-cognition and object permanence but not between…

  1. Semantic memory in object use.

    Science.gov (United States)

    Silveri, Maria Caterina; Ciccarelli, Nicoletta

    2009-10-01

    We studied five patients with semantic memory disorders, four with semantic dementia and one with herpes simplex virus encephalitis, to investigate the involvement of semantic conceptual knowledge in object use. Comparisons between patients who had semantic deficits of different severity, as well as the follow-up, showed that the ability to use objects was largely preserved when the deficit was mild but progressively decayed as the deficit became more severe. Naming was generally more impaired than object use. Production tasks (pantomime execution and actual object use) and comprehension tasks (pantomime recognition and action recognition) as well as functional knowledge about objects were impaired when the semantic deficit was severe. Semantic and unrelated errors were produced during object use, but actions were always fluent and patients performed normally on a novel tools task in which the semantic demand was minimal. Patients with severe semantic deficits scored borderline on ideational apraxia tasks. Our data indicate that functional semantic knowledge is crucial for using objects in a conventional way and suggest that non-semantic factors, mainly non-declarative components of memory, might compensate to some extent for semantic disorders and guarantee some residual ability to use very common objects independently of semantic knowledge.

  2. Genetic specificity of face recognition.

    Science.gov (United States)

    Shakeshaft, Nicholas G; Plomin, Robert

    2015-10-13

    Specific cognitive abilities in diverse domains are typically found to be highly heritable and substantially correlated with general cognitive ability (g), both phenotypically and genetically. Recent twin studies have found the ability to memorize and recognize faces to be an exception, being similarly heritable but phenotypically substantially uncorrelated both with g and with general object recognition. However, the genetic relationships between face recognition and other abilities (the extent to which they share a common genetic etiology) cannot be determined from phenotypic associations. In this, to our knowledge, first study of the genetic associations between face recognition and other domains, 2,000 18- and 19-year-old United Kingdom twins completed tests assessing their face recognition, object recognition, and general cognitive abilities. Results confirmed the substantial heritability of face recognition (61%), and multivariate genetic analyses found that most of this genetic influence is unique and not shared with other cognitive abilities.

  3. Developing Mathematical Knowledge Through Class Discussion: One Teacher's Struggles in Implementing Reform

    OpenAIRE

    Nelson, Rebecca S.

    1997-01-01

    The purpose of this case study was to examine the experience of one secondary mathematics teacher during his efforts to facilitate mathematical discussions in a secondary algebra class. Class discussions and interviews were documented and analyzed to investigate the patterns of discussion, the teacher's role in facilitating discussion, and the struggles encountered by the teacher through his attempts to enact reform-oriented strategies. The investigation focused on the teacher's vision for ...

  4. Surveillance of a nuclear reactor core by use of a pattern recognition method

    International Nuclear Information System (INIS)

    Invernizzi, Michel.

    1982-07-01

    A pattern recognition system is described for the surveillance of a PWR reactor. This report contains four chapters. The first one succinctly deals with statistical pattern recognition principles. In the second chapter we show how a surveillance problem may be treated by pattern recognition and we present methods for surveillances (detection of abnormalities), controls (kind of running recognition) and diagnotics (kind of abnormality recognition). The third chapter shows a surveillance method of a nuclear plant. The signals used are the neutron noise observations made by the ionization chambers inserted in the reactor. Abnormality is defined in opposition with the training set witch is supposed to be an exhaustive summary of normality. In the fourth chapter we propose a scheme for an adaptative recognition and a method based on classes modelisations by hyper-spheres. This method has been tested on simulated training sets in two-dimensional feature spaces. It gives solutions to problems of non-linear separability [fr

  5. Diagram, a Learning Environment for Initiation to Object-Oriented Modeling with UML Class Diagrams

    Science.gov (United States)

    Py, Dominique; Auxepaules, Ludovic; Alonso, Mathilde

    2013-01-01

    This paper presents Diagram, a learning environment for object-oriented modelling (OOM) with UML class diagrams. Diagram an open environment, in which the teacher can add new exercises without constraints on the vocabulary or the size of the diagram. The interface includes methodological help, encourages self-correcting and self-monitoring, and…

  6. Medial prefrontal cortex role in recognition memory in rodents.

    Science.gov (United States)

    Morici, Juan Facundo; Bekinschtein, Pedro; Weisstaub, Noelia V

    2015-10-01

    The study of the neurobiology of recognition memory, defined by the integration of the different components of experiences that support recollection of past experiences have been a challenge for memory researches for many years. In the last twenty years, with the development of the spontaneous novel object recognition task and all its variants this has started to change. The features of recognition memory include a particular object or person ("what"), the context in which the experience took place, which can be the arena itself or the location within a particular arena ("where") and the particular time at which the event occurred ("when"). This definition instead of the historical anthropocentric one allows the study of this type of episodic memory in animal models. Some forms of recognition memory that require integration of different features recruit the medial prefrontal cortex. Focusing on findings from spontaneous recognition memory tasks performed by rodents, this review concentrates on the description of previous works that have examined the role that the medial prefrontal cortex has on the different steps of recognition memory. We conclude that this structure, independently of the task used, is required at different memory stages when the task cannot be solved by a single item strategy. Copyright © 2015 Elsevier B.V. All rights reserved.

  7. Predictive Coding Strategies for Invariant Object Recognition and Volitional Motion Control in Neuromorphic Agents

    Science.gov (United States)

    2015-09-02

    model for scene understanding was proposed based on deep convolutional neural networks to improve recognition accuracy. Facial expression recognition ...A deep-learning-based model for facial expression recognition was formulated. It could recognize emotional status of people regardless of...CVPRW), 2014 IEEE Conference on. IEEE, 2014. DISTRIBUTION A: Distribution approved for public release. 4 Facial Expression Recognition

  8. Effects of diesel engine exhaust origin secondary organic aerosols on novel object recognition ability and maternal behavior in BALB/c mice.

    Science.gov (United States)

    Win-Shwe, Tin-Tin; Fujitani, Yuji; Kyi-Tha-Thu, Chaw; Furuyama, Akiko; Michikawa, Takehiro; Tsukahara, Shinji; Nitta, Hiroshi; Hirano, Seishiro

    2014-10-30

    Epidemiological studies have reported an increased risk of cardiopulmonary and lung cancer mortality associated with increasing exposure to air pollution. Ambient particulate matter consists of primary particles emitted directly from diesel engine vehicles and secondary organic aerosols (SOAs) are formed by oxidative reaction of the ultrafine particle components of diesel exhaust (DE) in the atmosphere. However, little is known about the relationship between exposure to SOA and central nervous system functions. Recently, we have reported that an acute single intranasal instillation of SOA may induce inflammatory response in lung, but not in brain of adult mice. To clarify the whole body exposure effects of SOA on central nervous system functions, we first created inhalation chambers for diesel exhaust origin secondary organic aerosols (DE-SOAs) produced by oxidation of diesel exhaust particles caused by adding ozone. Male BALB/c mice were exposed to clean air (control), DE and DE-SOA in inhalation chambers for one or three months (5 h/day, 5 days/week) and were examined for memory function using a novel object recognition test and for memory function-related gene expressions in the hippocampus by real-time RT-PCR. Moreover, female mice exposed to DE-SOA for one month were mated and maternal behaviors and the related gene expressions in the hypothalamus examined. Novel object recognition ability and N-methyl-D-aspartate (NMDA) receptor expression in the hippocampus were affected in male mice exposed to DE-SOA. Furthermore, a tendency to decrease maternal performance and significantly decreased expression levels of estrogen receptor (ER)-α, and oxytocin receptor were found in DE-SOA exposed dams compared with the control. This is the first study of this type and our results suggest that the constituents of DE-SOA may be associated with memory function and maternal performance based on the impaired gene expressions in the hippocampus and hypothalamus, respectively.

  9. Effects of Diesel Engine Exhaust Origin Secondary Organic Aerosols on Novel Object Recognition Ability and Maternal Behavior in BALB/C Mice

    Directory of Open Access Journals (Sweden)

    Tin-Tin Win-Shwe

    2014-10-01

    Full Text Available Epidemiological studies have reported an increased risk of cardiopulmonary and lung cancer mortality associated with increasing exposure to air pollution. Ambient particulate matter consists of primary particles emitted directly from diesel engine vehicles and secondary organic aerosols (SOAs are formed by oxidative reaction of the ultrafine particle components of diesel exhaust (DE in the atmosphere. However, little is known about the relationship between exposure to SOA and central nervous system functions. Recently, we have reported that an acute single intranasal instillation of SOA may induce inflammatory response in lung, but not in brain of adult mice. To clarify the whole body exposure effects of SOA on central nervous system functions, we first created inhalation chambers for diesel exhaust origin secondary organic aerosols (DE-SOAs produced by oxidation of diesel exhaust particles caused by adding ozone. Male BALB/c mice were exposed to clean air (control, DE and DE-SOA in inhalation chambers for one or three months (5 h/day, 5 days/week and were examined for memory function using a novel object recognition test and for memory function-related gene expressions in the hippocampus by real-time RT-PCR. Moreover, female mice exposed to DE-SOA for one month were mated and maternal behaviors and the related gene expressions in the hypothalamus examined. Novel object recognition ability and N-methyl-D-aspartate (NMDA receptor expression in the hippocampus were affected in male mice exposed to DE-SOA. Furthermore, a tendency to decrease maternal performance and significantly decreased expression levels of estrogen receptor (ER-a, and oxytocin receptor were found in DE-SOA exposed dams compared with the control. This is the first study of this type and our results suggest that the constituents of DE-SOA may be associated with memory function and maternal performance based on the impaired gene expressions in the hippocampus and hypothalamus

  10. Channel-dependent GMM and multi-class logistic: Regression models for language recognition

    NARCIS (Netherlands)

    Leeuwen, D.A. van; Brümmer, Niko

    2006-01-01

    This paper describes two new approaches to spoken language recognition. These were both successfully applied in the NIST 2005 Language Recognition Evaluation. The first approach extends the Gaussian Mixture Model technique with channel dependency, which results in actual detection costs (CDET) of

  11. Automatic anatomy recognition on CT images with pathology

    Science.gov (United States)

    Huang, Lidong; Udupa, Jayaram K.; Tong, Yubing; Odhner, Dewey; Torigian, Drew A.

    2016-03-01

    Body-wide anatomy recognition on CT images with pathology becomes crucial for quantifying body-wide disease burden. This, however, is a challenging problem because various diseases result in various abnormalities of objects such as shape and intensity patterns. We previously developed an automatic anatomy recognition (AAR) system [1] whose applicability was demonstrated on near normal diagnostic CT images in different body regions on 35 organs. The aim of this paper is to investigate strategies for adapting the previous AAR system to diagnostic CT images of patients with various pathologies as a first step toward automated body-wide disease quantification. The AAR approach consists of three main steps - model building, object recognition, and object delineation. In this paper, within the broader AAR framework, we describe a new strategy for object recognition to handle abnormal images. In the model building stage an optimal threshold interval is learned from near-normal training images for each object. This threshold is optimally tuned to the pathological manifestation of the object in the test image. Recognition is performed following a hierarchical representation of the objects. Experimental results for the abdominal body region based on 50 near-normal images used for model building and 20 abnormal images used for object recognition show that object localization accuracy within 2 voxels for liver and spleen and 3 voxels for kidney can be achieved with the new strategy.

  12. Dynamic evolving spiking neural networks for on-line spatio- and spectro-temporal pattern recognition.

    Science.gov (United States)

    Kasabov, Nikola; Dhoble, Kshitij; Nuntalid, Nuttapod; Indiveri, Giacomo

    2013-05-01

    On-line learning and recognition of spatio- and spectro-temporal data (SSTD) is a very challenging task and an important one for the future development of autonomous machine learning systems with broad applications. Models based on spiking neural networks (SNN) have already proved their potential in capturing spatial and temporal data. One class of them, the evolving SNN (eSNN), uses a one-pass rank-order learning mechanism and a strategy to evolve a new spiking neuron and new connections to learn new patterns from incoming data. So far these networks have been mainly used for fast image and speech frame-based recognition. Alternative spike-time learning methods, such as Spike-Timing Dependent Plasticity (STDP) and its variant Spike Driven Synaptic Plasticity (SDSP), can also be used to learn spatio-temporal representations, but they usually require many iterations in an unsupervised or semi-supervised mode of learning. This paper introduces a new class of eSNN, dynamic eSNN, that utilise both rank-order learning and dynamic synapses to learn SSTD in a fast, on-line mode. The paper also introduces a new model called deSNN, that utilises rank-order learning and SDSP spike-time learning in unsupervised, supervised, or semi-supervised modes. The SDSP learning is used to evolve dynamically the network changing connection weights that capture spatio-temporal spike data clusters both during training and during recall. The new deSNN model is first illustrated on simple examples and then applied on two case study applications: (1) moving object recognition using address-event representation (AER) with data collected using a silicon retina device; (2) EEG SSTD recognition for brain-computer interfaces. The deSNN models resulted in a superior performance in terms of accuracy and speed when compared with other SNN models that use either rank-order or STDP learning. The reason is that the deSNN makes use of both the information contained in the order of the first input spikes

  13. A validated set of tool pictures with matched objects and non-objects for laterality research.

    Science.gov (United States)

    Verma, Ark; Brysbaert, Marc

    2015-01-01

    Neuropsychological and neuroimaging research has established that knowledge related to tool use and tool recognition is lateralized to the left cerebral hemisphere. Recently, behavioural studies with the visual half-field technique have confirmed the lateralization. A limitation of this research was that different sets of stimuli had to be used for the comparison of tools to other objects and objects to non-objects. Therefore, we developed a new set of stimuli containing matched triplets of tools, other objects and non-objects. With the new stimulus set, we successfully replicated the findings of no visual field advantage for objects in an object recognition task combined with a significant right visual field advantage for tools in a tool recognition task. The set of stimuli is available as supplemental data to this article.

  14. Pipeline leakage recognition based on the projection singular value features and support vector machine

    Energy Technology Data Exchange (ETDEWEB)

    Liang, Wei; Zhang, Laibin; Mingda, Wang; Jinqiu, Hu [College of Mechanical and Transportation Engineering, China University of Petroleum, Beijing, (China)

    2010-07-01

    The negative wave pressure method is one of the processes used to detect leaks on oil pipelines. The development of new leakage recognition processes is difficult because it is practically impossible to collect leakage pressure samples. The method of leakage feature extraction and the selection of the recognition model are also important in pipeline leakage detection. This study investigated a new feature extraction approach Singular Value Projection (SVP). It projects the singular value to a standard basis. A new pipeline recognition model based on the multi-class Support Vector Machines was also developed. It was found that SVP is a clear and concise recognition feature of the negative pressure wave. Field experiments proved that the model provided a high recognition accuracy rate. This approach to pipeline leakage detection based on the SVP and SVM has a high application value.

  15. Analysis and recognition of 5 ' UTR intron splice sites in human pre-mRNA

    DEFF Research Database (Denmark)

    Eden, E.; Brunak, Søren

    2004-01-01

    Prediction of splice sites in non-coding regions of genes is one of the most challenging aspects of gene structure recognition. We perform a rigorous analysis of such splice sites embedded in human 5' untranslated regions (UTRs), and investigate correlations between this class of splice sites and...

  16. Palmprint and face multi-modal biometric recognition based on SDA-GSVD and its kernelization.

    Science.gov (United States)

    Jing, Xiao-Yuan; Li, Sheng; Li, Wen-Qian; Yao, Yong-Fang; Lan, Chao; Lu, Jia-Sen; Yang, Jing-Yu

    2012-01-01

    When extracting discriminative features from multimodal data, current methods rarely concern themselves with the data distribution. In this paper, we present an assumption that is consistent with the viewpoint of discrimination, that is, a person's overall biometric data should be regarded as one class in the input space, and his different biometric data can form different Gaussians distributions, i.e., different subclasses. Hence, we propose a novel multimodal feature extraction and recognition approach based on subclass discriminant analysis (SDA). Specifically, one person's different bio-data are treated as different subclasses of one class, and a transformed space is calculated, where the difference among subclasses belonging to different persons is maximized, and the difference within each subclass is minimized. Then, the obtained multimodal features are used for classification. Two solutions are presented to overcome the singularity problem encountered in calculation, which are using PCA preprocessing, and employing the generalized singular value decomposition (GSVD) technique, respectively. Further, we provide nonlinear extensions of SDA based multimodal feature extraction, that is, the feature fusion based on KPCA-SDA and KSDA-GSVD. In KPCA-SDA, we first apply Kernel PCA on each single modal before performing SDA. While in KSDA-GSVD, we directly perform Kernel SDA to fuse multimodal data by applying GSVD to avoid the singular problem. For simplicity two typical types of biometric data are considered in this paper, i.e., palmprint data and face data. Compared with several representative multimodal biometrics recognition methods, experimental results show that our approaches outperform related multimodal recognition methods and KSDA-GSVD achieves the best recognition performance.

  17. Palmprint and Face Multi-Modal Biometric Recognition Based on SDA-GSVD and Its Kernelization

    Science.gov (United States)

    Jing, Xiao-Yuan; Li, Sheng; Li, Wen-Qian; Yao, Yong-Fang; Lan, Chao; Lu, Jia-Sen; Yang, Jing-Yu

    2012-01-01

    When extracting discriminative features from multimodal data, current methods rarely concern themselves with the data distribution. In this paper, we present an assumption that is consistent with the viewpoint of discrimination, that is, a person's overall biometric data should be regarded as one class in the input space, and his different biometric data can form different Gaussians distributions, i.e., different subclasses. Hence, we propose a novel multimodal feature extraction and recognition approach based on subclass discriminant analysis (SDA). Specifically, one person's different bio-data are treated as different subclasses of one class, and a transformed space is calculated, where the difference among subclasses belonging to different persons is maximized, and the difference within each subclass is minimized. Then, the obtained multimodal features are used for classification. Two solutions are presented to overcome the singularity problem encountered in calculation, which are using PCA preprocessing, and employing the generalized singular value decomposition (GSVD) technique, respectively. Further, we provide nonlinear extensions of SDA based multimodal feature extraction, that is, the feature fusion based on KPCA-SDA and KSDA-GSVD. In KPCA-SDA, we first apply Kernel PCA on each single modal before performing SDA. While in KSDA-GSVD, we directly perform Kernel SDA to fuse multimodal data by applying GSVD to avoid the singular problem. For simplicity two typical types of biometric data are considered in this paper, i.e., palmprint data and face data. Compared with several representative multimodal biometrics recognition methods, experimental results show that our approaches outperform related multimodal recognition methods and KSDA-GSVD achieves the best recognition performance. PMID:22778600

  18. Antidepressant drugs specifically inhibiting noradrenaline reuptake enhance recognition memory in rats.

    Science.gov (United States)

    Feltmann, Kristin; Konradsson-Geuken, Åsa; De Bundel, Dimitri; Lindskog, Maria; Schilström, Björn

    2015-12-01

    Patients suffering from major depression often experience memory deficits even after the remission of mood symptoms, and many antidepressant drugs do not affect, or impair, memory in animals and humans. However, some antidepressant drugs, after a single dose, enhance cognition in humans (Harmer et al., 2009). To compare different classes of antidepressant drugs for their potential as memory enhancers, we used a version of the novel object recognition task in which rats spontaneously forget objects 24 hr after their presentation. Antidepressant drugs were injected systemically 30 min before or directly after the training phase (Session 1 [S1]). Post-S1 injections were used to test for specific memory-consolidation effects. The noradrenaline reuptake inhibitors reboxetine and atomoxetine, as well as the serotonin noradrenaline reuptake inhibitor duloxetine, injected prior to S1 significantly enhanced recognition memory. In contrast, the serotonin reuptake inhibitors citalopram and paroxetine and the cyclic antidepressant drugs desipramine and mianserin did not enhance recognition memory. Post-S1 injection of either reboxetine or citalopram significantly enhanced recognition memory, indicating an effect on memory consolidation. The fact that citalopram had an effect only when injected after S1 suggests that it may counteract its own consolidation-enhancing effect by interfering with memory acquisition. However, pretreatment with citalopram did not attenuate reboxetine's memory-enhancing effect. The D1/5-receptor antagonist SCH23390 blunted reboxetine's memory-enhancing effect, indicating a role of dopaminergic transmission in reboxetine-induced recognition memory enhancement. Our results suggest that antidepressant drugs specifically inhibiting noradrenaline reuptake enhance cognition and may be beneficial in the treatment of cognitive symptoms of depression. (c) 2015 APA, all rights reserved).

  19. The impact of feature selection on one and two-class classification performance for plant microRNAs.

    Science.gov (United States)

    Khalifa, Waleed; Yousef, Malik; Saçar Demirci, Müşerref Duygu; Allmer, Jens

    2016-01-01

    MicroRNAs (miRNAs) are short nucleotide sequences that form a typical hairpin structure which is recognized by a complex enzyme machinery. It ultimately leads to the incorporation of 18-24 nt long mature miRNAs into RISC where they act as recognition keys to aid in regulation of target mRNAs. It is involved to determine miRNAs experimentally and, therefore, machine learning is used to complement such endeavors. The success of machine learning mostly depends on proper input data and appropriate features for parameterization of the data. Although, in general, two-class classification (TCC) is used in the field; because negative examples are hard to come by, one-class classification (OCC) has been tried for pre-miRNA detection. Since both positive and negative examples are currently somewhat limited, feature selection can prove to be vital for furthering the field of pre-miRNA detection. In this study, we compare the performance of OCC and TCC using eight feature selection methods and seven different plant species providing positive pre-miRNA examples. Feature selection was very successful for OCC where the best feature selection method achieved an average accuracy of 95.6%, thereby being ∼29% better than the worst method which achieved 66.9% accuracy. While the performance is comparable to TCC, which performs up to 3% better than OCC, TCC is much less affected by feature selection and its largest performance gap is ∼13% which only occurs for two of the feature selection methodologies. We conclude that feature selection is crucially important for OCC and that it can perform on par with TCC given the proper set of features.

  20. The impact of feature selection on one and two-class classification performance for plant microRNAs

    Directory of Open Access Journals (Sweden)

    Waleed Khalifa

    2016-06-01

    Full Text Available MicroRNAs (miRNAs are short nucleotide sequences that form a typical hairpin structure which is recognized by a complex enzyme machinery. It ultimately leads to the incorporation of 18–24 nt long mature miRNAs into RISC where they act as recognition keys to aid in regulation of target mRNAs. It is involved to determine miRNAs experimentally and, therefore, machine learning is used to complement such endeavors. The success of machine learning mostly depends on proper input data and appropriate features for parameterization of the data. Although, in general, two-class classification (TCC is used in the field; because negative examples are hard to come by, one-class classification (OCC has been tried for pre-miRNA detection. Since both positive and negative examples are currently somewhat limited, feature selection can prove to be vital for furthering the field of pre-miRNA detection. In this study, we compare the performance of OCC and TCC using eight feature selection methods and seven different plant species providing positive pre-miRNA examples. Feature selection was very successful for OCC where the best feature selection method achieved an average accuracy of 95.6%, thereby being ∼29% better than the worst method which achieved 66.9% accuracy. While the performance is comparable to TCC, which performs up to 3% better than OCC, TCC is much less affected by feature selection and its largest performance gap is ∼13% which only occurs for two of the feature selection methodologies. We conclude that feature selection is crucially important for OCC and that it can perform on par with TCC given the proper set of features.

  1. Toward retail product recognition on grocery shelves

    Science.gov (United States)

    Varol, Gül; Kuzu, Rıdvan S.

    2015-03-01

    This paper addresses the problem of retail product recognition on grocery shelf images. We present a technique for accomplishing this task with a low time complexity. We decompose the problem into detection and recognition. The former is achieved by a generic product detection module which is trained on a specific class of products (e.g. tobacco packages). Cascade object detection framework of Viola and Jones [1] is used for this purpose. We further make use of Support Vector Machines (SVMs) to recognize the brand inside each detected region. We extract both shape and color information; and apply feature-level fusion from two separate descriptors computed with the bag of words approach. Furthermore, we introduce a dataset (available on request) that we have collected for similar research purposes. Results are presented on this dataset of more than 5,000 images consisting of 10 tobacco brands. We show that satisfactory detection and classification can be achieved on devices with cheap computational power. Potential applications of the proposed approach include planogram compliance control, inventory management and assisting visually impaired people during shopping.

  2. Age, environment, object recognition and morphological diversity of GFAP-immunolabeled astrocytes.

    Science.gov (United States)

    Diniz, Daniel Guerreiro; de Oliveira, Marcus Augusto; de Lima, Camila Mendes; Fôro, César Augusto Raiol; Sosthenes, Marcia Consentino Kronka; Bento-Torres, João; da Costa Vasconcelos, Pedro Fernando; Anthony, Daniel Clive; Diniz, Cristovam Wanderley Picanço

    2016-10-10

    Few studies have explored the glial response to a standard environment and how the response may be associated with age-related cognitive decline in learning and memory. Here we investigated aging and environmental influences on hippocampal-dependent tasks and on the morphology of an unbiased selected population of astrocytes from the molecular layer of dentate gyrus, which is the main target of perforant pathway. Six and twenty-month-old female, albino Swiss mice were housed, from weaning, in a standard or enriched environment, including running wheels for exercise and tested for object recognition and contextual memories. Young adult and aged subjects, independent of environment, were able to distinguish familiar from novel objects. All experimental groups, except aged mice from standard environment, distinguish stationary from displaced objects. Young adult but not aged mice, independent of environment, were able to distinguish older from recent objects. Only young mice from an enriched environment were able to distinguish novel from familiar contexts. Unbiased selected astrocytes from the molecular layer of the dentate gyrus were reconstructed in three-dimensions and classified using hierarchical cluster analysis of bimodal or multimodal morphological features. We found two morphological phenotypes of astrocytes and we designated type I the astrocytes that exhibited significantly higher values of morphological complexity as compared with type II. Complexity = [Sum of the terminal orders + Number of terminals] × [Total branch length/Number of primary branches]. On average, type I morphological complexity seems to be much more sensitive to age and environmental influences than that of type II. Indeed, aging and environmental impoverishment interact and reduce the morphological complexity of type I astrocytes at a point that they could not be distinguished anymore from type II. We suggest these two types of astrocytes may have different physiological roles

  3. Positive regulation of plasmacytoid dendritic cell function via Ly49Q recognition of class I MHC

    Science.gov (United States)

    Tai, Lee-Hwa; Goulet, Marie-Line; Belanger, Simon; Toyama-Sorimachi, Noriko; Fodil-Cornu, Nassima; Vidal, Silvia M.; Troke, Angela D.; McVicar, Daniel W.; Makrigiannis, Andrew P.

    2008-01-01

    Plasmacytoid dendritic cells (pDCs) are an important source of type I interferon (IFN) during initial immune responses to viral infections. In mice, pDCs are uniquely characterized by high-level expression of Ly49Q, a C-type lectin-like receptor specific for class I major histocompatibility complex (MHC) molecules. Despite having a cytoplasmic immunoreceptor tyrosine-based inhibitory motif, Ly49Q was found to enhance pDC function in vitro, as pDC cytokine production in response to the Toll-like receptor (TLR) 9 agonist CpG-oligonucleotide (ODN) could be blocked using soluble monoclonal antibody (mAb) to Ly49Q or H-2Kb. Conversely, CpG-ODN–dependent IFN-α production by pDCs was greatly augmented upon receptor cross-linking using immobilized anti-Ly49Q mAb or recombinant H-2Kb ligand. Accordingly, Ly49Q-deficient pDCs displayed a severely reduced capacity to produce cytokines in response to TLR7 and TLR9 stimulation both in vitro and in vivo. Finally, TLR9-dependent antiviral responses were compromised in Ly49Q-null mice infected with mouse cytomegalovirus. Thus, class I MHC recognition by Ly49Q on pDCs is necessary for optimal activation of innate immune responses in vivo. PMID:19075287

  4. A Virtual Class Calculus

    DEFF Research Database (Denmark)

    Ernst, Erik; Ostermann, Klaus; Cook, William Randall

    2006-01-01

    Virtual classes are class-valued attributes of objects. Like virtual methods, virtual classes are defined in an object's class and may be redefined within subclasses. They resemble inner classes, which are also defined within a class, but virtual classes are accessed through object instances...... model for virtual classes has been a long-standing open question. This paper presents a virtual class calculus, vc, that captures the essence of virtual classes in these full-fledged programming languages. The key contributions of the paper are a formalization of the dynamic and static semantics of vc...

  5. On the Evaluation of Outlier Detection and One-Class Classification Methods

    DEFF Research Database (Denmark)

    Swersky, Lorne; Marques, Henrique O.; Sander, Jörg

    2016-01-01

    It has been shown that unsupervised outlier detection methods can be adapted to the one-class classification problem. In this paper, we focus on the comparison of oneclass classification algorithms with such adapted unsupervised outlier detection methods, improving on previous comparison studies ...

  6. Mapping US Urban Extents from MODIS Data Using One-Class Classification Method

    Directory of Open Access Journals (Sweden)

    Bo Wan

    2015-08-01

    Full Text Available Urban areas are one of the most important components of human society. Their extents have been continuously growing during the last few decades. Accurate and timely measurements of the extents of urban areas can help in analyzing population densities and urban sprawls and in studying environmental issues related to urbanization. Urban extents detected from remotely sensed data are usually a by-product of land use classification results, and their interpretation requires a full understanding of land cover types. In this study, for the first time, we mapped urban extents in the continental United States using a novel one-class classification method, i.e., positive and unlabeled learning (PUL, with multi-temporal Moderate Resolution Imaging Spectroradiometer (MODIS data for the year 2010. The Defense Meteorological Satellite Program Operational Linescan System (DMSP-OLS night stable light data were used to calibrate the urban extents obtained from the one-class classification scheme. Our results demonstrated the effectiveness of the use of the PUL algorithm in mapping large-scale urban areas from coarse remote-sensing images, for the first time. The total accuracy of mapped urban areas was 92.9% and the kappa coefficient was 0.85. The use of DMSP-OLS night stable light data can significantly reduce false detection rates from bare land and cropland far from cities. Compared with traditional supervised classification methods, the one-class classification scheme can greatly reduce the effort involved in collecting training datasets, without losing predictive accuracy.

  7. Object Recognition in Flight: How Do Bees Distinguish between 3D Shapes?

    Science.gov (United States)

    Werner, Annette; Stürzl, Wolfgang; Zanker, Johannes

    2016-01-01

    Honeybees (Apis mellifera) discriminate multiple object features such as colour, pattern and 2D shape, but it remains unknown whether and how bees recover three-dimensional shape. Here we show that bees can recognize objects by their three-dimensional form, whereby they employ an active strategy to uncover the depth profiles. We trained individual, free flying honeybees to collect sugar water from small three-dimensional objects made of styrofoam (sphere, cylinder, cuboids) or folded paper (convex, concave, planar) and found that bees can easily discriminate between these stimuli. We also tested possible strategies employed by the bees to uncover the depth profiles. For the card stimuli, we excluded overall shape and pictorial features (shading, texture gradients) as cues for discrimination. Lacking sufficient stereo vision, bees are known to use speed gradients in optic flow to detect edges; could the bees apply this strategy also to recover the fine details of a surface depth profile? Analysing the bees' flight tracks in front of the stimuli revealed specific combinations of flight maneuvers (lateral translations in combination with yaw rotations), which are particularly suitable to extract depth cues from motion parallax. We modelled the generated optic flow and found characteristic patterns of angular displacement corresponding to the depth profiles of our stimuli: optic flow patterns from pure translations successfully recovered depth relations from the magnitude of angular displacements, additional rotation provided robust depth information based on the direction of the displacements; thus, the bees flight maneuvers may reflect an optimized visuo-motor strategy to extract depth structure from motion signals. The robustness and simplicity of this strategy offers an efficient solution for 3D-object-recognition without stereo vision, and could be employed by other flying insects, or mobile robots.

  8. Shrinking an arbitrary object as one desires using metamaterials

    Science.gov (United States)

    Jiang, Wei Xiang; Cui, Tie Jun; Yang, Xin Mi; Ma, Hui Feng; Cheng, Qiang

    2011-05-01

    Based on transformation optics, we present a shrinking device, which can transform an arbitrary object virtually into a small-size object with different material parameters as one desires. Such an illusion device will confuse the detectors or the viewers, and hence the real size and material parameters of the enclosed object cannot be perceived. We fabricated and measured a shrinking device by using metamaterials, which works at the nonresonant frequency and has low loss. The device has been validated by both numerical simulations and experiments on circular and square objects. Good shrinking performance has been demonstrated.

  9. A combined MRI and MRSI based multiclass system for brain tumour recognition using LS-SVMs with class probabilities and feature selection.

    NARCIS (Netherlands)

    Luts, J.; Heerschap, A.; Suykens, J.A.; Huffel, S. van

    2007-01-01

    OBJECTIVE: This study investigates the use of automated pattern recognition methods on magnetic resonance data with the ultimate goal to assist clinicians in the diagnosis of brain tumours. Recently, the combined use of magnetic resonance imaging (MRI) and magnetic resonance spectroscopic imaging

  10. Multiple Levels of Recognition in Ants: A Feature of Complex Societies

    DEFF Research Database (Denmark)

    D'Ettorre, Patrizia

    2008-01-01

    diverse. In ants, social interactions are regulated by at least three levels of recognition. Nestmate recognition occurs between colonies, is very effective, and involves fast processing. Within a colony, division of labor is enhanced by recognition of different classes of individuals. Ultimately......, in particular circumstances, such as cooperative colony founding with stable dominance hierarchies, ants are capable of individual recognition. The underlying recognition cues and mechanisms appear to be specific to each recognition level, and their integrated understanding could contribute...

  11. When is the hippocampus involved in recognition memory?

    OpenAIRE

    Barker, Gareth R. I.; Warburton, Elizabeth C.

    2011-01-01

    The role of the hippocampus in recognition memory is controversial. Recognition memory judgments may be made using different types of information, including object familiarity, an object's spatial location, or when an object was encountered. Experiment 1 examined the role of the hippocampus in recognition memory tasks that required the animals to use these different types of mnemonic information. Rats with bilateral cytotoxic lesions in the hippocampus or perirhinal or prefrontal cortex were ...

  12. Currency recognition using a smartphone: Comparison between color SIFT and gray scale SIFT algorithms

    Directory of Open Access Journals (Sweden)

    Iyad Abu Doush

    2017-10-01

    Full Text Available Banknote recognition means classifying the currency (coin and paper to the correct class. In this paper, we developed a dataset for Jordanian currency. After that we applied automatic mobile recognition system using a smartphone on the dataset using scale-invariant feature transform (SIFT algorithm. This is the first attempt, to the best of the authors knowledge, to recognize both coins and paper banknotes on a smartphone using SIFT algorithm. SIFT has been developed to be the most robust and efficient local invariant feature descriptor. Color provides significant information and important values in the object description process and matching tasks. Many objects cannot be classified correctly without their color features. We compared between two approaches colored local invariant feature descriptor (color SIFT approach and gray image local invariant feature descriptor (gray SIFT approach. The evaluation results show that the color SIFT approach outperforms the gray SIFT approach in terms of processing time and accuracy.

  13. The devil you know: The effect of brand recognition and product ratings on consumer choice

    Directory of Open Access Journals (Sweden)

    Volker Thoma

    2013-01-01

    Full Text Available Previous research on the role of recognition in decision-making in inferential choice has focussed on the Recognition Heuristic (RH, which proposes that in situations where recognition is predictive of a decision criterion, recognized objects will be chosen over unrecognized ones, regardless of any other available relevant information. In the current study we examine the role of recognition in preferential choice, in which subjects had to choose one of a pair of consumer objects that were presented with quality ratings (positive, neutral, and negative. The results showed that subjects' choices were largely based on recognition, as the famous brand was preferred even when additional star ratings rendered it as less attractive. However, the additional information did affect the proportion of chosen famous items, in particular in the cases when star ratings for the recognised brand were negative. This condition also resulted in longer response times compared to neutral and positive conditions. Thus, the current data do not point to a simple compensatory mechanism in preferential choice: although choice is affected by additional information, it seems that recognition is employed as an initial important first step in the decision-making process.

  14. Acute fasting inhibits central caspase-1 activity reducing anxiety-like behavior and increasing novel object and object location recognition.

    Science.gov (United States)

    Towers, Albert E; Oelschlager, Maci L; Patel, Jay; Gainey, Stephen J; McCusker, Robert H; Freund, Gregory G

    2017-06-01

    Inflammation within the central nervous system (CNS) is frequently comorbid with anxiety. Importantly, the pro-inflammatory cytokine most commonly associated with anxiety is IL-1β. The bioavailability and activity of IL-1β are regulated by caspase-1-dependent proteolysis vis-a-vis the inflammasome. Thus, interventions regulating the activation or activity of caspase-1 should reduce anxiety especially in states that foster IL-1β maturation. Male C57BL/6j, C57BL/6j mice treated with the capase-1 inhibitor biotin-YVAD-cmk, caspase-1 knockout (KO) mice and IL-1R1 KO mice were fasted for 24h or allowed ad libitum access to food. Immediately after fasting, caspase-1 activity was measured in brain region homogenates while activated caspase-1 was localized in the brain by immunohistochemistry. Mouse anxiety-like behavior and cognition were tested using the elevated zero maze and novel object/object location tasks, respectively. A 24h fast in mice reduced the activity of caspase-1 in whole brain and in the prefrontal cortex, amygdala, hippocampus, and hypothalamus by 35%, 25%, 40%, 40%, and 40% respectively. A 24h fast also reduced anxiety-like behavior by 40% and increased novel object and object location recognition by 21% and 31%, respectively. IL-1β protein, however, was not reduced in the brain by fasting. ICV administration of YVAD decreased caspase-1 activity in the prefrontal cortex and amygdala by 55%, respectively leading to a 64% reduction in anxiety like behavior. Importantly, when caspase-1 KO or IL1-R1 KO mice are fasted, no fasting-dependent reduction in anxiety-like behavior was observed. Results indicate that fasting decrease anxiety-like behavior and improves memory by a mechanism tied to reducing caspase-1 activity throughout the brain. Copyright © 2017 Elsevier Inc. All rights reserved.

  15. Efficient Interaction Recognition through Positive Action Representation

    Directory of Open Access Journals (Sweden)

    Tao Hu

    2013-01-01

    Full Text Available This paper proposes a novel approach to decompose two-person interaction into a Positive Action and a Negative Action for more efficient behavior recognition. A Positive Action plays the decisive role in a two-person exchange. Thus, interaction recognition can be simplified to Positive Action-based recognition, focusing on an action representation of just one person. Recently, a new depth sensor has become widely available, the Microsoft Kinect camera, which provides RGB-D data with 3D spatial information for quantitative analysis. However, there are few publicly accessible test datasets using this camera, to assess two-person interaction recognition approaches. Therefore, we created a new dataset with six types of complex human interactions (i.e., named K3HI, including kicking, pointing, punching, pushing, exchanging an object, and shaking hands. Three types of features were extracted for each Positive Action: joint, plane, and velocity features. We used continuous Hidden Markov Models (HMMs to evaluate the Positive Action-based interaction recognition method and the traditional two-person interaction recognition approach with our test dataset. Experimental results showed that the proposed recognition technique is more accurate than the traditional method, shortens the sample training time, and therefore achieves comprehensive superiority.

  16. What pharmacological interventions indicate concerning the role of the perirhinal cortex in recognition memory.

    Science.gov (United States)

    Brown, M W; Barker, G R I; Aggleton, J P; Warburton, E C

    2012-11-01

    Findings of pharmacological studies that have investigated the involvement of specific regions of the brain in recognition memory are reviewed. The particular emphasis of the review concerns what such studies indicate concerning the role of the perirhinal cortex in recognition memory. Most of the studies involve rats and most have investigated recognition memory for objects. Pharmacological studies provide a large body of evidence supporting the essential role of the perirhinal cortex in the acquisition, consolidation and retrieval of object recognition memory. Such studies provide increasingly detailed evidence concerning both the neurotransmitter systems and the underlying intracellular mechanisms involved in recognition memory processes. They have provided evidence in support of synaptic weakening as a major synaptic plastic process within perirhinal cortex underlying object recognition memory. They have also supplied confirmatory evidence that that there is more than one synaptic plastic process involved. The demonstrated necessity to long-term recognition memory of intracellular signalling mechanisms related to synaptic modification within perirhinal cortex establishes a central role for the region in the information storage underlying such memory. Perirhinal cortex is thereby established as an information storage site rather than solely a processing station. Pharmacological studies have also supplied new evidence concerning the detailed roles of other regions, including the hippocampus and the medial prefrontal cortex in different types of recognition memory tasks that include a spatial or temporal component. In so doing, they have also further defined the contribution of perirhinal cortex to such tasks. To date it appears that the contribution of perirhinal cortex to associative and temporal order memory reflects that in simple object recognition memory, namely that perirhinal cortex provides information concerning objects and their prior occurrence (novelty

  17. Threshold models of recognition and the recognition heuristic

    Directory of Open Access Journals (Sweden)

    Edgar Erdfelder

    2011-02-01

    Full Text Available According to the recognition heuristic (RH theory, decisions follow the recognition principle: Given a high validity of the recognition cue, people should prefer recognized choice options compared to unrecognized ones. Assuming that the memory strength of choice options is strongly correlated with both the choice criterion and recognition judgments, the RH is a reasonable strategy that approximates optimal decisions with a minimum of cognitive effort (Davis-Stober, Dana, and Budescu, 2010. However, theories of recognition memory are not generally compatible with this assumption. For example, some threshold models of recognition presume that recognition judgments can arise from two types of cognitive states: (1 certainty states in which judgments are almost perfectly correlated with memory strength and (2 uncertainty states in which recognition judgments reflect guessing rather than differences in memory strength. We report an experiment designed to test the prediction that the RH applies to certainty states only. Our results show that memory states rather than recognition judgments affect use of recognition information in binary decisions.

  18. Changing predictions, stable recognition: Children's representations of downward incline motion.

    Science.gov (United States)

    Hast, Michael; Howe, Christine

    2017-11-01

    Various studies to-date have demonstrated children hold ill-conceived expressed beliefs about the physical world such as that one ball will fall faster than another because it is heavier. At the same time, they also demonstrate accurate recognition of dynamic events. How these representations relate is still unresolved. This study examined 5- to 11-year-olds' (N = 130) predictions and recognition of motion down inclines. Predictions were typically in error, matching previous work, but children largely recognized correct events as correct and rejected incorrect ones. The results also demonstrate while predictions change with increasing age, recognition shows signs of stability. The findings provide further support for a hybrid model of object representations and argue in favour of stable core cognition existing alongside developmental changes. Statement of contribution What is already known on this subject? Children's predictions of physical events show limitations in accuracy Their recognition of such events suggests children may use different knowledge sources in their reasoning What the present study adds? Predictions fluctuate more strongly than recognition, suggesting stable core cognition But recognition also shows some fluctuation, arguing for a hybrid model of knowledge representation. © 2017 The British Psychological Society.

  19. Poka Yoke system based on image analysis and object recognition

    Science.gov (United States)

    Belu, N.; Ionescu, L. M.; Misztal, A.; Mazăre, A.

    2015-11-01

    Poka Yoke is a method of quality management which is related to prevent faults from arising during production processes. It deals with “fail-sating” or “mistake-proofing”. The Poka-yoke concept was generated and developed by Shigeo Shingo for the Toyota Production System. Poka Yoke is used in many fields, especially in monitoring production processes. In many cases, identifying faults in a production process involves a higher cost than necessary cost of disposal. Usually, poke yoke solutions are based on multiple sensors that identify some nonconformities. This means the presence of different equipment (mechanical, electronic) on production line. As a consequence, coupled with the fact that the method itself is an invasive, affecting the production process, would increase its price diagnostics. The bulky machines are the means by which a Poka Yoke system can be implemented become more sophisticated. In this paper we propose a solution for the Poka Yoke system based on image analysis and identification of faults. The solution consists of a module for image acquisition, mid-level processing and an object recognition module using associative memory (Hopfield network type). All are integrated into an embedded system with AD (Analog to Digital) converter and Zync 7000 (22 nm technology).

  20. One-Dimensional Vertex Models Associated with a Class of Yangian Invariant Haldane-Shastry Like Spin Chains

    Directory of Open Access Journals (Sweden)

    Kazuhiro Hikami

    2010-12-01

    Full Text Available We define a class of Y(sl_{(m|n} Yangian invariant Haldane-Shastry (HS like spin chains, by assuming that their partition functions can be written in a particular form in terms of the super Schur polynomials. Using some properties of the super Schur polynomials, we show that the partition functions of this class of spin chains are equivalent to the partition functions of a class of one-dimensional vertex models with appropriately defined energy functions. We also establish a boson-fermion duality relation for the partition functions of this class of supersymmetric HS like spin chains by using their correspondence with one-dimensional vertex models.

  1. Rank one chaos in a class of planar systems with heteroclinic cycle.

    Science.gov (United States)

    Chen, Fengjuan; Han, Maoan

    2009-12-01

    In this paper, we study rank one chaos in a class of planar systems with heteroclinic cycle. We first find a stable limit cycle inside the heteroclinic cycle. We then add an external periodic forcing to create rank one chaos. We follow a step-by-step procedure guided by the theory of rank one chaos to find experimental evidence of strange attractors with Sinai, Ruelle, and Bowen measures.

  2. Automatic object recognition and change detection of urban trees

    NARCIS (Netherlands)

    Van der Sande, C.J.

    2010-01-01

    Monitoring of tree objects is relevant in many current policy issues and relate to the quality of the public space, municipal urban green management, management fees for green areas or Kyoto protocol reporting and all have one thing in common: the need for an up to date tree database. This study,

  3. Supervised Filter Learning for Representation Based Face Recognition.

    Directory of Open Access Journals (Sweden)

    Chao Bi

    Full Text Available Representation based classification methods, such as Sparse Representation Classification (SRC and Linear Regression Classification (LRC have been developed for face recognition problem successfully. However, most of these methods use the original face images without any preprocessing for recognition. Thus, their performances may be affected by some problematic factors (such as illumination and expression variances in the face images. In order to overcome this limitation, a novel supervised filter learning algorithm is proposed for representation based face recognition in this paper. The underlying idea of our algorithm is to learn a filter so that the within-class representation residuals of the faces' Local Binary Pattern (LBP features are minimized and the between-class representation residuals of the faces' LBP features are maximized. Therefore, the LBP features of filtered face images are more discriminative for representation based classifiers. Furthermore, we also extend our algorithm for heterogeneous face recognition problem. Extensive experiments are carried out on five databases and the experimental results verify the efficacy of the proposed algorithm.

  4. Sources of interference in item and associative recognition memory.

    Science.gov (United States)

    Osth, Adam F; Dennis, Simon

    2015-04-01

    A powerful theoretical framework for exploring recognition memory is the global matching framework, in which a cue's memory strength reflects the similarity of the retrieval cues being matched against the contents of memory simultaneously. Contributions at retrieval can be categorized as matches and mismatches to the item and context cues, including the self match (match on item and context), item noise (match on context, mismatch on item), context noise (match on item, mismatch on context), and background noise (mismatch on item and context). We present a model that directly parameterizes the matches and mismatches to the item and context cues, which enables estimation of the magnitude of each interference contribution (item noise, context noise, and background noise). The model was fit within a hierarchical Bayesian framework to 10 recognition memory datasets that use manipulations of strength, list length, list strength, word frequency, study-test delay, and stimulus class in item and associative recognition. Estimates of the model parameters revealed at most a small contribution of item noise that varies by stimulus class, with virtually no item noise for single words and scenes. Despite the unpopularity of background noise in recognition memory models, background noise estimates dominated at retrieval across nearly all stimulus classes with the exception of high frequency words, which exhibited equivalent levels of context noise and background noise. These parameter estimates suggest that the majority of interference in recognition memory stems from experiences acquired before the learning episode. (c) 2015 APA, all rights reserved).

  5. Object-relational database design-exploiting object orientation at the ...

    African Journals Online (AJOL)

    This paper applies the object-relational database paradigm in the design of a Health Management Information System. The class design, mapping of object classes to relational tables, the representation of inheritance hierarchies, and the appropriate database schema are all examined. Keywords: object relational ...

  6. A Large Class of Exact Solutions to the One-Dimensional Schrodinger Equation

    Science.gov (United States)

    Karaoglu, Bekir

    2007-01-01

    A remarkable property of a large class of functions is exploited to generate exact solutions to the one-dimensional Schrodinger equation. The method is simple and easy to implement. (Contains 1 table and 1 figure.)

  7. Palmprint and Face Multi-Modal Biometric Recognition Based on SDA-GSVD and Its Kernelization

    Directory of Open Access Journals (Sweden)

    Jing-Yu Yang

    2012-04-01

    Full Text Available When extracting discriminative features from multimodal data, current methods rarely concern themselves with the data distribution. In this paper, we present an assumption that is consistent with the viewpoint of discrimination, that is, a person’s overall biometric data should be regarded as one class in the input space, and his different biometric data can form different Gaussians distributions, i.e., different subclasses. Hence, we propose a novel multimodal feature extraction and recognition approach based on subclass discriminant analysis (SDA. Specifically, one person’s different bio-data are treated as different subclasses of one class, and a transformed space is calculated, where the difference among subclasses belonging to different persons is maximized, and the difference within each subclass is minimized. Then, the obtained multimodal features are used for classification. Two solutions are presented to overcome the singularity problem encountered in calculation, which are using PCA preprocessing, and employing the generalized singular value decomposition (GSVD technique, respectively. Further, we provide nonlinear extensions of SDA based multimodal feature extraction, that is, the feature fusion based on KPCA-SDA and KSDA-GSVD. In KPCA-SDA, we first apply Kernel PCA on each single modal before performing SDA. While in KSDA-GSVD, we directly perform Kernel SDA to fuse multimodal data by applying GSVD to avoid the singular problem. For simplicity two typical types of biometric data are considered in this paper, i.e., palmprint data and face data. Compared with several representative multimodal biometrics recognition methods, experimental results show that our approaches outperform related multimodal recognition methods and KSDA-GSVD achieves the best recognition performance.

  8. One-against-all weighted dynamic time warping for language-independent and speaker-dependent speech recognition in adverse conditions.

    Directory of Open Access Journals (Sweden)

    Xianglilan Zhang

    Full Text Available Considering personal privacy and difficulty of obtaining training material for many seldom used English words and (often non-English names, language-independent (LI with lightweight speaker-dependent (SD automatic speech recognition (ASR is a promising option to solve the problem. The dynamic time warping (DTW algorithm is the state-of-the-art algorithm for small foot-print SD ASR applications with limited storage space and small vocabulary, such as voice dialing on mobile devices, menu-driven recognition, and voice control on vehicles and robotics. Even though we have successfully developed two fast and accurate DTW variations for clean speech data, speech recognition for adverse conditions is still a big challenge. In order to improve recognition accuracy in noisy environment and bad recording conditions such as too high or low volume, we introduce a novel one-against-all weighted DTW (OAWDTW. This method defines a one-against-all index (OAI for each time frame of training data and applies the OAIs to the core DTW process. Given two speech signals, OAWDTW tunes their final alignment score by using OAI in the DTW process. Our method achieves better accuracies than DTW and merge-weighted DTW (MWDTW, as 6.97% relative reduction of error rate (RRER compared with DTW and 15.91% RRER compared with MWDTW are observed in our extensive experiments on one representative SD dataset of four speakers' recordings. To the best of our knowledge, OAWDTW approach is the first weighted DTW specially designed for speech data in adverse conditions.

  9. The Pattern Recognition in Cattle Brand using Bag of Visual Words and Support Vector Machines Multi-Class

    Directory of Open Access Journals (Sweden)

    Carlos Silva, Mr

    2018-03-01

    Full Text Available The recognition images of cattle brand in an automatic way is a necessity to governmental organs responsible for this activity. To help this process, this work presents a method that consists in using Bag of Visual Words for extracting of characteristics from images of cattle brand and Support Vector Machines Multi-Class for classification. This method consists of six stages: a select database of images; b extract points of interest (SURF; c create vocabulary (K-means; d create vector of image characteristics (visual words; e train and sort images (SVM; f evaluate the classification results. The accuracy of the method was tested on database of municipal city hall, where it achieved satisfactory results, reporting 86.02% of accuracy and 56.705 seconds of processing time, respectively.

  10. Learning Objects and Grasp Affordances through Autonomous Exploration

    DEFF Research Database (Denmark)

    Kraft, Dirk; Detry, Renaud; Pugeault, Nicolas

    2009-01-01

    We describe a system for autonomous learning of visual object representations and their grasp affordances on a robot-vision system. It segments objects by grasping and moving 3D scene features, and creates probabilistic visual representations for object detection, recognition and pose estimation...... image sequences as well as (3) a number of built-in behavioral modules on the one hand, and autonomous exploration on the other hand, the system is able to generate object and grasping knowledge through interaction with its environment....

  11. Unified Probabilistic Models for Face Recognition from a Single Example Image per Person

    Institute of Scientific and Technical Information of China (English)

    Pin Liao; Li Shen

    2004-01-01

    This paper presents a new technique of unified probabilistic models for face recognition from only one single example image per person. The unified models, trained on an obtained training set with multiple samples per person, are used to recognize facial images from another disjoint database with a single sample per person. Variations between facial images are modeled as two unified probabilistic models: within-class variations and between-class variations. Gaussian Mixture Models are used to approximate the distributions of the two variations and exploit a classifier combination method to improve the performance. Extensive experimental results on the ORL face database and the authors' database (the ICT-JDL database) including totally 1,750facial images of 350 individuals demonstrate that the proposed technique, compared with traditional eigenface method and some well-known traditional algorithms, is a significantly more effective and robust approach for face recognition.

  12. An Unsupervised Approach to Activity Recognition and Segmentation based on Object-Use Fingerprints

    DEFF Research Database (Denmark)

    Gu, Tao; Chen, Shaxun; Tao, Xianping

    2010-01-01

    Human activity recognition is an important task which has many potential applications. In recent years, researchers from pervasive computing are interested in deploying on-body sensors to collect observations and applying machine learning techniques to model and recognize activities. Supervised...... machine learning techniques typically require an appropriate training process in which training data need to be labeled manually. In this paper, we propose an unsupervised approach based on object-use fingerprints to recognize activities without human labeling. We show how to build our activity models...... a trace and detect the boundary of any two adjacent activities. We develop a wearable RFID system and conduct a real-world trace collection done by seven volunteers in a smart home over a period of 2 weeks. We conduct comprehensive experimental evaluations and comparison study. The results show that our...

  13. Three-class classification in computer-aided diagnosis of breast cancer by support vector machine

    Science.gov (United States)

    Sun, Xuejun; Qian, Wei; Song, Dansheng

    2004-05-01

    Design of classifier in computer-aided diagnosis (CAD) scheme of breast cancer plays important role to its overall performance in sensitivity and specificity. Classification of a detected object as malignant lesion, benign lesion, or normal tissue on mammogram is a typical three-class pattern recognition problem. This paper presents a three-class classification approach by using two-stage classifier combined with support vector machine (SVM) learning algorithm for classification of breast cancer on mammograms. The first classification stage is used to detect abnormal areas and normal breast tissues, and the second stage is for classification of malignant or benign in detected abnormal objects. A series of spatial, morphology and texture features have been extracted on detected objects areas. By using genetic algorithm (GA), different feature groups for different stage classification have been investigated. Computerized free-response receiver operating characteristic (FROC) and receiver operating characteristic (ROC) analyses have been employed in different classification stages. Results have shown that obvious performance improvement in both sensitivity and specificity was observed through proposed classification approach compared with conventional two-class classification approaches, indicating its effectiveness in classification of breast cancer on mammograms.

  14. Invariant Face recognition Using Infrared Images

    International Nuclear Information System (INIS)

    Zahran, E.G.

    2012-01-01

    Over the past few decades, face recognition has become a rapidly growing research topic due to the increasing demands in many applications of our daily life such as airport surveillance, personal identification in law enforcement, surveillance systems, information safety, securing financial transactions, and computer security. The objective of this thesis is to develop a face recognition system capable of recognizing persons with a high recognition capability, low processing time, and under different illumination conditions, and different facial expressions. The thesis presents a study for the performance of the face recognition system using two techniques; the Principal Component Analysis (PCA), and the Zernike Moments (ZM). The performance of the recognition system is evaluated according to several aspects including the recognition rate, and the processing time. Face recognition systems that use visual images are sensitive to variations in the lighting conditions and facial expressions. The performance of these systems may be degraded under poor illumination conditions or for subjects of various skin colors. Several solutions have been proposed to overcome these limitations. One of these solutions is to work in the Infrared (IR) spectrum. IR images have been suggested as an alternative source of information for detection and recognition of faces, when there is little or no control over lighting conditions. This arises from the fact that these images are formed due to thermal emissions from skin, which is an intrinsic property because these emissions depend on the distribution of blood vessels under the skin. On the other hand IR face recognition systems still have limitations with temperature variations and recognition of persons wearing eye glasses. In this thesis we will fuse IR images with visible images to enhance the performance of face recognition systems. Images are fused using the wavelet transform. Simulation results show that the fusion of visible and

  15. Optical Character Recognition Using Active Contour Segmentation

    Directory of Open Access Journals (Sweden)

    Nabeel Oudah

    2018-01-01

    Full Text Available Document analysis of images snapped by camera is a growing challenge. These photos are often poor-quality compound images, composed of various objects and text; this makes automatic analysis complicated. OCR is one of the image processing techniques which is used to perform automatic identification of texts. Existing image processing techniques need to manage many parameters in order to clearly recognize the text in such pictures. Segmentation is regarded one of these essential parameters. This paper discusses the accuracy of segmentation process and its effect over the recognition process. According to the proposed method, the images were firstly filtered using the wiener filter then the active contour algorithm could be applied in the segmentation process. The Tesseract OCR Engine was selected in order to evaluate the performance and identification accuracy of the proposed method. The results showed that a more accurate segmentation process shall lead to a more accurate recognition results. The rate of recognition accuracy was 0.95 for the proposed algorithm compared with 0.85 for the Tesseract OCR Engine.

  16. Short exposure to a diet rich in both fat and sugar or sugar alone impairs place, but not object recognition memory in rats.

    Science.gov (United States)

    Beilharz, Jessica E; Maniam, Jayanthi; Morris, Margaret J

    2014-03-01

    High energy diets have been shown to impair cognition however, the rapidity of these effects, and the dietary component/s responsible are currently unclear. We conducted two experiments in rats to examine the effects of short-term exposure to a diet rich in sugar and fat or rich in sugar on object (perirhinal-dependent) and place (hippocampal-dependent) recognition memory, and the role of inflammatory mediators in these responses. In Experiment 1, rats fed a cafeteria style diet containing chow supplemented with lard, cakes, biscuits, and a 10% sucrose solution performed worse on the place, but not the object recognition task, than chow fed control rats when tested after 5, 11, and 20 days. In Experiment 2, rats fed the cafeteria style diet either with or without sucrose and rats fed chow supplemented with sucrose also performed worse on the place, but not the object recognition task when tested after 5, 11, and 20 days. Rats fed the cafeteria diets consumed five times more energy than control rats and exhibited increased plasma leptin, insulin and triglyceride concentrations; these were not affected in the sucrose only rats. Rats exposed to sucrose exhibited both increased hippocampal inflammation (TNF-α and IL-1β mRNA) and oxidative stress, as indicated by an upregulation of NRF1 mRNA compared to control rats. In contrast, these markers were not significantly elevated in rats that received the cafeteria diet without added sucrose. Hippocampal BDNF and neuritin mRNA were similar across all groups. These results show that relatively short exposures to diets rich in both fat and sugar or rich in sugar, impair hippocampal-dependent place recognition memory prior to the emergence of weight differences, and suggest a role for oxidative stress and neuroinflammation in this impairment. Crown Copyright © 2013. Published by Elsevier Inc. All rights reserved.

  17. Robust selectivity to two-object images in human visual cortex

    Science.gov (United States)

    Agam, Yigal; Liu, Hesheng; Papanastassiou, Alexander; Buia, Calin; Golby, Alexandra J.; Madsen, Joseph R.; Kreiman, Gabriel

    2010-01-01

    SUMMARY We can recognize objects in a fraction of a second in spite of the presence of other objects [1–3]. The responses in macaque areas V4 and inferior temporal cortex [4–15] to a neuron’s preferred stimuli are typically suppressed by the addition of a second object within the receptive field (see however [16, 17]). How can this suppression be reconciled with rapid visual recognition in complex scenes? One option is that certain “special categories” are unaffected by other objects [18] but this leaves the problem unsolved for other categories. Another possibility is that serial attentional shifts help ameliorate the problem of distractor objects [19–21]. Yet, psychophysical studies [1–3], scalp recordings [1] and neurophysiological recordings [14, 16, 22–24], suggest that the initial sweep of visual processing contains a significant amount of information. We recorded intracranial field potentials in human visual cortex during presentation of flashes of two-object images. Visual selectivity from temporal cortex during the initial ~200 ms was largely robust to the presence of other objects. We could train linear decoders on the responses to isolated objects and decode information in two-object images. These observations are compatible with parallel, hierarchical and feed-forward theories of rapid visual recognition [25] and may provide a neural substrate to begin to unravel rapid recognition in natural scenes. PMID:20417105

  18. Method for secure electronic voting system: face recognition based approach

    Science.gov (United States)

    Alim, M. Affan; Baig, Misbah M.; Mehboob, Shahzain; Naseem, Imran

    2017-06-01

    In this paper, we propose a framework for low cost secure electronic voting system based on face recognition. Essentially Local Binary Pattern (LBP) is used for face feature characterization in texture format followed by chi-square distribution is used for image classification. Two parallel systems are developed based on smart phone and web applications for face learning and verification modules. The proposed system has two tire security levels by using person ID followed by face verification. Essentially class specific threshold is associated for controlling the security level of face verification. Our system is evaluated three standard databases and one real home based database and achieve the satisfactory recognition accuracies. Consequently our propose system provides secure, hassle free voting system and less intrusive compare with other biometrics.

  19. From brain synapses to systems for learning and memory: Object recognition, spatial navigation, timed conditioning, and movement control.

    Science.gov (United States)

    Grossberg, Stephen

    2015-09-24

    This article provides an overview of neural models of synaptic learning and memory whose expression in adaptive behavior depends critically on the circuits and systems in which the synapses are embedded. It reviews Adaptive Resonance Theory, or ART, models that use excitatory matching and match-based learning to achieve fast category learning and whose learned memories are dynamically stabilized by top-down expectations, attentional focusing, and memory search. ART clarifies mechanistic relationships between consciousness, learning, expectation, attention, resonance, and synchrony. ART models are embedded in ARTSCAN architectures that unify processes of invariant object category learning, recognition, spatial and object attention, predictive remapping, and eye movement search, and that clarify how conscious object vision and recognition may fail during perceptual crowding and parietal neglect. The generality of learned categories depends upon a vigilance process that is regulated by acetylcholine via the nucleus basalis. Vigilance can get stuck at too high or too low values, thereby causing learning problems in autism and medial temporal amnesia. Similar synaptic learning laws support qualitatively different behaviors: Invariant object category learning in the inferotemporal cortex; learning of grid cells and place cells in the entorhinal and hippocampal cortices during spatial navigation; and learning of time cells in the entorhinal-hippocampal system during adaptively timed conditioning, including trace conditioning. Spatial and temporal processes through the medial and lateral entorhinal-hippocampal system seem to be carried out with homologous circuit designs. Variations of a shared laminar neocortical circuit design have modeled 3D vision, speech perception, and cognitive working memory and learning. A complementary kind of inhibitory matching and mismatch learning controls movement. This article is part of a Special Issue entitled SI: Brain and Memory

  20. Crystal structure of the PAC1R extracellular domain unifies a consensus fold for hormone recognition by class B G-protein coupled receptors.

    Directory of Open Access Journals (Sweden)

    Shiva Kumar

    Full Text Available Pituitary adenylate cyclase activating polypeptide (PACAP is a member of the PACAP/glucagon family of peptide hormones, which controls many physiological functions in the immune, nervous, endocrine, and muscular systems. It activates adenylate cyclase by binding to its receptor, PAC1R, a member of class B G-protein coupled receptors (GPCR. Crystal structures of a number of Class B GPCR extracellular domains (ECD bound to their respective peptide hormones have revealed a consensus mechanism of hormone binding. However, the mechanism of how PACAP binds to its receptor remains controversial as an NMR structure of the PAC1R ECD/PACAP complex reveals a different topology of the ECD and a distinct mode of ligand recognition. Here we report a 1.9 Å crystal structure of the PAC1R ECD, which adopts the same fold as commonly observed for other members of Class B GPCR. Binding studies and cell-based assays with alanine-scanned peptides and mutated receptor support a model that PAC1R uses the same conserved fold of Class B GPCR ECD for PACAP binding, thus unifying the consensus mechanism of hormone binding for this family of receptors.

  1. Are Haar-like Rectangular Features for Biometric Recognition Reducible?

    DEFF Research Database (Denmark)

    Nasrollahi, Kamal; Moeslund, Thomas B.

    2013-01-01

    Biometric recognition is still a very difficult task in real-world scenarios wherein unforeseen changes in degradations factors like noise, occlusion, blurriness and illumination can drastically affect the extracted features from the biometric signals. Very recently Haar-like rectangular features...... which have usually been used for object detection were introduced for biometric recognition resulting in systems that are robust against most of the mentioned degradations [9]. The problem with these features is that one can define many different such features for a given biometric signal...... and it is not clear whether all of these features are required for the actual recognition or not. This is exactly what we are dealing with in this paper: How can an initial set of Haar-like rectangular features, that have been used for biometric recognition, be reduced to a set of most influential features...

  2. Contemporary deep recurrent learning for recognition

    Science.gov (United States)

    Iftekharuddin, K. M.; Alam, M.; Vidyaratne, L.

    2017-05-01

    Large-scale feed-forward neural networks have seen intense application in many computer vision problems. However, these networks can get hefty and computationally intensive with increasing complexity of the task. Our work, for the first time in literature, introduces a Cellular Simultaneous Recurrent Network (CSRN) based hierarchical neural network for object detection. CSRN has shown to be more effective to solving complex tasks such as maze traversal and image processing when compared to generic feed forward networks. While deep neural networks (DNN) have exhibited excellent performance in object detection and recognition, such hierarchical structure has largely been absent in neural networks with recurrency. Further, our work introduces deep hierarchy in SRN for object recognition. The simultaneous recurrency results in an unfolding effect of the SRN through time, potentially enabling the design of an arbitrarily deep network. This paper shows experiments using face, facial expression and character recognition tasks using novel deep recurrent model and compares recognition performance with that of generic deep feed forward model. Finally, we demonstrate the flexibility of incorporating our proposed deep SRN based recognition framework in a humanoid robotic platform called NAO.

  3. Action recognition using mined hierarchical compound features.

    Science.gov (United States)

    Gilbert, Andrew; Illingworth, John; Bowden, Richard

    2011-05-01

    The field of Action Recognition has seen a large increase in activity in recent years. Much of the progress has been through incorporating ideas from single-frame object recognition and adapting them for temporal-based action recognition. Inspired by the success of interest points in the 2D spatial domain, their 3D (space-time) counterparts typically form the basic components used to describe actions, and in action recognition the features used are often engineered to fire sparsely. This is to ensure that the problem is tractable; however, this can sacrifice recognition accuracy as it cannot be assumed that the optimum features in terms of class discrimination are obtained from this approach. In contrast, we propose to initially use an overcomplete set of simple 2D corners in both space and time. These are grouped spatially and temporally using a hierarchical process, with an increasing search area. At each stage of the hierarchy, the most distinctive and descriptive features are learned efficiently through data mining. This allows large amounts of data to be searched for frequently reoccurring patterns of features. At each level of the hierarchy, the mined compound features become more complex, discriminative, and sparse. This results in fast, accurate recognition with real-time performance on high-resolution video. As the compound features are constructed and selected based upon their ability to discriminate, their speed and accuracy increase a