The utilization of human color categorization for content-based image retrieval

NARCIS (Netherlands)

van den Broek, Egon; Rogowitz, Bernice E.; Kisters, Peter M.F.; Pappas, Thrasyvoulos N.; Vuurpijl, Louis G.

2004-01-01

We present the concept of intelligent Content-Based Image Retrieval (iCBIR), which incorporates knowledge concerning human cognition in system development. The present research focuses on the utilization of color categories (or focal colors) for CBIR purposes, in particularly considered to be useful

Content-Based Image Retrieval Benchmarking: Utilizing color categories and color distributions

NARCIS (Netherlands)

van den Broek, Egon; Kisters, Peter M.F.; Vuurpijl, Louis G.

From a human centered perspective three ingredients for Content-Based Image Retrieval (CBIR) were developed. First, with their existence confirmed by experimental data, 11 color categories were utilized for CBIR and used as input for a new color space segmentation technique. The complete HSI color

Content-Based Image Retrial Based on Hadoop

Directory of Open Access Journals (Sweden)

DongSheng Yin

2013-01-01

Full Text Available Generally, time complexity of algorithms for content-based image retrial is extremely high. In order to retrieve images on large-scale databases efficiently, a new way for retrieving based on Hadoop distributed framework is proposed. Firstly, a database of images features is built by using Speeded Up Robust Features algorithm and Locality-Sensitive Hashing and then perform the search on Hadoop platform in a parallel way specially designed. Considerable experimental results show that it is able to retrieve images based on content on large-scale cluster and image sets effectively.

Plant leaf chlorophyll content retrieval based on a field imaging spectroscopy system.

Science.gov (United States)

Liu, Bo; Yue, Yue-Min; Li, Ru; Shen, Wen-Jing; Wang, Ke-Lin

2014-10-23

A field imaging spectrometer system (FISS; 380-870 nm and 344 bands) was designed for agriculture applications. In this study, FISS was used to gather spectral information from soybean leaves. The chlorophyll content was retrieved using a multiple linear regression (MLR), partial least squares (PLS) regression and support vector machine (SVM) regression. Our objective was to verify the performance of FISS in a quantitative spectral analysis through the estimation of chlorophyll content and to determine a proper quantitative spectral analysis method for processing FISS data. The results revealed that the derivative reflectance was a more sensitive indicator of chlorophyll content and could extract content information more efficiently than the spectral reflectance, which is more significant for FISS data compared to ASD (analytical spectral devices) data, reducing the corresponding RMSE (root mean squared error) by 3.3%-35.6%. Compared with the spectral features, the regression methods had smaller effects on the retrieval accuracy. A multivariate linear model could be the ideal model to retrieve chlorophyll information with a small number of significant wavelengths used. The smallest RMSE of the chlorophyll content retrieved using FISS data was 0.201 mg/g, a relative reduction of more than 30% compared with the RMSE based on a non-imaging ASD spectrometer, which represents a high estimation accuracy compared with the mean chlorophyll content of the sampled leaves (4.05 mg/g). Our study indicates that FISS could obtain both spectral and spatial detailed information of high quality. Its image-spectrum-in-one merit promotes the good performance of FISS in quantitative spectral analyses, and it can potentially be widely used in the agricultural sector.

An efficient similarity measure for content based image retrieval using memetic algorithm

Directory of Open Access Journals (Sweden)

Mutasem K. Alsmadi

2017-06-01

Full Text Available Content based image retrieval (CBIR systems work by retrieving images which are related to the query image (QI from huge databases. The available CBIR systems extract limited feature sets which confine the retrieval efficacy. In this work, extensive robust and important features were extracted from the images database and then stored in the feature repository. This feature set is composed of color signature with the shape and color texture features. Where, features are extracted from the given QI in the similar fashion. Consequently, a novel similarity evaluation using a meta-heuristic algorithm called a memetic algorithm (genetic algorithm with great deluge is achieved between the features of the QI and the features of the database images. Our proposed CBIR system is assessed by inquiring number of images (from the test dataset and the efficiency of the system is evaluated by calculating precision-recall value for the results. The results were superior to other state-of-the-art CBIR systems in regard to precision.

Content-based multimedia retrieval: indexing and diversification

NARCIS (Netherlands)

van Leuken, R.H.

2009-01-01

The demand for efficient systems that facilitate searching in multimedia databases and collections is vastly increasing. Application domains include criminology, musicology, trademark registration, medicine and image or video retrieval on the web. This thesis discusses content-based retrieval

Wavelet optimization for content-based image retrieval in medical databases.

Science.gov (United States)

Quellec, G; Lamard, M; Cazuguel, G; Cochener, B; Roux, C

2010-04-01

We propose in this article a content-based image retrieval (CBIR) method for diagnosis aid in medical fields. In the proposed system, images are indexed in a generic fashion, without extracting domain-specific features: a signature is built for each image from its wavelet transform. These image signatures characterize the distribution of wavelet coefficients in each subband of the decomposition. A distance measure is then defined to compare two image signatures and thus retrieve the most similar images in a database when a query image is submitted by a physician. To retrieve relevant images from a medical database, the signatures and the distance measure must be related to the medical interpretation of images. As a consequence, we introduce several degrees of freedom in the system so that it can be tuned to any pathology and image modality. In particular, we propose to adapt the wavelet basis, within the lifting scheme framework, and to use a custom decomposition scheme. Weights are also introduced between subbands. All these parameters are tuned by an optimization procedure, using the medical grading of each image in the database to define a performance measure. The system is assessed on two medical image databases: one for diabetic retinopathy follow up and one for screening mammography, as well as a general purpose database. Results are promising: a mean precision of 56.50%, 70.91% and 96.10% is achieved for these three databases, when five images are returned by the system. Copyright 2009 Elsevier B.V. All rights reserved.

A review of content-based image retrieval systems in medical applications-clinical benefits and future directions.

Science.gov (United States)

Müller, Henning; Michoux, Nicolas; Bandon, David; Geissbuhler, Antoine

2004-02-01

Content-based visual information retrieval (CBVIR) or content-based image retrieval (CBIR) has been one on the most vivid research areas in the field of computer vision over the last 10 years. The availability of large and steadily growing amounts of visual and multimedia data, and the development of the Internet underline the need to create thematic access methods that offer more than simple text-based queries or requests based on matching exact database fields. Many programs and tools have been developed to formulate and execute queries based on the visual or audio content and to help browsing large multimedia repositories. Still, no general breakthrough has been achieved with respect to large varied databases with documents of differing sorts and with varying characteristics. Answers to many questions with respect to speed, semantic descriptors or objective image interpretations are still unanswered. In the medical field, images, and especially digital images, are produced in ever-increasing quantities and used for diagnostics and therapy. The Radiology Department of the University Hospital of Geneva alone produced more than 12,000 images a day in 2002. The cardiology is currently the second largest producer of digital images, especially with videos of cardiac catheterization ( approximately 1800 exams per year containing almost 2000 images each). The total amount of cardiologic image data produced in the Geneva University Hospital was around 1 TB in 2002. Endoscopic videos can equally produce enormous amounts of data. With digital imaging and communications in medicine (DICOM), a standard for image communication has been set and patient information can be stored with the actual image(s), although still a few problems prevail with respect to the standardization. In several articles, content-based access to medical images for supporting clinical decision-making has been proposed that would ease the management of clinical data and scenarios for the integration of

INTEGRATION OF SPATIAL INFORMATION WITH COLOR FOR CONTENT RETRIEVAL OF REMOTE SENSING IMAGES

Directory of Open Access Journals (Sweden)

Bikesh Kumar Singh

2010-08-01

Full Text Available There is rapid increase in image databases of remote sensing images due to image satellites with high resolution, commercial applications of remote sensing & high available bandwidth in last few years. The problem of content-based image retrieval (CBIR of remotely sensed images presents a major challenge not only because of the surprisingly increasing volume of images acquired from a wide range of sensors but also because of the complexity of images themselves. In this paper, a software system for content-based retrieval of remote sensing images using RGB and HSV color spaces is presented. Further, we also compare our results with spatiogram based content retrieval which integrates spatial information along with color histogram. Experimental results show that the integration of spatial information in color improves the image analysis of remote sensing data. In general, retrievals in HSV color space showed better performance than in RGB color space.

Ontology of gaps in content-based image retrieval.

Science.gov (United States)

Deserno, Thomas M; Antani, Sameer; Long, Rodney

2009-04-01

Content-based image retrieval (CBIR) is a promising technology to enrich the core functionality of picture archiving and communication systems (PACS). CBIR has a potential for making a strong impact in diagnostics, research, and education. Research as reported in the scientific literature, however, has not made significant inroads as medical CBIR applications incorporated into routine clinical medicine or medical research. The cause is often attributed (without supporting analysis) to the inability of these applications in overcoming the "semantic gap." The semantic gap divides the high-level scene understanding and interpretation available with human cognitive capabilities from the low-level pixel analysis of computers, based on mathematical processing and artificial intelligence methods. In this paper, we suggest a more systematic and comprehensive view of the concept of "gaps" in medical CBIR research. In particular, we define an ontology of 14 gaps that addresses the image content and features, as well as system performance and usability. In addition to these gaps, we identify seven system characteristics that impact CBIR applicability and performance. The framework we have created can be used a posteriori to compare medical CBIR systems and approaches for specific biomedical image domains and goals and a priori during the design phase of a medical CBIR application, as the systematic analysis of gaps provides detailed insight in system comparison and helps to direct future research.

Relevance Feedback in Content Based Image Retrieval: A Review

Directory of Open Access Journals (Sweden)

Manesh B. Kokare

2011-01-01

Full Text Available This paper provides an overview of the technical achievements in the research area of relevance feedback (RF in content-based image retrieval (CBIR. Relevance feedback is a powerful technique in CBIR systems, in order to improve the performance of CBIR effectively. It is an open research area to the researcher to reduce the semantic gap between low-level features and high level concepts. The paper covers the current state of art of the research in relevance feedback in CBIR, various relevance feedback techniques and issues in relevance feedback are discussed in detail.

Improved image retrieval based on fuzzy colour feature vector

Science.gov (United States)

Ben-Ahmeida, Ahlam M.; Ben Sasi, Ahmed Y.

2013-03-01

One of Image indexing techniques is the Content-Based Image Retrieval which is an efficient way for retrieving images from the image database automatically based on their visual contents such as colour, texture, and shape. In this paper will be discuss how using content-based image retrieval (CBIR) method by colour feature extraction and similarity checking. By dividing the query image and all images in the database into pieces and extract the features of each part separately and comparing the corresponding portions in order to increase the accuracy in the retrieval. The proposed approach is based on the use of fuzzy sets, to overcome the problem of curse of dimensionality. The contribution of colour of each pixel is associated to all the bins in the histogram using fuzzy-set membership functions. As a result, the Fuzzy Colour Histogram (FCH), outperformed the Conventional Colour Histogram (CCH) in image retrieving, due to its speedy results, where were images represented as signatures that took less size of memory, depending on the number of divisions. The results also showed that FCH is less sensitive and more robust to brightness changes than the CCH with better retrieval recall values.

Biased discriminant euclidean embedding for content-based image retrieval.

Science.gov (United States)

Bian, Wei; Tao, Dacheng

2010-02-01

With many potential multimedia applications, content-based image retrieval (CBIR) has recently gained more attention for image management and web search. A wide variety of relevance feedback (RF) algorithms have been developed in recent years to improve the performance of CBIR systems. These RF algorithms capture user's preferences and bridge the semantic gap. However, there is still a big room to further the RF performance, because the popular RF algorithms ignore the manifold structure of image low-level visual features. In this paper, we propose the biased discriminative Euclidean embedding (BDEE) which parameterises samples in the original high-dimensional ambient space to discover the intrinsic coordinate of image low-level visual features. BDEE precisely models both the intraclass geometry and interclass discrimination and never meets the undersampled problem. To consider unlabelled samples, a manifold regularization-based item is introduced and combined with BDEE to form the semi-supervised BDEE, or semi-BDEE for short. To justify the effectiveness of the proposed BDEE and semi-BDEE, we compare them against the conventional RF algorithms and show a significant improvement in terms of accuracy and stability based on a subset of the Corel image gallery.

Retrieval Architecture with Classified Query for Content Based Image Recognition

Directory of Open Access Journals (Sweden)

Rik Das

2016-01-01

Full Text Available The consumer behavior has been observed to be largely influenced by image data with increasing familiarity of smart phones and World Wide Web. Traditional technique of browsing through product varieties in the Internet with text keywords has been gradually replaced by the easy accessible image data. The importance of image data has portrayed a steady growth in application orientation for business domain with the advent of different image capturing devices and social media. The paper has described a methodology of feature extraction by image binarization technique for enhancing identification and retrieval of information using content based image recognition. The proposed algorithm was tested on two public datasets, namely, Wang dataset and Oliva and Torralba (OT-Scene dataset with 3688 images on the whole. It has outclassed the state-of-the-art techniques in performance measure and has shown statistical significance.

Design and development of a content-based medical image retrieval system for spine vertebrae irregularity.

Science.gov (United States)

Mustapha, Aouache; Hussain, Aini; Samad, Salina Abdul; Zulkifley, Mohd Asyraf; Diyana Wan Zaki, Wan Mimi; Hamid, Hamzaini Abdul

2015-01-16

Content-based medical image retrieval (CBMIR) system enables medical practitioners to perform fast diagnosis through quantitative assessment of the visual information of various modalities. In this paper, a more robust CBMIR system that deals with both cervical and lumbar vertebrae irregularity is afforded. It comprises three main phases, namely modelling, indexing and retrieval of the vertebrae image. The main tasks in the modelling phase are to improve and enhance the visibility of the x-ray image for better segmentation results using active shape model (ASM). The segmented vertebral fractures are then characterized in the indexing phase using region-based fracture characterization (RB-FC) and contour-based fracture characterization (CB-FC). Upon a query, the characterized features are compared to the query image. Effectiveness of the retrieval phase is determined by its retrieval, thus, we propose an integration of the predictor model based cross validation neural network (PMCVNN) and similarity matching (SM) in this stage. The PMCVNN task is to identify the correct vertebral irregularity class through classification allowing the SM process to be more efficient. Retrieval performance between the proposed and the standard retrieval architectures are then compared using retrieval precision (Pr@M) and average group score (AGS) measures. Experimental results show that the new integrated retrieval architecture performs better than those of the standard CBMIR architecture with retrieval results of cervical (AGS > 87%) and lumbar (AGS > 82%) datasets. The proposed CBMIR architecture shows encouraging results with high Pr@M accuracy. As a result, images from the same visualization class are returned for further used by the medical personnel.

Combining semantic technologies with a content-based image retrieval system - Preliminary considerations

Science.gov (United States)

Chmiel, P.; Ganzha, M.; Jaworska, T.; Paprzycki, M.

2017-10-01

Nowadays, as a part of systematic growth of volume, and variety, of information that can be found on the Internet, we observe also dramatic increase in sizes of available image collections. There are many ways to help users browsing / selecting images of interest. One of popular approaches are Content-Based Image Retrieval (CBIR) systems, which allow users to search for images that match their interests, expressed in the form of images (query by example). However, we believe that image search and retrieval could take advantage of semantic technologies. We have decided to test this hypothesis. Specifically, on the basis of knowledge captured in the CBIR, we have developed a domain ontology of residential real estate (detached houses, in particular). This allows us to semantically represent each image (and its constitutive architectural elements) represented within the CBIR. The proposed ontology was extended to capture not only the elements resulting from image segmentation, but also "spatial relations" between them. As a result, a new approach to querying the image database (semantic querying) has materialized, thus extending capabilities of the developed system.

Content-based image retrieval using spatial layout information in brain tumor T1-weighted contrast-enhanced MR images.

Science.gov (United States)

Huang, Meiyan; Yang, Wei; Wu, Yao; Jiang, Jun; Gao, Yang; Chen, Yang; Feng, Qianjin; Chen, Wufan; Lu, Zhentai

2014-01-01

This study aims to develop content-based image retrieval (CBIR) system for the retrieval of T1-weighted contrast-enhanced MR (CE-MR) images of brain tumors. When a tumor region is fed to the CBIR system as a query, the system attempts to retrieve tumors of the same pathological category. The bag-of-visual-words (BoVW) model with partition learning is incorporated into the system to extract informative features for representing the image contents. Furthermore, a distance metric learning algorithm called the Rank Error-based Metric Learning (REML) is proposed to reduce the semantic gap between low-level visual features and high-level semantic concepts. The effectiveness of the proposed method is evaluated on a brain T1-weighted CE-MR dataset with three types of brain tumors (i.e., meningioma, glioma, and pituitary tumor). Using the BoVW model with partition learning, the mean average precision (mAP) of retrieval increases beyond 4.6% with the learned distance metrics compared with the spatial pyramid BoVW method. The distance metric learned by REML significantly outperforms three other existing distance metric learning methods in terms of mAP. The mAP of the CBIR system is as high as 91.8% using the proposed method, and the precision can reach 93.1% when the top 10 images are returned by the system. These preliminary results demonstrate that the proposed method is effective and feasible for the retrieval of brain tumors in T1-weighted CE-MR Images.

Content-based image retrieval using spatial layout information in brain tumor T1-weighted contrast-enhanced MR images.

Directory of Open Access Journals (Sweden)

Meiyan Huang

Full Text Available This study aims to develop content-based image retrieval (CBIR system for the retrieval of T1-weighted contrast-enhanced MR (CE-MR images of brain tumors. When a tumor region is fed to the CBIR system as a query, the system attempts to retrieve tumors of the same pathological category. The bag-of-visual-words (BoVW model with partition learning is incorporated into the system to extract informative features for representing the image contents. Furthermore, a distance metric learning algorithm called the Rank Error-based Metric Learning (REML is proposed to reduce the semantic gap between low-level visual features and high-level semantic concepts. The effectiveness of the proposed method is evaluated on a brain T1-weighted CE-MR dataset with three types of brain tumors (i.e., meningioma, glioma, and pituitary tumor. Using the BoVW model with partition learning, the mean average precision (mAP of retrieval increases beyond 4.6% with the learned distance metrics compared with the spatial pyramid BoVW method. The distance metric learned by REML significantly outperforms three other existing distance metric learning methods in terms of mAP. The mAP of the CBIR system is as high as 91.8% using the proposed method, and the precision can reach 93.1% when the top 10 images are returned by the system. These preliminary results demonstrate that the proposed method is effective and feasible for the retrieval of brain tumors in T1-weighted CE-MR Images.

Mobile object retrieval in server-based image databases

Science.gov (United States)

Manger, D.; Pagel, F.; Widak, H.

2013-05-01

The increasing number of mobile phones equipped with powerful cameras leads to huge collections of user-generated images. To utilize the information of the images on site, image retrieval systems are becoming more and more popular to search for similar objects in an own image database. As the computational performance and the memory capacity of mobile devices are constantly increasing, this search can often be performed on the device itself. This is feasible, for example, if the images are represented with global image features or if the search is done using EXIF or textual metadata. However, for larger image databases, if multiple users are meant to contribute to a growing image database or if powerful content-based image retrieval methods with local features are required, a server-based image retrieval backend is needed. In this work, we present a content-based image retrieval system with a client server architecture working with local features. On the server side, the scalability to large image databases is addressed with the popular bag-of-word model with state-of-the-art extensions. The client end of the system focuses on a lightweight user interface presenting the most similar images of the database highlighting the visual information which is common with the query image. Additionally, new images can be added to the database making it a powerful and interactive tool for mobile contentbased image retrieval.

TBIdoc: 3D content-based CT image retrieval system for traumatic brain injury

Science.gov (United States)

Li, Shimiao; Gong, Tianxia; Wang, Jie; Liu, Ruizhe; Tan, Chew Lim; Leong, Tze Yun; Pang, Boon Chuan; Lim, C. C. Tchoyoson; Lee, Cheng Kiang; Tian, Qi; Zhang, Zhuo

2010-03-01

Traumatic brain injury (TBI) is a major cause of death and disability. Computed Tomography (CT) scan is widely used in the diagnosis of TBI. Nowadays, large amount of TBI CT data is stacked in the hospital radiology department. Such data and the associated patient information contain valuable information for clinical diagnosis and outcome prediction. However, current hospital database system does not provide an efficient and intuitive tool for doctors to search out cases relevant to the current study case. In this paper, we present the TBIdoc system: a content-based image retrieval (CBIR) system which works on the TBI CT images. In this web-based system, user can query by uploading CT image slices from one study, retrieval result is a list of TBI cases ranked according to their 3D visual similarity to the query case. Specifically, cases of TBI CT images often present diffuse or focal lesions. In TBIdoc system, these pathological image features are represented as bin-based binary feature vectors. We use the Jaccard-Needham measure as the similarity measurement. Based on these, we propose a 3D similarity measure for computing the similarity score between two series of CT slices. nDCG is used to evaluate the system performance, which shows the system produces satisfactory retrieval results. The system is expected to improve the current hospital data management in TBI and to give better support for the clinical decision-making process. It may also contribute to the computer-aided education in TBI.

Enhancing Image Retrieval System Using Content Based Search ...

African Journals Online (AJOL)

The output shows more efficiency in retrieval because instead of performing the search on the entire image database, the image category option directs the retrieval engine to the specified category. Also, there is provision to update or modify the different image categories in the image database as need arise. Keywords: ...

Interactive classification and content-based retrieval of tissue images

Science.gov (United States)

Aksoy, Selim; Marchisio, Giovanni B.; Tusk, Carsten; Koperski, Krzysztof

2002-11-01

We describe a system for interactive classification and retrieval of microscopic tissue images. Our system models tissues in pixel, region and image levels. Pixel level features are generated using unsupervised clustering of color and texture values. Region level features include shape information and statistics of pixel level feature values. Image level features include statistics and spatial relationships of regions. To reduce the gap between low-level features and high-level expert knowledge, we define the concept of prototype regions. The system learns the prototype regions in an image collection using model-based clustering and density estimation. Different tissue types are modeled using spatial relationships of these regions. Spatial relationships are represented by fuzzy membership functions. The system automatically selects significant relationships from training data and builds models which can also be updated using user relevance feedback. A Bayesian framework is used to classify tissues based on these models. Preliminary experiments show that the spatial relationship models we developed provide a flexible and powerful framework for classification and retrieval of tissue images.

Fundus Image Features Extraction for Exudate Mining in Coordination with Content Based Image Retrieval: A Study

Science.gov (United States)

Gururaj, C.; Jayadevappa, D.; Tunga, Satish

2018-06-01

Medical field has seen a phenomenal improvement over the previous years. The invention of computers with appropriate increase in the processing and internet speed has changed the face of the medical technology. However there is still scope for improvement of the technologies in use today. One of the many such technologies of medical aid is the detection of afflictions of the eye. Although a repertoire of research has been accomplished in this field, most of them fail to address how to take the detection forward to a stage where it will be beneficial to the society at large. An automated system that can predict the current medical condition of a patient after taking the fundus image of his eye is yet to see the light of the day. Such a system is explored in this paper by summarizing a number of techniques for fundus image features extraction, predominantly hard exudate mining, coupled with Content Based Image Retrieval to develop an automation tool. The knowledge of the same would bring about worthy changes in the domain of exudates extraction of the eye. This is essential in cases where the patients may not have access to the best of technologies. This paper attempts at a comprehensive summary of the techniques for Content Based Image Retrieval (CBIR) or fundus features image extraction, and few choice methods of both, and an exploration which aims to find ways to combine these two attractive features, and combine them so that it is beneficial to all.

Fundus Image Features Extraction for Exudate Mining in Coordination with Content Based Image Retrieval: A Study

Science.gov (United States)

Gururaj, C.; Jayadevappa, D.; Tunga, Satish

2018-02-01

Medical field has seen a phenomenal improvement over the previous years. The invention of computers with appropriate increase in the processing and internet speed has changed the face of the medical technology. However there is still scope for improvement of the technologies in use today. One of the many such technologies of medical aid is the detection of afflictions of the eye. Although a repertoire of research has been accomplished in this field, most of them fail to address how to take the detection forward to a stage where it will be beneficial to the society at large. An automated system that can predict the current medical condition of a patient after taking the fundus image of his eye is yet to see the light of the day. Such a system is explored in this paper by summarizing a number of techniques for fundus image features extraction, predominantly hard exudate mining, coupled with Content Based Image Retrieval to develop an automation tool. The knowledge of the same would bring about worthy changes in the domain of exudates extraction of the eye. This is essential in cases where the patients may not have access to the best of technologies. This paper attempts at a comprehensive summary of the techniques for Content Based Image Retrieval (CBIR) or fundus features image extraction, and few choice methods of both, and an exploration which aims to find ways to combine these two attractive features, and combine them so that it is beneficial to all.

Optimizing top precision performance measure of content-based image retrieval by learning similarity function

KAUST Repository

Liang, Ru-Ze

2017-04-24

In this paper we study the problem of content-based image retrieval. In this problem, the most popular performance measure is the top precision measure, and the most important component of a retrieval system is the similarity function used to compare a query image against a database image. However, up to now, there is no existing similarity learning method proposed to optimize the top precision measure. To fill this gap, in this paper, we propose a novel similarity learning method to maximize the top precision measure. We model this problem as a minimization problem with an objective function as the combination of the losses of the relevant images ranked behind the top-ranked irrelevant image, and the squared Frobenius norm of the similarity function parameter. This minimization problem is solved as a quadratic programming problem. The experiments over two benchmark data sets show the advantages of the proposed method over other similarity learning methods when the top precision is used as the performance measure.

Optimizing top precision performance measure of content-based image retrieval by learning similarity function

KAUST Repository

Liang, Ru-Ze; Shi, Lihui; Wang, Haoxiang; Meng, Jiandong; Wang, Jim Jing-Yan; Sun, Qingquan; Gu, Yi

2017-01-01

In this paper we study the problem of content-based image retrieval. In this problem, the most popular performance measure is the top precision measure, and the most important component of a retrieval system is the similarity function used to compare a query image against a database image. However, up to now, there is no existing similarity learning method proposed to optimize the top precision measure. To fill this gap, in this paper, we propose a novel similarity learning method to maximize the top precision measure. We model this problem as a minimization problem with an objective function as the combination of the losses of the relevant images ranked behind the top-ranked irrelevant image, and the squared Frobenius norm of the similarity function parameter. This minimization problem is solved as a quadratic programming problem. The experiments over two benchmark data sets show the advantages of the proposed method over other similarity learning methods when the top precision is used as the performance measure.

Image Retrieval based on Integration between Color and Geometric Moment Features

International Nuclear Information System (INIS)

Saad, M.H.; Saleh, H.I.; Konbor, H.; Ashour, M.

2012-01-01

Content based image retrieval is the retrieval of images based on visual features such as colour, texture and shape. .the Current approaches to CBIR differ in terms of which image features are extracted; recent work deals with combination of distances or scores from different and usually independent representations in an attempt to induce high level semantics from the low level descriptors of the images. content-based image retrieval has many application areas such as, education, commerce, military, searching, commerce, and biomedicine and Web image classification. This paper proposes a new image retrieval system, which uses color and geometric moment feature to form the feature vectors. Bhattacharyya distance and histogram intersection are used to perform feature matching. This framework integrates the color histogram which represents the global feature and geometric moment as local descriptor to enhance the retrieval results. The proposed technique is proper for precisely retrieving images even in deformation cases such as geometric deformations and noise. It is tested on a standard the results shows that a combination of our approach as a local image descriptor with other global descriptors outperforms other approaches.

Content-based image retrieval applied to bone age assessment

Science.gov (United States)

Fischer, Benedikt; Brosig, André; Welter, Petra; Grouls, Christoph; Günther, Rolf W.; Deserno, Thomas M.

2010-03-01

Radiological bone age assessment is based on local image regions of interest (ROI), such as the epiphysis or the area of carpal bones. These are compared to a standardized reference and scores determining the skeletal maturity are calculated. For computer-aided diagnosis, automatic ROI extraction and analysis is done so far mainly by heuristic approaches. Due to high variations in the imaged biological material and differences in age, gender and ethnic origin, automatic analysis is difficult and frequently requires manual interactions. On the contrary, epiphyseal regions (eROIs) can be compared to previous cases with known age by content-based image retrieval (CBIR). This requires a sufficient number of cases with reliable positioning of the eROI centers. In this first approach to bone age assessment by CBIR, we conduct leaving-oneout experiments on 1,102 left hand radiographs and 15,428 metacarpal and phalangeal eROIs from the USC hand atlas. The similarity of the eROIs is assessed by cross-correlation of 16x16 scaled eROIs. The effects of the number of eROIs, two age computation methods as well as the number of considered CBIR references are analyzed. The best results yield an error rate of 1.16 years and a standard deviation of 0.85 years. As the appearance of the hand varies naturally by up to two years, these results clearly demonstrate the applicability of the CBIR approach for bone age estimation.

Experiments with a novel content-based image retrieval software: can we eliminate classification systems in adolescent idiopathic scoliosis?

Science.gov (United States)

Menon, K Venugopal; Kumar, Dinesh; Thomas, Tessamma

2014-02-01

Study Design Preliminary evaluation of new tool. Objective To ascertain whether the newly developed content-based image retrieval (CBIR) software can be used successfully to retrieve images of similar cases of adolescent idiopathic scoliosis (AIS) from a database to help plan treatment without adhering to a classification scheme. Methods Sixty-two operated cases of AIS were entered into the newly developed CBIR database. Five new cases of different curve patterns were used as query images. The images were fed into the CBIR database that retrieved similar images from the existing cases. These were analyzed by a senior surgeon for conformity to the query image. Results Within the limits of variability set for the query system, all the resultant images conformed to the query image. One case had no similar match in the series. The other four retrieved several images that were matching with the query. No matching case was left out in the series. The postoperative images were then analyzed to check for surgical strategies. Broad guidelines for treatment could be derived from the results. More precise query settings, inclusion of bending films, and a larger database will enhance accurate retrieval and better decision making. Conclusion The CBIR system is an effective tool for accurate documentation and retrieval of scoliosis images. Broad guidelines for surgical strategies can be made from the postoperative images of the existing cases without adhering to any classification scheme.

Three-dimensional spatiotemporal features for fast content-based retrieval of focal liver lesions.

Science.gov (United States)

Roy, Sharmili; Chi, Yanling; Liu, Jimin; Venkatesh, Sudhakar K; Brown, Michael S

2014-11-01

Content-based image retrieval systems for 3-D medical datasets still largely rely on 2-D image-based features extracted from a few representative slices of the image stack. Most 2 -D features that are currently used in the literature not only model a 3-D tumor incompletely but are also highly expensive in terms of computation time, especially for high-resolution datasets. Radiologist-specified semantic labels are sometimes used along with image-based 2-D features to improve the retrieval performance. Since radiological labels show large interuser variability, are often unstructured, and require user interaction, their use as lesion characterizing features is highly subjective, tedious, and slow. In this paper, we propose a 3-D image-based spatiotemporal feature extraction framework for fast content-based retrieval of focal liver lesions. All the features are computer generated and are extracted from four-phase abdominal CT images. Retrieval performance and query processing times for the proposed framework is evaluated on a database of 44 hepatic lesions comprising of five pathological types. Bull's eye percentage score above 85% is achieved for three out of the five lesion pathologies and for 98% of query lesions, at least one same type of lesion is ranked among the top two retrieved results. Experiments show that the proposed system's query processing is more than 20 times faster than other already published systems that use 2-D features. With fast computation time and high retrieval accuracy, the proposed system has the potential to be used as an assistant to radiologists for routine hepatic tumor diagnosis.

Cobra: A content-based video retrieval system

NARCIS (Netherlands)

Petkovic, M.; Jonker, W.; Jensen, C.S.; Jeffery, K.G.; Pokorny, J.; Saltenis, S.; Bertino, E.; Böhm, K.; Jarke, M.

2002-01-01

An increasing number of large publicly available video libraries results in a demand for techniques that can manipulate the video data based on content. In this paper, we present a content-based video retrieval system called Cobra. The system supports automatic extraction and retrieval of high-level

Content-based image retrieval using a signature graph and a self-organizing map

Directory of Open Access Journals (Sweden)

Van Thanh The

2016-06-01

Full Text Available In order to effectively retrieve a large database of images, a method of creating an image retrieval system CBIR (contentbased image retrieval is applied based on a binary index which aims to describe features of an image object of interest. This index is called the binary signature and builds input data for the problem of matching similar images. To extract the object of interest, we propose an image segmentation method on the basis of low-level visual features including the color and texture of the image. These features are extracted at each block of the image by the discrete wavelet frame transform and the appropriate color space. On the basis of a segmented image, we create a binary signature to describe the location, color and shape of the objects of interest. In order to match similar images, we provide a similarity measure between the images based on binary signatures. Then, we present a CBIR model which combines a signature graph and a self-organizing map to cluster and store similar images. To illustrate the proposed method, experiments on image databases are reported, including COREL,Wang and MSRDI.

Content-based retrieval in videos from laparoscopic surgery

Science.gov (United States)

Schoeffmann, Klaus; Beecks, Christian; Lux, Mathias; Uysal, Merih Seran; Seidl, Thomas

2016-03-01

In the field of medical endoscopy more and more surgeons are changing over to record and store videos of their endoscopic procedures for long-term archival. These endoscopic videos are a good source of information for explanations to patients and follow-up operations. As the endoscope is the "eye of the surgeon", the video shows the same information the surgeon has seen during the operation, and can describe the situation inside the patient much more precisely than an operation report would do. Recorded endoscopic videos can also be used for training young surgeons and in some countries the long-term archival of video recordings from endoscopic procedures is even enforced by law. A major challenge, however, is to efficiently access these very large video archives for later purposes. One problem, for example, is to locate specific images in the videos that show important situations, which are additionally captured as static images during the procedure. This work addresses this problem and focuses on contentbased video retrieval in data from laparoscopic surgery. We propose to use feature signatures, which can appropriately and concisely describe the content of laparoscopic images, and show that by using this content descriptor with an appropriate metric, we are able to efficiently perform content-based retrieval in laparoscopic videos. In a dataset with 600 captured static images from 33 hours recordings, we are able to find the correct video segment for more than 88% of these images.

Image Retrieval Berdasarkan Fitur Warna, Bentuk, dan Tekstur

Directory of Open Access Journals (Sweden)

Rita Layona

2014-12-01

Full Text Available Along with the times, information retrieval is no longer just on textual data, but also the visual data. The technique was originally used is Text-Based Image Retrieval (TBIR, but the technique still has some shortcomings such as the relevance of the picture successfully retrieved, and the specific space required to store meta-data in the image. Seeing the shortage of Text-Based Image Retrieval techniques, then other techniques were developed, namely Image Retrieval based on content or commonly called Content Based Image Retrieval (CBIR. In this research, CBIR will be discussed based on color, shape and texture using a color histogram, Gabor and SIFT. This study aimed to compare the results of image retrieval with some of these techniques. The results obtained are by combining color, shape and texture features, the performance of the system can be improved.

Region-Based Color Image Indexing and Retrieval

DEFF Research Database (Denmark)

Kompatsiaris, Ioannis; Triantafyllou, Evangelia; Strintzis, Michael G.

2001-01-01

In this paper a region-based color image indexing and retrieval algorithm is presented. As a basis for the indexing, a novel K-Means segmentation algorithm is used, modified so as to take into account the coherence of the regions. A new color distance is also defined for this algorithm. Based on ....... Experimental results demonstrate the performance of the algorithm. The development of an intelligent image content-based search engine for the World Wide Web is also presented, as a direct application of the presented algorithm....

Content-Based High-Resolution Remote Sensing Image Retrieval via Unsupervised Feature Learning and Collaborative Affinity Metric Fusion

Directory of Open Access Journals (Sweden)

Yansheng Li

2016-08-01

Full Text Available With the urgent demand for automatic management of large numbers of high-resolution remote sensing images, content-based high-resolution remote sensing image retrieval (CB-HRRS-IR has attracted much research interest. Accordingly, this paper proposes a novel high-resolution remote sensing image retrieval approach via multiple feature representation and collaborative affinity metric fusion (IRMFRCAMF. In IRMFRCAMF, we design four unsupervised convolutional neural networks with different layers to generate four types of unsupervised features from the fine level to the coarse level. In addition to these four types of unsupervised features, we also implement four traditional feature descriptors, including local binary pattern (LBP, gray level co-occurrence (GLCM, maximal response 8 (MR8, and scale-invariant feature transform (SIFT. In order to fully incorporate the complementary information among multiple features of one image and the mutual information across auxiliary images in the image dataset, this paper advocates collaborative affinity metric fusion to measure the similarity between images. The performance evaluation of high-resolution remote sensing image retrieval is implemented on two public datasets, the UC Merced (UCM dataset and the Wuhan University (WH dataset. Large numbers of experiments show that our proposed IRMFRCAMF can significantly outperform the state-of-the-art approaches.

Content-based retrieval of brain tumor in contrast-enhanced MRI images using tumor margin information and learned distance metric.

Science.gov (United States)

Yang, Wei; Feng, Qianjin; Yu, Mei; Lu, Zhentai; Gao, Yang; Xu, Yikai; Chen, Wufan

2012-11-01

A content-based image retrieval (CBIR) method for T1-weighted contrast-enhanced MRI (CE-MRI) images of brain tumors is presented for diagnosis aid. The method is thoroughly evaluated on a large image dataset. Using the tumor region as a query, the authors' CBIR system attempts to retrieve tumors of the same pathological category. Aside from commonly used features such as intensity, texture, and shape features, the authors use a margin information descriptor (MID), which is capable of describing the characteristics of tissue surrounding a tumor, for representing image contents. In addition, the authors designed a distance metric learning algorithm called Maximum mean average Precision Projection (MPP) to maximize the smooth approximated mean average precision (mAP) to optimize retrieval performance. The effectiveness of MID and MPP algorithms was evaluated using a brain CE-MRI dataset consisting of 3108 2D scans acquired from 235 patients with three categories of brain tumors (meningioma, glioma, and pituitary tumor). By combining MID and other features, the mAP of retrieval increased by more than 6% with the learned distance metrics. The distance metric learned by MPP significantly outperformed the other two existing distance metric learning methods in terms of mAP. The CBIR system using the proposed strategies achieved a mAP of 87.3% and a precision of 89.3% when top 10 images were returned by the system. Compared with scale-invariant feature transform, the MID, which uses the intensity profile as descriptor, achieves better retrieval performance. Incorporating tumor margin information represented by MID with the distance metric learned by the MPP algorithm can substantially improve the retrieval performance for brain tumors in CE-MRI.

Content-based analysis improves audiovisual archive retrieval

NARCIS (Netherlands)

Huurnink, B.; Snoek, C.G.M.; de Rijke, M.; Smeulders, A.W.M.

2012-01-01

Content-based video retrieval is maturing to the point where it can be used in real-world retrieval practices. One such practice is the audiovisual archive, whose users increasingly require fine-grained access to broadcast television content. In this paper, we take into account the information needs

Pareto-depth for multiple-query image retrieval.

Science.gov (United States)

Hsiao, Ko-Jen; Calder, Jeff; Hero, Alfred O

2015-02-01

Most content-based image retrieval systems consider either one single query, or multiple queries that include the same object or represent the same semantic information. In this paper, we consider the content-based image retrieval problem for multiple query images corresponding to different image semantics. We propose a novel multiple-query information retrieval algorithm that combines the Pareto front method with efficient manifold ranking. We show that our proposed algorithm outperforms state of the art multiple-query retrieval algorithms on real-world image databases. We attribute this performance improvement to concavity properties of the Pareto fronts, and prove a theoretical result that characterizes the asymptotic concavity of the fronts.

Transformation invariant image indexing and retrieval for image databases

NARCIS (Netherlands)

Gevers, Th.; Smeulders, A.W.M.

1994-01-01

This paper presents a novel design of an image database system which supports storage, indexing and retrieval of images by content. The image retrieval methodology is based on the observation that images can be discriminated by the presence of image objects and their spatial relations. Images in the

Image Information Retrieval: An Overview of Current Research

OpenAIRE

Abby A. Goodrum

2000-01-01

This paper provides an overview of current research in image information retrieval and provides an outline of areas for future research. The approach is broad and interdisciplinary and focuses on three aspects of image research (IR): text-based retrieval, content-based retrieval, and user interactions with image information retrieval systems. The review concludes with a call for image retrieval evaluation studies similar to TREC.

Automating the construction of scene classifiers for content-based video retrieval

NARCIS (Netherlands)

Khan, L.; Israël, Menno; Petrushin, V.A.; van den Broek, Egon; van der Putten, Peter

2004-01-01

This paper introduces a real time automatic scene classifier within content-based video retrieval. In our envisioned approach end users like documentalists, not image processing experts, build classifiers interactively, by simply indicating positive examples of a scene. Classification consists of a

Optimization of reference library used in content-based medical image retrieval scheme

International Nuclear Information System (INIS)

Park, Sang Cheol; Sukthankar, Rahul; Mummert, Lily; Satyanarayanan, Mahadev; Zheng Bin

2007-01-01

Building an optimal image reference library is a critical step in developing the interactive computer-aided detection and diagnosis (I-CAD) systems of medical images using content-based image retrieval (CBIR) schemes. In this study, the authors conducted two experiments to investigate (1) the relationship between I-CAD performance and size of reference library and (2) a new reference selection strategy to optimize the library and improve I-CAD performance. The authors assembled a reference library that includes 3153 regions of interest (ROI) depicting either malignant masses (1592) or CAD-cued false-positive regions (1561) and an independent testing data set including 200 masses and 200 false-positive regions. A CBIR scheme using a distance-weighted K-nearest neighbor algorithm is applied to retrieve references that are considered similar to the testing sample from the library. The area under receiver operating characteristic curve (A z ) is used as an index to evaluate the I-CAD performance. In the first experiment, the authors systematically increased reference library size and tested I-CAD performance. The result indicates that scheme performance improves initially from A z =0.715 to 0.874 and then plateaus when the library size reaches approximately half of its maximum capacity. In the second experiment, based on the hypothesis that a ROI should be removed if it performs poorly compared to a group of similar ROIs in a large and diverse reference library, the authors applied a new strategy to identify 'poorly effective' references. By removing 174 identified ROIs from the reference library, I-CAD performance significantly increases to A z =0.914 (p<0.01). The study demonstrates that increasing reference library size and removing poorly effective references can significantly improve I-CAD performance

A Database Approach to Content-based XML retrieval

NARCIS (Netherlands)

Hiemstra, Djoerd

2003-01-01

This paper describes a rst prototype system for content-based retrieval from XML data. The system's design supports both XPath queries and complex information retrieval queries based on a language modelling approach to information retrieval. Evaluation using the INEX benchmark shows that it is

Computer-aided diagnostics of screening mammography using content-based image retrieval

Science.gov (United States)

Deserno, Thomas M.; Soiron, Michael; de Oliveira, Júlia E. E.; de A. Araújo, Arnaldo

2012-03-01

Breast cancer is one of the main causes of death among women in occidental countries. In the last years, screening mammography has been established worldwide for early detection of breast cancer, and computer-aided diagnostics (CAD) is being developed to assist physicians reading mammograms. A promising method for CAD is content-based image retrieval (CBIR). Recently, we have developed a classification scheme of suspicious tissue pattern based on the support vector machine (SVM). In this paper, we continue moving towards automatic CAD of screening mammography. The experiments are based on in total 10,509 radiographs that have been collected from different sources. From this, 3,375 images are provided with one and 430 radiographs with more than one chain code annotation of cancerous regions. In different experiments, this data is divided into 12 and 20 classes, distinguishing between four categories of tissue density, three categories of pathology and in the 20 class problem two categories of different types of lesions. Balancing the number of images in each class yields 233 and 45 images remaining in each of the 12 and 20 classes, respectively. Using a two-dimensional principal component analysis, features are extracted from small patches of 128 x 128 pixels and classified by means of a SVM. Overall, the accuracy of the raw classification was 61.6 % and 52.1 % for the 12 and the 20 class problem, respectively. The confusion matrices are assessed for detailed analysis. Furthermore, an implementation of a SVM-based CBIR system for CADx in screening mammography is presented. In conclusion, with a smarter patch extraction, the CBIR approach might reach precision rates that are helpful for the physicians. This, however, needs more comprehensive evaluation on clinical data.

Video retrieval by still-image analysis with ImageMiner

Science.gov (United States)

Kreyss, Jutta; Roeper, M.; Alshuth, Peter; Hermes, Thorsten; Herzog, Otthein

1997-01-01

The large amount of available multimedia information (e.g. videos, audio, images) requires efficient and effective annotation and retrieval methods. As videos start playing a more important role in the frame of multimedia, we want to make these available for content-based retrieval. The ImageMiner-System, which was developed at the University of Bremen in the AI group, is designed for content-based retrieval of single images by a new combination of techniques and methods from computer vision and artificial intelligence. In our approach to make videos available for retrieval in a large database of videos and images there are two necessary steps: First, the detection and extraction of shots from a video, which is done by a histogram based method and second, the construction of the separate frames in a shot to one still single images. This is performed by a mosaicing-technique. The resulting mosaiced image gives a one image visualization of the shot and can be analyzed by the ImageMiner-System. ImageMiner has been tested on several domains, (e.g. landscape images, technical drawings), which cover a wide range of applications.

Content-Based Multimedia Retrieval in the Presence of Unknown User Preferences

DEFF Research Database (Denmark)

Beecks, Christian; Assent, Ira; Seidl, Thomas

2011-01-01

Content-based multimedia retrieval requires an appropriate similarity model which reflects user preferences. When these preferences are unknown or when the structure of the data collection is unclear, retrieving the most preferable objects the user has in mind is challenging, as the notion...... address the problem of content-based multimedia retrieval in the presence of unknown user preferences. Our idea consists in performing content-based retrieval by considering all possibilities in a family of similarity models simultaneously. To this end, we propose a novel content-based retrieval approach...

Automatic medical image annotation and keyword-based image retrieval using relevance feedback.

Science.gov (United States)

Ko, Byoung Chul; Lee, JiHyeon; Nam, Jae-Yeal

2012-08-01

This paper presents novel multiple keywords annotation for medical images, keyword-based medical image retrieval, and relevance feedback method for image retrieval for enhancing image retrieval performance. For semantic keyword annotation, this study proposes a novel medical image classification method combining local wavelet-based center symmetric-local binary patterns with random forests. For keyword-based image retrieval, our retrieval system use the confidence score that is assigned to each annotated keyword by combining probabilities of random forests with predefined body relation graph. To overcome the limitation of keyword-based image retrieval, we combine our image retrieval system with relevance feedback mechanism based on visual feature and pattern classifier. Compared with other annotation and relevance feedback algorithms, the proposed method shows both improved annotation performance and accurate retrieval results.

Design and Realization of Music Retrieval System Based on Feature Content

Directory of Open Access Journals (Sweden)

Li Lei

2015-01-01

Full Text Available As computer technology develops rapidly, retrieval systems have also undergone great changes. People are no longer contented with singular retrieval means, but are trying many other ways to retrieve feature content. When it comes to music, however, the complexity of sound is still preventing its retrieval from moving further forward. To solve this problem, systematic analysis and study is carried out on music retrieval system based on feature content. A music retrieval system model based on feature content consisting of technical approaches for processing and retrieving of extraction symbols of music feature content is built and realized. An SML model is proposed and tested on two different types of song sets. The result shows good performance of the system. Besides, the shortfalls of the model are also noted and the future prospects of the music retrieval system based on feature content are outlined.

Quantifying the margin sharpness of lesions on radiological images for content-based image retrieval

International Nuclear Information System (INIS)

Xu Jiajing; Napel, Sandy; Greenspan, Hayit; Beaulieu, Christopher F.; Agrawal, Neeraj; Rubin, Daniel

2012-01-01

. Equivalence across deformations was assessed using Schuirmann's paired two one-sided tests. Results: In simulated images, the concordance correlation between measured gradient and actual gradient was 0.994. The mean (s.d.) and standard deviation NDCG score for the retrieval of K images, K = 5, 10, and 15, were 84% (8%), 85% (7%), and 85% (7%) for CT images containing liver lesions, and 82% (7%), 84% (6%), and 85% (4%) for CT images containing lung nodules, respectively. The authors’ proposed method outperformed the two existing margin characterization methods in average NDCG scores over all K, by 1.5% and 3% in datasets containing liver lesion, and 4.5% and 5% in datasets containing lung nodules. Equivalence testing showed that the authors’ feature is more robust across all margin deformations (p < 0.05) than the two existing methods for margin sharpness characterization in both simulated and clinical datasets. Conclusions: The authors have described a new image feature to quantify the margin sharpness of lesions. It has strong correlation with known margin sharpness in simulated images and in clinical CT images containing liver lesions and lung nodules. This image feature has excellent performance for retrieving images with similar margin characteristics, suggesting potential utility, in conjunction with other lesion features, for content-based image retrieval applications.

Color-Based Image Retrieval from High-Similarity Image Databases

DEFF Research Database (Denmark)

Hansen, Michael Adsetts Edberg; Carstensen, Jens Michael

2003-01-01

Many image classification problems can fruitfully be thought of as image retrieval in a "high similarity image database" (HSID) characterized by being tuned towards a specific application and having a high degree of visual similarity between entries that should be distinguished. We introduce...... a method for HSID retrieval using a similarity measure based on a linear combination of Jeffreys-Matusita (JM) distances between distributions of color (and color derivatives) estimated from a set of automatically extracted image regions. The weight coefficients are estimated based on optimal retrieval...... performance. Experimental results on the difficult task of visually identifying clones of fungal colonies grown in a petri dish and categorization of pelts show a high retrieval accuracy of the method when combined with standardized sample preparation and image acquisition....

Toward privacy-preserving JPEG image retrieval

Science.gov (United States)

Cheng, Hang; Wang, Jingyue; Wang, Meiqing; Zhong, Shangping

2017-07-01

This paper proposes a privacy-preserving retrieval scheme for JPEG images based on local variance. Three parties are involved in the scheme: the content owner, the server, and the authorized user. The content owner encrypts JPEG images for privacy protection by jointly using permutation cipher and stream cipher, and then, the encrypted versions are uploaded to the server. With an encrypted query image provided by an authorized user, the server may extract blockwise local variances in different directions without knowing the plaintext content. After that, it can calculate the similarity between the encrypted query image and each encrypted database image by a local variance-based feature comparison mechanism. The authorized user with the encryption key can decrypt the returned encrypted images with plaintext content similar to the query image. The experimental results show that the proposed scheme not only provides effective privacy-preserving retrieval service but also ensures both format compliance and file size preservation for encrypted JPEG images.

A fully automatic end-to-end method for content-based image retrieval of CT scans with similar liver lesion annotations.

Science.gov (United States)

Spanier, A B; Caplan, N; Sosna, J; Acar, B; Joskowicz, L

2018-01-01

The goal of medical content-based image retrieval (M-CBIR) is to assist radiologists in the decision-making process by retrieving medical cases similar to a given image. One of the key interests of radiologists is lesions and their annotations, since the patient treatment depends on the lesion diagnosis. Therefore, a key feature of M-CBIR systems is the retrieval of scans with the most similar lesion annotations. To be of value, M-CBIR systems should be fully automatic to handle large case databases. We present a fully automatic end-to-end method for the retrieval of CT scans with similar liver lesion annotations. The input is a database of abdominal CT scans labeled with liver lesions, a query CT scan, and optionally one radiologist-specified lesion annotation of interest. The output is an ordered list of the database CT scans with the most similar liver lesion annotations. The method starts by automatically segmenting the liver in the scan. It then extracts a histogram-based features vector from the segmented region, learns the features' relative importance, and ranks the database scans according to the relative importance measure. The main advantages of our method are that it fully automates the end-to-end querying process, that it uses simple and efficient techniques that are scalable to large datasets, and that it produces quality retrieval results using an unannotated CT scan. Our experimental results on 9 CT queries on a dataset of 41 volumetric CT scans from the 2014 Image CLEF Liver Annotation Task yield an average retrieval accuracy (Normalized Discounted Cumulative Gain index) of 0.77 and 0.84 without/with annotation, respectively. Fully automatic end-to-end retrieval of similar cases based on image information alone, rather that on disease diagnosis, may help radiologists to better diagnose liver lesions.

Interactive Exploration for Image Retrieval

Directory of Open Access Journals (Sweden)

Jérôme Fournier

2005-08-01

Full Text Available We present a new version of our content-based image retrieval system RETIN. It is based on adaptive quantization of the color space, together with new features aiming at representing the spatial relationship between colors. Color analysis is also extended to texture. Using these powerful indexes, an original interactive retrieval strategy is introduced. The process is based on two steps for handling the retrieval of very large image categories. First, a controlled exploration method of the database is presented. Second, a relevance feedback method based on statistical learning is proposed. All the steps are evaluated by experiments on a generalist database.

A content-based news video retrieval system: NVRS

Science.gov (United States)

Liu, Huayong; He, Tingting

2009-10-01

This paper focus on TV news programs and design a content-based news video browsing and retrieval system, NVRS, which is convenient for users to fast browsing and retrieving news video by different categories such as political, finance, amusement, etc. Combining audiovisual features and caption text information, the system automatically segments a complete news program into separate news stories. NVRS supports keyword-based news story retrieval, category-based news story browsing and generates key-frame-based video abstract for each story. Experiments show that the method of story segmentation is effective and the retrieval is also efficient.

Supervised learning of tools for content-based search of image databases

Science.gov (United States)

Delanoy, Richard L.

1996-03-01

A computer environment, called the Toolkit for Image Mining (TIM), is being developed with the goal of enabling users with diverse interests and varied computer skills to create search tools for content-based image retrieval and other pattern matching tasks. Search tools are generated using a simple paradigm of supervised learning that is based on the user pointing at mistakes of classification made by the current search tool. As mistakes are identified, a learning algorithm uses the identified mistakes to build up a model of the user's intentions, construct a new search tool, apply the search tool to a test image, display the match results as feedback to the user, and accept new inputs from the user. Search tools are constructed in the form of functional templates, which are generalized matched filters capable of knowledge- based image processing. The ability of this system to learn the user's intentions from experience contrasts with other existing approaches to content-based image retrieval that base searches on the characteristics of a single input example or on a predefined and semantically- constrained textual query. Currently, TIM is capable of learning spectral and textural patterns, but should be adaptable to the learning of shapes, as well. Possible applications of TIM include not only content-based image retrieval, but also quantitative image analysis, the generation of metadata for annotating images, data prioritization or data reduction in bandwidth-limited situations, and the construction of components for larger, more complex computer vision algorithms.

Dialog-based Interactive Image Retrieval

OpenAIRE

Guo, Xiaoxiao; Wu, Hui; Cheng, Yu; Rennie, Steven; Feris, Rogerio Schmidt

2018-01-01

Existing methods for interactive image retrieval have demonstrated the merit of integrating user feedback, improving retrieval results. However, most current systems rely on restricted forms of user feedback, such as binary relevance responses, or feedback based on a fixed set of relative attributes, which limits their impact. In this paper, we introduce a new approach to interactive image search that enables users to provide feedback via natural language, allowing for more natural and effect...

Algorithm for image retrieval based on edge gradient orientation statistical code.

Science.gov (United States)

Zeng, Jiexian; Zhao, Yonggang; Li, Weiye; Fu, Xiang

2014-01-01

Image edge gradient direction not only contains important information of the shape, but also has a simple, lower complexity characteristic. Considering that the edge gradient direction histograms and edge direction autocorrelogram do not have the rotation invariance, we put forward the image retrieval algorithm which is based on edge gradient orientation statistical code (hereinafter referred to as EGOSC) by sharing the application of the statistics method in the edge direction of the chain code in eight neighborhoods to the statistics of the edge gradient direction. Firstly, we construct the n-direction vector and make maximal summation restriction on EGOSC to make sure this algorithm is invariable for rotation effectively. Then, we use Euclidean distance of edge gradient direction entropy to measure shape similarity, so that this method is not sensitive to scaling, color, and illumination change. The experimental results and the algorithm analysis demonstrate that the algorithm can be used for content-based image retrieval and has good retrieval results.

PROTOTYPE CONTENT BASED IMAGE RETRIEVAL UNTUK DETEKSI PEN YAKIT KULIT DENGAN METODE EDGE DETECTION

Directory of Open Access Journals (Sweden)

Erick Fernando

2016-05-01

Full Text Available Dokter spesialis kulit melakukan pemeriksa secara visual objek mata, capture objek dengan kamera digital dan menanyakan riwayat perjalanan penyakit pasien, tanpa melakukan perbandingan terhadap gejala dan tanda yang ada sebelummnya. Sehingga pemeriksaan dan perkiraan jenis penyakit kulit. Pengolahan data citra dalam bentuk digital khususnya citra medis sudah sangat dibutuhkan dengan pra-processing. Banyak pasien yang dilayani di rumah sakit masih menggunakan data citra analog. Data analog ini membutuhkan ruangan khusus untuk menyimpan guna menghindarkan kerusakan mekanis. Uraian mengatasi permasalahan ini, citra medis dibuat dalam bentuk digital dan disimpan dalam sistem database dan dapat melihat kesamaan citra kulit yang baru. Citra akan dapat ditampilkan dengan pra- processing dengan identifikasi kesamaan dengan Content Based Image Retrieval (CBIR bekerja dengan cara mengukur kemiripan citra query dengan semua citra yang ada dalam database sehingga query cost berbanding lurus dengan jumlah citra dalam database.

Modelling of chromatic contrast for retrieval of wallpaper images

OpenAIRE

Gao, Xiaohong W.; Wang, Yuanlei; Qian, Yu; Gao, Alice

2015-01-01

Colour remains one of the key factors in presenting an object and consequently has been widely applied in retrieval of images based on their visual contents. However, a colour appearance changes with the change of viewing surroundings, the phenomenon that has not been paid attention yet while performing colour-based image retrieval. To comprehend this effect, in this paper, a chromatic contrast model, CAMcc, is developed for the application of retrieval of colour intensive images, cementing t...

Content-based TV sports video retrieval using multimodal analysis

Science.gov (United States)

Yu, Yiqing; Liu, Huayong; Wang, Hongbin; Zhou, Dongru

2003-09-01

In this paper, we propose content-based video retrieval, which is a kind of retrieval by its semantical contents. Because video data is composed of multimodal information streams such as video, auditory and textual streams, we describe a strategy of using multimodal analysis for automatic parsing sports video. The paper first defines the basic structure of sports video database system, and then introduces a new approach that integrates visual stream analysis, speech recognition, speech signal processing and text extraction to realize video retrieval. The experimental results for TV sports video of football games indicate that the multimodal analysis is effective for video retrieval by quickly browsing tree-like video clips or inputting keywords within predefined domain.

Research of image retrieval technology based on color feature

Science.gov (United States)

Fu, Yanjun; Jiang, Guangyu; Chen, Fengying

2009-10-01

Recently, with the development of the communication and the computer technology and the improvement of the storage technology and the capability of the digital image equipment, more and more image resources are given to us than ever. And thus the solution of how to locate the proper image quickly and accurately is wanted.The early method is to set up a key word for searching in the database, but now the method has become very difficult when we search much more picture that we need. In order to overcome the limitation of the traditional searching method, content based image retrieval technology was aroused. Now, it is a hot research subject.Color image retrieval is the important part of it. Color is the most important feature for color image retrieval. Three key questions on how to make use of the color characteristic are discussed in the paper: the expression of color, the abstraction of color characteristic and the measurement of likeness based on color. On the basis, the extraction technology of the color histogram characteristic is especially discussed. Considering the advantages and disadvantages of the overall histogram and the partition histogram, a new method based the partition-overall histogram is proposed. The basic thought of it is to divide the image space according to a certain strategy, and then calculate color histogram of each block as the color feature of this block. Users choose the blocks that contain important space information, confirming the right value. The system calculates the distance between the corresponding blocks that users choosed. Other blocks merge into part overall histograms again, and the distance should be calculated. Then accumulate all the distance as the real distance between two pictures. The partition-overall histogram comprehensive utilizes advantages of two methods above, by choosing blocks makes the feature contain more spatial information which can improve performance; the distances between partition-overall histogram

Applying GA for Optimizing the User Query in Image and Video Retrieval

OpenAIRE

Ehsan Lotfi

2014-01-01

In an information retrieval system, the query can be made by user sketch. The new method presented here, optimizes the user sketch and applies the optimized query to retrieval the information. This optimization may be used in Content-Based Image Retrieval (CBIR) and Content-Based Video Retrieval (CBVR) which is based on trajectory extraction. To optimize the retrieval process, one stage of retrieval is performed by the user sketch. The retrieval criterion is based on the proposed distance met...

Feature hashing for fast image retrieval

Science.gov (United States)

Yan, Lingyu; Fu, Jiarun; Zhang, Hongxin; Yuan, Lu; Xu, Hui

2018-03-01

Currently, researches on content based image retrieval mainly focus on robust feature extraction. However, due to the exponential growth of online images, it is necessary to consider searching among large scale images, which is very timeconsuming and unscalable. Hence, we need to pay much attention to the efficiency of image retrieval. In this paper, we propose a feature hashing method for image retrieval which not only generates compact fingerprint for image representation, but also prevents huge semantic loss during the process of hashing. To generate the fingerprint, an objective function of semantic loss is constructed and minimized, which combine the influence of both the neighborhood structure of feature data and mapping error. Since the machine learning based hashing effectively preserves neighborhood structure of data, it yields visual words with strong discriminability. Furthermore, the generated binary codes leads image representation building to be of low-complexity, making it efficient and scalable to large scale databases. Experimental results show good performance of our approach.

A Novel Image Retrieval Based on Visual Words Integration of SIFT and SURF.

Directory of Open Access Journals (Sweden)

Nouman Ali

Full Text Available With the recent evolution of technology, the number of image archives has increased exponentially. In Content-Based Image Retrieval (CBIR, high-level visual information is represented in the form of low-level features. The semantic gap between the low-level features and the high-level image concepts is an open research problem. In this paper, we present a novel visual words integration of Scale Invariant Feature Transform (SIFT and Speeded-Up Robust Features (SURF. The two local features representations are selected for image retrieval because SIFT is more robust to the change in scale and rotation, while SURF is robust to changes in illumination. The visual words integration of SIFT and SURF adds the robustness of both features to image retrieval. The qualitative and quantitative comparisons conducted on Corel-1000, Corel-1500, Corel-2000, Oliva and Torralba and Ground Truth image benchmarks demonstrate the effectiveness of the proposed visual words integration.

Stochastic Optimized Relevance Feedback Particle Swarm Optimization for Content Based Image Retrieval

Directory of Open Access Journals (Sweden)

Muhammad Imran

2014-01-01

Full Text Available One of the major challenges for the CBIR is to bridge the gap between low level features and high level semantics according to the need of the user. To overcome this gap, relevance feedback (RF coupled with support vector machine (SVM has been applied successfully. However, when the feedback sample is small, the performance of the SVM based RF is often poor. To improve the performance of RF, this paper has proposed a new technique, namely, PSO-SVM-RF, which combines SVM based RF with particle swarm optimization (PSO. The aims of this proposed technique are to enhance the performance of SVM based RF and also to minimize the user interaction with the system by minimizing the RF number. The PSO-SVM-RF was tested on the coral photo gallery containing 10908 images. The results obtained from the experiments showed that the proposed PSO-SVM-RF achieved 100% accuracy in 8 feedback iterations for top 10 retrievals and 80% accuracy in 6 iterations for 100 top retrievals. This implies that with PSO-SVM-RF technique high accuracy rate is achieved at a small number of iterations.

Region-Based Image Retrieval Using an Object Ontology and Relevance Feedback

Directory of Open Access Journals (Sweden)

Kompatsiaris Ioannis

2004-01-01

Full Text Available An image retrieval methodology suited for search in large collections of heterogeneous images is presented. The proposed approach employs a fully unsupervised segmentation algorithm to divide images into regions and endow the indexing and retrieval system with content-based functionalities. Low-level descriptors for the color, position, size, and shape of each region are subsequently extracted. These arithmetic descriptors are automatically associated with appropriate qualitative intermediate-level descriptors, which form a simple vocabulary termed object ontology. The object ontology is used to allow the qualitative definition of the high-level concepts the user queries for (semantic objects, each represented by a keyword and their relations in a human-centered fashion. When querying for a specific semantic object (or objects, the intermediate-level descriptor values associated with both the semantic object and all image regions in the collection are initially compared, resulting in the rejection of most image regions as irrelevant. Following that, a relevance feedback mechanism, based on support vector machines and using the low-level descriptors, is invoked to rank the remaining potentially relevant image regions and produce the final query results. Experimental results and comparisons demonstrate, in practice, the effectiveness of our approach.

Dual-force ISOMAP: a new relevance feedback method for medical image retrieval.

Science.gov (United States)

Shen, Hualei; Tao, Dacheng; Ma, Dianfu

2013-01-01

With great potential for assisting radiological image interpretation and decision making, content-based image retrieval in the medical domain has become a hot topic in recent years. Many methods to enhance the performance of content-based medical image retrieval have been proposed, among which the relevance feedback (RF) scheme is one of the most promising. Given user feedback information, RF algorithms interactively learn a user's preferences to bridge the "semantic gap" between low-level computerized visual features and high-level human semantic perception and thus improve retrieval performance. However, most existing RF algorithms perform in the original high-dimensional feature space and ignore the manifold structure of the low-level visual features of images. In this paper, we propose a new method, termed dual-force ISOMAP (DFISOMAP), for content-based medical image retrieval. Under the assumption that medical images lie on a low-dimensional manifold embedded in a high-dimensional ambient space, DFISOMAP operates in the following three stages. First, the geometric structure of positive examples in the learned low-dimensional embedding is preserved according to the isometric feature mapping (ISOMAP) criterion. To precisely model the geometric structure, a reconstruction error constraint is also added. Second, the average distance between positive and negative examples is maximized to separate them; this margin maximization acts as a force that pushes negative examples far away from positive examples. Finally, the similarity propagation technique is utilized to provide negative examples with another force that will pull them back into the negative sample set. We evaluate the proposed method on a subset of the IRMA medical image dataset with a RF-based medical image retrieval framework. Experimental results show that DFISOMAP outperforms popular approaches for content-based medical image retrieval in terms of accuracy and stability.

Intelligent image retrieval based on radiology reports

Energy Technology Data Exchange (ETDEWEB)

Gerstmair, Axel; Langer, Mathias; Kotter, Elmar [University Medical Center Freiburg, Department of Diagnostic Radiology, Freiburg (Germany); Daumke, Philipp; Simon, Kai [Averbis GmbH, Freiburg (Germany)

2012-12-15

To create an advanced image retrieval and data-mining system based on in-house radiology reports. Radiology reports are semantically analysed using natural language processing (NLP) techniques and stored in a state-of-the-art search engine. Images referenced by sequence and image number in the reports are retrieved from the picture archiving and communication system (PACS) and stored for later viewing. A web-based front end is used as an interface to query for images and show the results with the retrieved images and report text. Using a comprehensive radiological lexicon for the underlying terminology, the search algorithm also finds results for synonyms, abbreviations and related topics. The test set was 108 manually annotated reports analysed by different system configurations. Best results were achieved using full syntactic and semantic analysis with a precision of 0.929 and recall of 0.952. Operating successfully since October 2010, 258,824 reports have been indexed and a total of 405,146 preview images are stored in the database. Data-mining and NLP techniques provide quick access to a vast repository of images and radiology reports with both high precision and recall values. Consequently, the system has become a valuable tool in daily clinical routine, education and research. (orig.)

Intelligent image retrieval based on radiology reports

International Nuclear Information System (INIS)

Gerstmair, Axel; Langer, Mathias; Kotter, Elmar; Daumke, Philipp; Simon, Kai

2012-01-01

To create an advanced image retrieval and data-mining system based on in-house radiology reports. Radiology reports are semantically analysed using natural language processing (NLP) techniques and stored in a state-of-the-art search engine. Images referenced by sequence and image number in the reports are retrieved from the picture archiving and communication system (PACS) and stored for later viewing. A web-based front end is used as an interface to query for images and show the results with the retrieved images and report text. Using a comprehensive radiological lexicon for the underlying terminology, the search algorithm also finds results for synonyms, abbreviations and related topics. The test set was 108 manually annotated reports analysed by different system configurations. Best results were achieved using full syntactic and semantic analysis with a precision of 0.929 and recall of 0.952. Operating successfully since October 2010, 258,824 reports have been indexed and a total of 405,146 preview images are stored in the database. Data-mining and NLP techniques provide quick access to a vast repository of images and radiology reports with both high precision and recall values. Consequently, the system has become a valuable tool in daily clinical routine, education and research. (orig.)

Retrieving clinically relevant diabetic retinopathy images using a multi-class multiple-instance framework

Science.gov (United States)

Chandakkar, Parag S.; Venkatesan, Ragav; Li, Baoxin

2013-02-01

Diabetic retinopathy (DR) is a vision-threatening complication from diabetes mellitus, a medical condition that is rising globally. Unfortunately, many patients are unaware of this complication because of absence of symptoms. Regular screening of DR is necessary to detect the condition for timely treatment. Content-based image retrieval, using archived and diagnosed fundus (retinal) camera DR images can improve screening efficiency of DR. This content-based image retrieval study focuses on two DR clinical findings, microaneurysm and neovascularization, which are clinical signs of non-proliferative and proliferative diabetic retinopathy. The authors propose a multi-class multiple-instance image retrieval framework which deploys a modified color correlogram and statistics of steerable Gaussian Filter responses, for retrieving clinically relevant images from a database of DR fundus image database.

PCI bus content-addressable-memory (CAM) implementation on FPGA for pattern recognition/image retrieval in a distributed environment

Science.gov (United States)

Megherbi, Dalila B.; Yan, Yin; Tanmay, Parikh; Khoury, Jed; Woods, C. L.

2004-11-01

Recently surveillance and Automatic Target Recognition (ATR) applications are increasing as the cost of computing power needed to process the massive amount of information continues to fall. This computing power has been made possible partly by the latest advances in FPGAs and SOPCs. In particular, to design and implement state-of-the-Art electro-optical imaging systems to provide advanced surveillance capabilities, there is a need to integrate several technologies (e.g. telescope, precise optics, cameras, image/compute vision algorithms, which can be geographically distributed or sharing distributed resources) into a programmable system and DSP systems. Additionally, pattern recognition techniques and fast information retrieval, are often important components of intelligent systems. The aim of this work is using embedded FPGA as a fast, configurable and synthesizable search engine in fast image pattern recognition/retrieval in a distributed hardware/software co-design environment. In particular, we propose and show a low cost Content Addressable Memory (CAM)-based distributed embedded FPGA hardware architecture solution with real time recognition capabilities and computing for pattern look-up, pattern recognition, and image retrieval. We show how the distributed CAM-based architecture offers a performance advantage of an order-of-magnitude over RAM-based architecture (Random Access Memory) search for implementing high speed pattern recognition for image retrieval. The methods of designing, implementing, and analyzing the proposed CAM based embedded architecture are described here. Other SOPC solutions/design issues are covered. Finally, experimental results, hardware verification, and performance evaluations using both the Xilinx Virtex-II and the Altera Apex20k are provided to show the potential and power of the proposed method for low cost reconfigurable fast image pattern recognition/retrieval at the hardware/software co-design level.

AN ENSEMBLE TEMPLATE MATCHING AND CONTENT-BASED IMAGE RETRIEVAL SCHEME TOWARDS EARLY STAGE DETECTION OF MELANOMA

Directory of Open Access Journals (Sweden)

Spiros Kostopoulos

2016-12-01

Full Text Available Malignant melanoma represents the most dangerous type of skin cancer. In this study we present an ensemble classification scheme, employing the mutual information, the cross-correlation and the clustering based on proximity of image features methods, for early stage assessment of melanomas on plain photography images. The proposed scheme performs two main operations. First, it retrieves the most similar, to the unknown case, image samples from an available image database with verified benign moles and malignant melanoma cases. Second, it provides an automated estimation regarding the nature of the unknown image sample based on the majority of the most similar images retrieved from the available database. Clinical material comprised 75 melanoma and 75 benign plain photography images collected from publicly available dermatological atlases. Results showed that the ensemble scheme outperformed all other methods tested in terms of accuracy with 94.9±1.5%, following an external cross-validation evaluation methodology. The proposed scheme may benefit patients by providing a second opinion consultation during the self-skin examination process and the physician by providing a second opinion estimation regarding the nature of suspicious moles that may assist towards decision making especially for ambiguous cases, safeguarding, in this way from potential diagnostic misinterpretations.

An Effective Combined Feature For Web Based Image Retrieval

Directory of Open Access Journals (Sweden)

H.M.R.B Herath

2015-08-01

Full Text Available Abstract Technology advances as well as the emergence of large scale multimedia applications and the revolution of the World Wide Web has changed the world into a digital age. Anybody can use their mobile phone to take a photo at any time anywhere and upload that image to ever growing image databases. Development of effective techniques for visual and multimedia retrieval systems is one of the most challenging and important directions of the future research. This paper proposes an effective combined feature for web based image retrieval. Frequently used colour and texture features are explored in order to develop a combined feature for this purpose. Widely used three colour features Colour moments Colour coherence vector and Colour Correlogram and three texture features Grey Level Co-occurrence matrix Tamura features and Gabor filter were analyzed for their performance. Precision and Recall were used to evaluate the performance of each of these techniques. By comparing precision and recall values the methods that performed best were taken and combined to form a hybrid feature. The developed combined feature was evaluated by developing a web based CBIR system. A web crawler was used to first crawl through Web sites and images found in those sites are downloaded and the combined feature representation technique was used to extract image features. The test results indicated that this web system can be used to index web images with the combined feature representation schema and to find similar images. Random image retrievals using the web system shows that the combined feature can be used to retrieve images belonging to the general image domain. Accuracy of the retrieval can be noted high for natural images like outdoor scenes images of flowers etc. Also images which have a similar colour and texture distribution were retrieved as similar even though the images were belonging to deferent semantic categories. This can be ideal for an artist who wants

Simultenious binary hash and features learning for image retrieval

Science.gov (United States)

Frantc, V. A.; Makov, S. V.; Voronin, V. V.; Marchuk, V. I.; Semenishchev, E. A.; Egiazarian, K. O.; Agaian, S.

2016-05-01

Content-based image retrieval systems have plenty of applications in modern world. The most important one is the image search by query image or by semantic description. Approaches to this problem are employed in personal photo-collection management systems, web-scale image search engines, medical systems, etc. Automatic analysis of large unlabeled image datasets is virtually impossible without satisfactory image-retrieval technique. It's the main reason why this kind of automatic image processing has attracted so much attention during recent years. Despite rather huge progress in the field, semantically meaningful image retrieval still remains a challenging task. The main issue here is the demand to provide reliable results in short amount of time. This paper addresses the problem by novel technique for simultaneous learning of global image features and binary hash codes. Our approach provide mapping of pixel-based image representation to hash-value space simultaneously trying to save as much of semantic image content as possible. We use deep learning methodology to generate image description with properties of similarity preservation and statistical independence. The main advantage of our approach in contrast to existing is ability to fine-tune retrieval procedure for very specific application which allow us to provide better results in comparison to general techniques. Presented in the paper framework for data- dependent image hashing is based on use two different kinds of neural networks: convolutional neural networks for image description and autoencoder for feature to hash space mapping. Experimental results confirmed that our approach has shown promising results in compare to other state-of-the-art methods.

Attention-based image similarity measure with application to content-based information retrieval

Science.gov (United States)

Stentiford, Fred W. M.

2003-01-01

Whilst storage and capture technologies are able to cope with huge numbers of images, image retrieval is in danger of rendering many repositories valueless because of the difficulty of access. This paper proposes a similarity measure that imposes only very weak assumptions on the nature of the features used in the recognition process. This approach does not make use of a pre-defined set of feature measurements which are extracted from a query image and used to match those from database images, but instead generates features on a trial and error basis during the calculation of the similarity measure. This has the significant advantage that features that determine similarity can match whatever image property is important in a particular region whether it be a shape, a texture, a colour or a combination of all three. It means that effort is expended searching for the best feature for the region rather than expecting that a fixed feature set will perform optimally over the whole area of an image and over every image in a database. The similarity measure is evaluated on a problem of distinguishing similar shapes in sets of black and white symbols.

W-transform method for feature-oriented multiresolution image retrieval

Energy Technology Data Exchange (ETDEWEB)

Kwong, M.K.; Lin, B. [Argonne National Lab., IL (United States). Mathematics and Computer Science Div.

1995-07-01

Image database management is important in the development of multimedia technology. Since an enormous amount of digital images is likely to be generated within the next few decades in order to integrate computers, television, VCR, cables, telephone and various imaging devices. Effective image indexing and retrieval systems are urgently needed so that images can be easily organized, searched, transmitted, and presented. Here, the authors present a local-feature-oriented image indexing and retrieval method based on Kwong, and Tang`s W-transform. Multiresolution histogram comparison is an effective method for content-based image indexing and retrieval. However, most recent approaches perform multiresolution analysis for whole images but do not exploit the local features present in the images. Since W-transform is featured by its ability to handle images of arbitrary size, with no periodicity assumptions, it provides a natural tool for analyzing local image features and building indexing systems based on such features. In this approach, the histograms of the local features of images are used in the indexing, system. The system not only can retrieve images that are similar or identical to the query images but also can retrieve images that contain features specified in the query images, even if the retrieved images as a whole might be very different from the query images. The local-feature-oriented method also provides a speed advantage over the global multiresolution histogram comparison method. The feature-oriented approach is expected to be applicable in managing large-scale image systems such as video databases and medical image databases.

Combining textual and visual information for image retrieval in the medical domain.

Science.gov (United States)

Gkoufas, Yiannis; Morou, Anna; Kalamboukis, Theodore

2011-01-01

In this article we have assembled the experience obtained from our participation in the imageCLEF evaluation task over the past two years. Exploitation on the use of linear combinations for image retrieval has been attempted by combining visual and textual sources of images. From our experiments we conclude that a mixed retrieval technique that applies both textual and visual retrieval in an interchangeably repeated manner improves the performance while overcoming the scalability limitations of visual retrieval. In particular, the mean average precision (MAP) has increased from 0.01 to 0.15 and 0.087 for 2009 and 2010 data, respectively, when content-based image retrieval (CBIR) is performed on the top 1000 results from textual retrieval based on natural language processing (NLP).

Improving performance of content-based image retrieval schemes in searching for similar breast mass regions: an assessment

International Nuclear Information System (INIS)

Wang Xiaohui; Park, Sang Cheol; Zheng Bin

2009-01-01

This study aims to assess three methods commonly used in content-based image retrieval (CBIR) schemes and investigate the approaches to improve scheme performance. A reference database involving 3000 regions of interest (ROIs) was established. Among them, 400 ROIs were randomly selected to form a testing dataset. Three methods, namely mutual information, Pearson's correlation and a multi-feature-based k-nearest neighbor (KNN) algorithm, were applied to search for the 15 'the most similar' reference ROIs to each testing ROI. The clinical relevance and visual similarity of searching results were evaluated using the areas under receiver operating characteristic (ROC) curves (A Z ) and average mean square difference (MSD) of the mass boundary spiculation level ratings between testing and selected ROIs, respectively. The results showed that the A Z values were 0.893 ± 0.009, 0.606 ± 0.021 and 0.699 ± 0.026 for the use of KNN, mutual information and Pearson's correlation, respectively. The A Z values increased to 0.724 ± 0.017 and 0.787 ± 0.016 for mutual information and Pearson's correlation when using ROIs with the size adaptively adjusted based on actual mass size. The corresponding MSD values were 2.107 ± 0.718, 2.301 ± 0.733 and 2.298 ± 0.743. The study demonstrates that due to the diversity of medical images, CBIR schemes using multiple image features and mass size-based ROIs can achieve significantly improved performance.

Semantics-Based Intelligent Indexing and Retrieval of Digital Images - A Case Study

Science.gov (United States)

Osman, Taha; Thakker, Dhavalkumar; Schaefer, Gerald

The proliferation of digital media has led to a huge interest in classifying and indexing media objects for generic search and usage. In particular, we are witnessing colossal growth in digital image repositories that are difficult to navigate using free-text search mechanisms, which often return inaccurate matches as they typically rely on statistical analysis of query keyword recurrence in the image annotation or surrounding text. In this chapter we present a semantically enabled image annotation and retrieval engine that is designed to satisfy the requirements of commercial image collections market in terms of both accuracy and efficiency of the retrieval process. Our search engine relies on methodically structured ontologies for image annotation, thus allowing for more intelligent reasoning about the image content and subsequently obtaining a more accurate set of results and a richer set of alternatives matchmaking the original query. We also show how our well-analysed and designed domain ontology contributes to the implicit expansion of user queries as well as presenting our initial thoughts on exploiting lexical databases for explicit semantic-based query expansion.

An efficient and robutst method for shape-based image retrieval

International Nuclear Information System (INIS)

Salih, N.D.; Besar, R.; Abas, F.S.

2007-01-01

Shapes can be thought as being the words oft he visual language. Shape boundaries need to be simplified and estimated in a wide variety of image analysis applications. Representation and description of Shapes is one of the major problems in content-based image retrieval (CBIR). This paper present an a novel method for shape representation and description named block-based shape representation (BSR), which is capable of extracting reliable information of the object outline in a concise manner. Our technique is translation, scale, and rotation invariant. It works well on different types of shapes and fast enough for use in real-time. This technique has been implemented and evaluated in order to analyze its accuracy and Efficiency. Based on the experimental results, we urge that the proposed BSR is a compact and reliable shape representation method. (author)

Document image retrieval through word shape coding.

Science.gov (United States)

Lu, Shijian; Li, Linlin; Tan, Chew Lim

2008-11-01

This paper presents a document retrieval technique that is capable of searching document images without OCR (optical character recognition). The proposed technique retrieves document images by a new word shape coding scheme, which captures the document content through annotating each word image by a word shape code. In particular, we annotate word images by using a set of topological shape features including character ascenders/descenders, character holes, and character water reservoirs. With the annotated word shape codes, document images can be retrieved by either query keywords or a query document image. Experimental results show that the proposed document image retrieval technique is fast, efficient, and tolerant to various types of document degradation.

Analysis, Retrieval and Delivery of Multimedia Content

CERN Document Server

Cavallaro, Andrea; Leonardi, Riccardo; Migliorati, Pierangelo

2013-01-01

Covering some of the most cutting-edge research on the delivery and retrieval of interactive multimedia content, this volume of specially chosen contributions provides the most updated perspective on one of the hottest contemporary topics. The material represents extended versions of papers presented at the 11th International Workshop on Image Analysis for Multimedia Interactive Services, a vital international forum on this fast-moving field. Logically organized in discrete sections that approach the subject from its various angles, the content deals in turn with content analysis, motion and activity analysis, high-level descriptors and video retrieval, 3-D and multi-view, and multimedia delivery. The chapters cover the finest detail of emerging techniques such as the use of high-level audio information in improving scene segmentation and the use of subjective logic for forensic visual surveillance. On content delivery, the book examines both images and video, focusing on key subjects including an efficient p...

Multimedia human brain database system for surgical candidacy determination in temporal lobe epilepsy with content-based image retrieval

Science.gov (United States)

Siadat, Mohammad-Reza; Soltanian-Zadeh, Hamid; Fotouhi, Farshad A.; Elisevich, Kost

2003-01-01

This paper presents the development of a human brain multimedia database for surgical candidacy determination in temporal lobe epilepsy. The focus of the paper is on content-based image management, navigation and retrieval. Several medical image-processing methods including our newly developed segmentation method are utilized for information extraction/correlation and indexing. The input data includes T1-, T2-Weighted MRI and FLAIR MRI and ictal and interictal SPECT modalities with associated clinical data and EEG data analysis. The database can answer queries regarding issues such as the correlation between the attribute X of the entity Y and the outcome of a temporal lobe epilepsy surgery. The entity Y can be a brain anatomical structure such as the hippocampus. The attribute X can be either a functionality feature of the anatomical structure Y, calculated with SPECT modalities, such as signal average, or a volumetric/morphological feature of the entity Y such as volume or average curvature. The outcome of the surgery can be any surgery assessment such as memory quotient. A determination is made regarding surgical candidacy by analysis of both textual and image data. The current database system suggests a surgical determination for the cases with relatively small hippocampus and high signal intensity average on FLAIR images within the hippocampus. This indication pretty much fits with the surgeons" expectations/observations. Moreover, as the database gets more populated with patient profiles and individual surgical outcomes, using data mining methods one may discover partially invisible correlations between the contents of different modalities of data and the outcome of the surgery.

Content-Based Information Retrieval from Forensic Databases

NARCIS (Netherlands)

Geradts, Z.J.M.H.

2002-01-01

In forensic science, the number of image databases is growing rapidly. For this reason, it is necessary to have a proper procedure for searching in these images databases based on content. The use of image databases results in more solved crimes; furthermore, statistical information can be obtained

Optical image transformation and encryption by phase-retrieval-based double random-phase encoding and compressive ghost imaging

Science.gov (United States)

Yuan, Sheng; Yang, Yangrui; Liu, Xuemei; Zhou, Xin; Wei, Zhenzhuo

2018-01-01

An optical image transformation and encryption scheme is proposed based on double random-phase encoding (DRPE) and compressive ghost imaging (CGI) techniques. In this scheme, a secret image is first transformed into a binary image with the phase-retrieval-based DRPE technique, and then encoded by a series of random amplitude patterns according to the ghost imaging (GI) principle. Compressive sensing, corrosion and expansion operations are implemented to retrieve the secret image in the decryption process. This encryption scheme takes the advantage of complementary capabilities offered by the phase-retrieval-based DRPE and GI-based encryption techniques. That is the phase-retrieval-based DRPE is used to overcome the blurring defect of the decrypted image in the GI-based encryption, and the CGI not only reduces the data amount of the ciphertext, but also enhances the security of DRPE. Computer simulation results are presented to verify the performance of the proposed encryption scheme.

Diversification in an image retrieval system based on text and image processing

Directory of Open Access Journals (Sweden)

Adrian Iftene

2014-11-01

Full Text Available In this paper we present an image retrieval system created within the research project MUCKE (Multimedia and User Credibility Knowledge Extraction, a CHIST-ERA research project where UAIC{\\footnote{"Alexandru Ioan Cuza" University of Iasi}} is one of the partners{\\footnote{Together with Technical University from Wienna, Austria, CEA-LIST Institute from Paris, France and BILKENT University from Ankara, Turkey}}. Our discussion in this work will focus mainly on components that are part of our image retrieval system proposed in MUCKE, and we present the work done by the UAIC group. MUCKE incorporates modules for processing multimedia content in different modes and languages (like English, French, German and Romanian and UAIC is responsible with text processing tasks (for Romanian and English. One of the problems addressed by our work is related to search results diversification. In order to solve this problem, we first process the user queries in both languages and secondly, we create clusters of similar images.

Multi-instance learning based on instance consistency for image retrieval

Science.gov (United States)

Zhang, Miao; Wu, Zhize; Wan, Shouhong; Yue, Lihua; Yin, Bangjie

2017-07-01

Multiple-instance learning (MIL) has been successfully utilized in image retrieval. Existing approaches cannot select positive instances correctly from positive bags which may result in a low accuracy. In this paper, we propose a new image retrieval approach called multiple instance learning based on instance-consistency (MILIC) to mitigate such issue. First, we select potential positive instances effectively in each positive bag by ranking instance-consistency (IC) values of instances. Then, we design a feature representation scheme, which can represent the relationship among bags and instances, based on potential positive instances to convert a bag into a single instance. Finally, we can use a standard single-instance learning strategy, such as the support vector machine, for performing object-based image retrieval. Experimental results on two challenging data sets show the effectiveness of our proposal in terms of accuracy and run time.

Facilitating medical information search using Google Glass connected to a content-based medical image retrieval system.

Science.gov (United States)

Widmer, Antoine; Schaer, Roger; Markonis, Dimitrios; Muller, Henning

2014-01-01

Wearable computing devices are starting to change the way users interact with computers and the Internet. Among them, Google Glass includes a small screen located in front of the right eye, a camera filming in front of the user and a small computing unit. Google Glass has the advantage to provide online services while allowing the user to perform tasks with his/her hands. These augmented glasses uncover many useful applications, also in the medical domain. For example, Google Glass can easily provide video conference between medical doctors to discuss a live case. Using these glasses can also facilitate medical information search by allowing the access of a large amount of annotated medical cases during a consultation in a non-disruptive fashion for medical staff. In this paper, we developed a Google Glass application able to take a photo and send it to a medical image retrieval system along with keywords in order to retrieve similar cases. As a preliminary assessment of the usability of the application, we tested the application under three conditions (images of the skin; printed CT scans and MRI images; and CT and MRI images acquired directly from an LCD screen) to explore whether using Google Glass affects the accuracy of the results returned by the medical image retrieval system. The preliminary results show that despite minor problems due to the relative stability of the Google Glass, images can be sent to and processed by the medical image retrieval system and similar images are returned to the user, potentially helping in the decision making process.

iPixel: a visual content-based and semantic search engine for retrieving digitized mammograms by using collective intelligence.

Science.gov (United States)

Alor-Hernández, Giner; Pérez-Gallardo, Yuliana; Posada-Gómez, Rubén; Cortes-Robles, Guillermo; Rodríguez-González, Alejandro; Aguilar-Laserre, Alberto A

2012-09-01

Nowadays, traditional search engines such as Google, Yahoo and Bing facilitate the retrieval of information in the format of images, but the results are not always useful for the users. This is mainly due to two problems: (1) the semantic keywords are not taken into consideration and (2) it is not always possible to establish a query using the image features. This issue has been covered in different domains in order to develop content-based image retrieval (CBIR) systems. The expert community has focussed their attention on the healthcare domain, where a lot of visual information for medical analysis is available. This paper provides a solution called iPixel Visual Search Engine, which involves semantics and content issues in order to search for digitized mammograms. iPixel offers the possibility of retrieving mammogram features using collective intelligence and implementing a CBIR algorithm. Our proposal compares not only features with similar semantic meaning, but also visual features. In this sense, the comparisons are made in different ways: by the number of regions per image, by maximum and minimum size of regions per image and by average intensity level of each region. iPixel Visual Search Engine supports the medical community in differential diagnoses related to the diseases of the breast. The iPixel Visual Search Engine has been validated by experts in the healthcare domain, such as radiologists, in addition to experts in digital image analysis.

A Novel Relevance Feedback Approach Based on Similarity Measure Modification in an X-Ray Image Retrieval System Based on Fuzzy Representation Using Fuzzy Attributed Relational Graph

Directory of Open Access Journals (Sweden)

Hossien Pourghassem

2011-04-01

Full Text Available Relevance feedback approaches is used to improve the performance of content-based image retrieval systems. In this paper, a novel relevance feedback approach based on similarity measure modification in an X-ray image retrieval system based on fuzzy representation using fuzzy attributed relational graph (FARG is presented. In this approach, optimum weight of each feature in feature vector is calculated using similarity rate between query image and relevant and irrelevant images in user feedback. The calculated weight is used to tune fuzzy graph matching algorithm as a modifier parameter in similarity measure. The standard deviation of the retrieved image features is applied to calculate the optimum weight. The proposed image retrieval system uses a FARG for representation of images, a fuzzy matching graph algorithm as similarity measure and a semantic classifier based on merging scheme for determination of the search space in image database. To evaluate relevance feedback approach in the proposed system, a standard X-ray image database consisting of 10000 images in 57 classes is used. The improvement of the evaluation parameters shows proficiency and efficiency of the proposed system.

Scalable Integrated Region-Based Image Retrieval Using IRM and Statistical Clustering.

Science.gov (United States)

Wang, James Z.; Du, Yanping

Statistical clustering is critical in designing scalable image retrieval systems. This paper presents a scalable algorithm for indexing and retrieving images based on region segmentation. The method uses statistical clustering on region features and IRM (Integrated Region Matching), a measure developed to evaluate overall similarity between images…

Content-based video retrieval by example video clip

Science.gov (United States)

Dimitrova, Nevenka; Abdel-Mottaleb, Mohamed

1997-01-01

This paper presents a novel approach for video retrieval from a large archive of MPEG or Motion JPEG compressed video clips. We introduce a retrieval algorithm that takes a video clip as a query and searches the database for clips with similar contents. Video clips are characterized by a sequence of representative frame signatures, which are constructed from DC coefficients and motion information (`DC+M' signatures). The similarity between two video clips is determined by using their respective signatures. This method facilitates retrieval of clips for the purpose of video editing, broadcast news retrieval, or copyright violation detection.

Low-dose multiple-information retrieval algorithm for X-ray grating-based imaging

International Nuclear Information System (INIS)

Wang Zhentian; Huang Zhifeng; Chen Zhiqiang; Zhang Li; Jiang Xiaolei; Kang Kejun; Yin Hongxia; Wang Zhenchang; Stampanoni, Marco

2011-01-01

The present work proposes a low dose information retrieval algorithm for X-ray grating-based multiple-information imaging (GB-MII) method, which can retrieve the attenuation, refraction and scattering information of samples by only three images. This algorithm aims at reducing the exposure time and the doses delivered to the sample. The multiple-information retrieval problem in GB-MII is solved by transforming a nonlinear equations set to a linear equations and adopting the nature of the trigonometric functions. The proposed algorithm is validated by experiments both on conventional X-ray source and synchrotron X-ray source, and compared with the traditional multiple-image-based retrieval algorithm. The experimental results show that our algorithm is comparable with the traditional retrieval algorithm and especially suitable for high Signal-to-Noise system.

Multi-clues image retrieval based on improved color invariants

Science.gov (United States)

Liu, Liu; Li, Jian-Xun

2012-05-01

At present, image retrieval has a great progress in indexing efficiency and memory usage, which mainly benefits from the utilization of the text retrieval technology, such as the bag-of-features (BOF) model and the inverted-file structure. Meanwhile, because the robust local feature invariants are selected to establish BOF, the retrieval precision of BOF is enhanced, especially when it is applied to a large-scale database. However, these local feature invariants mainly consider the geometric variance of the objects in the images, and thus the color information of the objects fails to be made use of. Because of the development of the information technology and Internet, the majority of our retrieval objects is color images. Therefore, retrieval performance can be further improved through proper utilization of the color information. We propose an improved method through analyzing the flaw of shadow-shading quasi-invariant. The response and performance of shadow-shading quasi-invariant for the object edge with the variance of lighting are enhanced. The color descriptors of the invariant regions are extracted and integrated into BOF based on the local feature. The robustness of the algorithm and the improvement of the performance are verified in the final experiments.

Image Retrieval Algorithm Based on Discrete Fractional Transforms

Science.gov (United States)

Jindal, Neeru; Singh, Kulbir

2013-06-01

The discrete fractional transforms is a signal processing tool which suggests computational algorithms and solutions to various sophisticated applications. In this paper, a new technique to retrieve the encrypted and scrambled image based on discrete fractional transforms has been proposed. Two-dimensional image was encrypted using discrete fractional transforms with three fractional orders and two random phase masks placed in the two intermediate planes. The significant feature of discrete fractional transforms benefits from its extra degree of freedom that is provided by its fractional orders. Security strength was enhanced (1024!)4 times by scrambling the encrypted image. In decryption process, image retrieval is sensitive for both correct fractional order keys and scrambling algorithm. The proposed approach make the brute force attack infeasible. Mean square error and relative error are the recital parameters to verify validity of proposed method.

Generating region proposals for histopathological whole slide image retrieval.

Science.gov (United States)

Ma, Yibing; Jiang, Zhiguo; Zhang, Haopeng; Xie, Fengying; Zheng, Yushan; Shi, Huaqiang; Zhao, Yu; Shi, Jun

2018-06-01

Content-based image retrieval is an effective method for histopathological image analysis. However, given a database of huge whole slide images (WSIs), acquiring appropriate region-of-interests (ROIs) for training is significant and difficult. Moreover, histopathological images can only be annotated by pathologists, resulting in the lack of labeling information. Therefore, it is an important and challenging task to generate ROIs from WSI and retrieve image with few labels. This paper presents a novel unsupervised region proposing method for histopathological WSI based on Selective Search. Specifically, the WSI is over-segmented into regions which are hierarchically merged until the WSI becomes a single region. Nucleus-oriented similarity measures for region mergence and Nucleus-Cytoplasm color space for histopathological image are specially defined to generate accurate region proposals. Additionally, we propose a new semi-supervised hashing method for image retrieval. The semantic features of images are extracted with Latent Dirichlet Allocation and transformed into binary hashing codes with Supervised Hashing. The methods are tested on a large-scale multi-class database of breast histopathological WSIs. The results demonstrate that for one WSI, our region proposing method can generate 7.3 thousand contoured regions which fit well with 95.8% of the ROIs annotated by pathologists. The proposed hashing method can retrieve a query image among 136 thousand images in 0.29 s and reach precision of 91% with only 10% of images labeled. The unsupervised region proposing method can generate regions as predictions of lesions in histopathological WSI. The region proposals can also serve as the training samples to train machine-learning models for image retrieval. The proposed hashing method can achieve fast and precise image retrieval with small amount of labels. Furthermore, the proposed methods can be potentially applied in online computer-aided-diagnosis systems. Copyright

Evaluation of information-theoretic similarity measures for content-based retrieval and detection of masses in mammograms

International Nuclear Information System (INIS)

Tourassi, Georgia D.; Harrawood, Brian; Singh, Swatee; Lo, Joseph Y.; Floyd, Carey E.

2007-01-01

The purpose of this study was to evaluate image similarity measures employed in an information-theoretic computer-assisted detection (IT-CAD) scheme. The scheme was developed for content-based retrieval and detection of masses in screening mammograms. The study is aimed toward an interactive clinical paradigm where physicians query the proposed IT-CAD scheme on mammographic locations that are either visually suspicious or indicated as suspicious by other cuing CAD systems. The IT-CAD scheme provides an evidence-based, second opinion for query mammographic locations using a knowledge database of mass and normal cases. In this study, eight entropy-based similarity measures were compared with respect to retrieval precision and detection accuracy using a database of 1820 mammographic regions of interest. The IT-CAD scheme was then validated on a separate database for false positive reduction of progressively more challenging visual cues generated by an existing, in-house mass detection system. The study showed that the image similarity measures fall into one of two categories; one category is better suited to the retrieval of semantically similar cases while the second is more effective with knowledge-based decisions regarding the presence of a true mass in the query location. In addition, the IT-CAD scheme yielded a substantial reduction in false-positive detections while maintaining high detection rate for malignant masses

Qualification of a Null Lens Using Image-Based Phase Retrieval

Science.gov (United States)

Bolcar, Matthew R.; Aronstein, David L.; Hill, Peter C.; Smith, J. Scott; Zielinski, Thomas P.

2012-01-01

In measuring the figure error of an aspheric optic using a null lens, the wavefront contribution from the null lens must be independently and accurately characterized in order to isolate the optical performance of the aspheric optic alone. Various techniques can be used to characterize such a null lens, including interferometry, profilometry and image-based methods. Only image-based methods, such as phase retrieval, can measure the null-lens wavefront in situ - in single-pass, and at the same conjugates and in the same alignment state in which the null lens will ultimately be used - with no additional optical components. Due to the intended purpose of a Dull lens (e.g., to null a large aspheric wavefront with a near-equal-but-opposite spherical wavefront), characterizing a null-lens wavefront presents several challenges to image-based phase retrieval: Large wavefront slopes and high-dynamic-range data decrease the capture range of phase-retrieval algorithms, increase the requirements on the fidelity of the forward model of the optical system, and make it difficult to extract diagnostic information (e.g., the system F/#) from the image data. In this paper, we present a study of these effects on phase-retrieval algorithms in the context of a null lens used in component development for the Climate Absolute Radiance and Refractivity Observatory (CLARREO) mission. Approaches for mitigation are also discussed.

Optical multiple-image encryption based on multiplane phase retrieval and interference

International Nuclear Information System (INIS)

Chen, Wen; Chen, Xudong

2011-01-01

In this paper, we propose a new method for optical multiple-image encryption based on multiplane phase retrieval and interference. An optical encoding system is developed in the Fresnel domain. A phase-only map is iteratively extracted based on a multiplane phase retrieval algorithm, and multiple plaintexts are simultaneously encrypted. Subsequently, the extracted phase-only map is further encrypted into two phase-only masks based on a non-iterative interference algorithm. During image decryption, the advantages and security of the proposed optical cryptosystem are analyzed. Numerical results are presented to demonstrate the validity of the proposed optical multiple-image encryption method

Context-based adaptive filtering of interest points in image retrieval

DEFF Research Database (Denmark)

Nguyen, Phuong Giang; Andersen, Hans Jørgen

2009-01-01

Interest points have been used as local features with success in many computer vision applications such as image/video retrieval and object recognition. However, a major issue when using this approach is a large number of interest points detected from each image and created a dense feature space...... a subset of features. Our approach differs from others in a fact that selected feature is based on the context of the given image. Our experimental results show a significant reduction rate of features while preserving the retrieval performance....

Active learning methods for interactive image retrieval.

Science.gov (United States)

Gosselin, Philippe Henri; Cord, Matthieu

2008-07-01

Active learning methods have been considered with increased interest in the statistical learning community. Initially developed within a classification framework, a lot of extensions are now being proposed to handle multimedia applications. This paper provides algorithms within a statistical framework to extend active learning for online content-based image retrieval (CBIR). The classification framework is presented with experiments to compare several powerful classification techniques in this information retrieval context. Focusing on interactive methods, active learning strategy is then described. The limitations of this approach for CBIR are emphasized before presenting our new active selection process RETIN. First, as any active method is sensitive to the boundary estimation between classes, the RETIN strategy carries out a boundary correction to make the retrieval process more robust. Second, the criterion of generalization error to optimize the active learning selection is modified to better represent the CBIR objective of database ranking. Third, a batch processing of images is proposed. Our strategy leads to a fast and efficient active learning scheme to retrieve sets of online images (query concept). Experiments on large databases show that the RETIN method performs well in comparison to several other active strategies.

Dictionary Pruning with Visual Word Significance for Medical Image Retrieval.

Science.gov (United States)

Zhang, Fan; Song, Yang; Cai, Weidong; Hauptmann, Alexander G; Liu, Sidong; Pujol, Sonia; Kikinis, Ron; Fulham, Michael J; Feng, David Dagan; Chen, Mei

2016-02-12

Content-based medical image retrieval (CBMIR) is an active research area for disease diagnosis and treatment but it can be problematic given the small visual variations between anatomical structures. We propose a retrieval method based on a bag-of-visual-words (BoVW) to identify discriminative characteristics between different medical images with Pruned Dictionary based on Latent Semantic Topic description. We refer to this as the PD-LST retrieval. Our method has two main components. First, we calculate a topic-word significance value for each visual word given a certain latent topic to evaluate how the word is connected to this latent topic. The latent topics are learnt, based on the relationship between the images and words, and are employed to bridge the gap between low-level visual features and high-level semantics. These latent topics describe the images and words semantically and can thus facilitate more meaningful comparisons between the words. Second, we compute an overall-word significance value to evaluate the significance of a visual word within the entire dictionary. We designed an iterative ranking method to measure overall-word significance by considering the relationship between all latent topics and words. The words with higher values are considered meaningful with more significant discriminative power in differentiating medical images. We evaluated our method on two public medical imaging datasets and it showed improved retrieval accuracy and efficiency.

Socializing the Semantic Gap: A Comparative Survey on Image Tag Assignment, Refinement and Retrieval

NARCIS (Netherlands)

Li, X.; Uricchio, T.; Ballan, L.; Bertini, M.; Snoek, C.G.M.; Del Bimbo, A.

2016-01-01

Where previous reviews on content-based image retrieval emphasize what can be seen in an image to bridge the semantic gap, this survey considers what people tag about an image. A comprehensive treatise of three closely linked problems (i.e., image tag assignment, refinement, and tag-based image

Extending a DBMS to Support Content-Based Video Retrieval : A Formula 1 Case Study

NARCIS (Netherlands)

Petkovic, M.; Jonker, Willem; Mihajlovic, V.

Content-based retrieval has been identified as one of the most challenging problems, requiring a multidisciplinary research among computer vision, information retrieval, artificial intelligence, database, and other fields. In this paper, we address the specific aspect of inferring semantics

Robust histogram-based image retrieval

Czech Academy of Sciences Publication Activity Database

Höschl, Cyril; Flusser, Jan

2016-01-01

Roč. 69, č. 1 (2016), s. 72-81 ISSN 0167-8655 R&D Projects: GA ČR GA15-16928S Institutional support: RVO:67985556 Keywords : Image retrieval * Noisy image * Histogram * Convolution * Moments * Invariants Subject RIV: JD - Computer Applications, Robotics Impact factor: 1.995, year: 2016 http://library.utia.cas.cz/separaty/2015/ZOI/hoschl-0452147.pdf

Color Texture Image Retrieval Based on Local Extrema Features and Riemannian Distance

Directory of Open Access Journals (Sweden)

Minh-Tan Pham

2017-10-01

Full Text Available A novel efficient method for content-based image retrieval (CBIR is developed in this paper using both texture and color features. Our motivation is to represent and characterize an input image by a set of local descriptors extracted from characteristic points (i.e., keypoints within the image. Then, dissimilarity measure between images is calculated based on the geometric distance between the topological feature spaces (i.e., manifolds formed by the sets of local descriptors generated from each image of the database. In this work, we propose to extract and use the local extrema pixels as our feature points. Then, the so-called local extrema-based descriptor (LED is generated for each keypoint by integrating all color, spatial as well as gradient information captured by its nearest local extrema. Hence, each image is encoded by an LED feature point cloud and Riemannian distances between these point clouds enable us to tackle CBIR. Experiments performed on several color texture databases including Vistex, STex, color Brodazt, USPtex and Outex TC-00013 using the proposed approach provide very efficient and competitive results compared to the state-of-the-art methods.

Content-aware network storage system supporting metadata retrieval

Science.gov (United States)

Liu, Ke; Qin, Leihua; Zhou, Jingli; Nie, Xuejun

2008-12-01

Nowadays, content-based network storage has become the hot research spot of academy and corporation[1]. In order to solve the problem of hit rate decline causing by migration and achieve the content-based query, we exploit a new content-aware storage system which supports metadata retrieval to improve the query performance. Firstly, we extend the SCSI command descriptor block to enable system understand those self-defined query requests. Secondly, the extracted metadata is encoded by extensible markup language to improve the universality. Thirdly, according to the demand of information lifecycle management (ILM), we store those data in different storage level and use corresponding query strategy to retrieval them. Fourthly, as the file content identifier plays an important role in locating data and calculating block correlation, we use it to fetch files and sort query results through friendly user interface. Finally, the experiments indicate that the retrieval strategy and sort algorithm have enhanced the retrieval efficiency and precision.

Implementation of Texture Based Image Retrieval Using M-band Wavelet Transform

Institute of Scientific and Technical Information of China (English)

LiaoYa-li; Yangyan; CaoYang

2003-01-01

Wavelet transform has attracted attention because it is a very useful tool for signal analyzing. As a fundamental characteristic of an image, texture traits play an important role in the human vision system for recognition and interpretation of images. The paper presents an approach to implement texture-based image retrieval using M-band wavelet transform. Firstly the traditional 2-band wavelet is extended to M-band wavelet transform. Then the wavelet moments are computed by M-band wavelet coefficients in the wavelet domain. The set of wavelet moments forms the feature vector related to the texture distribution of each wavelet images. The distances between the feature vectors describe the similarities of different images. The experimental result shows that the M-band wavelet moment features of the images are effective for image indexing.The retrieval method has lower computational complexity, yet it is capable of giving better retrieval performance for a given medical image database.

Image retrieval

DEFF Research Database (Denmark)

Ørnager, Susanne

1997-01-01

The paper touches upon indexing and retrieval for effective searches of digitized images. Different conceptions of what subject indexing means are described as a basis for defining an operational subject indexing strategy for images. The methodology is based on the art historian Erwin Panofsky......), special knowledge about image codes, and special knowledge about history of ideas. The semiologist Roland Barthes has established a semiology for pictorial expressions based on advertising photos. Barthes uses the concepts denotation/connotation where denotations can be explained as the sober expression...

Hybrid Histogram Descriptor: A Fusion Feature Representation for Image Retrieval.

Science.gov (United States)

Feng, Qinghe; Hao, Qiaohong; Chen, Yuqi; Yi, Yugen; Wei, Ying; Dai, Jiangyan

2018-06-15

Currently, visual sensors are becoming increasingly affordable and fashionable, acceleratingly the increasing number of image data. Image retrieval has attracted increasing interest due to space exploration, industrial, and biomedical applications. Nevertheless, designing effective feature representation is acknowledged as a hard yet fundamental issue. This paper presents a fusion feature representation called a hybrid histogram descriptor (HHD) for image retrieval. The proposed descriptor comprises two histograms jointly: a perceptually uniform histogram which is extracted by exploiting the color and edge orientation information in perceptually uniform regions; and a motif co-occurrence histogram which is acquired by calculating the probability of a pair of motif patterns. To evaluate the performance, we benchmarked the proposed descriptor on RSSCN7, AID, Outex-00013, Outex-00014 and ETHZ-53 datasets. Experimental results suggest that the proposed descriptor is more effective and robust than ten recent fusion-based descriptors under the content-based image retrieval framework. The computational complexity was also analyzed to give an in-depth evaluation. Furthermore, compared with the state-of-the-art convolutional neural network (CNN)-based descriptors, the proposed descriptor also achieves comparable performance, but does not require any training process.

Efficient Retrieval of Massive Ocean Remote Sensing Images via a Cloud-Based Mean-Shift Algorithm.

Science.gov (United States)

Yang, Mengzhao; Song, Wei; Mei, Haibin

2017-07-23

The rapid development of remote sensing (RS) technology has resulted in the proliferation of high-resolution images. There are challenges involved in not only storing large volumes of RS images but also in rapidly retrieving the images for ocean disaster analysis such as for storm surges and typhoon warnings. In this paper, we present an efficient retrieval of massive ocean RS images via a Cloud-based mean-shift algorithm. Distributed construction method via the pyramid model is proposed based on the maximum hierarchical layer algorithm and used to realize efficient storage structure of RS images on the Cloud platform. We achieve high-performance processing of massive RS images in the Hadoop system. Based on the pyramid Hadoop distributed file system (HDFS) storage method, an improved mean-shift algorithm for RS image retrieval is presented by fusion with the canopy algorithm via Hadoop MapReduce programming. The results show that the new method can achieve better performance for data storage than HDFS alone and WebGIS-based HDFS. Speedup and scaleup are very close to linear changes with an increase of RS images, which proves that image retrieval using our method is efficient.

Mutual information based feature selection for medical image retrieval

Science.gov (United States)

Zhi, Lijia; Zhang, Shaomin; Li, Yan

2018-04-01

In this paper, authors propose a mutual information based method for lung CT image retrieval. This method is designed to adapt to different datasets and different retrieval task. For practical applying consideration, this method avoids using a large amount of training data. Instead, with a well-designed training process and robust fundamental features and measurements, the method in this paper can get promising performance and maintain economic training computation. Experimental results show that the method has potential practical values for clinical routine application.

Deep Hashing Based Fusing Index Method for Large-Scale Image Retrieval

Directory of Open Access Journals (Sweden)

Lijuan Duan

2017-01-01

Full Text Available Hashing has been widely deployed to perform the Approximate Nearest Neighbor (ANN search for the large-scale image retrieval to solve the problem of storage and retrieval efficiency. Recently, deep hashing methods have been proposed to perform the simultaneous feature learning and the hash code learning with deep neural networks. Even though deep hashing has shown the better performance than traditional hashing methods with handcrafted features, the learned compact hash code from one deep hashing network may not provide the full representation of an image. In this paper, we propose a novel hashing indexing method, called the Deep Hashing based Fusing Index (DHFI, to generate a more compact hash code which has stronger expression ability and distinction capability. In our method, we train two different architecture’s deep hashing subnetworks and fuse the hash codes generated by the two subnetworks together to unify images. Experiments on two real datasets show that our method can outperform state-of-the-art image retrieval applications.

Secure image retrieval with multiple keys

Science.gov (United States)

Liang, Haihua; Zhang, Xinpeng; Wei, Qiuhan; Cheng, Hang

2018-03-01

This article proposes a secure image retrieval scheme under a multiuser scenario. In this scheme, the owner first encrypts and uploads images and their corresponding features to the cloud; then, the user submits the encrypted feature of the query image to the cloud; next, the cloud compares the encrypted features and returns encrypted images with similar content to the user. To find the nearest neighbor in the encrypted features, an encryption with multiple keys is proposed, in which the query feature of each user is encrypted by his/her own key. To improve the key security and space utilization, global optimization and Gaussian distribution are, respectively, employed to generate multiple keys. The experiments show that the proposed encryption can provide effective and secure image retrieval for each user and ensure confidentiality of the query feature of each user.

Pleasant/Unpleasant Filtering for Affective Image Retrieval Based on Cross-Correlation of EEG Features

Directory of Open Access Journals (Sweden)

Keranmu Xielifuguli

2014-01-01

Full Text Available People often make decisions based on sensitivity rather than rationality. In the field of biological information processing, methods are available for analyzing biological information directly based on electroencephalogram: EEG to determine the pleasant/unpleasant reactions of users. In this study, we propose a sensitivity filtering technique for discriminating preferences (pleasant/unpleasant for images using a sensitivity image filtering system based on EEG. Using a set of images retrieved by similarity retrieval, we perform the sensitivity-based pleasant/unpleasant classification of images based on the affective features extracted from images with the maximum entropy method: MEM. In the present study, the affective features comprised cross-correlation features obtained from EEGs produced when an individual observed an image. However, it is difficult to measure the EEG when a subject visualizes an unknown image. Thus, we propose a solution where a linear regression method based on canonical correlation is used to estimate the cross-correlation features from image features. Experiments were conducted to evaluate the validity of sensitivity filtering compared with image similarity retrieval methods based on image features. We found that sensitivity filtering using color correlograms was suitable for the classification of preferred images, while sensitivity filtering using local binary patterns was suitable for the classification of unpleasant images. Moreover, sensitivity filtering using local binary patterns for unpleasant images had a 90% success rate. Thus, we conclude that the proposed method is efficient for filtering unpleasant images.

Pathfinder: multiresolution region-based searching of pathology images using IRM.

OpenAIRE

Wang, J. Z.

2000-01-01

The fast growth of digitized pathology slides has created great challenges in research on image database retrieval. The prevalent retrieval technique involves human-supplied text annotations to describe slide contents. These pathology images typically have very high resolution, making it difficult to search based on image content. In this paper, we present Pathfinder, an efficient multiresolution region-based searching system for high-resolution pathology image libraries. The system uses wave...

A novel biomedical image indexing and retrieval system via deep preference learning.

Science.gov (United States)

Pang, Shuchao; Orgun, Mehmet A; Yu, Zhezhou

2018-05-01

The traditional biomedical image retrieval methods as well as content-based image retrieval (CBIR) methods originally designed for non-biomedical images either only consider using pixel and low-level features to describe an image or use deep features to describe images but still leave a lot of room for improving both accuracy and efficiency. In this work, we propose a new approach, which exploits deep learning technology to extract the high-level and compact features from biomedical images. The deep feature extraction process leverages multiple hidden layers to capture substantial feature structures of high-resolution images and represent them at different levels of abstraction, leading to an improved performance for indexing and retrieval of biomedical images. We exploit the current popular and multi-layered deep neural networks, namely, stacked denoising autoencoders (SDAE) and convolutional neural networks (CNN) to represent the discriminative features of biomedical images by transferring the feature representations and parameters of pre-trained deep neural networks from another domain. Moreover, in order to index all the images for finding the similarly referenced images, we also introduce preference learning technology to train and learn a kind of a preference model for the query image, which can output the similarity ranking list of images from a biomedical image database. To the best of our knowledge, this paper introduces preference learning technology for the first time into biomedical image retrieval. We evaluate the performance of two powerful algorithms based on our proposed system and compare them with those of popular biomedical image indexing approaches and existing regular image retrieval methods with detailed experiments over several well-known public biomedical image databases. Based on different criteria for the evaluation of retrieval performance, experimental results demonstrate that our proposed algorithms outperform the state

Image retrieval by information fusion based on scalable vocabulary tree and robust Hausdorff distance

Science.gov (United States)

Che, Chang; Yu, Xiaoyang; Sun, Xiaoming; Yu, Boyang

2017-12-01

In recent years, Scalable Vocabulary Tree (SVT) has been shown to be effective in image retrieval. However, for general images where the foreground is the object to be recognized while the background is cluttered, the performance of the current SVT framework is restricted. In this paper, a new image retrieval framework that incorporates a robust distance metric and information fusion is proposed, which improves the retrieval performance relative to the baseline SVT approach. First, the visual words that represent the background are diminished by using a robust Hausdorff distance between different images. Second, image matching results based on three image signature representations are fused, which enhances the retrieval precision. We conducted intensive experiments on small-scale to large-scale image datasets: Corel-9, Corel-48, and PKU-198, where the proposed Hausdorff metric and information fusion outperforms the state-of-the-art methods by about 13, 15, and 15%, respectively.

Mobile medical image retrieval

Science.gov (United States)

Duc, Samuel; Depeursinge, Adrien; Eggel, Ivan; Müller, Henning

2011-03-01

Images are an integral part of medical practice for diagnosis, treatment planning and teaching. Image retrieval has gained in importance mainly as a research domain over the past 20 years. Both textual and visual retrieval of images are essential. In the process of mobile devices becoming reliable and having a functionality equaling that of formerly desktop clients, mobile computing has gained ground and many applications have been explored. This creates a new field of mobile information search & access and in this context images can play an important role as they often allow understanding complex scenarios much quicker and easier than free text. Mobile information retrieval in general has skyrocketed over the past year with many new applications and tools being developed and all sorts of interfaces being adapted to mobile clients. This article describes constraints of an information retrieval system including visual and textual information retrieval from the medical literature of BioMedCentral and of the RSNA journals Radiology and Radiographics. Solutions for mobile data access with an example on an iPhone in a web-based environment are presented as iPhones are frequently used and the operating system is bound to become the most frequent smartphone operating system in 2011. A web-based scenario was chosen to allow for a use by other smart phone platforms such as Android as well. Constraints of small screens and navigation with touch screens are taken into account in the development of the application. A hybrid choice had to be taken to allow for taking pictures with the cell phone camera and upload them for visual similarity search as most producers of smart phones block this functionality to web applications. Mobile information access and in particular access to images can be surprisingly efficient and effective on smaller screens. Images can be read on screen much faster and relevance of documents can be identified quickly through the use of images contained in

A Learning State-Space Model for Image Retrieval

Directory of Open Access Journals (Sweden)

Lee Greg C

2007-01-01

Full Text Available This paper proposes an approach based on a state-space model for learning the user concepts in image retrieval. We first design a scheme of region-based image representation based on concept units, which are integrated with different types of feature spaces and with different region scales of image segmentation. The design of the concept units aims at describing similar characteristics at a certain perspective among relevant images. We present the details of our proposed approach based on a state-space model for interactive image retrieval, including likelihood and transition models, and we also describe some experiments that show the efficacy of our proposed model. This work demonstrates the feasibility of using a state-space model to estimate the user intuition in image retrieval.

A new method for information retrieval in two-dimensional grating-based X-ray phase contrast imaging

International Nuclear Information System (INIS)

Wang Zhi-Li; Gao Kun; Chen Jian; Ge Xin; Tian Yang-Chao; Wu Zi-Yu; Zhu Pei-Ping

2012-01-01

Grating-based X-ray phase contrast imaging has been demonstrated to be an extremely powerful phase-sensitive imaging technique. By using two-dimensional (2D) gratings, the observable contrast is extended to two refraction directions. Recently, we have developed a novel reverse-projection (RP) method, which is capable of retrieving the object information efficiently with one-dimensional (1D) grating-based phase contrast imaging. In this contribution, we present its extension to the 2D grating-based X-ray phase contrast imaging, named the two-dimensional reverse-projection (2D-RP) method, for information retrieval. The method takes into account the nonlinear contributions of two refraction directions and allows the retrieval of the absorption, the horizontal and the vertical refraction images. The obtained information can be used for the reconstruction of the three-dimensional phase gradient field, and for an improved phase map retrieval and reconstruction. Numerical experiments are carried out, and the results confirm the validity of the 2D-RP method

Encryption of QR code and grayscale image in interference-based scheme with high quality retrieval and silhouette problem removal

Science.gov (United States)

Qin, Yi; Wang, Hongjuan; Wang, Zhipeng; Gong, Qiong; Wang, Danchen

2016-09-01

In optical interference-based encryption (IBE) scheme, the currently available methods have to employ the iterative algorithms in order to encrypt two images and retrieve cross-talk free decrypted images. In this paper, we shall show that this goal can be achieved via an analytical process if one of the two images is QR code. For decryption, the QR code is decrypted in the conventional architecture and the decryption has a noisy appearance. Nevertheless, the robustness of QR code against noise enables the accurate acquisition of its content from the noisy retrieval, as a result of which the primary QR code can be exactly regenerated. Thereafter, a novel optical architecture is proposed to recover the grayscale image by aid of the QR code. In addition, the proposal has totally eliminated the silhouette problem existing in the previous IBE schemes, and its effectiveness and feasibility have been demonstrated by numerical simulations.

System for accessing a collection of histology images using content-based strategies

International Nuclear Information System (INIS)

Gonzalez F; Caicedo J C; Cruz Roa A; Camargo, J; Spinel, C

2010-01-01

Histology images are an important resource for research, education and medical practice. The availability of image collections with reference purposes is limited to printed formats such as books and specialized journals. When histology image sets are published in digital formats, they are composed of some tens of images that do not represent the wide diversity of biological structures that can be found in fundamental tissues; making a complete histology image collection available to the general public having a great impact on research and education in different areas such as medicine, biology and natural sciences. This work presents the acquisition process of a histology image collection with 20,000 samples in digital format, from tissue processing to digital image capturing. The main purpose of collecting these images is to make them available as reference material to the academic community. In addition, this paper presents the design and architecture of a system to query and explore the image collection, using content-based image retrieval tools and text-based search on the annotations provided by experts. The system also offers novel image visualization methods to allow easy identification of interesting images among hundreds of possible pictures. The system has been developed using a service-oriented architecture and allows web-based access in http://www.informed.unal.edu.co

Smart Images Search based on Visual Features Fusion

International Nuclear Information System (INIS)

Saad, M.H.

2013-01-01

Image search engines attempt to give fast and accurate access to the wide range of the huge amount images available on the Internet. There have been a number of efforts to build search engines based on the image content to enhance search results. Content-Based Image Retrieval (CBIR) systems have achieved a great interest since multimedia files, such as images and videos, have dramatically entered our lives throughout the last decade. CBIR allows automatically extracting target images according to objective visual contents of the image itself, for example its shapes, colors and textures to provide more accurate ranking of the results. The recent approaches of CBIR differ in terms of which image features are extracted to be used as image descriptors for matching process. This thesis proposes improvements of the efficiency and accuracy of CBIR systems by integrating different types of image features. This framework addresses efficient retrieval of images in large image collections. A comparative study between recent CBIR techniques is provided. According to this study; image features need to be integrated to provide more accurate description of image content and better image retrieval accuracy. In this context, this thesis presents new image retrieval approaches that provide more accurate retrieval accuracy than previous approaches. The first proposed image retrieval system uses color, texture and shape descriptors to form the global features vector. This approach integrates the yc b c r color histogram as a color descriptor, the modified Fourier descriptor as a shape descriptor and modified Edge Histogram as a texture descriptor in order to enhance the retrieval results. The second proposed approach integrates the global features vector, which is used in the first approach, with the SURF salient point technique as local feature. The nearest neighbor matching algorithm with a proposed similarity measure is applied to determine the final image rank. The second approach

Density-based retrieval from high-similarity image databases

DEFF Research Database (Denmark)

Hansen, Michael Edberg; Carstensen, Jens Michael

2004-01-01

Many image classification problems can fruitfully be thought of as image retrieval in a "high similarity image database" (HSID) characterized by being tuned towards a specific application and having a high degree of visual similarity between entries that should be distinguished. We introduce a me...

Optical image encryption using password key based on phase retrieval algorithm

Science.gov (United States)

Zhao, Tieyu; Ran, Qiwen; Yuan, Lin; Chi, Yingying; Ma, Jing

2016-04-01

A novel optical image encryption system is proposed using password key based on phase retrieval algorithm (PRA). In the encryption process, a shared image is taken as a symmetric key and the plaintext is encoded into the phase-only mask based on the iterative PRA. The linear relationship between the plaintext and ciphertext is broken using the password key, which can resist the known plaintext attack. The symmetric key and the retrieved phase are imported into the input plane and Fourier plane of 4f system during the decryption, respectively, so as to obtain the plaintext on the CCD. Finally, we analyse the key space of the password key, and the results show that the proposed scheme can resist a brute force attack due to the flexibility of the password key.

Modeling multiple visual words assignment for bag-of-features based medical image retrieval

KAUST Repository

Wang, Jim Jing-Yan

2012-01-01

In this paper, we investigate the bag-of-features based medical image retrieval methods, which represent an image as a collection of local features, such as image patch and key points with SIFT descriptor. To improve the bag-of-features method, we first model the assignment of local descriptor as contribution functions, and then propose a new multiple assignment strategy. By assuming the local feature can be reconstructed by its neighboring visual words in vocabulary, we solve the reconstruction weights as a QP problem and then use the solved weights as contribution functions, which results in a new assignment method called the QP assignment. We carry our experiments on ImageCLEFmed datasets. Experiments\\' results show that our proposed method exceeds the performances of traditional solutions and works well for the bag-of-features based medical image retrieval tasks.

Modeling multiple visual words assignment for bag-of-features based medical image retrieval

KAUST Repository

Wang, Jim Jing-Yan; Almasri, Islam

2012-01-01

In this paper, we investigate the bag-of-features based medical image retrieval methods, which represent an image as a collection of local features, such as image patch and key points with SIFT descriptor. To improve the bag-of-features method, we first model the assignment of local descriptor as contribution functions, and then propose a new multiple assignment strategy. By assuming the local feature can be reconstructed by its neighboring visual words in vocabulary, we solve the reconstruction weights as a QP problem and then use the solved weights as contribution functions, which results in a new assignment method called the QP assignment. We carry our experiments on ImageCLEFmed datasets. Experiments' results show that our proposed method exceeds the performances of traditional solutions and works well for the bag-of-features based medical image retrieval tasks.

Large-Scale Partial-Duplicate Image Retrieval and Its Applications

Science.gov (United States)

2016-04-23

tree based image retrieval , a semantic-aware co-indexing algorithm is proposed to jointly embed two strong cues into the inverted indexes: 1) local...based image retrieval , a semantic-aware co-indexing algorithm is proposed to jointly embed two strong cues into the inverted indexes: 1) local...Distribution Unlimited UU UU UU UU 23-04-2016 23-Jan-2012 22-Jan-2016 Final Report: Large-Scale Partial-Duplicate Image Retrieval and Its Applications

Automatic content linking: Speech-based just-in-time retrieval for multimedia archives

NARCIS (Netherlands)

Popescu-Belis, A.; Kilgour, J.; Poller, P.; Nanchen, A.; Boertjes, E.; Wit, J. de

2010-01-01

The Automatic Content Linking Device monitors a conversation and uses automatically recognized words to retrieve documents that are of potential use to the participants. The document set includes project related reports or emails, transcribed snippets of past meetings, and websites. Retrieval

View-based 3-D object retrieval

CERN Document Server

Gao, Yue

2014-01-01

Content-based 3-D object retrieval has attracted extensive attention recently and has applications in a variety of fields, such as, computer-aided design, tele-medicine,mobile multimedia, virtual reality, and entertainment. The development of efficient and effective content-based 3-D object retrieval techniques has enabled the use of fast 3-D reconstruction and model design. Recent technical progress, such as the development of camera technologies, has made it possible to capture the views of 3-D objects. As a result, view-based 3-D object retrieval has become an essential but challenging res

Model-based magnetization retrieval from holographic phase images

Energy Technology Data Exchange (ETDEWEB)

Röder, Falk, E-mail: f.roeder@hzdr.de [Helmholtz-Zentrum Dresden-Rossendorf, Institut für Ionenstrahlphysik und Materialforschung, Bautzner Landstr. 400, D-01328 Dresden (Germany); Triebenberg Labor, Institut für Strukturphysik, Technische Universität Dresden, D-01062 Dresden (Germany); Vogel, Karin [Triebenberg Labor, Institut für Strukturphysik, Technische Universität Dresden, D-01062 Dresden (Germany); Wolf, Daniel [Helmholtz-Zentrum Dresden-Rossendorf, Institut für Ionenstrahlphysik und Materialforschung, Bautzner Landstr. 400, D-01328 Dresden (Germany); Triebenberg Labor, Institut für Strukturphysik, Technische Universität Dresden, D-01062 Dresden (Germany); Hellwig, Olav [Helmholtz-Zentrum Dresden-Rossendorf, Institut für Ionenstrahlphysik und Materialforschung, Bautzner Landstr. 400, D-01328 Dresden (Germany); AG Magnetische Funktionsmaterialien, Institut für Physik, Technische Universität Chemnitz, D-09126 Chemnitz (Germany); HGST, A Western Digital Company, 3403 Yerba Buena Rd., San Jose, CA 95135 (United States); Wee, Sung Hun [HGST, A Western Digital Company, 3403 Yerba Buena Rd., San Jose, CA 95135 (United States); Wicht, Sebastian; Rellinghaus, Bernd [IFW Dresden, Institute for Metallic Materials, P.O. Box 270116, D-01171 Dresden (Germany)

2017-05-15

The phase shift of the electron wave is a useful measure for the projected magnetic flux density of magnetic objects at the nanometer scale. More important for materials science, however, is the knowledge about the magnetization in a magnetic nano-structure. As demonstrated here, a dominating presence of stray fields prohibits a direct interpretation of the phase in terms of magnetization modulus and direction. We therefore present a model-based approach for retrieving the magnetization by considering the projected shape of the nano-structure and assuming a homogeneous magnetization therein. We apply this method to FePt nano-islands epitaxially grown on a SrTiO{sub 3} substrate, which indicates an inclination of their magnetization direction relative to the structural easy magnetic [001] axis. By means of this real-world example, we discuss prospects and limits of this approach. - Highlights: • Retrieval of the magnetization from holographic phase images. • Magnetostatic model constructed for a magnetic nano-structure. • Decomposition into homogeneously magnetized components. • Discretization of a each component by elementary cuboids. • Analytic solution for the phase of a magnetized cuboid considered. • Fitting a set of magnetization vectors to experimental phase images.

The Wikipedia Image Retrieval Task

NARCIS (Netherlands)

T. Tsikrika (Theodora); J. Kludas

2010-01-01

htmlabstractThe wikipedia image retrieval task at ImageCLEF provides a testbed for the system-oriented evaluation of visual information retrieval from a collection of Wikipedia images. The aim is to investigate the effectiveness of retrieval approaches that exploit textual and visual evidence in the

Phase Retrieval Using a Genetic Algorithm on the Systematic Image-Based Optical Alignment Testbed

Science.gov (United States)

Taylor, Jaime R.

2003-01-01

NASA s Marshall Space Flight Center s Systematic Image-Based Optical Alignment (SIBOA) Testbed was developed to test phase retrieval algorithms and hardware techniques. Individuals working with the facility developed the idea of implementing phase retrieval by breaking the determination of the tip/tilt of each mirror apart from the piston motion (or translation) of each mirror. Presented in this report is an algorithm that determines the optimal phase correction associated only with the piston motion of the mirrors. A description of the Phase Retrieval problem is first presented. The Systematic Image-Based Optical Alignment (SIBOA) Testbeb is then described. A Discrete Fourier Transform (DFT) is necessary to transfer the incoming wavefront (or estimate of phase error) into the spatial frequency domain to compare it with the image. A method for reducing the DFT to seven scalar/matrix multiplications is presented. A genetic algorithm is then used to search for the phase error. The results of this new algorithm on a test problem are presented.

Genetic Algorithm Phase Retrieval for the Systematic Image-Based Optical Alignment Testbed

Science.gov (United States)

Taylor, Jaime; Rakoczy, John; Steincamp, James

2003-01-01

Phase retrieval requires calculation of the real-valued phase of the pupil fimction from the image intensity distribution and characteristics of an optical system. Genetic 'algorithms were used to solve two one-dimensional phase retrieval problem. A GA successfully estimated the coefficients of a polynomial expansion of the phase when the number of coefficients was correctly specified. A GA also successfully estimated the multiple p h e s of a segmented optical system analogous to the seven-mirror Systematic Image-Based Optical Alignment (SIBOA) testbed located at NASA s Marshall Space Flight Center. The SIBOA testbed was developed to investigate phase retrieval techniques. Tiphilt and piston motions of the mirrors accomplish phase corrections. A constant phase over each mirror can be achieved by an independent tip/tilt correction: the phase Conection term can then be factored out of the Discrete Fourier Tranform (DFT), greatly reducing computations.

Psychophysical studies of the performance of an image database retrieval system

Science.gov (United States)

Papathomas, Thomas V.; Conway, Tiffany E.; Cox, Ingemar J.; Ghosn, Joumana; Miller, Matt L.; Minka, Thomas P.; Yianilos, Peter N.

1998-07-01

We describe psychophysical experiments conducted to study PicHunter, a content-based image retrieval (CBIR) system. Experiment 1 studies the importance of using (a) semantic information, (2) memory of earlier input and (3) relative, rather than absolute, judgements of image similarity. The target testing paradigm is used in which a user must search for an image identical to a target. We find that the best performance comes from a version of PicHunter that uses only semantic cues, with memory and relative similarity judgements. Second best is use of both pictorial and semantic cues, with memory and relative similarity judgements. Most reports of CBIR systems provide only qualitative measures of performance based on how similar retrieved images are to a target. Experiment 2 puts PicHunter into this context with a more rigorous test. We first establish a baseline for our database by measuring the time required to find an image that is similar to a target when the images are presented in random order. Although PicHunter's performance is measurably better than this, the test is weak because even random presentation of images yields reasonably short search times. This casts doubt on the strength of results given in other reports where no baseline is established.

Unified modeling language and design of a case-based retrieval system in medical imaging.

Science.gov (United States)

LeBozec, C; Jaulent, M C; Zapletal, E; Degoulet, P

1998-01-01

One goal of artificial intelligence research into case-based reasoning (CBR) systems is to develop approaches for designing useful and practical interactive case-based environments. Explaining each step of the design of the case-base and of the retrieval process is critical for the application of case-based systems to the real world. We describe herein our approach to the design of IDEM--Images and Diagnosis from Examples in Medicine--a medical image case-based retrieval system for pathologists. Our approach is based on the expressiveness of an object-oriented modeling language standard: the Unified Modeling Language (UML). We created a set of diagrams in UML notation illustrating the steps of the CBR methodology we used. The key aspect of this approach was selecting the relevant objects of the system according to user requirements and making visualization of cases and of the components of the case retrieval process. Further evaluation of the expressiveness of the design document is required but UML seems to be a promising formalism, improving the communication between the developers and users.

Quantification of signal detection performance degradation induced by phase-retrieval in propagation-based x-ray phase-contrast imaging

Science.gov (United States)

Chou, Cheng-Ying; Anastasio, Mark A.

2016-04-01

In propagation-based X-ray phase-contrast (PB XPC) imaging, the measured image contains a mixture of absorption- and phase-contrast. To obtain separate images of the projected absorption and phase (i.e., refractive) properties of a sample, phase retrieval methods can be employed. It has been suggested that phase-retrieval can always improve image quality in PB XPC imaging. However, when objective (task-based) measures of image quality are employed, this is not necessarily true and phase retrieval can be detrimental. In this work, signal detection theory is utilized to quantify the performance of a Hotelling observer (HO) for detecting a known signal in a known background. Two cases are considered. In the first case, the HO acts directly on the measured intensity data. In the second case, the HO acts on either the retrieved phase or absorption image. We demonstrate that the performance of the HO is superior when acting on the measured intensity data. The loss of task-specific information induced by phase-retrieval is quantified by computing the efficiency of the HO as the ratio of the test statistic signal-to-noise ratio (SNR) for the two cases. The effect of the system geometry on this efficiency is systematically investigated. Our findings confirm that phase-retrieval can impair signal detection performance in XPC imaging.

Multimedia content analysis, management and retrieval: trends and challenges

Science.gov (United States)

Hanjalic, Alan; Sebe, Nicu; Chang, Edward

2006-01-01

Recent advances in computing, communications and storage technology have made multimedia data become prevalent. Multimedia has gained enormous potential in improving the processes in a wide range of fields, such as advertising and marketing, education and training, entertainment, medicine, surveillance, wearable computing, biometrics, and remote sensing. Rich content of multimedia data, built through the synergies of the information contained in different modalities, calls for new and innovative methods for modeling, processing, mining, organizing, and indexing of this data for effective and efficient searching, retrieval, delivery, management and sharing of multimedia content, as required by the applications in the abovementioned fields. The objective of this paper is to present our views on the trends that should be followed when developing such methods, to elaborate on the related research challenges, and to introduce the new conference, Multimedia Content Analysis, Management and Retrieval, as a premium venue for presenting and discussing these methods with the scientific community. Starting from 2006, the conference will be held annually as a part of the IS&T/SPIE Electronic Imaging event.

A novel 3D shape descriptor for automatic retrieval of anatomical structures from medical images

Science.gov (United States)

Nunes, Fátima L. S.; Bergamasco, Leila C. C.; Delmondes, Pedro H.; Valverde, Miguel A. G.; Jackowski, Marcel P.

2017-03-01

Content-based image retrieval (CBIR) aims at retrieving from a database objects that are similar to an object provided by a query, by taking into consideration a set of extracted features. While CBIR has been widely applied in the two-dimensional image domain, the retrieval of3D objects from medical image datasets using CBIR remains to be explored. In this context, the development of descriptors that can capture information specific to organs or structures is desirable. In this work, we focus on the retrieval of two anatomical structures commonly imaged by Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) techniques, the left ventricle of the heart and blood vessels. Towards this aim, we developed the Area-Distance Local Descriptor (ADLD), a novel 3D local shape descriptor that employs mesh geometry information, namely facet area and distance from centroid to surface, to identify shape changes. Because ADLD only considers surface meshes extracted from volumetric medical images, it substantially diminishes the amount of data to be analyzed. A 90% precision rate was obtained when retrieving both convex (left ventricle) and non-convex structures (blood vessels), allowing for detection of abnormalities associated with changes in shape. Thus, ADLD has the potential to aid in the diagnosis of a wide range of vascular and cardiac diseases.

High sensitivity phase retrieval method in grating-based x-ray phase contrast imaging

Energy Technology Data Exchange (ETDEWEB)

Wu, Zhao; Gao, Kun; Chen, Jian; Wang, Dajiang; Wang, Shenghao; Chen, Heng; Bao, Yuan; Shao, Qigang; Wang, Zhili, E-mail: wangnsrl@ustc.edu.cn [National Synchrotron Radiation Laboratory, University of Science and Technology of China, Hefei 230029 (China); Zhang, Kai [Institute of High Energy Physics, Chinese Academy of Sciences, Beijing 100049 (China); Zhu, Peiping; Wu, Ziyu, E-mail: wuzy@ustc.edu.cn [National Synchrotron Radiation Laboratory, University of Science and Technology of China, Hefei 230029, China and Institute of High Energy Physics, Chinese Academy of Sciences, Beijing 100049 (China)

2015-02-15

Purpose: Grating-based x-ray phase contrast imaging is considered as one of the most promising techniques for future medical imaging. Many different methods have been developed to retrieve phase signal, among which the phase stepping (PS) method is widely used. However, further practical implementations are hindered, due to its complex scanning mode and high radiation dose. In contrast, the reverse projection (RP) method is a novel fast and low dose extraction approach. In this contribution, the authors present a quantitative analysis of the noise properties of the refraction signals retrieved by the two methods and compare their sensitivities. Methods: Using the error propagation formula, the authors analyze theoretically the signal-to-noise ratios (SNRs) of the refraction images retrieved by the two methods. Then, the sensitivities of the two extraction methods are compared under an identical exposure dose. Numerical experiments are performed to validate the theoretical results and provide some quantitative insight. Results: The SNRs of the two methods are both dependent on the system parameters, but in different ways. Comparison between their sensitivities reveals that for the refraction signal, the RP method possesses a higher sensitivity, especially in the case of high visibility and/or at the edge of the object. Conclusions: Compared with the PS method, the RP method has a superior sensitivity and provides refraction images with a higher SNR. Therefore, one can obtain highly sensitive refraction images in grating-based phase contrast imaging. This is very important for future preclinical and clinical implementations.

High sensitivity phase retrieval method in grating-based x-ray phase contrast imaging

International Nuclear Information System (INIS)

Wu, Zhao; Gao, Kun; Chen, Jian; Wang, Dajiang; Wang, Shenghao; Chen, Heng; Bao, Yuan; Shao, Qigang; Wang, Zhili; Zhang, Kai; Zhu, Peiping; Wu, Ziyu

2015-01-01

Purpose: Grating-based x-ray phase contrast imaging is considered as one of the most promising techniques for future medical imaging. Many different methods have been developed to retrieve phase signal, among which the phase stepping (PS) method is widely used. However, further practical implementations are hindered, due to its complex scanning mode and high radiation dose. In contrast, the reverse projection (RP) method is a novel fast and low dose extraction approach. In this contribution, the authors present a quantitative analysis of the noise properties of the refraction signals retrieved by the two methods and compare their sensitivities. Methods: Using the error propagation formula, the authors analyze theoretically the signal-to-noise ratios (SNRs) of the refraction images retrieved by the two methods. Then, the sensitivities of the two extraction methods are compared under an identical exposure dose. Numerical experiments are performed to validate the theoretical results and provide some quantitative insight. Results: The SNRs of the two methods are both dependent on the system parameters, but in different ways. Comparison between their sensitivities reveals that for the refraction signal, the RP method possesses a higher sensitivity, especially in the case of high visibility and/or at the edge of the object. Conclusions: Compared with the PS method, the RP method has a superior sensitivity and provides refraction images with a higher SNR. Therefore, one can obtain highly sensitive refraction images in grating-based phase contrast imaging. This is very important for future preclinical and clinical implementations

Content-based Image Hiding Method for Secure Network Biometric Verification

Directory of Open Access Journals (Sweden)

Xiangjiu Che

2011-08-01

Full Text Available For secure biometric verification, most existing methods embed biometric information directly into the cover image, but content correlation analysis between the biometric image and the cover image is often ignored. In this paper, we propose a novel biometric image hiding approach based on the content correlation analysis to protect the network-based transmitted image. By using principal component analysis (PCA, the content correlation between the biometric image and the cover image is firstly analyzed. Then based on particle swarm optimization (PSO algorithm, some regions of the cover image are selected to represent the biometric image, in which the cover image can carry partial content of the biometric image. As a result of the correlation analysis, the unrepresented part of the biometric image is embedded into the cover image by using the discrete wavelet transform (DWT. Combined with human visual system (HVS model, this approach makes the hiding result perceptually invisible. The extensive experimental results demonstrate that the proposed hiding approach is robust against some common frequency and geometric attacks; it also provides an effective protection for the secure biometric verification.

Application of content-based image compression to telepathology

Science.gov (United States)

Varga, Margaret J.; Ducksbury, Paul G.; Callagy, Grace

2002-05-01

Telepathology is a means of practicing pathology at a distance, viewing images on a computer display rather than directly through a microscope. Without compression, images take too long to transmit to a remote location and are very expensive to store for future examination. However, to date the use of compressed images in pathology remains controversial. This is because commercial image compression algorithms such as JPEG achieve data compression without knowledge of the diagnostic content. Often images are lossily compressed at the expense of corrupting informative content. None of the currently available lossy compression techniques are concerned with what information has been preserved and what data has been discarded. Their sole objective is to compress and transmit the images as fast as possible. By contrast, this paper presents a novel image compression technique, which exploits knowledge of the slide diagnostic content. This 'content based' approach combines visually lossless and lossy compression techniques, judiciously applying each in the appropriate context across an image so as to maintain 'diagnostic' information while still maximising the possible compression. Standard compression algorithms, e.g. wavelets, can still be used, but their use in a context sensitive manner can offer high compression ratios and preservation of diagnostically important information. When compared with lossless compression the novel content-based approach can potentially provide the same degree of information with a smaller amount of data. When compared with lossy compression it can provide more information for a given amount of compression. The precise gain in the compression performance depends on the application (e.g. database archive or second opinion consultation) and the diagnostic content of the images.

An intelligent framework for medical image retrieval using MDCT and multi SVM.

Science.gov (United States)

Balan, J A Alex Rajju; Rajan, S Edward

2014-01-01

Volumes of medical images are rapidly generated in medical field and to manage them effectively has become a great challenge. This paper studies the development of innovative medical image retrieval based on texture features and accuracy. The objective of the paper is to analyze the image retrieval based on diagnosis of healthcare management systems. This paper traces the development of innovative medical image retrieval to estimate both the image texture features and accuracy. The texture features of medical images are extracted using MDCT and multi SVM. Both the theoretical approach and the simulation results revealed interesting observations and they were corroborated using MDCT coefficients and SVM methodology. All attempts to extract the data about the image in response to the query has been computed successfully and perfect image retrieval performance has been obtained. Experimental results on a database of 100 trademark medical images show that an integrated texture feature representation results in 98% of the images being retrieved using MDCT and multi SVM. Thus we have studied a multiclassification technique based on SVM which is prior suitable for medical images. The results show the retrieval accuracy of 98%, 99% for different sets of medical images with respect to the class of image.

Robustness of phase retrieval methods in x-ray phase contrast imaging: A comparison

International Nuclear Information System (INIS)

Yan, Aimin; Wu, Xizeng; Liu, Hong

2011-01-01

Purpose: The robustness of the phase retrieval methods is of critical importance for limiting and reducing radiation doses involved in x-ray phase contrast imaging. This work is to compare the robustness of two phase retrieval methods by analyzing the phase maps retrieved from the experimental images of a phantom. Methods: Two phase retrieval methods were compared. One method is based on the transport of intensity equation (TIE) for phase contrast projections, and the TIE-based method is the most commonly used method for phase retrieval in the literature. The other is the recently developed attenuation-partition based (AP-based) phase retrieval method. The authors applied these two methods to experimental projection images of an air-bubble wrap phantom for retrieving the phase map of the bubble wrap. The retrieved phase maps obtained by using the two methods are compared. Results: In the wrap's phase map retrieved by using the TIE-based method, no bubble is recognizable, hence, this method failed completely for phase retrieval from these bubble wrap images. Even with the help of the Tikhonov regularization, the bubbles are still hardly visible and buried in the cluttered background in the retrieved phase map. The retrieved phase values with this method are grossly erroneous. In contrast, in the wrap's phase map retrieved by using the AP-based method, the bubbles are clearly recovered. The retrieved phase values with the AP-based method are reasonably close to the estimate based on the thickness-based measurement. The authors traced these stark performance differences of the two methods to their different techniques employed to deal with the singularity problem involved in the phase retrievals. Conclusions: This comparison shows that the conventional TIE-based phase retrieval method, regardless if Tikhonov regularization is used or not, is unstable against the noise in the wrap's projection images, while the AP-based phase retrieval method is shown in these

Wave Optics Based LEO-LEO Radio Occultation Retrieval

DEFF Research Database (Denmark)

von Benzon, Hans-Henrik; Høeg, Per

2016-01-01

of the atmospheric products such as the correct water vapor content in the atmosphere. These limitations can be overcome when a proper selected range of high frequency waves are used to probe the atmosphere. Probing frequencies close to the absorption line of water vapor have been included, thus allowing...... the retrieval of the water vapor content. Selecting the correct probing frequencies would make it possible to retrieve other information such as the content of ozone. The retrieval is performed through a number of processing steps which are based on the Full Spectrum Inversion (FSI) technique. The retrieval...... optics based retrieval chain is used on a number of examples and the retrieved atmospheric parameters are compared to the parameters from a global ECMWF analysis model. This model is used in a forward propagator that simulates the electromagnetic field amplitudes and phases at the receiver on board...

Benchmarking, Research, Development, and Support for ORNL Automated Image and Signature Retrieval (AIR/ASR) Technologies

Energy Technology Data Exchange (ETDEWEB)

Tobin, K.W.

2004-06-01

This report describes the results of a Cooperative Research and Development Agreement (CRADA) with Applied Materials, Inc. (AMAT) of Santa Clara, California. This project encompassed the continued development and integration of the ORNL Automated Image Retrieval (AIR) technology, and an extension of the technology denoted Automated Signature Retrieval (ASR), and other related technologies with the Defect Source Identification (DSI) software system that was under development by AMAT at the time this work was performed. In the semiconductor manufacturing environment, defect imagery is used to diagnose problems in the manufacturing line, train yield management engineers, and examine historical data for trends. Image management in semiconductor data systems is a growing cause of concern in the industry as fabricators are now collecting up to 20,000 images each week. In response to this concern, researchers at the Oak Ridge National Laboratory (ORNL) developed a semiconductor-specific content-based image retrieval method and system, also known as AIR. The system uses an image-based query-by-example method to locate and retrieve similar imagery from a database of digital imagery using visual image characteristics. The query method is based on a unique architecture that takes advantage of the statistical, morphological, and structural characteristics of image data, generated by inspection equipment in industrial applications. The system improves the manufacturing process by allowing rapid access to historical records of similar events so that errant process equipment can be isolated and corrective actions can be quickly taken to improve yield. The combined ORNL and AMAT technology is referred to hereafter as DSI-AIR and DSI-ASR.

Robust retrieval of fine art paintings

Science.gov (United States)

Smolka, Bogdan; Lukac, Rastislav; Plataniotis, Konstantinos N.; Venetsanopoulos, Anastasios N.

2003-10-01

The rapid growth of image archives increases the need for efficient and fast tools that can retrieve and search through large amount of visual data. In this paper we propose an efficient method of extracting the image color content, which serves as an image digital signature, allowing to efficiently index and retrieve the content of large, heterogeneous multimedia databases. We apply the proposed method for the retrieval of images from the WEBMUSEUM Internet database, containing the collection of fine art images and show that the new method of image color representation is robust to image distorsions caused by resizing and compression and can be incorporated into existing retrieval systems which exploit the information on color content in digital images.

Physical retrieval of precipitation water contents from Special Sensor Microwave/Imager (SSM/I) data. Part 2: Retrieval method and applications (report version)

Science.gov (United States)

Olson, William S.

1990-01-01

A physical retrieval method for estimating precipitating water distributions and other geophysical parameters based upon measurements from the DMSP-F8 SSM/I is developed. Three unique features of the retrieval method are (1) sensor antenna patterns are explicitly included to accommodate varying channel resolution; (2) precipitation-brightness temperature relationships are quantified using the cloud ensemble/radiative parameterization; and (3) spatial constraints are imposed for certain background parameters, such as humidity, which vary more slowly in the horizontal than the cloud and precipitation water contents. The general framework of the method will facilitate the incorporation of measurements from the SSMJT, SSM/T-2 and geostationary infrared measurements, as well as information from conventional sources (e.g., radiosondes) or numerical forecast model fields.

Conjunctive patches subspace learning with side information for collaborative image retrieval.

Science.gov (United States)

Zhang, Lining; Wang, Lipo; Lin, Weisi

2012-08-01

Content-Based Image Retrieval (CBIR) has attracted substantial attention during the past few years for its potential practical applications to image management. A variety of Relevance Feedback (RF) schemes have been designed to bridge the semantic gap between the low-level visual features and the high-level semantic concepts for an image retrieval task. Various Collaborative Image Retrieval (CIR) schemes aim to utilize the user historical feedback log data with similar and dissimilar pairwise constraints to improve the performance of a CBIR system. However, existing subspace learning approaches with explicit label information cannot be applied for a CIR task, although the subspace learning techniques play a key role in various computer vision tasks, e.g., face recognition and image classification. In this paper, we propose a novel subspace learning framework, i.e., Conjunctive Patches Subspace Learning (CPSL) with side information, for learning an effective semantic subspace by exploiting the user historical feedback log data for a CIR task. The CPSL can effectively integrate the discriminative information of labeled log images, the geometrical information of labeled log images and the weakly similar information of unlabeled images together to learn a reliable subspace. We formally formulate this problem into a constrained optimization problem and then present a new subspace learning technique to exploit the user historical feedback log data. Extensive experiments on both synthetic data sets and a real-world image database demonstrate the effectiveness of the proposed scheme in improving the performance of a CBIR system by exploiting the user historical feedback log data.

H-Metric: Characterizing Image Datasets via Homogenization Based on KNN-Queries

Directory of Open Access Journals (Sweden)

Welington M da Silva

2012-01-01

Full Text Available Precision-Recall is one of the main metrics for evaluating content-based image retrieval techniques. However, it does not provide an ample perception of the properties of an image dataset immersed in a metric space. In this work, we describe an alternative metric named H-Metric, which is determined along a sequence of controlled modifications in the image dataset. The process is named homogenization and works by altering the homogeneity characteristics of the classes of the images. The result is a process that measures how hard it is to deal with a set of images in respect to content-based retrieval, offering support in the task of analyzing configurations of distance functions and of features extractors.

Complex event processing for content-based text, image, and video retrieval

NARCIS (Netherlands)

Bowman, E.K.; Broome, B.D.; Holland, V.M.; Summers-Stay, D.; Rao, R.M.; Duselis, J.; Howe, J.; Madahar, B.K.; Boury-Brisset, A.C.; Forrester, B.; Kwantes, P.; Burghouts, G.; Huis, J. van; Mulayim, A.Y.

2016-01-01

This report summarizes the findings of an exploratory team of the North Atlantic Treaty Organization (NATO) Information Systems Technology panel into Content-Based Analytics (CBA). The team carried out a technical review into the current status of theoretical and practical developments of methods,

Retinal image quality assessment based on image clarity and content

Science.gov (United States)

Abdel-Hamid, Lamiaa; El-Rafei, Ahmed; El-Ramly, Salwa; Michelson, Georg; Hornegger, Joachim

2016-09-01

Retinal image quality assessment (RIQA) is an essential step in automated screening systems to avoid misdiagnosis caused by processing poor quality retinal images. A no-reference transform-based RIQA algorithm is introduced that assesses images based on five clarity and content quality issues: sharpness, illumination, homogeneity, field definition, and content. Transform-based RIQA algorithms have the advantage of considering retinal structures while being computationally inexpensive. Wavelet-based features are proposed to evaluate the sharpness and overall illumination of the images. A retinal saturation channel is designed and used along with wavelet-based features for homogeneity assessment. The presented sharpness and illumination features are utilized to assure adequate field definition, whereas color information is used to exclude nonretinal images. Several publicly available datasets of varying quality grades are utilized to evaluate the feature sets resulting in area under the receiver operating characteristic curve above 0.99 for each of the individual feature sets. The overall quality is assessed by a classifier that uses the collective features as an input vector. The classification results show superior performance of the algorithm in comparison to other methods from literature. Moreover, the algorithm addresses efficiently and comprehensively various quality issues and is suitable for automatic screening systems.

Online Hashing for Scalable Remote Sensing Image Retrieval

Directory of Open Access Journals (Sweden)

Peng Li

2018-05-01

Full Text Available Recently, hashing-based large-scale remote sensing (RS image retrieval has attracted much attention. Many new hashing algorithms have been developed and successfully applied to fast RS image retrieval tasks. However, there exists an important problem rarely addressed in the research literature of RS image hashing. The RS images are practically produced in a streaming manner in many real-world applications, which means the data distribution keeps changing over time. Most existing RS image hashing methods are batch-based models whose hash functions are learned once for all and kept fixed all the time. Therefore, the pre-trained hash functions might not fit the ever-growing new RS images. Moreover, the batch-based models have to load all the training images into memory for model learning, which consumes many computing and memory resources. To address the above deficiencies, we propose a new online hashing method, which learns and adapts its hashing functions with respect to the newly incoming RS images in terms of a novel online partial random learning scheme. Our hash model is updated in a sequential mode such that the representative power of the learned binary codes for RS images are improved accordingly. Moreover, benefiting from the online learning strategy, our proposed hashing approach is quite suitable for scalable real-world remote sensing image retrieval. Extensive experiments on two large-scale RS image databases under online setting demonstrated the efficacy and effectiveness of the proposed method.

Annotating image ROIs with text descriptions for multimodal biomedical document retrieval

Science.gov (United States)

You, Daekeun; Simpson, Matthew; Antani, Sameer; Demner-Fushman, Dina; Thoma, George R.

2013-01-01

Regions of interest (ROIs) that are pointed to by overlaid markers (arrows, asterisks, etc.) in biomedical images are expected to contain more important and relevant information than other regions for biomedical article indexing and retrieval. We have developed several algorithms that localize and extract the ROIs by recognizing markers on images. Cropped ROIs then need to be annotated with contents describing them best. In most cases accurate textual descriptions of the ROIs can be found from figure captions, and these need to be combined with image ROIs for annotation. The annotated ROIs can then be used to, for example, train classifiers that separate ROIs into known categories (medical concepts), or to build visual ontologies, for indexing and retrieval of biomedical articles. We propose an algorithm that pairs visual and textual ROIs that are extracted from images and figure captions, respectively. This algorithm based on dynamic time warping (DTW) clusters recognized pointers into groups, each of which contains pointers with identical visual properties (shape, size, color, etc.). Then a rule-based matching algorithm finds the best matching group for each textual ROI mention. Our method yields a precision and recall of 96% and 79%, respectively, when ground truth textual ROI data is used.

Fast DCNN based on FWT, intelligent dropout and layer skipping for image retrieval.

Science.gov (United States)

ElAdel, Asma; Zaied, Mourad; Amar, Chokri Ben

2017-11-01

Deep Convolutional Neural Network (DCNN) can be marked as a powerful tool for object and image classification and retrieval. However, the training stage of such networks is highly consuming in terms of storage space and time. Also, the optimization is still a challenging subject. In this paper, we propose a fast DCNN based on Fast Wavelet Transform (FWT), intelligent dropout and layer skipping. The proposed approach led to improve the image retrieval accuracy as well as the searching time. This was possible thanks to three key advantages: First, the rapid way to compute the features using FWT. Second, the proposed intelligent dropout method is based on whether or not a unit is efficiently and not randomly selected. Third, it is possible to classify the image using efficient units of earlier layer(s) and skipping all the subsequent hidden layers directly to the output layer. Our experiments were performed on CIFAR-10 and MNIST datasets and the obtained results are very promising. Copyright © 2017 Elsevier Ltd. All rights reserved.

Computer-aided diagnosis of mammographic masses using geometric verification-based image retrieval

Science.gov (United States)

Li, Qingliang; Shi, Weili; Yang, Huamin; Zhang, Huimao; Li, Guoxin; Chen, Tao; Mori, Kensaku; Jiang, Zhengang

2017-03-01

Computer-Aided Diagnosis of masses in mammograms is an important indicator of breast cancer. The use of retrieval systems in breast examination is increasing gradually. In this respect, the method of exploiting the vocabulary tree framework and the inverted file in the mammographic masse retrieval have been proved high accuracy and excellent scalability. However it just considered the features in each image as a visual word and had ignored the spatial configurations of features. It greatly affect the retrieval performance. To overcome this drawback, we introduce the geometric verification method to retrieval in mammographic masses. First of all, we obtain corresponding match features based on the vocabulary tree framework and the inverted file. After that, we grasps the main point of local similarity characteristic of deformations in the local regions by constructing the circle regions of corresponding pairs. Meanwhile we segment the circle to express the geometric relationship of local matches in the area and generate the spatial encoding strictly. Finally we judge whether the matched features are correct or not, based on verifying the all spatial encoding are whether satisfied the geometric consistency. Experiments show the promising results of our approach.

Linear information retrieval method in X-ray grating-based phase contrast imaging and its interchangeability with tomographic reconstruction

Science.gov (United States)

Wu, Z.; Gao, K.; Wang, Z. L.; Shao, Q. G.; Hu, R. F.; Wei, C. X.; Zan, G. B.; Wali, F.; Luo, R. H.; Zhu, P. P.; Tian, Y. C.

2017-06-01

In X-ray grating-based phase contrast imaging, information retrieval is necessary for quantitative research, especially for phase tomography. However, numerous and repetitive processes have to be performed for tomographic reconstruction. In this paper, we report a novel information retrieval method, which enables retrieving phase and absorption information by means of a linear combination of two mutually conjugate images. Thanks to the distributive law of the multiplication as well as the commutative law and associative law of the addition, the information retrieval can be performed after tomographic reconstruction, thus simplifying the information retrieval procedure dramatically. The theoretical model of this method is established in both parallel beam geometry for Talbot interferometer and fan beam geometry for Talbot-Lau interferometer. Numerical experiments are also performed to confirm the feasibility and validity of the proposed method. In addition, we discuss its possibility in cone beam geometry and its advantages compared with other methods. Moreover, this method can also be employed in other differential phase contrast imaging methods, such as diffraction enhanced imaging, non-interferometric imaging, and edge illumination.

Mammogram retrieval through machine learning within BI-RADS standards.

Science.gov (United States)

Wei, Chia-Hung; Li, Yue; Huang, Pai Jung

2011-08-01

A content-based mammogram retrieval system can support usual comparisons made on images by physicians, answering similarity queries over images stored in the database. The importance of searching for similar mammograms lies in the fact that physicians usually try to recall similar cases by seeking images that are pathologically similar to a given image. This paper presents a content-based mammogram retrieval system, which employs a query example to search for similar mammograms in the database. In this system the mammographic lesions are interpreted based on their medical characteristics specified in the Breast Imaging Reporting and Data System (BI-RADS) standards. A hierarchical similarity measurement scheme based on a distance weighting function is proposed to model user's perception and maximizes the effectiveness of each feature in a mammographic descriptor. A machine learning approach based on support vector machines and user's relevance feedback is also proposed to analyze the user's information need in order to retrieve target images more accurately. Experimental results demonstrate that the proposed machine learning approach with Radial Basis Function (RBF) kernel function achieves the best performance among all tested ones. Furthermore, the results also show that the proposed learning approach can improve retrieval performance when applied to retrieve mammograms with similar mass and calcification lesions, respectively. Copyright © 2011 Elsevier Inc. All rights reserved.

A boosting framework for visuality-preserving distance metric learning and its application to medical image retrieval.

Science.gov (United States)

Yang, Liu; Jin, Rong; Mummert, Lily; Sukthankar, Rahul; Goode, Adam; Zheng, Bin; Hoi, Steven C H; Satyanarayanan, Mahadev

2010-01-01

Similarity measurement is a critical component in content-based image retrieval systems, and learning a good distance metric can significantly improve retrieval performance. However, despite extensive study, there are several major shortcomings with the existing approaches for distance metric learning that can significantly affect their application to medical image retrieval. In particular, "similarity" can mean very different things in image retrieval: resemblance in visual appearance (e.g., two images that look like one another) or similarity in semantic annotation (e.g., two images of tumors that look quite different yet are both malignant). Current approaches for distance metric learning typically address only one goal without consideration of the other. This is problematic for medical image retrieval where the goal is to assist doctors in decision making. In these applications, given a query image, the goal is to retrieve similar images from a reference library whose semantic annotations could provide the medical professional with greater insight into the possible interpretations of the query image. If the system were to retrieve images that did not look like the query, then users would be less likely to trust the system; on the other hand, retrieving images that appear superficially similar to the query but are semantically unrelated is undesirable because that could lead users toward an incorrect diagnosis. Hence, learning a distance metric that preserves both visual resemblance and semantic similarity is important. We emphasize that, although our study is focused on medical image retrieval, the problem addressed in this work is critical to many image retrieval systems. We present a boosting framework for distance metric learning that aims to preserve both visual and semantic similarities. The boosting framework first learns a binary representation using side information, in the form of labeled pairs, and then computes the distance as a weighted Hamming

Semantic-based surveillance video retrieval.

Science.gov (United States)

Hu, Weiming; Xie, Dan; Fu, Zhouyu; Zeng, Wenrong; Maybank, Steve

2007-04-01

Visual surveillance produces large amounts of video data. Effective indexing and retrieval from surveillance video databases are very important. Although there are many ways to represent the content of video clips in current video retrieval algorithms, there still exists a semantic gap between users and retrieval systems. Visual surveillance systems supply a platform for investigating semantic-based video retrieval. In this paper, a semantic-based video retrieval framework for visual surveillance is proposed. A cluster-based tracking algorithm is developed to acquire motion trajectories. The trajectories are then clustered hierarchically using the spatial and temporal information, to learn activity models. A hierarchical structure of semantic indexing and retrieval of object activities, where each individual activity automatically inherits all the semantic descriptions of the activity model to which it belongs, is proposed for accessing video clips and individual objects at the semantic level. The proposed retrieval framework supports various queries including queries by keywords, multiple object queries, and queries by sketch. For multiple object queries, succession and simultaneity restrictions, together with depth and breadth first orders, are considered. For sketch-based queries, a method for matching trajectories drawn by users to spatial trajectories is proposed. The effectiveness and efficiency of our framework are tested in a crowded traffic scene.

Context based multimedia information retrieval

DEFF Research Database (Denmark)

Mølgaard, Lasse Lohilahti

The large amounts of digital media becoming available require that new approaches are developed for retrieving, navigating and recommending the data to users in a way that refl ects how we semantically perceive the content. The thesis investigates ways to retrieve and present content for users...... topics from a large collection of the transcribed speech to improve retrieval of spoken documents. The context modelling is done using a variant of probabilistic latent semantic analysis (PLSA), to extract properties of the textual sources that refl ect how humans perceive context. We perform PLSA...... of Wikipedia , as well as text-based semantic similarity. The final aspect investigated is how to include some of the structured data available in Wikipedia to include temporal information. We show that a multiway extension of PLSA makes it possible to extract temporally meaningful topics, better than using...

A multimedia retrieval framework based on semi-supervised ranking and relevance feedback.

Science.gov (United States)

Yang, Yi; Nie, Feiping; Xu, Dong; Luo, Jiebo; Zhuang, Yueting; Pan, Yunhe

2012-04-01

We present a new framework for multimedia content analysis and retrieval which consists of two independent algorithms. First, we propose a new semi-supervised algorithm called ranking with Local Regression and Global Alignment (LRGA) to learn a robust Laplacian matrix for data ranking. In LRGA, for each data point, a local linear regression model is used to predict the ranking scores of its neighboring points. A unified objective function is then proposed to globally align the local models from all the data points so that an optimal ranking score can be assigned to each data point. Second, we propose a semi-supervised long-term Relevance Feedback (RF) algorithm to refine the multimedia data representation. The proposed long-term RF algorithm utilizes both the multimedia data distribution in multimedia feature space and the history RF information provided by users. A trace ratio optimization problem is then formulated and solved by an efficient algorithm. The algorithms have been applied to several content-based multimedia retrieval applications, including cross-media retrieval, image retrieval, and 3D motion/pose data retrieval. Comprehensive experiments on four data sets have demonstrated its advantages in precision, robustness, scalability, and computational efficiency.

Natural texture retrieval based on perceptual similarity measurement

Science.gov (United States)

Gao, Ying; Dong, Junyu; Lou, Jianwen; Qi, Lin; Liu, Jun

2018-04-01

A typical texture retrieval system performs feature comparison and might not be able to make human-like judgments of image similarity. Meanwhile, it is commonly known that perceptual texture similarity is difficult to be described by traditional image features. In this paper, we propose a new texture retrieval scheme based on texture perceptual similarity. The key of the proposed scheme is that prediction of perceptual similarity is performed by learning a non-linear mapping from image features space to perceptual texture space by using Random Forest. We test the method on natural texture dataset and apply it on a new wallpapers dataset. Experimental results demonstrate that the proposed texture retrieval scheme with perceptual similarity improves the retrieval performance over traditional image features.

Biomedical image representation approach using visualness and spatial information in a concept feature space for interactive region-of-interest-based retrieval.

Science.gov (United States)

Rahman, Md Mahmudur; Antani, Sameer K; Demner-Fushman, Dina; Thoma, George R

2015-10-01

This article presents an approach to biomedical image retrieval by mapping image regions to local concepts where images are represented in a weighted entropy-based concept feature space. The term "concept" refers to perceptually distinguishable visual patches that are identified locally in image regions and can be mapped to a glossary of imaging terms. Further, the visual significance (e.g., visualness) of concepts is measured as the Shannon entropy of pixel values in image patches and is used to refine the feature vector. Moreover, the system can assist the user in interactively selecting a region-of-interest (ROI) and searching for similar image ROIs. Further, a spatial verification step is used as a postprocessing step to improve retrieval results based on location information. The hypothesis that such approaches would improve biomedical image retrieval is validated through experiments on two different data sets, which are collected from open access biomedical literature.

iScreen: Image-Based High-Content RNAi Screening Analysis Tools.

Science.gov (United States)

Zhong, Rui; Dong, Xiaonan; Levine, Beth; Xie, Yang; Xiao, Guanghua

2015-09-01

High-throughput RNA interference (RNAi) screening has opened up a path to investigating functional genomics in a genome-wide pattern. However, such studies are often restricted to assays that have a single readout format. Recently, advanced image technologies have been coupled with high-throughput RNAi screening to develop high-content screening, in which one or more cell image(s), instead of a single readout, were generated from each well. This image-based high-content screening technology has led to genome-wide functional annotation in a wider spectrum of biological research studies, as well as in drug and target discovery, so that complex cellular phenotypes can be measured in a multiparametric format. Despite these advances, data analysis and visualization tools are still largely lacking for these types of experiments. Therefore, we developed iScreen (image-Based High-content RNAi Screening Analysis Tool), an R package for the statistical modeling and visualization of image-based high-content RNAi screening. Two case studies were used to demonstrate the capability and efficiency of the iScreen package. iScreen is available for download on CRAN (http://cran.cnr.berkeley.edu/web/packages/iScreen/index.html). The user manual is also available as a supplementary document. © 2014 Society for Laboratory Automation and Screening.

Medical Content Searching, Retrieving, and Sharing Over the Internet: Lessons Learned From the mEducator Through a Scenario-Based Evaluation

Science.gov (United States)

Spachos, Dimitris; Mylläri, Jarkko; Giordano, Daniela; Dafli, Eleni; Mitsopoulou, Evangelia; Schizas, Christos N; Pattichis, Constantinos; Nikolaidou, Maria

2015-01-01

Background The mEducator Best Practice Network (BPN) implemented and extended standards and reference models in e-learning to develop innovative frameworks as well as solutions that enable specialized state-of-the-art medical educational content to be discovered, retrieved, shared, and re-purposed across European Institutions, targeting medical students, doctors, educators and health care professionals. Scenario-based evaluation for usability testing, complemented with data from online questionnaires and field notes of users’ performance, was designed and utilized for the evaluation of these solutions. Objective The objective of this work is twofold: (1) to describe one instantiation of the mEducator BPN solutions (mEducator3.0 - “MEdical Education LINnked Arena” MELINA+) with a focus on the metadata schema used, as well as on other aspects of the system that pertain to usability and acceptance, and (2) to present evaluation results on the suitability of the proposed metadata schema for searching, retrieving, and sharing of medical content and with respect to the overall usability and acceptance of the system from the target users. Methods A comprehensive evaluation methodology framework was developed and applied to four case studies, which were conducted in four different countries (ie, Greece, Cyprus, Bulgaria and Romania), with a total of 126 participants. In these case studies, scenarios referring to creating, sharing, and retrieving medical educational content using mEducator3.0 were used. The data were collected through two online questionnaires, consisting of 36 closed-ended questions and two open-ended questions that referred to mEducator 3.0 and through the use of field notes during scenario-based evaluations. Results The main findings of the study showed that even though the informational needs of the mEducator target groups were addressed to a satisfactory extent and the metadata schema supported content creation, sharing, and retrieval from an end

Synergistic Instance-Level Subspace Alignment for Fine-Grained Sketch-Based Image Retrieval.

Science.gov (United States)

Li, Ke; Pang, Kaiyue; Song, Yi-Zhe; Hospedales, Timothy M; Xiang, Tao; Zhang, Honggang

2017-08-25

We study the problem of fine-grained sketch-based image retrieval. By performing instance-level (rather than category-level) retrieval, it embodies a timely and practical application, particularly with the ubiquitous availability of touchscreens. Three factors contribute to the challenging nature of the problem: (i) free-hand sketches are inherently abstract and iconic, making visual comparisons with photos difficult, (ii) sketches and photos are in two different visual domains, i.e. black and white lines vs. color pixels, and (iii) fine-grained distinctions are especially challenging when executed across domain and abstraction-level. To address these challenges, we propose to bridge the image-sketch gap both at the high-level via parts and attributes, as well as at the low-level, via introducing a new domain alignment method. More specifically, (i) we contribute a dataset with 304 photos and 912 sketches, where each sketch and image is annotated with its semantic parts and associated part-level attributes. With the help of this dataset, we investigate (ii) how strongly-supervised deformable part-based models can be learned that subsequently enable automatic detection of part-level attributes, and provide pose-aligned sketch-image comparisons. To reduce the sketch-image gap when comparing low-level features, we also (iii) propose a novel method for instance-level domain-alignment, that exploits both subspace and instance-level cues to better align the domains. Finally (iv) these are combined in a matching framework integrating aligned low-level features, mid-level geometric structure and high-level semantic attributes. Extensive experiments conducted on our new dataset demonstrate effectiveness of the proposed method.

Signature detection and matching for document image retrieval.

Science.gov (United States)

Zhu, Guangyu; Zheng, Yefeng; Doermann, David; Jaeger, Stefan

2009-11-01

As one of the most pervasive methods of individual identification and document authentication, signatures present convincing evidence and provide an important form of indexing for effective document image processing and retrieval in a broad range of applications. However, detection and segmentation of free-form objects such as signatures from clustered background is currently an open document analysis problem. In this paper, we focus on two fundamental problems in signature-based document image retrieval. First, we propose a novel multiscale approach to jointly detecting and segmenting signatures from document images. Rather than focusing on local features that typically have large variations, our approach captures the structural saliency using a signature production model and computes the dynamic curvature of 2D contour fragments over multiple scales. This detection framework is general and computationally tractable. Second, we treat the problem of signature retrieval in the unconstrained setting of translation, scale, and rotation invariant nonrigid shape matching. We propose two novel measures of shape dissimilarity based on anisotropic scaling and registration residual error and present a supervised learning framework for combining complementary shape information from different dissimilarity metrics using LDA. We quantitatively study state-of-the-art shape representations, shape matching algorithms, measures of dissimilarity, and the use of multiple instances as query in document image retrieval. We further demonstrate our matching techniques in offline signature verification. Extensive experiments using large real-world collections of English and Arabic machine-printed and handwritten documents demonstrate the excellent performance of our approaches.

Large-scale retrieval for medical image analytics: A comprehensive review.

Science.gov (United States)

Li, Zhongyu; Zhang, Xiaofan; Müller, Henning; Zhang, Shaoting

2018-01-01

Over the past decades, medical image analytics was greatly facilitated by the explosion of digital imaging techniques, where huge amounts of medical images were produced with ever-increasing quality and diversity. However, conventional methods for analyzing medical images have achieved limited success, as they are not capable to tackle the huge amount of image data. In this paper, we review state-of-the-art approaches for large-scale medical image analysis, which are mainly based on recent advances in computer vision, machine learning and information retrieval. Specifically, we first present the general pipeline of large-scale retrieval, summarize the challenges/opportunities of medical image analytics on a large-scale. Then, we provide a comprehensive review of algorithms and techniques relevant to major processes in the pipeline, including feature representation, feature indexing, searching, etc. On the basis of existing work, we introduce the evaluation protocols and multiple applications of large-scale medical image retrieval, with a variety of exploratory and diagnostic scenarios. Finally, we discuss future directions of large-scale retrieval, which can further improve the performance of medical image analysis. Copyright © 2017 Elsevier B.V. All rights reserved.

Using Fuzzy SOM Strategy for Satellite Image Retrieval and Information Mining

Directory of Open Access Journals (Sweden)

Yo-Ping Huang

2008-02-01

Full Text Available This paper proposes an efficient satellite image retrieval and knowledge discovery model. The strategy comprises two major parts. First, a computational algorithm is used for off-line satellite image feature extraction, image data representation and image retrieval. Low level features are automatically extracted from the segmented regions of satellite images. A self-organization feature map is used to construct a two-layer satellite image concept hierarchy. The events are stored in one layer and the corresponding feature vectors are categorized in the other layer. Second, a user friendly interface is provided that retrieves images of interest and mines useful information based on the events in the concept hierarchy. The proposed system is evaluated with prominent features such as typhoons or high-pressure masses.

Bread Water Content Measurement Based on Hyperspectral Imaging

DEFF Research Database (Denmark)

Liu, Zhi; Møller, Flemming

2011-01-01

Water content is one of the most important properties of the bread for tasting assesment or store monitoring. Traditional bread water content measurement methods mostly are processed manually, which is destructive and time consuming. This paper proposes an automated water content measurement...... for bread quality based on near-infrared hyperspectral imaging against the conventional manual loss-in-weight method. For this purpose, the hyperspectral components unmixing technology is used for measuring the water content quantitatively. And the definition on bread water content index is presented...

Segmentation Technique for Image Indexing and Retrieval on Discrete Cosines Domain

Directory of Open Access Journals (Sweden)

Suhendro Yusuf Irianto

2013-03-01

Full Text Available This paper uses region growing segmentation technique to segment the Discrete Cosines (DC  image. The problem of content Based image retrieval (CBIR is the luck of accuracy in matching between image query and image in the database as it matches object and background in the same time.   This the reason previous CBIR techniques inaccurate and time consuming. The CBIR   based on the segmented region proposed in this work  separates object from background as CBIR need only match the object not the background.  By using region growing technique on DC image, it reduces the number of image       regions.    The proposed of recursive region growing is not new technique but its application on DC images to build    indexing keys is quite new and not yet presented by many     authors. The experimental results show  that the proposed methods on   segmented images present good precision which are higher than 0.60 on all classes . It can be concluded that  region growing segmented based CBIR more efficient    compare to DC images  in term of their precision 0.59 and 0.75, respectively. Moreover,  DC based CBIR  can save time and simplify algorithm compare to DCT images.

SIFT Meets CNN: A Decade Survey of Instance Retrieval.

Science.gov (United States)

Zheng, Liang; Yang, Yi; Tian, Qi

2018-05-01

In the early days, content-based image retrieval (CBIR) was studied with global features. Since 2003, image retrieval based on local descriptors (de facto SIFT) has been extensively studied for over a decade due to the advantage of SIFT in dealing with image transformations. Recently, image representations based on the convolutional neural network (CNN) have attracted increasing interest in the community and demonstrated impressive performance. Given this time of rapid evolution, this article provides a comprehensive survey of instance retrieval over the last decade. Two broad categories, SIFT-based and CNN-based methods, are presented. For the former, according to the codebook size, we organize the literature into using large/medium-sized/small codebooks. For the latter, we discuss three lines of methods, i.e., using pre-trained or fine-tuned CNN models, and hybrid methods. The first two perform a single-pass of an image to the network, while the last category employs a patch-based feature extraction scheme. This survey presents milestones in modern instance retrieval, reviews a broad selection of previous works in different categories, and provides insights on the connection between SIFT and CNN-based methods. After analyzing and comparing retrieval performance of different categories on several datasets, we discuss promising directions towards generic and specialized instance retrieval.

Retrieve An Image

Indian Academy of Sciences (India)

First page Back Continue Last page Overview Graphics. Retrieve An Image. “A building”. “Box-shaped”. “Brown Color”. “Foreshortened view”. OR. Why not specify a similar looking picture? -- Main Motivation!

Performance analysis of algorithms for retrieval of magnetic resonance images for interactive teleradiology

Science.gov (United States)

Atkins, M. Stella; Hwang, Robert; Tang, Simon

2001-05-01

We have implemented a prototype system consisting of a Java- based image viewer and a web server extension component for transmitting Magnetic Resonance Images (MRI) to an image viewer, to test the performance of different image retrieval techniques. We used full-resolution images, and images compressed/decompressed using the Set Partitioning in Hierarchical Trees (SPIHT) image compression algorithm. We examined the SPIHT decompression algorithm using both non- progressive and progressive transmission, focusing on the running times of the algorithm, client memory usage and garbage collection. We also compared the Java implementation with a native C++ implementation of the non- progressive SPIHT decompression variant. Our performance measurements showed that for uncompressed image retrieval using a 10Mbps Ethernet, a film of 16 MR images can be retrieved and displayed almost within interactive times. The native C++ code implementation of the client-side decoder is twice as fast as the Java decoder. If the network bandwidth is low, the high communication time for retrieving uncompressed images may be reduced by use of SPIHT-compressed images, although the image quality is then degraded. To provide diagnostic quality images, we also investigated the retrieval of up to 3 images on a MR film at full-resolution, using progressive SPIHT decompression. The Java-based implementation of progressive decompression performed badly, mainly due to the memory requirements for maintaining the image states, and the high cost of execution of the Java garbage collector. Hence, in systems where the bandwidth is high, such as found in a hospital intranet, SPIHT image compression does not provide advantages for image retrieval performance.

Fractional Fourier domain optical image hiding using phase retrieval algorithm based on iterative nonlinear double random phase encoding.

Science.gov (United States)

Wang, Xiaogang; Chen, Wen; Chen, Xudong

2014-09-22

We present a novel image hiding method based on phase retrieval algorithm under the framework of nonlinear double random phase encoding in fractional Fourier domain. Two phase-only masks (POMs) are efficiently determined by using the phase retrieval algorithm, in which two cascaded phase-truncated fractional Fourier transforms (FrFTs) are involved. No undesired information disclosure, post-processing of the POMs or digital inverse computation appears in our proposed method. In order to achieve the reduction in key transmission, a modified image hiding method based on the modified phase retrieval algorithm and logistic map is further proposed in this paper, in which the fractional orders and the parameters with respect to the logistic map are regarded as encryption keys. Numerical results have demonstrated the feasibility and effectiveness of the proposed algorithms.

Retrieval and classification of food images.

Science.gov (United States)

Farinella, Giovanni Maria; Allegra, Dario; Moltisanti, Marco; Stanco, Filippo; Battiato, Sebastiano

2016-10-01

Automatic food understanding from images is an interesting challenge with applications in different domains. In particular, food intake monitoring is becoming more and more important because of the key role that it plays in health and market economies. In this paper, we address the study of food image processing from the perspective of Computer Vision. As first contribution we present a survey of the studies in the context of food image processing from the early attempts to the current state-of-the-art methods. Since retrieval and classification engines able to work on food images are required to build automatic systems for diet monitoring (e.g., to be embedded in wearable cameras), we focus our attention on the aspect of the representation of the food images because it plays a fundamental role in the understanding engines. The food retrieval and classification is a challenging task since the food presents high variableness and an intrinsic deformability. To properly study the peculiarities of different image representations we propose the UNICT-FD1200 dataset. It was composed of 4754 food images of 1200 distinct dishes acquired during real meals. Each food plate is acquired multiple times and the overall dataset presents both geometric and photometric variabilities. The images of the dataset have been manually labeled considering 8 categories: Appetizer, Main Course, Second Course, Single Course, Side Dish, Dessert, Breakfast, Fruit. We have performed tests employing different representations of the state-of-the-art to assess the related performances on the UNICT-FD1200 dataset. Finally, we propose a new representation based on the perceptual concept of Anti-Textons which is able to encode spatial information between Textons outperforming other representations in the context of food retrieval and Classification. Copyright © 2016 Elsevier Ltd. All rights reserved.

Visual analytics for semantic queries of TerraSAR-X image content

Science.gov (United States)

Espinoza-Molina, Daniela; Alonso, Kevin; Datcu, Mihai

2015-10-01

With the continuous image product acquisition of satellite missions, the size of the image archives is considerably increasing every day as well as the variety and complexity of their content, surpassing the end-user capacity to analyse and exploit them. Advances in the image retrieval field have contributed to the development of tools for interactive exploration and extraction of the images from huge archives using different parameters like metadata, key-words, and basic image descriptors. Even though we count on more powerful tools for automated image retrieval and data analysis, we still face the problem of understanding and analyzing the results. Thus, a systematic computational analysis of these results is required in order to provide to the end-user a summary of the archive content in comprehensible terms. In this context, visual analytics combines automated analysis with interactive visualizations analysis techniques for an effective understanding, reasoning and decision making on the basis of very large and complex datasets. Moreover, currently several researches are focused on associating the content of the images with semantic definitions for describing the data in a format to be easily understood by the end-user. In this paper, we present our approach for computing visual analytics and semantically querying the TerraSAR-X archive. Our approach is mainly composed of four steps: 1) the generation of a data model that explains the information contained in a TerraSAR-X product. The model is formed by primitive descriptors and metadata entries, 2) the storage of this model in a database system, 3) the semantic definition of the image content based on machine learning algorithms and relevance feedback, and 4) querying the image archive using semantic descriptors as query parameters and computing the statistical analysis of the query results. The experimental results shows that with the help of visual analytics and semantic definitions we are able to explain

Content-based analysis and indexing of sports video

Science.gov (United States)

Luo, Ming; Bai, Xuesheng; Xu, Guang-you

2001-12-01

An explosion of on-line image and video data in digital form is already well underway. With the exponential rise in interactive information exploration and dissemination through the World-Wide Web, the major inhibitors of rapid access to on-line video data are the management of capture and storage, and content-based intelligent search and indexing techniques. This paper proposes an approach for content-based analysis and event-based indexing of sports video. It includes a novel method to organize shots - classifying shots as close shots and far shots, an original idea of blur extent-based event detection, and an innovative local mutation-based algorithm for caption detection and retrieval. Results on extensive real TV programs demonstrate the applicability of our approach.

Image content authentication based on channel coding

Science.gov (United States)

Zhang, Fan; Xu, Lei

2008-03-01

The content authentication determines whether an image has been tampered or not, and if necessary, locate malicious alterations made on the image. Authentication on a still image or a video are motivated by recipient's interest, and its principle is that a receiver must be able to identify the source of this document reliably. Several techniques and concepts based on data hiding or steganography designed as a means for the image authentication. This paper presents a color image authentication algorithm based on convolution coding. The high bits of color digital image are coded by the convolution codes for the tamper detection and localization. The authentication messages are hidden in the low bits of image in order to keep the invisibility of authentication. All communications channels are subject to errors introduced because of additive Gaussian noise in their environment. Data perturbations cannot be eliminated but their effect can be minimized by the use of Forward Error Correction (FEC) techniques in the transmitted data stream and decoders in the receiving system that detect and correct bits in error. This paper presents a color image authentication algorithm based on convolution coding. The message of each pixel is convolution encoded with the encoder. After the process of parity check and block interleaving, the redundant bits are embedded in the image offset. The tamper can be detected and restored need not accessing the original image.

Model-based VQ for image data archival, retrieval and distribution

Science.gov (United States)

Manohar, Mareboyana; Tilton, James C.

1995-01-01

An ideal image compression technique for image data archival, retrieval and distribution would be one with the asymmetrical computational requirements of Vector Quantization (VQ), but without the complications arising from VQ codebooks. Codebook generation and maintenance are stumbling blocks which have limited the use of VQ as a practical image compression algorithm. Model-based VQ (MVQ), a variant of VQ described here, has the computational properties of VQ but does not require explicit codebooks. The codebooks are internally generated using mean removed error and Human Visual System (HVS) models. The error model assumed is the Laplacian distribution with mean, lambda-computed from a sample of the input image. A Laplacian distribution with mean, lambda, is generated with uniform random number generator. These random numbers are grouped into vectors. These vectors are further conditioned to make them perceptually meaningful by filtering the DCT coefficients from each vector. The DCT coefficients are filtered by multiplying by a weight matrix that is found to be optimal for human perception. The inverse DCT is performed to produce the conditioned vectors for the codebook. The only image dependent parameter used in the generation of codebook is the mean, lambda, that is included in the coded file to repeat the codebook generation process for decoding.

Large-Scale Query-by-Image Video Retrieval Using Bloom Filters

OpenAIRE

Araujo, Andre; Chaves, Jason; Lakshman, Haricharan; Angst, Roland; Girod, Bernd

2016-01-01

We consider the problem of using image queries to retrieve videos from a database. Our focus is on large-scale applications, where it is infeasible to index each database video frame independently. Our main contribution is a framework based on Bloom filters, which can be used to index long video segments, enabling efficient image-to-video comparisons. Using this framework, we investigate several retrieval architectures, by considering different types of aggregation and different functions to ...

A Fast, Background-Independent Retrieval Strategy for Color Image Databases

National Research Council Canada - National Science Library

Das, M; Draper, B. A; Lim, W. J; Manmatha, R; Riseman, E. M

1996-01-01

We describe an interactive, multi-phase color-based image retrieval system which is capable of identifying query objects specified by the user in an image in the presence of significant, interfering backgrounds...

Phase retrieval for X-ray in-line phase contrast imaging

International Nuclear Information System (INIS)

Scattarella, F.; Bellotti, R.; Tangaro, S.; Gargano, G.; Giannini, C.

2011-01-01

A review article about phase retrieval problem in X-ray phase contrast imaging is presented. A simple theoretical framework of Fresnel diffraction imaging by X-rays is introduced. A review of the most important methods for phase retrieval in free-propagation-based X-ray imaging and a new method developed by our collaboration are shown. The proposed algorithm, Combined Mixed Approach (CMA) is based on a mixed transfer function and transport of intensity approach, and it requires at most an initial approximate estimate of the average phase shift introduced by the object as prior knowledge. The accuracy with which this initial estimate is known determines the convenience speed of algorithm. The new proposed algorithm is based on the retrieval of both the object phase and its complex conjugate. The results obtained by the algorithm on simulated data have shown that the obtained reconstructed phase maps are characterized by particularly low normalized mean square errors. The algorithm was also tested on noisy experimental phase contrast data, showing a good efficiency in recovering phase information and enhancing the visibility of details inside soft tissues.

Bag-of-features based medical image retrieval via multiple assignment and visual words weighting

KAUST Repository

Wang, Jingyan

2011-11-01

Bag-of-features based approaches have become prominent for image retrieval and image classification tasks in the past decade. Such methods represent an image as a collection of local features, such as image patches and key points with scale invariant feature transform (SIFT) descriptors. To improve the bag-of-features methods, we first model the assignments of local descriptors as contribution functions, and then propose a novel multiple assignment strategy. Assuming the local features can be reconstructed by their neighboring visual words in a vocabulary, reconstruction weights can be solved by quadratic programming. The weights are then used to build contribution functions, resulting in a novel assignment method, called quadratic programming (QP) assignment. We further propose a novel visual word weighting method. The discriminative power of each visual word is analyzed by the sub-similarity function in the bin that corresponds to the visual word. Each sub-similarity function is then treated as a weak classifier. A strong classifier is learned by boosting methods that combine those weak classifiers. The weighting factors of the visual words are learned accordingly. We evaluate the proposed methods on medical image retrieval tasks. The methods are tested on three well-known data sets, i.e., the ImageCLEFmed data set, the 304 CT Set, and the basal-cell carcinoma image set. Experimental results demonstrate that the proposed QP assignment outperforms the traditional nearest neighbor assignment, the multiple assignment, and the soft assignment, whereas the proposed boosting based weighting strategy outperforms the state-of-the-art weighting methods, such as the term frequency weights and the term frequency-inverse document frequency weights. © 2011 IEEE.

Bag-of-features based medical image retrieval via multiple assignment and visual words weighting

KAUST Repository

Wang, Jingyan; Li, Yongping; Zhang, Ying; Wang, Chao; Xie, Honglan; Chen, Guoling; Gao, Xin

2011-01-01

Bag-of-features based approaches have become prominent for image retrieval and image classification tasks in the past decade. Such methods represent an image as a collection of local features, such as image patches and key points with scale invariant feature transform (SIFT) descriptors. To improve the bag-of-features methods, we first model the assignments of local descriptors as contribution functions, and then propose a novel multiple assignment strategy. Assuming the local features can be reconstructed by their neighboring visual words in a vocabulary, reconstruction weights can be solved by quadratic programming. The weights are then used to build contribution functions, resulting in a novel assignment method, called quadratic programming (QP) assignment. We further propose a novel visual word weighting method. The discriminative power of each visual word is analyzed by the sub-similarity function in the bin that corresponds to the visual word. Each sub-similarity function is then treated as a weak classifier. A strong classifier is learned by boosting methods that combine those weak classifiers. The weighting factors of the visual words are learned accordingly. We evaluate the proposed methods on medical image retrieval tasks. The methods are tested on three well-known data sets, i.e., the ImageCLEFmed data set, the 304 CT Set, and the basal-cell carcinoma image set. Experimental results demonstrate that the proposed QP assignment outperforms the traditional nearest neighbor assignment, the multiple assignment, and the soft assignment, whereas the proposed boosting based weighting strategy outperforms the state-of-the-art weighting methods, such as the term frequency weights and the term frequency-inverse document frequency weights. © 2011 IEEE.

Kingfisher: a system for remote sensing image database management

Science.gov (United States)

Bruzzo, Michele; Giordano, Ferdinando; Dellepiane, Silvana G.

2003-04-01

At present retrieval methods in remote sensing image database are mainly based on spatial-temporal information. The increasing amount of images to be collected by the ground station of earth observing systems emphasizes the need for database management with intelligent data retrieval capabilities. The purpose of the proposed method is to realize a new content based retrieval system for remote sensing images database with an innovative search tool based on image similarity. This methodology is quite innovative for this application, at present many systems exist for photographic images, as for example QBIC and IKONA, but they are not able to extract and describe properly remote image content. The target database is set by an archive of images originated from an X-SAR sensor (spaceborne mission, 1994). The best content descriptors, mainly texture parameters, guarantees high retrieval performances and can be extracted without losses independently of image resolution. The latter property allows DBMS (Database Management System) to process low amount of information, as in the case of quick-look images, improving time performance and memory access without reducing retrieval accuracy. The matching technique has been designed to enable image management (database population and retrieval) independently of dimensions (width and height). Local and global content descriptors are compared, during retrieval phase, with the query image and results seem to be very encouraging.

Large Scale Hierarchical K-Means Based Image Retrieval With MapReduce

Science.gov (United States)

2014-03-27

flat vocabulary on MapReduce. In 2013, Moise and Shestakov [32, 40], have been researching large scale indexing and search with MapReduce. They...time will be greatly reduced, however image retrieval performance will almost certainly suffer. Moise and Shestakov ran tests with 100M images on 108...43–72, 2005. [32] Diana Moise , Denis Shestakov, Gylfi Gudmundsson, and Laurent Amsaleg. Indexing and searching 100m images with map-reduce. In

Storage and retrieval of large digital images

Science.gov (United States)

Bradley, J.N.

1998-01-20

Image compression and viewing are implemented with (1) a method for performing DWT-based compression on a large digital image with a computer system possessing a two-level system of memory and (2) a method for selectively viewing areas of the image from its compressed representation at multiple resolutions and, if desired, in a client-server environment. The compression of a large digital image I(x,y) is accomplished by first defining a plurality of discrete tile image data subsets T{sub ij}(x,y) that, upon superposition, form the complete set of image data I(x,y). A seamless wavelet-based compression process is effected on I(x,y) that is comprised of successively inputting the tiles T{sub ij}(x,y) in a selected sequence to a DWT routine, and storing the resulting DWT coefficients in a first primary memory. These coefficients are periodically compressed and transferred to a secondary memory to maintain sufficient memory in the primary memory for data processing. The sequence of DWT operations on the tiles T{sub ij}(x,y) effectively calculates a seamless DWT of I(x,y). Data retrieval consists of specifying a resolution and a region of I(x,y) for display. The subset of stored DWT coefficients corresponding to each requested scene is determined and then decompressed for input to an inverse DWT, the output of which forms the image display. The repeated process whereby image views are specified may take the form an interaction with a computer pointing device on an image display from a previous retrieval. 6 figs.

Memory retrieval of smoking-related images induce greater insula activation as revealed by an fMRI-based delayed matching to sample task.

Science.gov (United States)

Janes, Amy C; Ross, Robert S; Farmer, Stacey; Frederick, Blaise B; Nickerson, Lisa D; Lukas, Scott E; Stern, Chantal E

2015-03-01

Nicotine dependence is a chronic and difficult to treat disorder. While environmental stimuli associated with smoking precipitate craving and relapse, it is unknown whether smoking cues are cognitively processed differently than neutral stimuli. To evaluate working memory differences between smoking-related and neutral stimuli, we conducted a delay-match-to-sample (DMS) task concurrently with functional magnetic resonance imaging (fMRI) in nicotine-dependent participants. The DMS task evaluates brain activation during the encoding, maintenance and retrieval phases of working memory. Smoking images induced significantly more subjective craving, and greater midline cortical activation during encoding in comparison to neutral stimuli that were similar in content yet lacked a smoking component. The insula, which is involved in maintaining nicotine dependence, was active during the successful retrieval of previously viewed smoking versus neutral images. In contrast, neutral images required more prefrontal cortex-mediated active maintenance during the maintenance period. These findings indicate that distinct brain regions are involved in the different phases of working memory for smoking-related versus neutral images. Importantly, the results implicate the insula in the retrieval of smoking-related stimuli, which is relevant given the insula's emerging role in addiction. © 2013 Society for the Study of Addiction.

Intelligent retrieval of chest X-ray image database using sketches

International Nuclear Information System (INIS)

Hasegawa, Jun-ichi; Okada, Noritake; Toriwaki, Jun-ichiro

1988-01-01

This paper presents further experiments on intelligent retrieval in our chest X-ray image database system using 'sketches'. First, in the previous sketch extraction procedure, vertical-location-invariant thresholding and shape-oriented smoothing are newly developed to improve the precision of lung borders and rib images in each sketch, respectively. Then, two new ways for image retrieval using sketches; (1) image-description retrieval and (2) pattern-matching retrieval, are proposed. In each retrieval way, a procedure for understanding picture queries input through a sketch is described in detail. (author)

Modelamiento de un sistema de recuperación de imágenes de recursos acuáticos, basado en contenido y calidad de la información Modeling of an aquatic resource image retrieval system, based on content and information quality

Directory of Open Access Journals (Sweden)

Bell Manrique Losada

2008-07-01

Full Text Available En el marco de los Sistemas de Recuperación de Información, se ubican los Sistemas de Recuperación de Imágenes, los cuales permiten generar procesos de búsqueda y almacenamiento de recursos por medio de coincidencias por palabras claves u otros métodos en tiempo real. Este tipo de sistemas pueden usar como í ndices, contenido visual de las imágenes como color, textura y brillo, y además combinar diferentes atributos para mejorar los procesos de clasificación y relevancia de los resultados del proceso de búsqueda, que se conocen como 'de la calidad de la información'. Este artículo presenta el modelamiento de un Sistema de Recuperación de Imágenes que combina atributos de la recuperación basada en contenido como color, textura y forma, con la recuperación basada en la calidad de la información, como frecuencia de actualización, portabilidad y relevancia, en el contexto de la Colección Digital de Imágenes de Ecosistemas Acuáticos Amazónicos del Grupo CAPREA de la Universidad de la Amazonia.In Information Retrieval Systems, Image Retrieval Systems are located; they allow generating searching and storing processes of resources through coincidences by key words or other real-time methods. This type of systems can use visual content of images (color, texture, and brightness as indices. In addition, these systems combine different attributes to improve the processes of classification and relevance of the searching process results known as 'Information Quality.' This paper presents the modeling of a Image Retrieval System which combines attributes of the contentbased retrieval such as color, texture, and shape, with the Information Quality-based retrieval as updating portability and relevance frequency in the context of Digital Image Collection of Aquatic Amazon Ecosystems of Universidad del Amazonia CAPREA Research Group.

Propagation based phase retrieval of simulated intensity measurements using artificial neural networks

Science.gov (United States)

Kemp, Z. D. C.

2018-04-01

Determining the phase of a wave from intensity measurements has many applications in fields such as electron microscopy, visible light optics, and medical imaging. Propagation based phase retrieval, where the phase is obtained from defocused images, has shown significant promise. There are, however, limitations in the accuracy of the retrieved phase arising from such methods. Sources of error include shot noise, image misalignment, and diffraction artifacts. We explore the use of artificial neural networks (ANNs) to improve the accuracy of propagation based phase retrieval algorithms applied to simulated intensity measurements. We employ a phase retrieval algorithm based on the transport-of-intensity equation to obtain the phase from simulated micrographs of procedurally generated specimens. We then train an ANN with pairs of retrieved and exact phases, and use the trained ANN to process a test set of retrieved phase maps. The total error in the phase is significantly reduced using this method. We also discuss a variety of potential extensions to this work.

STUDY COMPARISON OF SVM-, K-NN- AND BACKPROPAGATION-BASED CLASSIFIER FOR IMAGE RETRIEVAL

Directory of Open Access Journals (Sweden)

Muhammad Athoillah

2015-03-01

Full Text Available Classification is a method for compiling data systematically according to the rules that have been set previously. In recent years classification method has been proven to help many people’s work, such as image classification, medical biology, traffic light, text classification etc. There are many methods to solve classification problem. This variation method makes the researchers find it difficult to determine which method is best for a problem. This framework is aimed to compare the ability of classification methods, such as Support Vector Machine (SVM, K-Nearest Neighbor (K-NN, and Backpropagation, especially in study cases of image retrieval with five category of image dataset. The result shows that K-NN has the best average result in accuracy with 82%. It is also the fastest in average computation time with 17,99 second during retrieve session for all categories class. The Backpropagation, however, is the slowest among three of them. In average it needed 883 second for training session and 41,7 second for retrieve session.

A multi-tiered architecture for content retrieval in mobile peer-to-peer networks.

Science.gov (United States)

2012-01-01

In this paper, we address content retrieval in Mobile Peer-to-Peer (P2P) Networks. We design a multi-tiered architecture for content : retrieval, where at Tier 1, we design a protocol for content similarity governed by a parameter that trades accu...

Localization-based super-resolution imaging meets high-content screening.

Science.gov (United States)

Beghin, Anne; Kechkar, Adel; Butler, Corey; Levet, Florian; Cabillic, Marine; Rossier, Olivier; Giannone, Gregory; Galland, Rémi; Choquet, Daniel; Sibarita, Jean-Baptiste

2017-12-01

Single-molecule localization microscopy techniques have proven to be essential tools for quantitatively monitoring biological processes at unprecedented spatial resolution. However, these techniques are very low throughput and are not yet compatible with fully automated, multiparametric cellular assays. This shortcoming is primarily due to the huge amount of data generated during imaging and the lack of software for automation and dedicated data mining. We describe an automated quantitative single-molecule-based super-resolution methodology that operates in standard multiwell plates and uses analysis based on high-content screening and data-mining software. The workflow is compatible with fixed- and live-cell imaging and allows extraction of quantitative data like fluorophore photophysics, protein clustering or dynamic behavior of biomolecules. We demonstrate that the method is compatible with high-content screening using 3D dSTORM and DNA-PAINT based super-resolution microscopy as well as single-particle tracking.

Medical Image Retrieval Based On the Parallelization of the Cluster Sampling Algorithm

OpenAIRE

Ali, Hesham Arafat; Attiya, Salah; El-henawy, Ibrahim

2017-01-01

In this paper we develop parallel cluster sampling algorithms and show that a multi-chain version is embarrassingly parallel and can be used efficiently for medical image retrieval among other applications.

Joint Textual And Visual Cues For Retrieving Images Using Latent Semantic Indexing

OpenAIRE

Pecenovic, Zoran; Ayer, Serge; Vetterli, Martin

2001-01-01

In this article we present a novel approach of integrating textual and visual descriptors of images in a unified retrieval structure. The methodology, inspired from text retrieval and information filtering is based on Latent Semantic Indexing (LS1).

Implementação e avaliação de um sistema de gerenciamento de imagens médicas com suporte à recuperação baseada em conteúdo Implementation and evaluation of a medical image management system with content-based retrieval support

Directory of Open Access Journals (Sweden)

Edilson Carlos Caritá

2008-10-01

Full Text Available OBJETIVO: Neste artigo são descritas a implementação e avaliação de um sistema de gerenciamento de imagens médicas com suporte à recuperação baseada em conteúdo (PACS-CBIR, integrando módulos voltados para a aquisição, armazenamento e distribuição de imagens, e a recuperação de informação textual por palavras-chave e de imagens por similaridade. MATERIAIS E MÉTODOS: O sistema foi implementado com tecnologias para Internet, utilizando-se programas livres, plataforma Linux e linguagem de programação C++, PHP e Java. Há um módulo de gerenciamento de imagens compatível com o padrão DICOM e outros dois módulos de busca, um baseado em informações textuais e outro na similaridade de atributos de textura de imagens. RESULTADOS: Os resultados obtidos indicaram que as imagens são gerenciadas e armazenadas corretamente e que o tempo de retorno das imagens, sempre menor do que 15 segundos, foi considerado bom pelos usuários. As avaliações da recuperação por similaridade demonstraram que o extrator escolhido possibilitou a separação das imagens por região anatômica. CONCLUSÃO: Com os resultados obtidos pode-se concluir que é viável a implementação de um PACS-CBIR. O sistema apresentou-se compatível com as funcionalidades do DICOM e integrável ao sistema de informação local. A funcionalidade de recuperação de imagens similares pode ser melhorada com a inclusão de outros descritores.OBJECTIVE: The present paper describes the implementation and evaluation of a medical images management system with content-based retrieval support (PACS-CBIR integrating modules focused on images acquisition, storage and distribution, and text retrieval by keyword and images retrieval by similarity. MATERIALS AND METHODS: Internet-compatible technologies were utilized for the system implementation with freeware, and C++, PHP and Java languages on a Linux platform. There is a DICOM-compatible image management module and two query

A similarity measure method combining location feature for mammogram retrieval.

Science.gov (United States)

Wang, Zhiqiong; Xin, Junchang; Huang, Yukun; Li, Chen; Xu, Ling; Li, Yang; Zhang, Hao; Gu, Huizi; Qian, Wei

2018-05-28

method have obvious advantage, compared with the content-based image retrieval.

Measuring and Predicting Tag Importance for Image Retrieval.

Science.gov (United States)

Li, Shangwen; Purushotham, Sanjay; Chen, Chen; Ren, Yuzhuo; Kuo, C-C Jay

2017-12-01

Textual data such as tags, sentence descriptions are combined with visual cues to reduce the semantic gap for image retrieval applications in today's Multimodal Image Retrieval (MIR) systems. However, all tags are treated as equally important in these systems, which may result in misalignment between visual and textual modalities during MIR training. This will further lead to degenerated retrieval performance at query time. To address this issue, we investigate the problem of tag importance prediction, where the goal is to automatically predict the tag importance and use it in image retrieval. To achieve this, we first propose a method to measure the relative importance of object and scene tags from image sentence descriptions. Using this as the ground truth, we present a tag importance prediction model to jointly exploit visual, semantic and context cues. The Structural Support Vector Machine (SSVM) formulation is adopted to ensure efficient training of the prediction model. Then, the Canonical Correlation Analysis (CCA) is employed to learn the relation between the image visual feature and tag importance to obtain robust retrieval performance. Experimental results on three real-world datasets show a significant performance improvement of the proposed MIR with Tag Importance Prediction (MIR/TIP) system over other MIR systems.

Characterizing the information content of cloud thermodynamic phase retrievals from the notional PACE OCI shortwave reflectance measurements

Science.gov (United States)

Coddington, O. M.; Vukicevic, T.; Schmidt, K. S.; Platnick, S.

2017-08-01

We rigorously quantify the probability of liquid or ice thermodynamic phase using only shortwave spectral channels specific to the National Aeronautics and Space Administration's Moderate Resolution Imaging Spectroradiometer, Visible Infrared Imaging Radiometer Suite, and the notional future Plankton, Aerosol, Cloud, ocean Ecosystem imager. The results show that two shortwave-infrared channels (2135 and 2250 nm) provide more information on cloud thermodynamic phase than either channel alone; in one case, the probability of ice phase retrieval increases from 65 to 82% by combining 2135 and 2250 nm channels. The analysis is performed with a nonlinear statistical estimation approach, the GEneralized Nonlinear Retrieval Analysis (GENRA). The GENRA technique has previously been used to quantify the retrieval of cloud optical properties from passive shortwave observations, for an assumed thermodynamic phase. Here we present the methodology needed to extend the utility of GENRA to a binary thermodynamic phase space (i.e., liquid or ice). We apply formal information content metrics to quantify our results; two of these (mutual and conditional information) have not previously been used in the field of cloud studies.

Unsupervised symmetrical trademark image retrieval in soccer telecast using wavelet energy and quadtree decomposition

Science.gov (United States)

Ong, Swee Khai; Lim, Wee Keong; Soo, Wooi King

2013-04-01

Trademark, a distinctive symbol, is used to distinguish products or services provided by a particular person, group or organization from other similar entries. As trademark represents the reputation and credit standing of the owner, it is important to differentiate one trademark from another. Many methods have been proposed to identify, classify and retrieve trademarks. However, most methods required features database and sample sets for training prior to recognition and retrieval process. In this paper, a new feature on wavelet coefficients, the localized wavelet energy, is introduced to extract features of trademarks. With this, unsupervised content-based symmetrical trademark image retrieval is proposed without the database and prior training set. The feature analysis is done by an integration of the proposed localized wavelet energy and quadtree decomposed regional symmetrical vector. The proposed framework eradicates the dependence on query database and human participation during the retrieval process. In this paper, trademarks for soccer games sponsors are the intended trademark category. Video frames from soccer telecast are extracted and processed for this study. Reasonably good localization and retrieval results on certain categories of trademarks are achieved. A distinctive symbol is used to distinguish products or services provided by a particular person, group or organization from other similar entries.

Three-dimensional imaging using phase retrieval with two focus planes

Science.gov (United States)

Ilovitsh, Tali; Ilovitsh, Asaf; Weiss, Aryeh; Meir, Rinat; Zalevsky, Zeev

2016-03-01

This work presents a technique for a full 3D imaging of biological samples tagged with gold-nanoparticles (GNPs) using only two images, rather than many images per volume as is currently needed for 3D optical sectioning microscopy. The proposed approach is based on the Gerchberg-Saxton (GS) phase retrieval algorithm. The reconstructed field is free space propagated to all other focus planes using post processing, and the 2D z-stack is merged to create a 3D image of the sample with high fidelity. Because we propose to apply the phase retrieving on nano particles, the regular ambiguities typical to the Gerchberg-Saxton algorithm, are eliminated. In addition, since the method requires the capturing of two images only, it can be suitable for 3D live cell imaging. The proposed concept is presented and validated both on simulated data as well as experimentally.

An On-Demand Retrieval Method Based on Hybrid NoSQL for Multi-Layer Image Tiles in Disaster Reduction Visualization

Directory of Open Access Journals (Sweden)

Linyao Qiu

2017-01-01

Full Text Available Monitoring, response, mitigation and damage assessment of disasters places a wide variety of demands on the spatial and temporal resolutions of remote sensing images. Images are divided into tile pyramids by data sources or resolutions and published as independent image services for visualization. A disaster-affected area is commonly covered by multiple image layers to express hierarchical surface information, which generates a large amount of namesake tiles from different layers that overlay the same location. The traditional tile retrieval method for visualization cannot distinguish between distinct layers and traverses all image datasets for each tile query. This process produces redundant queries and invalid access that can seriously affect the visualization performance of clients, servers and network transmission. This paper proposes an on-demand retrieval method for multi-layer images and defines semantic annotations to enrich the description of each dataset. By matching visualization demands with the semantic information of datasets, this method automatically filters inappropriate layers and finds the most suitable layer for the final tile query. The design and implementation are based on a two-layer NoSQL database architecture that provides scheduling optimization and concurrent processing capability. The experimental results reflect the effectiveness and stability of the approach for multi-layer retrieval in disaster reduction visualization.

Content-based intermedia synchronization

Science.gov (United States)

Oh, Dong-Young; Sampath-Kumar, Srihari; Rangan, P. Venkat

1995-03-01

Inter-media synchronization methods developed until now have been based on syntactic timestamping of video frames and audio samples. These methods are not fully appropriate for the synchronization of multimedia objects which may have to be accessed individually by their contents, e.g. content-base data retrieval. We propose a content-based multimedia synchronization scheme in which a media stream is viewed as hierarchial composition of smaller objects which are logically structured based on the contents, and the synchronization is achieved by deriving temporal relations among logical units of media object. content-based synchronization offers several advantages such as, elimination of the need for time stamping, freedom from limitations of jitter, synchronization of independently captured media objects in video editing, and compensation for inherent asynchronies in capture times of video and audio.

Supporting Keyword Search for Image Retrieval with Integration of Probabilistic Annotation

Directory of Open Access Journals (Sweden)

Tie Hua Zhou

2015-05-01

Full Text Available The ever-increasing quantities of digital photo resources are annotated with enriching vocabularies to form semantic annotations. Photo-sharing social networks have boosted the need for efficient and intuitive querying to respond to user requirements in large-scale image collections. In order to help users formulate efficient and effective image retrieval, we present a novel integration of a probabilistic model based on keyword query architecture that models the probability distribution of image annotations: allowing users to obtain satisfactory results from image retrieval via the integration of multiple annotations. We focus on the annotation integration step in order to specify the meaning of each image annotation, thus leading to the most representative annotations of the intent of a keyword search. For this demonstration, we show how a probabilistic model has been integrated to semantic annotations to allow users to intuitively define explicit and precise keyword queries in order to retrieve satisfactory image results distributed in heterogeneous large data sources. Our experiments on SBU (collected by Stony Brook University database show that (i our integrated annotation contains higher quality representatives and semantic matches; and (ii the results indicating annotation integration can indeed improve image search result quality.

Image encryption using fingerprint as key based on phase retrieval algorithm and public key cryptography

Science.gov (United States)

Zhao, Tieyu; Ran, Qiwen; Yuan, Lin; Chi, Yingying; Ma, Jing

2015-09-01

In this paper, a novel image encryption system with fingerprint used as a secret key is proposed based on the phase retrieval algorithm and RSA public key algorithm. In the system, the encryption keys include the fingerprint and the public key of RSA algorithm, while the decryption keys are the fingerprint and the private key of RSA algorithm. If the users share the fingerprint, then the system will meet the basic agreement of asymmetric cryptography. The system is also applicable for the information authentication. The fingerprint as secret key is used in both the encryption and decryption processes so that the receiver can identify the authenticity of the ciphertext by using the fingerprint in decryption process. Finally, the simulation results show the validity of the encryption scheme and the high robustness against attacks based on the phase retrieval technique.

Physical retrieval of precipitation water contents from Special Sensor Microwave/Imager (SSM/I) data. Part 1: A cloud ensemble/radiative parameterization for sensor response (report version)

Science.gov (United States)

Olson, William S.; Raymond, William H.

1990-01-01

The physical retrieval of geophysical parameters based upon remotely sensed data requires a sensor response model which relates the upwelling radiances that the sensor observes to the parameters to be retrieved. In the retrieval of precipitation water contents from satellite passive microwave observations, the sensor response model has two basic components. First, a description of the radiative transfer of microwaves through a precipitating atmosphere must be considered, because it is necessary to establish the physical relationship between precipitation water content and upwelling microwave brightness temperature. Also the spatial response of the satellite microwave sensor (or antenna pattern) must be included in the description of sensor response, since precipitation and the associated brightness temperature field can vary over a typical microwave sensor resolution footprint. A 'population' of convective cells, as well as stratiform clouds, are simulated using a computationally-efficient multi-cylinder cloud model. Ensembles of clouds selected at random from the population, distributed over a 25 km x 25 km model domain, serve as the basis for radiative transfer calculations of upwelling brightness temperatures at the SSM/I frequencies. Sensor spatial response is treated explicitly by convolving the upwelling brightness temperature by the domain-integrated SSM/I antenna patterns. The sensor response model is utilized in precipitation water content retrievals.

A Probabilistic Framework for Content-Based Diagnosis of Retinal Disease

Energy Technology Data Exchange (ETDEWEB)

Tobin Jr, Kenneth William [ORNL; Abdelrahman, Mohamed A [ORNL; Chaum, Edward [ORNL; Muthusamy Govindasamy, Vijaya Priya [ORNL; Karnowski, Thomas Paul [ORNL

2007-01-01

Diabetic retinopathy is the leading cause of blindness in the working age population around the world. Computer assisted analysis has the potential to assist in the early detection of diabetes by regular screening of large populations. The widespread availability of digital fundus cameras today is resulting in the accumulation of large image archives of diagnosed patient data that captures historical knowledge of retinal pathology. Through this research we are developing a content-based image retrieval method to verify our hypothesis that retinal pathology can be identified and quantified from visually similar retinal images in an image archive. We will present diagnostic results for specificity and sensitivity on a population of 395 fundus images representing the normal fundus and 14 stratified disease states.

[Vegetation index estimation by chlorophyll content of grassland based on spectral analysis].

Science.gov (United States)

Xiao, Han; Chen, Xiu-Wan; Yang, Zhen-Yu; Li, Huai-Yu; Zhu, Han

2014-11-01

Comparing the methods of existing remote sensing research on the estimation of chlorophyll content, the present paper confirms that the vegetation index is one of the most practical and popular research methods. In recent years, the increasingly serious problem of grassland degradation. This paper, firstly, analyzes the measured reflectance spectral curve and its first derivative curve in the grasslands of Songpan, Sichuan and Gongger, Inner Mongolia, conducts correlation analysis between these two spectral curves and chlorophyll content, and finds out the regulation between REP (red edge position) and grassland chlorophyll content, that is, the higher the chlorophyll content is, the higher the REIP (red-edge inflection point) value would be. Then, this paper constructs GCI (grassland chlorophyll index) and selects the most suitable band for retrieval. Finally, this paper calculates the GCI by the use of satellite hyperspectral image, conducts the verification and accuracy analysis of the calculation results compared with chlorophyll content data collected from field of twice experiments. The result shows that for grassland chlorophyll content, GCI has stronger sensitivity than other indices of chlorophyll, and has higher estimation accuracy. GCI is the first proposed to estimate the grassland chlorophyll content, and has wide application potential for the remote sensing retrieval of grassland chlorophyll content. In addition, the grassland chlorophyll content estimation method based on remote sensing retrieval in this paper provides new research ideas for other vegetation biochemical parameters' estimation, vegetation growth status' evaluation and grassland ecological environment change's monitoring.

Image Retargeting by Content-Aware Synthesis

OpenAIRE

Dong, Weiming; Wu, Fuzhang; Kong, Yan; Mei, Xing; Lee, Tong-Yee; Zhang, Xiaopeng

2014-01-01

Real-world images usually contain vivid contents and rich textural details, which will complicate the manipulation on them. In this paper, we design a new framework based on content-aware synthesis to enhance content-aware image retargeting. By detecting the textural regions in an image, the textural image content can be synthesized rather than simply distorted or cropped. This method enables the manipulation of textural & non-textural regions with different strategy since they have different...

A picture tells a thousand words: A content analysis of concussion-related images online.

Science.gov (United States)

Ahmed, Osman H; Lee, Hopin; Struik, Laura L

2016-09-01

Recently image-sharing social media platforms have become a popular medium for sharing health-related images and associated information. However within the field of sports medicine, and more specifically sports related concussion, the content of images and meta-data shared through these popular platforms have not been investigated. The aim of this study was to analyse the content of concussion-related images and its accompanying meta-data on image-sharing social media platforms. We retrieved 300 images from Pinterest, Instagram and Flickr by using a standardised search strategy. All images were screened and duplicate images were removed. We excluded images if they were: non-static images; illustrations; animations; or screenshots. The content and characteristics of each image was evaluated using a customised coding scheme to determine major content themes, and images were referenced to the current international concussion management guidelines. From 300 potentially relevant images, 176 images were included for analysis; 70 from Pinterest, 63 from Flickr, and 43 from Instagram. Most images were of another person or a scene (64%), with the primary content depicting injured individuals (39%). The primary purposes of the images were to share a concussion-related incident (33%) and to dispense education (19%). For those images where it could be evaluated, the majority (91%) were found to reflect the Sports Concussion Assessment Tool 3 (SCAT3) guidelines. The ability to rapidly disseminate rich information though photos, images, and infographics to a wide-reaching audience suggests that image-sharing social media platforms could be used as an effective communication tool for sports concussion. Public health strategies could direct educative content to targeted populations via the use of image-sharing platforms. Further research is required to understand how image-sharing platforms can be used to effectively relay evidence-based information to patients and sports medicine

Extraction of Lesion-Partitioned Features and Retrieval of Contrast-Enhanced Liver Images

Directory of Open Access Journals (Sweden)

Mei Yu

2012-01-01

Full Text Available The most critical step in grayscale medical image retrieval systems is feature extraction. Understanding the interrelatedness between the characteristics of lesion images and corresponding imaging features is crucial for image training, as well as for features extraction. A feature-extraction algorithm is developed based on different imaging properties of lesions and on the discrepancy in density between the lesions and their surrounding normal liver tissues in triple-phase contrast-enhanced computed tomographic (CT scans. The algorithm includes mainly two processes: (1 distance transformation, which is used to divide the lesion into distinct regions and represents the spatial structure distribution and (2 representation using bag of visual words (BoW based on regions. The evaluation of this system based on the proposed feature extraction algorithm shows excellent retrieval results for three types of liver lesions visible on triple-phase scans CT images. The results of the proposed feature extraction algorithm show that although single-phase scans achieve the average precision of 81.9%, 80.8%, and 70.2%, dual- and triple-phase scans achieve 86.3% and 88.0%.

Detection of Isoflavones Content in Soybean Based on Hyperspectral Imaging Technology

Directory of Open Access Journals (Sweden)

Tan Kezhu

2014-04-01

Full Text Available Because of many important biological activities, Soybean isoflavones which has great potential for exploitation is significant to practical applications. Due to the conventional methods for determination of soybean isoflavones having long detection period, used too many reagents, couldn’t be detected on-line, and other issues, we propose hyperspectral imaging technology to detect the contents of soybean isoflavones. Based on the 40 varieties of soybeans produced in Heilongjiang province, we get the spectral reflection datum of soybean samples varied from the soybean’s hyperspectral images which are collected by the hyperspectral imaging system, and apply high performance liquid chromatography (HPLC method to determine the true value of the selected samples of isoflavones. The feature wavelengths for isoflavones content prediction (1516, 1572, 1691, 1716 and 1760 nm were selected based on correlation analysis. The prediction model was established by using the method of BP neural network in order to realize the prediction of soybean isoflavones content analysis. The experimental results show that, the ANN model could predict isoflavones content of soybean samples with of 0.9679, the average relative error is 0.8032 %, and the mean square error (MSE is 0.110328, which indicates the effectiveness of the proposed method and provides a theoretical basis for the applications of hyerspectral imaging in non-destructive detection for interior quality of soybean.

A Hybrid Probabilistic Model for Unified Collaborative and Content-Based Image Tagging.

Science.gov (United States)

Zhou, Ning; Cheung, William K; Qiu, Guoping; Xue, Xiangyang

2011-07-01

The increasing availability of large quantities of user contributed images with labels has provided opportunities to develop automatic tools to tag images to facilitate image search and retrieval. In this paper, we present a novel hybrid probabilistic model (HPM) which integrates low-level image features and high-level user provided tags to automatically tag images. For images without any tags, HPM predicts new tags based solely on the low-level image features. For images with user provided tags, HPM jointly exploits both the image features and the tags in a unified probabilistic framework to recommend additional tags to label the images. The HPM framework makes use of the tag-image association matrix (TIAM). However, since the number of images is usually very large and user-provided tags are diverse, TIAM is very sparse, thus making it difficult to reliably estimate tag-to-tag co-occurrence probabilities. We developed a collaborative filtering method based on nonnegative matrix factorization (NMF) for tackling this data sparsity issue. Also, an L1 norm kernel method is used to estimate the correlations between image features and semantic concepts. The effectiveness of the proposed approach has been evaluated using three databases containing 5,000 images with 371 tags, 31,695 images with 5,587 tags, and 269,648 images with 5,018 tags, respectively.

Understanding human quality judgment in assessing online forum contents for thread retrieval purpose

Science.gov (United States)

Ismail, Zuriati; Salim, Naomie; Huspi, Sharin Hazlin

2017-10-01

Compared to traditional materials or journals, user-generated contents are not peer-reviewed. Lack of quality control and the explosive growth of web contents make the task of finding quality information on the web especially critical. The existence of new facilities for producing web contents such as forum makes this issue more significant. This study focuses on online forums threads or discussion, where the forums contain valuable human-generated information in a form of discussions. Due to the unique structure of the online forum pages, special techniques are required to organize and search for information in these forums. Quality biased retrieval is a retrieval approach that search for relevant document and prioritized higher quality documents. Despite major concern of quality content and recent development of quality biased retrieval, there is an urgent need to understand how quality content is being judged, for retrieval and performance evaluation purposes. Furthermore, even though there are various studies on the quality of information, there is no standard framework that has been established. The primary aim of this paper is to contribute to the understanding of human quality judgment in assessing online forum contents. The foundation of this study is to compare and evaluate different frameworks (for quality biased retrieval and information quality). This led to the finding that many quality dimensions are redundant and some dimensions are understood differently between different studies. We conducted a survey on crowdsourcing community to measure the importance of each quality dimensions found in various frameworks. Accuracy and ease of understanding are among top important dimensions while threads popularity and contents manipulability are among least important dimensions. This finding is beneficial in evaluating contents of online forum.

Retrieving high-resolution images over the Internet from an anatomical image database

Science.gov (United States)

Strupp-Adams, Annette; Henderson, Earl

1999-12-01

The Visible Human Data set is an important contribution to the national collection of anatomical images. To enhance the availability of these images, the National Library of Medicine has supported the design and development of a prototype object-oriented image database which imports, stores, and distributes high resolution anatomical images in both pixel and voxel formats. One of the key database modules is its client-server Internet interface. This Web interface provides a query engine with retrieval access to high-resolution anatomical images that range in size from 100KB for browser viewable rendered images, to 1GB for anatomical structures in voxel file formats. The Web query and retrieval client-server system is composed of applet GUIs, servlets, and RMI application modules which communicate with each other to allow users to query for specific anatomical structures, and retrieve image data as well as associated anatomical images from the database. Selected images can be downloaded individually as single files via HTTP or downloaded in batch-mode over the Internet to the user's machine through an applet that uses Netscape's Object Signing mechanism. The image database uses ObjectDesign's object-oriented DBMS, ObjectStore that has a Java interface. The query and retrieval systems has been tested with a Java-CDE window system, and on the x86 architecture using Windows NT 4.0. This paper describes the Java applet client search engine that queries the database; the Java client module that enables users to view anatomical images online; the Java application server interface to the database which organizes data returned to the user, and its distribution engine that allow users to download image files individually and/or in batch-mode.

Retrieval of Ice Cloud Properties Using an Optimal Estimation Algorithm and MODIS Infrared Observations. Part I: Forward Model, Error Analysis, and Information Content

Science.gov (United States)

Wang, Chenxi; Platnick, Steven; Zhang, Zhibo; Meyer, Kerry; Yang, Ping

2016-01-01

An optimal estimation (OE) retrieval method is developed to infer three ice cloud properties simultaneously: optical thickness (tau), effective radius (r(sub eff)), and cloud top height (h). This method is based on a fast radiative transfer (RT) model and infrared (IR) observations from the MODerate resolution Imaging Spectroradiometer (MODIS). This study conducts thorough error and information content analyses to understand the error propagation and performance of retrievals from various MODIS band combinations under different cloud/atmosphere states. Specifically, the algorithm takes into account four error sources: measurement uncertainty, fast RT model uncertainty, uncertainties in ancillary data sets (e.g., atmospheric state), and assumed ice crystal habit uncertainties. It is found that the ancillary and ice crystal habit error sources dominate the MODIS IR retrieval uncertainty and cannot be ignored. The information content analysis shows that for a given ice cloud, the use of four MODIS IR observations is sufficient to retrieve the three cloud properties. However, the selection of MODIS IR bands that provide the most information and their order of importance varies with both the ice cloud properties and the ambient atmospheric and the surface states. As a result, this study suggests the inclusion of all MODIS IR bands in practice since little a priori information is available.

Retrieval of ice cloud properties using an optimal estimation algorithm and MODIS infrared observations. Part I: Forward model, error analysis, and information content

Science.gov (United States)

Wang, Chenxi; Platnick, Steven; Zhang, Zhibo; Meyer, Kerry; Yang, Ping

2018-01-01

An optimal estimation (OE) retrieval method is developed to infer three ice cloud properties simultaneously: optical thickness (τ), effective radius (reff), and cloud-top height (h). This method is based on a fast radiative transfer (RT) model and infrared (IR) observations from the MODerate resolution Imaging Spectroradiometer (MODIS). This study conducts thorough error and information content analyses to understand the error propagation and performance of retrievals from various MODIS band combinations under different cloud/atmosphere states. Specifically, the algorithm takes into account four error sources: measurement uncertainty, fast RT model uncertainty, uncertainties in ancillary datasets (e.g., atmospheric state), and assumed ice crystal habit uncertainties. It is found that the ancillary and ice crystal habit error sources dominate the MODIS IR retrieval uncertainty and cannot be ignored. The information content analysis shows that, for a given ice cloud, the use of four MODIS IR observations is sufficient to retrieve the three cloud properties. However, the selection of MODIS IR bands that provide the most information and their order of importance varies with both the ice cloud properties and the ambient atmospheric and the surface states. As a result, this study suggests the inclusion of all MODIS IR bands in practice since little a priori information is available. PMID:29707470

Diversification of visual media retrieval results using saliency detection

Science.gov (United States)

Muratov, Oleg; Boato, Giulia; De Natale, Franesco G. B.

2013-03-01

Diversification of retrieval results allows for better and faster search. Recently there has been proposed different methods for diversification of image retrieval results mainly utilizing text information and techniques imported from natural language processing domain. However, images contain visual information that is impossible to describe in text and the use of visual features is inevitable. Visual saliency is information about the main object of an image implicitly included by humans while creating visual content. For this reason it is naturally to exploit this information for the task of diversification of the content. In this work we study whether visual saliency can be used for the task of diversification and propose a method for re-ranking image retrieval results using saliency. The evaluation has shown that the use of saliency information results in higher diversity of retrieval results.

Similarity estimation for reference image retrieval in mammograms using convolutional neural network

Science.gov (United States)

Muramatsu, Chisako; Higuchi, Shunichi; Morita, Takako; Oiwa, Mikinao; Fujita, Hiroshi

2018-02-01

Periodic breast cancer screening with mammography is considered effective in decreasing breast cancer mortality. For screening programs to be successful, an intelligent image analytic system may support radiologists' efficient image interpretation. In our previous studies, we have investigated image retrieval schemes for diagnostic references of breast lesions on mammograms and ultrasound images. Using a machine learning method, reliable similarity measures that agree with radiologists' similarity were determined and relevant images could be retrieved. However, our previous method includes a feature extraction step, in which hand crafted features were determined based on manual outlines of the masses. Obtaining the manual outlines of masses is not practical in clinical practice and such data would be operator-dependent. In this study, we investigated a similarity estimation scheme using a convolutional neural network (CNN) to skip such procedure and to determine data-driven similarity scores. By using CNN as feature extractor, in which extracted features were employed in determination of similarity measures with a conventional 3-layered neural network, the determined similarity measures were correlated well with the subjective ratings and the precision of retrieving diagnostically relevant images was comparable with that of the conventional method using handcrafted features. By using CNN for determination of similarity measure directly, the result was also comparable. By optimizing the network parameters, results may be further improved. The proposed method has a potential usefulness in determination of similarity measure without precise lesion outlines for retrieval of similar mass images on mammograms.

A novel method for efficient archiving and retrieval of biomedical images using MPEG-7

Science.gov (United States)

Meyer, Joerg; Pahwa, Ash

2004-10-01

Digital archiving and efficient retrieval of radiological scans have become critical steps in contemporary medical diagnostics. Since more and more images and image sequences (single scans or video) from various modalities (CT/MRI/PET/digital X-ray) are now available in digital formats (e.g., DICOM-3), hospitals and radiology clinics need to implement efficient protocols capable of managing the enormous amounts of data generated daily in a typical clinical routine. We present a method that appears to be a viable way to eliminate the tedious step of manually annotating image and video material for database indexing. MPEG-7 is a new framework that standardizes the way images are characterized in terms of color, shape, and other abstract, content-related criteria. A set of standardized descriptors that are automatically generated from an image is used to compare an image to other images in a database, and to compute the distance between two images for a given application domain. Text-based database queries can be replaced with image-based queries using MPEG-7. Consequently, image queries can be conducted without any prior knowledge of the keys that were used as indices in the database. Since the decoding and matching steps are not part of the MPEG-7 standard, this method also enables searches that were not planned by the time the keys were generated.

Phase-image-based content-addressable holographic data storage

Science.gov (United States)

John, Renu; Joseph, Joby; Singh, Kehar

2004-03-01

We propose and demonstrate the use of phase images for content-addressable holographic data storage. Use of binary phase-based data pages with 0 and π phase changes, produces uniform spectral distribution at the Fourier plane. The absence of strong DC component at the Fourier plane and more intensity of higher order spatial frequencies facilitate better recording of higher spatial frequencies, and improves the discrimination capability of the content-addressable memory. This improves the results of the associative recall in a holographic memory system, and can give low number of false hits even for small search arguments. The phase-modulated pixels also provide an opportunity of subtraction among data pixels leading to better discrimination between similar data pages.

Information management for high content live cell imaging

Directory of Open Access Journals (Sweden)

White Michael RH

2009-07-01

Full Text Available Abstract Background High content live cell imaging experiments are able to track the cellular localisation of labelled proteins in multiple live cells over a time course. Experiments using high content live cell imaging will generate multiple large datasets that are often stored in an ad-hoc manner. This hinders identification of previously gathered data that may be relevant to current analyses. Whilst solutions exist for managing image data, they are primarily concerned with storage and retrieval of the images themselves and not the data derived from the images. There is therefore a requirement for an information management solution that facilitates the indexing of experimental metadata and results of high content live cell imaging experiments. Results We have designed and implemented a data model and information management solution for the data gathered through high content live cell imaging experiments. Many of the experiments to be stored measure the translocation of fluorescently labelled proteins from cytoplasm to nucleus in individual cells. The functionality of this database has been enhanced by the addition of an algorithm that automatically annotates results of these experiments with the timings of translocations and periods of any oscillatory translocations as they are uploaded to the repository. Testing has shown the algorithm to perform well with a variety of previously unseen data. Conclusion Our repository is a fully functional example of how high throughput imaging data may be effectively indexed and managed to address the requirements of end users. By implementing the automated analysis of experimental results, we have provided a clear impetus for individuals to ensure that their data forms part of that which is stored in the repository. Although focused on imaging, the solution provided is sufficiently generic to be applied to other functional proteomics and genomics experiments. The software is available from: fhttp://code.google.com/p/livecellim/

Retrieval of spruce leaf chlorophyll content from airborne image data using continuum removal and radiative transfer

Czech Academy of Sciences Publication Activity Database

Malenovský, Z.; Homolová, L.; Zurita-Milla, R.; Lukeš, Petr; Kaplan, Věroslav; Hanuš, Jan; Gastellu-Etchegory, J.P.; Schaepman, M.E.

2013-01-01

Roč. 131, APR (2013), s. 85-102 ISSN 0034-4257 R&D Projects: GA MŠk(CZ) ED1.1.00/02.0073; GA MŠk(CZ) LM2010007 Institutional support: RVO:67179843 Keywords : Chlorophyll retrieval * Imaging spectroscopy * Continuum removal * Radiative transfer * PROSPECT * DART * Optical indices * Norway spruce * High spatial resolution * AISA Subject RIV: EH - Ecology, Behaviour Impact factor: 4.769, year: 2013

Design Pattern Retrieval and Style Analysis for Content Creation of Comic Figures

Directory of Open Access Journals (Sweden)

Bor-Shen Lin

2014-01-01

Full Text Available Placement of objects within a constrained space is a common challenge for designers; it is associated with decisions regarding the furnishing of a space with furniture, collocation of dressings, flower arrangement, and design of comic figures. Though many design elements can be shared on the Internet in the current age of technology, it is still not easy to compare or search for design patterns based on these elements. Thus, it is difficult for designers to efficiently retrieve similar patterns designed by others, to compare them, or to learn from them. This paper proposes the architecture of representing, comparing, retrieving, and analyzing the design patterns of digital contents for design support. This scheme can help the designers to explore the huge space of design patterns efficiently, to analyze and summarize the design styles quickly, and to improve design skills and stimulate imaginations effectively during the process of learning or creating. The proposed scheme has been verified with a design support system for the content creation of comic figures. It is generally applicable to the creation of digital contents and shows potential for applications in the fields of design and education.

Curvature histogram features for retrieval of images of smooth 3D objects

International Nuclear Information System (INIS)

Zhdanov, I; Scherbakov, O; Potapov, A; Peterson, M

2014-01-01

We consider image features on the base of histograms of oriented gradients (HOG) with addition of contour curvature histogram (HOG-CH), and also compare it with results of known scale-invariant feature transform (SIFT) approach in application to retrieval of images of smooth 3D objects.

Towards brain-activity-controlled information retrieval: Decoding image relevance from MEG signals.

Science.gov (United States)

Kauppi, Jukka-Pekka; Kandemir, Melih; Saarinen, Veli-Matti; Hirvenkari, Lotta; Parkkonen, Lauri; Klami, Arto; Hari, Riitta; Kaski, Samuel

2015-05-15

We hypothesize that brain activity can be used to control future information retrieval systems. To this end, we conducted a feasibility study on predicting the relevance of visual objects from brain activity. We analyze both magnetoencephalographic (MEG) and gaze signals from nine subjects who were viewing image collages, a subset of which was relevant to a predetermined task. We report three findings: i) the relevance of an image a subject looks at can be decoded from MEG signals with performance significantly better than chance, ii) fusion of gaze-based and MEG-based classifiers significantly improves the prediction performance compared to using either signal alone, and iii) non-linear classification of the MEG signals using Gaussian process classifiers outperforms linear classification. These findings break new ground for building brain-activity-based interactive image retrieval systems, as well as for systems utilizing feedback both from brain activity and eye movements. Copyright © 2015 Elsevier Inc. All rights reserved.

Content Based Searching for INIS

International Nuclear Information System (INIS)

Jain, V.; Jain, R.K.

2016-01-01

Full text: Whatever a user wants is available on the internet, but to retrieve the information efficiently, a multilingual and most-relevant document search engine is a must. Most current search engines are word based or pattern based. They do not consider the meaning of the query posed to them; purely based on the keywords of the query; no support of multilingual query and and dismissal of nonrelevant results. Current information-retrieval techniques either rely on an encoding process, using a certain perspective or classification scheme, to describe a given item, or perform a full-text analysis, searching for user-specified words. Neither case guarantees content matching because an encoded description might reflect only part of the content and the mere occurrence of a word does not necessarily reflect the document’s content. For general documents, there doesn’t yet seem to be a much better option than lazy full-text analysis, by manually going through those endless results pages. In contrast to this, new search engine should extract the meaning of the query and then perform the search based on this extracted meaning. New search engine should also employ Interlingua based machine translation technology to present information in the language of choice of the user. (author

Coupled Retrieval of Aerosol Properties and Surface Reflection Using the Airborne Multi-angle SpectroPolarimetric Imager (AirMSPI)

Science.gov (United States)

Xu, F.; van Harten, G.; Kalashnikova, O. V.; Diner, D. J.; Seidel, F. C.; Garay, M. J.; Dubovik, O.

2016-12-01

The Airborne Multi-angle SpectroPolarimetric Imager (AirMSPI) [1] has been flying aboard the NASA ER-2 high altitude aircraft since October 2010. In step-and-stare operation mode, AirMSPI acquires radiance and polarization data at 355, 380, 445, 470*, 555, 660*, 865*, and 935 nm (* denotes polarimetric bands). The imaged area covers about 10 km by 10 km and is observed from 9 view angles between ±67° off of nadir. We have developed an efficient and flexible code that uses the information content of AirMSPI data for a coupled retrieval of aerosol properties and surface reflection. The retrieval was built based on the multi-pixel optimization concept [2], with the use of a hybrid radiative transfer model [3] that combines the Markov Chain [4] and adding/doubling methods [5]. The convergence and robustness of our algorithm is ensured by applying constraints on (a) the spectral variation of the Bidirectional Polarization Distribution Function (BPDF) and angular shape of the Bidirectional Reflectance Distribution Function (BRDF); (b) the spectral variation of aerosol optical properties; and (c) the spatial variation of aerosol parameters across neighboring image pixels. Our retrieval approach has been tested using over 20 AirMSPI datasets having low to moderately high aerosol loadings ( 0.02550-nmSpace Sci. Rev. 16, 527 (1974).

A Study on Retrieval Algorithm of Black Water Aggregation in Taihu Lake Based on HJ-1 Satellite Images

International Nuclear Information System (INIS)

Lei, Zou; Bing, Zhang; Junsheng, Li; Qian, Shen; Fangfang, Zhang; Ganlin, Wang

2014-01-01

The phenomenon of black water aggregation (BWA) occurs in inland water when massive algal bodies aggregate, die, and react with the toxic sludge in certain climate conditions to deprive the water of oxygen. This process results in the deterioration of water quality and damage to the ecosystem. Because charge coupled device (CCD) camera data from the Chinese HJ environmental satellite shows high potential in monitoring BWA, we acquired four HJ-CCD images of Taihu Lake captured during 2009 to 2011 to study this phenomenon. The first study site was selected near the Shore of Taihu Lake. We pre-processed the HJ-CCD images and analyzed the digital number (DN) gray values in the research area and in typical BWA areas. The results show that the DN values of visible bands in BWA areas are obviously lower than those in the research areas. Moreover, we developed an empirical retrieving algorithm of BWA based on the DN mean values and variances of research areas. Finally, we tested the accuracy of this empirical algorithm. The retrieving accuracies were89.9%, 58.1%, 73.4%, and 85.5%, respectively, which demonstrates the efficiency of empirical algorithm in retrieving the approximate distributions of BWA

Quantifying Vegetation Biophysical Variables from Imaging Spectroscopy Data: A Review on Retrieval Methods

Science.gov (United States)

Verrelst, Jochem; Malenovský, Zbyněk; Van der Tol, Christiaan; Camps-Valls, Gustau; Gastellu-Etchegorry, Jean-Philippe; Lewis, Philip; North, Peter; Moreno, Jose

2018-06-01

An unprecedented spectroscopic data stream will soon become available with forthcoming Earth-observing satellite missions equipped with imaging spectroradiometers. This data stream will open up a vast array of opportunities to quantify a diversity of biochemical and structural vegetation properties. The processing requirements for such large data streams require reliable retrieval techniques enabling the spatiotemporally explicit quantification of biophysical variables. With the aim of preparing for this new era of Earth observation, this review summarizes the state-of-the-art retrieval methods that have been applied in experimental imaging spectroscopy studies inferring all kinds of vegetation biophysical variables. Identified retrieval methods are categorized into: (1) parametric regression, including vegetation indices, shape indices and spectral transformations; (2) nonparametric regression, including linear and nonlinear machine learning regression algorithms; (3) physically based, including inversion of radiative transfer models (RTMs) using numerical optimization and look-up table approaches; and (4) hybrid regression methods, which combine RTM simulations with machine learning regression methods. For each of these categories, an overview of widely applied methods with application to mapping vegetation properties is given. In view of processing imaging spectroscopy data, a critical aspect involves the challenge of dealing with spectral multicollinearity. The ability to provide robust estimates, retrieval uncertainties and acceptable retrieval processing speed are other important aspects in view of operational processing. Recommendations towards new-generation spectroscopy-based processing chains for operational production of biophysical variables are given.

Optical image encryption based on phase retrieval combined with three-dimensional particle-like distribution

International Nuclear Information System (INIS)

Chen, Wen; Chen, Xudong; Sheppard, Colin J R

2012-01-01

We propose a new phase retrieval algorithm for optical image encryption in three-dimensional (3D) space. The two-dimensional (2D) plaintext is considered as a series of particles distributed in 3D space, and an iterative phase retrieval algorithm is developed to encrypt the series of particles into phase-only masks. The feasibility and effectiveness of the proposed method are demonstrated by a numerical experiment, and the advantages and security of the proposed optical cryptosystems are also analyzed and discussed. (paper)

Blind phase retrieval for aberrated linear shift-invariant imaging systems

International Nuclear Information System (INIS)

Yu, Rotha P; Paganin, David M

2010-01-01

We develop a means to reconstruct an input complex coherent scalar wavefield, given a through focal series (TFS) of three intensity images output from a two-dimensional (2D) linear shift-invariant optical imaging system with unknown aberrations. This blind phase retrieval technique unites two methods, namely (i) TFS phase retrieval and (ii) iterative blind deconvolution. The efficacy of our blind phase retrieval procedure has been demonstrated using simulated data, for a variety of Poisson noise levels.

Content Based Image Matching for Planetary Science

Science.gov (United States)

Deans, M. C.; Meyer, C.

2006-12-01

Planetary missions generate large volumes of data. With the MER rovers still functioning on Mars, PDS contains over 7200 released images from the Microscopic Imagers alone. These data products are only searchable by keys such as the Sol, spacecraft clock, or rover motion counter index, with little connection to the semantic content of the images. We have developed a method for matching images based on the visual textures in images. For every image in a database, a series of filters compute the image response to localized frequencies and orientations. Filter responses are turned into a low dimensional descriptor vector, generating a 37 dimensional fingerprint. For images such as the MER MI, this represents a compression ratio of 99.9965% (the fingerprint is approximately 0.0035% the size of the original image). At query time, fingerprints are quickly matched to find images with similar appearance. Image databases containing several thousand images are preprocessed offline in a matter of hours. Image matches from the database are found in a matter of seconds. We have demonstrated this image matching technique using three sources of data. The first database consists of 7200 images from the MER Microscopic Imager. The second database consists of 3500 images from the Narrow Angle Mars Orbital Camera (MOC-NA), which were cropped into 1024×1024 sub-images for consistency. The third database consists of 7500 scanned archival photos from the Apollo Metric Camera. Example query results from all three data sources are shown. We have also carried out user tests to evaluate matching performance by hand labeling results. User tests verify approximately 20% false positive rate for the top 14 results for MOC NA and MER MI data. This means typically 10 to 12 results out of 14 match the query image sufficiently. This represents a powerful search tool for databases of thousands of images where the a priori match probability for an image might be less than 1%. Qualitatively, correct

Object-Location-Aware Hashing for Multi-Label Image Retrieval via Automatic Mask Learning.

Science.gov (United States)

Huang, Chang-Qin; Yang, Shang-Ming; Pan, Yan; Lai, Han-Jiang

2018-09-01

Learning-based hashing is a leading approach of approximate nearest neighbor search for large-scale image retrieval. In this paper, we develop a deep supervised hashing method for multi-label image retrieval, in which we propose to learn a binary "mask" map that can identify the approximate locations of objects in an image, so that we use this binary "mask" map to obtain length-limited hash codes which mainly focus on an image's objects but ignore the background. The proposed deep architecture consists of four parts: 1) a convolutional sub-network to generate effective image features; 2) a binary "mask" sub-network to identify image objects' approximate locations; 3) a weighted average pooling operation based on the binary "mask" to obtain feature representations and hash codes that pay most attention to foreground objects but ignore the background; and 4) the combination of a triplet ranking loss designed to preserve relative similarities among images and a cross entropy loss defined on image labels. We conduct comprehensive evaluations on four multi-label image data sets. The results indicate that the proposed hashing method achieves superior performance gains over the state-of-the-art supervised or unsupervised hashing baselines.

Fast Depiction Invariant Visual Similarity for Content Based Image Retrieval Based on Data-driven Visual Similarity using Linear Discriminant Analysis

Science.gov (United States)

Wihardi, Y.; Setiawan, W.; Nugraha, E.

2018-01-01

On this research we try to build CBIRS based on Learning Distance/Similarity Function using Linear Discriminant Analysis (LDA) and Histogram of Oriented Gradient (HoG) feature. Our method is invariant to depiction of image, such as similarity of image to image, sketch to image, and painting to image. LDA can decrease execution time compared to state of the art method, but it still needs an improvement in term of accuracy. Inaccuracy in our experiment happen because we did not perform sliding windows search and because of low number of negative samples as natural-world images.

Contextual Distance Refining for Image Retrieval

KAUST Repository

Islam, Almasri

2014-01-01

Recently, a number of methods have been proposed to improve image retrieval accuracy by capturing context information. These methods try to compensate for the fact that a visually less similar image might be more relevant because it depicts the same object. We propose a new quick method for refining any pairwise distance metric, it works by iteratively discovering the object in the image from the most similar images, and then refine the distance metric accordingly. Test show that our technique improves over the state of art in terms of accuracy over the MPEG7 dataset.

Contextual Distance Refining for Image Retrieval

KAUST Repository

Islam, Almasri

2014-09-16

Recently, a number of methods have been proposed to improve image retrieval accuracy by capturing context information. These methods try to compensate for the fact that a visually less similar image might be more relevant because it depicts the same object. We propose a new quick method for refining any pairwise distance metric, it works by iteratively discovering the object in the image from the most similar images, and then refine the distance metric accordingly. Test show that our technique improves over the state of art in terms of accuracy over the MPEG7 dataset.

Color and neighbor edge directional difference feature for image retrieval

Institute of Scientific and Technical Information of China (English)

Chaobing Huang; Shengsheng Yu; Jingli Zhou; Hongwei Lu

2005-01-01

@@ A novel image feature termed neighbor edge directional difference unit histogram is proposed, in which the neighbor edge directional difference unit is defined and computed for every pixel in the image, and is used to generate the neighbor edge directional difference unit histogram. This histogram and color histogram are used as feature indexes to retrieve color image. The feature is invariant to image scaling and translation and has more powerful descriptive for the natural color images. Experimental results show that the feature can achieve better retrieval performance than other color-spatial features.

Dead fuel moisture estimation with MSG-SEVIRI data. Retrieval of meteorological data for the calculation of the equilibrium moisture content

DEFF Research Database (Denmark)

Nieto Solana, Hector; Sandholt, Inge; Aguado, Inmaculada

2010-01-01

In this study we propose to use remote sensing data to estimate hourly meteorological data and then assess the moisture content of dead fuels. Three different models to estimate the equilibrium moisture content (EMC) were applied together with remotely sensed retrieved air temperature and relative...... humidity. The input data were acquired by the Spinning Enhanced Visible and Infrared Imager (SEVIRI) sensor, on board the Meteosat Second Generation (MSG) satellite, from which air temperature and relative humidity were estimated every 15 min. Air temperature estimations are based on the Temperature-Vegetation...... Index (TVX) algorithm. This algorithm exploits the inverse linear relationship between the land surface temperature and the vegetation fractional cover. This relationship was evaluated in a spatial window where the meteorological forcing is assumed to be constant. To estimate the vapour pressure...

Multimedia information retrieval theory and techniques

CERN Document Server

Raieli, Roberto

2013-01-01

Novel processing and searching tools for the management of new multimedia documents have developed. Multimedia Information Retrieval (MMIR) is an organic system made up of Text Retrieval (TR); Visual Retrieval (VR); Video Retrieval (VDR); and Audio Retrieval (AR) systems. So that each type of digital document may be analysed and searched by the elements of language appropriate to its nature, search criteria must be extended. Such an approach is known as the Content Based Information Retrieval (CBIR), and is the core of MMIR. This novel content-based concept of information handling needs to be integrated with more traditional semantics. Multimedia Information Retrieval focuses on the tools of processing and searching applicable to the content-based management of new multimedia documents. Translated from Italian by Giles Smith, the book is divided in to two parts. Part one discusses MMIR and related theories, and puts forward new methodologies; part two reviews various experimental and operating MMIR systems, a...

Robust information encryption diffractive-imaging-based scheme with special phase retrieval algorithm for a customized data container

Science.gov (United States)

Qin, Yi; Wang, Zhipeng; Wang, Hongjuan; Gong, Qiong; Zhou, Nanrun

2018-06-01

The diffractive-imaging-based encryption (DIBE) scheme has aroused wide interesting due to its compact architecture and low requirement of conditions. Nevertheless, the primary information can hardly be recovered exactly in the real applications when considering the speckle noise and potential occlusion imposed on the ciphertext. To deal with this issue, the customized data container (CDC) into DIBE is introduced and a new phase retrieval algorithm (PRA) for plaintext retrieval is proposed. The PRA, designed according to the peculiarity of the CDC, combines two key techniques from previous approaches, i.e., input-support-constraint and median-filtering. The proposed scheme can guarantee totally the reconstruction of the primary information despite heavy noise or occlusion and its effectiveness and feasibility have been demonstrated with simulation results.

Retrieval of bilingual autobiographical memories: effects of cue language and cue imageability.

Science.gov (United States)

Mortensen, Linda; Berntsen, Dorthe; Bohn, Ocke-Schwen

2015-01-01

An important issue in theories of bilingual autobiographical memory is whether linguistically encoded memories are represented in language-specific stores or in a common language-independent store. Previous research has found that autobiographical memory retrieval is facilitated when the language of the cue is the same as the language of encoding, consistent with language-specific memory stores. The present study examined whether this language congruency effect is influenced by cue imageability. Danish-English bilinguals retrieved autobiographical memories in response to Danish and English high- or low-imageability cues. Retrieval latencies were shorter to Danish than English cues and shorter to high- than low-imageability cues. Importantly, the cue language effect was stronger for low-than high-imageability cues. To examine the relationship between cue language and the language of internal retrieval, participants identified the language in which the memories were internally retrieved. More memories were retrieved when the cue language was the same as the internal language than when the cue was in the other language, and more memories were identified as being internally retrieved in Danish than English, regardless of the cue language. These results provide further evidence for language congruency effects in bilingual memory and suggest that this effect is influenced by cue imageability.

Chinese Herbal Medicine Image Recognition and Retrieval by Convolutional Neural Network.

Science.gov (United States)

Sun, Xin; Qian, Huinan

2016-01-01

Chinese herbal medicine image recognition and retrieval have great potential of practical applications. Several previous studies have focused on the recognition with hand-crafted image features, but there are two limitations in them. Firstly, most of these hand-crafted features are low-level image representation, which is easily affected by noise and background. Secondly, the medicine images are very clean without any backgrounds, which makes it difficult to use in practical applications. Therefore, designing high-level image representation for recognition and retrieval in real world medicine images is facing a great challenge. Inspired by the recent progress of deep learning in computer vision, we realize that deep learning methods may provide robust medicine image representation. In this paper, we propose to use the Convolutional Neural Network (CNN) for Chinese herbal medicine image recognition and retrieval. For the recognition problem, we use the softmax loss to optimize the recognition network; then for the retrieval problem, we fine-tune the recognition network by adding a triplet loss to search for the most similar medicine images. To evaluate our method, we construct a public database of herbal medicine images with cluttered backgrounds, which has in total 5523 images with 95 popular Chinese medicine categories. Experimental results show that our method can achieve the average recognition precision of 71% and the average retrieval precision of 53% over all the 95 medicine categories, which are quite promising given the fact that the real world images have multiple pieces of occluded herbal and cluttered backgrounds. Besides, our proposed method achieves the state-of-the-art performance by improving previous studies with a large margin.

Single-image phase retrieval using an edge illumination X-ray phase-contrast imaging setup

Energy Technology Data Exchange (ETDEWEB)

Diemoz, Paul C., E-mail: p.diemoz@ucl.ac.uk; Vittoria, Fabio A. [University College London, London WC1 E6BT (United Kingdom); Research Complex at Harwell, Oxford Harwell Campus, Didcot OX11 0FA (United Kingdom); Hagen, Charlotte K.; Endrizzi, Marco [University College London, London WC1 E6BT (United Kingdom); Coan, Paola [Ludwig-Maximilians-University, Munich 81377 (Germany); Ludwig-Maximilians-University, Garching 85748 (Germany); Brun, Emmanuel [Ludwig-Maximilians-University, Garching 85748 (Germany); European Synchrotron Radiation Facility, Grenoble 38043 (France); Wagner, Ulrich H.; Rau, Christoph [Diamond Light Source, Harwell Oxford Campus, Didcot OX11 0DE (United Kingdom); Robinson, Ian K. [Research Complex at Harwell, Oxford Harwell Campus, Didcot OX11 0FA (United Kingdom); London Centre for Nanotechnology, London WC1 H0AH (United Kingdom); Bravin, Alberto [European Synchrotron Radiation Facility, Grenoble 38043 (France); Olivo, Alessandro [University College London, London WC1 E6BT (United Kingdom); Research Complex at Harwell, Oxford Harwell Campus, Didcot OX11 0FA (United Kingdom)

2015-06-25

A method enabling the retrieval of thickness or projected electron density of a sample from a single input image is derived theoretically and successfully demonstrated on experimental data. A method is proposed which enables the retrieval of the thickness or of the projected electron density of a sample from a single input image acquired with an edge illumination phase-contrast imaging setup. The method assumes the case of a quasi-homogeneous sample, i.e. a sample with a constant ratio between the real and imaginary parts of its complex refractive index. Compared with current methods based on combining two edge illumination images acquired in different configurations of the setup, this new approach presents advantages in terms of simplicity of acquisition procedure and shorter data collection time, which are very important especially for applications such as computed tomography and dynamical imaging. Furthermore, the fact that phase information is directly extracted, instead of its derivative, can enable a simpler image interpretation and be beneficial for subsequent processing such as segmentation. The method is first theoretically derived and its conditions of applicability defined. Quantitative accuracy in the case of homogeneous objects as well as enhanced image quality for the imaging of complex biological samples are demonstrated through experiments at two synchrotron radiation facilities. The large range of applicability, the robustness against noise and the need for only one input image suggest a high potential for investigations in various research subjects.

A high accuracy land use/cover retrieval system

Directory of Open Access Journals (Sweden)

Alaa Hefnawy

2012-03-01

Full Text Available The effects of spatial resolution on the accuracy of mapping land use/cover types have received increasing attention as a large number of multi-scale earth observation data become available. Although many methods of semi automated image classification of remotely sensed data have been established for improving the accuracy of land use/cover classification during the past 40 years, most of them were employed in single-resolution image classification, which led to unsatisfactory results. In this paper, we propose a multi-resolution fast adaptive content-based retrieval system of satellite images. Through our proposed system, we apply a Super Resolution technique for the Landsat-TM images to have a high resolution dataset. The human–computer interactive system is based on modified radial basis function for retrieval of satellite database images. We apply the backpropagation supervised artificial neural network classifier for both the multi and single resolution datasets. The results show significant improved land use/cover classification accuracy for the multi-resolution approach compared with those from single-resolution approach.

Neural mechanism of lmplicit and explicit memory retrieval: functional MR imaging

International Nuclear Information System (INIS)

Kang, Heoung Keun; Jeong, Gwang Woo; Park, Tae Jin; Seo, Jeong Jin; Kim, Hyung Joong; Eun, Sung Jong; Chung, Tae Woong

2003-01-01

To identify, using functional MR imaging, distinct cerebral centers and to evaluate the neural mechanism associated with implicit and explicit retrieval of words during conceptual processing. Seven healthy volunteers aged 21-25 (mean, 22) years underwent BOLD-based fMR imaging using a 1.5T signa horizon echospeed MR system. To activate the cerebral cortices, a series of tasks was performed as follows: the encoding of two-syllable words, and implicit and explicit retrieval of previously learned words during conceptual processing. The activation paradigm consisted of a cycle of alternating periods of 30 seconds of stimulation and 30 seconds of rest. Stimulation was accomplished by encoding eight two-syllable words and the retrieval of previously presented words, while the control condition was a white screen with a small fixed cross. During the tasks we acquired ten slices (6 mm slice thickness, 1 mm gap) parallel to the AC-PC line, and the resulting functional activation maps were reconstructed using a statistical parametric mapping program (SPM99). A comparison of activation ratios (percentages), based on the number of volunteers, showed that activation of Rhs-35, PoCiG-23 and ICiG-26·30 was associated with explicit retrieval only; other brain areas were activated during the performance of both implicit and explicit retrieval tasks. Activation ratios were higher for explicit tasks than for implicit; in the cingulate gyrus and temporal lobe they were 30% and 10% greater, respectively. During explicit retrieval, a distinct brain activation index (percentage) was seen in the temporal, parietal, and occipital lobe and cingulate gyrus, and PrCeG-4, Pr/ PoCeG-43 in the frontal lobe. During implicit retrieval, on the other hand, activity was greater in the frontal lobe, including the areas of SCA-25, SFG/MFG-10, IFG-44·45, OrbG-11·47, SFG-6·8 and MFG-9·46. Overall, activation was lateralized mainly in the left hemisphere during both implicit and explicit retrieval

Neural mechanism of lmplicit and explicit memory retrieval: functional MR imaging

Energy Technology Data Exchange (ETDEWEB)

Kang, Heoung Keun; Jeong, Gwang Woo; Park, Tae Jin; Seo, Jeong Jin; Kim, Hyung Joong; Eun, Sung Jong; Chung, Tae Woong [Chonnam National University Medical School, Gwangju (Korea, Republic of)

2003-03-01

To identify, using functional MR imaging, distinct cerebral centers and to evaluate the neural mechanism associated with implicit and explicit retrieval of words during conceptual processing. Seven healthy volunteers aged 21-25 (mean, 22) years underwent BOLD-based fMR imaging using a 1.5T signa horizon echospeed MR system. To activate the cerebral cortices, a series of tasks was performed as follows: the encoding of two-syllable words, and implicit and explicit retrieval of previously learned words during conceptual processing. The activation paradigm consisted of a cycle of alternating periods of 30 seconds of stimulation and 30 seconds of rest. Stimulation was accomplished by encoding eight two-syllable words and the retrieval of previously presented words, while the control condition was a white screen with a small fixed cross. During the tasks we acquired ten slices (6 mm slice thickness, 1 mm gap) parallel to the AC-PC line, and the resulting functional activation maps were reconstructed using a statistical parametric mapping program (SPM99). A comparison of activation ratios (percentages), based on the number of volunteers, showed that activation of Rhs-35, PoCiG-23 and ICiG-26{center_dot}30 was associated with explicit retrieval only; other brain areas were activated during the performance of both implicit and explicit retrieval tasks. Activation ratios were higher for explicit tasks than for implicit; in the cingulate gyrus and temporal lobe they were 30% and 10% greater, respectively. During explicit retrieval, a distinct brain activation index (percentage) was seen in the temporal, parietal, and occipital lobe and cingulate gyrus, and PrCeG-4, Pr/ PoCeG-43 in the frontal lobe. During implicit retrieval, on the other hand, activity was greater in the frontal lobe, including the areas of SCA-25, SFG/MFG-10, IFG-44{center_dot}45, OrbG-11{center_dot}47, SFG-6{center_dot}8 and MFG-9{center_dot}46. Overall, activation was lateralized mainly in the left

Beyond information retrieval: information discovery and multimedia information retrieval

OpenAIRE

Roberto Raieli

2017-01-01

The paper compares the current methodologies for search and discovery of information and information resources: terminological search and term-based language, own of information retrieval (IR); semantic search and information discovery, being developed mainly through the language of linked data; semiotic search and content-based language, experienced by multimedia information retrieval (MIR).MIR semiotic methodology is, then, detailed.

Retrieval of Landuse and Hydrology-based Parameters from ...

African Journals Online (AJOL)

Landuse and hydrology-based information on the Volta Lake Basin have been retrieved from Satellite remote sensing data. The results obtained could be applied in Hydro-Geographical Information System models, such as the TOPMODEL, for water balance studies. Eight Synthetic Aperture Radar Precision Images of the ...

Information content of OCO-2 oxygen A-band channels for retrieving marine liquid cloud properties

Science.gov (United States)

Richardson, Mark; Stephens, Graeme L.

2018-03-01

Information content analysis is used to select channels for a marine liquid cloud retrieval using the high-spectral-resolution oxygen A-band instrument on NASA's Orbiting Carbon Observatory-2 (OCO-2). Desired retrieval properties are cloud optical depth, cloud-top pressure and cloud pressure thickness, which is the geometric thickness expressed in hectopascals. Based on information content criteria we select a micro-window of 75 of the 853 functioning OCO-2 channels spanning 763.5-764.6 nm and perform a series of synthetic retrievals with perturbed initial conditions. We estimate posterior errors from the sample standard deviations and obtain ±0.75 in optical depth and ±12.9 hPa in both cloud-top pressure and cloud pressure thickness, although removing the 10 % of samples with the highest χ2 reduces posterior error in cloud-top pressure to ±2.9 hPa and cloud pressure thickness to ±2.5 hPa. The application of this retrieval to real OCO-2 measurements is briefly discussed, along with limitations and the greatest caution is urged regarding the assumption of a single homogeneous cloud layer, which is often, but not always, a reasonable approximation for marine boundary layer clouds.

Coupled binary embedding for large-scale image retrieval.

Science.gov (United States)

Zheng, Liang; Wang, Shengjin; Tian, Qi

2014-08-01

Visual matching is a crucial step in image retrieval based on the bag-of-words (BoW) model. In the baseline method, two keypoints are considered as a matching pair if their SIFT descriptors are quantized to the same visual word. However, the SIFT visual word has two limitations. First, it loses most of its discriminative power during quantization. Second, SIFT only describes the local texture feature. Both drawbacks impair the discriminative power of the BoW model and lead to false positive matches. To tackle this problem, this paper proposes to embed multiple binary features at indexing level. To model correlation between features, a multi-IDF scheme is introduced, through which different binary features are coupled into the inverted file. We show that matching verification methods based on binary features, such as Hamming embedding, can be effectively incorporated in our framework. As an extension, we explore the fusion of binary color feature into image retrieval. The joint integration of the SIFT visual word and binary features greatly enhances the precision of visual matching, reducing the impact of false positive matches. Our method is evaluated through extensive experiments on four benchmark datasets (Ukbench, Holidays, DupImage, and MIR Flickr 1M). We show that our method significantly improves the baseline approach. In addition, large-scale experiments indicate that the proposed method requires acceptable memory usage and query time compared with other approaches. Further, when global color feature is integrated, our method yields competitive performance with the state-of-the-arts.

Aerosol Retrieval Sensitivity and Error Analysis for the Cloud and Aerosol Polarimetric Imager on Board TanSat: The Effect of Multi-Angle Measurement

Directory of Open Access Journals (Sweden)

Xi Chen

2017-02-01

Full Text Available Aerosol scattering is an important source of error in CO2 retrievals from satellite. This paper presents an analysis of aerosol information content from the Cloud and Aerosol Polarimetric Imager (CAPI onboard the Chinese Carbon Dioxide Observation Satellite (TanSat to be launched in 2016. Based on optimal estimation theory, aerosol information content is quantified from radiance and polarization observed by CAPI in terms of the degrees of freedom for the signal (DFS. A linearized vector radiative transfer model is used with a linearized Mie code to simulate observation and sensitivity (or Jacobians with respect to aerosol parameters. In satellite nadir mode, the DFS for aerosol optical depth is the largest, but for mode radius, it is only 0.55. Observation geometry is found to affect aerosol DFS based on the aerosol scattering phase function from the comparison between different viewing zenith angles or solar zenith angles. When TanSat is operated in target mode, we note that multi-angle retrieval represented by three along-track measurements provides additional 0.31 DFS on average, mainly from mode radius. When adding another two measurements, the a posteriori error decreases by another 2%–6%. The correlation coefficients between retrieved parameters show that aerosol is strongly correlated with surface reflectance, but multi-angle retrieval can weaken this correlation.

Mosaicing of single plane illumination microscopy images using groupwise registration and fast content-based image fusion

Science.gov (United States)

Preibisch, Stephan; Rohlfing, Torsten; Hasak, Michael P.; Tomancak, Pavel

2008-03-01

Single Plane Illumination Microscopy (SPIM; Huisken et al., Nature 305(5686):1007-1009, 2004) is an emerging microscopic technique that enables live imaging of large biological specimens in their entirety. By imaging the living biological sample from multiple angles SPIM has the potential to achieve isotropic resolution throughout even relatively large biological specimens. For every angle, however, only a relatively shallow section of the specimen is imaged with high resolution, whereas deeper regions appear increasingly blurred. In order to produce a single, uniformly high resolution image, we propose here an image mosaicing algorithm that combines state of the art groupwise image registration for alignment with content-based image fusion to prevent degrading of the fused image due to regional blurring of the input images. For the registration stage, we introduce an application-specific groupwise transformation model that incorporates per-image as well as groupwise transformation parameters. We also propose a new fusion algorithm based on Gaussian filters, which is substantially faster than fusion based on local image entropy. We demonstrate the performance of our mosaicing method on data acquired from living embryos of the fruit fly, Drosophila, using four and eight angle acquisitions.

Management of Scientific Images: an approach to the extraction, annotation and retrieval of figures in the field of High Energy Physics

CERN Document Server

Praczyk, Piotr Adam; Mele, Salvatore

The information environment of the first decade of the XXIst century is unprecedented. The physical barriers limiting access to the knowledge are disappearing as traditional methods of accessing information are being replaced or enhanced by computer systems. Digital systems are able to manage much larger sets of documents, confronting information users with the deluge of documents related to their topic of interest. This new situation created an incentive for the rapid development of Data Mining techniques and to the creation of more efficient search engines capable of limiting the search results to a small subset of the most relevant ones. However, most of the up to date search engines operate using the text descriptions of the documents. Those descriptions can either be extracted from the content of the document or be obtained from the external sources. The retrieval based on the non-textual content of documents is a subject of ongoing research. In particular, the retrieval of images and unlocking the infor...

Water vapor retrieval from near-IR measurements of polarized scanning atmospheric corrector

Science.gov (United States)

Qie, Lili; Ning, Yuanming; Zhang, Yang; Chen, Xingfeng; Ma, Yan; Li, Zhengqiang; Cui, Wenyu

2018-02-01

Water vapor and aerosol are two key atmospheric factors effecting the remote sensing image quality. As water vapor is responsible for most of the solar radiation absorption occurring in the cloudless atmosphere, accurate measurement of water content is important to not only atmospheric correction of remote sensing images, but also many other applications such as the study of energy balance and global climate change, land surface temperature retrieval in thermal remote sensing. A multi-spectral, single-angular, polarized radiometer called Polarized Scanning Atmospheric Corrector (PSAC) were developed in China, which are designed to mount on the same satellite platform with the principle payload and provide essential parameters for principle payload image atmospheric correction. PSAC detect water vapor content via measuring atmosphere reflectance at water vapor absorbing channels (i.e. 0.91 μm) and nearby atmospheric window channel (i.e. 0.865μm). A near-IR channel ratio method was implemented to retrieve column water vapor (CWV) amount from PSAC measurements. Field experiments were performed at Yantai, in Shandong province of China, PSAC aircraft observations were acquired. The comparison between PSAC retrievals and ground-based Sun-sky radiometer measurements of CWV during the experimental flights illustrates that this method retrieves CWV with relative deviations ranging from 4% 13%. This method retrieve CWV more accurate over land than over ocean, as the water reflectance is low.

Image Re-Ranking Based on Topic Diversity.

Science.gov (United States)

Qian, Xueming; Lu, Dan; Wang, Yaxiong; Zhu, Li; Tang, Yuan Yan; Wang, Meng

2017-08-01

Social media sharing Websites allow users to annotate images with free tags, which significantly contribute to the development of the web image retrieval. Tag-based image search is an important method to find images shared by users in social networks. However, how to make the top ranked result relevant and with diversity is challenging. In this paper, we propose a topic diverse ranking approach for tag-based image retrieval with the consideration of promoting the topic coverage performance. First, we construct a tag graph based on the similarity between each tag. Then, the community detection method is conducted to mine the topic community of each tag. After that, inter-community and intra-community ranking are introduced to obtain the final retrieved results. In the inter-community ranking process, an adaptive random walk model is employed to rank the community based on the multi-information of each topic community. Besides, we build an inverted index structure for images to accelerate the searching process. Experimental results on Flickr data set and NUS-Wide data sets show the effectiveness of the proposed approach.

Compounds in dictionary-based Cross-language information retrieval_revised

Directory of Open Access Journals (Sweden)

2002-01-01

Full Text Available Compound words form an important part of natural language. From the cross-lingual information retrieval (CLIR point of view it is important that many natural languages are highly productive with compounds, and translation resources cannot include entries for all compounds. Also, compounds are often content bearing words in a sentence. In Swedish, German and Finnish roughly one tenth of the words in a text prepared for information retrieval purposes are compounds. Important research questions concerning compound handling in dictionary-based cross-language information retrieval are 1 compound splitting into components, 2 normalisation of components, 3 translation of components and 4 query structuring for compounds and their components in the target language. The impact of compound processing on the performance of the cross-language information retrieval process is evaluated in this study and the results indicate that the effect is clearly positive.

Annotation and retrieval system of CAD models based on functional semantics

Science.gov (United States)

Wang, Zhansong; Tian, Ling; Duan, Wenrui

2014-11-01

CAD model retrieval based on functional semantics is more significant than content-based 3D model retrieval during the mechanical conceptual design phase. However, relevant research is still not fully discussed. Therefore, a functional semantic-based CAD model annotation and retrieval method is proposed to support mechanical conceptual design and design reuse, inspire designer creativity through existing CAD models, shorten design cycle, and reduce costs. Firstly, the CAD model functional semantic ontology is constructed to formally represent the functional semantics of CAD models and describe the mechanical conceptual design space comprehensively and consistently. Secondly, an approach to represent CAD models as attributed adjacency graphs(AAG) is proposed. In this method, the geometry and topology data are extracted from STEP models. On the basis of AAG, the functional semantics of CAD models are annotated semi-automatically by matching CAD models that contain the partial features of which functional semantics have been annotated manually, thereby constructing CAD Model Repository that supports model retrieval based on functional semantics. Thirdly, a CAD model retrieval algorithm that supports multi-function extended retrieval is proposed to explore more potential creative design knowledge in the semantic level. Finally, a prototype system, called Functional Semantic-based CAD Model Annotation and Retrieval System(FSMARS), is implemented. A case demonstrates that FSMARS can successfully botain multiple potential CAD models that conform to the desired function. The proposed research addresses actual needs and presents a new way to acquire CAD models in the mechanical conceptual design phase.

Hierarchical multiple binary image encryption based on a chaos and phase retrieval algorithm in the Fresnel domain

International Nuclear Information System (INIS)

Wang, Zhipeng; Hou, Chenxia; Lv, Xiaodong; Wang, Hongjuan; Gong, Qiong; Qin, Yi

2016-01-01

Based on the chaos and phase retrieval algorithm, a hierarchical multiple binary image encryption is proposed. In the encryption process, each plaintext is encrypted into a diffraction intensity pattern by two chaos-generated random phase masks (RPMs). Thereafter, the captured diffraction intensity patterns are partially selected by different binary masks and then combined together to form a single intensity pattern. The combined intensity pattern is saved as ciphertext. For decryption, an iterative phase retrieval algorithm is performed, in which a support constraint in the output plane and a median filtering operation are utilized to achieve a rapid convergence rate without a stagnation problem. The proposed scheme has a simple optical setup and large encryption capacity. In particular, it is well suited for constructing a hierarchical security system. The security and robustness of the proposal are also investigated. (letter)

Texture Retrieval from VHR Optical Remote Sensed Images Using the Local Extrema Descriptor with Application to Vineyard Parcel Detection

Directory of Open Access Journals (Sweden)

Minh-Tan Pham

2016-04-01

Full Text Available In this article, we develop a novel method for the detection of vineyard parcels in agricultural landscapes based on very high resolution (VHR optical remote sensing images. Our objective is to perform texture-based image retrieval and supervised classification algorithms. To do that, the local textural and structural features inside each image are taken into account to measure its similarity to other images. In fact, VHR images usually involve a variety of local textures and structures that may verify a weak stationarity hypothesis. Hence, an approach only based on characteristic points, not on all pixels of the image, is supposed to be relevant. This work proposes to construct the local extrema-based descriptor (LED by using the local maximum and local minimum pixels extracted from the image. The LED descriptor is formed based on the radiometric, geometric and gradient features from these local extrema. We first exploit the proposed LED descriptor for the retrieval task to evaluate its performance on texture discrimination. Then, it is embedded into a supervised classification framework to detect vine parcels using VHR satellite images. Experiments performed on VHR panchromatic PLEIADES image data prove the effectiveness of the proposed strategy. Compared to state-of-the-art methods, an enhancement of about 7% in retrieval rate is achieved. For the detection task, about 90% of vineyards are correctly detected.

The Harmonics of Kansei Images

DEFF Research Database (Denmark)

Su, Jianning; Restrepo-Giraldo, John Dairo

2008-01-01

sensibility it elicits on a person (kansei), is a key factor in the design of tools to support designers in delivering the right product’s appearance. This paper presents an approach to mathematically represent a product’s kansei based on the frequency signature (harmonics) of a shape. This mathematical...... representation should allow the automatic indexing and retrieval of images from a repository of design precedents. This is done through a series of experiments aiming at determining the relation between images, kansei words and the frequency signatures of those images. Tests suggest the method is promising...... and can be used for indexing images in Content Based Image Retrieval Systems....

Content Progressive Coding of Limited Bits/pixel Images

DEFF Research Database (Denmark)

Jensen, Ole Riis; Forchhammer, Søren

1999-01-01

A new lossless context based method for content progressive coding of limited bits/pixel images is proposed. Progressive coding is achieved by separating the image into contelnt layers. Digital maps are compressed up to 3 times better than GIF.......A new lossless context based method for content progressive coding of limited bits/pixel images is proposed. Progressive coding is achieved by separating the image into contelnt layers. Digital maps are compressed up to 3 times better than GIF....

Content-Based Covert Group Detection in Social Networks

Science.gov (United States)

2017-09-06

The students took courses in natural language processing, data mining in various multi-media data sets, text retrieval, text summarization and... mining in social media including: we performed work, on (a) diffusion in social networks, (b) influence maximization in signed social networks, (c...Learning, Information Retrieval, Data Mining and Database. There are 8,293 messages. Our method outperformed state of the art methods based on content

[Estimation of forest canopy chlorophyll content based on PROSPECT and SAIL models].

Science.gov (United States)

Yang, Xi-guang; Fan, Wen-yi; Yu, Ying

2010-11-01

The forest canopy chlorophyll content directly reflects the health and stress of forest. The accurate estimation of the forest canopy chlorophyll content is a significant foundation for researching forest ecosystem cycle models. In the present paper, the inversion of the forest canopy chlorophyll content was based on PROSPECT and SAIL models from the physical mechanism angle. First, leaf spectrum and canopy spectrum were simulated by PROSPECT and SAIL models respectively. And leaf chlorophyll content look-up-table was established for leaf chlorophyll content retrieval. Then leaf chlorophyll content was converted into canopy chlorophyll content by Leaf Area Index (LAD). Finally, canopy chlorophyll content was estimated from Hyperion image. The results indicated that the main effect bands of chlorophyll content were 400-900 nm, the simulation of leaf and canopy spectrum by PROSPECT and SAIL models fit better with the measured spectrum with 7.06% and 16.49% relative error respectively, the RMSE of LAI inversion was 0. 542 6 and the forest canopy chlorophyll content was estimated better by PROSPECT and SAIL models with precision = 77.02%.

4D reconstruction of the past: the image retrieval and 3D model construction pipeline

Science.gov (United States)

Hadjiprocopis, Andreas; Ioannides, Marinos; Wenzel, Konrad; Rothermel, Mathias; Johnsons, Paul S.; Fritsch, Dieter; Doulamis, Anastasios; Protopapadakis, Eftychios; Kyriakaki, Georgia; Makantasis, Kostas; Weinlinger, Guenther; Klein, Michael; Fellner, Dieter; Stork, Andre; Santos, Pedro

2014-08-01

One of the main characteristics of the Internet era we are living in, is the free and online availability of a huge amount of data. This data is of varied reliability and accuracy and exists in various forms and formats. Often, it is cross-referenced and linked to other data, forming a nexus of text, images, animation and audio enabled by hypertext and, recently, by the Web3.0 standard. Our main goal is to enable historians, architects, archaeolo- gists, urban planners and affiliated professionals to reconstruct views of historical monuments from thousands of images floating around the web. This paper aims to provide an update of our progress in designing and imple- menting a pipeline for searching, filtering and retrieving photographs from Open Access Image Repositories and social media sites and using these images to build accurate 3D models of archaeological monuments as well as enriching multimedia of cultural / archaeological interest with metadata and harvesting the end products to EU- ROPEANA. We provide details of how our implemented software searches and retrieves images of archaeological sites from Flickr and Picasa repositories as well as strategies on how to filter the results, on two levels; a) based on their built-in metadata including geo-location information and b) based on image processing and clustering techniques. We also describe our implementation of a Structure from Motion pipeline designed for producing 3D models using the large collection of 2D input images (>1000) retrieved from Internet Repositories.

Information content and sensitivity of the 3β + 2α lidar measurement system for aerosol microphysical retrievals

Science.gov (United States)

Burton, Sharon P.; Chemyakin, Eduard; Liu, Xu; Knobelspiesse, Kirk; Stamnes, Snorre; Sawamura, Patricia; Moore, Richard H.; Hostetler, Chris A.; Ferrare, Richard A.

2016-11-01

There is considerable interest in retrieving profiles of aerosol effective radius, total number concentration, and complex refractive index from lidar measurements of extinction and backscatter at several wavelengths. The combination of three backscatter channels plus two extinction channels (3β + 2α) is particularly important since it is believed to be the minimum configuration necessary for the retrieval of aerosol microphysical properties and because the technological readiness of lidar systems permits this configuration on both an airborne and future spaceborne instrument. The second-generation NASA Langley airborne High Spectral Resolution Lidar (HSRL-2) has been making 3β + 2α measurements since 2012. The planned NASA Aerosol/Clouds/Ecosystems (ACE) satellite mission also recommends the 3β + 2α combination.Here we develop a deeper understanding of the information content and sensitivities of the 3β + 2α system in terms of aerosol microphysical parameters of interest. We use a retrieval-free methodology to determine the basic sensitivities of the measurements independent of retrieval assumptions and constraints. We calculate information content and uncertainty metrics using tools borrowed from the optimal estimation methodology based on Bayes' theorem, using a simplified forward model look-up table, with no explicit inversion. The forward model is simplified to represent spherical particles, monomodal log-normal size distributions, and wavelength-independent refractive indices. Since we only use the forward model with no retrieval, the given simplified aerosol scenario is applicable as a best case for all existing retrievals in the absence of additional constraints. Retrieval-dependent errors due to mismatch between retrieval assumptions and true atmospheric aerosols are not included in this sensitivity study, and neither are retrieval errors that may be introduced in the inversion process. The choice of a simplified model adds clarity to the

Combination of image descriptors for the exploration of cultural photographic collections

Science.gov (United States)

Bhowmik, Neelanjan; Gouet-Brunet, Valérie; Bloch, Gabriel; Besson, Sylvain

2017-01-01

The rapid growth of image digitization and collections in recent years makes it challenging and burdensome to organize, categorize, and retrieve similar images from voluminous collections. Content-based image retrieval (CBIR) is immensely convenient in this context. A considerable number of local feature detectors and descriptors are present in the literature of CBIR. We propose a model to anticipate the best feature combinations for image retrieval-related applications. Several spatial complementarity criteria of local feature detectors are analyzed and then engaged in a regression framework to find the optimal combination of detectors for a given dataset and are better adapted for each given image; the proposed model is also useful to optimally fix some other parameters, such as the k in k-nearest neighbor retrieval. Three public datasets of various contents and sizes are employed to evaluate the proposal, which is legitimized by improving the quality of retrieval notably facing classical approaches. Finally, the proposed image search engine is applied to the cultural photographic collections of a French museum, where it demonstrates its added value for the exploration and promotion of these contents at different levels from their archiving up to their exhibition in or ex situ.

A single-image method of aberration retrieval for imaging systems under partially coherent illumination

International Nuclear Information System (INIS)

Xu, Shuang; Liu, Shiyuan; Zhang, Chuanwei; Wei, Haiqing

2014-01-01

We propose a method for retrieving small lens aberrations in optical imaging systems under partially coherent illumination, which only requires to measure one single defocused image of intensity. By deriving a linear theory of imaging systems, we obtain a generalized formulation of aberration sensitivity in a matrix form, which provides a set of analytic kernels that relate the measured intensity distribution directly to the unknown Zernike coefficients. Sensitivity analysis is performed and test patterns are optimized to ensure well-posedness of the inverse problem. Optical lithography simulations have validated the theoretical derivation and confirmed its simplicity and superior performance in retrieving small lens aberrations. (fast track communication)

Grating-based x-ray differential phase contrast imaging with twin peaks in phase-stepping curves—phase retrieval and dewrapping

Energy Technology Data Exchange (ETDEWEB)

Yang, Yi; Xie, Huiqiao; Tang, Xiangyang, E-mail: xiangyang.tang@emory.edu [Imaging and Medical Physics, Department of Radiology and Imaging Sciences, Emory University School of Medicine, 1701 Uppergate Dr., C-5018, Atlanta, Georgia 30322 (United States); Cai, Weixing [Department of Radiation Oncology, Brigham and Women’s Hospital Harvard Medical School, 75 Francis Street, Boston, Massachusetts 02115 (United States); Mao, Hui [Laboratory of Functional and Molecular Imaging and Nanomedicine, Department of Radiology and Imaging Sciences, Emory University School of Medicine, 1841 Clifton Road NE, Atlanta, Georgia 30329 (United States)

2016-06-15

Purpose: X-ray differential phase contrast CT implemented with Talbot interferometry employs phase-stepping to extract information of x-ray attenuation, phase shift, and small-angle scattering. Since inaccuracy may exist in the absorption grating G{sub 2} due to an imperfect fabrication, the effective period of G{sub 2} can be as large as twice the nominal period, leading to a phenomenon of twin peaks that differ remarkably in their heights. In this work, the authors investigate how to retrieve and dewrap the phase signal from the phase-stepping curve (PSC) with the feature of twin peaks for x-ray phase contrast imaging. Methods: Based on the paraxial Fresnel–Kirchhoff theory, the analytical formulae to characterize the phenomenon of twin peaks in the PSC are derived. Then an approach to dewrap the retrieved phase signal by jointly using the phases of the first- and second-order Fourier components is proposed. Through an experimental investigation using a prototype x-ray phase contrast imaging system implemented with Talbot interferometry, the authors evaluate and verify the derived analytic formulae and the proposed approach for phase retrieval and dewrapping. Results: According to theoretical analysis, the twin-peak phenomenon in PSC is a consequence of combined effects, including the inaccuracy in absorption grating G{sub 2}, mismatch between phase grating and x-ray source spectrum, and finite size of x-ray tube’s focal spot. The proposed approach is experimentally evaluated by scanning a phantom consisting of organic materials and a lab mouse. The preliminary data show that compared to scanning G{sub 2} over only one single nominal period and correcting the measured phase signal with an intuitive phase dewrapping method that is being used in the field, stepping G{sub 2} over twice its nominal period and dewrapping the measured phase signal with the proposed approach can significantly improve the quality of x-ray differential phase contrast imaging in both

An Intelligent Web Digital Image Metadata Service Platform for Social Curation Commerce Environment

Directory of Open Access Journals (Sweden)

Seong-Yong Hong

2015-01-01

Full Text Available Information management includes multimedia data management, knowledge management, collaboration, and agents, all of which are supporting technologies for XML. XML technologies have an impact on multimedia databases as well as collaborative technologies and knowledge management. That is, e-commerce documents are encoded in XML and are gaining much popularity for business-to-business or business-to-consumer transactions. Recently, the internet sites, such as e-commerce sites and shopping mall sites, deal with a lot of image and multimedia information. This paper proposes an intelligent web digital image information retrieval platform, which adopts XML technology for social curation commerce environment. To support object-based content retrieval on product catalog images containing multiple objects, we describe multilevel metadata structures representing the local features, global features, and semantics of image data. To enable semantic-based and content-based retrieval on such image data, we design an XML-Schema for the proposed metadata. We also describe how to automatically transform the retrieval results into the forms suitable for the various user environments, such as web browser or mobile device, using XSLT. The proposed scheme can be utilized to enable efficient e-catalog metadata sharing between systems, and it will contribute to the improvement of the retrieval correctness and the user’s satisfaction on semantic-based web digital image information retrieval.

MPEG-7-based description infrastructure for an audiovisual content analysis and retrieval system

Science.gov (United States)

Bailer, Werner; Schallauer, Peter; Hausenblas, Michael; Thallinger, Georg

2005-01-01

We present a case study of establishing a description infrastructure for an audiovisual content-analysis and retrieval system. The description infrastructure consists of an internal metadata model and access tool for using it. Based on an analysis of requirements, we have selected, out of a set of candidates, MPEG-7 as the basis of our metadata model. The openness and generality of MPEG-7 allow using it in broad range of applications, but increase complexity and hinder interoperability. Profiling has been proposed as a solution, with the focus on selecting and constraining description tools. Semantic constraints are currently only described in textual form. Conformance in terms of semantics can thus not be evaluated automatically and mappings between different profiles can only be defined manually. As a solution, we propose an approach to formalize the semantic constraints of an MPEG-7 profile using a formal vocabulary expressed in OWL, which allows automated processing of semantic constraints. We have defined the Detailed Audiovisual Profile as the profile to be used in our metadata model and we show how some of the semantic constraints of this profile can be formulated using ontologies. To work practically with the metadata model, we have implemented a MPEG-7 library and a client/server document access infrastructure.

Today's and tomorrow's retrieval practice in the audiovisual archive

NARCIS (Netherlands)

Huurnink, B.; Snoek, C.G.M.; de Rijke, M.; Smeulders, A.W.M.

2010-01-01

Content-based video retrieval is maturing to the point where it can be used in real-world retrieval practices. One such practice is the audiovisual archive, whose users increasingly require fine-grained access to broadcast television content. We investigate to what extent content-based video

Hurricane Imaging Radiometer Wind Speed and Rain Rate Retrievals during the 2010 GRIP Flight Experiment

Science.gov (United States)

Sahawneh, Saleem; Farrar, Spencer; Johnson, James; Jones, W. Linwood; Roberts, Jason; Biswas, Sayak; Cecil, Daniel

2014-01-01

Microwave remote sensing observations of hurricanes, from NOAA and USAF hurricane surveillance aircraft, provide vital data for hurricane research and operations, for forecasting the intensity and track of tropical storms. The current operational standard for hurricane wind speed and rain rate measurements is the Stepped Frequency Microwave Radiometer (SFMR), which is a nadir viewing passive microwave airborne remote sensor. The Hurricane Imaging Radiometer, HIRAD, will extend the nadir viewing SFMR capability to provide wide swath images of wind speed and rain rate, while flying on a high altitude aircraft. HIRAD was first flown in the Genesis and Rapid Intensification Processes, GRIP, NASA hurricane field experiment in 2010. This paper reports on geophysical retrieval results and provides hurricane images from GRIP flights. An overview of the HIRAD instrument and the radiative transfer theory based, wind speed/rain rate retrieval algorithm is included. Results are presented for hurricane wind speed and rain rate for Earl and Karl, with comparison to collocated SFMR retrievals and WP3D Fuselage Radar images for validation purposes.

Recent advances in intelligent image search and video retrieval

CERN Document Server

2017-01-01

This book initially reviews the major feature representation and extraction methods and effective learning and recognition approaches, which have broad applications in the context of intelligent image search and video retrieval. It subsequently presents novel methods, such as improved soft assignment coding, Inheritable Color Space (InCS) and the Generalized InCS framework, the sparse kernel manifold learner method, the efficient Support Vector Machine (eSVM), and the Scale-Invariant Feature Transform (SIFT) features in multiple color spaces. Lastly, the book presents clothing analysis for subject identification and retrieval, and performance evaluation methods of video analytics for traffic monitoring. Digital images and videos are proliferating at an amazing speed in the fields of science, engineering and technology, media and entertainment. With the huge accumulation of such data, keyword searches and manual annotation schemes may no longer be able to meet the practical demand for retrieving relevant conte...

Attentional Mechanisms for Interactive Image Exploration

Directory of Open Access Journals (Sweden)

Philippe Tarroux

2005-08-01

Full Text Available A lot of work has been devoted to content-based image retrieval from large image databases. The traditional approaches are based on the analysis of the whole image content both in terms of low-level and semantic characteristics. We investigate in this paper an approach based on attentional mechanisms and active vision. We describe a visual architecture that combines bottom-up and top-down approaches for identifying regions of interest according to a given goal. We show that a coarse description of the searched target combined with a bottom-up saliency map provides an efficient way to find specified targets on images. The proposed system is a first step towards the development of software agents able to search for image content in image databases.

Independent component analysis for understanding multimedia content

DEFF Research Database (Denmark)

Kolenda, Thomas; Hansen, Lars Kai; Larsen, Jan

2002-01-01

Independent component analysis of combined text and image data from Web pages has potential for search and retrieval applications by providing more meaningful and context dependent content. It is demonstrated that ICA of combined text and image features has a synergistic effect, i.e., the retrieval...

SOFTWARE FOR REGIONS OF INTEREST RETRIEVAL ON MEDICAL 3D IMAGES

Directory of Open Access Journals (Sweden)

G. G. Stromov

2014-01-01

Full Text Available Background. Implementation of software for areas of interest retrieval in 3D medical images is described in this article. It has been tested against large volume of model MRIs.Material and methods. We tested software against normal and pathological (severe multiple sclerosis model MRIs from tge BrainWeb resource. Technological stack is based on open-source cross-platform solutions. We implemented storage system on Maria DB (an open-sourced fork of MySQL with P/SQL extensions. Python 2.7 scripting was used for automatization of extract-transform-load operations. The computational core is written on Java 7 with Spring framework 3. MongoDB was used as a cache in the cluster of workstations. Maven 3 was chosen as a dependency manager and build system, the project is hosted at Github.Results. As testing on SSMU's LAN has showed, software has been developed is quite efficiently retrieves ROIs are matching for the morphological substratum on pathological MRIs.Conclusion. Automation of a diagnostic process using medical imaging allows to level down the subjective component in decision making and increase the availability of hi-tech medicine. Software has shown in the article is a complex solution for ROI retrieving and segmentation process on model medical images in full-automated mode.We would like to thank Robert Vincent for great help with consulting of usage the BrainWeb resource.

Content-Based tile Retrieval System

Czech Academy of Sciences Publication Activity Database

Vácha, Pavel; Haindl, Michal

-, č. 85 (2011), s. 45-45 ISSN 0926-4981 R&D Projects: GA MŠk 1M0572; GA ČR GA102/08/0593; GA MŠk(CZ) LG11009 Institutional research plan: CEZ:AV0Z10750506 Keywords : CBIR * Markov random fields Subject RIV: BD - Theory of Information http://ercim-news.ercim.eu/images/stories/EN85/EN85-web.pdf

Intelligent distributed medical image management

Science.gov (United States)

Garcia, Hong-Mei C.; Yun, David Y.

1995-05-01

The rapid advancements in high performance global communication have accelerated cooperative image-based medical services to a new frontier. Traditional image-based medical services such as radiology and diagnostic consultation can now fully utilize multimedia technologies in order to provide novel services, including remote cooperative medical triage, distributed virtual simulation of operations, as well as cross-country collaborative medical research and training. Fast (efficient) and easy (flexible) retrieval of relevant images remains a critical requirement for the provision of remote medical services. This paper describes the database system requirements, identifies technological building blocks for meeting the requirements, and presents a system architecture for our target image database system, MISSION-DBS, which has been designed to fulfill the goals of Project MISSION (medical imaging support via satellite integrated optical network) -- an experimental high performance gigabit satellite communication network with access to remote supercomputing power, medical image databases, and 3D visualization capabilities in addition to medical expertise anywhere and anytime around the country. The MISSION-DBS design employs a synergistic fusion of techniques in distributed databases (DDB) and artificial intelligence (AI) for storing, migrating, accessing, and exploring images. The efficient storage and retrieval of voluminous image information is achieved by integrating DDB modeling and AI techniques for image processing while the flexible retrieval mechanisms are accomplished by combining attribute- based and content-based retrievals.

Content-based quality evaluation of color images: overview and proposals

Science.gov (United States)

Tremeau, Alain; Richard, Noel; Colantoni, Philippe; Fernandez-Maloigne, Christine

2003-12-01

The automatic prediction of perceived quality from image data in general, and the assessment of particular image characteristics or attributes that may need improvement in particular, becomes an increasingly important part of intelligent imaging systems. The purpose of this paper is to propose to the color imaging community in general to develop a software package available on internet to help the user to select among all these approaches which is better appropriated to a given application. The ultimate goal of this project is to propose, next to implement, an open and unified color imaging system to set up a favourable context for the evaluation and analysis of color imaging processes. Many different methods for measuring the performance of a process have been proposed by different researchers. In this paper, we will discuss the advantages and shortcomings of most of main analysis criteria and performance measures currently used. The aim is not to establish a harsh competition between algorithms or processes, but rather to test and compare the efficiency of methodologies firstly to highlight strengths and weaknesses of a given algorithm or methodology on a given image type and secondly to have these results publicly available. This paper is focused on two important unsolved problems. Why it is so difficult to select a color space which gives better results than another one? Why it is so difficult to select an image quality metric which gives better results than another one, with respect to the judgment of the Human Visual System? Several methods used either in color imaging or in image quality will be thus discussed. Proposals for content-based image measures and means of developing a standard test suite for will be then presented. The above reference advocates for an evaluation protocol based on an automated procedure. This is the ultimate goal of our proposal.

Exploring The Limits Of Variational Passive Microwave Retrievals

Science.gov (United States)

Duncan, David Ian

Passive microwave observations from satellite platforms constitute one of the most important data records of the global observing system. Operational since the late 1970s, passive microwave data underpin climate records of precipitation, sea ice extent, water vapor, and more, and contribute significantly to numerical weather prediction via data assimilation. Detailed understanding of the observation errors in these data is key to maximizing their utility for research and operational applications alike. However, the treatment of observation errors in this data record has been lacking and somewhat divergent when considering the retrieval and data assimilation communities. In this study, some limits of passive microwave imager data are considered in light of more holistic treatment of observation errors. A variational retrieval, named the CSU 1DVAR, was developed for microwave imagers and applied to the GMI and AMSR2 sensors for ocean scenes. Via an innovative method to determine forward model error, this retrieval accounts for error covariances across all channels used in the iteration. This improves validation in more complex scenes such as high wind speed and persistently cloudy regimes. In addition, it validates on par with a benchmark dataset without any tuning to in-situ observations. The algorithm yields full posterior error diagnostics and its physical forward model is applicable to other sensors, pending intercalibration. This retrieval is used to explore the viability of retrieving parameters at the limits of the available information content from a typical microwave imager. Retrieval of warm rain, marginal sea ice, and falling snow are explored with the variational retrieval. Warm rain retrieval shows some promise, with greater sensitivity than operational GPM algorithms due to leveraging CloudSat data and accounting for drop size distribution variability. Marginal sea ice is also detected with greater sensitivity than a standard operational retrieval

Content-adaptive Image Enhancement, Based on Sky and Grass Segmentation

NARCIS (Netherlands)

Zafarifar, B.; With, de P.H.N.

2009-01-01

Current TV image enhancement functions employ globally controlled settings. A more flexible system can be achieved if the global control is extended to incorporate semantic-level image content information. In this paper, we present a system that extends existing TV image enhancement functions with

Quantitative evaluation of a single-distance phase-retrieval method applied on in-line phase-contrast images of a mouse lung

International Nuclear Information System (INIS)

Mohammadi, Sara; Larsson, Emanuel; Alves, Frauke; Dal Monego, Simeone; Biffi, Stefania; Garrovo, Chiara; Lorenzon, Andrea; Tromba, Giuliana; Dullin, Christian

2014-01-01

Quantitative analysis concerning the application of a single-distance phase-retrieval algorithm on in-line phase-contrast images of a mouse lung at different sample-to-detector distances is presented. Propagation-based X-ray phase-contrast computed tomography (PBI) has already proven its potential in a great variety of soft-tissue-related applications including lung imaging. However, the strong edge enhancement, caused by the phase effects, often hampers image segmentation and therefore the quantitative analysis of data sets. Here, the benefits of applying single-distance phase retrieval prior to the three-dimensional reconstruction (PhR) are discussed and quantified compared with three-dimensional reconstructions of conventional PBI data sets in terms of contrast-to-noise ratio (CNR) and preservation of image features. The PhR data sets show more than a tenfold higher CNR and only minor blurring of the edges when compared with PBI in a predominately absorption-based set-up. Accordingly, phase retrieval increases the sensitivity and provides more functionality in computed tomography imaging

Developing an A Priori Database for Passive Microwave Snow Water Retrievals Over Ocean

Science.gov (United States)

Yin, Mengtao; Liu, Guosheng

2017-12-01

A physically optimized a priori database is developed for Global Precipitation Measurement Microwave Imager (GMI) snow water retrievals over ocean. The initial snow water content profiles are derived from CloudSat Cloud Profiling Radar (CPR) measurements. A radiative transfer model in which the single-scattering properties of nonspherical snowflakes are based on the discrete dipole approximate results is employed to simulate brightness temperatures and their gradients. Snow water content profiles are then optimized through a one-dimensional variational (1D-Var) method. The standard deviations of the difference between observed and simulated brightness temperatures are in a similar magnitude to the observation errors defined for observation error covariance matrix after the 1D-Var optimization, indicating that this variational method is successful. This optimized database is applied in a Bayesian retrieval snow water algorithm. The retrieval results indicated that the 1D-Var approach has a positive impact on the GMI retrieved snow water content profiles by improving the physical consistency between snow water content profiles and observed brightness temperatures. Global distribution of snow water contents retrieved from the a priori database is compared with CloudSat CPR estimates. Results showed that the two estimates have a similar pattern of global distribution, and the difference of their global means is small. In addition, we investigate the impact of using physical parameters to subset the database on snow water retrievals. It is shown that using total precipitable water to subset the database with 1D-Var optimization is beneficial for snow water retrievals.

Retrieval of Sentence Sequences for an Image Stream via Coherence Recurrent Convolutional Networks.

Science.gov (United States)

Park, Cesc Chunseong; Kim, Youngjin; Kim, Gunhee

2018-04-01

We propose an approach for retrieving a sequence of natural sentences for an image stream. Since general users often take a series of pictures on their experiences, much online visual information exists in the form of image streams, for which it would better take into consideration of the whole image stream to produce natural language descriptions. While almost all previous studies have dealt with the relation between a single image and a single natural sentence, our work extends both input and output dimension to a sequence of images and a sequence of sentences. For retrieving a coherent flow of multiple sentences for a photo stream, we propose a multimodal neural architecture called coherence recurrent convolutional network (CRCN), which consists of convolutional neural networks, bidirectional long short-term memory (LSTM) networks, and an entity-based local coherence model. Our approach directly learns from vast user-generated resource of blog posts as text-image parallel training data. We collect more than 22 K unique blog posts with 170 K associated images for the travel topics of NYC, Disneyland , Australia, and Hawaii. We demonstrate that our approach outperforms other state-of-the-art image captioning methods for text sequence generation, using both quantitative measures and user studies via Amazon Mechanical Turk.

Rotation Invariant Color Retrieval

OpenAIRE

Swapna Borde; Udhav Bhosle

2013-01-01

The new technique for image retrieval using the color features extracted from images based on LogHistogram is proposed. The proposed technique is compared with Global color histogram and histogram ofcorners .It has been observed that number of histogram bins used for retrieval comparison of proposedtechnique (Log Histogram)is less as compared to Global Color Histogram and Histogram of corners. Theexperimental results on a database of 792 images with 11 classes indicate that proposed method (L...

Aerosol Retrievals from Proposed Satellite Bistatic Lidar Observations: Algorithm and Information Content

Science.gov (United States)

Alexandrov, M. D.; Mishchenko, M. I.

2017-12-01

Accurate aerosol retrievals from space remain quite challenging and typically involve solving a severely ill-posed inverse scattering problem. We suggested to address this ill-posedness by flying a bistatic lidar system. Such a system would consist of formation flying constellation of a primary satellite equipped with a conventional monostatic (backscattering) lidar and an additional platform hosting a receiver of the scattered laser light. If successfully implemented, this concept would combine the measurement capabilities of a passive multi-angle multi-spectral polarimeter with the vertical profiling capability of a lidar. Thus, bistatic lidar observations will be free of deficiencies affecting both monostatic lidar measurements (caused by the highly limited information content) and passive photopolarimetric measurements (caused by vertical integration and surface reflection).We present a preliminary aerosol retrieval algorithm for a bistatic lidar system consisting of a high spectral resolution lidar (HSRL) and an additional receiver flown in formation with it at a scattering angle of 165 degrees. This algorithm was applied to synthetic data generated using Mie-theory computations. The model/retrieval parameters in our tests were the effective radius and variance of the aerosol size distribution, complex refractive index of the particles, and their number concentration. Both mono- and bimodal aerosol mixtures were considered. Our algorithm allowed for definitive evaluation of error propagation from measurements to retrievals using a Monte Carlo technique, which involves random distortion of the observations and statistical characterization of the resulting retrieval errors. Our tests demonstrated that supplementing a conventional monostatic HSRL with an additional receiver dramatically increases the information content of the measurements and allows for a sufficiently accurate characterization of tropospheric aerosols.

A rapid automatic analyzer and its methodology for effective bentonite content based on image recognition technology

Directory of Open Access Journals (Sweden)

Wei Long

2016-09-01

Full Text Available Fast and accurate determination of effective bentonite content in used clay bonded sand is very important for selecting the correct mixing ratio and mixing process to obtain high-performance molding sand. Currently, the effective bentonite content is determined by testing the ethylene blue absorbed in used clay bonded sand, which is usually a manual operation with some disadvantages including complicated process, long testing time and low accuracy. A rapid automatic analyzer of the effective bentonite content in used clay bonded sand was developed based on image recognition technology. The instrument consists of auto stirring, auto liquid removal, auto titration, step-rotation and image acquisition components, and processor. The principle of the image recognition method is first to decompose the color images into three-channel gray images based on the photosensitive degree difference of the light blue and dark blue in the three channels of red, green and blue, then to make the gray values subtraction calculation and gray level transformation of the gray images, and finally, to extract the outer circle light blue halo and the inner circle blue spot and calculate their area ratio. The titration process can be judged to reach the end-point while the area ratio is higher than the setting value.

A unified framework for image retrieval using keyword and visual features.

Science.gov (United States)

Jing, Feng; Li, Mingling; Zhang, Hong-Jiang; Zhang, Bo

2005-07-01

In this paper, a unified image retrieval framework based on both keyword annotations and visual features is proposed. In this framework, a set of statistical models are built based on visual features of a small set of manually labeled images to represent semantic concepts and used to propagate keywords to other unlabeled images. These models are updated periodically when more images implicitly labeled by users become available through relevance feedback. In this sense, the keyword models serve the function of accumulation and memorization of knowledge learned from user-provided relevance feedback. Furthermore, two sets of effective and efficient similarity measures and relevance feedback schemes are proposed for query by keyword scenario and query by image example scenario, respectively. Keyword models are combined with visual features in these schemes. In particular, a new, entropy-based active learning strategy is introduced to improve the efficiency of relevance feedback for query by keyword. Furthermore, a new algorithm is proposed to estimate the keyword features of the search concept for query by image example. It is shown to be more appropriate than two existing relevance feedback algorithms. Experimental results demonstrate the effectiveness of the proposed framework.

High resolution satellite image indexing and retrieval using SURF features and bag of visual words

Science.gov (United States)

Bouteldja, Samia; Kourgli, Assia

2017-03-01

In this paper, we evaluate the performance of SURF descriptor for high resolution satellite imagery (HRSI) retrieval through a BoVW model on a land-use/land-cover (LULC) dataset. Local feature approaches such as SIFT and SURF descriptors can deal with a large variation of scale, rotation and illumination of the images, providing, therefore, a better discriminative power and retrieval efficiency than global features, especially for HRSI which contain a great range of objects and spatial patterns. Moreover, we combine SURF and color features to improve the retrieval accuracy, and we propose to learn a category-specific dictionary for each image category which results in a more discriminative image representation and boosts the image retrieval performance.

Retrieve polarization aberration from image degradation: a new measurement method in DUV lithography

Science.gov (United States)

Xiang, Zhongbo; Li, Yanqiu

2017-10-01

Detailed knowledge of polarization aberration (PA) of projection lens in higher-NA DUV lithographic imaging is necessary due to its impact to imaging degradations, and precise measurement of PA is conductive to computational lithography techniques such as RET and OPC. Current in situ measurement method of PA thorough the detection of degradations of aerial images need to do linear approximation and apply the assumption of 3-beam/2-beam interference condition. The former approximation neglects the coupling effect of the PA coefficients, which would significantly influence the accuracy of PA retrieving. The latter assumption restricts the feasible pitch of test masks in higher-NA system, conflicts with the Kirhhoff diffraction model of test mask used in retrieving model, and introduces 3D mask effect as a source of retrieving error. In this paper, a new in situ measurement method of PA is proposed. It establishes the analytical quadratic relation between the PA coefficients and the degradations of aerial images of one-dimensional dense lines in coherent illumination through vector aerial imaging, which does not rely on the assumption of 3-beam/2- beam interference and linear approximation. In this case, the retrieval of PA from image degradation can be convert from the nonlinear system of m-quadratic equations to a multi-objective quadratic optimization problem, and finally be solved by nonlinear least square method. Some preliminary simulation results are given to demonstrate the correctness and accuracy of the new PA retrieving model.

Advances in audio source seperation and multisource audio content retrieval

Science.gov (United States)

Vincent, Emmanuel

2012-06-01

Audio source separation aims to extract the signals of individual sound sources from a given recording. In this paper, we review three recent advances which improve the robustness of source separation in real-world challenging scenarios and enable its use for multisource content retrieval tasks, such as automatic speech recognition (ASR) or acoustic event detection (AED) in noisy environments. We present a Flexible Audio Source Separation Toolkit (FASST) and discuss its advantages compared to earlier approaches such as independent component analysis (ICA) and sparse component analysis (SCA). We explain how cues as diverse as harmonicity, spectral envelope, temporal fine structure or spatial location can be jointly exploited by this toolkit. We subsequently present the uncertainty decoding (UD) framework for the integration of audio source separation and audio content retrieval. We show how the uncertainty about the separated source signals can be accurately estimated and propagated to the features. Finally, we explain how this uncertainty can be efficiently exploited by a classifier, both at the training and the decoding stage. We illustrate the resulting performance improvements in terms of speech separation quality and speaker recognition accuracy.

High-resolution fluorescence imaging for red and far-red SIF retrieval at leaf and canopy scales

Science.gov (United States)

Albert, L.; Alonso, L.; Cushman, K.; Kellner, J. R.

2017-12-01

New commercial-off-the-shelf imaging spectrometers promise the combination of high spatial and spectral resolution needed to retrieve solar induced fluorescence (SIF) at multiple wavelengths for individual plants and even individual leaves from low-altitude airborne or ground-based platforms. Data from these instruments could provide insight into the status of the photosynthetic apparatus at scales of space and time not observable from high-altitude and space-based platforms, and could support calibration and validation activities of current and forthcoming space missions to quantify SIF (OCO-2, OCO-3, FLEX, and GEOCARB). High-spectral resolution enables SIF retrieval from regions of strong telluric absorption by molecular oxygen, and also within numerous solar Fraunhofer lines in atmospheric windows not obscured by oxygen or water absorptions. Here we evaluate algorithms for SIF retrieval using a commercial-off-the-shelf diffraction-grating imaging spectrometer with a spectral sampling interval of 0.05 nm and a FWHM 650 or 700 nm. These filters enable a direct measurement of SIF emission > 650 or 700 nm that serves as a benchmark against which retrievals from reflectance spectra can be evaluated. We repeated this comparison between leaf-level SIF emission spectra and retrieved SIF emission spectra for leaves treated with drought stress and an herbicide (DCMU) that inhibits electron transfer from QA to QB of PSII.

Information Content of Aerosol Retrievals in the Sunglint Region

Science.gov (United States)

Ottaviani, M.; Knobelspiesse, K.; Cairns, B.; Mishchenko, M.

2013-01-01

We exploit quantitative metrics to investigate the information content in retrievals of atmospheric aerosol parameters (with a focus on single-scattering albedo), contained in multi-angle and multi-spectral measurements with sufficient dynamical range in the sunglint region. The simulations are performed for two classes of maritime aerosols with optical and microphysical properties compiled from measurements of the Aerosol Robotic Network. The information content is assessed using the inverse formalism and is compared to that deriving from observations not affected by sunglint. We find that there indeed is additional information in measurements containing sunglint, not just for single-scattering albedo, but also for aerosol optical thickness and the complex refractive index of the fine aerosol size mode, although the amount of additional information varies with aerosol type.

Using the fuzzy modeling for the retrieval algorithms

International Nuclear Information System (INIS)

Mohamed, A.H

2010-01-01

A rapid growth in number and size of images in databases and world wide web (www) has created a strong need for more efficient search and retrieval systems to exploit the benefits of this large amount of information. However, the collection of this information is now based on the image technology. One of the limitations of the current image analysis techniques necessitates that most image retrieval systems use some form of text description provided by the users as the basis to index and retrieve images. To overcome this problem, the proposed system introduces the using of fuzzy modeling to describe the image by using the linguistic ambiguities. Also, the proposed system can include vague or fuzzy terms in modeling the queries to match the image descriptions in the retrieval process. This can facilitate the indexing and retrieving process, increase their performance and decrease its computational time . Therefore, the proposed system can improve the performance of the traditional image retrieval algorithms.

A visual perceptual descriptor with depth feature for image retrieval

Science.gov (United States)

Wang, Tianyang; Qin, Zhengrui

2017-07-01

This paper proposes a visual perceptual descriptor (VPD) and a new approach to extract perceptual depth feature for 2D image retrieval. VPD mimics human visual system, which can easily distinguish regions that have different textures, whereas for regions which have similar textures, color features are needed for further differentiation. We apply VPD on the gradient direction map of an image, capture texture-similar regions to generate a VPD map. We then impose the VPD map on a quantized color map and extract color features only from the overlapped regions. To reflect the nature of perceptual distance in single 2D image, we propose and extract the perceptual depth feature by computing the nuclear norm of the sparse depth map of an image. Extracted color features and the perceptual depth feature are both incorporated to a feature vector, we utilize this vector to represent an image and measure similarity. We observe that the proposed VPD + depth method achieves a promising result, and extensive experiments prove that it outperforms other typical methods on 2D image retrieval.

A hierarchical SVG image abstraction layer for medical imaging

Science.gov (United States)

Kim, Edward; Huang, Xiaolei; Tan, Gang; Long, L. Rodney; Antani, Sameer

2010-03-01

As medical imaging rapidly expands, there is an increasing need to structure and organize image data for efficient analysis, storage and retrieval. In response, a large fraction of research in the areas of content-based image retrieval (CBIR) and picture archiving and communication systems (PACS) has focused on structuring information to bridge the "semantic gap", a disparity between machine and human image understanding. An additional consideration in medical images is the organization and integration of clinical diagnostic information. As a step towards bridging the semantic gap, we design and implement a hierarchical image abstraction layer using an XML based language, Scalable Vector Graphics (SVG). Our method encodes features from the raw image and clinical information into an extensible "layer" that can be stored in a SVG document and efficiently searched. Any feature extracted from the raw image including, color, texture, orientation, size, neighbor information, etc., can be combined in our abstraction with high level descriptions or classifications. And our representation can natively characterize an image in a hierarchical tree structure to support multiple levels of segmentation. Furthermore, being a world wide web consortium (W3C) standard, SVG is able to be displayed by most web browsers, interacted with by ECMAScript (standardized scripting language, e.g. JavaScript, JScript), and indexed and retrieved by XML databases and XQuery. Using these open source technologies enables straightforward integration into existing systems. From our results, we show that the flexibility and extensibility of our abstraction facilitates effective storage and retrieval of medical images.

Aspect-based Relevance Learning for Image Retrieval

NARCIS (Netherlands)

M.J. Huiskes (Mark)

2005-01-01

htmlabstractWe analyze the special structure of the relevance feedback learning problem, focusing particularly on the effects of image selection by partial relevance on the clustering behavior of feedback examples. We propose a scheme, aspect-based relevance learning, which guarantees that feedback

Time-series MODIS image-based retrieval and distribution analysis of total suspended matter concentrations in Lake Taihu (China).

Science.gov (United States)

Zhang, Yuchao; Lin, Shan; Liu, Jianping; Qian, Xin; Ge, Yi

2010-09-01

Although there has been considerable effort to use remotely sensed images to provide synoptic maps of total suspended matter (TSM), there are limited studies on universal TSM retrieval models. In this paper, we have developed a TSM retrieval model for Lake Taihu using TSM concentrations measured in situ and a time series of quasi-synchronous MODIS 250 m images from 2005. After simple geometric and atmospheric correction, we found a significant relationship (R = 0.8736, N = 166) between in situ measured TSM concentrations and MODIS band normalization difference of band 3 and band 1. From this, we retrieved TSM concentrations in eight regions of Lake Taihu in 2007 and analyzed the characteristic distribution and variation of TSM. Synoptic maps of model-estimated TSM of 2007 showed clear geographical and seasonal variations. TSM in Central Lake and Southern Lakeshore were consistently higher than in other regions, while TSM in East Taihu was generally the lowest among the regions throughout the year. Furthermore, a wide range of TSM concentrations appeared from winter to summer. TSM in winter could be several times that in summer.

Content dependent selection of image enhancement parameters for mobile displays

Science.gov (United States)

Lee, Yoon-Gyoo; Kang, Yoo-Jin; Kim, Han-Eol; Kim, Ka-Hee; Kim, Choon-Woo

2011-01-01

Mobile devices such as cellular phones and portable multimedia player with capability of playing terrestrial digital multimedia broadcasting (T-DMB) contents have been introduced into consumer market. In this paper, content dependent image quality enhancement method for sharpness and colorfulness and noise reduction is presented to improve perceived image quality on mobile displays. Human visual experiments are performed to analyze viewers' preference. Relationship between the objective measures and the optimal values of image control parameters are modeled by simple lookup tables based on the results of human visual experiments. Content dependent values of image control parameters are determined based on the calculated measures and predetermined lookup tables. Experimental results indicate that dynamic selection of image control parameters yields better image quality.

Comparison of the effectiveness of alternative feature sets in shape retrieval of multicomponent images

Science.gov (United States)

Eakins, John P.; Edwards, Jonathan D.; Riley, K. Jonathan; Rosin, Paul L.

2001-01-01

Many different kinds of features have been used as the basis for shape retrieval from image databases. This paper investigates the relative effectiveness of several types of global shape feature, both singly and in combination. The features compared include well-established descriptors such as Fourier coefficients and moment invariants, as well as recently-proposed measures of triangularity and ellipticity. Experiments were conducted within the framework of the ARTISAN shape retrieval system, and retrieval effectiveness assessed on a database of over 10,000 images, using 24 queries and associated ground truth supplied by the UK Patent Office . Our experiments revealed only minor differences in retrieval effectiveness between different measures, suggesting that a wide variety of shape feature combinations can provide adequate discriminating power for effective shape retrieval in multi-component image collections such as trademark registries. Marked differences between measures were observed for some individual queries, suggesting that there could be considerable scope for improving retrieval effectiveness by providing users with an improved framework for searching multi-dimensional feature space.

Spline based iterative phase retrieval algorithm for X-ray differential phase contrast radiography.

Science.gov (United States)

Nilchian, Masih; Wang, Zhentian; Thuering, Thomas; Unser, Michael; Stampanoni, Marco

2015-04-20

Differential phase contrast imaging using grating interferometer is a promising alternative to conventional X-ray radiographic methods. It provides the absorption, differential phase and scattering information of the underlying sample simultaneously. Phase retrieval from the differential phase signal is an essential problem for quantitative analysis in medical imaging. In this paper, we formalize the phase retrieval as a regularized inverse problem, and propose a novel discretization scheme for the derivative operator based on B-spline calculus. The inverse problem is then solved by a constrained regularized weighted-norm algorithm (CRWN) which adopts the properties of B-spline and ensures a fast implementation. The method is evaluated with a tomographic dataset and differential phase contrast mammography data. We demonstrate that the proposed method is able to produce phase image with enhanced and higher soft tissue contrast compared to conventional absorption-based approach, which can potentially provide useful information to mammographic investigations.

Learning Low Dimensional Convolutional Neural Networks for High-Resolution Remote Sensing Image Retrieval

Directory of Open Access Journals (Sweden)

Weixun Zhou

2017-05-01

Full Text Available Learning powerful feature representations for image retrieval has always been a challenging task in the field of remote sensing. Traditional methods focus on extracting low-level hand-crafted features which are not only time-consuming but also tend to achieve unsatisfactory performance due to the complexity of remote sensing images. In this paper, we investigate how to extract deep feature representations based on convolutional neural networks (CNNs for high-resolution remote sensing image retrieval (HRRSIR. To this end, several effective schemes are proposed to generate powerful feature representations for HRRSIR. In the first scheme, a CNN pre-trained on a different problem is treated as a feature extractor since there are no sufficiently-sized remote sensing datasets to train a CNN from scratch. In the second scheme, we investigate learning features that are specific to our problem by first fine-tuning the pre-trained CNN on a remote sensing dataset and then proposing a novel CNN architecture based on convolutional layers and a three-layer perceptron. The novel CNN has fewer parameters than the pre-trained and fine-tuned CNNs and can learn low dimensional features from limited labelled images. The schemes are evaluated on several challenging, publicly available datasets. The results indicate that the proposed schemes, particularly the novel CNN, achieve state-of-the-art performance.

Seasonal Bias of Retrieved Ice Cloud Optical Properties Based on MISR and MODIS Measurements

Science.gov (United States)

Wang, Y.; Hioki, S.; Yang, P.; Di Girolamo, L.; Fu, D.

2017-12-01

The precise estimation of two important cloud optical and microphysical properties, cloud particle optical thickness and cloud particle effective radius, is fundamental in the study of radiative energy budget and hydrological cycle. In retrieving these two properties, an appropriate selection of ice particle surface roughness is important because it substantially affects the single-scattering properties. At present, using a predetermined ice particle shape without spatial and temporal variations is a common practice in satellite-based retrieval. This approach leads to substantial uncertainties in retrievals. The cloud radiances measured by each of the cameras of the Multi-angle Imaging SpectroRadiometer (MISR) instrument are used to estimate spherical albedo values at different scattering angles. By analyzing the directional distribution of estimated spherical albedo values, the degree of ice particle surface roughness is estimated. With an optimal degree of ice particle roughness, cloud optical thickness and effective radius are retrieved based on a bi-spectral shortwave technique in conjunction with two Moderate Resolution Imaging Spectroradiometer (MODIS) bands centered at 0.86 and 2.13 μm. The seasonal biases of retrieved cloud optical and microphysical properties, caused by the uncertainties in ice particle roughness, are investigated by using one year of MISR-MODIS fused data.

Retrieval of Brain Tumors by Adaptive Spatial Pooling and Fisher Vector Representation.

Science.gov (United States)

Cheng, Jun; Yang, Wei; Huang, Meiyan; Huang, Wei; Jiang, Jun; Zhou, Yujia; Yang, Ru; Zhao, Jie; Feng, Yanqiu; Feng, Qianjin; Chen, Wufan

2016-01-01

Content-based image retrieval (CBIR) techniques have currently gained increasing popularity in the medical field because they can use numerous and valuable archived images to support clinical decisions. In this paper, we concentrate on developing a CBIR system for retrieving brain tumors in T1-weighted contrast-enhanced MRI images. Specifically, when the user roughly outlines the tumor region of a query image, brain tumor images in the database of the same pathological type are expected to be returned. We propose a novel feature extraction framework to improve the retrieval performance. The proposed framework consists of three steps. First, we augment the tumor region and use the augmented tumor region as the region of interest to incorporate informative contextual information. Second, the augmented tumor region is split into subregions by an adaptive spatial division method based on intensity orders; within each subregion, we extract raw image patches as local features. Third, we apply the Fisher kernel framework to aggregate the local features of each subregion into a respective single vector representation and concatenate these per-subregion vector representations to obtain an image-level signature. After feature extraction, a closed-form metric learning algorithm is applied to measure the similarity between the query image and database images. Extensive experiments are conducted on a large dataset of 3604 images with three types of brain tumors, namely, meningiomas, gliomas, and pituitary tumors. The mean average precision can reach 94.68%. Experimental results demonstrate the power of the proposed algorithm against some related state-of-the-art methods on the same dataset.

A Sensitive Measurement for Estimating Impressions of Image-Contents

Science.gov (United States)

Sato, Mie; Matouge, Shingo; Mori, Toshifumi; Suzuki, Noboru; Kasuga, Masao

We have investigated Kansei Content that appeals maker's intention to viewer's kansei. An SD method is a very good way to evaluate subjective impression of image-contents. However, because the SD method is performed after subjects view the image-contents, it is difficult to examine impression of detailed scenes of the image-contents in real time. To measure viewer's impression of the image-contents in real time, we have developed a Taikan sensor. With the Taikan sensor, we investigate relations among the image-contents, the grip strength and the body temperature. We also explore the interface of the Taikan sensor to use it easily. In our experiment, a horror movie is used that largely affects emotion of the subjects. Our results show that there is a possibility that the grip strength increases when the subjects view a strained scene and that it is easy to use the Taikan sensor without its circle base that is originally installed.

Web tools for effective retrieval, visualization, and evaluation of cardiology medical images and records

Science.gov (United States)

Masseroli, Marco; Pinciroli, Francesco

2000-12-01

To provide easy retrieval, integration and evaluation of multimodal cardiology images and data in a web browser environment, distributed application technologies and java programming were used to implement a client-server architecture based on software agents. The server side manages secure connections and queries to heterogeneous remote databases and file systems containing patient personal and clinical data. The client side is a Java applet running in a web browser and providing a friendly medical user interface to perform queries on patient and medical test dat and integrate and visualize properly the various query results. A set of tools based on Java Advanced Imaging API enables to process and analyze the retrieved cardiology images, and quantify their features in different regions of interest. The platform-independence Java technology makes the developed prototype easy to be managed in a centralized form and provided in each site where an intranet or internet connection can be located. Giving the healthcare providers effective tools for querying, visualizing and evaluating comprehensively cardiology medical images and records in all locations where they can need them- i.e. emergency, operating theaters, ward, or even outpatient clinics- the developed prototype represents an important aid in providing more efficient diagnoses and medical treatments.

Learning tag relevance by neighbor voting for social image retrieval

NARCIS (Netherlands)

Li, X.; Snoek, C.G.M.; Worring, M.

2008-01-01

Social image retrieval is important for exploiting the increasing amounts of amateur-tagged multimedia such as Flickr images. Since amateur tagging is known to be uncontrolled, ambiguous, and personalized, a fundamental problem is how to reliably interpret the relevance of a tag with respect to the