WorldWideScience

Sample records for bright feature image

  1. Bright Retinal Lesions Detection using Colour Fundus Images Containing Reflective Features

    Energy Technology Data Exchange (ETDEWEB)

    Giancardo, Luca [ORNL; Karnowski, Thomas Paul [ORNL; Chaum, Edward [ORNL; Meriaudeau, Fabrice [ORNL; Tobin Jr, Kenneth William [ORNL; Li, Yaquin [University of Tennessee, Knoxville (UTK)

    2009-01-01

    In the last years the research community has developed many techniques to detect and diagnose diabetic retinopathy with retinal fundus images. This is a necessary step for the implementation of a large scale screening effort in rural areas where ophthalmologists are not available. In the United States of America, the incidence of diabetes is worryingly increasing among the young population. Retina fundus images of patients younger than 20 years old present a high amount of reflection due to the Nerve Fibre Layer (NFL), the younger the patient the more these reflections are visible. To our knowledge we are not aware of algorithms able to explicitly deal with this type of reflection artefact. This paper presents a technique to detect bright lesions also in patients with a high degree of reflective NFL. First, the candidate bright lesions are detected using image equalization and relatively simple histogram analysis. Then, a classifier is trained using texture descriptor (Multi-scale Local Binary Patterns) and other features in order to remove the false positives in the lesion detection. Finally, the area of the lesions is used to diagnose diabetic retinopathy. Our database consists of 33 images from a telemedicine network currently developed. When determining moderate to high diabetic retinopathy using the bright lesions detected the algorithm achieves a sensitivity of 100% at a specificity of 100% using hold-one-out testing.

  2. Automated local bright feature image analysis of nuclear proteindistribution identifies changes in tissue phenotype

    Energy Technology Data Exchange (ETDEWEB)

    Knowles, David; Sudar, Damir; Bator, Carol; Bissell, Mina

    2006-02-01

    The organization of nuclear proteins is linked to cell and tissue phenotypes. When cells arrest proliferation, undergo apoptosis, or differentiate, the distribution of nuclear proteins changes. Conversely, forced alteration of the distribution of nuclear proteins modifies cell phenotype. Immunostaining and fluorescence microscopy have been critical for such findings. However, there is an increasing need for quantitative analysis of nuclear protein distribution to decipher epigenetic relationships between nuclear structure and cell phenotype, and to unravel the mechanisms linking nuclear structure and function. We have developed imaging methods to quantify the distribution of fluorescently-stained nuclear protein NuMA in different mammary phenotypes obtained using three-dimensional cell culture. Automated image segmentation of DAPI-stained nuclei was generated to isolate thousands of nuclei from three-dimensional confocal images. Prominent features of fluorescently-stained NuMA were detected using a novel local bright feature analysis technique, and their normalized spatial density calculated as a function of the distance from the nuclear perimeter to its center. The results revealed marked changes in the distribution of the density of NuMA bright features as non-neoplastic cells underwent phenotypically normal acinar morphogenesis. In contrast, we did not detect any reorganization of NuMA during the formation of tumor nodules by malignant cells. Importantly, the analysis also discriminated proliferating non-neoplastic cells from proliferating malignant cells, suggesting that these imaging methods are capable of identifying alterations linked not only to the proliferation status but also to the malignant character of cells. We believe that this quantitative analysis will have additional applications for classifying normal and pathological tissues.

  3. Facial Expression Recognition using Entropy and Brightness Features

    OpenAIRE

    Khan, Rizwan Ahmed; Meyer, Alexandre; Konik, Hubert; Bouakaz, Saïda

    2011-01-01

    International audience This paper proposes a novel framework for universal facial expression recognition. The framework is based on two sets of features extracted from the face image: entropy and brightness. First, saliency maps are obtained by state-of-the-art saliency detection algorithm i.e. "frequencytuned salient region detection". Then only localized salient facial regions from saliency maps are processed to extract entropy and brightness features. To validate the performance of sali...

  4. Gamma Correction Based on Different Brightness Regional Features for Images%基于图像不同亮度区域特征的Gamma矫正方法

    Institute of Scientific and Technical Information of China (English)

    丁毅; 李玉惠; 李勃

    2016-01-01

    在图像处理领域中,图像亮度不均会大大降低图像分割的正确性。为了有效弱化图像亮度不均对图像分割带来的影响,对处理图像亮度不均具有优势的Gamma矫正方法及各种改进方法进行了对比分析。针对现有Gamma矫正方法对图像高光区矫正效果的不佳,文中提出了类余切Gamma矫正函数和椭圆非线性矫正模型。实验结果表明,按图像像素值对图像分区,该方法不仅保持了现有Gamma矫正方法对阴影区和过渡区亮度处理的效果,而且缩小了图像高光区的像素取值范围,提高了对图像高光区矫正的效果,有效降低了整幅图像亮度的比例,在一定程度上使图像亮度分布更加均匀。同时,该方法具有较好的普适性,在处理其他亮度比例较大的图像时,该方法可以较好地均衡图像亮度的分布,在某些特殊场景下会大大提高图像分割的正确性和准确率。%Uneven brightness can reduce greatly the correctness of image segmentation in image processing. In order to effectively weaken the influence on the image segmentation which brought by uneven brightness,in this paper,a variety of methods of Gamma correction and improved ones are compared and analyzed. In view of the bad effect on correcting image highlights district by using the existing Gamma correction methods,the class cotangent Gamma correction function and elliptical nonlinear correction model are proposed. The experiment shows that on the basis of maintaining the effect on luminance processing in the shadow area and the transition zone by the existing Gam-ma correction methods,this method narrows the pixel value range of the image highlights area,enhances the correction effect of the image highlights area,and reduces the proportion of the whole image brightness effectively,which makes the brightness distribution more uni-form to some extent. In dealing with a larger brightness proportion of image

  5. Image Contrast Enhancement for Brightness Preservation Based on Dynamic Stretching

    Directory of Open Access Journals (Sweden)

    M.A. Rahman

    2015-08-01

    Full Text Available Histogram equalization is an efficient process often employed in consumer electronic systems for image contrast enhancement. In addition to an increase in contrast, it is also required to preserve the mean brightness of an image in order to convey the true scene information to the viewer. A conventional approach is to separate the image into sub-images and then process independently by histogram equalization towards a modified profile. However, due to the variations in image contents, the histogram separation threshold greatly influences the level of shift in mean brightness with respect to the uniform histogram in the equalization process. Therefore, the choice of a proper threshold, to separate the input image into sub-images, is very critical in order to preserve the mean brightness of the output image. In this research work, a dynamic range stretching approach is adopted to reduce the shift in output image mean brightness. Moreover, the computationally efficient golden section search algorithm is applied to obtain a proper separation into sub-images to preserve the mean brightness. Experiments were carried out on a large number of color images of natural scenes. Results, as compared to current available approaches, showed that the proposed method performed satisfactorily in terms of mean brightness preservation and enhancement in image contrast.

  6. Annular bright and dark field imaging of soft materials

    International Nuclear Information System (INIS)

    Here polyethylene, as an example of an important soft material, was studied by STEM annular bright and dark field. The contrast as function of the probe size/shape and the detector collection angle are discussed. The results are compared to conventional bright field transmission electron microscopy, electron energy filtered imaging and energy dispersive spectroscopy mapping. Annular bright and dark field gave a higher contrast than conventional transmission and analytical mapping techniques

  7. Kinematics of magnetic bright features in the solar photosphere

    CERN Document Server

    Jafarzadeh, Shahin; Cameron, R H; Barthol, P; Rodriguez, J Blanco; Iniesta, J C del Toro; Gandorfer, A; Gizon, L; Hirzberger, J; Knoelker, M; Pillet, V Martinez; Suarez, D Orozco; Riethmueller, T L; Schmidt, W; van Noort, M

    2016-01-01

    Convective flows are known as the prime means of transporting magnetic fields on the solar surface. Thus, small magnetic structures are good tracers of the turbulent flows. We study the migration and dispersal of magnetic bright features (MBFs) in intergranular areas observed at high-spatial resolution with Sunrise/IMaX. We describe the flux dispersal of individual MBFs as a diffusion process whose parameters are computed for various areas in the quiet Sun and the vicinity of active regions from seeing-free data. We find that magnetic concentrations are best described as random walkers close to network areas (diffusion index, gamma=1.0), travelers with constant speeds over a supergranule (gamma=1.9-2.0), and decelerating movers in the vicinity of flux-emergence and/or within active regions (gamma=1.4-1.5). The three types of regions host MBFs with mean diffusion coefficients of 130 km^2/s, 80-90 km^2/s, and 25-70 km^2/s, respectively. The MBFs in these three types of regions are found to display a distinct ki...

  8. Graphical Methods for Quantifying Macromolecules through Bright Field Imaging

    Energy Technology Data Exchange (ETDEWEB)

    Chang, Hang; DeFilippis, Rosa Anna; Tlsty, Thea D.; Parvin, Bahram

    2008-08-14

    Bright ?eld imaging of biological samples stained with antibodies and/or special stains provides a rapid protocol for visualizing various macromolecules. However, this method of sample staining and imaging is rarely employed for direct quantitative analysis due to variations in sample fixations, ambiguities introduced by color composition, and the limited dynamic range of imaging instruments. We demonstrate that, through the decomposition of color signals, staining can be scored on a cell-by-cell basis. We have applied our method to Flbroblasts grown from histologically normal breast tissue biopsies obtained from two distinct populations. Initially, nuclear regions are segmented through conversion of color images into gray scale, and detection of dark elliptic features. Subsequently, the strength of staining is quanti?ed by a color decomposition model that is optimized by a graph cut algorithm. In rare cases where nuclear signal is significantly altered as a result of samplepreparation, nuclear segmentation can be validated and corrected. Finally, segmented stained patterns are associated with each nuclear region following region-based tessellation. Compared to classical non-negative matrix factorization, proposed method (i) improves color decomposition, (ii) has a better noise immunity, (iii) is more invariant to initial conditions, and (iv) has a superior computing performance

  9. Abdominal tuberculosis: Imaging features

    Energy Technology Data Exchange (ETDEWEB)

    Pereira, Jose M. [Department of Radiology, Hospital de S. Joao, Porto (Portugal)]. E-mail: jmpjesus@yahoo.com; Madureira, Antonio J. [Department of Radiology, Hospital de S. Joao, Porto (Portugal); Vieira, Alberto [Department of Radiology, Hospital de S. Joao, Porto (Portugal); Ramos, Isabel [Department of Radiology, Hospital de S. Joao, Porto (Portugal)

    2005-08-01

    Radiological findings of abdominal tuberculosis can mimic those of many different diseases. A high level of suspicion is required, especially in high-risk population. In this article, we will describe barium studies, ultrasound (US) and computed tomography (CT) findings of abdominal tuberculosis (TB), with emphasis in the latest. We will illustrate CT findings that can help in the diagnosis of abdominal tuberculosis and describe imaging features that differentiate it from other inflammatory and neoplastic diseases, particularly lymphoma and Crohn's disease. As tuberculosis can affect any organ in the abdomen, emphasis is placed to ileocecal involvement, lymphadenopathy, peritonitis and solid organ disease (liver, spleen and pancreas). A positive culture or hystologic analysis of biopsy is still required in many patients for definitive diagnosis. Learning objectives:1.To review the relevant pathophysiology of abdominal tuberculosis. 2.Illustrate CT findings that can help in the diagnosis.

  10. Histogram Equalization with Range Offset for Brightness Preserved Image Enhancement

    Directory of Open Access Journals (Sweden)

    Haidi Ibrahim

    2011-12-01

    Full Text Available In this paper, a simple modification to Global Histogram Equalization (GHE, a well known digital image enhancement method, has been proposed. This proposed method known as Histogram Equalization with Range Offset (HERO is divided into two stages. In its first stage, an intensity mapping function is constructed by using the cumulative density function of the input image, similar to GHE. Then, during the second stage, an offset for the intensity mapping function will be determined to maintain the mean brightness of the image, which is a crucial criterion for digital image enhancement in consumer electronic products. Comparison with some of the current histogram equalization based enhancement methods shows that HERO successfully preserves the mean brightness and give good enhancement to the image.

  11. Segmentation and classification of bright lesions to diagnose diabetic retinopathy in retinal images.

    Science.gov (United States)

    Santhi, D; Manimegalai, D; Parvathi, S; Karkuzhali, S

    2016-08-01

    In view of predicting bright lesions such as hard exudates, cotton wool spots, and drusen in retinal images, three different segmentation techniques have been proposed and their effectiveness is compared with existing segmentation techniques. The benchmark images with annotations present in the structured analysis of the retina (STARE) database is considered for testing the proposed techniques. The proposed segmentation techniques such as region growing (RG), region growing with background correction (RGWBC), and adaptive region growing with background correction (ARGWBC) have been used, and the effectiveness of the algorithms is compared with existing fuzzy-based techniques. Images of eight categories of various annotations and 10 images in each category have been used to test the consistency of the proposed algorithms. Among the proposed techniques, ARGWBC has been identified to be the best method for segmenting the bright lesions based on its sensitivity, specificity, and accuracy. Fifteen different features are extracted from retinal images for the purpose of identification and classification of bright lesions. Feedforward backpropagation neural network (FFBPNN) and pattern recognition neural network (PRNN) are used for the classification of normal/abnormal images. Probabilistic neural network (PNN), radial basis exact fit (RBE), radial basis fewer neurons (RB), and FFBPNN are used for further bright lesion classification and achieve 100% accuracy. PMID:27060730

  12. Hybrid bright-field and hologram imaging of cell dynamics

    Science.gov (United States)

    Byeon, Hyeokjun; Lee, Jaehyun; Doh, Junsang; Lee, Sang Joon

    2016-09-01

    Volumetric observation is essential for understanding the details of complex biological phenomena. In this study, a bright-field microscope, which provides information on a specific 2D plane, and a holographic microscope, which provides information spread over 3D volumes, are integrated to acquire two complementary images simultaneously. The developed system was successfully applied to capture distinct T-cell adhesion dynamics on inflamed endothelial layers, including capture, rolling, crawling, transendothelial migration, and subendothelial migration.

  13. Microwave brightness temperature imaging and dielectric properties of lunar soil

    Indian Academy of Sciences (India)

    Wu Ji; Li Dihui; Zhang Xiaohui; Jiang Jingshan; A T Altyntsev; B I Lubyshev

    2005-12-01

    Among many scientific objectives of lunar exploration, investigations on lunar soil become attractive due to the existence of He3 and ilmenite in the lunar soil and their possible utilization as nuclear fuel for power generation.Although the composition of the lunar surface soil can be determined by optical and /X-ray spectrometers, etc., the evaluation of the total reserves of He3 and ilmenite within the regolith and in the lunar interior are still not available.In this paper,we give a rough analysis of the microwave brightness temperature images of the lunar disc observed using the NRAO 12 meter Telescope and Siberian Solar Radio Telescope.We also present the results of the microwave dielectric properties of terrestrial analogues of lunar soil and,discuss some basic relations between the microwave brightness temperature and lunar soil properties.

  14. Ultra Low Surface Brightness Imaging with the Dragonfly Telephoto Array

    CERN Document Server

    Abraham, Roberto G

    2014-01-01

    We describe the Dragonfly Telephoto Array, a robotic imaging system optimized for the detection of extended ultra low surface brightness structures. The array consists of eight Canon 400mm f/2.8 telephoto lenses coupled to eight science-grade commercial CCD cameras. The lenses are mounted on a common framework and are co-aligned to image simultaneously the same position on the sky. The system provides an imaging capability equivalent to a 0.4m aperture f/1.0 refractor with a 2.6 deg X 1.9 deg field of view. The system has no obstructions in the light path, optimized baffling, and internal optical surfaces coated with a new generation of anti-reflection coatings based on sub-wavelength nanostructures. As a result, the array's point spread function has a factor of ~10 less scattered light at large radii than well-baffled reflecting telescopes. The Dragonfly Telephoto Array is capable of imaging extended structures to surface brightness levels below 30 mag/arcsec^2 in 10h integrations (without binning or foregro...

  15. Direct imaging of phase objects enables conventional deconvolution in bright field light microscopy.

    Directory of Open Access Journals (Sweden)

    Carmen Noemí Hernández Candia

    Full Text Available In transmitted optical microscopy, absorption structure and phase structure of the specimen determine the three-dimensional intensity distribution of the image. The elementary impulse responses of the bright field microscope therefore consist of separate absorptive and phase components, precluding general application of linear, conventional deconvolution processing methods to improve image contrast and resolution. However, conventional deconvolution can be applied in the case of pure phase (or pure absorptive objects if the corresponding phase (or absorptive impulse responses of the microscope are known. In this work, we present direct measurements of the phase point- and line-spread functions of a high-aperture microscope operating in transmitted bright field. Polystyrene nanoparticles and microtubules (biological polymer filaments serve as the pure phase point and line objects, respectively, that are imaged with high contrast and low noise using standard microscopy plus digital image processing. Our experimental results agree with a proposed model for the response functions, and confirm previous theoretical predictions. Finally, we use the measured phase point-spread function to apply conventional deconvolution on the bright field images of living, unstained bacteria, resulting in improved definition of cell boundaries and sub-cellular features. These developments demonstrate practical application of standard restoration methods to improve imaging of phase objects such as cells in transmitted light microscopy.

  16. Bright Ray-like Features in the Aftermath of CMEs: White Light vs UV Spectra

    CERN Document Server

    Ciaravella, A; Giordano, S; Raymond, J C

    2013-01-01

    Current sheets are important signatures of magnetic reconnection in the eruption of confined solar magnetic structures. Models of Coronal Mass Ejections (CMEs) involve formation of a current sheet connecting the ejected flux rope with the post eruption magnetic loops. Current sheets have been identified in white light images of CMEs as narrow rays trailing the outward moving CME core, and in ultraviolet spectra as narrow bright features emitting the Fe XVIII line. In this work samples of rays detected in white light images or in ultraviolet spectra have been analyzed. Temperatures, widths, and line intensities of the rays have been measured, and their correlation to the CME properties has been studied. The samples show a wide range of temperatures with hot, coronal and cool rays. In some cases, the UV spectra support the identification of rays as current sheets, but they show that some white light rays are cool material from the CME core. In many cases, both hot and cool material are present, but offset from ...

  17. Imaging features of aggressive angiomyxoma

    International Nuclear Information System (INIS)

    AIM: To describe the imaging features of aggressive angiomyxoma in a rare benign mesenchymal tumour most frequently arising from the perineum in young female patients. MATERIALS AND METHODS: We reviewed the computed tomography (CT) and magnetic resonance (MR) imaging features of patients with aggressive angiomyxoma who were referred to our hospital. The imaging features were correlated with clinical information and pathology in all patients. RESULTS: Four CT and five MR studies were available for five patients (all women, mean age 39, range 24-55). Three patients had recurrent tumour at follow-up. CT and MR imaging demonstrated a well-defined mass-displacing adjacent structures. The tumour was of low attenuation relative to muscle on CT. On MR, the tumour was isointense relative to muscle on T1-weighted image, hyperintense on T2-weighted image and enhanced avidly after gadolinium contrast with a characteristic 'swirled' internal pattern. MR imaging demonstrates the extent of the tumour and its relation to the pelvic floor. Recurrent tumour has a similar appearance to the primary lesion. CONCLUSION: The MR appearances of aggressive angiomyxomas are characteristic, and the diagnosis should be considered in any young woman presenting with a well-defined mass arising from the perineum. Jeyadevan, N. N. etal. (2003). Clinical Radiology58, 157--162

  18. Imaging features of aggressive angiomyxoma

    Energy Technology Data Exchange (ETDEWEB)

    Jeyadevan, N.N.; Sohaib, S.A.A.; Thomas, J.M.; Jeyarajah, A.; Shepherd, J.H.; Fisher, C

    2003-02-01

    AIM: To describe the imaging features of aggressive angiomyxoma in a rare benign mesenchymal tumour most frequently arising from the perineum in young female patients. MATERIALS AND METHODS: We reviewed the computed tomography (CT) and magnetic resonance (MR) imaging features of patients with aggressive angiomyxoma who were referred to our hospital. The imaging features were correlated with clinical information and pathology in all patients. RESULTS: Four CT and five MR studies were available for five patients (all women, mean age 39, range 24-55). Three patients had recurrent tumour at follow-up. CT and MR imaging demonstrated a well-defined mass-displacing adjacent structures. The tumour was of low attenuation relative to muscle on CT. On MR, the tumour was isointense relative to muscle on T1-weighted image, hyperintense on T2-weighted image and enhanced avidly after gadolinium contrast with a characteristic 'swirled' internal pattern. MR imaging demonstrates the extent of the tumour and its relation to the pelvic floor. Recurrent tumour has a similar appearance to the primary lesion. CONCLUSION: The MR appearances of aggressive angiomyxomas are characteristic, and the diagnosis should be considered in any young woman presenting with a well-defined mass arising from the perineum. Jeyadevan, N. N. etal. (2003). Clinical Radiology58, 157--162.

  19. Featured Image: Solar Prominence Eruptions

    Science.gov (United States)

    Kohler, Susanna

    2016-02-01

    In these images from the Solar Dynamics Observatorys AIA instrument (click for the full resolution!), two solar prominence eruptions (one from June 2011 and one from August 2012) are shown in pre- and post-eruption states. The images at the top are taken in the Fe XII 193 bandpass and the images at the bottom are taken in the He II 304 bandpass. When a team of scientists searched through seven years of solar images taken by the STEREO (Solar Terrestrial Relations Observatory) spacecraft, these two eruptions were found to extend all the way out to a distance of 1 AU. They were the only two examples of clear, bright, and compact prominence eruptions found to do so. The scientists, led by Brian Wood (Naval Research Laboratory), used these observations to reconstruct the motion of the eruption and model how prominences expand as they travel away from the Sun. Theimage to the rightshowsa STEREO observation compared to the teams 3D model of theprominences shape and expansion. To learn more about theresults from this study, check out the paper below.CitationBrian E. Wood et al 2016 ApJ 816 67. doi:10.3847/0004-637X/816/2/67

  20. A spectral k-means approach to bright-field cell image segmentation.

    Science.gov (United States)

    Bradbury, Laura; Wan, Justin W L

    2010-01-01

    Automatic segmentation of bright-field cell images is important to cell biologists, but difficult to complete due to the complex nature of the cells in bright-field images (poor contrast, broken halo, missing boundaries). Standard approaches such as level set segmentation and active contours work well for fluorescent images where cells appear as round shape, but become less effective when optical artifacts such as halo exist in bright-field images. In this paper, we present a robust segmentation method which combines the spectral and k-means clustering techniques to locate cells in bright-field images. This approach models an image as a matrix graph and segment different regions of the image by computing the appropriate eigenvectors of the matrix graph and using the k-means algorithm. We illustrate the effectiveness of the method by segmentation results of C2C12 (muscle) cells in bright-field images. PMID:21096019

  1. The Altitude of an Infrared Bright Cloud Feature on Neptune from Near-Infrared Spectroscopy

    CERN Document Server

    Roe, H G; McLean, I S; De Pater, I; Becklin, E E; Figer, D F; Gilbert, A M; Larkin, J E; Levenson, N A; Teplitz, H I; Wilcox, M K; Roe, Henry G.; Graham, James R.; Lean, Ian S. Mc; Pater, Imke de; Figer, Donald F.; Gilbert, Andrea M.; Larkin, James E.; Teplitz, Harry I.; Wilcox, Mavourneen K.

    2001-01-01

    We present 2.03-2.30 micron near-infrared spectroscopy of Neptune taken 1999 June 2 (UT) with the W.M. Keck Observatory's near-infrared spectrometer (NIRSPEC) during the commissioning of the instrument. The spectrum is dominated by a bright cloud feature, possibly a storm or upwelling, in the southern hemisphere at approximately 50 degrees S latitude. The spectrum also includes light from a dimmer northern feature at approximately 30 degrees N latitude. We compare our spectra (R ~ 2000) of these two features with a simple model of Neptune's atmosphere. Given our model assumption that the clouds are flat reflecting layers, we find that the top of the bright southern cloud feature sat at a pressure level of 0.14 (+0.05, -0.03) bar, and thus this cloud did not extend into the stratosphere (P < 0.1 bar). A similar analysis of the dimmer northern feature gives a cloud-top pressure of 0.084 +/- 0.026 bar. This suggests that the features we observed efficiently transport methane to the base of the stratosphere, b...

  2. An Ultraviolet imager to study bright UV sources

    CERN Document Server

    Mathew, Joice; Sarpotdar, Mayuresh; Sreejith, A G; Safonova, Margarita; Murthy, Jayant

    2016-01-01

    We have designed and developed a compact ultraviolet imaging payload to fly on a range of possible platforms such as high altitude balloon experiments, cubesats, space missions, etc. The primary science goals are to study the bright UV sources (mag < 10) and also to look for transients in the Near UV (200 - 300 nm) domain. Our first choice is to place this instrument on a spacecraft going to the Moon as part of the Indian entry into Google lunar X-Prize competition. The major constraints for the instrument are, it should be lightweight (< 2Kg), compact (length < 50cm) and cost effective. The instrument is an 80 mm diameter Cassegrain telescope with a field of view of around half a degree designated for UV imaging. In this paper we will discuss about the various science cases that can be performed by having observations with the instrument on different platforms. We will also describe the design, development and the current state of implementation of the instrument. This includes opto-mechanical and e...

  3. Imaging features of musculoskeletal tuberculosis

    International Nuclear Information System (INIS)

    The purpose of this article is to review the imaging characteristics of musculoskeletal tuberculosis. Skeletal tuberculosis represents one-third of all cases of tuberculosis occurring in extrapulmonary sites. Hematogenous spread from a distant focus elsewhere in the body is the cornerstone in the understanding of imaging features of musculoskeletal tuberculosis. The most common presentations are tuberculous spondylitis, arthritis, osteomyelitis, and soft tissue involvement. The diagnostic value of the different imaging techniques, which include conventional radiography, CT, and MR imaging, are emphasized. Whereas conventional radiography is the mainstay in the diagnosis of tuberculous arthritis and osteomyelitis, MR imaging may detect associated bone marrow and soft tissue abnormalities. MR imaging is generally accepted as the imaging modality of choice for diagnosis, demonstration of the extent of the disease of tuberculous spondylitis, and soft tissue tuberculosis. Moreover, it may be very helpful in the differential diagnosis with pyogenic spondylodiscitis, as it may easily demonstrate anterior corner destruction, the relative preservation of the intervertebral disk, multilevel involvement with or without skip lesions, and a large soft tissue abscess, as these are all arguments in favor of a tuberculous spondylitis. On the other hand, CT is still superior in the demonstration of calcifications, which are found in chronic tuberculous abscesses. (orig.)

  4. Textural features for image classification

    Science.gov (United States)

    Haralick, R. M.; Dinstein, I.; Shanmugam, K.

    1973-01-01

    Description of some easily computable textural features based on gray-tone spatial dependances, and illustration of their application in category-identification tasks of three different kinds of image data - namely, photomicrographs of five kinds of sandstones, 1:20,000 panchromatic aerial photographs of eight land-use categories, and ERTS multispectral imagery containing several land-use categories. Two kinds of decision rules are used - one for which the decision regions are convex polyhedra (a piecewise-linear decision rule), and one for which the decision regions are rectangular parallelpipeds (a min-max decision rule). In each experiment the data set was divided into two parts, a training set and a test set. Test set identification accuracy is 89% for the photomicrographs, 82% for the aerial photographic imagery, and 83% for the satellite imagery. These results indicate that the easily computable textural features probably have a general applicability for a wide variety of image-classification applications.

  5. Automated Adaptive Brightness in Wireless Capsule Endoscopy Using Image Segmentation and Sigmoid Function.

    Science.gov (United States)

    Shrestha, Ravi; Mohammed, Shahed K; Hasan, Md Mehedi; Zhang, Xuechao; Wahid, Khan A

    2016-08-01

    Wireless capsule endoscopy (WCE) plays an important role in the diagnosis of gastrointestinal (GI) diseases by capturing images of human small intestine. Accurate diagnosis of endoscopic images depends heavily on the quality of captured images. Along with image and frame rate, brightness of the image is an important parameter that influences the image quality which leads to the design of an efficient illumination system. Such design involves the choice and placement of proper light source and its ability to illuminate GI surface with proper brightness. Light emitting diodes (LEDs) are normally used as sources where modulated pulses are used to control LED's brightness. In practice, instances like under- and over-illumination are very common in WCE, where the former provides dark images and the later provides bright images with high power consumption. In this paper, we propose a low-power and efficient illumination system that is based on an automated brightness algorithm. The scheme is adaptive in nature, i.e., the brightness level is controlled automatically in real-time while the images are being captured. The captured images are segmented into four equal regions and the brightness level of each region is calculated. Then an adaptive sigmoid function is used to find the optimized brightness level and accordingly a new value of duty cycle of the modulated pulse is generated to capture future images. The algorithm is fully implemented in a capsule prototype and tested with endoscopic images. Commercial capsules like Pillcam and Mirocam were also used in the experiment. The results show that the proposed algorithm works well in controlling the brightness level accordingly to the environmental condition, and as a result, good quality images are captured with an average of 40% brightness level that saves power consumption of the capsule. PMID:27333609

  6. Cell motility dynamics: a novel segmentation algorithm to quantify multi-cellular bright field microscopy images.

    Directory of Open Access Journals (Sweden)

    Assaf Zaritsky

    Full Text Available Confocal microscopy analysis of fluorescence and morphology is becoming the standard tool in cell biology and molecular imaging. Accurate quantification algorithms are required to enhance the understanding of different biological phenomena. We present a novel approach based on image-segmentation of multi-cellular regions in bright field images demonstrating enhanced quantitative analyses and better understanding of cell motility. We present MultiCellSeg, a segmentation algorithm to separate between multi-cellular and background regions for bright field images, which is based on classification of local patches within an image: a cascade of Support Vector Machines (SVMs is applied using basic image features. Post processing includes additional classification and graph-cut segmentation to reclassify erroneous regions and refine the segmentation. This approach leads to a parameter-free and robust algorithm. Comparison to an alternative algorithm on wound healing assay images demonstrates its superiority. The proposed approach was used to evaluate common cell migration models such as wound healing and scatter assay. It was applied to quantify the acceleration effect of Hepatocyte growth factor/scatter factor (HGF/SF on healing rate in a time lapse confocal microscopy wound healing assay and demonstrated that the healing rate is linear in both treated and untreated cells, and that HGF/SF accelerates the healing rate by approximately two-fold. A novel fully automated, accurate, zero-parameters method to classify and score scatter-assay images was developed and demonstrated that multi-cellular texture is an excellent descriptor to measure HGF/SF-induced cell scattering. We show that exploitation of textural information from differential interference contrast (DIC images on the multi-cellular level can prove beneficial for the analyses of wound healing and scatter assays. The proposed approach is generic and can be used alone or alongside traditional

  7. Extramedullary haematopoiesis: radiological imaging features.

    Science.gov (United States)

    Roberts, A S; Shetty, A S; Mellnick, V M; Pickhardt, P J; Bhalla, S; Menias, C O

    2016-09-01

    Extramedullary haematopoiesis (EMH) is defined as the production of blood cells outside of the bone marrow, which occurs when there is inadequate production of blood cells. The most common causes of EMH are myelofibrosis, diffuse osseous metastatic disease replacing the bone marrow, leukaemia, sickle cell disease, and thalassemia. The purpose of this article is to review the common and uncommon imaging appearances of EMH by anatomical compartment. In the thorax, EMH most commonly presents as paravertebral fat-containing masses, and typically does not present a diagnostic dilemma; however, EMH in the abdomen most commonly manifests as hepatosplenomegaly with or without focal soft-tissue masses in the liver, spleen, perirenal space, and in the peritoneum. Hepatosplenomegaly, a non-specific feature, most often occurs without an associated focal mass, which makes suggestion of EMH difficult. EMH manifesting as visceral soft-tissue masses often requires biopsy as the differential diagnosis can include lymphoma, metastatic disease, and sarcoma. Many of these soft-tissue masses do not contain adipose elements, making the diagnosis of EMH difficult. Clinical history is crucial, as EMH would likely not otherwise be in the differential in patients with non-specific abdominal masses. Careful biopsy planning is necessary when EMH is a diagnostic consideration, given the propensity for haemorrhage. Understanding the typical imaging appearances of EMH based on its site of manifestation can help the radiologist when encountered with a finding that is diagnostic for EMH, and can help the radiologist suggest the need and plan appropriately for image-guided biopsy. PMID:27377325

  8. Tongue Image Feature Extraction in TCM

    Institute of Scientific and Technical Information of China (English)

    LI Dong; DU Lian-xiang; LU Fu-ping; DU Jun-ping

    2004-01-01

    In this paper, digital image processing and computer vision techniques are applied to study tongue images for feature extraction with VC++ and Matlab. Extraction and analysis of the tongue surface features are based on shape, color, edge, and texture. The developed software has various functions and good user interface and is easy to use. Feature data for tongue image pattern recognition is provided, which form a sound basis for the future tongue image recognition.

  9. Feature-based Image Sequence Compression Coding

    Institute of Scientific and Technical Information of China (English)

    2001-01-01

    A novel compressing method for video teleconference applications is presented. Semantic-based coding based on human image feature is realized, where human features are adopted as parameters. Model-based coding and the concept of vector coding are combined with the work on image feature extraction to obtain the result.

  10. Color features for dating historical color images

    OpenAIRE

    Fernando, Basura; Muselet, Damien; Khan, Rahat; Tuytelaars, Tinne

    2014-01-01

    Fernando B., Muselet D., Khan R., Tuytelaars T., ''Color features for dating historical color image'', IEEE international conference on image processing - ICIP 2014, 5 pp., October 27-30, 2014, Paris, France.

  11. BRIGHT RAY-LIKE FEATURES IN THE AFTERMATH OF CORONAL MASS EJECTIONS: WHITE LIGHT VERSUS ULTRAVIOLET SPECTRA

    Energy Technology Data Exchange (ETDEWEB)

    Ciaravella, A. [INAF-Osservatorio Astronomico di Palermo, P.za Parlamento 1, I-90134 Palermo (Italy); Webb, D. F. [Institute for Scientific Research, Boston College, Newton, MA 02459 (United States); Giordano, S. [INAF-Osservatorio Astrofisico di Torino, via Osservatorio 20, I-10025 Pino Torinese (Italy); Raymond, J. C. [Harvard-Smithsonian Center for Astrophysics, 60 Garden Street, Cambridge, MA 02138 (United States)

    2013-03-20

    Current sheets (CSs) are important signatures of magnetic reconnection in the eruption of confined solar magnetic structures. Models of coronal mass ejections (CMEs) involve formation of a CS connecting the ejected flux rope with the post-eruption magnetic loops. CSs have been identified in white light (WL) images of CMEs as narrow rays trailing the outward moving CME core, and in ultraviolet spectra as narrow bright features emitting the [Fe XVIII] line. In this work, samples of rays detected in WL images or in ultraviolet spectra have been analyzed. Temperatures, widths, and line intensities of the rays have been measured, and their correlation to the CME properties has been studied. The samples show a wide range of temperatures with hot, coronal, and cool rays. In some cases, the UV spectra support the identification of rays as CSs, but they show that some WL rays are cool material from the CME core. In many cases, both hot and cool material are present, but offset from each other along the Ultraviolet Coronagraph Spectrometer slit. We find that about 18% of the WL rays show very hot gas consistent with the CS interpretation, while about 23% show cold gas that we attribute to cool prominence material draining back from the CME core. The remaining events have ordinary coronal temperatures, perhaps because they have relaxed back to a quiescent state.

  12. Hepatic CT image query using Gabor features

    Institute of Scientific and Technical Information of China (English)

    Chenguang Zhao(赵晨光); Hongyan Cheng(程红岩); Tiange Zhuang(庄天戈)

    2004-01-01

    A retrieval scheme for liver computerize tomography (CT) images based on Gabor texture is presented.For each hepatic CT image, we manually delineate abnormal regions within liver area. Then, a continuous Gabor transform is utilized to analyze the texture of the pathology bearing region and extract the corresponding feature vectors. For a given sample image, we compare its feature vector with those of other images. Similar images with the highest rank are retrieved. In experiments, 45 liver CT images are collected, and the effectiveness of Gabor texture for content based retrieval is verified.

  13. Bright pituitary stalk on MR T1-weighted image. Damming up phenomenon of the neurosecretory granules

    Energy Technology Data Exchange (ETDEWEB)

    Fujisawa, Ichiro; Uokawa, Kyosuke; Horii, Naotoshi; Murakami, Norihiko; Azuma, Nobuyuki; Furuto-Kato, Sumiko; Yamashita, Kohsuke; Nakao, Satoshi; Kageyama, Naoki [Kishiwada City Hospital, Osaka (Japan)

    2002-04-01

    Characteristic findings of the pituitary stalk on magnetic resonance (MR) imaging, which suggest a damming-up phenomenon of neurosecretory granules, were reported. Neurosecretory granules containing vasopressin influence the signal intensity on MR T1-weighted image (T1WI). The normal posterior lobe of the pituitary gland appears as a bright signal on T1WI. The bright signal of the posterior lobe represents the normal content of neurosecretory granules and disappears in patients with central diabetes insipidus. The normal pituitary stalk appears as a low-intermediate intensity signal on sagittal and coronal T1WIs with 3 mm-slice thickness. The pituitary stalk appeared as a bright signal in 20 patients; 13 with pituitary adenoma, 4 with an intrasellar cystic lesion, one with cavernous sinus mass, and 2 with no abnormal MR findings. The pituitary stalk was not severed in any of the cases. The normal bright signal of the posterior lobe disappeared in 17 patients. No patients suffered from symptoms of central diabetes insipidus when the bright pituitary stalk appeared. It is suggested that the origin of the bright signal in the pituitary stalk is the damming up and accumulation of neurosecretory granules in the nerve fibers of the hypothalamohypophyseal tract obstructed by adenoma, postoperative scarring, cystic mass and so on. Probably, the damming-up phenomenon on MR imaging represents the functional integrity of the hypothalamo-neurohypophyseal system, and should be distinguished from an ectopic posterior lobe formation which is caused by stalk transection. (author)

  14. Performance Evaluation of Dominant Brightness Level Based Image Enhancement

    Directory of Open Access Journals (Sweden)

    Geetika Mahajan

    2014-11-01

    Full Text Available This paper has concentrated on the distinctive image enhancement methods. Image enhancement has discovered a standout amongst the most imperative vision applications as it has capability to improve the quality of the digital images. Quality of the poor pictures is improved by this. Various methodologies have been proposed so far for enhancing the nature of the digital pictures. To upgrade picture quality image enhancement can particularly enhance and limit some information introduced in the input image. It is a sort of vision framework which diminishes picture commotion, kill antiquities, and keep up the useful parts. Its aim is to open up certain picture attributes for examination, conclusion and further utilization. The main aim of this paper is to assess the effectiveness of the DBLA over different image enhancement strategies.

  15. Blue Laser Imaging-Bright Improves Endoscopic Recognition of Superficial Esophageal Squamous Cell Carcinoma

    Science.gov (United States)

    Tomie, Akira; Yagi, Nobuaki; Kitae, Hiroaki; Majima, Atsushi; Horii, Yusuke; Kitaichi, Tomoko; Onozawa, Yuriko; Suzuki, Kentaro; Kimura-Tsuchiya, Reiko; Okayama, Tetsuya; Kamada, Kazuhiro; Katada, Kazuhiro; Uchiyama, Kazuhiko; Ishikawa, Takeshi; Takagi, Tomohisa; Naito, Yuji; Itoh, Yoshito

    2016-01-01

    Background/Aims. The aim of this study was to evaluate the endoscopic recognition of esophageal squamous cell carcinoma (ESCC) using four different methods (Olympus white light imaging (O-WLI), Fujifilm white light imaging (F-WLI), narrow band imaging (NBI), and blue laser imaging- (BLI-) bright). Methods. We retrospectively analyzed 25 superficial ESCCs that had been examined using the four different methods. Subjective evaluation was provided by three endoscopists as a ranking score (RS) of each image based on the ease of detection of the cancerous area. For the objective evaluation we calculated the color difference scores (CDS) between the cancerous and noncancerous areas with each of the four methods. Results. There was no difference between the mean RS of O-WLI and F-WLI. The mean RS of NBI was significantly higher than that of O-WLI and that of BLI-bright was significantly higher than that of F-WLI. Moreover, the mean RS of BLI-bright was significantly higher than that of NBI. Furthermore, in the objective evaluation, the mean CDS of BLI-bright was significantly higher than that of O-WLI, F-WLI, and NBI. Conclusion. The recognition of superficial ESCC using BLI-bright was more efficacious than the other methods tested both subjectively and objectively.

  16. The brightness reversal of submarine sand waves in “HJ-1A/B” CCD sun glitter images

    Institute of Scientific and Technical Information of China (English)

    HE Xiekai; CHEN Ninghua; ZHANG Huaguo; GUAN Weibing

    2015-01-01

    The brightness reversal of submarine sand waves appearing in the small satellite constellation for environ-ment and disaster monitoring and forecasting (“HJ-1A/B”) CCD sun glitter images can affect the observation and depth inversion of sand wave topography. The simulations of the normalized sun glitter radiance on the submarine sand waves confirm that the reversal would happen at a specific sensor viewing angle, defined as the critical angle. The difference between the calculated critical angle position and the reversal position in the image is about 1ƍ, which is excellent in agreement. Both the simulation and actual image show that sand wave crests would be indistinct at the reversal position, which may cause problems when using these sun glitter images to analyze spatial characteristics and migration of sand waves. When using the sun glitter image to obtain the depth inversion, one should take the advantage of image properties of sand waves and choose the location in between the reversal position and the brightest position. It is also necessary to pay attention to the brightness reversal when using “HJ-1A/B” CCD images to analyze other oceanic features, such as internal waves, oil slicks, eddies, and ship wakes.

  17. Image fusion using sparse overcomplete feature dictionaries

    Energy Technology Data Exchange (ETDEWEB)

    Brumby, Steven P.; Bettencourt, Luis; Kenyon, Garrett T.; Chartrand, Rick; Wohlberg, Brendt

    2015-10-06

    Approaches for deciding what individuals in a population of visual system "neurons" are looking for using sparse overcomplete feature dictionaries are provided. A sparse overcomplete feature dictionary may be learned for an image dataset and a local sparse representation of the image dataset may be built using the learned feature dictionary. A local maximum pooling operation may be applied on the local sparse representation to produce a translation-tolerant representation of the image dataset. An object may then be classified and/or clustered within the translation-tolerant representation of the image dataset using a supervised classification algorithm and/or an unsupervised clustering algorithm.

  18. Image segmentation using association rule features.

    Science.gov (United States)

    Rushing, John A; Ranganath, Heggere; Hinke, Thomas H; Graves, Sara J

    2002-01-01

    A new type of texture feature based on association rules is described. Association rules have been used in applications such as market basket analysis to capture relationships present among items in large data sets. It is shown that association rules can be adapted to capture frequently occurring local structures in images. The frequency of occurrence of these structures can be used to characterize texture. Methods for segmentation of textured images based on association rule features are described. Simulation results using images consisting of man made and natural textures show that association rule features perform well compared to other widely used texture features. Association rule features are used to detect cumulus cloud fields in GOES satellite images and are found to achieve higher accuracy than other statistical texture features for this problem.

  19. Bright features in Neptune on 2013-2015 from ground-based observations with small (40 cm) and large telescopes (10 m)

    Science.gov (United States)

    Hueso, Ricardo; Delcroix, Marc; Baranec, Christoph; Sánchez-Lavega, Agustín; María Gómez-Forrellad, Josep; Félix Rojas, Jose; Luszcz-Cook, Statia; de Pater, Imke; de Kleer, Katherine; Colas, François; Guarro, Joan; Goczynski, Peter; Jones, Paul; Kivits, Willem; Maxson, Paul; Phillips, Michael; Sussenbach, John; Wesley, Anthony; Hammel, Heidi B.; Pérez-Hoyos, Santiago; Mendikoa, Iñigo; Riddle, Reed; Law, Nicholas M.; Sayanagi, Kunio

    2015-11-01

    Observations of Neptune over the last few years obtained with small telescopes (30-50 cm) have resulted in several detections of bright features on the planet. In 2013, 2014 and 2015, different observers have repeatedly observed features of high contrast at Neptune’s mid-latitudes using long-pass red filters. This success at observing Neptune clouds with such small telescopes is due to the presence of strong methane absorption bands in Neptune’s spectra at red and near infrared wavelengths; these bands provide good contrast for elevated cloud structures. In each case, the atmospheric features identified in the images survived at least a few weeks, but were essentially much more variable and apparently shorter-lived, than the large convective system recently reported on Uranus [de Pater et al. 2015]. The latest and brightest spot on Neptune was first detected on July 13th 2015 with the 2.2m telescope at Calar Alto observatory with the PlanetCam UPV/EHU instrument. The range of wavelengths covered by PlanetCam (from 350 nm to the H band including narrow-band and wide-band filters in and out of methane bands) allows the study of the vertical cloud structure of this bright spot. In particular, the spot is particularly well contrasted at the H band where it accounted to a 40% of the total planet brightness. Observations obtained with small telescopes a few days later provide a good comparison that can be used to scale similar structures in 2013 and 2014 that were observed with 30-50 cm telescopes and the Robo-AO instrument at Palomar observatory. Further high-resolution observations of the 2015 event were obtained in July 25th with the NIRC2 camera in the Keck 2 10-m telescope. These images show the bright spot as a compact bright feature in H band with a longitudinal size of 8,300 km and a latitudinal extension of 5,300 km, well separated from a nearby bright band. The ensemble of observations locate the structure at -41º latitude drifting at about +24.27º/day or

  20. Imaging features of iliopsoas bursitis

    Energy Technology Data Exchange (ETDEWEB)

    Wunderbaldinger, P. [Department of Radiology, University of Vienna (Austria); Center of Molecular Imaging Research, Massachusetts General Hospital, Harvard Medical School, Charlestown, MA (United States); Bremer, C. [Department of Radiology, University of Muenster (Germany); Schellenberger, E. [Center of Molecular Imaging Research, Massachusetts General Hospital, Harvard Medical School, Charlestown, MA (United States); Department of Radiology, Martin-Luther University of Halle-Wittenberg, Halle (Germany); Cejna, M.; Turetschek, K.; Kainberger, F. [Department of Radiology, University of Vienna (Austria)

    2002-02-01

    The aim of this study was firstly to describe the spectrum of imaging findings seen in iliopsoas bursitis, and secondly to compare cross-sectional imaging techniques in the demonstration of the extent, size and appearance of the iliopsoas bursitis as referenced by surgery. Imaging studies of 18 patients (13 women, 5 men; mean age 53 years) with surgically proven iliopsoas bursitis were reviewed. All patients received conventional radiographs of the pelvis and hip, US and MR imaging of the hip. The CT was performed in 5 of the 18 patients. Ultrasound, CT and MR all demonstrated enlarged iliopsoas bursae. The bursal wall was thin and well defined in 83% and thickened in 17% of all cases. The two cases with septations on US were not seen by CT and MRI. A communication between the bursa and the hip joint was seen, and surgically verified, in all 18 patients by MR imaging, whereas US and CT failed to demonstrate it in 44 and 40% of the cases, respectively. Hip joint effusion was seen and verified by surgery in 16 patients by MRI, whereas CT (4 of 5) and US (n=12) underestimated the number. The overall size of the bursa corresponded best between MRI and surgery, whereas CT and US tended to underestimate the size. Contrast enhancement of the bursal wall was seen in all cases. The imaging characteristics of iliopsoas bursitis are a well-defined, thin-walled cystic mass with a communication to the hip joint and peripheral contrast enhancement. The most accurate way to assess iliopsoas bursitis is with MR imaging; thus, it should be used for accurate therapy planning and follow-up studies. In order to initially prove an iliopsoas bursitis, US is the most cost-effective, easy-to-perform and fast alternative. (orig.)

  1. Imaging features of iliopsoas bursitis

    International Nuclear Information System (INIS)

    The aim of this study was firstly to describe the spectrum of imaging findings seen in iliopsoas bursitis, and secondly to compare cross-sectional imaging techniques in the demonstration of the extent, size and appearance of the iliopsoas bursitis as referenced by surgery. Imaging studies of 18 patients (13 women, 5 men; mean age 53 years) with surgically proven iliopsoas bursitis were reviewed. All patients received conventional radiographs of the pelvis and hip, US and MR imaging of the hip. The CT was performed in 5 of the 18 patients. Ultrasound, CT and MR all demonstrated enlarged iliopsoas bursae. The bursal wall was thin and well defined in 83% and thickened in 17% of all cases. The two cases with septations on US were not seen by CT and MRI. A communication between the bursa and the hip joint was seen, and surgically verified, in all 18 patients by MR imaging, whereas US and CT failed to demonstrate it in 44 and 40% of the cases, respectively. Hip joint effusion was seen and verified by surgery in 16 patients by MRI, whereas CT (4 of 5) and US (n=12) underestimated the number. The overall size of the bursa corresponded best between MRI and surgery, whereas CT and US tended to underestimate the size. Contrast enhancement of the bursal wall was seen in all cases. The imaging characteristics of iliopsoas bursitis are a well-defined, thin-walled cystic mass with a communication to the hip joint and peripheral contrast enhancement. The most accurate way to assess iliopsoas bursitis is with MR imaging; thus, it should be used for accurate therapy planning and follow-up studies. In order to initially prove an iliopsoas bursitis, US is the most cost-effective, easy-to-perform and fast alternative. (orig.)

  2. Content Based Image Retrieval by Multi Features using Image Blocks

    Directory of Open Access Journals (Sweden)

    Arpita Mathur

    2013-12-01

    Full Text Available Content based image retrieval (CBIR is an effective method of retrieving images from large image resources. CBIR is a technique in which images are indexed by extracting their low level features like, color, texture, shape, and spatial location, etc. Effective and efficient feature extraction mechanisms are required to improve existing CBIR performance. This paper presents a novel approach of CBIR system in which higher retrieval efficiency is achieved by combining the information of image features color, shape and texture. The color feature is extracted using color histogram for image blocks, for shape feature Canny edge detection algorithm is used and the HSB extraction in blocks is used for texture feature extraction. The feature set of the query image are compared with the feature set of each image in the database. The experiments show that the fusion of multiple features retrieval gives better retrieval results than another approach used by Rao et al. This paper presents comparative study of performance of the two different approaches of CBIR system in which the image features color, shape and texture are used.

  3. Quantitative imaging features: extension of the oncology medical image database

    Science.gov (United States)

    Patel, M. N.; Looney, P. T.; Young, K. C.; Halling-Brown, M. D.

    2015-03-01

    Radiological imaging is fundamental within the healthcare industry and has become routinely adopted for diagnosis, disease monitoring and treatment planning. With the advent of digital imaging modalities and the rapid growth in both diagnostic and therapeutic imaging, the ability to be able to harness this large influx of data is of paramount importance. The Oncology Medical Image Database (OMI-DB) was created to provide a centralized, fully annotated dataset for research. The database contains both processed and unprocessed images, associated data, and annotations and where applicable expert determined ground truths describing features of interest. Medical imaging provides the ability to detect and localize many changes that are important to determine whether a disease is present or a therapy is effective by depicting alterations in anatomic, physiologic, biochemical or molecular processes. Quantitative imaging features are sensitive, specific, accurate and reproducible imaging measures of these changes. Here, we describe an extension to the OMI-DB whereby a range of imaging features and descriptors are pre-calculated using a high throughput approach. The ability to calculate multiple imaging features and data from the acquired images would be valuable and facilitate further research applications investigating detection, prognosis, and classification. The resultant data store contains more than 10 million quantitative features as well as features derived from CAD predictions. Theses data can be used to build predictive models to aid image classification, treatment response assessment as well as to identify prognostic imaging biomarkers.

  4. Retinal image quality assessment using generic features

    Science.gov (United States)

    Fasih, Mahnaz; Langlois, J. M. Pierre; Ben Tahar, Houssem; Cheriet, Farida

    2014-03-01

    Retinal image quality assessment is an important step in automated eye disease diagnosis. Diagnosis accuracy is highly dependent on the quality of retinal images, because poor image quality might prevent the observation of significant eye features and disease manifestations. A robust algorithm is therefore required in order to evaluate the quality of images in a large database. We developed an algorithm for retinal image quality assessment based on generic features that is independent from segmentation methods. It exploits the local sharpness and texture features by applying the cumulative probability of blur detection metric and run-length encoding algorithm, respectively. The quality features are combined to evaluate the image's suitability for diagnosis purposes. Based on the recommendations of medical experts and our experience, we compared a global and a local approach. A support vector machine with radial basis functions was used as a nonlinear classifier in order to classify images to gradable and ungradable groups. We applied our methodology to 65 images of size 2592×1944 pixels that had been graded by a medical expert. The expert evaluated 38 images as gradable and 27 as ungradable. The results indicate very good agreement between the proposed algorithm's predictions and the medical expert's judgment: the sensitivity and specificity for the local approach are respectively 92% and 94%. The algorithm demonstrates sufficient robustness to identify relevant images for automated diagnosis.

  5. Extraction of Facial Features from Color Images

    Directory of Open Access Journals (Sweden)

    J. Pavlovicova

    2008-09-01

    Full Text Available In this paper, a method for localization and extraction of faces and characteristic facial features such as eyes, mouth and face boundaries from color image data is proposed. This approach exploits color properties of human skin to localize image regions – face candidates. The facial features extraction is performed only on preselected face-candidate regions. Likewise, for eyes and mouth localization color information and local contrast around eyes are used. The ellipse of face boundary is determined using gradient image and Hough transform. Algorithm was tested on image database Feret.

  6. A new method for imaging faint objects nearby a bright source

    Institute of Scientific and Technical Information of China (English)

    2000-01-01

    In astronomical observation, it is difficult to obtain the image of faint objects in the peripheral area around a bright celestial body. In order to solve the problem, a new method is designed and experimented, which is called the separation readout technique (SRT). SRT is different from either the traditional coronagraphy or the newly-developed anti-blooming CCD technique, and allows an enough-long exposure to the faint objects in the area around a bright celestial body with the well-preserved bright body's image in one frame. This paper describes in detail the principle of SRT, the computer simulation, the experimental devising and result of SRT observation on a telescope.

  7. Terrain Classification using Multiple Image Features

    Directory of Open Access Journals (Sweden)

    Jharna Majumdar

    2008-05-01

    Full Text Available A wide variety of image processing applications require segmentation and classification ofimages. The problem becomes complex when the images are obtained in an uncontrolledenvironment with a non-uniform illumination. The selection of suitable features is a critical partof an image segmentation and classification process, where the basic objective is to identify theimage regions that are homogeneous but dissimilar to all spatially adjacent regions. This paperproposes an automatic method for the classification of a terrain using image features such asintensity, texture, and edge. The textural features are calculated using statistics of geometricalattributes of connected regions in a sequence of binary images obtained from a texture image.A pixel-wise image segmentation scheme using a multi-resolution pyramid is used to correct thesegmentation process so as to get homogeneous image regions. Localisation of texture boundariesis done using a refined-edge map obtained by convolution, thinning, thresholding, and linking.The individual regions are classified using a database generated from the features extracted fromknown samples of the actual terrain. The algorithm is used to classify airborne images of a terrainobtained from the sensor mounted on an aerial reconnaissance platform and the results arepresented.

  8. Featured Image: Modeling Supernova Remnants

    Science.gov (United States)

    Kohler, Susanna

    2016-05-01

    This image shows a computer simulation of the hydrodynamics within a supernova remnant. The mixing between the outer layers (where color represents the log of density) is caused by turbulence from the Rayleigh-Taylor instability, an effect that arises when the expanding core gas of the supernova is accelerated into denser shell gas. The past standard for supernova-evolution simulations was to perform them in one dimension and then, in post-processing, manually smooth out regions that undergo Rayleigh-Taylor turbulence (an intrinsically multidimensional effect). But in a recent study, Paul Duffell (University of California, Berkeley) has explored how a 1D model could be used to reproduce the multidimensional dynamics that occur in turbulence from this instability. For more information, check out the paper below!CitationPaul C. Duffell 2016 ApJ 821 76. doi:10.3847/0004-637X/821/2/76

  9. Automatic Extraction of Planetary Image Features

    Science.gov (United States)

    Troglio, G.; LeMoigne, J.; Moser, G.; Serpico, S. B.; Benediktsson, J. A.

    2009-01-01

    With the launch of several Lunar missions such as the Lunar Reconnaissance Orbiter (LRO) and Chandrayaan-1, a large amount of Lunar images will be acquired and will need to be analyzed. Although many automatic feature extraction methods have been proposed and utilized for Earth remote sensing images, these methods are not always applicable to Lunar data that often present low contrast and uneven illumination characteristics. In this paper, we propose a new method for the extraction of Lunar features (that can be generalized to other planetary images), based on the combination of several image processing techniques, a watershed segmentation and the generalized Hough Transform. This feature extraction has many applications, among which image registration.

  10. Bright-field cell image segmentation by principal component pursuit with an Ncut penalization

    Science.gov (United States)

    Chen, Yuehuan; Wan, Justin W. L.

    2015-03-01

    Segmentation of cells in time-lapse bright-field microscopic images is crucial in understanding cell behaviours for oncological research. However, the complex nature of the cells makes it difficult to segment cells accurately. Furthermore, poor contrast, broken cell boundaries and the halo artifact pose additional challenges to this problem. Standard segmentation techniques such as edged-based methods, watershed, or active contours result in poor segmentation. Other existing methods for bright-field images cannot provide good results without localized segmentation steps. In this paper, we present two robust mathematical models to segment bright-field cells automatically for the entire image. These models treat cell image segmentation as a background subtraction problem, which can be formulated as a Principal Component Pursuit (PCP) problem. Our first segmentation model is formulated as a PCP with nonnegative constraints. We exploit the sparse component of the PCP solution for identifying the cell pixels. However, there is no control on the quality of the sparse component and the nonzero entries can scatter all over the image, resulting in a noisy segmentation. The second model is an improvement of the first model by combining PCP with spectral clustering. Seemingly unrelated approaches, we combine the two techniques by incorporating normalized-cut in the PCP as a measure for the quality of the segmentation. These two models have been applied to a set of C2C12 cells obtained from bright-field microscopy. Experimental results demonstrate that the proposed models are effective in segmenting cells from bright-field images.

  11. Imaging features of ciliated hepatic foregut cyst

    Institute of Scientific and Technical Information of China (English)

    Song-Hua Fang; Dan-Jun Dong; Shi-Zheng Zhang

    2005-01-01

    Ciliated hepatic foregut cyst (CHFC) is a very rare cystic lesion of the liver that is histologically similar to bronchogenic cyst. We report one case of CHFC that was hard to distinguish from solid-cystic neoplasm in imaging features. Magnetic resonance imaging was helpful in differentiating these cysts from other lesions.

  12. Logarithmic Adaptive Neighborhood Image Processing (LANIP: Introduction, Connections to Human Brightness Perception, and Application Issues

    Directory of Open Access Journals (Sweden)

    J. Debayle

    2007-01-01

    Full Text Available A new framework for image representation, processing, and analysis is introduced and exposed through practical applications. The proposed approach is called logarithmic adaptive neighborhood image processing (LANIP since it is based on the logarithmic image processing (LIP and on the general adaptive neighborhood image processing (GANIP approaches, that allow several intensity and spatial properties of the human brightness perception to be mathematically modeled and operationalized, and computationally implemented. The LANIP approach is mathematically, computationally, and practically relevant and is particularly connected to several human visual laws and characteristics such as: intensity range inversion, saturation characteristic, Weber’s and Fechner’s laws, psychophysical contrast, spatial adaptivity, multiscale adaptivity, morphological symmetry property. The LANIP approach is finally exposed in several areas: image multiscale decomposition, image restoration, image segmentation, and image enhancement, through biomedical materials and visual imaging applications.

  13. Logarithmic Adaptive Neighborhood Image Processing (LANIP: Introduction, Connections to Human Brightness Perception, and Application Issues

    Directory of Open Access Journals (Sweden)

    Pinoli J-C

    2007-01-01

    Full Text Available A new framework for image representation, processing, and analysis is introduced and exposed through practical applications. The proposed approach is called logarithmic adaptive neighborhood image processing (LANIP since it is based on the logarithmic image processing (LIP and on the general adaptive neighborhood image processing (GANIP approaches, that allow several intensity and spatial properties of the human brightness perception to be mathematically modeled and operationalized, and computationally implemented. The LANIP approach is mathematically, computationally, and practically relevant and is particularly connected to several human visual laws and characteristics such as: intensity range inversion, saturation characteristic, Weber's and Fechner's laws, psychophysical contrast, spatial adaptivity, multiscale adaptivity, morphological symmetry property. The LANIP approach is finally exposed in several areas: image multiscale decomposition, image restoration, image segmentation, and image enhancement, through biomedical materials and visual imaging applications.

  14. MULTI-FEATURE MUTUAL INFORMATION IMAGE REGISTRATION

    Directory of Open Access Journals (Sweden)

    Dejan Tomaževič

    2012-03-01

    Full Text Available Nowadays, information-theoretic similarity measures, especially the mutual information and its derivatives, are one of the most frequently used measures of global intensity feature correspondence in image registration. Because the traditional mutual information similarity measure ignores the dependency of intensity values of neighboring image elements, registration based on mutual information is not robust in cases of low global intensity correspondence. Robustness can be improved by adding spatial information in the form of local intensity changes to the global intensity correspondence. This paper presents a novel method, by which intensities, together with spatial information, i.e., relations between neighboring image elements in the form of intensity gradients, are included in information-theoretic similarity measures. In contrast to a number of heuristic methods that include additional features into the generic mutual information measure, the proposed method strictly follows information theory under certain assumptions on feature probability distribution. The novel approach solves the problem of efficient estimation of multifeature mutual information from sparse high-dimensional feature space. The proposed measure was tested on magnetic resonance (MR and computed tomography (CT images. In addition, the measure was tested on positron emission tomography (PET and MR images from the widely used Retrospective Image Registration Evaluation project image database. The results indicate that multi-feature mutual information, which combines image intensities and intensity gradients, is more robust than the standard single-feature intensity based mutual information, especially in cases of low global intensity correspondences, such as in PET/MR images or significant intensity inhomogeneity.

  15. Approximating tasseled cap values to evaluate brightness, greenness, and wetness for the Advanced Land Imager (ALI)

    Science.gov (United States)

    Yamamoto, Kristina H.; Finn, Michael P.

    2012-01-01

    The Tasseled Cap transformation is a method of image band conversion to enhance spectral information. It primarily is used to detect vegetation using the derived brightness, greenness, and wetness bands. An approximation of Tasseled Cap values for the Advanced Land Imager was investigated and compared to the Landsat Thematic Mapper Tasseled Cap values. Despite sharing similar spectral, temporal, and spatial resolution, the two systems are not interchangeable with regard to Tasseled Cap matrices.

  16. Edge detection and reduction of brightness of students' bubble form images

    Science.gov (United States)

    Ilkin, Sümeyya; Şahin, Suhap

    2015-03-01

    Optical Mark Recognition (OMR) is a traditional data input technique and an important human computer interaction technique which is widely used in education testing. This paper proposes a new idea for grading multiple-choice test which is based on a camera on smartphone. The system key techniques and relevant implementations, which include the image scan, edge detection and reduction of brightness on colorful bubble form images, are presented.

  17. Near-Infrared Imaging of Barred Halo Dominated Low Surface Brightness Galaxies

    OpenAIRE

    Honey, M.; Das, M.; Ninan, J. P.; Purvankara, M.

    2016-01-01

    We present a near-infrared (NIR) imaging study of barred low surface brightness (LSB) galaxies using the TIFR near-infrared Spectrometer and Imager (TIRSPEC). LSB galaxies are dark matter dominated, late type spirals that have low luminosity stellar disks but large neutral hydrogen (HI) gas disks. Using SDSS images of a very large sample of LSB galaxies derived from the literature, we found that the barred fraction is only 8.3%. We imaged twenty five barred LSB galaxies in the J, H, K$_S$ wav...

  18. Secret data embedding scheme modifying the frequency of occurrence of image brightness values

    Indian Academy of Sciences (India)

    Yildiray Yalman; Ismail Erturk

    2014-08-01

    The main purpose of this presented work is to develop a data embedding method based on a new digital image histogram modification approach. The proposed scheme fundamentally is concerned about the frequency of occurrence of the image brightness values of the cover image for the data embedding procedures. The proposed scheme effectively realizes both perceptual invisibility and statistical invisibility so that obtained covered images are highly robust against common perceptual and statistical steganalysis techniques. The scheme provides reasonably higher payload values than its counterparts, as well as providing comparatively improved PSNR results.

  19. Solving jigsaw puzzles using image features

    DEFF Research Database (Denmark)

    Nielsen, Ture R.; Drewsen, Peter; Hansen, Klaus

    2008-01-01

    algorithm which exploits the divide and conquer paradigm to reduce the combinatorially complex problem by classifying the puzzle pieces and comparing pieces drawn from the same group. The paper includes a brief preliminary investigation of some image features used in the classification.......In this article, we describe a method for automatic solving of the jigsaw puzzle problem based on using image features instead of the shape of the pieces. The image features are used for obtaining an accurate measure for edge similarity to be used in a new edge matching algorithm. The algorithm...... is used in a general puzzle solving method which is based on a greedy algorithm previously proved successful. We have been able to solve computer generated puzzles of 320 pieces as well as a real puzzle of 54 pieces by exclusively using image information. Additionally, we investigate a new scalable...

  20. Sunspot Bright Points

    CERN Document Server

    Choudhary, Debi Prasad

    2010-01-01

    We used the flux calibrated images through the Broad Band Filter Imager and Stokes Polarimeter data obtained with the Solar Optical Telescope onboard the Hinode spacecraft to study the properties of bright points in and around the sunspots. The well isolated bright points were selected and classified as umbral dot, peripheral umbral dot, penumbral grains and G-band bright point depending on their location. Most of the bright points are smaller than about 150 km. The larger points are mostly associated with the penumbral features. The bright points are not uniformly distributed over the umbra but preferentially located around the penumbral boundary and in the fast decaying parts of umbra. The color temperature of the bright points, derived using the continuum irradiance, are in the range of 4600 K to 6600 K with cooler ones located in the umbra. The temperature increases as a function of distance from the center to outside. The G-band, CN-band and CaII H flux of the bright points as a function of their blue ba...

  1. Bright-Field Imaging and Optical Coherence Tomography of the Mouse Posterior Eye.

    Science.gov (United States)

    Krebs, Mark P; Xiao, Mei; Sheppard, Keith; Hicks, Wanda; Nishina, Patsy M

    2016-01-01

    Noninvasive live imaging has been used extensively for ocular phenotyping in mouse vision research. Bright-field imaging and optical coherence tomography (OCT) are two methods that are particularly useful for assessing the posterior mouse eye (fundus), including the retina, retinal pigment epithelium, and choroid, and are widely applied due to the commercial availability of sophisticated instruments and software. Here, we provide a guide to using these approaches with an emphasis on post-acquisition image processing using Fiji, a bundled version of the Java-based public domain software ImageJ. A bright-field fundus imaging protocol is described for acquisition of multi-frame videos, followed by image registration to reduce motion artifacts, averaging to reduce noise, shading correction to compensate for uneven illumination, filtering to improve image detail, and rotation to adjust orientation. An OCT imaging protocol is described for acquiring replicate volume scans, with subsequent registration and averaging to yield three-dimensional datasets that show reduced motion artifacts and enhanced detail. The Fiji algorithms used in these protocols are designed for batch processing and are freely available. The image acquisition and processing approaches described here may facilitate quantitative phenotyping of the mouse eye in drug discovery, mutagenesis screening, and the functional cataloging of mouse genes by individual laboratories and large-scale projects, such as the Knockout Mouse Phenotyping Project and International Mouse Phenotyping Consortium.

  2. Featured Image: A New Look at Malin 1

    Science.gov (United States)

    Kohler, Susanna

    2016-01-01

    Monochrome, inverted version of Malin 1. [Adapted from Galaz et al. 2015]The above image of Malin 1, the faintest and largest low-surface-brightness galaxy ever observed, was obtained with an instrument called Megacam on the 6.5m Magellan/Clay telescope. Gaspar Galaz (Pontifical Catholic University of Chile) and collaborators used Megacam to obtain deep optical observations of Malin 1. They then used novel noise-reduction and image-processing techniques to create this spectacular image of the spiral galaxy located roughly 1.2 billion light-years away. This new view of Malin 1 reveals details weve never before seen, including a stream within the disk that may have been caused by a past interaction between Malin 1 and another galaxy near it. Check outthe image to the rightfor a monochrome, inverted version thatmakes it a little easier to see some of Malin 1s features. To see the full original images and to learn more about what the images reveal about Malin 1, see the paper below.CitationGaspar Galaz et al 2015 ApJ 815 L29. doi:10.1088/2041-8205/815/2/L29

  3. Automatic Feature Extraction from Planetary Images

    Science.gov (United States)

    Troglio, Giulia; Le Moigne, Jacqueline; Benediktsson, Jon A.; Moser, Gabriele; Serpico, Sebastiano B.

    2010-01-01

    With the launch of several planetary missions in the last decade, a large amount of planetary images has already been acquired and much more will be available for analysis in the coming years. The image data need to be analyzed, preferably by automatic processing techniques because of the huge amount of data. Although many automatic feature extraction methods have been proposed and utilized for Earth remote sensing images, these methods are not always applicable to planetary data that often present low contrast and uneven illumination characteristics. Different methods have already been presented for crater extraction from planetary images, but the detection of other types of planetary features has not been addressed yet. Here, we propose a new unsupervised method for the extraction of different features from the surface of the analyzed planet, based on the combination of several image processing techniques, including a watershed segmentation and the generalized Hough Transform. The method has many applications, among which image registration and can be applied to arbitrary planetary images.

  4. Wood recognition using image texture features.

    Directory of Open Access Journals (Sweden)

    Hang-jun Wang

    Full Text Available Inspired by theories of higher local order autocorrelation (HLAC, this paper presents a simple, novel, yet very powerful approach for wood recognition. The method is suitable for wood database applications, which are of great importance in wood related industries and administrations. At the feature extraction stage, a set of features is extracted from Mask Matching Image (MMI. The MMI features preserve the mask matching information gathered from the HLAC methods. The texture information in the image can then be accurately extracted from the statistical and geometrical features. In particular, richer information and enhanced discriminative power is achieved through the length histogram, a new histogram that embodies the width and height histograms. The performance of the proposed approach is compared to the state-of-the-art HLAC approaches using the wood stereogram dataset ZAFU WS 24. By conducting extensive experiments on ZAFU WS 24, we show that our approach significantly improves the classification accuracy.

  5. Robustness of the Digital Image Watermarking Techniques against Brightness and Rotation Attack

    Directory of Open Access Journals (Sweden)

    Raman Kumar, Singh

    2009-09-01

    Full Text Available The recent advent in the field of multimedia proposed a many facilities in transport, transmission and manipulation of data. Along with this advancement of facilities there are larger threats in authentication of data, its licensed use and protection against illegal use of data. A lot of digital image watermarking techniques have been designed and implemented to stop the illegal use of the digital multimedia images. This paper compares the robustness of three different watermarking schemes against brightness and rotation attacks. The robustness of the watermarked images has been verified on the parameters of PSNR (Peak Signal to Noise Ratio, RMSE (Root Mean Square Error and MAE (Mean Absolute Error.

  6. Onboard Image Registration from Invariant Features

    Science.gov (United States)

    Wang, Yi; Ng, Justin; Garay, Michael J.; Burl, Michael C

    2008-01-01

    This paper describes a feature-based image registration technique that is potentially well-suited for onboard deployment. The overall goal is to provide a fast, robust method for dynamically combining observations from multiple platforms into sensors webs that respond quickly to short-lived events and provide rich observations of objects that evolve in space and time. The approach, which has enjoyed considerable success in mainstream computer vision applications, uses invariant SIFT descriptors extracted at image interest points together with the RANSAC algorithm to robustly estimate transformation parameters that relate one image to another. Experimental results for two satellite image registration tasks are presented: (1) automatic registration of images from the MODIS instrument on Terra to the MODIS instrument on Aqua and (2) automatic stabilization of a multi-day sequence of GOES-West images collected during the October 2007 Southern California wildfires.

  7. Imaging features of alveolar soft part sarcoma

    Institute of Scientific and Technical Information of China (English)

    Teng Jin; Ping Zhang Co-first author; Xiaoming Li

    2015-01-01

    Objective The aim of this study was to analyze the imaging features of alveolar soft part sarcoma (ASPS). Methods The imaging features of 11 cases with ASPS were retrospectively analyzed. Results ASPS mainly exhibited an isointense or slightly high signal intensity on T1-weighted imaging (T1WI), and a mixed high signal on T2-weighted imaging (T2WI). ASPS was partial, with rich tortuous flow voids, or “line-like” low signal septa. The essence of the mass was heterogeneous enhancement. The 1H-MRS showed a slight choline peak at 3.2 ppm. Conclusion The wel-circumscribed mass and blood voids, combined with “line-like” low signals play a significant role in diagnosis. The choline peak and the other signs may be auxiliary diagnoses.

  8. Vector quantizer based on brightness maps for image compression with the polynomial transform

    Science.gov (United States)

    Escalante-Ramirez, Boris; Moreno-Gutierrez, Mauricio; Silvan-Cardenas, Jose L.

    2002-11-01

    We present a vector quantization scheme acting on brightness fields based on distance/distortion criteria correspondent with psycho-visual aspects. These criteria quantify sensorial distortion between vectors that represent either portions of a digital image or alternatively, coefficients of a transform-based coding system. In the latter case, we use an image representation model, namely the Hermite transform, that is based on some of the main perceptual characteristics of the human vision system (HVS) and in their response to light stimulus. Energy coding in the brightness domain, determination of local structure, code-book training and local orientation analysis are all obtained by means of the Hermite transform. This paper, for thematic reasons, is divided in four sections. The first one will shortly highlight the importance of having newer and better compression algorithms. This section will also serve to explain briefly the most relevant characteristics of the HVS, advantages and disadvantages related with the behavior of our vision in front of ocular stimulus. The second section shall go through a quick review of vector quantization techniques, focusing their performance on image treatment, as a preview for the image vector quantizer compressor actually constructed in section 5. Third chapter was chosen to concentrate the most important data gathered on brightness models. The building of this so-called brightness maps (quantification of the human perception on the visible objects reflectance), in a bi-dimensional model, will be addressed here. The Hermite transform, a special case of polynomial transforms, and its usefulness, will be treated, in an applicable discrete form, in the fourth chapter. As we have learned from previous works 1, Hermite transform has showed to be a useful and practical solution to efficiently code the energy within an image block, deciding which kind of quantization is to be used upon them (whether scalar or vector). It will also be

  9. Straight line feature based image distortion correction

    Institute of Scientific and Technical Information of China (English)

    Zhang Haofeng; Zhao Chunxia; Lu Jianfeng; Tang Zhenmin; Yang Jingyu

    2008-01-01

    An image distortion correction method is proposed, which uses the straight line features. Many parallel lines of different direction from different images were extracted, and then were used to optimize the distortion parameters by nonlinear least square. The thought of step by step was added when the optimization method working. 3D world coordi-nation is not need to know, and the method is easy to implement. The experiment result shows its high accuracy.

  10. Image Mining Using Texture and Shape Feature

    Directory of Open Access Journals (Sweden)

    Prof.Rupali Sawant

    2010-12-01

    Full Text Available Discovering knowledge from data stored in typical alphanumeric databases, such as relational databases, has been the focal point of most of the work in database mining. However, with advances in secondary and tertiary storage capacity, coupled with a relatively low storage cost, more and more non standard data (in the form of images is being accumulated. This vast collection of image data can also be mined to discover new and valuable knowledge. During theprocess of image mining, the concepts in different hierarchiesand their relationships are extracted from different hierarchies and granularities, and association rule mining and concept clustering are consequently implemented. The generalization and specialization of concepts are realized in different hierarchies, lower layer concepts can be upgraded to upper layer concepts, and upper layer concepts guide the extraction of lower layer concepts. It is a process from image data to image information, from image information to imageknowledge, from lower layer concepts to upper layer concept lattice and cloud model theory is proposed. The methods of image mining from image texture and shape features are introduced here, which include the following basic steps: firstly pre-process images secondly use cloud model to extract concepts, lastly use concept lattice to extracta series of image knowledge.

  11. Near-infrared imaging of barred halo-dominated low surface brightness galaxies

    Science.gov (United States)

    Honey, M.; Das, M.; Ninan, J. P.; Manoj, P.

    2016-10-01

    We present a near-infrared (NIR) imaging study of barred low surface brightness (LSB) galaxies using the TIFR1 NIR Spectrometer and Imager. LSB galaxies are dark matter dominated, late-type spirals that have low-luminosity stellar discs but large neutral hydrogen (H I) gas discs. Using Sloan Digital Sky Survey images of a very large sample of LSB galaxies derived from the literature, we found that the barred fraction is only 8.3 per cent. We imaged 25 barred LSB galaxies in the J, H, KS wavebands and 29 in the KS band. Most of the bars are much brighter than their stellar discs, which appear to be very diffuse. Our image analysis gives deprojected mean bar sizes of Rb/R25 = 0.40 and ellipticities e ≈ 0.45, which are similar to bars in high surface brightness galaxies. Thus, although bars are rare in LSB galaxies, they appear to be just as strong as bars found in normal galaxies. There is no correlation of Rb/R25 or e with the relative H I or stellar masses of the galaxies. In the (J - KS) colour images most of the bars have no significant colour gradient which indicates that their stellar population is uniformly distributed and confirms that they have low dust content.

  12. Microburst applications of brightness temperature difference between GOES Imager channels 3 and 4

    CERN Document Server

    Pryor, Kenneth L

    2010-01-01

    This paper presents a new application of brightness temperature difference (BTD) between Geostationary Operational Environmental Satellite (GOES) imager channels 3 and 4. It has been found recently that the BTD between GOES infrared channel 3 (water vapor) and channel 4 (thermal infrared) can highlight regions where severe outflow wind generation (i.e. downbursts, microbursts) is likely due to the channeling of dry mid-tropospheric air into the precipitation core of a deep, moist convective storm. Case studies demonstrating effective operational use of this image product are presented for two significant marine transportation accidents as well as a severe downburst event over the Washington, DC metropolitan area in April 2010.

  13. Near-Infrared Imaging of Barred Halo Dominated Low Surface Brightness Galaxies

    CERN Document Server

    Honey, M; Ninan, J P; Purvankara, M

    2016-01-01

    We present a near-infrared (NIR) imaging study of barred low surface brightness (LSB) galaxies using the TIFR near-infrared Spectrometer and Imager (TIRSPEC). LSB galaxies are dark matter dominated, late type spirals that have low luminosity stellar disks but large neutral hydrogen (HI) gas disks. Using SDSS images of a very large sample of LSB galaxies derived from the literature, we found that the barred fraction is only 8.3%. We imaged twenty five barred LSB galaxies in the J, H, K$_S$ wavebands and twenty nine in the K$_S$ band. Most of the bars are much brighter than their stellar disks, which appear to be very diffuse. Our image analysis gives deprojected mean bar sizes of $R_{b}/R_{25}$ = 0.40 and ellipticities $e$ $\\approx$ 0.45, which are similar to bars in high surface brightness galaxies. Thus, although bars are rare in LSB galaxies, they appear to be just as strong as bars found in normal galaxies. There is no correlation of $R_{b}/R_{25}$ or $e$ with the relative HI or stellar masses of the galax...

  14. Barrett's esophagus: clinical features, obesity, and imaging.

    LENUS (Irish Health Repository)

    Quigley, Eamonn M M

    2011-09-01

    The following includes commentaries on clinical features and imaging of Barrett\\'s esophagus (BE); the clinical factors that influence the development of BE; the influence of body fat distribution and central obesity; the role of adipocytokines and proinflammatory markers in carcinogenesis; the role of body mass index (BMI) in healing of Barrett\\'s epithelium; the role of surgery in prevention of carcinogenesis in BE; the importance of double-contrast esophagography and cross-sectional images of the esophagus; and the value of positron emission tomography\\/computed tomography.

  15. Bright-field imaging of compound semiconductors using aberration-corrected scanning transmission electron microscopy

    Science.gov (United States)

    Aoki, Toshihiro; Lu, Jing; McCartney, Martha R.; Smith, David J.

    2016-09-01

    This study reports the observation of six different zincblende compound semiconductors in [110] projection using large-collection-angle bright-field (LABF) imaging with an aberration-corrected scanning transmission electron microscope. Phase contrast is completely suppressed when the collection semi-angle is set equal to the convergence semi-angle and there are no reversals in image contrast with changes in defocus or thickness. The optimum focus for imaging closely separated pairs of atomic columns (‘dumbbells’) is unique and easily recognized, and the positions of atomic columns occupied by heavier atoms always have darker intensity than those occupied by lighter atoms. Thus, the crystal polarity of compound semiconductors can be determined unambiguously. Moreover, it is concluded that the LABF imaging mode will be highly beneficial for studying other more complicated heterostructures at the atomic scale.

  16. Feature Evaluation for Building Facade Images - AN Empirical Study

    Science.gov (United States)

    Yang, M. Y.; Förstner, W.; Chai, D.

    2012-08-01

    The classification of building facade images is a challenging problem that receives a great deal of attention in the photogrammetry community. Image classification is critically dependent on the features. In this paper, we perform an empirical feature evaluation task for building facade images. Feature sets we choose are basic features, color features, histogram features, Peucker features, texture features, and SIFT features. We present an approach for region-wise labeling using an efficient randomized decision forest classifier and local features. We conduct our experiments with building facade image classification on the eTRIMS dataset, where our focus is the object classes building, car, door, pavement, road, sky, vegetation, and window.

  17. Image Denoising with Modified Wavelets Feature Restoration

    Directory of Open Access Journals (Sweden)

    Sachin D Ruikar

    2012-03-01

    Full Text Available Image Denoising is the principle problem of image restoration and many scholars have been devoted to this area and proposed lots of methods. In this paper we propose modified feature restoration algorithm based on threshold and neighbor technique which gives better result for all types of noise. Because of some limits of conventional methods in image denoising, several drawbacks are seen in the conventional methods such as introduction of blur and edges degradation. Those can be removed by using the new technique which is based on the wavelet transforms. The shrinkage algorithms like Universal shrink, Visue shrink, bays shrink; have strengths in Gaussian noise removal. Our proposed method gives noise removal for all types of noise, in wavelet domain. It gives a better peak signal to noise ratio as compared to traditional methods.

  18. Imaging features of juxtacortical chondroma in children

    Energy Technology Data Exchange (ETDEWEB)

    Miller, Stephen F. [St. Jude Children' s Research Hospital, Department of Radiological Sciences, Memphis, TN (United States)

    2014-01-15

    Juxtacortical chondroma is a rare benign bone lesion in children. Children usually present with a mildly painful mass, which prompts diagnostic imaging studies. The rarity of this condition often presents a diagnostic challenge. Correct diagnosis is crucial in guiding surgical management. To describe the characteristic imaging findings of juxtacortical chondroma in children. We identified all children who were diagnosed with juxtacortical chondroma between 1998 and 2012. A single experienced pediatric radiologist reviewed all diagnostic imaging studies, including plain radiographs, CT, MR and bone scans. Seven children (5 boys and 2 girls) with juxtacortical chondroma were identified, ranging in age from 6 years to 16 years (mean 12.3 years). Mild pain and a palpable mass were present in all seven children. Plain radiographs were available in 6/7, MR in 7/7, CT in 4/7 and skeletal scintigraphy in 5/7 children. Three lesions were located in the proximal humerus, with one each in the distal radius, distal femur, proximal tibia and scapula. Radiographic and CT features deemed highly suggestive of juxtacortical chondroma included cortical scalloping, underlying cortical sclerosis and overhanging margins. MRI features consistent with juxtacortical chondroma included isointensity to skeletal muscle on T1, marked hyperintensity on T2 and peripheral rim enhancement after contrast agent administration. One of seven lesions demonstrated intramedullary extension, and 2/7 showed adjacent soft-tissue edema. Juxtacortical chondroma is an uncommon benign lesion in children with characteristic features on plain radiographs, CT and MR. Recognition of these features is invaluable in guiding appropriate surgical management. (orig.)

  19. Augmented microscopy: real-time overlay of bright-field and near-infrared fluorescence images.

    Science.gov (United States)

    Watson, Jeffrey R; Gainer, Christian F; Martirosyan, Nikolay; Skoch, Jesse; Lemole, G Michael; Anton, Rein; Romanowski, Marek

    2015-10-01

    Intraoperative applications of near-infrared (NIR) fluorescent contrast agents can be aided by instrumentation capable of merging the view of surgical field with that of NIR fluorescence. We demonstrate augmented microscopy, an intraoperative imaging technique in which bright-field (real) and electronically processed NIR fluorescence (synthetic) images are merged within the optical path of a stereomicroscope. Under luminance of 100,000 lx, representing typical illumination of the surgical field, the augmented microscope detects 189 nM concentration of indocyanine green and produces a composite of the real and synthetic images within the eyepiece of the microscope at 20 fps. Augmentation described here can be implemented as an add-on module to visualize NIR contrast agents, laser beams, or various types of electronic data within the surgical microscopes commonly used in neurosurgical, cerebrovascular, otolaryngological, and ophthalmic procedures.

  20. Bone feature analysis using image processing techniques.

    Science.gov (United States)

    Liu, Z Q; Austin, T; Thomas, C D; Clement, J G

    1996-01-01

    In order to establish the correlation between bone structure and age, and information about age-related bone changes, it is necessary to study microstructural features of human bone. Traditionally, in bone biology and forensic science, the analysis if bone cross-sections has been carried out manually. Such a process is known to be slow, inefficient and prone to human error. Consequently, the results obtained so far have been unreliable. In this paper we present a new approach to quantitative analysis of cross-sections of human bones using digital image processing techniques. We demonstrate that such a system is able to extract various bone features consistently and is capable of providing more reliable data and statistics for bones. Consequently, we will be able to correlate features of bone microstructure with age and possibly also with age related bone diseases such as osteoporosis. The development of knowledge-based computer vision-systems for automated bone image analysis can now be considered feasible.

  1. A hybrid features based image matching algorithm

    Science.gov (United States)

    Tu, Zhenbiao; Lin, Tao; Sun, Xiao; Dou, Hao; Ming, Delie

    2015-12-01

    In this paper, we present a novel image matching method to find the correspondences between two sets of image interest points. The proposed method is based on a revised third-order tensor graph matching method, and introduces an energy function that takes four kinds of energy term into account. The third-order tensor method can hardly deal with the situation that the number of interest points is huge. To deal with this problem, we use a potential matching set and a vote mechanism to decompose the matching task into several sub-tasks. Moreover, the third-order tensor method sometimes could only find a local optimum solution. Thus we use a cluster method to divide the feature points into some groups and only sample feature triangles between different groups, which could make the algorithm to find the global optimum solution much easier. Experiments on different image databases could prove that our new method would obtain correct matching results with relatively high efficiency.

  2. Image Processing Based Customized Image Editor and Gesture Controlled Embedded Robot Coupled with Voice Control Features

    Directory of Open Access Journals (Sweden)

    Somnath Kar

    2015-11-01

    Full Text Available In modern sciences and technologies, images gain much broader scopes due to the ever growing importance of scientific visualization (of often large-scale complex scientific/experimental data like microarray data in genetic research, or real-time multi-asset portfolio trading in finance etc. In this paper, a proposal has been presented to implement a Graphical User Interface (GUI consisting of various MATLAB functions related to image processing and using the same to create a basic image processing editor having different features like, viewing the red, green and blue components of a color image separately, color detection and various other features like noise addition and removal, edge detection, cropping, resizing, rotation, histogram adjust, brightness control that is used in a basic image editor along with object detection and tracking. This has been further extended to provide reliable and a more natural technique for the user to navigate a robot in the natural environment using gestures based on color tracking. Additionally, Voice control technique has been employed to navigate the robot in various directions in the Cartesian plane employing normal Speech recognition techniques available in Microsoft Visual Basic.

  3. Integrated Feature Extraction for Image Retrieval

    OpenAIRE

    Poorani M; Prathiba T; Ravindran G

    2013-01-01

    To retrieve the images from large database that are highly related to the query image where query image is given by user. Three features are used for retrieving the images, which are color, shape and texture. These features are extracted by different techniques. Color feature is extracted by Color Histogram and Color Descriptor. Shape feature is extracted by Hu Moment and Edge detection Method. Texture feature is extracted by Gray Level co-occurrence matrix and texture descriptor. We Compare ...

  4. Imaging features of foot osteoid osteoma

    Energy Technology Data Exchange (ETDEWEB)

    Shukla, Satyen; Clarke, Andrew W.; Saifuddin, Asif [Royal National Orthopaedic Hospital NHS Trust, Department of Radiology, Stanmore, Middlesex (United Kingdom)

    2010-07-15

    We performed a retrospective review of the imaging of nine patients with a diagnosis of foot osteoid osteoma (OO). Radiographs, computed tomography (CT) and magnetic resonance imaging (MRI) had been performed in all patients. Radiographic features evaluated were the identification of a nidus and cortical thickening. CT features noted were nidus location (affected bone - intramedullary, intracortical, subarticular) and nidus calcification. MRI features noted were the presence of an identifiable nidus, presence and grade of bone oedema and whether a joint effusion was identified. Of the nine patients, three were female and six male, with a mean age of 21 years (range 11-39 years). Classical symptoms of OO (night pain, relief with aspirin) were identified in five of eight (62.5%) cases (in one case, the medical records could not be retrieved). In five patients the lesion was located in the hindfoot (four calcaneus, one talus), while four were in the mid- or forefoot (two metatarsal and two phalangeal). Radiographs were normal in all patients with hindfoot OO. CT identified the nidus in all cases (89%) except one terminal phalanx lesion, while MRI demonstrated a nidus in six of nine cases (67%). The nidus was of predominantly intermediate signal intensity on T1-weighted (T1W) sequences, with intermediate to high signal intensity on T2-weighted (T2W) sequences. High-grade bone marrow oedema, limited to the affected bone and adjacent soft tissue oedema was identified in all cases. In a young patient with chronic hindfoot pain and a normal radiograph, MRI features suggestive of possible OO include extensive bone marrow oedema limited to one bone, with a possible nidus demonstrated in two-thirds of cases. The presence or absence of a nidus should be confirmed with high-resolution CT. (orig.)

  5. Feature extraction & image processing for computer vision

    CERN Document Server

    Nixon, Mark

    2012-01-01

    This book is an essential guide to the implementation of image processing and computer vision techniques, with tutorial introductions and sample code in Matlab. Algorithms are presented and fully explained to enable complete understanding of the methods and techniques demonstrated. As one reviewer noted, ""The main strength of the proposed book is the exemplar code of the algorithms."" Fully updated with the latest developments in feature extraction, including expanded tutorials and new techniques, this new edition contains extensive new material on Haar wavelets, Viola-Jones, bilateral filt

  6. Percentage Contributions from Atmospheric and Surface Features to Computed Brightness Temperatures

    Science.gov (United States)

    Jackson, G. S.

    2006-12-01

    Over the past few years, there has become an increasing interest in the use of millimeter-wave (mm-wave) and sub-millimeter-wave (submm-wave) radiometer observations to investigate the properties of ice particles in clouds. Passive radiometric channels respond to both the integrated particle mass throughout the volume and field of view, and to the amount, location, and size distribution of the frozen (and liquid) particles with the sensitivity varying for different frequencies and hydrometeor types. One methodology used since the 1960's to discern the relationship between the physical state observed and the brightness temperature (TB) is through the temperature weighting function profile. In this research, the temperature weighting function concept is exploited to analyze the sensitivity of various characteristics of the cloud profile, such as relative humidity, ice water path, liquid water path, and surface emissivity. In our numerical analysis, we compute the contribution (in Kelvin) from each of these cloud and surface characteristics, so that the sum of these various parts equals the computed TB. Furthermore, the percentage contribution from each of these characteristics is assessed. There is some intermingling/contamination of the contributions from various components due to the integrated nature of passive observations and the absorption and scattering between the vertical layers, but all in all the knowledge gained is useful. This investigation probes the sensitivity over several cloud classifications, such as cirrus, blizzards, light snow, anvil clouds, and heavy rain. The focus is on mm-wave and submm-wave frequencies, however discussions of the effects of cloud variations to frequencies as low as 10 GHz and up to 874 GHz will also be presented. The results show that nearly 60% of the TB value at 89 GHz comes from the earth's surface for even the heaviest blizzard snow rates. On the other hand, a significant percentage of the TB value comes from the snow

  7. Targeted imaging of EGFR overexpressed cancer cells by brightly fluorescent nanoparticles conjugated with cetuximab.

    Science.gov (United States)

    Gao, Meng; Su, Huifang; Lin, Gengwei; Li, Shiwu; Yu, Xingsu; Qin, Anjun; Zhao, Zujin; Zhang, Zhenfeng; Tang, Ben Zhong

    2016-08-11

    To improve the treatment efficiency and reduce side effects in cancer therapy, accurate diagnosis of cancer cell types at a molecular level is highly desirable. Fluorescent nanoparticles (NPs) are especially suitable for detecting molecular biomarkers of cancer with advantages of superior brightness, easy decoration and high resolution. However, the conventional organic fluorophores, conjugated polymers, and inorganic quantum dots suffer from the drawbacks of aggregation-caused quenching (ACQ), low photostability, and heavy metal toxicity, respectively, which severely restrict their applications in NPs-based fluorescence imaging. To overcome these limitations, herein, we have developed fluorescent nanoparticles based on a t-BuPITBT-TPE fluorophore derived from aggregation-induced emission (AIE)-active tetraphenylethene. Through encapsulating t-BuPITBT-TPE within biocompatible DSPE-PEG and further decorating with a monoclonal antibody cetuximab (C225), the obtained t-BuPITBT-TPE-C225 NPs can be used for targeted imaging of non-small cell lung cancer cells with an overexpressed epidermal growth factor receptor (EGFR). The specific targeting ability of t-BuPITBT-TPE-C225 NPs has been well verified by confocal microscopy and flow cytometry experiments. The t-BuPITBT-TPE-C225 NPs have shown significant advantages in terms of highly efficient red emission, good bio-compatibility, and excellent photostability. This work provides a promising method for precise diagnosis of cancer cells by antibody-functionalized fluorescent NPs with high brightness. PMID:27468980

  8. Bright and black blood imaging of the carotid bifurcation at 3.0 T

    International Nuclear Information System (INIS)

    Purpose: The aim of this study was to evaluate our preliminary experience at 3.0 T with imaging of the carotid bifurcation in healthy and atherosclerotic subjects. Application at 3.0 T is motivated by the signal-to-noise gain for improving spatial resolution and reducing signal averaging requirements. Materials and methods: We utilized a dual phased array coil and applied 2D, 3D time of flight (TOF) and turbo spin echo (TSE) sequences with comparison of two lumen signal suppression methods for black blood (BB) TSE imaging including double inversion preparation (DIR) and spatial presaturation pulses. The signal-to-noise ratios (SNR) of healthy carotid vessel walls were compared in 2D and 3D BB TSE acquisitions. The bright and black blood multi-contrast exam was demonstrated for a complex carotid plaque. Results: Contrast-to-noise (CNR) greater than 150 was achieved between the lumen and suppressed background for 3D TOF. For BB, both methods provided sufficient lumen signal suppression but slight residual flow artifacts remained at the bifurcation level. As expected 3D TSE images had higher SNR compared to 2D, but increased motion sensitivity is a significant issue for 3D at high field. For multi-contrast imaging of atherosclerotic plaque, fibrous, calcified and lipid components were resolved. The CNR ratio of fibrous (bright on PDW, T2W) and calcified (dark in T1W, T2W, PDW) plaque components was maximal in the T2W images. The 3D TOF angiogram indicating a 40% stenosis was complemented by 3D multi-planar reformat of BB images that displayed plaque extent. Detection of intimal thickening, the earliest change associated with atherosclerotic progression was observed in BB PDW images at 3.0 T. Conclusions: High SNR and CNR images have been demonstrated for the healthy and diseased carotid. Improvements in RF coils along with pulse sequence optimization, and evaluation of endogenous and exogenous contrast mechanisms will further enhance carotid imaging at 3.0 T

  9. Magnetic Resonance Imaging Features of Neuromyelitis Optica

    Energy Technology Data Exchange (ETDEWEB)

    You, Sun Kyung; Song, Chang June; Park, Woon Ju; Lee, In Ho; Son, Eun Hee [Chungnam National University College of Medicine, Chungnam National University Hospital, Daejeon (Korea, Republic of)

    2013-03-15

    To report the magnetic resonance (MR) imaging features of the spinal cord and brain in patients of neuromyelitis optica (NMO). Between January 2001 and March 2010, the MR images (spinal cord, brain, and orbit) and the clinical and serologic findings of 11 NMO patients were retrospectively reviewed. The contrast-enhancement of the spinal cord was performed (20/23). The presence and pattern of the contrast-enhancement in the spinal cord were classified into 5 types. Acute myelitis was monophasic in 8 patients (8/11, 72.7%); and optic neuritis preceded acute myelitis in most patients. Longitudinally extensive cord lesion (average, 7.3 vertebral segments) was involved. The most common type was the diffuse and subtle enhancement of the spinal cord with a multifocal nodular, linear or segmental intense enhancement (45%). Most of the brain lesions (5/11, 10 lesions) were located in the brain stem, thalamus and callososeptal interphase. Anti-Ro autoantibody was positive in 2 patients, and they showed a high relapse rate of acute myelitis. Anti-NMO IgG was positive in 4 patients (4/7, 66.7%). The imaging findings of acute myelitis in NMO may helpful in making an early diagnosis of NMO which can result in a severe damage to the spinal cord, and to make a differential diagnosis of multiple sclerosis and inflammatory diseases of the spinal cord such as toxocariasis.

  10. Color image retrieval using edge and edge-spatial features

    Institute of Scientific and Technical Information of China (English)

    Chaobing Huang; Quan Liu

    2006-01-01

    @@ A novel methodology to integrate edge feature and edge-spatial feature of an image is proposed. The edge feature is described by edge histogram of image, the edge-spatial feature is described by spatial distribution of pixels of identical edge value in the image. Experimental results show that the method can achieve better retrieval performance, especially for color natural images with more complex spatial layout.

  11. Image Retrieval Based on Content Using Color Feature

    OpenAIRE

    Afifi, Ahmed J.; Wesam M. Ashour

    2012-01-01

    Content-based image retrieval from large resources has become an area of wide interest in many applications. In this paper we present a CBIR system that uses Ranklet Transform and the color feature as a visual feature to represent the images. Ranklet Transform is proposed as a preprocessing step to make the image invariant to rotation and any image enhancement operations. To speed up the retrieval time, images are clustered according to their features using k-means clustering algorithm.

  12. The relationship study between image features and detection probability based on psychology experiments

    Science.gov (United States)

    Lin, Wei; Chen, Yu-hua; Wang, Ji-yuan; Gao, Hong-sheng; Wang, Ji-jun; Su, Rong-hua; Mao, Wei

    2011-04-01

    Detection probability is an important index to represent and estimate target viability, which provides basis for target recognition and decision-making. But it will expend a mass of time and manpower to obtain detection probability in reality. At the same time, due to the different interpretation of personnel practice knowledge and experience, a great difference will often exist in the datum obtained. By means of studying the relationship between image features and perception quantity based on psychology experiments, the probability model has been established, in which the process is as following.Firstly, four image features have been extracted and quantified, which affect directly detection. Four feature similarity degrees between target and background were defined. Secondly, the relationship between single image feature similarity degree and perception quantity was set up based on psychological principle, and psychological experiments of target interpretation were designed which includes about five hundred people for interpretation and two hundred images. In order to reduce image features correlativity, a lot of artificial synthesis images have been made which include images with single brightness feature difference, images with single chromaticity feature difference, images with single texture feature difference and images with single shape feature difference. By analyzing and fitting a mass of experiments datum, the model quantitys have been determined. Finally, by applying statistical decision theory and experimental results, the relationship between perception quantity with target detection probability has been found. With the verification of a great deal of target interpretation in practice, the target detection probability can be obtained by the model quickly and objectively.

  13. Retrieval of Ocean Surface Windspeed and Rainrate from the Hurricane Imaging Radiometer (HIRAD) Brightness Temperature Observations

    Science.gov (United States)

    Biswas, Sayak K.; Jones, Linwood; Roberts, Jason; Ruf, Christopher; Ulhorn, Eric; Miller, Timothy

    2012-01-01

    The Hurricane Imaging Radiometer (HIRAD) is a new airborne synthetic aperture passive microwave radiometer capable of wide swath imaging of the ocean surface wind speed under heavy precipitation e.g. in tropical cyclones. It uses interferometric signal processing to produce upwelling brightness temperature (Tb) images at its four operating frequencies 4, 5, 6 and 6.6 GHz [1,2]. HIRAD participated in NASA s Genesis and Rapid Intensification Processes (GRIP) mission during 2010 as its first science field campaign. It produced Tb images with 70 km swath width and 3 km resolution from a 20 km altitude. From this, ocean surface wind speed and column averaged atmospheric liquid water content can be retrieved across the swath. The column averaged liquid water then could be related to an average rain rate. The retrieval algorithm (and the HIRAD instrument itself) is a direct descendant of the nadir-only Stepped Frequency Microwave Radiometer that is used operationally by the NOAA Hurricane Research Division to monitor tropical cyclones [3,4]. However, due to HIRAD s slant viewing geometry (compared to nadir viewing SFMR) a major modification is required in the algorithm. Results based on the modified algorithm from the GRIP campaign will be presented in the paper.

  14. 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.

  15. Digital Dental X-Ray Image Segmentation and Feature Extraction

    OpenAIRE

    Abdolvahab Ehsani Rad; Mohd. Shafry Mohd. Rahim; Alireza Norouzi

    2013-01-01

    The process of analysis of such images is important in order to improve quantify medical imaging systems. It is significant to analysis the dental x-ray images we need features of image. In this paper we present a method for segmentation and feature extraction of dental x-ray images. The proposed method has been implemented by using level-set method for segmentation after image enhancement and illustrate contour for teeth to complete the segmentation step. Furthermore, we extracted multiple f...

  16. Fast Fractal Image Encoding Based on Special Image Features

    Institute of Scientific and Technical Information of China (English)

    ZHANG Chao; ZHOU Yiming; ZHANG Zengke

    2007-01-01

    The fractal image encoding method has received much attention for its many advantages over other methods,such as high decoding quality at high compression ratios. However, because every range block must be compared to all domain blocks in the codebook to find the best-matched one during the coding procedure, baseline fractal coding (BFC) is quite time consuming. To speed up fractal coding, a new fast fractal encoding algorithm is proposed. This algorithm aims at reducing the size of the search window during the domain-range matching process to minimize the computational cost. A new theorem presented in this paper shows that a special feature of the image can be used to do this work. Based on this theorem, the most inappropriate domain blocks, whose features are not similar to that of the given range block, are excluded before matching. Thus, the best-matched block can be captured much more quickly than in the BFC approachThe experimental results show that the runtime of the proposed method is reduced greatly compared to the BFC method. At the same time,the new algorithm also achieves high reconstructed image quality. In addition,the method can be incorporated with other fast algorithms to achieve better performance.Therefore, the proposed algorithm has a much better application potential than BFC.

  17. Accurate Image Retrieval Algorithm Based on Color and Texture Feature

    Directory of Open Access Journals (Sweden)

    Chunlai Yan

    2013-06-01

    Full Text Available Content-Based Image Retrieval (CBIR is one of the most active hot spots in the current research field of multimedia retrieval. According to the description and extraction of visual content (feature of the image, CBIR aims to find images that contain specified content (feature in the image database. In this paper, several key technologies of CBIR, e. g. the extraction of the color and texture features of the image, as well as the similarity measures are investigated. On the basis of the theoretical research, an image retrieval system based on color and texture features is designed. In this system, the Weighted Color Feature based on HSV space is adopted as a color feature vector, four features of the Co-occurrence Matrix, saying Energy, Entropy, Inertia Quadrature and Correlation, are used to construct texture vectors, and the Euclidean distance for similarity measure is employed as well. Experimental results show that this CBIR system is efficient in image retrieval.

  18. Image retrieval using both color and texture features

    Institute of Scientific and Technical Information of China (English)

    2007-01-01

    In order to improve the retrieval performance of images, this paper proposes an efficient approach for extracting and retrieving color images. The block diagram of our proposed approach to content-based image retrieval (CBIR) is given firstly, and then we introduce three image feature extracting arithmetic including color histogram, edge histogram and edge direction histogram, the histogram Euclidean distance, cosine distance and histogram intersection are used to measure the image level similarity. On the basis of using color and texture features separately, a new method for image retrieval using combined features is proposed. With the test for an image database including 766 general-purpose images and comparison and analysis of performance evaluation for features and similarity measures, our proposed retrieval approach demonstrates a promising performance. Experiment shows that combined features are superior to every single one of the three features in retrieval.

  19. Color Image Segmentation Based on Statistics of Location and Feature Similarity

    Science.gov (United States)

    Mori, Fumihiko; Yamada, Hiromitsu; Mizuno, Makoto; Sugano, Naotoshi

    The process of “image segmentation and extracting remarkable regions” is an important research subject for the image understanding. However, an algorithm based on the global features is hardly found. The requisite of such an image segmentation algorism is to reduce as much as possible the over segmentation and over unification. We developed an algorithm using the multidimensional convex hull based on the density as the global feature. In the concrete, we propose a new algorithm in which regions are expanded according to the statistics of the region such as the mean value, standard deviation, maximum value and minimum value of pixel location, brightness and color elements and the statistics are updated. We also introduced a new concept of conspicuity degree and applied it to the various 21 images to examine the effectiveness. The remarkable object regions, which were extracted by the presented system, highly coincided with those which were pointed by the sixty four subjects who attended the psychological experiment.

  20. Content-Based Image Retrieval Using Multiple Features

    OpenAIRE

    Zhang, Chi; Huang, Lei

    2014-01-01

    Algorithms of Content-Based Image Retrieval (CBIR) have been well developed along with the explosion of information. These algorithms are mainly distinguished based on feature used to describe the image content. In this paper, the algorithms that are based on color feature and texture feature for image retrieval will be presented. Color Coherence Vector based image retrieval algorithm is also attempted during the implementation process, but the best result is generated from the algorithms tha...

  1. Inter- and Intra-Observer Variability in Prostate Definition With Tissue Harmonic and Brightness Mode Imaging

    International Nuclear Information System (INIS)

    Purpose: The objective of this study was to compare the relative utility of tissue harmonic (H) and brightness (B) transrectal ultrasound (TRUS) images of the prostate by studying interobserver and intraobserver variation in prostate delineation. Methods and Materials: Ten patients with early-stage disease were randomly selected. TRUS images of prostates were acquired using B and H modes. The prostates on all images were contoured by an experienced radiation oncologist (RO) and five equally trained observers. The observers were blinded to information regarding patient and imaging mode. The volumes of prostate glands and areas of midgland slices were calculated. Volumes contoured were compared among the observers and between observer group and RO. Contours on one patient were repeated five times by four observers to evaluate the intraobserver variability. Results: A one-sample Student t-test showed the volumes outlined by five observers are in agreement (p > 0.05) with the RO. Paired Student t-test showed prostate volumes (p = 0.008) and midgland areas (p = 0.006) with H mode were significantly smaller than that with B mode. Two-factor analysis of variances showed significant interobserver variability (p < 0.001) in prostate volumes and areas. Inter- and intraobserver consistency was quantified as the standard deviation of mean volumes and areas, and concordance indices. It was found that for small glands (≤35 cc) H mode provided greater interobserver consistency; however, for large glands (≥35 cc), B mode provided more consistent estimates. Conclusions: H mode provided superior inter- and intraobserver agreement in prostate volume definition for small to medium prostates. In large glands, H mode does not exhibit any additional advantage. Although harmonic imaging has not proven advantageous for all cases, its utilization seems to be judicious for small prostates.

  2. Inter- and Intra-Observer Variability in Prostate Definition With Tissue Harmonic and Brightness Mode Imaging

    Energy Technology Data Exchange (ETDEWEB)

    Sandhu, Gurpreet Kaur, E-mail: Gurpreet.Sandhu2@albertahealthservices.ca [Department of Medical Physics, Tom Baker Cancer Centre, Calgary, Alberta (Canada); Department of Physics and Astronomy, University of Calgary, Calgary, Alberta (Canada); Dunscombe, Peter [Department of Medical Physics, Tom Baker Cancer Centre, Calgary, Alberta (Canada); Department of Physics and Astronomy, University of Calgary, Calgary, Alberta (Canada); Department of Oncology, Faculty of Medicine, University of Calgary, Calgary, Alberta (Canada); Meyer, Tyler [Department of Medical Physics, Tom Baker Cancer Centre, Calgary, Alberta (Canada); Department of Physics and Astronomy, University of Calgary, Calgary, Alberta (Canada); Pavamani, Simon [Department of Oncology, Faculty of Medicine, University of Calgary, Calgary, Alberta (Canada); Department of Radiation Oncology, Christian Medical College, Vellore (India); Khan, Rao [Department of Medical Physics, Tom Baker Cancer Centre, Calgary, Alberta (Canada); Department of Physics and Astronomy, University of Calgary, Calgary, Alberta (Canada); Department of Oncology, Faculty of Medicine, University of Calgary, Calgary, Alberta (Canada)

    2012-01-01

    Purpose: The objective of this study was to compare the relative utility of tissue harmonic (H) and brightness (B) transrectal ultrasound (TRUS) images of the prostate by studying interobserver and intraobserver variation in prostate delineation. Methods and Materials: Ten patients with early-stage disease were randomly selected. TRUS images of prostates were acquired using B and H modes. The prostates on all images were contoured by an experienced radiation oncologist (RO) and five equally trained observers. The observers were blinded to information regarding patient and imaging mode. The volumes of prostate glands and areas of midgland slices were calculated. Volumes contoured were compared among the observers and between observer group and RO. Contours on one patient were repeated five times by four observers to evaluate the intraobserver variability. Results: A one-sample Student t-test showed the volumes outlined by five observers are in agreement (p > 0.05) with the RO. Paired Student t-test showed prostate volumes (p = 0.008) and midgland areas (p = 0.006) with H mode were significantly smaller than that with B mode. Two-factor analysis of variances showed significant interobserver variability (p < 0.001) in prostate volumes and areas. Inter- and intraobserver consistency was quantified as the standard deviation of mean volumes and areas, and concordance indices. It was found that for small glands ({<=}35 cc) H mode provided greater interobserver consistency; however, for large glands ({>=}35 cc), B mode provided more consistent estimates. Conclusions: H mode provided superior inter- and intraobserver agreement in prostate volume definition for small to medium prostates. In large glands, H mode does not exhibit any additional advantage. Although harmonic imaging has not proven advantageous for all cases, its utilization seems to be judicious for small prostates.

  3. 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

  4. Image feature extraction based multiple ant colonies cooperation

    Science.gov (United States)

    Zhang, Zhilong; Yang, Weiping; Li, Jicheng

    2015-05-01

    This paper presents a novel image feature extraction algorithm based on multiple ant colonies cooperation. Firstly, a low resolution version of the input image is created using Gaussian pyramid algorithm, and two ant colonies are spread on the source image and low resolution image respectively. The ant colony on the low resolution image uses phase congruency as its inspiration information, while the ant colony on the source image uses gradient magnitude as its inspiration information. These two ant colonies cooperate to extract salient image features through sharing a same pheromone matrix. After the optimization process, image features are detected based on thresholding the pheromone matrix. Since gradient magnitude and phase congruency of the input image are used as inspiration information of the ant colonies, our algorithm shows higher intelligence and is capable of acquiring more complete and meaningful image features than other simpler edge detectors.

  5. Image feature detectors and descriptors foundations and applications

    CERN Document Server

    Hassaballah, Mahmoud

    2016-01-01

    This book provides readers with a selection of high-quality chapters that cover both theoretical concepts and practical applications of image feature detectors and descriptors. It serves as reference for researchers and practitioners by featuring survey chapters and research contributions on image feature detectors and descriptors. Additionally, it emphasizes several keywords in both theoretical and practical aspects of image feature extraction. The keywords include acceleration of feature detection and extraction, hardware implantations, image segmentation, evolutionary algorithm, ordinal measures, as well as visual speech recognition. .

  6. Imaging features of extraaxial musculoskeletal tuberculosis

    International Nuclear Information System (INIS)

    Tuberculosis (TB) continues to be a public health problem in both developing and industrialized countries. TB can involve pulmonary as well as extrapulmonary sites. The musculoskeletal system is involved in 1–3% of patients with tuberculosis. Although musculoskeletal TB has become uncommon in the Western world, it remains a huge problem in Asia, Africa, and many developing countries. Tuberculous spondylitis is the most common form of musculoskeletal TB and accounts for approximately 50% of cases. Extraspinal musculoskeletal TB shows a predilection for large joints (hip and knee) and para-articular areas; isolated soft tissue TB is extremely rare. Early diagnosis and prompt treatment are mandatory to prevent serious destruction of joints and skeletal deformity. However, due to the nonspecific and often indolent clinical presentation, the diagnosis may be delayed. Radiological assessment is often the first step in the diagnostic workup of patients with musculoskeletal TB and further investigations are decided by the findings on radiography. Both the radiologist and the clinician should be aware of the possibility of this diagnosis. In this manuscript we review the imaging features of extraspinal bone, joint, and soft tissue TB

  7. Image registration in high-dimensional feature space

    Science.gov (United States)

    Neemuchwala, Huzefa F.; Hero, Alfred O.

    2005-03-01

    Image registration is a difficult task especially when spurrious image intensity differences and spatial variations between the two images are present. To robustify image registration algorithms to such spurrious variations it can be useful to employ an image registration matching criteria on higher dimensional feature spaces. This paper will present an overviewof our recent work on image registration using high dimensional image features and entropic graph matching criteria. New entropic graph estimates of information divergence measures will be presented. We will demonstrate the advantage of our approach for ultrasound breast image registration.

  8. THE IDENTIFICATION OF PILL USING FEATURE EXTRACTION IN IMAGE MINING

    OpenAIRE

    Hema, A.; E. Anna Saro

    2015-01-01

    With the help of image mining techniques, an automatic pill identification system was investigated in this study for matching the images of the pills based on its several features like imprint, color, size and shape. Image mining is an inter-disciplinary task requiring expertise from various fields such as computer vision, image retrieval, image matching and pattern recognition. Image mining is the method in which the unusual patterns are detected so that both hidden and useful data images ca...

  9. Comparative Study of Triangulation based and Feature based Image Morphing

    Directory of Open Access Journals (Sweden)

    Ms. Bhumika G. Bhatt

    2012-01-01

    Full Text Available Image Morphing is one of the most powerful Digital Image processing technique, which is used to enhancemany multimedia projects, presentations, education and computer based training. It is also used inmedical imaging field to recover features not visible in images by establishing correspondence of featuresamong successive pair of scanned images. This paper discuss what morphing is and implementation ofTriangulation based morphing Technique and Feature based Image Morphing. IT analyze both morphingtechniques in terms of different attributes such as computational complexity, Visual quality of morphobtained and complexity involved in selection of features.

  10. Feature coding for image representation and recognition

    CERN Document Server

    Huang, Yongzhen

    2015-01-01

    This brief presents a comprehensive introduction to feature coding, which serves as a key module for the typical object recognition pipeline. The text offers a rich blend of theory and practice while reflects the recent developments on feature coding, covering the following five aspects: (1) Review the state-of-the-art, analyzing the motivations and mathematical representations of various feature coding methods; (2) Explore how various feature coding algorithms evolve along years; (3) Summarize the main characteristics of typical feature coding algorithms and categorize them accordingly; (4) D

  11. A NOVEL REGION FEATURE USED IN MULTISENSOR IMAGE FUSION

    Institute of Scientific and Technical Information of China (English)

    2006-01-01

    A new region feature which emphasized the salience of target region and its neighbors is proposed.In region segmentation-based multisensor image fusion scheme, the presented feature can be extracted from each segmented region to determine the fusion weight. Experimental results demonstrate that the proposed feature has extensive application scope and it provides much more information for each region. It can not only be used in image fusion but also be used in other image processing applications.

  12. Gender Classification Based on Geometry Features of Palm Image

    OpenAIRE

    Ming Wu; Yubo Yuan

    2014-01-01

    This paper presents a novel gender classification method based on geometry features of palm image which is simple, fast, and easy to handle. This gender classification method based on geometry features comprises two main attributes. The first one is feature extraction by image processing. The other one is classification system with polynomial smooth support vector machine (PSSVM). A total of 180 palm images were collected from 30 persons to verify the validity of the proposed gender classi...

  13. Assessing image features for vision-based robot positioning

    OpenAIRE

    Wells, Gordon; Torras, Carme

    2001-01-01

    The development of any robotics application relying on visual information always raises the key question of what image features would be most informative about the motion to be performed. In this paper, we address this question in the context of visual robot positioning, where a neural network is used to learn the mapping between image features and robot movements, and global image descriptors are preferred to local geometric features. Using a statistical measure of variable interdependence c...

  14. New synthesizing feature parameter of wear particles image

    Institute of Scientific and Technical Information of China (English)

    2001-01-01

    This paper outlines the application of wavelet analysis method to computering wear par-ticles image processing and introduces the concept of grain parameter for wear particle imagebased on statistical feature parameters. The feature of wear particles image can be obtained fromthe wavelet decomposition and the statistics analysis. Test results showed that grain parametercan be used as a synthesizing feature parameter for wear particle image.

  15. Feature fusion method for edge detection of color images

    Institute of Scientific and Technical Information of China (English)

    Ma Yu; Gu Xiaodong; Wang Yuanyuan

    2009-01-01

    A novel feature fusion method is proposed for the edge detection of color images. Except for the typical features used in edge detection, the color contrast similarity and the orientation consistency are also selected as the features. The four features are combined together as a parameter to detect the edges of color images. Experimental results show that the method can inhibit noisy edges and facilitate the detection for weak edges. It has a better performance than conventional methods in noisy environments.

  16. Intrinsic feature-based pose measurement for imaging motion compensation

    Science.gov (United States)

    Baba, Justin S.; Goddard, Jr., James Samuel

    2014-08-19

    Systems and methods for generating motion corrected tomographic images are provided. A method includes obtaining first images of a region of interest (ROI) to be imaged and associated with a first time, where the first images are associated with different positions and orientations with respect to the ROI. The method also includes defining an active region in the each of the first images and selecting intrinsic features in each of the first images based on the active region. Second, identifying a portion of the intrinsic features temporally and spatially matching intrinsic features in corresponding ones of second images of the ROI associated with a second time prior to the first time and computing three-dimensional (3D) coordinates for the portion of the intrinsic features. Finally, the method includes computing a relative pose for the first images based on the 3D coordinates.

  17. Improving SMOS retrieved salinity: characterization of systematic errors in reconstructed and modelled brightness temperature images

    Science.gov (United States)

    Gourrion, J.; Guimbard, S.; Sabia, R.; Portabella, M.; Gonzalez, V.; Turiel, A.; Ballabrera, J.; Gabarro, C.; Perez, F.; Martinez, J.

    2012-04-01

    The Microwave Imaging Radiometer using Aperture Synthesis (MIRAS) instrument onboard the Soil Moisture and Ocean Salinity (SMOS) mission was launched on November 2nd, 2009 with the aim of providing, over the oceans, synoptic sea surface salinity (SSS) measurements with spatial and temporal coverage adequate for large-scale oceanographic studies. For each single satellite overpass, SSS is retrieved after collecting, at fixed ground locations, a series of brightness temperature from successive scenes corresponding to various geometrical and polarization conditions. SSS is inversed through minimization of the difference between reconstructed and modeled brightness temperatures. To meet the challenging mission requirements, retrieved SSS needs to accomplish an accuracy of 0.1 psu after averaging in a 10- or 30-day period and 2°x2° or 1°x1° spatial boxes, respectively. It is expected that, at such scales, the high radiometric noise can be reduced to a level such that remaining errors and inconsistencies in the retrieved salinity fields can essentially be related to (1) systematic brightness temperature errors in the antenna reference frame, (2) systematic errors in the Geophysical Model Function - GMF, used to model the observations and retrieve salinity - for specific environmental conditions and/or particular auxiliary parameter values and (3) errors in the auxiliary datasets used as input to the GMF. The present communication primarily aims at adressing above point 1 and possibly point 2 for the whole polarimetric information i.e. issued from both co-polar and cross-polar measurements. Several factors may potentially produce systematic errors in the antenna reference frame: the unavoidable fact that all antenna are not perfectly identical, the imperfect characterization of the instrument response e.g. antenna patterns, account for receiver temperatures in the reconstruction, calibration using flat sky scenes, implementation of ripple reduction algorithms at sharp

  18. Introduction: feature issue on In Vivo Microcirculation Imaging

    OpenAIRE

    Dunn, Andrew K.; Leitgeb, Rainer; Wang, Ruikang K.; Zhang, Hao F.

    2011-01-01

    The editors introduce the Biomedical Optics Express feature issue, “In Vivo Microcirculation Imaging,” which includes 14 contributions from the biomedical optics community, covering such imaging techniques as optical coherence tomography, photoacoustic microscopy, laser Doppler /speckle imaging, and near infrared spectroscopy and fluorescence imaging.

  19. Hubble Space Telescope Imaging of Globular Cluster Candidates in Low Surface Brightness Dwarf Galaxies

    CERN Document Server

    Sharina, M E; Makarov, D I; Sharina, Margarita E.; Puzia, Thomas H.; Makarov, Dmitry I.

    2005-01-01

    Fifty-seven nearby low surface brightness dwarf galaxies were searched for globular cluster candidates (GCCs) using Hubble Space Telescope WFPC2 imaging in V and I. The sample consists of 18 dwarf spheroidal (dSph), 36 irregular (dIrr), and 3 "transition" type (dIrr/dSph) galaxies with angular sizes less than 3.7 kpc situated at distances 2-6 Mpc in the field and in the nearby groups: M81, Centaurus A, Sculptor, Canes Venatici I cloud. We find that ~50% of dSph, dIrr/dSph, and dIrr galaxies contain GCCs. The fraction of GCCs located near the center of dwarf spheroidal galaxies is >2 times higher than that for dIrrs. The mean integral color of GCCs in dSphs, V-I = 1.04+/-0.16 mag, coincides with the corresponding value for Galactic globular clusters and is similar to the blue globular cluster sub-populations in massive early-type galaxies. The color distribution for GCCs in dIrrs shows a clear bimodality with peaks near V-I = 0.5 and 1.0 mag. Blue GCCs are presumably young with ages t -6.5 mag in both dSph an...

  20. Remote Sensing Image Feature Extracting Based Multiple Ant Colonies Cooperation

    Directory of Open Access Journals (Sweden)

    Zhang Zhi-long

    2014-02-01

    Full Text Available This paper presents a novel feature extraction method for remote sensing imagery based on the cooperation of multiple ant colonies. First, multiresolution expression of the input remote sensing imagery is created, and two different ant colonies are spread on different resolution images. The ant colony in the low-resolution image uses phase congruency as the inspiration information, whereas that in the high-resolution image uses gradient magnitude. The two ant colonies cooperate to detect features in the image by sharing the same pheromone matrix. Finally, the image features are extracted on the basis of the pheromone matrix threshold. Because a substantial amount of information in the input image is used as inspiration information of the ant colonies, the proposed method shows higher intelligence and acquires more complete and meaningful image features than those of other simple edge detectors.

  1. Feature extraction of RGB-D images using joint spatial-depth feature pooling

    DEFF Research Database (Denmark)

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

    2016-01-01

    Recent development in depth imaging technology makes acquisition of depth information easier. With the additional depth cue, RGB-D cameras can provide effective support for many RGB-D perception tasks beyond traditional RGB information. However, current feature representation based on RGB-D images...... utilizes depth information only to extract local features, without considering it to improve robustness and discriminability of the feature representation by merging depth cues into feature pooling. Spatial pyramid model (SPM) has become the standard protocol to split a 2D image plane into sub...

  2. Feature representation of RGB-D images using joint spatial-depth feature pooling

    DEFF Research Database (Denmark)

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

    2016-01-01

    Recent development in depth imaging technology makes acquisition of depth information easier. With the additional depth cue, RGB-D cameras can provide effective support for many RGB-D perception tasks beyond traditional RGB information. However, current feature representation based on RGB-D images...... utilizes depth information only to extract local features, without considering it to improve robustness and discriminability of the feature representation by merging depth cues into feature pooling. Spatial pyramid model (SPM) has become the standard protocol to split a 2D image plane into sub...

  3. Digital Dental X-Ray Image Segmentation and Feature Extraction

    Directory of Open Access Journals (Sweden)

    Abdolvahab Ehsani Rad

    2013-06-01

    Full Text Available The process of analysis of such images is important in order to improve quantify medical imaging systems. It is significant to analysis the dental x-ray images we need features of image. In this paper we present a method for segmentation and feature extraction of dental x-ray images. The proposed method has been implemented by using level-set method for segmentation after image enhancement and illustrate contour for teeth to complete the segmentation step. Furthermore, we extracted multiple features of dental x-ray images using texture statistics techniques by gray-level co-occurrence matrix. Extracted data can perform to obtain the teeth measurements for automatic dental systems such human identification or dental diagnosis systems. Preparatory experiments show the significance of the proposed method to extract teeth from an x-ray image.

  4. Remote sensing image classification based on block feature point density analysis and multiple-feature fusion

    Science.gov (United States)

    Li, Shijin; Jiang, Yaping; Zhang, Yang; Feng, Jun

    2015-10-01

    With the development of remote sensing (RS) and the related technologies, the resolution of RS images is enhancing. Compared with moderate or low resolution images, high-resolution ones can provide more detailed ground information. However, a variety of terrain has complex spatial distribution. The different objectives of high-resolution images have a variety of features. The effectiveness of these features is not the same, but some of them are complementary. Considering the above information and characteristics, a new method is proposed to classify RS images based on hierarchical fusion of multi-features. Firstly, RS images are pre-classified into two categories in terms of whether feature points are uniformly or non-uniformly distributed. Then, the color histogram and Gabor texture feature are extracted from the uniformly-distributed categories, and the linear spatial pyramid matching using sparse coding (ScSPM) feature is obtained from the non-uniformly-distributed categories. Finally, the classification is performed by two support vector machine classifiers. The experimental results on a large RS image database with 2100 images show that the overall classification accuracy is boosted by 10.1% in comparison with the highest accuracy of single feature classification method. Compared with other multiple-feature fusion methods, the proposed method has achieved the highest classification accuracy on this dataset which has reached 90.1%, and the time complexity of the algorithm is also greatly reduced.

  5. Prototype Theory Based Feature Representation for PolSAR Images

    OpenAIRE

    Huang Xiaojing; Yang Xiangli; Huang Pingping; Yang Wen

    2016-01-01

    This study presents a new feature representation approach for Polarimetric Synthetic Aperture Radar (PolSAR) image based on prototype theory. First, multiple prototype sets are generated using prototype theory. Then, regularized logistic regression is used to predict similarities between a test sample and each prototype set. Finally, the PolSAR image feature representation is obtained by ensemble projection. Experimental results of an unsupervised classification of PolSAR images show that our...

  6. Identification of Image Operations Based on Steganalytic Features

    OpenAIRE

    Li, Haodong; Luo, Weiqi; Qiu, Xiaoqing; Huang, Jiwu

    2015-01-01

    Image forensics have attracted wide attention during the past decade. Though many forensic methods have been proposed to identify image forgeries, most of them are targeted ones, since their proposed features are highly dependent on the image operation under investigation. The performance of the well-designed features for detecting the targeted operation usually degrades significantly for other operations. On the other hand, a wise attacker can perform anti-forensics to fool the existing fore...

  7. Segmentation-Based PolSAR Image Classification Using Visual Features: RHLBP and Color Features

    Directory of Open Access Journals (Sweden)

    Jian Cheng

    2015-05-01

    Full Text Available A segmentation-based fully-polarimetric synthetic aperture radar (PolSAR image classification method that incorporates texture features and color features is designed and implemented. This method is based on the framework that conjunctively uses statistical region merging (SRM for segmentation and support vector machine (SVM for classification. In the segmentation step, we propose an improved local binary pattern (LBP operator named the regional homogeneity local binary pattern (RHLBP to guarantee the regional homogeneity in PolSAR images. In the classification step, the color features extracted from false color images are applied to improve the classification accuracy. The RHLBP operator and color features can provide discriminative information to separate those pixels and regions with similar polarimetric features, which are from different classes. Extensive experimental comparison results with conventional methods on L-band PolSAR data demonstrate the effectiveness of our proposed method for PolSAR image classification.

  8. Featured Image: The Milky Way's X

    Science.gov (United States)

    Kohler, Susanna

    2016-09-01

    The X-shaped bulge is even more evident in this image, wherein a simple exponential disk model has been subtracted off. [Adapted from Ness Lang 2016]This contrast-enhanced image of the Milky Way, observed by the Wide-Field Infrared Survey Explorer (WISE), clearly reveals that the bulge of stars at the center of our galaxy is shaped like a large X. The boxy nature of the Milky Ways bulge was revealed by satellite image in 1995, but in recent years, star counts along the line of sight toward the bulge have suggested that the bulge may be X-shaped. It was unclear whether this apparent morphology was due to the difference in the distributions of different stellar populations, or if the actual physical structure of the bulge was X-shaped. But these new WISE images, produced by astronomers Melissa Ness (Max Planck Institute for Astronomy) and Dustin Lang (University of Toronto and University of Waterloo), now provide firm evidence that the Milky Ways bulge actually is X-shaped, supplying clues as to how our galaxys center may have formed. This morphology is not uncommon; observations of other barred galaxies reveal similar X-shaped profiles. To learn more, check out the paper below!CitationMelissa Ness and Dustin Lang 2016 AJ 152 14. doi:10.3847/0004-6256/152/1/14

  9. Automated Recognition of 3D Features in GPIR Images

    Science.gov (United States)

    Park, Han; Stough, Timothy; Fijany, Amir

    2007-01-01

    A method of automated recognition of three-dimensional (3D) features in images generated by ground-penetrating imaging radar (GPIR) is undergoing development. GPIR 3D images can be analyzed to detect and identify such subsurface features as pipes and other utility conduits. Until now, much of the analysis of GPIR images has been performed manually by expert operators who must visually identify and track each feature. The present method is intended to satisfy a need for more efficient and accurate analysis by means of algorithms that can automatically identify and track subsurface features, with minimal supervision by human operators. In this method, data from multiple sources (for example, data on different features extracted by different algorithms) are fused together for identifying subsurface objects. The algorithms of this method can be classified in several different ways. In one classification, the algorithms fall into three classes: (1) image-processing algorithms, (2) feature- extraction algorithms, and (3) a multiaxis data-fusion/pattern-recognition algorithm that includes a combination of machine-learning, pattern-recognition, and object-linking algorithms. The image-processing class includes preprocessing algorithms for reducing noise and enhancing target features for pattern recognition. The feature-extraction algorithms operate on preprocessed data to extract such specific features in images as two-dimensional (2D) slices of a pipe. Then the multiaxis data-fusion/ pattern-recognition algorithm identifies, classifies, and reconstructs 3D objects from the extracted features. In this process, multiple 2D features extracted by use of different algorithms and representing views along different directions are used to identify and reconstruct 3D objects. In object linking, which is an essential part of this process, features identified in successive 2D slices and located within a threshold radius of identical features in adjacent slices are linked in a

  10. Image counter-forensics based on feature injection

    Science.gov (United States)

    Iuliani, M.; Rossetto, S.; Bianchi, T.; De Rosa, Alessia; Piva, A.; Barni, M.

    2014-02-01

    Starting from the concept that many image forensic tools are based on the detection of some features revealing a particular aspect of the history of an image, in this work we model the counter-forensic attack as the injection of a specific fake feature pointing to the same history of an authentic reference image. We propose a general attack strategy that does not rely on a specific detector structure. Given a source image x and a target image y, the adversary processes x in the pixel domain producing an attacked image ~x, perceptually similar to x, whose feature f(~x) is as close as possible to f(y) computed on y. Our proposed counter-forensic attack consists in the constrained minimization of the feature distance Φ(z) =│ f(z) - f(y)│ through iterative methods based on gradient descent. To solve the intrinsic limit due to the numerical estimation of the gradient on large images, we propose the application of a feature decomposition process, that allows the problem to be reduced into many subproblems on the blocks the image is partitioned into. The proposed strategy has been tested by attacking three different features and its performance has been compared to state-of-the-art counter-forensic methods.

  11. Model Based Analysis of Face Images for Facial Feature Extraction

    Science.gov (United States)

    Riaz, Zahid; Mayer, Christoph; Beetz, Michael; Radig, Bernd

    This paper describes a comprehensive approach to extract a common feature set from the image sequences. We use simple features which are easily extracted from a 3D wireframe model and efficiently used for different applications on a benchmark database. Features verstality is experimented on facial expressions recognition, face reognition and gender classification. We experiment different combinations of the features and find reasonable results with a combined features approach which contain structural, textural and temporal variations. The idea follows in fitting a model to human face images and extracting shape and texture information. We parametrize these extracted information from the image sequences using active appearance model (AAM) approach. We further compute temporal parameters using optical flow to consider local feature variations. Finally we combine these parameters to form a feature vector for all the images in our database. These features are then experimented with binary decision tree (BDT) and Bayesian Network (BN) for classification. We evaluated our results on image sequences of Cohn Kanade Facial Expression Database (CKFED). The proposed system produced very promising recognition rates for our applications with same set of features and classifiers. The system is also realtime capable and automatic.

  12. Image Representation Using EPANECHNIKOV Density Feature Points Estimator

    Directory of Open Access Journals (Sweden)

    Tranos Zuva

    2013-02-01

    Full Text Available In image retrieval most of the existing visual content based representation methods are usually application dependent or non robust, making them not suitable for generic applications. These representation methods use visual contents such as colour, texture, shape, size etc. Human image recognition is largely based on shape, thus making it very appealing for image repr esentation algorithms in computer vision. In this paper we propose a generic image representation algorithm using Epanechnikov Density Feature Points Estimator (EDFPE. It is invariant to rotation, scale and translation. The image density feature points within defined rectangular rings around the gravitational centre of the image are obtained in the form of a vector. The EDFPE is applied to the vecto r representation of the image. The Cosine Angle Distance (CAD algorithm is used to measure similarity of the images in the database. Quantitative evaluation of the performance of the system and comparison with other algorithms was done.

  13. Imaging in osteomyelitis: Special features in childhood

    International Nuclear Information System (INIS)

    The prognosis of acute hematogenous osteomyelitis in children ist mainly influenced by early diagnosis and prompt initiation of antibiotic and surgical therapy. In this age group, two forms of manifestation are differentiated: Osteomyelitis in infants up to 18 months and juvenile osteomyelitis until the closure of the epiphyseal plate. Osteomyelitis in infants is often accompanied by septic arthritis of the adjacent joint. In juvenile osteomyelitis, the disease is mostly confined to the metaphysis. Plain films and ultrasonography represent the basic imaging modalities. Depending on the age of the child, the clinical course of the disease and the availability of the various methods, MRI and multiphase bone scintigraphy can be performed for further imaging. CT is of only limited value and should only be used for special cases concerning chronic osteomyelitis. (orig.)

  14. Supratentorial cystic intracranial lesions: MR imaging features

    Energy Technology Data Exchange (ETDEWEB)

    Kim, Young Joo; Son, Young Bo; Choi, Kyu Ho; Chun, Kyung Ah; Kim, Sung Hoon; Park, Seog Hee; Shinn, Kyung Sub [The Catholic University of Korea College of Medicine, Seoul (Korea, Republic of)

    1997-01-01

    To describe MR findings and differential points of supratentorial cystic intracranial lesions. We retrospectively reviewed and analyzed the MR findings of 59 patients with supratentorial cystic intracranial lesions, and classified them as follows : tumor-associated cyst, infectious cyst, ex-vacuo type cyst, and congentital/developmental cyst. Among 59 patients, 47 tumor-associated cysts were seen in 17, 42 infectious cysts in 13, 17 ex-vacuo type cysts in 10, and 19 congenital/developmental cysts in 19. In 44 of 47 tumor-associate cysts, increased or inhomogeneous internal signal intensity was seen on T1-weighted image, 37 of 47 showed thick uneven walls ; 37 of 47 had enhancing solid components and there was variable perifocal edema and mass effect. Infectious cysts were multiple (11 of 13). In cases of brain abscess, increased internal signal intensity on T1-weighted image, low signal intensity of abscess wall on T2-weighted image, thick even enhancing wall, and marked perifocal edema (4 of 4) were seen in all four cases. Cysts in cysticercosis were variable in appearance depending on the stage, but were smaller than other cystic lesions. Ex vacuo type cysts were of uniform CSF signal intensity in all pulse sequences and there was no identifiable wall or enhancement associated with enlarged adjacent ventricle and encephalomalacia (17 of 17). Congenital/developmental cysts showed a single lesion (19 of 19), a signal intensity similar to CSF in all pulse sequences (15 of 19), no identifiable wall (16 of 19), no enhancement (17 of 19), and no perifocal edema (19 of 19). MR was used to categorize supratentorial cystic intracranial lesions into four groups on the basis of their number, size, internal homogeneity of signal intensity on T1-weighted image, enhancing pattern, perifocal edema and mass effect, thereby improving diagnostic specificity and patient management.

  15. Robust Image Hashing Using Radon Transform and Invariant Features

    Directory of Open Access Journals (Sweden)

    Y.L. Liu

    2016-09-01

    Full Text Available A robust image hashing method based on radon transform and invariant features is proposed for image authentication, image retrieval, and image detection. Specifically, an input image is firstly converted into a counterpart with a normalized size. Then the invariant centroid algorithm is applied to obtain the invariant feature point and the surrounding circular area, and the radon transform is employed to acquire the mapping coefficient matrix of the area. Finally, the hashing sequence is generated by combining the feature vectors and the invariant moments calculated from the coefficient matrix. Experimental results show that this method not only can resist against the normal image processing operations, but also some geometric distortions. Comparisons of receiver operating characteristic (ROC curve indicate that the proposed method outperforms some existing methods in classification between perceptual robustness and discrimination.

  16. Registration of Standardized Histological Images in Feature Space

    CERN Document Server

    Bagci, Ulas; 10.1117/12.770219

    2009-01-01

    In this paper, we propose three novel and important methods for the registration of histological images for 3D reconstruction. First, possible intensity variations and nonstandardness in images are corrected by an intensity standardization process which maps the image scale into a standard scale where the similar intensities correspond to similar tissues meaning. Second, 2D histological images are mapped into a feature space where continuous variables are used as high confidence image features for accurate registration. Third, we propose an automatic best reference slice selection algorithm that improves reconstruction quality based on both image entropy and mean square error of the registration process. We demonstrate that the choice of reference slice has a significant impact on registration error, standardization, feature space and entropy information. After 2D histological slices are registered through an affine transformation with respect to an automatically chosen reference, the 3D volume is reconstruct...

  17. Diffuse pancreatic ductal adenocarcinoma: Characteristic imaging features

    International Nuclear Information System (INIS)

    Purpose: To evaluate imaging findings of diffuse pancreatic ductal adenocarcinoma. Materials and methods: We included 14 patients (4 men and 10 women; mean age, 64.5 years) with diffuse pancreatic ductal adenocarcinoma on the basis of retrospective radiological review. Two radiologists retrospectively reviewed 14 CT scans in consensus with respect to the following: tumor site, peripheral capsule-like structure, dilatation of intratumoral pancreatic duct, parenchymal atrophy, and ancillary findings. Eight magnetic resonance (MR) examinations with MR cholangiopancreatography (MRCP) and seven endoscopic retrograde cholangiopancreatography (ERCP) were also reviewed, focusing on peripheral capsule-like structure and dilatation of intratumoral pancreatic duct. Results: CT revealed tumor localization to the body and tail in 11 (79%) patients and peripheral capsule-like structure in 13 (93%). The intratumoral pancreatic duct was not visible in 13 (93%). Pancreatic parenchymal atrophy was not present in all 14 patients. Tumor invasion of vessels was observed in all 14 patients and of neighbor organs in 8 (57%). On contrast-enhanced T1-weighted MR images, peripheral capsule-like structure showed higher signal intensity in five patients (71%). In all 11 patients with MRCP and/or ERCP, the intratumoral pancreatic duct was not dilated. Conclusion: Diffuse pancreatic ductal adenocarcinoma has characteristic imaging findings, including peripheral capsule-like structure, local invasiveness, and absence of both dilatation of intratumoral pancreatic duct and parenchymal atrophy

  18. Simple Low Level Features for Image Analysis

    Science.gov (United States)

    Falcoz, Paolo

    As human beings, we perceive the world around us mainly through our eyes, and give what we see the status of “reality”; as such we historically tried to create ways of recording this reality so we could augment or extend our memory. From early attempts in photography like the image produced in 1826 by the French inventor Nicéphore Niépce (Figure 2.1) to the latest high definition camcorders, the number of recorded pieces of reality increased exponentially, posing the problem of managing all that information. Most of the raw video material produced today has lost its memory augmentation function, as it will hardly ever be viewed by any human; pervasive CCTVs are an example. They generate an enormous amount of data each day, but there is not enough “human processing power” to view them. Therefore the need for effective automatic image analysis tools is great, and a lot effort has been put in it, both from the academia and the industry. In this chapter, a review of some of the most important image analysis tools are presented.

  19. Adaptive enhancement method of infrared image based on scene feature

    Science.gov (United States)

    Zhang, Xiao; Bai, Tingzhu; Shang, Fei

    2008-12-01

    All objects emit radiation in amounts related to their temperature and their ability to emit radiation. The infrared image shows the invisible infrared radiation emitted directly. Because of the advantages, the technology of infrared imaging is applied to many kinds of fields. But compared with visible image, the disadvantages of infrared image are obvious. The characteristics of low luminance, low contrast and the inconspicuous difference target and background are the main disadvantages of infrared image. The aim of infrared image enhancement is to improve the interpretability or perception of information in infrared image for human viewers, or to provide 'better' input for other automated image processing techniques. Most of the adaptive algorithm for image enhancement is mainly based on the gray-scale distribution of infrared image, and is not associated with the actual image scene of the features. So the pertinence of infrared image enhancement is not strong, and the infrared image is not conducive to the application of infrared surveillance. In this paper we have developed a scene feature-based algorithm to enhance the contrast of infrared image adaptively. At first, after analyzing the scene feature of different infrared image, we have chosen the feasible parameters to describe the infrared image. In the second place, we have constructed the new histogram distributing base on the chosen parameters by using Gaussian function. In the last place, the infrared image is enhanced by constructing a new form of histogram. Experimental results show that the algorithm has better performance than other methods mentioned in this paper for infrared scene images.

  20. Object Detection Combining Brightness Feature Autocorrelation and Gaussian Mixture Models%亮度特征自相关和GMM相结合的目标检测

    Institute of Scientific and Technical Information of China (English)

    王思明; 赵伟

    2014-01-01

    The background modeling algorithm based on Gaussian Mixture Models(GMM) is used widely in moving objects detection, but it can not accurately detect moving objects in some video sequences that have rapid changes of light. Moreover, in the initialization of GMM parameters, the result of object detection contains the moving objects of the initialization image and leads to error detection if the initialization image has moving objects. In allusion to the problems mentioned above, a GMM algorithm based on the intensity feature autocorrelation is proposed. The brightness feature autocorrelation parameters are used to identify whether there is a moving object in the initialization image, the fit value of intensity feature autocorrelation parameters is used to identify that there is a fast illumination variation or not in the current frame, and the object detection is made by using the ideas of GMM and intensity difference. The video taken actually is simulated by using the proposed algorithm that is of high accuracy and of high real-time, and results show that a moving object is extracted well from video sequences that have rapid changes of light under the disturbed condition that the initialization image of GMM has moving objects.%基于混合高斯模型(GMM)的背景建模算法被广泛运用于运动目标检测,但在一些发生快速光照变化的视频序列中,不能正确地检测出运动目标。此外在对 GMM 参数进行初始化时,若初始化图像中存在运动目标,则目标检测的结果会出现初始化图像中的运动目标,从而导致误检测。针对上述问题,提出一种基于亮度特征自相关的 GMM 算法,该算法根据亮度特征自相关参数判断初始化图像中是否存在运动目标,利用亮度特征自相关参数的拟合值判断当前帧是否发生快速光照变化,运用 GMM 和亮度差值相结合进行目标检测。对实际摄取的视频进行仿真实验

  1. Neonatal nasopharyngeal teratomas: cross sectional imaging features

    Energy Technology Data Exchange (ETDEWEB)

    Andronikou, S. [Radiology Dept., Royal Children' s Hospital, Parkville, Melbourne (Australia); Dept. of Radiology, Royal Children' s Hospital, Univ. of Cape Town, Rondebosch (South Africa); Kumbla, S.; Fink, A.M. [Radiology Dept., Royal Children' s Hospital, Parkville, Melbourne (Australia)

    2003-04-01

    Background: Neonatal nasopharyngeal teratomas are extremely rare and there are few reports describing both CT and MRI features of these lesions. Objective: To describe the CT and MRI appearances of neonatal nasopharyngeal teratoma. Materials and methods: Three neonates with nasopharyngeal teratomas and severe respiratory distress were reviewed. Results: The nasopharyngeal mass resulted in severe respiratory compromise requiring urgent intervention. Characteristic mandibular and pterygoid plate abnormalities demonstrated by CT and MRI are described. Conclusions: Prenatal MRI enables the diagnosis, delineates tumour extent and allows planned delivery. CT and MRI play a key role in differentiating neonatal nasopharyngeal teratomas from other causes of a neonatal neck mass, thus optimising management. (orig.)

  2. Performance Analysis of Texture Image Classification Using Wavelet Feature

    Directory of Open Access Journals (Sweden)

    Dolly Choudhary

    2013-01-01

    Full Text Available This paper compares the performance of various classifiers for multi class image classification. Where the features are extracted by the proposed algorithm in using Haar wavelet coefficient. The wavelet features are extracted from original texture images and corresponding complementary images. As it is really very difficult to decide which classifier would show better performance for multi class image classification. Hence, this work is an analytical study of performance of various classifiers for the single multiclass classification problem. In this work fifteen textures are taken for classification using Feed Forward Neural Network, Naïve Bays Classifier, K-nearest neighbor Classifier and Cascaded Neural Network.

  3. Maize Seed Variety Classification Using the Integration of Spectral and Image Features Combined with Feature Transformation Based on Hyperspectral Imaging

    Directory of Open Access Journals (Sweden)

    Min Huang

    2016-06-01

    Full Text Available Hyperspectral imaging (HSI technology has been extensively studied in the classification of seed variety. A novel procedure for the classification of maize seed varieties based on HSI was proposed in this study. The optimal wavelengths for the classification of maize seed varieties were selected using the successive projections algorithm (SPA to improve the acquiring and processing speed of HSI. Subsequently, spectral and imaging features were extracted from regions of interest of the hyperspectral images. Principle component analysis and multidimensional scaling were then introduced to transform/reduce the classification features for overcoming the risk of dimension disaster caused by the use of a large number of features. Finally, the integrating features were used to develop a least squares–support vector machines (LS–SVM model. The LS–SVM model, using the integration of spectral and image features combined with feature transformation methods, achieved more than 90% of test accuracy, which was better than the 83.68% obtained by model using the original spectral and image features, and much higher than the 76.18% obtained by the model only using the spectral features. This procedure provides a possible way to apply the multispectral imaging system to classify seed varieties with high accuracy.

  4. THE IDENTIFICATION OF PILL USING FEATURE EXTRACTION IN IMAGE MINING

    Directory of Open Access Journals (Sweden)

    A. Hema

    2015-02-01

    Full Text Available With the help of image mining techniques, an automatic pill identification system was investigated in this study for matching the images of the pills based on its several features like imprint, color, size and shape. Image mining is an inter-disciplinary task requiring expertise from various fields such as computer vision, image retrieval, image matching and pattern recognition. Image mining is the method in which the unusual patterns are detected so that both hidden and useful data images can only be stored in large database. It involves two different approaches for image matching. This research presents a drug identification, registration, detection and matching, Text, color and shape extraction of the image with image mining concept to identify the legal and illegal pills with more accuracy. Initially, the preprocessing process is carried out using novel interpolation algorithm. The main aim of this interpolation algorithm is to reduce the artifacts, blurring and jagged edges introduced during up-sampling. Then the registration process is proposed with two modules they are, feature extraction and corner detection. In feature extraction the noisy high frequency edges are discarded and relevant high frequency edges are selected. The corner detection approach detects the high frequency pixels in the intersection points. Through the overall performance gets improved. There is a need of segregate the dataset into groups based on the query image’s size, shape, color, text, etc. That process of segregating required information is called as feature extraction. The feature extraction is done using Geometrical Gradient feature transformation. Finally, color and shape feature extraction were performed using color histogram and geometrical gradient vector. Simulation results shows that the proposed techniques provide accurate retrieval results both in terms of time and accuracy when compared to conventional approaches.

  5. Featured Image: A Bubble Triggering Star Formation

    Science.gov (United States)

    Kohler, Susanna

    2016-05-01

    This remarkable false-color, mid-infrared image (click for the full view!) was produced by the Wide-field Infrared Survey Explorer (WISE). It captures a tantalizing view of Sh 2-207 and Sh 2-208, the latter of which is one of the lowest-metallicity star-forming regions in the Galaxy. In a recent study led by Chikako Yasui (University of Tokyo and the Koyama Astronomical Observatory), a team of scientists has examined this region to better understand how star formation in low-metallicity environments differs from that in the solar neighborhood. The authors analysis suggests that sequential star formation is taking place in these low-metallicity regions, triggered by an expanding bubble (the large dashed oval indicated in the image) with a ~30 pc radius. You can find out more about their study by checking out the paper below!CitationChikako Yasui et al 2016 AJ 151 115. doi:10.3847/0004-6256/151/5/115

  6. Magnetic resonance imaging of hypothalamus hypophysis axis lesions; Relationship between posterior pituitary function and posterior bright spot

    Energy Technology Data Exchange (ETDEWEB)

    Shiina, Takeki; Uno, Kimiichi; Arimizu, Noboru; Yoshida, Sho (Chiba Univ. (Japan). School of Medicine); Yamada, Kenichi

    1990-04-01

    Magnetic resonance imaging (MRI) using a 0.5T superconductive machine was performed to the thirty three cases with a variety of the sellar and parasellar tumors and with dysfunction of the hypothalamus-hypophysis axis. Posterior pituitary bright spot (PBS) on T1 weighted image was evaluated with the pituitary hormonal function. These cases were 12 cases of post-treated tumors including pituitary adenoma (9 patients), suprasellar germinoma (2 patients) and craniopharyngioma (one patient), and non-tumorous conditions including 15 cases of central diabetes insipidus (DI), Syndrome of inappropriate secretion of ADH (SIADH) (one patient), Sheehan's syndrome (3 patients) and anorexia nervosa (2 patients). Pituitary bright spot was not seen in all 19 cases with overt DI. On the other hand, PBS was not seen in 9 cases without overt DI. Three cases of these 9 cases showing Sheehan's syndrome with insufficient antidiuretic hormone (ADH) secretion was considered as the state of subclinical DI. Posterior bright spot was not seen in all 13 cases of empty sella including partial empty sella. The results suggested that disappearance of PBS represents abnormality or loss of posterior pituitary function and also it was considered to be closely related to the empty sella. (author).

  7. Texture features from Chaos Game Representation Images of Genomes

    Directory of Open Access Journals (Sweden)

    Vrinda V. Nair

    2013-04-01

    Full Text Available The proposed work investigates the effectiveness of coarse measures of the Chaos Game Representation (CGR images in differentiating genomes of various organisms. Major work in this area is seen to focus on feature extraction using Frequency Chaos Game Representation (FCGR matrices. Although it is biologically significant, FCGR matrix has an inherent error which is associated with the insufficient computing as well as the screen resolutions. Hence the CGR image is converted to a texture image and corresponding feature vectors extracted. Features such as the texture properties and the subsequent wavelet coefficients of the texture image are used. Our work suggests that texture features characterize genomes well further; their wavelet coefficients yield better distinguishing capabilities.

  8. An adaptive multi-feature segmentation model for infrared image

    Science.gov (United States)

    Zhang, Tingting; Han, Jin; Zhang, Yi; Bai, Lianfa

    2016-04-01

    Active contour models (ACM) have been extensively applied to image segmentation, conventional region-based active contour models only utilize global or local single feature information to minimize the energy functional to drive the contour evolution. Considering the limitations of original ACMs, an adaptive multi-feature segmentation model is proposed to handle infrared images with blurred boundaries and low contrast. In the proposed model, several essential local statistic features are introduced to construct a multi-feature signed pressure function (MFSPF). In addition, we draw upon the adaptive weight coefficient to modify the level set formulation, which is formed by integrating MFSPF with local statistic features and signed pressure function with global information. Experimental results demonstrate that the proposed method can make up for the inadequacy of the original method and get desirable results in segmenting infrared images.

  9. Features Selection for Skin Micro-Image Symptomatic Recognition

    Institute of Scientific and Technical Information of China (English)

    HUYue-li; CAOJia-lin; ZHAOQian; FENGXu

    2004-01-01

    Automatic recognition of skin micro-image symptom is important in skin diagnosis and treatment. Feature selection is to improve the classification performance of skin micro-image symptom.This paper proposes a hybrid approach based on the support vector machine (SVM) technique and genetic algorithm (GA) to select an optimum feature subset from the feature group extracted from the skin micro-images. An adaptive GA is introduced for maintaining the convergence rate. With the proposed method, the average cross validation accuracy is increased from 88.25% using all features to 96.92% using only selected features provided by a classifier for classification of 5 classes of skin symptoms. The experimental results are satisfactory.

  10. Features Selection for Skin Micro-Image Symptomatic Recognition

    Institute of Scientific and Technical Information of China (English)

    HU Yue-li; CAO Jia-lin; ZHAO Qian; FENG Xu

    2004-01-01

    Automatic recognition of skin micro-image symptom is important in skin diagnosis and treatment. Feature selection is to improve the classification performance of skin micro-image symptom.This paper proposes a hybrid approach based on the support vector machine (SVM) technique and genetic algorithm (GA) to select an optimum feature subset from the feature group extracted from the skin micro-images. An adaptive GA is introduced for maintaining the convergence rate. With the proposed method, the average cross validation accuracy is increased from 88.25% using all features to 96.92 % using only selected features provided by a classifier for classification of 5 classes of skin symptoms. The experimental results are satisfactory.

  11. Featured Image: Star Clusters in M51

    Science.gov (United States)

    Kohler, Susanna

    2016-06-01

    This beautiful mosaic of images of the Whirlpool galaxy (M51) and its companion was taken with the Advanced Camera for Surveys on the Hubble Space Telescope. This nearby, grand-design spiral galaxy has a rich population of star clusters, making it both a stunning target for imagery and an excellent resource for learning about stellar formation and evolution. In a recent study, Rupali Chandar (University of Toledo) and collaborators cataloged over 3,800 compact star clusters within this galaxy. They then used this catalog to determine the distributions for the clusters ages, masses, and sizes, which can provide important clues as to how star clusters form, evolve, and are eventually disrupted. You can read more about their study and what they discovered in the paper below.CitationRupali Chandar et al 2016 ApJ 824 71. doi:10.3847/0004-637X/824/2/71

  12. Image Retrieval Using a Combination of Keywords and Image Features

    OpenAIRE

    Reddy, Vishwanath Reddy Keshi; Bandikolla, Praveen

    2008-01-01

    Information retrieval systems are playing an important role in our day to day life for getting the required information. Many text retrieval systems are available and are working successfully. Even though internet is full of other media like images, audio and video, retrieval systems for these media are rare and have not achieved success as that of text retrieval systems. Image retrieval systems are useful in many applications; there is a high demand for effective and efficient tool for image...

  13. Assist features: placement, impact, and relevance for EUV imaging

    Science.gov (United States)

    Mochi, Iacopo; Philipsen, Vicky; Gallagher, Emily; Hendrickx, Eric; Lyakhova, Kateryna; Wittebrood, Friso; Schiffelers, Guido; Fliervoet, Timon; Wang, Shibing; Hsu, Stephen; Plachecki, Vince; Baron, Stan; Laenens, Bart

    2016-03-01

    Assist features are commonly used in DUV lithography to improve the lithographic process window of isolated features under illumination conditions that enable the printability of dense features. With the introduction of EUV lithography, the interaction between 13.5 nm light and the mask features generates strong mask 3D effects. On wafer, the mask 3D effects manifest as pitch-dependent best focus positions, pattern asymmetries and image contrast loss. To minimize the mask 3D effects, and enhance the lithographic process window, we explore by means of wafer print evaluation the use of assist features with different sizes and placements. The assist features are placed next to isolated features and two bar structures, consistent with theN5 (imec iN7) node dimensions for 0.33NA and we use different types of off-axis illumination . For the generic iN7 structures, wafer imaging will be compared to simulation results and an assessment of optimal assist feature configuration will be made. It is also essential to understand the potential benefit of using assist features and to weigh that benefit against the price of complexity associated with adding sub-resolution features on a production mask. To that end, we include an OPC study that compares a layout treated with assist features, to one without assist features, using full-chip complexity metrics like data size.

  14. Image mosaic method based on SIFT features of line segment.

    Science.gov (United States)

    Zhu, Jun; Ren, Mingwu

    2014-01-01

    This paper proposes a novel image mosaic method based on SIFT (Scale Invariant Feature Transform) feature of line segment, aiming to resolve incident scaling, rotation, changes in lighting condition, and so on between two images in the panoramic image mosaic process. This method firstly uses Harris corner detection operator to detect key points. Secondly, it constructs directed line segments, describes them with SIFT feature, and matches those directed segments to acquire rough point matching. Finally, Ransac method is used to eliminate wrong pairs in order to accomplish image mosaic. The results from experiment based on four pairs of images show that our method has strong robustness for resolution, lighting, rotation, and scaling. PMID:24511326

  15. Image Mosaic Method Based on SIFT Features of Line Segment

    Directory of Open Access Journals (Sweden)

    Jun Zhu

    2014-01-01

    Full Text Available This paper proposes a novel image mosaic method based on SIFT (Scale Invariant Feature Transform feature of line segment, aiming to resolve incident scaling, rotation, changes in lighting condition, and so on between two images in the panoramic image mosaic process. This method firstly uses Harris corner detection operator to detect key points. Secondly, it constructs directed line segments, describes them with SIFT feature, and matches those directed segments to acquire rough point matching. Finally, Ransac method is used to eliminate wrong pairs in order to accomplish image mosaic. The results from experiment based on four pairs of images show that our method has strong robustness for resolution, lighting, rotation, and scaling.

  16. Breast image feature learning with adaptive deconvolutional networks

    Science.gov (United States)

    Jamieson, Andrew R.; Drukker, Karen; Giger, Maryellen L.

    2012-03-01

    Feature extraction is a critical component of medical image analysis. Many computer-aided diagnosis approaches employ hand-designed, heuristic lesion extracted features. An alternative approach is to learn features directly from images. In this preliminary study, we explored the use of Adaptive Deconvolutional Networks (ADN) for learning high-level features in diagnostic breast mass lesion images with potential application to computer-aided diagnosis (CADx) and content-based image retrieval (CBIR). ADNs (Zeiler, et. al., 2011), are recently-proposed unsupervised, generative hierarchical models that decompose images via convolution sparse coding and max pooling. We trained the ADNs to learn multiple layers of representation for two breast image data sets on two different modalities (739 full field digital mammography (FFDM) and 2393 ultrasound images). Feature map calculations were accelerated by use of GPUs. Following Zeiler et. al., we applied the Spatial Pyramid Matching (SPM) kernel (Lazebnik, et. al., 2006) on the inferred feature maps and combined this with a linear support vector machine (SVM) classifier for the task of binary classification between cancer and non-cancer breast mass lesions. Non-linear, local structure preserving dimension reduction, Elastic Embedding (Carreira-Perpiñán, 2010), was then used to visualize the SPM kernel output in 2D and qualitatively inspect image relationships learned. Performance was found to be competitive with current CADx schemes that use human-designed features, e.g., achieving a 0.632+ bootstrap AUC (by case) of 0.83 [0.78, 0.89] for an ultrasound image set (1125 cases).

  17. Retinal image registration via feature-guided Gaussian mixture model.

    Science.gov (United States)

    Liu, Chengyin; Ma, Jiayi; Ma, Yong; Huang, Jun

    2016-07-01

    Registration of retinal images taken at different times, from different perspectives, or with different modalities is a critical prerequisite for the diagnoses and treatments of various eye diseases. This problem can be formulated as registration of two sets of sparse feature points extracted from the given images, and it is typically solved by first creating a set of putative correspondences and then removing the false matches as well as estimating the spatial transformation between the image pairs or solved by estimating the correspondence and transformation jointly involving an iteration process. However, the former strategy suffers from missing true correspondences, and the latter strategy does not make full use of local appearance information, which may be problematic for low-quality retinal images due to a lack of reliable features. In this paper, we propose a feature-guided Gaussian mixture model (GMM) to address these issues. We formulate point registration as the estimation of a feature-guided mixture of densities: A GMM is fitted to one point set, such that both the centers and local features of the Gaussian densities are constrained to coincide with the other point set. The problem is solved under a unified maximum-likelihood framework together with an iterative expectation-maximization algorithm initialized by the confident feature correspondences, where the image transformation is modeled by an affine function. Extensive experiments on various retinal images show the robustness of our approach, which consistently outperforms other state-of-the-art methods, especially when the data is badly degraded. PMID:27409682

  18. Morphological Feature Extraction for Automatic Registration of Multispectral Images

    Science.gov (United States)

    Plaza, Antonio; LeMoigne, Jacqueline; Netanyahu, Nathan S.

    2007-01-01

    The task of image registration can be divided into two major components, i.e., the extraction of control points or features from images, and the search among the extracted features for the matching pairs that represent the same feature in the images to be matched. Manual extraction of control features can be subjective and extremely time consuming, and often results in few usable points. On the other hand, automated feature extraction allows using invariant target features such as edges, corners, and line intersections as relevant landmarks for registration purposes. In this paper, we present an extension of a recently developed morphological approach for automatic extraction of landmark chips and corresponding windows in a fully unsupervised manner for the registration of multispectral images. Once a set of chip-window pairs is obtained, a (hierarchical) robust feature matching procedure, based on a multiresolution overcomplete wavelet decomposition scheme, is used for registration purposes. The proposed method is validated on a pair of remotely sensed scenes acquired by the Advanced Land Imager (ALI) multispectral instrument and the Hyperion hyperspectral instrument aboard NASA's Earth Observing-1 satellite.

  19. Featured Image: Mapping Jupiter with Hubble

    Science.gov (United States)

    Kohler, Susanna

    2016-07-01

    Zonal wind profile for Jupiter, describing the speed and direction of its winds at each latitude. [Simon et al. 2015]This global map of Jupiters surface (click for the full view!) was generated by the Hubble Outer Planet Atmospheres Legacy (OPAL) program, which aims to createnew yearly global maps for each of the outer planets. Presented in a study led by Amy Simon (NASA Goddard Space Flight Center), the map above is the first generated for Jupiter in the first year of the OPAL campaign. It provides a detailed look at Jupiters atmospheric structure including the Great Red Spot and allowed the authors to measure the speed and direction of the wind across Jupiters latitudes, constructing an updated zonal wind profile for Jupiter.In contrast to this study, the Juno mission (which will be captured into Jupiters orbit today after a 5-year journey to Jupiter!) will be focusing more on the features below Jupiters surface, studying its deep atmosphere and winds. Some of Junos primary goals are to learn about Jupiters composition, gravitational field, magnetic field, and polar magnetosphere. You can follow along with the NASATV livestream as Juno arrives at Jupiter tonight; orbit insertion coverage starts at 10:30 EDT.CitationAmy A. Simon et al 2015 ApJ 812 55. doi:10.1088/0004-637X/812/1/55

  20. Learning Hierarchical Spectral-Spatial Features for Hyperspectral Image Classification.

    Science.gov (United States)

    Zhou, Yicong; Wei, Yantao

    2016-07-01

    This paper proposes a spectral-spatial feature learning (SSFL) method to obtain robust features of hyperspectral images (HSIs). It combines the spectral feature learning and spatial feature learning in a hierarchical fashion. Stacking a set of SSFL units, a deep hierarchical model called the spectral-spatial networks (SSN) is further proposed for HSI classification. SSN can exploit both discriminative spectral and spatial information simultaneously. Specifically, SSN learns useful high-level features by alternating between spectral and spatial feature learning operations. Then, kernel-based extreme learning machine (KELM), a shallow neural network, is embedded in SSN to classify image pixels. Extensive experiments are performed on two benchmark HSI datasets to verify the effectiveness of SSN. Compared with state-of-the-art methods, SSN with a deep hierarchical architecture obtains higher classification accuracy in terms of the overall accuracy, average accuracy, and kappa ( κ ) coefficient of agreement, especially when the number of the training samples is small. PMID:26241988

  1. Automated blood vessel extraction using local features on retinal images

    Science.gov (United States)

    Hatanaka, Yuji; Samo, Kazuki; Tajima, Mikiya; Ogohara, Kazunori; Muramatsu, Chisako; Okumura, Susumu; Fujita, Hiroshi

    2016-03-01

    An automated blood vessel extraction using high-order local autocorrelation (HLAC) on retinal images is presented. Although many blood vessel extraction methods based on contrast have been proposed, a technique based on the relation of neighbor pixels has not been published. HLAC features are shift-invariant; therefore, we applied HLAC features to retinal images. However, HLAC features are weak to turned image, thus a method was improved by the addition of HLAC features to a polar transformed image. The blood vessels were classified using an artificial neural network (ANN) with HLAC features using 105 mask patterns as input. To improve performance, the second ANN (ANN2) was constructed by using the green component of the color retinal image and the four output values of ANN, Gabor filter, double-ring filter and black-top-hat transformation. The retinal images used in this study were obtained from the "Digital Retinal Images for Vessel Extraction" (DRIVE) database. The ANN using HLAC output apparent white values in the blood vessel regions and could also extract blood vessels with low contrast. The outputs were evaluated using the area under the curve (AUC) based on receiver operating characteristics (ROC) analysis. The AUC of ANN2 was 0.960 as a result of our study. The result can be used for the quantitative analysis of the blood vessels.

  2. Fingerprint image segmentation based on multi-features histogram analysis

    Science.gov (United States)

    Wang, Peng; Zhang, Youguang

    2007-11-01

    An effective fingerprint image segmentation based on multi-features histogram analysis is presented. We extract a new feature, together with three other features to segment fingerprints. Two of these four features, each of which is related to one of the other two, are reciprocals with each other, so features are divided into two groups. These two features' histograms are calculated respectively to determine which feature group is introduced to segment the aim-fingerprint. The features could also divide fingerprints into two classes with high and low quality. Experimental results show that our algorithm could classify foreground and background effectively with lower computational cost, and it can also reduce pseudo-minutiae detected and improve the performance of AFIS.

  3. Introduction: Feature Issue on Optical Imaging and Spectroscopy

    OpenAIRE

    Hielscher, Andreas H.; Mycek, Mary-Ann; Perelman, Lev T.

    2010-01-01

    The editors introduce the Biomedical Optics Express feature issue, “Optical Imaging and Spectroscopy,” which was a technical area at the 2010 Optical Society of America (OSA), Biomedical Optics (BIOMED) Topical Meeting held on 11–14 April in Miami, Florida. The feature issue includes 23 contributions from conference attendees.

  4. Smart Images Search based on Visual Features Fusion

    International Nuclear Information System (INIS)

    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 ycbcr 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 is

  5. Featured Image: Fireball After a Temporary Capture?

    Science.gov (United States)

    Kohler, Susanna

    2016-06-01

    This image of a fireball was captured in the Czech Republic by cameras at a digital autonomous observatory in the village of Kunak. This observatory is part of a network of stations known as the European Fireball Network, and this particular meteoroid detection, labeled EN130114, is notable because it has the lowest initial velocity of any natural object ever observed by the network. Led by David Clark (University of Western Ontario), the authors of a recent study speculate that before this meteoroid impacted Earth, it may have been a Temporarily Captured Orbiter (TCO). TCOs are near-Earth objects that make a few orbits of Earth before returning to heliocentric orbits. Only one has ever been observed to date, and though they are thought to make up 0.1% of all meteoroids, EN130114 is the first event ever detected that exhibits conclusive behavior of a TCO. For more information on EN130114 and why TCOs are important to study, check out the paper below!CitationDavid L. Clark et al 2016 AJ 151 135. doi:10.3847/0004-6256/151/6/135

  6. Feature-Area Optimization: A Novel SAR Image Registration Method

    OpenAIRE

    Liu, Fuqiang; Bi, Fukun; Chen, Liang; Shi, Hao; Liu, Wei

    2016-01-01

    This letter proposes a synthetic aperture radar (SAR) image registration method named Feature-Area Optimization (FAO). First, the traditional area-based optimization model is reconstructed and decomposed into three key but uncertain factors: initialization, slice set and regularization. Next, structural features are extracted by scale invariant feature transform (SIFT) in dual-resolution space (SIFT-DRS), a novel SIFT-Like method dedicated to FAO. Then, the three key factors are determined ba...

  7. Perinatal clinical and imaging features of CLOVES syndrome

    Energy Technology Data Exchange (ETDEWEB)

    Fernandez-Pineda, Israel [Virgen del Rocio Children' s Hospital, Department of Pediatric Surgery, Seville (Spain); Fajardo, Manuel [Virgen del Rocio Children' s Hospital, Department of Pediatric Radiology, Seville (Spain); Chaudry, Gulraiz; Alomari, Ahmad I. [Children' s Hospital Boston and Harvard Medical School, Division of Vascular and Interventional Radiology, Boston, MA (United States)

    2010-08-15

    We report a neonate with antenatal imaging features suggestive of CLOVES syndrome. Postnatal clinical and imaging findings confirmed the diagnosis, with the constellation of truncal overgrowth, cutaneous capillary malformation, lymphatic and musculoskeletal anomalies. The clinical, radiological and histopathological findings noted in this particular phenotype help differentiate it from other overgrowth syndromes with complex vascular anomalies. (orig.)

  8. Multiresolution image fusion scheme based on fuzzy region feature

    Institute of Scientific and Technical Information of China (English)

    LIU Gang; JING Zhong-liang; SUN Shao-yuan

    2006-01-01

    This paper proposes a novel region based image fusion scheme based on multiresolution analysis. The low frequency band of the image multiresolution representation is segmented into important regions, sub-important regions and background regions. Each feature of the regions is used to determine the region's degree of membership in the multiresolution representation,and then to achieve multiresolution representation of the fusion result. The final image fusion result can be obtained by using the inverse multiresolution transform. Experiments showed that the proposed image fusion method can have better performance than existing image fusion methods.

  9. Disorders of the pediatric pancreas: imaging features

    International Nuclear Information System (INIS)

    The purpose of this manuscript is to provide an overview of the normal development of the pancreas as well as pancreatic pathology in children. Diagnostic imaging plays a major role in the evaluation of the pancreas in infants and children. Familiarity with the range of normal appearance and the diseases that commonly affect this gland is important for the accurate and timely diagnosis of pancreatic disorders in the pediatric population. Normal embryology is discussed, as are the most common congenital anomalies that occur as a result of aberrant development during embryology. These include pancreas divisum, annular pancreas, agenesis of the dorsal pancreatic anlagen and ectopic pancreatic tissue. Syndromes that can manifest pancreatic pathology include: Beckwith Wiedemann syndrome, von Hippel-Lindau disease and autosomal dominant polycystic kidney disease. Children and adults with cystic fibrosis and Shwachman-Diamond syndrome frequently present with pancreatic insufficiency. Trauma is the most common cause of pancreatitis in children. In younger children, unexplained pancreatic injury must always alert the radiologist to potential child abuse. Pancreatic pseudocysts are a complication of trauma, but can also be seen in the setting of acute or chronic pancreatitis from other causes. Primary pancreatic neoplasms are rare in children and are divided into exocrine tumors such as pancreatoblastoma and adenocarcinoma and into endocrine or islet cell tumors. Islet cell tumors are classified as functioning (insulinoma, gastrinoma, VIPoma and glucagonoma) and nonfunctioning tumors. Solid-cystic papillary tumor is probably the most common pancreatic tumor in Asian children. Although quite rare, secondary tumors of the pancreas can be associated with certain primary malignancies. (orig.)

  10. Disorders of the pediatric pancreas: imaging features

    Energy Technology Data Exchange (ETDEWEB)

    Nijs, Els [University Hospital Gasthuisberg, Department of Radiology, Leuven (Belgium); Callahan, Michael J.; Taylor, George A. [Boston Children' s Hospital, Department of Radiology, Boston, MA (United States)

    2005-04-01

    The purpose of this manuscript is to provide an overview of the normal development of the pancreas as well as pancreatic pathology in children. Diagnostic imaging plays a major role in the evaluation of the pancreas in infants and children. Familiarity with the range of normal appearance and the diseases that commonly affect this gland is important for the accurate and timely diagnosis of pancreatic disorders in the pediatric population. Normal embryology is discussed, as are the most common congenital anomalies that occur as a result of aberrant development during embryology. These include pancreas divisum, annular pancreas, agenesis of the dorsal pancreatic anlagen and ectopic pancreatic tissue. Syndromes that can manifest pancreatic pathology include: Beckwith Wiedemann syndrome, von Hippel-Lindau disease and autosomal dominant polycystic kidney disease. Children and adults with cystic fibrosis and Shwachman-Diamond syndrome frequently present with pancreatic insufficiency. Trauma is the most common cause of pancreatitis in children. In younger children, unexplained pancreatic injury must always alert the radiologist to potential child abuse. Pancreatic pseudocysts are a complication of trauma, but can also be seen in the setting of acute or chronic pancreatitis from other causes. Primary pancreatic neoplasms are rare in children and are divided into exocrine tumors such as pancreatoblastoma and adenocarcinoma and into endocrine or islet cell tumors. Islet cell tumors are classified as functioning (insulinoma, gastrinoma, VIPoma and glucagonoma) and nonfunctioning tumors. Solid-cystic papillary tumor is probably the most common pancreatic tumor in Asian children. Although quite rare, secondary tumors of the pancreas can be associated with certain primary malignancies. (orig.)

  11. Image Processing Techniques and Feature Recognition in Solar Physics

    Science.gov (United States)

    Aschwanden, Markus J.

    2010-04-01

    This review presents a comprehensive and systematic overview of image-processing techniques that are used in automated feature-detection algorithms applied to solar data: i) image pre-processing procedures, ii) automated detection of spatial features, iii) automated detection and tracking of temporal features (events), and iv) post-processing tasks, such as visualization of solar imagery, cataloguing, statistics, theoretical modeling, prediction, and forecasting. For each aspect the most recent developments and science results are highlighted. We conclude with an outlook on future trends.

  12. DE-STRIPING FOR TDICCD REMOTE SENSING IMAGE BASED ON STATISTICAL FEATURES OF HISTOGRAM

    Directory of Open Access Journals (Sweden)

    H.-T. Gao

    2016-06-01

    Full Text Available Aim to striping noise brought by non-uniform response of remote sensing TDI CCD, a novel de-striping method based on statistical features of image histogram is put forward. By analysing the distribution of histograms,the centroid of histogram is selected to be an eigenvalue representing uniformity of ground objects,histogrammic centroid of whole image and each pixels are calculated first,the differences between them are regard as rough correction coefficients, then in order to avoid the sensitivity caused by single parameter and considering the strong continuity and pertinence of ground objects between two adjacent pixels,correlation coefficient of the histograms is introduces to reflect the similarities between them,fine correction coefficient is obtained by searching around the rough correction coefficient,additionally,in view of the influence of bright cloud on histogram,an automatic cloud detection based on multi-feature including grey level,texture,fractal dimension and edge is used to pre-process image.Two 0-level panchromatic images of SJ-9A satellite with obvious strip noise are processed by proposed method to evaluate the performance, results show that the visual quality of images are improved because the strip noise is entirely removed,we quantitatively analyse the result by calculating the non-uniformity ,which has reached about 1% and is better than histogram matching method.

  13. De-Striping for Tdiccd Remote Sensing Image Based on Statistical Features of Histogram

    Science.gov (United States)

    Gao, Hui-ting; Liu, Wei; He, Hong-yan; Zhang, Bing-xian; Jiang, Cheng

    2016-06-01

    Aim to striping noise brought by non-uniform response of remote sensing TDI CCD, a novel de-striping method based on statistical features of image histogram is put forward. By analysing the distribution of histograms,the centroid of histogram is selected to be an eigenvalue representing uniformity of ground objects,histogrammic centroid of whole image and each pixels are calculated first,the differences between them are regard as rough correction coefficients, then in order to avoid the sensitivity caused by single parameter and considering the strong continuity and pertinence of ground objects between two adjacent pixels,correlation coefficient of the histograms is introduces to reflect the similarities between them,fine correction coefficient is obtained by searching around the rough correction coefficient,additionally,in view of the influence of bright cloud on histogram,an automatic cloud detection based on multi-feature including grey level,texture,fractal dimension and edge is used to pre-process image.Two 0-level panchromatic images of SJ-9A satellite with obvious strip noise are processed by proposed method to evaluate the performance, results show that the visual quality of images are improved because the strip noise is entirely removed,we quantitatively analyse the result by calculating the non-uniformity ,which has reached about 1% and is better than histogram matching method.

  14. Integration of Image-Derived and Pos-Derived Features for Image Blur Detection

    Science.gov (United States)

    Teo, Tee-Ann; Zhan, Kai-Zhi

    2016-06-01

    The image quality plays an important role for Unmanned Aerial Vehicle (UAV)'s applications. The small fixed wings UAV is suffering from the image blur due to the crosswind and the turbulence. Position and Orientation System (POS), which provides the position and orientation information, is installed onto an UAV to enable acquisition of UAV trajectory. It can be used to calculate the positional and angular velocities when the camera shutter is open. This study proposes a POS-assisted method to detect the blur image. The major steps include feature extraction, blur image detection and verification. In feature extraction, this study extracts different features from images and POS. The image-derived features include mean and standard deviation of image gradient. For POS-derived features, we modify the traditional degree-of-linear-blur (blinear) method to degree-of-motion-blur (bmotion) based on the collinear condition equations and POS parameters. Besides, POS parameters such as positional and angular velocities are also adopted as POS-derived features. In blur detection, this study uses Support Vector Machines (SVM) classifier and extracted features (i.e. image information, POS data, blinear and bmotion) to separate blur and sharp UAV images. The experiment utilizes SenseFly eBee UAV system. The number of image is 129. In blur image detection, we use the proposed degree-of-motion-blur and other image features to classify the blur image and sharp images. The classification result shows that the overall accuracy using image features is only 56%. The integration of image-derived and POS-derived features have improved the overall accuracy from 56% to 76% in blur detection. Besides, this study indicates that the performance of the proposed degree-of-motion-blur is better than the traditional degree-of-linear-blur.

  15. Semantic Based Image Annotation Using Descriptive Features and Retagging approach

    Directory of Open Access Journals (Sweden)

    P.Nagarani

    2012-02-01

    Full Text Available The Semantic based annotation of an image is very important and a difficult task in content-based image retrieval (CBIR. The low-level features of the images are described using color and the texture features and the proposed model is used for semantic annotation of images. Also the textual annotations or the tags with multimedia content are the most effective approaches to organize and to support search over digital images and multimedia databases. The quality of the tags was refined using Image retagging method. The process is given as a multi-path graph based problem, which in parallel identifies the visual content of the images, semantic correlation of the tags as well as the primary information provided by users. The image annotation preferred because as the countless images exist in our lives it is not possible to annotate them all by hand. And so annotation by computer is a potential and promising solution to this problem precisely. The ability to annotate images semantically based on the objects that they contain is essential in image retrieval as it provides the mechanism to take advantage of existing text retrieval system

  16. Semantic Based Image Annotation Using Descriptive Features and Retagging approach

    Directory of Open Access Journals (Sweden)

    P.Nagarani

    2012-03-01

    Full Text Available The Semantic based annotation of an image is very important and a difficult task in content-based image retrieval (CBIR. The low-level features of the images are described using color and the texture features and the proposed model is used for semantic annotation of images. Also the textual annotations or the tags with multimedia content are the most effective approaches to organize and to support search over digital images and multimedia databases. The quality of the tags was refined using Image retagging method. Theprocess is given as a multi-path graph based problem, which in parallel identifies the visual content of the images, semantic correlation of the tags as well as the primary information provided by users. The image annotation preferred because as the countless images exist in our lives it is not possible to annotate them all by hand. And so annotation by computer is a potential and promising solution to thisproblem precisely. The ability to annotate images semantically based on the objects that they contain is essential in image retrieval as it provides the mechanism to take advantage of existing text retrieval systems.

  17. An image segmentation based method for iris feature extraction

    Institute of Scientific and Technical Information of China (English)

    XU Guang-zhu; ZHANG Zai-feng; MA Yi-de

    2008-01-01

    In this article, the local anomalistic blocks such ascrypts, furrows, and so on in the iris are initially used directly asiris features. A novel image segmentation method based onintersecting cortical model (ICM) neural network was introducedto segment these anomalistic blocks. First, the normalized irisimage was put into ICM neural network after enhancement.Second, the iris features were segmented out perfectly and wereoutput in binary image type by the ICM neural network. Finally,the fourth output pulse image produced by ICM neural networkwas chosen as the iris code for the convenience of real timeprocessing. To estimate the performance of the presentedmethod, an iris recognition platform was produced and theHamming Distance between two iris codes was computed tomeasure the dissimilarity between them. The experimentalresults in CASIA vl.0 and Bath iris image databases show thatthe proposed iris feature extraction algorithm has promisingpotential in iris recognition.

  18. Histopathological Image Classification Using Discriminative Feature-Oriented Dictionary Learning.

    Science.gov (United States)

    Vu, Tiep Huu; Mousavi, Hojjat Seyed; Monga, Vishal; Rao, Ganesh; Rao, U K Arvind

    2016-03-01

    In histopathological image analysis, feature extraction for classification is a challenging task due to the diversity of histology features suitable for each problem as well as presence of rich geometrical structures. In this paper, we propose an automatic feature discovery framework via learning class-specific dictionaries and present a low-complexity method for classification and disease grading in histopathology. Essentially, our Discriminative Feature-oriented Dictionary Learning (DFDL) method learns class-specific dictionaries such that under a sparsity constraint, the learned dictionaries allow representing a new image sample parsimoniously via the dictionary corresponding to the class identity of the sample. At the same time, the dictionary is designed to be poorly capable of representing samples from other classes. Experiments on three challenging real-world image databases: 1) histopathological images of intraductal breast lesions, 2) mammalian kidney, lung and spleen images provided by the Animal Diagnostics Lab (ADL) at Pennsylvania State University, and 3) brain tumor images from The Cancer Genome Atlas (TCGA) database, reveal the merits of our proposal over state-of-the-art alternatives. Moreover, we demonstrate that DFDL exhibits a more graceful decay in classification accuracy against the number of training images which is highly desirable in practice where generous training is often not available.

  19. Perceptual image hashing via feature points: performance evaluation and tradeoffs.

    Science.gov (United States)

    Monga, Vishal; Evans, Brian L

    2006-11-01

    We propose an image hashing paradigm using visually significant feature points. The feature points should be largely invariant under perceptually insignificant distortions. To satisfy this, we propose an iterative feature detector to extract significant geometry preserving feature points. We apply probabilistic quantization on the derived features to introduce randomness, which, in turn, reduces vulnerability to adversarial attacks. The proposed hash algorithm withstands standard benchmark (e.g., Stirmark) attacks, including compression, geometric distortions of scaling and small-angle rotation, and common signal-processing operations. Content changing (malicious) manipulations of image data are also accurately detected. Detailed statistical analysis in the form of receiver operating characteristic (ROC) curves is presented and reveals the success of the proposed scheme in achieving perceptual robustness while avoiding misclassification.

  20. Effective feature selection for image steganalysis using extreme learning machine

    Science.gov (United States)

    Feng, Guorui; Zhang, Haiyan; Zhang, Xinpeng

    2014-11-01

    Image steganography delivers secret data by slight modifications of the cover. To detect these data, steganalysis tries to create some features to embody the discrepancy between the cover and steganographic images. Therefore, the urgent problem is how to design an effective classification architecture for given feature vectors extracted from the images. We propose an approach to automatically select effective features based on the well-known JPEG steganographic methods. This approach, referred to as extreme learning machine revisited feature selection (ELM-RFS), can tune input weights in terms of the importance of input features. This idea is derived from cross-validation learning and one-dimensional (1-D) search. While updating input weights, we seek the energy decreasing direction using the leave-one-out (LOO) selection. Furthermore, we optimize the 1-D energy function instead of directly discarding the least significant feature. Since recent Liu features can gain considerable low detection errors compared to a previous JPEG steganalysis, the experimental results demonstrate that the new approach results in less classification error than other classifiers such as SVM, Kodovsky ensemble classifier, direct ELM-LOO learning, kernel ELM, and conventional ELM in Liu features. Furthermore, ELM-RFS achieves a similar performance with a deep Boltzmann machine using less training time.

  1. Featured Image: A Galaxy Plunges Into a Cluster Core

    Science.gov (United States)

    Kohler, Susanna

    2015-10-01

    The galaxy that takes up most of the frame in this stunning image (click for the full view!) is NGC 1427A. This is a dwarf irregular galaxy (unlike the fortuitously-located background spiral galaxy in the lower right corner of the image), and its currently in the process of plunging into the center of the Fornax galaxy cluster. Marcelo Mora (Pontifical Catholic University of Chile) and collaborators have analyzed observations of this galaxy made by both the Very Large Telescope in Chile and the Hubble Advanced Camera for Surveys, which produced the image shown here as a color composite in three channels. The team worked to characterize the clusters of star formation within NGC 1427A identifiable in the image as bright knots within the galaxy and determine how the interactions of this galaxy with its cluster environment affect the star formation within it. For more information and the original image, see the paper below.Citation:Marcelo D. Mora et al 2015 AJ 150 93. doi:10.1088/0004-6256/150/3/93

  2. High brightness imaging system using vertical cavity surface-emitting laser micro-arrays- results and proposed enhancements

    Science.gov (United States)

    Mentzer, Mark A.; Ghosh, Chuni L.

    2011-05-01

    Laser illumination systems for high brightness imaging through the self-luminosity of explosive events, at Aberdeen Proving Ground and elsewhere, required complex pulse timing, extensive cooling, large-scale laser systems (frequencydoubled flash-pumped Nd:YAG, Cu-vapor, Q-switched ruby), making them difficult to implement for range test illumination in high speed videography. A Vertical Cavity Surface-Emitting Laser (VCSEL) array was designed and implemented with spectral filtering to effectively remove self-luminosity and the fireball from the image, providing excellent background discrimination in a variety of range test scenarios. Further improvements to the system are proposed for applications such as imaging through murky water or dust clouds with optimal penetration of obscurants.

  3. Feature maps driven no-reference image quality prediction of authentically distorted images

    Science.gov (United States)

    Ghadiyaram, Deepti; Bovik, Alan C.

    2015-03-01

    Current blind image quality prediction models rely on benchmark databases comprised of singly and synthetically distorted images, thereby learning image features that are only adequate to predict human perceived visual quality on such inauthentic distortions. However, real world images often contain complex mixtures of multiple distortions. Rather than a) discounting the effect of these mixtures of distortions on an image's perceptual quality and considering only the dominant distortion or b) using features that are only proven to be efficient for singly distorted images, we deeply study the natural scene statistics of authentically distorted images, in different color spaces and transform domains. We propose a feature-maps-driven statistical approach which avoids any latent assumptions about the type of distortion(s) contained in an image, and focuses instead on modeling the remarkable consistencies in the scene statistics of real world images in the absence of distortions. We design a deep belief network that takes model-based statistical image features derived from a very large database of authentically distorted images as input and discovers good feature representations by generalizing over different distortion types, mixtures, and severities, which are later used to learn a regressor for quality prediction. We demonstrate the remarkable competence of our features for improving automatic perceptual quality prediction on a benchmark database and on the newly designed LIVE Authentic Image Quality Challenge Database and show that our approach of combining robust statistical features and the deep belief network dramatically outperforms the state-of-the-art.

  4. Image Recommendation Algorithm Using Feature-Based Collaborative Filtering

    Science.gov (United States)

    Kim, Deok-Hwan

    As the multimedia contents market continues its rapid expansion, the amount of image contents used in mobile phone services, digital libraries, and catalog service is increasing remarkably. In spite of this rapid growth, users experience high levels of frustration when searching for the desired image. Even though new images are profitable to the service providers, traditional collaborative filtering methods cannot recommend them. To solve this problem, in this paper, we propose feature-based collaborative filtering (FBCF) method to reflect the user's most recent preference by representing his purchase sequence in the visual feature space. The proposed approach represents the images that have been purchased in the past as the feature clusters in the multi-dimensional feature space and then selects neighbors by using an inter-cluster distance function between their feature clusters. Various experiments using real image data demonstrate that the proposed approach provides a higher quality recommendation and better performance than do typical collaborative filtering and content-based filtering techniques.

  5. MR imaging evaluation of perianal fistulas: spectrum of imaging features.

    Science.gov (United States)

    de Miguel Criado, Jaime; del Salto, Laura García; Rivas, Patricia Fraga; del Hoyo, Luis Felipe Aguilera; Velasco, Leticia Gutiérrez; de las Vacas, M Isabel Díez Pérez; Marco Sanz, Ana G; Paradela, Marcos Manzano; Moreno, Eduardo Fraile

    2012-01-01

    Perianal fistulization is an inflammatory condition that affects the region around the anal canal, causing significant morbidity and often requiring repeated surgical treatments due to its high tendency to recur. To adopt the best surgical strategy and avoid recurrences, it is necessary to obtain precise radiologic information about the location of the fistulous track and the affected pelvic structures. Until recently, imaging techniques played a limited role in evaluation of perianal fistulas. However, magnetic resonance (MR) imaging now provides more precise information on the anatomy of the anal canal, the anal sphincter complex, and the relationships of the fistula to the pelvic floor structures and the plane of the levator ani muscle. MR imaging allows precise definition of the fistulous track and identification of secondary fistulas or abscesses. It provides accurate information for appropriate surgical treatment, decreasing the incidence of recurrence and allowing side effects such as fecal incontinence to be avoided. Radiologists should be familiar with the anatomic and pathologic findings of perianal fistulas and classify them using the St James's University Hospital MR imaging-based grading system.

  6. 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.

  7. Photoacoustic Imaging: Semiconducting Oligomer Nanoparticles as an Activatable Photoacoustic Probe with Amplified Brightness for In Vivo Imaging of pH (Adv. Mater. 19/2016).

    Science.gov (United States)

    Miao, Qingqing; Lyu, Yan; Ding, Dan; Pu, Kanyi

    2016-05-01

    Despite the great potential of photoacoustic imaging in the life sciences, the development of smart activatable photoacoustic probes remains elusive. On page 3662, K. Pu and co-workers report a facile nanoengineering approach based on semiconducting oligomer nano-particles to develop ratiometric photoacoustic probes with amplified brightness and enhanced sensing capability for accurate photoacoustic mapping of pH in the tumors of living mice.

  8. MRI and PET image fusion using fuzzy logic and image local features.

    Science.gov (United States)

    Javed, Umer; Riaz, Muhammad Mohsin; Ghafoor, Abdul; Ali, Syed Sohaib; Cheema, Tanveer Ahmed

    2014-01-01

    An image fusion technique for magnetic resonance imaging (MRI) and positron emission tomography (PET) using local features and fuzzy logic is presented. The aim of proposed technique is to maximally combine useful information present in MRI and PET images. Image local features are extracted and combined with fuzzy logic to compute weights for each pixel. Simulation results show that the proposed scheme produces significantly better results compared to state-of-art schemes.

  9. Optimized Image Steganalysis through Feature Selection using MBEGA

    CERN Document Server

    Geetha, S

    2010-01-01

    Feature based steganalysis, an emerging branch in information forensics, aims at identifying the presence of a covert communication by employing the statistical features of the cover and stego image as clues/evidences. Due to the large volumes of security audit data as well as complex and dynamic properties of steganogram behaviours, optimizing the performance of steganalysers becomes an important open problem. This paper is focussed at fine tuning the performance of six promising steganalysers in this field, through feature selection. We propose to employ Markov Blanket-Embedded Genetic Algorithm (MBEGA) for stego sensitive feature selection process. In particular, the embedded Markov blanket based memetic operators add or delete features (or genes) from a genetic algorithm (GA) solution so as to quickly improve the solution and fine-tune the search. Empirical results suggest that MBEGA is effective and efficient in eliminating irrelevant and redundant features based on both Markov blanket and predictive pow...

  10. Identification of Image Spam by Using Low Level & Metadata Features

    Directory of Open Access Journals (Sweden)

    Anand Gupta,

    2012-04-01

    Full Text Available Spammers are constantly evolving new spam technologies, the latest of which is image spam. Till now research in spam image identification has been addressed by considering properties like colour, size, compressibility, entropy, content etc. However, we feel the methods of identification so evolved have certain limitations due to embedded obfuscation like complex backgrounds, compression artifacts and wide variety of fonts and formats .To overcome these limitations, we have proposed 2 methodologies(however there can be more. Each methodology has 4 stages. Both the methodologies are almost similar except in the second stage where methodology I extracts low level features while the other extracts metadata features. Also a comparison between both the methodologies is shown. The method works on images with and without noise separately. Colour properties of the images are altered so that OCR (Optical Character Recognition can easily read the text embedded in the image. The proposed methods are tested on a dataset of 1984 spam images and are found to be effective in identifying all types of spam images having (1 only text, (2 only images or (3 both text and images. The encouraging experimental results show that the methodology I achieves an accuracy of 92% while the other achieves an accuracy of 93.3%

  11. Content Based Image Recognition by Information Fusion with Multiview Features

    Directory of Open Access Journals (Sweden)

    Rik Das

    2015-09-01

    Full Text Available Substantial research interest has been observed in the field of object recognition as a vital component for modern intelligent systems. Content based image classification and retrieval have been considered as two popular techniques for identifying the object of interest. Feature extraction has played the pivotal role towards successful implementation of the aforesaid techniques. The paper has presented two novel techniques of feature extraction from diverse image categories both in spatial domain and in frequency domain. The multi view features from the image categories were evaluated for classification and retrieval performances by means of a fusion based recognition architecture. The experimentation was carried out with four different popular public datasets. The proposed fusion framework has exhibited an average increase of 24.71% and 20.78% in precision rates for classification and retrieval respectively, when compared to state-of-the art techniques. The experimental findings were validated with a paired t test for statistical significance.

  12. Automated Classification of Glaucoma Images by Wavelet Energy Features

    Directory of Open Access Journals (Sweden)

    N.Annu

    2013-04-01

    Full Text Available Glaucoma is the second leading cause of blindness worldwide. As glaucoma progresses, more optic nerve tissue is lost and the optic cup grows which leads to vision loss. This paper compiles a systemthat could be used by non-experts to filtrate cases of patients not affected by the disease. This work proposes glaucomatous image classification using texture features within images and efficient glaucoma classification based on Probabilistic Neural Network (PNN. Energy distribution over wavelet sub bands is applied to compute these texture features. Wavelet features were obtained from the daubechies (db3, symlets (sym3, and biorthogonal (bio3.3, bio3.5, and bio3.7 wavelet filters. It uses a technique to extract energy signatures obtained using 2-D discrete wavelet transform and the energy obtained from the detailed coefficients can be used to distinguish between normal and glaucomatous images. We observedan accuracy of around 95%, this demonstrates the effectiveness of these methods.

  13. Vaginal Masses: Magnetic Resonance Imaging Features with Pathologic Correlation

    International Nuclear Information System (INIS)

    The detection of vaginal lesions has increased with the expanding use of cross-sectional imaging. Magnetic resonance imaging (MRI) - with its high-contrast resolution and multiplanar capabilities - is often useful for characterizing vaginal masses. Vaginal masses can be classified as congenital, inflammatory, cystic (benign), and neoplastic (benign or malignant) in etiology. Recognition of the typical MR imaging features of such lesions is important because it often determines the treatment approach and may obviate surgery. Finally, vaginal MR imaging can be used to evaluate post-treatment changes related to previous surgery and radiation therapy. In this article, we will review pertinent vaginal anatomy, vaginal and pelvic MRI technique, and the MRI features of a variety of vaginal lesions with pathological correlation

  14. Deep optical images of malin 1 reveal new features

    OpenAIRE

    Galaz, Gaspar; Milovic, Carlos; Suc, Vincent; Busta, Luis; Lizana, Guadalupe; Infante, Leopoldo; Royo Royo, Santiago

    2015-01-01

    We present Megacam deep optical images (g and r) of Malin 1 obtained with the 6.5m Magellan/Clay telescope, detecting structures down to ~ 28 B mag arcsec-2. In order to enhance galaxy features buried in the noise, we use a noise reduction filter based on the total generalized variation regularizator. This method allows us to detect and resolve very faint morphological features, including spiral arms, with a high visual contrast. For the first time, we can appreciate an optical image of Malin...

  15. Imaging features of complex sclerosing lesions of the breast

    Energy Technology Data Exchange (ETDEWEB)

    Myong, Joo Hwa; Choi, Byung Gil; Kim, Sung Hun; Kang, Bong Joo; Lee, Ah Won; Song, Byung Joo [Seoul St. Mary' s Hospital, The Catholic University of Korea College of Medicine, Seoul (Korea, Republic of)

    2014-03-15

    The purpose of this study was to evaluate the imaging features of complex sclerosing lesions of the breast and to assess the rate of upgrade to breast cancer. From March 2008 to May 2012, seven lesions were confirmed as complex sclerosing lesions by ultrasonography-guided core needle biopsy. Final results by either surgical excision or follow-up imaging studies were reviewed to assess the rate of upgrade to breast cancer. Two radiologists retrospectively analyzed the imaging findings according to the Breast Imaging Reporting and Data System classification. Five lesions underwent subsequent surgical excision and two of them revealed ductal carcinoma in situ (n=1) and invasive ductal carcinoma (n=1). Our study showed a breast cancer upgrade rate of 28.6% (2 of 7 lesions). Two lesions were stable on imaging follow-up beyond 1 year. The mammographic features included masses (n=4, 57.1%), architectural distortion (n=2, 28.6%), and focal asymmetry (n=1, 14.3%). Common B-mode ultrasonographic features were irregular shape (n=6, 85.7%), spiculated margin (n=5, 71.4 %), and hypoechogenicity (n=7, 100%). The final assessment categories were category 4 (n=6, 85.7%) and category 5 (n=1, 14.3%). The complex sclerosing lesions were commonly mass-like on mammography and showed the suspicious ultrasonographic features of category 4. Due to a high underestimation rate, all complex sclerosing lesions by core needle biopsy should be excised.

  16. Spitzer/IRAC Imaging of Exceptionally Bright Cluster-Lensed Submillimeter Galaxies Discovered by the Herschel Lensing Survey

    Science.gov (United States)

    Egami, Eiichi; Ebeling, Harald; Rawle, Timothy; Clement, Benjamin; Walth, Gregory; Pereira, Maria; Richard, Johan; Kneib, Jean-Paul

    2012-12-01

    Over the last few years, discoveries of exceptionally bright (e.g., observed S_peak > 100 mJy in the Herschel/SPIRE bands) gravitationally lensed submillimeter galaxies (SMGs) have generated great excitement. This is because these gravitationally lensed SMGs are so bright that they enable us to perform a variety of follow-up observations using a suite of observing facilities in the submillimeter, millimeter, and radio now available on the ground. Using Herschel, our team has been conducting a survey of such bright lensed galaxies in the fields of massive galaxy clusters: ``The Herschel Lensing Survey (HLS)'' (PI: Egami; 419 hours). This large Herschel program targets a total of 581 X-ray/SZ-selected massive clusters, and is currently 80% complete. Cluster lenses are often more powerful than galaxy lenses, producing larger magnifications. For example, typical magnification factors for galaxy-lensed Herschel sources are x10 or less while cluster-lensed systems can often produce magnification factors of x20-30 and even above x100. Cluster lenses will therefore allow us to detect and study intrinsically less-luminous and/or more distant sources with the ability to provide a view of finer-scale (i.e., sub-kpc) structures. Here, we propose to conduct Spitzer/IRAC imaging of 56 bright lensed SMG candidates we have identified in the ~470 HLS cluster fields observed so far. The main scientific goal is twofold: (1) to locate the underlying stellar component, and (2) to study its properties (e.g., stellar mass, specific star-formation rate) by constraining the rest-frame near-infrared SED and comparing with the Herschel and other submillimeter/millimeter data (e.g., SMA, PdB, ALMA, etc.). These rare bright lensed SMGs will allow us to probe the population of heavily dust-obscured vigorously star-forming galaxies at high redshift (z>1), which is thought to play an important role in the cosmic star-formation history of the Universe and yet has been difficult to study due to the

  17. Modality prediction of biomedical literature images using multimodal feature representation

    Directory of Open Access Journals (Sweden)

    Pelka, Obioma

    2016-08-01

    Full Text Available This paper presents the modelling approaches performed to automatically predict the modality of images found in biomedical literature. Various state-of-the-art visual features such as Bag-of-Keypoints computed with dense SIFT descriptors, texture features and Joint Composite Descriptors were used for visual image representation. Text representation was obtained by vector quantisation on a Bag-of-Words dictionary generated using attribute importance derived from a χ-test. Computing the principal components separately on each feature, dimension reduction as well as computational load reduction was achieved. Various multiple feature fusions were adopted to supplement visual image information with corresponding text information. The improvement obtained when using multimodal features vs. visual or text features was detected, analysed and evaluated. Random Forest models with 100 to 500 deep trees grown by resampling, a multi class linear kernel SVM with C=0.05 and a late fusion of the two classifiers were used for modality prediction. A Random Forest classifier achieved a higher accuracy and computed Bag-of-Keypoints with dense SIFT descriptors proved to be a better approach than with Lowe SIFT.

  18. Dermoscopy analysis of RGB-images based on comparative features

    Science.gov (United States)

    Myakinin, Oleg O.; Zakharov, Valery P.; Bratchenko, Ivan A.; Artemyev, Dmitry N.; Neretin, Evgeny Y.; Kozlov, Sergey V.

    2015-09-01

    In this paper, we propose an algorithm for color and texture analysis for dermoscopic images of human skin based on Haar wavelets, Local Binary Patterns (LBP) and Histogram Analysis. This approach is a modification of «7-point checklist» clinical method. Thus, that is an "absolute" diagnostic method because one is using only features extracted from tumor's ROI (Region of Interest), which can be selected manually and/or using a special algorithm. We propose additional features extracted from the same image for comparative analysis of tumor and healthy skin. We used Euclidean distance, Cosine similarity, and Tanimoto coefficient as comparison metrics between color and texture features extracted from tumor's and healthy skin's ROI separately. A classifier for separating melanoma images from other tumors has been built by SVM (Support Vector Machine) algorithm. Classification's errors with and without comparative features between skin and tumor have been analyzed. Significant increase of recognition quality with comparative features has been demonstrated. Moreover, we analyzed two modes (manual and automatic) for ROI selecting on tumor and healthy skin areas. We have reached 91% of sensitivity using comparative features in contrast with 77% of sensitivity using the only "absolute" method. The specificity was the invariable (94%) in both cases.

  19. Texture Features based Blur Classification in Barcode Images

    OpenAIRE

    Shamik Tiwari; Vidya Prasad Shukla; Sangappa Birada; Ajay Singh

    2013-01-01

    Blur is an undesirable phenomenon which appears as image degradation. Blur classification is extremely desirable before application of any blur parameters estimation approach in case of blind restoration of barcode image. A novel approach to classify blur in motion, defocus, and co-existence of both blur categories is presented in this paper. The key idea involves statistical features extraction of blur pattern in frequency domain and designing of blur classification system with feed forward ...

  20. Image Retrieval via Relevance Vector Machine with Multiple Features

    Directory of Open Access Journals (Sweden)

    Zemin Liu

    2014-05-01

    Full Text Available With the fast development of computer network technique, there is large amount of image information every day. Researchers have paid more and more attention to the problem of how users quickly retrieving and identifying the images that they may interest. Meanwhile, with the rapid development of artificial intelligence and pattern recognition techniques, it provides people with new thought on the study on complex image retrieval while it’s very difficult for traditional machine learning method to get ideal retrieval results. For this reason, we in this paper propose a new approach for image retrieval based on multiple types of image features and relevance vector machine (RVM. The proposed method, termed as MF-RVM, integrates the informative cures of features and the discrimination ability of RVM. The retrieval experiment is conducted on COREL image library which is collected from internet. The experimental results show that the proposed method can significantly improve the performance for image retrieval, so MF-RVM presented in this paper has very high practicability in image retrieval.

  1. Geometrically invariant color image watermarking scheme using feature points

    Institute of Scientific and Technical Information of China (English)

    WANG XiangYang; MENG Lan; YANG HongYing

    2009-01-01

    Geometric distortion is known as one of the most difficult attacks to resist.Geometric distortion desynchronizes the location of the watermark and hence causes incorrect watermark detection.In this paper,we propose a geometrically invariant digital watermarking method for color images.In order to synchronize the location for watermark insertion and detection,we use a multi-scale Harris-Laplace detector,by which feature points of a color image can be extracted that are invariant to geometric distortions.Then,the self-adaptive local image region (LIR) detection based on the feature scale theory was considered for watermarking.At each local image region,the watermark is embedded after image normalization.By binding digital watermark with invariant image regions,resilience against geometric distortion can be readily obtained.Our method belongs to the category of blind watermarking techniques,because we do not need the original image during detection.Experimental results show that the proposed color image watermarking is not only invisible and robust against common signal processing such as sharpening,noise adding,and JPEG compression,but also robust against the geometric distortions such as rotation,translation,scaling,row or column removal,shearing,and local random bend.

  2. Feature analysis for detecting people from remotely sensed images

    Science.gov (United States)

    Sirmacek, Beril; Reinartz, Peter

    2013-01-01

    We propose a novel approach using airborne image sequences for detecting dense crowds and individuals. Although airborne images of this resolution range are not enough to see each person in detail, we can still notice a change of color and intensity components of the acquired image in the location where a person exists. Therefore, we propose a local feature detection-based probabilistic framework to detect people automatically. Extracted local features behave as observations of the probability density function (PDF) of the people locations to be estimated. Using an adaptive kernel density estimation method, we estimate the corresponding PDF. First, we use estimated PDF to detect boundaries of dense crowds. After that, using background information of dense crowds and previously extracted local features, we detect other people in noncrowd regions automatically for each image in the sequence. To test our crowd and people detection algorithm, we use airborne images taken over Munich during the Oktoberfest event, two different open-air concerts, and an outdoor festival. In addition, we apply tests on GeoEye-1 satellite images. Our experimental results indicate possible use of the algorithm in real-life mass events.

  3. Scene classification of infrared images based on texture feature

    Science.gov (United States)

    Zhang, Xiao; Bai, Tingzhu; Shang, Fei

    2008-12-01

    Scene Classification refers to as assigning a physical scene into one of a set of predefined categories. Utilizing the method texture feature is good for providing the approach to classify scenes. Texture can be considered to be repeating patterns of local variation of pixel intensities. And texture analysis is important in many applications of computer image analysis for classification or segmentation of images based on local spatial variations of intensity. Texture describes the structural information of images, so it provides another data to classify comparing to the spectrum. Now, infrared thermal imagers are used in different kinds of fields. Since infrared images of the objects reflect their own thermal radiation, there are some shortcomings of infrared images: the poor contrast between the objectives and background, the effects of blurs edges, much noise and so on. Because of these shortcomings, it is difficult to extract to the texture feature of infrared images. In this paper we have developed an infrared image texture feature-based algorithm to classify scenes of infrared images. This paper researches texture extraction using Gabor wavelet transform. The transformation of Gabor has excellent capability in analysis the frequency and direction of the partial district. Gabor wavelets is chosen for its biological relevance and technical properties In the first place, after introducing the Gabor wavelet transform and the texture analysis methods, the infrared images are extracted texture feature by Gabor wavelet transform. It is utilized the multi-scale property of Gabor filter. In the second place, we take multi-dimensional means and standard deviation with different scales and directions as texture parameters. The last stage is classification of scene texture parameters with least squares support vector machine (LS-SVM) algorithm. SVM is based on the principle of structural risk minimization (SRM). Compared with SVM, LS-SVM has overcome the shortcoming of

  4. Luminescent Silica Nanoparticles Featuring Collective Processes for Optical Imaging.

    Science.gov (United States)

    Rampazzo, Enrico; Prodi, Luca; Petrizza, Luca; Zaccheroni, Nelsi

    2016-01-01

    The field of nanoparticles has successfully merged with imaging to optimize contrast agents for many detection techniques. This combination has yielded highly positive results, especially in optical and magnetic imaging, leading to diagnostic methods that are now close to clinical use. Biological sciences have been taking advantage of luminescent labels for many years and the development of luminescent nanoprobes has helped definitively in making the crucial step forward in in vivo applications. To this end, suitable probes should present excitation and emission within the NIR region where tissues have minimal absorbance. Among several nanomaterials engineered with this aim, including noble metal, lanthanide, and carbon nanoparticles and quantum dots, we have focused our attention here on luminescent silica nanoparticles. Many interesting results have already been obtained with nanoparticles containing only one kind of photophysically active moiety. However, the presence of different emitting species in a single nanoparticle can lead to diverse properties including cooperative behaviours. We present here the state of the art in the field of silica luminescent nanoparticles exploiting collective processes to obtain ultra-bright units suitable as contrast agents in optical imaging and optical sensing and for other high sensitivity applications.

  5. MR Imaging Features of Obturator Internus Bursa of the Hip

    Energy Technology Data Exchange (ETDEWEB)

    Hwang, Ji Young; Lee, Sun Wha; Kim, Jong Oh [School of Medicine, Ewha Womans University, Seoul (Korea, Republic of)

    2008-08-15

    The authors report two cases with distension of the obturator internus bursa identified on MR images, and describe the location and characteristic features of obturator internus bursitis; the 'boomerang'-shaped fluid distension between the obturator internus tendon and the posterior grooved surface of the ischium

  6. Deep optical images of Malin 1 reveal new features

    CERN Document Server

    Galaz, Gaspar; Suc, Vincent; Busta, Luis; Lizana, Guadalupe; Infante, Leopoldo; Royo, Santiago

    2015-01-01

    We present Megacam deep optical images (g and r) of Malin 1 obtained with the 6.5m Magellan/Clay telescope, detecting structures down to ~ 28 B mag arcsec-2. In order to enhance galaxy features buried in the noise, we use a noise reduction filter based on the total generalized variation regularizator. This method allows us to detect and resolve very faint morphological features, including spiral arms, with a high visual contrast. For the first time, we can appreciate an optical image of Malin 1 and its morphology in full view. The images provide unprecedented detail, compared to those obtained in the past with photographic plates and CCD, including HST imaging. We detect two peculiar features in the disk/spiral arms. The analysis suggests that the first one is possibly a background galaxy, and the second is an apparent stream without a clear nature, but could be related to the claimed past interaction between Malin 1 and the galaxy SDSSJ123708.91 + 142253.2. Malin 1 exhibits features suggesting the presence o...

  7. Detection of fungal damaged popcorn using image property covariance features

    Science.gov (United States)

    Covariance-matrix-based features were applied to the detection of popcorn infected by a fungus that cause a symptom called “blue-eye.” This infection of popcorn kernels causes economic losses because of their poor appearance and the frequently disagreeable flavor of the popped kernels. Images of ker...

  8. Identification and Quantification Soil Redoximorphic Features by Digital Image Processing

    Science.gov (United States)

    Soil redoximorphic features (SRFs) have provided scientists and land managers with insight into relative soil moisture for approximately 60 years. The overall objective of this study was to develop a new method of SRF identification and quantification from soil cores using a digital camera and imag...

  9. Ovarian malignant germ cell tumors: cellular classification and clinical and imaging features.

    Science.gov (United States)

    Shaaban, Akram M; Rezvani, Maryam; Elsayes, Khaled M; Baskin, Henry; Mourad, Amr; Foster, Bryan R; Jarboe, Elke A; Menias, Christine O

    2014-01-01

    Ovarian malignant germ cell tumors (OMGCTs) are heterogeneous tumors that are derived from the primitive germ cells of the embryonic gonad. OMGCTs are rare, accounting for about 2.6% of all ovarian malignancies, and typically manifest in adolescence, usually with abdominal pain, a palpable mass, and elevated serum tumor marker levels, which may serve as an adjunct in the initial diagnosis, monitoring during therapy, and posttreatment surveillance. Dysgerminoma, the most common malignant germ cell tumor, usually manifests as a solid mass. Immature teratomas manifest as a solid mass with scattered foci of fat and calcifications. Yolk sac tumors usually manifest as a mixed solid and cystic mass. Capsular rupture or the bright dot sign, a result of increased vascularity and the formation of small vascular aneurysms, may be present. Embryonal carcinomas and polyembryomas rarely manifest in a pure form and are more commonly part of a mixed germ cell tumor. Some OMGCTs have characteristic features that allow a diagnosis to be confidently made, whereas others have nonspecific features, which make them difficult to diagnose. However, imaging features, the patient's age at presentation, and tumor markers may help establish a reasonable differential diagnosis. Malignant ovarian germ cell tumors spread in the same manner as epithelial ovarian neoplasms but are more likely to involve regional lymph nodes. Preoperative imaging may depict local extension, peritoneal disease, and distant metastases. Suspicious areas may be sampled during surgery. Because OMGCTs are almost always unilateral and are chemosensitive, fertility-sparing surgery is the standard of care. PMID:24819795

  10. Imaging features of multicentric Castleman's disease in HIV infection

    International Nuclear Information System (INIS)

    AIM: To describe the computed tomography (CT) features of human immunodeficiency virus (HIV)-associated Castleman's disease. MATERIALS AND METHODS: Nine HIV-positive patients with biopsy-proven Castleman's disease were studied. Clinical and demographic data, CD4 count, histological diagnosis and human herpes type 8 (HHV8) serology or immunostaining results were recorded. CT images were reviewed independently by two radiologists. RESULTS: CT findings included splenomegaly (n=7) and peripheral lymph node enlargement (axillary n=8, inguinal n=4). All nodes displayed mild to avid enhancement after intravenous administration of contrast material. Hepatomegaly was evident in seven patients. Other features included abdominal (n=6) and mediastinal (n=5) lymph node enlargement and pulmonary abnormalities (n=4). Patterns of parenchymal abnormality included bronchovascular nodularity (n=2), consolidation (n=1) and pleural effusion (n=2). On histological examination eight patients (spleen n=3, lymph node n=9, lung n=1 bone marrow n=1) had the plasma cell variant and one had mixed hyaline-vascular/plasma cell variant. The majority had either positive immunostaining for HHV8 or positive serology (n=8). CONCLUSION: Common imaging features of multicentric Castleman's disease in HIV infection are hepatosplenomegaly and peripheral lymph node enlargement. Although these imaging features may suggest the diagnosis in the appropriate clinical context, they lack specificity and so biopsy is needed for diagnosis. In distinction from multicentric Castleman's disease in other populations the plasma cell variant is most commonly encountered, splenomegaly is a universal feature and there is a strong association with Kaposi's sarcoma

  11. Diffusion tensor image registration using tensor geometry and orientation features.

    Science.gov (United States)

    Yang, Jinzhong; Shen, Dinggang; Davatzikos, Christos; Verma, Ragini

    2008-01-01

    This paper presents a method for deformable registration of diffusion tensor (DT) images that integrates geometry and orientation features into a hierarchical matching framework. The geometric feature is derived from the structural geometry of diffusion and characterizes the shape of the tensor in terms of prolateness, oblateness, and sphericity of the tensor. Local spatial distributions of the prolate, oblate, and spherical geometry are used to create an attribute vector of geometric feature for matching. The orientation feature improves the matching of the WM fiber tracts by taking into account the statistical information of underlying fiber orientations. These features are incorporated into a hierarchical deformable registration framework to develop a diffusion tensor image registration algorithm. Extensive experiments on simulated and real brain DT data establish the superiority of this algorithm for deformable matching of diffusion tensors, thereby aiding in atlas creation. The robustness of the method makes it potentially useful for group-based analysis of DT images acquired in large studies to identify disease-induced and developmental changes. PMID:18982691

  12. Cuckoo search algorithm based satellite image contrast and brightness enhancement using DWT-SVD.

    Science.gov (United States)

    Bhandari, A K; Soni, V; Kumar, A; Singh, G K

    2014-07-01

    This paper presents a new contrast enhancement approach which is based on Cuckoo Search (CS) algorithm and DWT-SVD for quality improvement of the low contrast satellite images. The input image is decomposed into the four frequency subbands through Discrete Wavelet Transform (DWT), and CS algorithm used to optimize each subband of DWT and then obtains the singular value matrix of the low-low thresholded subband image and finally, it reconstructs the enhanced image by applying IDWT. The singular value matrix employed intensity information of the particular image, and any modification in the singular values changes the intensity of the given image. The experimental results show superiority of the proposed method performance in terms of PSNR, MSE, Mean and Standard Deviation over conventional and state-of-the-art techniques. PMID:24893835

  13. Moment feature based fast feature extraction algorithm for moving object detection using aerial images.

    Directory of Open Access Journals (Sweden)

    A F M Saifuddin Saif

    Full Text Available Fast and computationally less complex feature extraction for moving object detection using aerial images from unmanned aerial vehicles (UAVs remains as an elusive goal in the field of computer vision research. The types of features used in current studies concerning moving object detection are typically chosen based on improving detection rate rather than on providing fast and computationally less complex feature extraction methods. Because moving object detection using aerial images from UAVs involves motion as seen from a certain altitude, effective and fast feature extraction is a vital issue for optimum detection performance. This research proposes a two-layer bucket approach based on a new feature extraction algorithm referred to as the moment-based feature extraction algorithm (MFEA. Because a moment represents the coherent intensity of pixels and motion estimation is a motion pixel intensity measurement, this research used this relation to develop the proposed algorithm. The experimental results reveal the successful performance of the proposed MFEA algorithm and the proposed methodology.

  14. New learning subspace method for image feature extraction

    Institute of Scientific and Technical Information of China (English)

    CAO Jian-hai; LI Long; LU Chang-hou

    2006-01-01

    A new method of Windows Minimum/Maximum Module Learning Subspace Algorithm(WMMLSA) for image feature extraction is presented. The WMMLSM is insensitive to the order of the training samples and can regulate effectively the radical vectors of an image feature subspace through selecting the study samples for subspace iterative learning algorithm,so it can improve the robustness and generalization capacity of a pattern subspace and enhance the recognition rate of a classifier. At the same time,a pattern subspace is built by the PCA method. The classifier based on WMMLSM is successfully applied to recognize the pressed characters on the gray-scale images. The results indicate that the correct recognition rate on WMMLSM is higher than that on Average Learning Subspace Method,and that the training speed and the classification speed are both improved. The new method is more applicable and efficient.

  15. Uranus' Persistent Patterns and Features from High-SNR Imaging in 2012-2014

    Science.gov (United States)

    Fry, Patrick M.; Sromovsky, Lawrence A.; de Pater, Imke; Hammel, Heidi B.; Marcus, Phillip

    2015-11-01

    Since 2012, Uranus has been the subject of an observing campaign utilizing high signal-to-noise imaging techniques at Keck Observatory (Fry et al. 2012, Astron. J. 143, 150-161). High quality observing conditions on four observing runs of consecutive nights allowed longitudinally-complete coverage of the atmosphere over a period of two years (Sromovsky et al. 2015, Icarus 258, 192-223). Global mosaic maps made from images acquired on successive nights in August 2012, November 2012, August 2013, and August 2014, show persistent patterns, and six easily distinguished long-lived cloud features, which we were able to track for long periods that ranged from 5 months to over two years. Two at similar latitudes are associated with dark spots, and move with the atmospheric zonal flow close to the location of their associated dark spot instead of following the flow at the latitude of the bright features. These features retained their morphologies and drift rates in spite of several close interactions. A second pair of features at similar latitudes also survived several close approaches. Several of the long-lived features also exhibited equatorward drifts and latitudinal oscillations. Also persistent are a remarkable near-equatorial wave feature and global zonal band structure. We will present imagery, maps, and analyses of these phenomena.PMF and LAS acknowledge support from NASA Planetary Astronomy Program; PMF and LAS acknowledge funding and technical support from W. M. Keck Observatory. We thank those of Hawaiian ancestry on whose sacred mountain we are privileged to be guests. Without their generous hospitality none of our groundbased observations would have been possible.

  16. TOPOGRAPHIC FEATURE EXTRACTION FOR BENGALI AND HINDI CHARACTER IMAGES

    Directory of Open Access Journals (Sweden)

    Soumen Bag

    2011-06-01

    Full Text Available Feature selection and extraction plays an important role in different classification based problems such as face recognition, signature verification, optical character recognition (OCR etc. The performance of OCR highly depends on the proper selection and extraction of feature set. In this paper, we present novel features based on the topography of a character as visible from different viewing directions on a 2D plane. By topography of a character we mean the structural features of the strokes and their spatial relations. In this work we develop topographic features of strokes visible with respect to views from different directions (e.g. North, South, East, and West. We consider three types of topographic features: closed region, convexity of strokes, and straight line strokes. These features are represented as a shapebased graph which acts as an invariant feature set for discriminating very similar type characters efficiently. We have tested the proposed method on printed and handwritten Bengali and Hindi character images. Initial results demonstrate the efficacy of our approach.

  17. Topographic Feature Extraction for Bengali and Hindi Character Images

    Directory of Open Access Journals (Sweden)

    Soumen Bag

    2011-09-01

    Full Text Available Feature selection and extraction plays an important role in different classification based problems such as face recognition, signature verification, optical character recognition (OCR etc. The performance of OCR highly depends on the proper selection and extraction of feature set. In this paper, we present novel features based on the topography of a character as visible from different viewing directions on a 2D plane. By topography of a character we mean the structural features of the strokes and their spatial relations. In this work we develop topographic features of strokes visible with respect to views from different directions (e.g. North, South, East, and West. We consider three types of topographic features: closed region, convexity of strokes, and straight line strokes. These features are represented as a shapebased graph which acts as an invariant feature set for discriminating very similar type characters efficiently. We have tested the proposed method on printed and handwritten Bengali and Hindi character images. Initial results demonstrate the efficacy of our approach.

  18. Single Image Superresolution via Directional Group Sparsity and Directional Features.

    Science.gov (United States)

    Li, Xiaoyan; He, Hongjie; Wang, Ruxin; Tao, Dacheng

    2015-09-01

    Single image superresolution (SR) aims to construct a high-resolution version from a single low-resolution (LR) image. The SR reconstruction is challenging because of the missing details in the given LR image. Thus, it is critical to explore and exploit effective prior knowledge for boosting the reconstruction performance. In this paper, we propose a novel SR method by exploiting both the directional group sparsity of the image gradients and the directional features in similarity weight estimation. The proposed SR approach is based on two observations: 1) most of the sharp edges are oriented in a limited number of directions and 2) an image pixel can be estimated by the weighted averaging of its neighbors. In consideration of these observations, we apply the curvelet transform to extract directional features which are then used for region selection and weight estimation. A combined total variation regularizer is presented which assumes that the gradients in natural images have a straightforward group sparsity structure. In addition, a directional nonlocal means regularization term takes pixel values and directional information into account to suppress unwanted artifacts. By assembling the designed regularization terms, we solve the SR problem of an energy function with minimal reconstruction error by applying a framework of templates for first-order conic solvers. The thorough quantitative and qualitative results in terms of peak signal-to-noise ratio, structural similarity, information fidelity criterion, and preference matrix demonstrate that the proposed approach achieves higher quality SR reconstruction than the state-of-the-art algorithms.

  19. Document image retrieval based on multi-density features

    Institute of Scientific and Technical Information of China (English)

    HU Zhilan; LIN Xinggang; YAN Hong

    2007-01-01

    The development of document image databases is becoming a challenge for document image retrieval techniques.Traditional layout-reconstructed-based methods rely on high quality document images as well as an optical character recognition (OCR) precision,and can only deal with several widely used languages.The complexity of document layouts greatly hinders layout analysis-based approaches.This paper describes a multi-density feature based algorithm for binary document images,which is independent of OCR or layout analyses.The text area was extracted after preprocessing such as skew correction and marginal noise removal.Then the aspect ratio and multi-density features were extracted from the text area to select the best candidates from the document image database.Experimental results show that this approach is simple with loss rates less than 3% and can efficiently analyze images with different resolutions and different input systems.The system is also robust to noise due to its notes and complex layouts,etc.

  20. Angular Variation of Solar Feature Contrast in Full-Disk G-Band Images

    Science.gov (United States)

    Blunt, Sarah Caroline; Criscuoli, Serena; Ermolli, Ilaria; Giorgi, Fabrizio

    2015-01-01

    We investigate the center-to-limb variation (CLV) of the contrasts of four types of solar surface features observed in the G-Band (430.6 nm, FWHM 1.2 nm) by analyzing 12 high quality full-disk images obtained from the Rome Precision Solar Photometric Telescope. The studied features, specifically network, enhanced network, plage, and bright plage, were singled out based on their brightness signatures in mean simultaneous Ca II K images using an intensity threshold technique. We compared our results with those obtained from high-resolution (HR) observations, and with the outputs of the spectral synthesis performed on semi-empirical models and magneto hydrodynamic (MHD) simulations. We find that the measured contrasts are systematically lower than those of HR observational results, as was expected due to the lower resolution of the analyzed observations. We also find that our observations best reflect the CLV derived from the recent one-dimensional atmospheric models described in Fontenla et al 2011 with respect to results obtained from earlier similar models. The measured CLV also agrees with those derived from the syntheses of MHD simulations and HR observations, if spatial resolution effects are properly taken into account. This work was carried out through the National Solar Observatory Summer Research Assistantship (SRA) Program. The National Solar Observatory is operated by the Association of Universities for Research in Astronomy, Inc. (AURA) under cooperative agreement with the National Science Foundation. This work was also partially supported by the European Union's Seventh Programme for Research, Technological Development and Demonstration under the grant agreements in 312495 (SOLARNET) and 313188 (SOLID).

  1. A flower image retrieval method based on ROI feature

    Institute of Scientific and Technical Information of China (English)

    洪安祥; 陈刚; 李均利; 池哲儒; 张亶

    2004-01-01

    Flower image retrieval is a very important step for computer-aided plant species recognition.In this paper,we propose an efficient segmentation method based on color clustering and domain knowledge to extract flower regions from flower images.For flower retrieval,we use the color histogram of a flower region to characterize the color features of flower and two shape-based features sets,Centroid-Contour Distance(CCD)and Angle Code Histogram(ACH),to characterize the shape features of a flower contour.Experimental results showed that our flower region extraction method based on color clustering and domain knowledge can produce accurate flower regions.Flower retrieval results on a database of 885 flower images collected from 14 plant species showed that our Region-of-Interest(ROD based retrieval approach using both color and shape features can perform better than a method based on the global color histogram proposed by Swain and Ballard(1991)and a method based on domain knowledge-driven segmentation and color names proposed by Das et al.(1999).

  2. A flower image retrieval method based on ROI feature

    Institute of Scientific and Technical Information of China (English)

    洪安祥; 陈刚; 李均利; 池哲儒; 张亶

    2004-01-01

    Flower image retrieval is a very important step for computer-aided plant species recognition. In this paper, we propose an efficient segmentation method based on color clustering and domain knowledge to extract flower regions from flower images. For flower retrieval, we use the color histogram of a flower region to characterize the color features of flower and two shape-based features sets, Centroid-Contour Distance (CCD) and Angle Code Histogram (ACH), to characterize the shape features of a flower contour. Experimental results showed that our flower region extraction method based on color clustering and domain knowledge can produce accurate flower regions. Flower retrieval results on a database of 885 flower images collected from 14 plant species showed that our Region-of-Interest (ROI) based retrieval approach using both color and shape features can perform better than a method based on the global color histogram proposed by Swain and Ballard (1991) and a method based on domain knowledge-driven segmentation and color names proposed by Das et al.(1999).

  3. Image recognition of diseased rice seeds based on color feature

    Science.gov (United States)

    Cheng, Fang; Ying, Yibin

    2004-11-01

    The objective of this research is to develop a digital image analysis algorithm for detection of diseased rice seeds based on color features. The rice seeds used for this study involved five varieties of Jinyou402, Shanyou10, Zhongyou207, Jiayou99 and IIyou3207. Images of rice seeds were acquired with a color machine vision system. Each original RGB image was converted to HSV color space and preprocessed to show, as hue in the seed region while the pixels value of background was zero. The hue values were scaled so that they varied from 0.0 to 1.0. Then six color features were extracted and evaluated for their contributions to seed classification. Determined using Blocks method, the mean hue value shows the strongest classification ability. Parzen windowing function method was used to estimate probability density distribution and a threshold of mean hue was drawn to classify normal seeds and diseased seeds. The average accuracy of test data set is 95% for Jinyou402. Then the feature of hue histogram was extracted for diseased seeds and partitioned into two clusters of spot diseased seeds and severe diseased seeds. Desired results were achieved when the two cancroids locations were used to discriminate the disease degree. Combined with the two features of mean hue and histogram, all seeds could be classified as normal seeds, spot diseased seeds and severe diseased seeds. Finally, the algorithm was implemented for all the five varieties to test the adaptability.

  4. Imaging features of Benign fibrous histiocytoma of bone

    International Nuclear Information System (INIS)

    Objective: To evaluate the imaging features of benign fibrous histiocytoma (BFH). Methods: Imaging data were retrospectively collected and reviewed in 11 patients with pathologically proved BFH. Of the 11 patients, X-ray was performed in all patients,MR scans in 6 patients, and CT scans in 4 patients. Results: All lesions detected were a solitary lesion.The distribution of BFH was in the tibia (n=5), femur (n=3), fibula (n=1), sacrum (n=1), and thoracic vertebrae (n=1). X-ray features included eccentric osteolytic lesions in 7 patients and centric in 2 patients, with clear boundary and thinning of the cortex, and 7 patients with varying degrees of ossified border were found. CT scan shows bone destruction with density similar to soft tissue. The majority of lesions (n=3) were observed in the expanding shell of bone, 2 patients in the tibia and 1 patient in the thoracic lesions with cortical bone perforation. The thoracic lesion as soft tissue mass was detected. All of the lesions detected in CT showed no periosteal reaction. In patients with MR images, hypo to isointense signal intensity on T1WI and hyperintense signal intensity on T2WI was found. All lesions on post-contrast T1WI were detected with homogeneous or heterogeneous lesion with moderate or significant enhancement. Conclusion: Imaging features were typical for MFH which is useful tool helping correct diagnosis of MFH. (authors)

  5. Quantitative imaging features to predict cancer status in lung nodules

    Science.gov (United States)

    Liu, Ying; Balagurunathan, Yoganand; Atwater, Thomas; Antic, Sanja; Li, Qian; Walker, Ronald; Smith, Gary T.; Massion, Pierre P.; Schabath, Matthew B.; Gillies, Robert J.

    2016-03-01

    Background: We propose a systematic methodology to quantify incidentally identified lung nodules based on observed radiological traits on a point scale. These quantitative traits classification model was used to predict cancer status. Materials and Methods: We used 102 patients' low dose computed tomography (LDCT) images for this study, 24 semantic traits were systematically scored from each image. We built a machine learning classifier in cross validation setting to find best predictive imaging features to differentiate malignant from benign lung nodules. Results: The best feature triplet to discriminate malignancy was based on long axis, concavity and lymphadenopathy with average AUC of 0.897 (Accuracy of 76.8%, Sensitivity of 64.3%, Specificity of 90%). A similar semantic triplet optimized on Sensitivity/Specificity (Youden's J index) included long axis, vascular convergence and lymphadenopathy which had an average AUC of 0.875 (Accuracy of 81.7%, Sensitivity of 76.2%, Specificity of 95%). Conclusions: Quantitative radiological image traits can differentiate malignant from benign lung nodules. These semantic features along with size measurement enhance the prediction accuracy.

  6. Estimating perception of scene layout properties from global image features.

    Science.gov (United States)

    Ross, Michael G; Oliva, Aude

    2010-01-08

    The relationship between image features and scene structure is central to the study of human visual perception and computer vision, but many of the specifics of real-world layout perception remain unknown. We do not know which image features are relevant to perceiving layout properties, or whether those features provide the same information for every type of image. Furthermore, we do not know the spatial resolutions required for perceiving different properties. This paper describes an experiment and a computational model that provides new insights on these issues. Humans perceive the global spatial layout properties such as dominant depth, openness, and perspective, from a single image. This work describes an algorithm that reliably predicts human layout judgments. This model's predictions are general, not specific to the observers it trained on. Analysis reveals that the optimal spatial resolutions for determining layout vary with the content of the space and the property being estimated. Openness is best estimated at high resolution, depth is best estimated at medium resolution, and perspective is best estimated at low resolution. Given the reliability and simplicity of estimating the global layout of real-world environments, this model could help resolve perceptual ambiguities encountered by more detailed scene reconstruction schemas.

  7. Content Based Image Retrieval using Color Boosted Salient Points and Shape features of an image.

    Directory of Open Access Journals (Sweden)

    Hiremath P. S

    2008-02-01

    Full Text Available Salient points are locations in an image where there is a significant variation withrespect to a chosen image feature. Since the set of salient points in an imagecapture important local characteristics of that image, they can form the basis of agood image representation for content-based image retrieval (CBIR. Salientfeatures are generally determined from the local differential structure of images.They focus on the shape saliency of the local neighborhood. Most of thesedetectors are luminance based which have the disadvantage that thedistinctiveness of the local color information is completely ignored in determiningsalient image features. To fully exploit the possibilities of salient point detection incolor images, color distinctiveness should be taken into account in addition toshape distinctiveness. This paper presents a method for salient pointsdetermination based on color saliency. The color and texture information aroundthese points of interest serve as the local descriptors of the image. In addition,the shape information is captured in terms of edge images computed usingGradient Vector Flow fields. Invariant moments are then used to record theshape features. The combination of the local color, texture and the global shapefeatures provides a robust feature set for image retrieval. The experimentalresults demonstrate the efficacy of the method.

  8. Active Detection and Imaging of Nuclear Materials with High-Brightness Gamma Rays

    Energy Technology Data Exchange (ETDEWEB)

    Barty, C J; Gibson, D J; Albert, F; Anderson, S G; Anderson, G G; Betts, S M; Berry, R D; Fisher, S E; Hagmann, C A; Johnson, M S; Messerly, M J; Phan, H H; Semenov, V A; Shverdin, M Y; Tremaine, A M; Hartemann, F V; Siders, C W; McNabb, D P

    2009-02-26

    A Compton scattering {gamma}-ray source, capable of producing photons with energies ranging from 0.1 MeV to 0.9 MeV has been commissioned and characterized, and then used to perform nuclear resonance fluorescence (NRF) experiments. The performances of the two laser systems (one for electron production, one for scattering), the electron photoinjector, and the linear accelerator are also detailed, and {gamma}-ray results are presented. The key source parameters are the size (0.01 mm{sup 2}), horizontal and vertical divergence (6 x 10 mrad{sup 2}), duration (10 ps), spectrum and intensity (10{sup 5} photons/shot). These parameters are summarized by the peak brightness, 1.5 x 10{sup 15} photons/mm{sup 2}/mrad{sup 2}/s/0.1% bandwidth, measured at 478 keV. Additional measurements of the flux as a function of the timing difference between the drive laser pulse and the relativistic photo-electron bunch, {gamma}-ray beam profile, and background evaluations are presented. These results are systematically compared to theoretical models and computer simulations. NRF measurements performed on {sup 7}Li in LiH demonstrate the potential of Compton scattering photon sources to accurately detect isotopes in situ.

  9. Deep Optical Images of Malin 1 Reveal New Features

    Science.gov (United States)

    Galaz, Gaspar; Milovic, Carlos; Suc, Vincent; Busta, Luis; Lizana, Guadalupe; Infante, Leopoldo; Royo, Santiago

    2015-12-01

    We present Megacam deep optical images (g and r) of Malin 1 obtained with the 6.5 m Magellan/Clay telescope, detecting structures down to ˜28 B mag arcsec-2. In order to enhance galaxy features buried in the noise, we use a noise reduction filter based on the total generalized variation regularizator. This method allows us to detect and resolve very faint morphological features, including spiral arms, with a high visual contrast. For the first time, we can appreciate an optical image of Malin 1 and its morphology in full view. The images provide unprecedented detail, compared to those obtained in the past with photographic plates and CCD, including Hubble Space Telescope imaging. We detect two peculiar features in the disk/spiral arms. The analysis suggests that the first one is possibly a background galaxy, and the second is an apparent stream without a clear nature, but could be related to the claimed past interaction between Malin 1 and the galaxy SDSSJ123708.91+142253.2. Malin 1 exhibits features suggesting the presence of stellar associations and clumps of molecular gas, not seen before with such a clarity. Using these images, we obtain a diameter for Malin 1 of 160 kpc, ˜50 kpc larger than previous estimates. A simple analysis shows that the observed spiral arms reach very low luminosity and mass surface densities, to levels much lower than the corresponding values for the Milky Way. This paper includes data gathered with the 6.5 meter Magellan Telescopes located at Las Campanas Observatory, Chile.

  10. Electronic image stabilization system based on global feature tracking

    Institute of Scientific and Technical Information of China (English)

    Zhu Juanjuan; Guo Baolong

    2008-01-01

    A new robust electronic image stabilization system is presented, which involves feature-point, tracking based global motion estimation and Kalman filtering based motion compensation. First, global motion is estimated from the local motions of selected feature points. Considering the local moving objects or the inevitable mismatch,the matching validation, based on the stable relative distance between the points set is proposed, thus maintaining high accuracy and robustness. Next, the global motion parameters are accumulated for correction by Kalman filter-ation. The experimental result illustrates that the proposed system is effective to stabilize translational, rotational,and zooming jitter and robust to local motions.

  11. Incorporating global information in feature-based multimodal image registration

    Science.gov (United States)

    Li, Yong; Stevenson, Robert

    2014-03-01

    A multimodal image registration framework based on searching the best matched keypoints and the incorporation of global information is proposed. It comprises two key elements: keypoint detection and an iterative process. Keypoints are detected from both the reference and test images. For each test keypoint, a number of reference keypoints are chosen as mapping candidates. A triplet of keypoint mappings determine an affine transformation that is evaluated using a similarity metric between the reference image and the transformed test image by the determined transformation. An iterative process is conducted on triplets of keypoint mappings, keeping track of the best matched reference keypoint. Random sample consensus and mutual information are applied to eliminate outlier keypoint mappings. The similarity metric is defined to be the number of overlapped edge pixels over the entire images, allowing for global information to be incorporated in the evaluation of triplets of mappings. The performance of the framework is investigated with keypoints extracted by scale invariant feature transform and partial intensity invariant feature descriptor. Experimental results show that the proposed framework can provide more accurate registration than existing methods.

  12. SAR Data Fusion Imaging Method Oriented to Target Feature Extraction

    Directory of Open Access Journals (Sweden)

    Yang Wei

    2015-02-01

    Full Text Available To deal with the difficulty for target outlines extracting precisely due to neglect of target scattering characteristic variation during the processing of high-resolution space-borne SAR data, a novel fusion imaging method is proposed oriented to target feature extraction. Firstly, several important aspects that affect target feature extraction and SAR image quality are analyzed, including curved orbit, stop-and-go approximation, atmospheric delay, and high-order residual phase error. Furthermore, the corresponding compensation methods are addressed as well. Based on the analysis, the mathematical model of SAR echo combined with target space-time spectrum is established for explaining the space-time-frequency change rule of target scattering characteristic. Moreover, a fusion imaging strategy and method under high-resolution and ultra-large observation angle range conditions are put forward to improve SAR quality by fusion processing in range-doppler and image domain. Finally, simulations based on typical military targets are used to verify the effectiveness of the fusion imaging method.

  13. Primary Neuroendocrine Tumor of the Breast: Imaging Features

    Energy Technology Data Exchange (ETDEWEB)

    Chang, Eun Deok [Department of Clinical Pathology, Uijeongbu St. Mary' s Hospital, College of Medicine, The Catholic University of Korea, Uijeongbu 480-717 (Korea, Republic of); Kim, Min Kyun [Department of Radiology, Uijeongbu St. Mary' s Hospital, College of Medicine, The Catholic University of Korea, Uijeongbu 480-717 (Korea, Republic of); Kim, Jeong Soo [Department of Surgery, Uijeongbu St. Mary' s Hospital, College of Medicine, The Catholic University of Korea, Uijeongbu 480-717 (Korea, Republic of); Whang, In Yong [Department of Radiology, Uijeongbu St. Mary' s Hospital, College of Medicine, The Catholic University of Korea, Uijeongbu 480-717 (Korea, Republic of)

    2013-07-01

    Focal neuroendocrine differentiation can be found in diverse histological types of breast tumors. However, the term, neuroendocrine breast tumor, indicates the diffuse expression of neuroendocrine markers in more than 50% of the tumor cell population. The imaging features of neuroendocrine breast tumor have not been accurately described due to extreme rarity of this tumor type. We present a case of a pathologically confirmed, primary neuroendocrine breast tumor in a 42-year-old woman, with imaging findings difficult to be differentiated from that of invasive ductal carcinoma.

  14. Imaging features of benign and malignant ampullary and periampullary lesions.

    Science.gov (United States)

    Nikolaidis, Paul; Hammond, Nancy A; Day, Kevin; Yaghmai, Vahid; Wood, Cecil G; Mosbach, David S; Harmath, Carla B; Taffel, Myles T; Horowitz, Jeanne M; Berggruen, Senta M; Miller, Frank H

    2014-01-01

    The ampulla of Vater is an important anatomic landmark where the common bile duct and main pancreatic duct converge in the major duodenal papilla. Imaging evaluation of the ampulla and periampullary region poses a unique diagnostic challenge to radiologists because of the region's complex and variable anatomy and the variety of lesions that can occur. Lesions intrinsic to the ampulla and involved segment of the biliary tree can be neoplastic, inflammatory, or congenital. Neoplastic lesions include ampullary adenocarcinomas and adenomas, which often are difficult to differentiate, as well as pancreatic or duodenal adenocarcinomas, pancreatic neuroendocrine tumors, and cholangiocarcinomas. Ultrasonography (US), computed tomography, magnetic resonance (MR) imaging, and MR cholangiopancreatography are commonly used to evaluate this region. Endoscopic retrograde cholangiopancreatography or endoscopic US examination may be necessary for more definitive evaluation. Periampullary conditions in the duodenum that may secondarily involve the ampulla include neoplasms, duodenitis, duodenal diverticula, and Brunner's gland hyperplasia or hamartomas. Because these lesions can exhibit a wide overlap of imaging features and subtle or nonspecific imaging findings, diagnosis is made on the basis of patient age, clinical history, and imaging and laboratory findings. Given the complexity of imaging evaluation of the ampulla and periampullary region, it is essential for radiologists to understand the variety of lesions that can occur and recognize their imaging characteristics. PMID:24819785

  15. FluoroMyelin™ Red is a bright, photostable and non-toxic fluorescent stain for live imaging of myelin.

    Science.gov (United States)

    Monsma, Paula C; Brown, Anthony

    2012-08-15

    FluoroMyelin™ Red is a commercially available water-soluble fluorescent dye that has selectivity for myelin. This dye is marketed for the visualization of myelin in brain cryosections, though it is also used widely to stain myelin in chemically fixed tissue. Here we have investigated the suitability of FluoroMyelin™ Red as a vital stain for live imaging of myelin in myelinating co-cultures of Schwann cells and dorsal root ganglion neurons. We show that addition of FluoroMyelin™ Red to the culture medium results in selective staining of myelin sheaths, with an optimal staining time of 2h, and has no apparent adverse effect on the neurons, their axons, or the myelinating cells at the light microscopic level. The fluorescence is bright and photostable, permitting long-term time-lapse imaging. After rinsing the cultures with medium lacking FluoroMyelin™ Red, the dye diffuses out of the myelin with a half life of about 130 min resulting in negligible fluorescence remaining after 18-24h. In addition, the large Stokes shift exhibited by FluoroMyelin™ Red makes it possible to readily distinguish it from popular and widely used green and red fluorescent probes such as GFP and mCherry. Thus FluoroMyelin™ Red is a useful reagent for live fluorescence imaging studies on myelinated axons.

  16. AKARI Near- to Mid-Infrared Imaging and Spectroscopic Observations of the Small Magellanic Cloud. I. Bright Point Source List

    CERN Document Server

    Ita, Y; Tanabe, T; Matsunaga, N; Matsuura, M; Yamamura, I; Nakada, Y; Izumiura, H; Ueta, T; Mito, H; Fukushi, H; Kato, D

    2010-01-01

    We carried out a near- to mid-infrared imaging and spectroscopic observations of the patchy areas in the Small Magellanic Cloud using the Infrared Camera on board AKARI. Two 100 arcmin2 areas were imaged in 3.2, 4.1, 7, 11, 15, and 24 um and also spectroscopically observed in the wavelength range continuously from 2.5 to 13.4 um. The spectral resolving power (lambda/Delta lambda) is about 20, 50, and 50 at 3.5, 6.6 and 10.6 um, respectively. Other than the two 100 arcmin2 areas, some patchy areas were imaged and/or spectroscopically observed as well. In this paper, we overview the observations and present a list of near- to mid-infrared photometric results, which lists ~ 12,000 near-infrared and ~ 1,800 mid-infrared bright point sources detected in the observed areas. The 10 sigma limits are 16.50, 16.12, 13.28, 11.26, 9.62, and 8.76 in Vega magnitudes at 3.2, 4.1, 7, 11, 15, and 24 um bands, respectively.

  17. A bright cyan-excitable orange fluorescent protein facilitates dual-emission microscopy and enhances bioluminescence imaging in vivo.

    Science.gov (United States)

    Chu, Jun; Oh, Younghee; Sens, Alex; Ataie, Niloufar; Dana, Hod; Macklin, John J; Laviv, Tal; Welf, Erik S; Dean, Kevin M; Zhang, Feijie; Kim, Benjamin B; Tang, Clement Tran; Hu, Michelle; Baird, Michelle A; Davidson, Michael W; Kay, Mark A; Fiolka, Reto; Yasuda, Ryohei; Kim, Douglas S; Ng, Ho-Leung; Lin, Michael Z

    2016-07-01

    Orange-red fluorescent proteins (FPs) are widely used in biomedical research for multiplexed epifluorescence microscopy with GFP-based probes, but their different excitation requirements make multiplexing with new advanced microscopy methods difficult. Separately, orange-red FPs are useful for deep-tissue imaging in mammals owing to the relative tissue transmissibility of orange-red light, but their dependence on illumination limits their sensitivity as reporters in deep tissues. Here we describe CyOFP1, a bright, engineered, orange-red FP that is excitable by cyan light. We show that CyOFP1 enables single-excitation multiplexed imaging with GFP-based probes in single-photon and two-photon microscopy, including time-lapse imaging in light-sheet systems. CyOFP1 also serves as an efficient acceptor for resonance energy transfer from the highly catalytic blue-emitting luciferase NanoLuc. An optimized fusion of CyOFP1 and NanoLuc, called Antares, functions as a highly sensitive bioluminescent reporter in vivo, producing substantially brighter signals from deep tissues than firefly luciferase and other bioluminescent proteins. PMID:27240196

  18. Multiwavelets domain singular value features for image texture classification

    Institute of Scientific and Technical Information of China (English)

    RAMAKRISHNAN S.; SELVAN S.

    2007-01-01

    A new approach based on multiwavelets transformation and singular value decomposition (SVD) is proposed for the classification of image textures. Lower singular values are truncated based on its energy distribution to classify the textures in the presence of additive white Gaussian noise (AWGN). The proposed approach extracts features such as energy, entropy, local homogeneity and max-min ratio from the selected singular values of multiwavelets transformation coefficients of image textures.The classification was carried out using probabilistic neural network (PNN). Performance of the proposed approach was compared with conventional wavelet domain gray level co-occurrence matrix (GLCM) based features, discrete multiwavelets transformation energy based approach, and HMM based approach. Experimental results showed the superiority of the proposed algorithms when compared with existing algorithms.

  19. MR imaging features of peritoneal adenomatoid mesothelioma: a case report

    International Nuclear Information System (INIS)

    Adenomatoid mesothelioma of the peritoneum (AMP) is a rare benign tumor originating from mesothelial cells.1 Most frequently, AMP occurs between 26 and 55 years of age, at a mean age of 41 years. In contrast to diffuse malignant mesothelioma, which has been linked to asbestos exposure, the etiology of AMP has not been established. Only a minority of patients have symptoms related to the tumor. AMP may present local recurrence, but it has no potential for malignant transformation. Although there are many case reports of abdominal mesotheliomas, to date, there have been no reports of MR imaging features of AMP. In this article, we present the MR imaging features of a case of AMP with histopathological correlation. (author)

  20. MR imaging features of peritoneal adenomatoid mesothelioma: a case report

    Energy Technology Data Exchange (ETDEWEB)

    Lins, Cynthia Maria Coelho; Elias Junior, Jorge; Muglia, Valdair Francisco; Monteiro, Carlos Ribeiro [University of Sao Paulo (USP), Ribeirao Preto, SP (Brazil). School of Medicine. Dept. of Internal Medicine], e-mail: jejunior@fmrp.usp.br; Cunha, Adilson Ferreira [School of Medicine of Sao Jose do Rio Preto (FAMERP), SP (Brazil). Dept. of Gynecology and Obstetrics; Valeri, Fabio V. [Victorio Valeri Institute of Medical Diagnosis, Ribeirao Preto, SP (Brazil); Feres, Omar [University of Sao Paulo (USP), Ribeirao Preto, SP (Brazil). School of Medicine. Dept. of Surgery and Anatomy

    2009-07-01

    Adenomatoid mesothelioma of the peritoneum (AMP) is a rare benign tumor originating from mesothelial cells.1 Most frequently, AMP occurs between 26 and 55 years of age, at a mean age of 41 years. In contrast to diffuse malignant mesothelioma, which has been linked to asbestos exposure, the etiology of AMP has not been established. Only a minority of patients have symptoms related to the tumor. AMP may present local recurrence, but it has no potential for malignant transformation. Although there are many case reports of abdominal mesotheliomas, to date, there have been no reports of MR imaging features of AMP. In this article, we present the MR imaging features of a case of AMP with histopathological correlation. (author)

  1. Simultaneous fluorescence and high-resolution bright-field imaging with aberration correction over a wide field-of-view with Fourier ptychographic microscopy (FPM) (Conference Presentation)

    Science.gov (United States)

    Chung, Jaebum; Kim, Jinho; Ou, Xiaoze; Horstmeyer, Roarke; Yang, Changhuei

    2016-03-01

    We present a method to acquire both fluorescence and high-resolution bright-field images with correction for the spatially varying aberrations over a microscope's wide field-of-view (FOV). First, the procedure applies Fourier ptychographic microscopy (FPM) to retrieve the amplitude and phase of a sample, at a resolution that significantly exceeds the cutoff frequency of the microscope objective lens. At the same time, FPM algorithm is able to leverage on the redundancy within the set of acquired FPM bright-field images to estimate the microscope aberrations, which usually deteriorate in regions further away from the FOV's center. Second, the procedure acquires a raw wide-FOV fluorescence image within the same setup. Lack of moving parts allows us to use the FPM-estimated aberration map to computationally correct for the aberrations in the fluorescence image through deconvolution. Overlaying the aberration-corrected fluorescence image on top of the high-resolution bright-field image can be done with accurate spatial correspondence. This can provide means to identifying fluorescent regions of interest within the context of the sample's bright-field information. An experimental demonstration successfully improves the bright-field resolution of fixed, stained and fluorescently tagged HeLa cells by a factor of 4.9, and reduces the error caused by aberrations in a fluorescence image by 31%, over a field of view of 6.2 mm by 9.3 mm. For optimal deconvolution, we show the fluorescence image needs to have a signal-to-noise ratio of ~18.

  2. Spinal cord ischemia: aetiology, clinical syndromes and imaging features

    Energy Technology Data Exchange (ETDEWEB)

    Weidauer, Stefan [Frankfurt Univ., Sankt Katharinen Hospital Teaching Hospital, Frankfurt am Main (Germany). Dept. of Neurology; Hattingen, Elke; Berkefeld, Joachim [Frankfurt Univ., Frankfurt am Main (Germany). Inst. of Neuroradiology; Nichtweiss, Michael

    2015-03-01

    The purpose of this study was to analyse MR imaging features and lesion patterns as defined by compromised vascular territories, correlating them to different clinical syndromes and aetiological aspects. In a 19.8-year period, clinical records and magnetic resonance imaging (MRI) features of 55 consecutive patients suffering from spinal cord ischemia were evaluated. Aetiologies of infarcts were arteriosclerosis of the aorta and vertebral arteries (23.6 %), aortic surgery or interventional aneurysm repair (11 %) and aortic and vertebral artery dissection (11 %), and in 23.6 %, aetiology remained unclear. Infarcts occurred in 38.2 % at the cervical and thoracic level, respectively, and 49 % of patients suffered from centromedullar syndrome caused by anterior spinal artery ischemia. MRI disclosed hyperintense pencil-like lesion pattern on T2WI in 98.2 %, cord swelling in 40 %, enhancement on post-contrast T1WI in 42.9 % and always hyperintense signal on diffusion-weighted imaging (DWI) when acquired. The most common clinical feature in spinal cord ischemia is a centromedullar syndrome, and in contrast to anterior spinal artery ischemia, infarcts in the posterior spinal artery territory are rare. The exclusively cervical location of the spinal sulcal artery syndrome seems to be a likely consequence of anterior spinal artery duplication which is observed preferentially here. (orig.)

  3. Local features in natural images via singularity theory

    CERN Document Server

    Damon, James; Haslinger, Gareth

    2016-01-01

    This monograph considers a basic problem in the computer analysis of natural images, which are images of scenes involving multiple objects that are obtained by a camera lens or a viewer’s eye. The goal is to detect geometric features of objects in the image and to separate regions of the objects with distinct visual properties. When the scene is illuminated by a single principal light source, we further include the visual clues resulting from the interaction of the geometric features of objects, the shade/shadow regions on the objects, and the “apparent contours”. We do so by a mathematical analysis using a repertoire of methods in singularity theory. This is applied for generic light directions of both the “stable configurations” for these interactions, whose features remain unchanged under small viewer movement, and the generic changes which occur under changes of view directions. These may then be used to differentiate between objects and determine their shapes and positions.

  4. A Robust Technique for Feature-based Image Mosaicing using Image Fusion

    Directory of Open Access Journals (Sweden)

    Vimal Singh Bind, Priya Ranjan Muduli, Umesh Chandra Pati

    2013-03-01

    Full Text Available Since last few decades, image mosaicing in real timeapplications has been a challenging field for imageprocessing experts. It has wide applications in the field ofvideo conferencing, 3D imagereconstruction, satelliteimaging and several medical as well as computer visionfields. In this paper, we have proposed a feature basedimage mosaicing technique using image fusion. Initially,the input images are stitched together using the popularstitching algorithms i.e. Scale Invariant FeatureTransform (SIFT and Speeded-Up Robust Features(SURF. To extract the best features from the stitchingresults, the blending process is done by means of DiscreteWavelet Transform (DWT using the maximum selectionrule for both approximate as well as detail-components.The SIFT provides scale as well as rotational invarianceproperty. The SURF provides better computation speed andillumination invariance. The robustness and quality of theabove mosaicing techniques are tested by meansofthree-dimensionalrotational images.

  5. Feature Based Image Mosaic Using Steerable Filters and Harris Corner Detector

    OpenAIRE

    Mahesh; Subramanyam M .V

    2013-01-01

    Image mosaic is to be combine several views of a scene in to single wide angle view. This paper proposes the feature based image mosaic approach. The mosaic image system includes feature point detection, feature point descriptor extraction and matching. A RANSAC algorithm is applied to eliminate number of mismatches and obtain transformation matrix between the images. The input image is transformed with the correct mapping model for image stitching and same is estimated. In this paper, featur...

  6. Unusual acute encephalitis involving the thalamus: imaging features

    Energy Technology Data Exchange (ETDEWEB)

    Kim, Sam Soo [Kangwon National University Hospital, Chuncheon (Korea, Republic of); Chang, Kee Hyun; Kim, Kyung Won; Han Moon Hee [Seoul National University College of Medicine, Seoul (Korea, Republic of); Park, Sung Ho; Nam, Hyun Woo [Seoul City Boramae Hospital, Seoul (Korea, Republic of); Choi, Kyu Ho [Kangnam St. Mary' s Hospital, Seoul (Korea, Republic of); Cho, Woo Ho [Sanggyo Paik Hospital, Seoul (Korea, Republic of)

    2001-06-01

    To describe the brain CT and MR imaging findings of unusual acute encephalitis involving the thalamus. We retrospectively reviewed the medical records and CT and/or MR imaging findings of six patients with acute encephalitis involving the thalamus. CT (n=6) and MR imaging (n=6) were performed during the acute and/or convalescent stage of the illness. Brain CT showed brain swelling (n=2), low attenuation of both thalami (n=1) or normal findings (n=3). Initial MR imaging indicated that in all patients the thalamus was involved either bilaterally (n=5) or unilaterally (n=1). Lesions were also present in the midbrain (n=5), medial temporal lobe (n=4), pons (n=3), both hippocampi (n=3) the insular cortex (n=2), medulla (n=2), lateral temporal lobe cortex (n=1), both cingulate gyri (n=1), both basal ganglia (n=1), and the left hemispheric cortex (n=1). These CT or MR imaging findings of acute encephalitis of unknown etiology were similar to a combination of those of Japanese encephalitis and herpes simplex encephalitis. In order to document the specific causative agents which lead to the appearance of these imaging features, further investigation is required.

  7. MR imaging features of the congenital uterine anomalies

    International Nuclear Information System (INIS)

    Full text: Introduction: Congenital uterine anomalies are common and usually asymptomatic. The agenesis, malfusion or deficient resorption of the Mullerian canals during embryogenesis may lead to these anomalies. Although ultrasonography (US) is the first step imaging technique in assessment of the uterine pathologies, it can be insufficient in differentiation of them. Magnetic resonance (MR) imaging is an adequate imaging technique in depicting pelvic anatomy and different types of uterine anomalies. Objectives and tasks: In this article, we aimed to present imaging features of the uterine anomalies. Material and methods: Pelvic MR scans of the cases who were referred to our radiology department for suspicious uterine anomaly were evaluated retrospectively. Results: We determined uniconuate uterus (type II), uterus didelphys (type III), bicornuate uterus (type IV), uterine septum (type V) and arcuate uterus (type VI) anomalies according to ASRM (American Society of Reproductive Medicine) classification. Conclusion: In cases with such pathologies leading to obstruction, dysmenorrhea or palpable pelvic mass in the puberty are the main clinical presentations. In cases without obstruction, infertility or multiple abortions can be encountered in reproductive ages. The identification of the subtype of the uterine anomalies is important for the preoperative planning of the management. MR that has multiplanar imaging capability and high soft tissue resolution is a non-invasive and the most important imaging modality for the detection and classification of the uterine anomalies

  8. MR imaging features of focal liver lesions in Wilson disease.

    Science.gov (United States)

    Dohan, Anthony; Vargas, Ottavia; Dautry, Raphael; Guerrache, Youcef; Woimant, France; Hamzi, Lounis; Boudiaf, Mourad; Poujois, Aurelia; Faraoun, Sid Ahmed; Soyer, Philippe

    2016-09-01

    Hepatic involvement in Wilson disease (WD) manifests as a diffuse chronic disease in the majority of patients. However, in a subset of patients focal liver lesions may develop, presenting with a wide range of imaging features. The majority of focal liver lesions in patients with WD are benign nodules, but there are reports that have described malignant liver tumors or dysplastic nodules in these patients. Because of the possibility of malignant transformation of liver nodules, major concerns have been raised with respect to the management and follow-up of patients with WD in whom focal liver lesions have been identified. The assessment of liver involvement in patients with WD is generally performed with ultrasonography. However, ultrasonography conveys limited specificity so that magnetic resonance (MR) imaging is often performed to improve lesion characterization. This review was performed to illustrate the spectrum of MR imaging features of focal liver lesions that develop in patients with WD. It is assumed that familiarity with the MR imaging presentation of focal liver lesions in WD may help clarify the actual nature of hepatic nodules in patients with this condition.

  9. Imaging features of thoracic metastases from gynecologic neoplasms.

    Science.gov (United States)

    Martínez-Jiménez, Santiago; Rosado-de-Christenson, Melissa L; Walker, Christopher M; Kunin, Jeffery R; Betancourt, Sonia L; Shoup, Brenda L; Pettavel, Paul P

    2014-10-01

    Gynecologic malignancies are a heterogeneous group of common neoplasms and represent the fourth most common malignancy in women. Thoracic metastases exhibit various imaging patterns and are usually associated with locally invasive primary neoplasms with intra-abdominal spread. However, thoracic involvement may also occur many months to years after initial diagnosis or as an isolated finding in patients without evidence of intra-abdominal neoplastic involvement. Thoracic metastases from endometrial carcinoma typically manifest as pulmonary nodules and lymphadenopathy. Thoracic metastases from ovarian cancer often manifest with small pleural effusions and subtle pleural nodules. Thoracic metastases to the lungs, lymph nodes, and pleura may also exhibit calcification and mimic granulomatous disease. Metastases from fallopian tube carcinomas exhibit imaging features identical to those of ovarian cancers. Most cervical cancers are of squamous histology, and while solid pulmonary metastases are more common, cavitary metastases occur with some frequency. Metastatic choriocarcinoma to the lung characteristically manifests with solid pulmonary nodules. Some pulmonary metastases from gynecologic malignancies exhibit characteristic features such as cavitation (in squamous cell cervical cancer) and the "halo" sign (in hemorrhagic metastatic choriocarcinoma) at computed tomography (CT). However, metastases from common gynecologic malignancies may be subtle and indolent and may mimic benign conditions such as intrapulmonary lymph nodes and remote granulomatous disease. Therefore, radiologists should consider the presence of locoregional disease as well as elevated tumor marker levels when interpreting imaging studies because subtle imaging findings may represent metastatic disease. Positron emission tomography/CT may be helpful in identifying early locoregional and distant tumor spread. PMID:25310428

  10. MR imaging features of focal liver lesions in Wilson disease.

    Science.gov (United States)

    Dohan, Anthony; Vargas, Ottavia; Dautry, Raphael; Guerrache, Youcef; Woimant, France; Hamzi, Lounis; Boudiaf, Mourad; Poujois, Aurelia; Faraoun, Sid Ahmed; Soyer, Philippe

    2016-09-01

    Hepatic involvement in Wilson disease (WD) manifests as a diffuse chronic disease in the majority of patients. However, in a subset of patients focal liver lesions may develop, presenting with a wide range of imaging features. The majority of focal liver lesions in patients with WD are benign nodules, but there are reports that have described malignant liver tumors or dysplastic nodules in these patients. Because of the possibility of malignant transformation of liver nodules, major concerns have been raised with respect to the management and follow-up of patients with WD in whom focal liver lesions have been identified. The assessment of liver involvement in patients with WD is generally performed with ultrasonography. However, ultrasonography conveys limited specificity so that magnetic resonance (MR) imaging is often performed to improve lesion characterization. This review was performed to illustrate the spectrum of MR imaging features of focal liver lesions that develop in patients with WD. It is assumed that familiarity with the MR imaging presentation of focal liver lesions in WD may help clarify the actual nature of hepatic nodules in patients with this condition. PMID:27116011

  11. Dual-pass feature extraction on human vessel images.

    Science.gov (United States)

    Hernandez, W; Grimm, S; Andriantsimiavona, R

    2014-06-01

    We present a novel algorithm for the extraction of cavity features on images of human vessels. Fat deposits in the inner wall of such structure introduce artifacts, and regions in the images captured invalidating the usual assumption of an elliptical model which makes the process of extracting the central passage effectively more difficult. Our approach was designed to cope with these challenges and extract the required image features in a fully automated, accurate, and efficient way using two stages: the first allows to determine a bounding segmentation mask to prevent major leakages from pixels of the cavity area by using a circular region fill that operates as a paint brush followed by Principal Component Analysis with auto correction; the second allows to extract a precise cavity enclosure using a micro-dilation filter and an edge-walking scheme. The accuracy of the algorithm has been tested using 30 computed tomography angiography scans of the lower part of the body containing different degrees of inner wall distortion. The results were compared to manual annotations from a specialist resulting in sensitivity around 98 %, false positive rate around 8 %, and positive predictive value around 93 %. The average execution time was 24 and 18 ms on two types of commodity hardware over sections of 15 cm of length (approx. 1 ms per contour) which makes it more than suitable for use in interactive software applications. Reproducibility tests were also carried out with synthetic images showing no variation for the computed diameters against the theoretical measure. PMID:24197278

  12. Image Relaxation Matching Based on Feature Points for DSM Generation

    Institute of Scientific and Technical Information of China (English)

    ZHENG Shunyi; ZHANG Zuxun; ZHANG Jianqing

    2004-01-01

    In photogrammetry and remote sensing, image matching is a basic and crucial process for automatic DEM generation. In this paper we presented a image relaxation matching method based on feature points. This method can be considered as an extention of regular grid point based matching. It avoids the shortcome of grid point based matching. For example, with this method, we can avoid low or even no texture area where errors frequently appear in cross correlaton matching. In the mean while, it makes full use of some mature techniques such as probability relaxation, image pyramid and the like which have already been successfully used in grid point matching process. Application of the technique to DEM generaton in different regions proved that it is more reasonable and reliable.

  13. Pro duct Image Classification Based on Fusion Features

    Institute of Scientific and Technical Information of China (English)

    YANG Xiao-hui; LIU Jing-jing; YANG Li-jun

    2015-01-01

    Two key challenges raised by a product images classification system are classi-fication precision and classification time. In some categories, classification precision of the latest techniques, in the product images classification system, is still low. In this paper, we propose a local texture descriptor termed fan refined local binary pattern, which captures more detailed information by integrating the spatial distribution into the local binary pattern feature. We compare our approach with different methods on a subset of product images on Amazon/eBay and parts of PI100 and experimental results have demonstrated that our proposed approach is superior to the current existing methods. The highest classification precision is increased by 21%and the average classification time is reduced by 2/3.

  14. CFA-aware features for steganalysis of color images

    Science.gov (United States)

    Goljan, Miroslav; Fridrich, Jessica

    2015-03-01

    Color interpolation is a form of upsampling, which introduces constraints on the relationship between neighboring pixels in a color image. These constraints can be utilized to substantially boost the accuracy of steganography detectors. In this paper, we introduce a rich model formed by 3D co-occurrences of color noise residuals split according to the structure of the Bayer color filter array to further improve detection. Some color interpolation algorithms, AHD and PPG, impose pixel constraints so tight that extremely accurate detection becomes possible with merely eight features eliminating the need for model richification. We carry out experiments on non-adaptive LSB matching and the content-adaptive algorithm WOW on five different color interpolation algorithms. In contrast to grayscale images, in color images that exhibit traces of color interpolation the security of WOW is significantly lower and, depending on the interpolation algorithm, may even be lower than non-adaptive LSB matching.

  15. Multispectral image feature fusion for detecting land mines

    Energy Technology Data Exchange (ETDEWEB)

    Clark, G.A.; Fields, D.J.; Sherwood, R.J. [Lawrence Livermore National Lab., CA (United States)] [and others

    1994-11-15

    Our system fuses information contained in registered images from multiple sensors to reduce the effect of clutter and improve the the ability to detect surface and buried land mines. The sensor suite currently consists if a camera that acquires images in sixible wavelength bands, du, dual-band infrared (5 micron and 10 micron) and ground penetrating radar. Past research has shown that it is extremely difficult to distinguish land mines from background clutter in images obtained from a single sensor. It is hypothesized, however, that information fused from a suite of various sensors is likely to provide better detection reliability, because the suite of sensors detects a variety of physical properties that are more separate in feature space. The materials surrounding the mines can include natural materials (soil, rocks, foliage, water, holes made by animals and natural processes, etc.) and some artifacts.

  16. Nanoscopy—imaging life at the nanoscale: a Nobel Prize achievement with a bright future

    Science.gov (United States)

    Blom, Hans; Bates, Mark

    2015-10-01

    A grand scientific prize was awarded last year to three pioneering scientists, for their discovery and development of molecular ‘ON-OFF’ switching which, when combined with optical imaging, can be used to see the previously invisible with light microscopy. The Royal Swedish Academy of Science announced on October 8th their decision and explained that this achievement—rooted in physics and applied in biology and medicine—was awarded with the Nobel Prize in Chemistry for controlling fluorescent molecules to create images of specimens smaller than anything previously observed with light. The story of how this noble switch in optical microscopy was achieved and how it was engineered to visualize life at the nanoscale is highlighted in this invited comment.

  17. A route to brightly fluorescent carbon nanotubes for near-infrared imaging in mice

    OpenAIRE

    Welsher, Kevin; Liu, Zhuang; Sarah P Sherlock; Robinson, Joshua Tucker; Chen, Zhuo; Daranciang, Dan; Dai, Hongjie

    2009-01-01

    The near-infrared photoluminescence intrinsic to semiconducting single-walled carbon nanotubes is ideal for biological imaging owing to the low autofluorescence and deep tissue penetration in the near-infrared region beyond 1 µm. However, biocompatible single-walled carbon nanotubes with high quantum yield have been elusive. Here, we show that sonicating single-walled carbon nanotubes with sodium cholate, followed by surfactant exchange to form phospholipid–polyethylene glycol coated nanotube...

  18. The SN 1006 Remnant Optical Proper Motions, Deep Imaging, Distance, and Brightness at Maximum

    CERN Document Server

    Winkler, P F; Long, K S; Gupta, Gaurav; Long, Knox S.

    2002-01-01

    We report the first measurement of proper motions in the SN1006 remnant (G327.6+14.6) based entirely on digital images. CCD images from three epochs spanning a period of 11 years are used: 1987 from Las Campanas, and 1991 and 1998 from CTIO. Measuring the shift of delicate Balmer filaments along the northwest rim of the remnant, we obtain proper motions of 280 +/- 8 mas/yr along the entire length where the filaments are well defined, with little systematic variation along the filaments. We also report very deep Halpha imaging observations of the entire remnant that clearly show very faint emission surrounding almost the entire shell, as well as some diffuse emission regions in the (projected) interior. Combining the proper motion measurement with a recent measurement of the shock velocity based on spectra of the same filaments by Ghavamian et al. leads to a distance of 2.17 +/- 0.08 kpc to SN1006. Several lines of argument suggest that SN1006 was a Type Ia event, so the improved distance measurement can be co...

  19. Feature extraction for target identification and image classification of OMIS hyperspectral image

    Institute of Scientific and Technical Information of China (English)

    DU Pei-jun; TAN Kun; SU Hong-jun

    2009-01-01

    In order to combine feature extraction operations with specific hyperspectrai remote sensing information processing objectives, two aspects of feature extraction were explored. Based on clustering and decision tree algorithm, spectral absorption index (SAI), continuum-removal and derivative spectral analysis were employed to discover characterized spectral features of dif-ferent targets, and decision trees for identifying a specific class and discriminating different classes were generated. By combining support vector machine (SVM) classifier with different feature extraction strategies including principal component analysis (PCA), minimum noise fraction (MNF), grouping PCA, and derivate spectral analysis, the performance of feature extraction approaches in classification was evaluated. The results show that feature extraction by PCA and derivate spectral analysis are effective to OMIS (operational modular imaging spectrometer) image classification using SVM, and SVM outperforms traditional SAM and MLC classifiers for OMIS data.

  20. Scalable High Performance Image Registration Framework by Unsupervised Deep Feature Representations Learning

    OpenAIRE

    Wu, Guorong; Kim, Minjeong; Wang, Qian; Munsell, Brent C.; Shen, Dinggang

    2015-01-01

    Feature selection is a critical step in deformable image registration. In particular, selecting the most discriminative features that accurately and concisely describe complex morphological patterns in image patches improves correspondence detection, which in turn improves image registration accuracy. Furthermore, since more and more imaging modalities are being invented to better identify morphological changes in medical imaging data,, the development of deformable image registration method ...

  1. A feature-enriched completely blind image quality evaluator.

    Science.gov (United States)

    Lin Zhang; Lei Zhang; Bovik, Alan C

    2015-08-01

    Existing blind image quality assessment (BIQA) methods are mostly opinion-aware. They learn regression models from training images with associated human subjective scores to predict the perceptual quality of test images. Such opinion-aware methods, however, require a large amount of training samples with associated human subjective scores and of a variety of distortion types. The BIQA models learned by opinion-aware methods often have weak generalization capability, hereby limiting their usability in practice. By comparison, opinion-unaware methods do not need human subjective scores for training, and thus have greater potential for good generalization capability. Unfortunately, thus far no opinion-unaware BIQA method has shown consistently better quality prediction accuracy than the opinion-aware methods. Here, we aim to develop an opinion-unaware BIQA method that can compete with, and perhaps outperform, the existing opinion-aware methods. By integrating the features of natural image statistics derived from multiple cues, we learn a multivariate Gaussian model of image patches from a collection of pristine natural images. Using the learned multivariate Gaussian model, a Bhattacharyya-like distance is used to measure the quality of each image patch, and then an overall quality score is obtained by average pooling. The proposed BIQA method does not need any distorted sample images nor subjective quality scores for training, yet extensive experiments demonstrate its superior quality-prediction performance to the state-of-the-art opinion-aware BIQA methods. The MATLAB source code of our algorithm is publicly available at www.comp.polyu.edu.hk/~cslzhang/IQA/ILNIQE/ILNIQE.htm.

  2. Venusian atmospheric turbulence evaluated from cloud brightness distribution in VEX UV images

    Science.gov (United States)

    Teraguchi, T.; Kasaba, Y.; Hoshino, N.; Sato, T. M.; Takahashi, Y.; Watanabe, S.; Yamada, M.; Matsuda, Y.; Kouyama, T.; Titov, D.; Markiewicz, W.

    2011-10-01

    This study suggested following points: (1) The power spectra mostly contained the inflection. The slope at lower wavenumbers was steeper than that at higher wavenumbers. Such a feature agrees with the characteristics in the kinetic energy spectra shon Earth (Nastrom et al., 1984; Nastrom and Gage, 1985). (2) The slopes at planetary wavenumbers K Matsuda (2006) suggested that the inflection point at 330 - 1000km can be a border between 2D and 3D turbulences. Our result indicates a possibility to have enstrophy forward cascade in 2D turbulence at lower wavenumbers and the energy forward cascade in 3D turbulence at higher wavenumbers.

  3. Shape Adaptive, Robust Iris Feature Extraction from Noisy Iris Images

    Science.gov (United States)

    Ghodrati, Hamed; Dehghani, Mohammad Javad; Danyali, Habibolah

    2013-01-01

    In the current iris recognition systems, noise removing step is only used to detect noisy parts of the iris region and features extracted from there will be excluded in matching step. Whereas depending on the filter structure used in feature extraction, the noisy parts may influence relevant features. To the best of our knowledge, the effect of noise factors on feature extraction has not been considered in the previous works. This paper investigates the effect of shape adaptive wavelet transform and shape adaptive Gabor-wavelet for feature extraction on the iris recognition performance. In addition, an effective noise-removing approach is proposed in this paper. The contribution is to detect eyelashes and reflections by calculating appropriate thresholds by a procedure called statistical decision making. The eyelids are segmented by parabolic Hough transform in normalized iris image to decrease computational burden through omitting rotation term. The iris is localized by an accurate and fast algorithm based on coarse-to-fine strategy. The principle of mask code generation is to assign the noisy bits in an iris code in order to exclude them in matching step is presented in details. An experimental result shows that by using the shape adaptive Gabor-wavelet technique there is an improvement on the accuracy of recognition rate. PMID:24696801

  4. Shape adaptive, robust iris feature extraction from noisy iris images.

    Science.gov (United States)

    Ghodrati, Hamed; Dehghani, Mohammad Javad; Danyali, Habibolah

    2013-10-01

    In the current iris recognition systems, noise removing step is only used to detect noisy parts of the iris region and features extracted from there will be excluded in matching step. Whereas depending on the filter structure used in feature extraction, the noisy parts may influence relevant features. To the best of our knowledge, the effect of noise factors on feature extraction has not been considered in the previous works. This paper investigates the effect of shape adaptive wavelet transform and shape adaptive Gabor-wavelet for feature extraction on the iris recognition performance. In addition, an effective noise-removing approach is proposed in this paper. The contribution is to detect eyelashes and reflections by calculating appropriate thresholds by a procedure called statistical decision making. The eyelids are segmented by parabolic Hough transform in normalized iris image to decrease computational burden through omitting rotation term. The iris is localized by an accurate and fast algorithm based on coarse-to-fine strategy. The principle of mask code generation is to assign the noisy bits in an iris code in order to exclude them in matching step is presented in details. An experimental result shows that by using the shape adaptive Gabor-wavelet technique there is an improvement on the accuracy of recognition rate. PMID:24696801

  5. The imaging features of neurologic complications of left atrial myxomas

    Energy Technology Data Exchange (ETDEWEB)

    Liao, Wei-Hua; Ramkalawan, Divya; Liu, Jian-Ling; Shi, Wei [Department of Radiology, Xiangya Hospital, Central South University, Changsha 410008, Hunan (China); Zee, Chi-Shing [Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA 90033 (United States); Yang, Xiao-Su; Li, Guo-Liang; Li, Jing [Department of Neurology, Xiangya Hospital, Central South University, Changsha 410008, Hunan (China); Wang, Xiao-Yi, E-mail: cjr.wangxiaoyi@vip.163.com [Department of Radiology, Xiangya Hospital, Central South University, Changsha 410008, Hunan (China)

    2015-05-15

    Background: Neurologic complications may be the first symptoms of atrial myxomas. Understanding the imaging features of neurologic complications of atrial myxomas can be helpful for the prompt diagnosis. Objective: To identify neuroimaging features for patients with neurologic complications attributed to atrial myxoma. Methods: We retrospectively reviewed the medical records of 103 patients with pathologically confirmed atrial myxoma at Xiangya Hospital from January 2009 to January 2014. The neuroimaging data for patients with neurologic complications were analyzed. Results: Eight patients with atrial myxomas (7.77%) presented with neurologic manifestations, which constituted the initial symptoms for seven patients (87.5%). Neuroimaging showed five cases of cerebral infarctions and three cases of aneurysms. The main patterns of the infarctions were multiplicity (100.0%) and involvement of the middle cerebral artery territory (80.0%). The aneurysms were fusiform in shape, multiple in number (100.0%) and located in the distal middle cerebral artery (100.0%). More specifically, high-density in the vicinity of the aneurysms was observed on CT for two patients (66.7%), and homogenous enhancement surrounding the aneurysms was detected in the enhanced imaging for two patients (66.7%). Conclusion: Neurologic complications secondary to atrial myxoma consist of cerebral infarctions and aneurysms, which show certain characteristic features in neuroimaging. Echocardiography should be performed in patients with multiple cerebral infarctions, and multiple aneurysms, especially when aneurysms are distal in location. More importantly, greater attention should be paid to the imaging changes surrounding the aneurysms when myxomatous aneurysms are suspected and these are going to be the relevant features in our article.

  6. The imaging features of neurologic complications of left atrial myxomas

    International Nuclear Information System (INIS)

    Background: Neurologic complications may be the first symptoms of atrial myxomas. Understanding the imaging features of neurologic complications of atrial myxomas can be helpful for the prompt diagnosis. Objective: To identify neuroimaging features for patients with neurologic complications attributed to atrial myxoma. Methods: We retrospectively reviewed the medical records of 103 patients with pathologically confirmed atrial myxoma at Xiangya Hospital from January 2009 to January 2014. The neuroimaging data for patients with neurologic complications were analyzed. Results: Eight patients with atrial myxomas (7.77%) presented with neurologic manifestations, which constituted the initial symptoms for seven patients (87.5%). Neuroimaging showed five cases of cerebral infarctions and three cases of aneurysms. The main patterns of the infarctions were multiplicity (100.0%) and involvement of the middle cerebral artery territory (80.0%). The aneurysms were fusiform in shape, multiple in number (100.0%) and located in the distal middle cerebral artery (100.0%). More specifically, high-density in the vicinity of the aneurysms was observed on CT for two patients (66.7%), and homogenous enhancement surrounding the aneurysms was detected in the enhanced imaging for two patients (66.7%). Conclusion: Neurologic complications secondary to atrial myxoma consist of cerebral infarctions and aneurysms, which show certain characteristic features in neuroimaging. Echocardiography should be performed in patients with multiple cerebral infarctions, and multiple aneurysms, especially when aneurysms are distal in location. More importantly, greater attention should be paid to the imaging changes surrounding the aneurysms when myxomatous aneurysms are suspected and these are going to be the relevant features in our article

  7. VLBI observations of bright AGN jets with KVN and VERA Array (KaVA): Evaluation of Imaging Capability

    CERN Document Server

    Niinuma, Kotaro; Kino, Motoki; Sohn, Bong Won; Akiyama, Kazunori; Zhao, Guang-Yao; Sawada-Satoh, Satoko; Trippe, Sascha; Hada, Kazuhiro; Jung, Taehyun; Hagiwara, Yoshiaki; Dodson, Richard; Koyama, Shoko; Honma, Mareki; Nagai, Hiroshi; Chung, Aeree; Doi, Akihiro; Fujisawa, Kenta; Han, Myoung-Hee; Kim, Joeng-Sook; Lee, Jeewon; Lee, Jeong Ae; Miyazaki, Atsushi; Oyama, Tomoaki; Sorai, Kazuo; Wajima, Kiyoaki; Bae, Jaehan; Byun, Do-Young; Cho, Se-Hyung; Choi, Yoon Kyung; Chung, Hyunsoo; Chung, Moon-Hee; Han, Seog-Tae; Hirota, Tomoya; Hwang, Jung-Wook; Je, Do-Heung; Jike, Takaaki; Jung, Dong-Kyu; Jung, Jin-Seung; Kang, Ji-Hyun; Kang, Jiman; Kang, Yong-Woo; Kan-ya, Yukitoshi; Kanaguchi, Masahiro; Kawaguchi, Noriyuki; Kim, Bong Gyu; Kim, Hyo Ryoung; Kim, Hyun-Goo; Kim, Jaeheon; Kim, Jongsoo; Kim, Kee-Tae; Kim, Mikyoung; Kobayashi, Hideyuki; Kono, Yusuke; Kurayama, Tomoharu; Lee, Changhoon; Lee, Jung-Won; Lee, Sang Hyun; Minh, Young Chol; Matsumoto, Naoko; Nakagawa, Akiharu; Oh, Chung Sik; Oh, Se-Jin; Park, Sun-Youp; Roh, Duk-Gyoo; Sasao, Tetsuo; Shibata, Katsunori M; Song, Min-Gyu; Tamura, Yoshiaki; Wi, Seog-Oh; Yeom, Jae-Hwan; Yun, Young Joo

    2014-01-01

    The Korean very-long-baseline interferometry (VLBI) network (KVN) and VLBI Exploration of Radio Astrometry (VERA) Array (KaVA) is the first international VLBI array dedicated to high-frequency (23 and 43 GHz bands) observations in East Asia. Here, we report the first imaging observations of three bright active galactic nuclei (AGNs) known for their complex morphologies: 4C 39.25, 3C 273, and M 87. This is one of the initial result of KaVA early science. Our KaVA images reveal extended outflows with complex substructure such as knots and limb brightening, in agreement with previous Very Long Baseline Array (VLBA) observations. Angular resolutions are better than 1.4 and 0.8 milliarcsecond at 23 GHz and 43 GHz, respectively. KaVA achieves a high dynamic range of ~1000, more than three times the value achieved by VERA. We conclude that KaVA is a powerful array with a great potential for the study of AGN outflows, at least comparable to the best existing radio interferometric arrays.

  8. Super-resolved 3-D imaging of live cells organelles from bright-field photon transmission micrographs

    CERN Document Server

    Rychtarikova, Renata; Shi, Kevin; Malakhova, Daria; Machacek, Petr; Smaha, Rebecca; Urban, Jan; Stys, Dalibor

    2016-01-01

    Current biological and medical research is aimed at obtaining a detailed spatiotemporal map of a live cell's interior to describe and predict cell's physiological state. We present here an algorithm for complete 3-D modelling of cellular structures from a z-stack of images obtained using label-free wide-field bright-field light-transmitted microscopy. The method visualizes 3-D objects with a volume equivalent to the area of a camera pixel multiplied by the z-height. The computation is based on finding pixels of unchanged intensities between two consecutive images of an object spread function. These pixels represent strongly light-diffracting, light-absorbing, or light-emitting objects. To accomplish this, variables derived from R\\'{e}nyi entropy are used to suppress camera noise. Using this algorithm, the detection limit of objects is only limited by the technical specifications of the microscope setup--we achieve the detection of objects of the size of one camera pixel. This method allows us to obtain 3-D re...

  9. Bright fluorescent chemosensor platforms for imaging endogenous pools of neuronal zinc.

    Science.gov (United States)

    Chang, Christopher J; Nolan, Elizabeth M; Jaworski, Jacek; Burdette, Shawn C; Sheng, Morgan; Lippard, Stephen J

    2004-02-01

    A series of new fluorescent Zinpyr (ZP) chemosensors based on the fluorescein platform have been prepared and evaluated for imaging neuronal Zn(2+). A systematic synthetic survey of electronegative substitution patterns on a homologous ZP scaffold provides a basis for tuning the fluorescence responses of "off-on" photoinduced electron transfer (PET) probes by controlling fluorophore pK(a) values and attendant proton-induced interfering fluorescence of the metal-free (apo) probes at physiological pH. We further establish the value of these improved optical tools for interrogating the metalloneurochemistry of Zn(2+); the novel ZP3 fluorophore images endogenous stores of Zn(2+) in live hippocampal neurons and slices, including the first fluorescence detection of Zn(2+) in isolated dentate gyrus cultures. Our findings reveal that careful control of fluorophore pK(a) can minimize proton-induced fluorescence of the apo probes and that electronegative substitution offers a general strategy for tuning PET chemosensors for cellular studies. In addition to providing improved optical tools for Zn(2+) in the neurosciences, these results afford a rational starting point for creating superior fluorescent probes for biological applications.

  10. Automatic archaeological feature extraction from satellite VHR images

    Science.gov (United States)

    Jahjah, Munzer; Ulivieri, Carlo

    2010-05-01

    Archaeological applications need a methodological approach on a variable scale able to satisfy the intra-site (excavation) and the inter-site (survey, environmental research). The increased availability of high resolution and micro-scale data has substantially favoured archaeological applications and the consequent use of GIS platforms for reconstruction of archaeological landscapes based on remotely sensed data. Feature extraction of multispectral remotely sensing image is an important task before any further processing. High resolution remote sensing data, especially panchromatic, is an important input for the analysis of various types of image characteristics; it plays an important role in the visual systems for recognition and interpretation of given data. The methods proposed rely on an object-oriented approach based on a theory for the analysis of spatial structures called mathematical morphology. The term "morphology" stems from the fact that it aims at analysing object shapes and forms. It is mathematical in the sense that the analysis is based on the set theory, integral geometry, and lattice algebra. Mathematical morphology has proven to be a powerful image analysis technique; two-dimensional grey tone images are seen as three-dimensional sets by associating each image pixel with an elevation proportional to its intensity level. An object of known shape and size, called the structuring element, is then used to investigate the morphology of the input set. This is achieved by positioning the origin of the structuring element to every possible position of the space and testing, for each position, whether the structuring element either is included or has a nonempty intersection with the studied set. The shape and size of the structuring element must be selected according to the morphology of the searched image structures. Other two feature extraction techniques were used, eCognition and ENVI module SW, in order to compare the results. These techniques were

  11. Secondary ovarian neoplasms in children: imaging features with histopathologic correlation

    Energy Technology Data Exchange (ETDEWEB)

    McCarville, M.B. [Dept. of Diagnostic Imaging, St. Jude Children' s Research Hospital, Memphis, TN (United States); Hill, D.A. [Dept. of Pathology, St. Jude Children' s Research Hospital, Memphis, TN (United States); Miller, B.E. [Dept. of Obstetrics and Gynecology, Univ. of Tennessee, Memphis (United States); Pratt, C.B. [Dept. of Hematology-Oncology, St. Jude Children' s Research Hospital, Memphis (United States)

    2001-05-01

    Background. Although the pathologic features and imaging appearance of childhood primary ovarian neoplasms have been well described, little information is available about the malignancies that may secondarily involve the ovary. Objective. To determine the relationship between the imaging features and the histopathology of secondary ovarian neoplasms in children treated at our institution. Materials and methods. We searched our institutional database for codes indicating metastatic ovarian disease. Of the 35 patients with such codes, 18 had pathologically proven secondary ovarian disease. From their medical records we recorded demographic data, presenting symptoms, and evidence of endocrine dysfunction. We reviewed the pre-oophorectomy imaging and the subsequent pathologic specimens. Results. One-third of the patients had bilateral pelvic masses; another third had large masses indistinguishable from the ovaries. Twelve (67 %) had either ascites, peritoneal implants, matted bowel, adenopathy, pleural effusions, or some combination of these. Five (28 %) had other metastatic disease. Primary tumors included colon adenocarcinoma (9), Burkitt's lymphoma (3), alveolar rhabdomyosarcoma (3), Wilms' tumor (1), neuroblastoma (1), and retinoblastoma (1). Conclusion. Although rare, secondary ovarian tumors should be considered in the differential diagnosis of children with ovarian masses. Bilateral ovarian masses or large masses indistinguishable from the ovaries, particularly in the presence of other metastatic foci, may help distinguish primary from secondary ovarian malignancies. (orig.)

  12. Two-Level Evaluation on Sensor Interoperability of Features in Fingerprint Image Segmentation

    OpenAIRE

    Ya-Shuo Li; Yilong Yin; Gongping Yang; Ying Li

    2012-01-01

    Features used in fingerprint segmentation significantly affect the segmentation performance. Various features exhibit different discriminating abilities on fingerprint images derived from different sensors. One feature which has better discriminating ability on images derived from a certain sensor may not adapt to segment images derived from other sensors. This degrades the segmentation performance. This paper empirically analyzes the sensor interoperability problem of segmentation feature, w...

  13. Collaborative Tracking of Image Features Based on Projective Invariance

    Science.gov (United States)

    Jiang, Jinwei

    -mode sensors for improving the flexibility and robustness of the system. From the experimental results during three field tests for the LASOIS system, we observed that most of the errors in the image processing algorithm are caused by the incorrect feature tracking. This dissertation addresses the feature tracking problem in image sequences acquired from cameras. Despite many alternatives to feature tracking problem, iterative least squares solution solving the optical flow equation has been the most popular approach used by many in the field. This dissertation attempts to leverage the former efforts to enhance feature tracking methods by introducing a view geometric constraint to the tracking problem, which provides collaboration among features. In contrast to alternative geometry based methods, the proposed approach provides an online solution to optical flow estimation in a collaborative fashion by exploiting Horn and Schunck flow estimation regularized by view geometric constraints. Proposed collaborative tracker estimates the motion of a feature based on the geometry of the scene and how the other features are moving. Alternative to this approach, a new closed form solution to tracking that combines the image appearance with the view geometry is also introduced. We particularly use invariants in the projective coordinates and conjecture that the traditional appearance solution can be significantly improved using view geometry. The geometric constraint is introduced by defining a new optical flow equation which exploits the scene geometry from a set drawn from tracked features. At the end of each tracking loop the quality of the tracked features is judged using both appearance similarity and geometric consistency. Our experiments demonstrate robust tracking performance even when the features are occluded or they undergo appearance changes due to projective deformation of the template. The proposed collaborative tracking method is also tested in the visual navigation

  14. Multimodal Ultrawide-Field Imaging Features in Waardenburg Syndrome.

    Science.gov (United States)

    Choudhry, Netan; Rao, Rajesh C

    2015-06-01

    A 45-year-old woman was referred for bilateral irregular fundus pigmentation. Dilated fundus examination revealed irregular hypopigmentation posterior to the equator in both eyes, confirmed by fundus autofluorescence. A thickened choroid was seen on enhanced-depth imaging spectral-domain optical coherence tomography (EDI SD-OCT). Systemic evaluation revealed sensorineural deafness, telecanthus, and a white forelock. Further investigation revealed a first-degree relative with Waardenburg syndrome. Waardenburg syndrome is characterized by a group of features including telecanthus, a broad nasal root, synophrys of the eyebrows, piedbaldism, heterochromia irides, and deafness. Choroidal hypopigmentation is a unique feature that can be visualized with ultrawide-field fundus autofluorescence. The choroid may also be thickened and its thickness measured with EDI SD-OCT. PMID:26114849

  15. MR imaging features of chronically torn anterior cruciate ligament

    Energy Technology Data Exchange (ETDEWEB)

    Niitsu, Mamoru; Kuramochi, Masashi; Ikeda, Kotaroh; Fukubayashi, Tohru; Anno, Izumi; Itai, Yuji [Tsukuba Univ., Ibaraki (Japan). Inst. of Clinical Medicine

    1995-06-01

    Magnetic resonance (MR) images of 40 knee joints with arthroscopically proved chronic anterior cruciate ligament (ACL) tears were retrospectively evaluated. MRI demonstrated various features of chronic ACL tears: 19 knees revealed with no identifiable ligamentous structure, and 21 had residual ligamentous structures. These pseudoligaments, 14 discontinuous bands and seven continuous bands with elongation, were residual torn ligamentous fibers and/or synovial tissues. All the discontinuous bands were disrupted from the femoral attachment and were likely to traverse the lower intercondylar space. Six disrupted ligaments were attached to the lateral aspect of the posterior cruciate ligament (PCL). Coronal T2{sup *}-weighted gradient echo images showed better delineation of the disrupted femoral attachment and adhesion to the PCL. A chronic ACL tear with minimal elongation or with PCL attachment at a higher position may occasionally be difficult to distinguish from an intact ligament. (author).

  16. MR imaging features of chronically torn anterior cruciate ligament

    International Nuclear Information System (INIS)

    Magnetic resonance (MR) images of 40 knee joints with arthroscopically proved chronic anterior cruciate ligament (ACL) tears were retrospectively evaluated. MRI demonstrated various features of chronic ACL tears: 19 knees revealed with no identifiable ligamentous structure, and 21 had residual ligamentous structures. These pseudoligaments, 14 discontinuous bands and seven continuous bands with elongation, were residual torn ligamentous fibers and/or synovial tissues. All the discontinuous bands were disrupted from the femoral attachment and were likely to traverse the lower intercondylar space. Six disrupted ligaments were attached to the lateral aspect of the posterior cruciate ligament (PCL). Coronal T2*-weighted gradient echo images showed better delineation of the disrupted femoral attachment and adhesion to the PCL. A chronic ACL tear with minimal elongation or with PCL attachment at a higher position may occasionally be difficult to distinguish from an intact ligament. (author)

  17. Aggressive primary thyroid lymphoma: imaging features of two elderly patients

    International Nuclear Information System (INIS)

    We report two cases of aggressive thyroid lymphoma in elderly patients that presented as Epub ahead of print large infiltrative thyroid masses with extensive invasion to adjacent structures including trachea, esophagus, and common carotid artery. Ultrasonography displayed irregular shaped, heterogeneous hypoechoic mass, mimicking anaplastic carcinoma. Computed tomography showed heterogeneously enhancing mass compared to surrounding muscles without calcification and hemorrhage. After biopsy, the masses were histopathologically diagnosed as lymphoma. Aggressive primary thyroid lymphoma is rare; therefore, here we report its image features, with emphasis on ultrasonographic findings, and discuss its differential diagnosis.

  18. Aggressive primary thyroid lymphoma: imaging features of two elderly patients

    Energy Technology Data Exchange (ETDEWEB)

    Kim, Eu Hyun; Kim, Jee Young; Kim, Tae Jung [Yeouido St. Mary' s Hospital, The Catholic University College of Medicine, Seoul (Korea, Republic of)

    2014-12-15

    We report two cases of aggressive thyroid lymphoma in elderly patients that presented as Epub ahead of print large infiltrative thyroid masses with extensive invasion to adjacent structures including trachea, esophagus, and common carotid artery. Ultrasonography displayed irregular shaped, heterogeneous hypoechoic mass, mimicking anaplastic carcinoma. Computed tomography showed heterogeneously enhancing mass compared to surrounding muscles without calcification and hemorrhage. After biopsy, the masses were histopathologically diagnosed as lymphoma. Aggressive primary thyroid lymphoma is rare; therefore, here we report its image features, with emphasis on ultrasonographic findings, and discuss its differential diagnosis.

  19. Probing the bright radio flare and afterglow of GRB 130427A with the Arcminute Microkelvin Imager

    Science.gov (United States)

    Anderson, G. E.; van der Horst, A. J.; Staley, T. D.; Fender, R. P.; Wijers, R. A. M. J.; Scaife, A. M. M.; Rumsey, C.; Titterington, D. J.; Rowlinson, A.; Saunders, R. D. E.

    2014-05-01

    We present one of the best sampled early-time light curves of a gamma-ray burst (GRB) at radio wavelengths. Using the Arcminute Mircrokelvin Imager (AMI), we observed GRB 130427A at the central frequency of 15.7 GHz between 0.36 and 59.32 d post-burst. These results yield one of the earliest radio detections of a GRB and demonstrate a clear rise in flux less than one day after the γ-ray trigger followed by a rapid decline. This early-time radio emission probably originates in the GRB reverse shock so our AMI light curve reveals the first ever confirmed detection of a reverse shock peak in the radio domain. At later times (about 3.2 d post-burst), the rate of decline decreases, indicating that the forward shock component has begun to dominate the light curve. Comparisons of the AMI light curve with modelling conducted by Perley et al. show that the most likely explanation of the early-time 15.7 GHz peak is caused by the self-absorption turn-over frequency, rather than the peak frequency, of the reverse shock moving through the observing bands.

  20. Imaging galactic diffuse gas: Bright, turbulent CO surrounding the line of sight to NRAO150

    CERN Document Server

    Pety, Jérôme; Liszt, Harvey S

    2008-01-01

    To understand the environment and extended structure of the host galactic gas whose molecular absorption line chemistry, we previously observed along the microscopic line of sight to the blazar/radiocontinuum source NRAO150 (aka B0355+508), we used the IRAM 30m Telescope and Plateau de Bure Interferometer to make two series of images of the host gas: i) 22.5 arcsec resolution single-dish maps of 12CO J=1-0 and 2-1 emission over a 220 arcsec by 220 arcsec field; ii) a hybrid (interferometer+singledish) aperture synthesis mosaic of 12CO J=1-0 emission at 5.8 arcsec resolution over a 90 arcsec-diameter region. CO components that are observed in absorption at a moderate optical depth (0.5) and are undetected in emission at 1 arcmin resolution toward NRAO 150 remain undetected at 6 arcsec resolution. This implies that they are not a previously-hidden large-scale molecular component revealed in absorption, but they do highlight the robustness of the chemistry into regions where the density and column density are to...

  1. Performance Characterization of Image Feature Detectors in Relation to the Scene Content Utilizing a Large Image Database

    OpenAIRE

    Ferrarini, Bruno; Ehsan, Shoaib; Rehman, Naveed Ur; McDonald-Maier, Klaus D.

    2015-01-01

    Selecting the most suitable local invariant feature detector for a particular application has rendered the task of evaluating feature detectors a critical issue in vision research. No state-of-the-art image feature detector works satisfactorily under all types of image transformations. Although the literature offers a variety of comparison works focusing on performance evaluation of image feature detectors under several types of image transformation, the influence of the scene content on the ...

  2. No functional magnetic resonance imaging evidence for brightness and color filling-in in early human visual cortex

    NARCIS (Netherlands)

    Cornelissen, FW; Wade, AR; Vladusich, T; Dougherty, RF; Wandell, BA

    2006-01-01

    The brightness and color of a surface depends on its contrast with nearby surfaces. For example, a gray surface can appear very light when surrounded by a black surface or dark when surrounded by a white surface. Some theories suggest that perceived surface brightness and color is represented explic

  3. Texture features analysis for coastline extraction in remotely sensed images

    Science.gov (United States)

    De Laurentiis, Raimondo; Dellepiane, Silvana G.; Bo, Giancarlo

    2002-01-01

    The accurate knowledge of the shoreline position is of fundamental importance in several applications such as cartography and ships positioning1. Moreover, the coastline could be seen as a relevant parameter for the monitoring of the coastal zone morphology, as it allows the retrieval of a much more precise digital elevation model of the entire coastal area. The study that has been carried out focuses on the development of a reliable technique for the detection of coastlines in remotely sensed images. An innovative approach which is based on the concepts of fuzzy connectivity and texture features extraction has been developed for the location of the shoreline. The system has been tested on several kind of images as SPOT, LANDSAT and the results obtained are good. Moreover, the algorithm has been tested on a sample of a SAR interferogram. The breakthrough consists in the fact that the coastline detection is seen as an important features in the framework of digital elevation model (DEM) retrieval. In particular, the coast could be seen as a boundary line all data beyond which (the ones representing the sea) are not significant. The processing for the digital elevation model could be refined, just considering the in-land data.

  4. Imaging features of ovarian metastases from colonic adenocarcinoma in adolescents

    International Nuclear Information System (INIS)

    This paper describes the imaging features of ovarian metastases from adenocarcinoma of the colon in adolescent females. We reviewed retrospectively abdominal and pelvic computed tomographic and pelvic ultrasound examinations, histologic slices, and clinical charts of six adolescent females with ovarian metastases secondary to adenocarcinoma of the colon. One patient had ovarian metastasis at presentation and was presumed to have a primary ovarian tumor. The ovarian metastases were either solid (n = 3), complex with both solid and cystic components (n = 2), or multilocular cysts (n = 1). The ovarian lesions were large, ranging from 6 cm to 18 cm in diameter. Colorectal carcinoma in adolescent females is frequently associated with ovarian metastases. One imaging characteristic differs in adult and adolescent ovarian metastases, although they do have features in common: in adolescents, a smaller proportion of colorectal ovarian metastases are multicystic (17%) compared with the adult series (45%). These lesions are frequently large and may be complex, multicystic, or solid. Although it is a rare disease, the differential dignosis of adnexal masses in adolescent females should include ovarian metastases from adenocarcinoma of the colon. (orig.)

  5. Clinical and imaging features of neonatal chlamydial pneumonia

    International Nuclear Information System (INIS)

    Objective: To study the clinical and imaging features of chlamydial pneumonia in newborns. Methods: Medical records,chest X-Ray and CT findings of 17 neonates with chlamydia pneumonia were reviewed. The age was ranged from 9.0 to 28.0 days with mean of (16.8 ± 5.8) days. There were 11 males and 6 females. Sixteen were full term infants and one was born post term. All babies were examined with chest X-ray film, and 13 patients also underwent chest CT scan. Serologic test using immunofluorescence method for Chlamydia IgG and IgM antibodies were performed in all patients. Results: All newborns presented with cough but without fever. Positive results of the serologic tests were demonstrated. Chest films showed bilateral hyperventilation in 10 patients, diffuse reticular nodules in 10 patients including nodules mimicking military tuberculosis in 7 patients, and accompanying consolidation in 9 patients. CT features included interstitial reticular nodules in 13 patients with size, density, and distribution varied. Subpleural nodules (11 patients) and fusion of nodules (10 patients) predominated. Bilateral hyperinflation was found in 10 patients, which combined with infiltration in 12 patients, thickening of bronchovascular bundles in 10 patients, and ground glass sign in 5 patients. No pleural effusion and lymphadenopathy was detected in any patient. Conclusions: Bilateral hyperinflation and diffuse interstitial reticular nodules were the most common imaging features of neonatal chlamydial pneumonia. The main clinical characteristic of neonatal chlamydial pneumonia is respiratory symptoms without fever, which is helpful to its diagnosis. (authors)

  6. Robust image analysis with sparse representation on quantized visual features.

    Science.gov (United States)

    Bao, Bing-Kun; Zhu, Guangyu; Shen, Jialie; Yan, Shuicheng

    2013-03-01

    Recent techniques based on sparse representation (SR) have demonstrated promising performance in high-level visual recognition, exemplified by the highly accurate face recognition under occlusion and other sparse corruptions. Most research in this area has focused on classification algorithms using raw image pixels, and very few have been proposed to utilize the quantized visual features, such as the popular bag-of-words feature abstraction. In such cases, besides the inherent quantization errors, ambiguity associated with visual word assignment and misdetection of feature points, due to factors such as visual occlusions and noises, constitutes the major cause of dense corruptions of the quantized representation. The dense corruptions can jeopardize the decision process by distorting the patterns of the sparse reconstruction coefficients. In this paper, we aim to eliminate the corruptions and achieve robust image analysis with SR. Toward this goal, we introduce two transfer processes (ambiguity transfer and mis-detection transfer) to account for the two major sources of corruption as discussed. By reasonably assuming the rarity of the two kinds of distortion processes, we augment the original SR-based reconstruction objective with l(0) norm regularization on the transfer terms to encourage sparsity and, hence, discourage dense distortion/transfer. Computationally, we relax the nonconvex l(0) norm optimization into a convex l(1) norm optimization problem, and employ the accelerated proximal gradient method to optimize the convergence provable updating procedure. Extensive experiments on four benchmark datasets, Caltech-101, Caltech-256, Corel-5k, and CMU pose, illumination, and expression, manifest the necessity of removing the quantization corruptions and the various advantages of the proposed framework.

  7. SOFT COMPUTING BASED MEDICAL IMAGE RETRIEVAL USING SHAPE AND TEXTURE FEATURES

    Directory of Open Access Journals (Sweden)

    M. Mary Helta Daisy

    2014-01-01

    Full Text Available Image retrieval is a challenging and important research applications like digital libraries and medical image databases. Content-based image retrieval is useful in retrieving images from database based on the feature vector generated with the help of the image features. In this study, we present image retrieval based on the genetic algorithm. The shape feature and morphological based texture features are extracted images in the database and query image. Then generating chromosome based on the distance value obtained by the difference feature vector of images in the data base and the query image. In the selected chromosome the genetic operators like cross over and mutation are applied. After that the best chromosome selected and displays the most similar images to the query image. The retrieval performance of the method shows better retrieval result.

  8. Robust Colour Image Watermarking Scheme Based on Feature Points and Image Normalization in DCT Domain

    Directory of Open Access Journals (Sweden)

    Ibrahim Alsonosi Nasir

    2014-04-01

    Full Text Available Geometric attacks can desynchronize the location of the watermark and hence cause incorrect watermark detection. This paper presents a robust c olour image watermarking scheme based on visually significant feature points and image norma lization technique. The feature points are used as synchronization marks between watermark emb edding and detection. The watermark is embedded into the non overlapped normalized circula r regions in the luminance component or the blue component of a color image. The embedding of the watermark is carried out by modifying the DCT coefficients values in selected b locks. The original unmarked image is not required for watermark extraction Experimental results show that the proposed scheme successfully makes the watermark perceptually invis ible as well as robust to common signal processing and geometric attacks.

  9. Magnetic Resonance Imaging and DWI Features of Orbital Rhabdomyosarcoma

    Institute of Scientific and Technical Information of China (English)

    Xuetao Mu; Hong Wang; Yueyue Li; Yuwen Hao; Chunnan Wu; Lin Ma

    2014-01-01

    Purpose:.To describe the magnetic resonance imaging (MRI) features of orbital rhabdomyosarcoma (RMS). Methods:.Thirty-nine patients with histopathologically con-firmed orbital RMS were retrospectively reviewed. All patients underwent orbital conventional MRI, including axial,.sagittal, and coronal T1-weighted,.T2-weighted,.and postcontrast T1-weighted sequences. The location, shape, margin, and MRI signal of the 39 lesions were reviewed..DWI in 15 patients and susceptibility weighted imaging (SWI) in 2 patients were also analyzed. Results:.Orbital MRI was available in 39 patients and re-vealed a soft tissue mass in the orbital region in all cases..Of the 39 patients,.the primary tumor sites were limited to the orbital proper in 31 cases, while 28 cases had extraocular muscle invasion and 8 cases had extraorbital invasion..All le-sions were unilateral..Thirty-three cases were well-defined soft tissue masses and 6 cases appeared as less well-defined soft-tissue masses..Thirty-four cases showed homogeneous isoin-tense or slightly hypointense signals on T1-weighted imaging (T1WI) and hyperintense signal on T2-weighted imaging (T2WI) compared with extraocular muscles. Five cases had heterogeneous signals with focal areas of increased signal on T1WI or decreased signal on T2WI, including 1 case with hy-pointense signal on SWI..The mean apparent diffusion coeffi-cient (ADC) value of the viable part of tumors was (0.925 ± 0.09)×10-3 mm2/s. All cases showed moderate to marked en-hancement after contrast administration. Conclusion:Several MRI features-including homogeneous isointense or slightly hypointense signal on T1WI and slightly hyperintense signal on T2WI, relative low ADC values, and moderate to marked enhancement,.extraocular muscles inva-sion, and extraorbital extensionare helpful in the diagnosis of orbital RMS. (Eye Science 2014; 29:6-11).

  10. Registration of image feature points using differential evolution

    Institute of Scientific and Technical Information of China (English)

    ZHANG Hao; HUANG Zhan-hua; YU Dao-ying

    2005-01-01

    This paper introduces a robust global nonlinear optimizer-differential evolution(DE),which is a simple evolution algorithm to search for an optimal transformation that makes the best alignment of two sets of feature points.To map the problem of matching into the framework of DE,the objective function is proportional to the registration error which is measured by Hausdorff distance,while the parameters of transformation are encoded in floating-point as the functional variables.Three termination criteria are proposed for DE.A simulation of 2-dimensional point sets and a similarity transformation are presented to compare the robustness and convergence properties of DE with genetic algorithm's (GA).And the registration of an object and its contour model have been demonstrated by using of DE to natural images.

  11. Imaging trace element distributions in single organelles and subcellular features

    Science.gov (United States)

    Kashiv, Yoav; Austin, Jotham R.; Lai, Barry; Rose, Volker; Vogt, Stefan; El-Muayed, Malek

    2016-02-01

    The distributions of chemical elements within cells are of prime importance in a wide range of basic and applied biochemical research. An example is the role of the subcellular Zn distribution in Zn homeostasis in insulin producing pancreatic beta cells and the development of type 2 diabetes mellitus. We combined transmission electron microscopy with micro- and nano-synchrotron X-ray fluorescence to image unequivocally for the first time, to the best of our knowledge, the natural elemental distributions, including those of trace elements, in single organelles and other subcellular features. Detected elements include Cl, K, Ca, Co, Ni, Cu, Zn and Cd (which some cells were supplemented with). Cell samples were prepared by a technique that minimally affects the natural elemental concentrations and distributions, and without using fluorescent indicators. It could likely be applied to all cell types and provide new biochemical insights at the single organelle level not available from organelle population level studies.

  12. An image-tracking algorithm based on object center distance-weighting and image feature recognition

    Institute of Scientific and Technical Information of China (English)

    JIANG Shuhong; WANG Qin; ZHANG Jianqiu; HU Bo

    2007-01-01

    Areal-time image-tracking algorithm is proposed.which gives small weights to pixels farther from the object center and uses the quantized image gray scales as a template.It identifies the target's location by the mean-shift iteration method and arrives at the target's scale by using image feature recognition.It improves the kernel-based algorithm in tracking scale-changing targets.A decimation mcthod is proposed to track large-sized targets and real-time experimental results verify the effectiveness of the proposed algorithm.

  13. Automated Image Retrieval of Chest CT Images Based on Local Grey Scale Invariant Features.

    Science.gov (United States)

    Arrais Porto, Marcelo; Cordeiro d'Ornellas, Marcos

    2015-01-01

    Textual-based tools are regularly employed to retrieve medical images for reading and interpretation using current retrieval Picture Archiving and Communication Systems (PACS) but pose some drawbacks. All-purpose content-based image retrieval (CBIR) systems are limited when dealing with medical images and do not fit well into PACS workflow and clinical practice. This paper presents an automated image retrieval approach for chest CT images based local grey scale invariant features from a local database. Performance was measured in terms of precision and recall, average retrieval precision (ARP), and average retrieval rate (ARR). Preliminary results have shown the effectiveness of the proposed approach. The prototype is also a useful tool for radiology research and education, providing valuable information to the medical and broader healthcare community. PMID:26262345

  14. Hemicrania Continua: Functional Imaging and Clinical Features With Diagnostic Implications.

    Science.gov (United States)

    Sahler, Kristen

    2013-04-10

    This review focuses on summarizing 2 pivotal articles in the clinical and pathophysiologic understanding of hemicrania continua (HC). The first article, a functional imaging project, identifies both the dorsal rostral pons (a region associated with the generation of migraines) and the posterior hypothalamus (a region associated with the generation of cluster and short-lasting unilateral neuralgiform headache with conjunctival injection and tearing [SUNCT]) as active during HC. The second article is a summary of the clinical features seen in a prospective cohort of HC patients that carry significant diagnostic implications. In particular, they identify a wider range of autonomic signs than what is currently included in the International Headache Society criteria (including an absence of autonomic signs in a small percentage of patients), a high frequency of migrainous features, and the presence of aggravation and/or restlessness during attacks. Wide variations in exacerbation length, frequency, pain description, and pain location (including side-switching pain) are also noted. Thus, a case is made for widening and modifying the clinical diagnostic criteria used to identify patients with HC.

  15. Covert photo classification by fusing image features and visual attributes.

    Science.gov (United States)

    Lang, Haitao; Ling, Haibin

    2015-10-01

    In this paper, we study a novel problem of classifying covert photos, whose acquisition processes are intentionally concealed from the subjects being photographed. Covert photos are often privacy invasive and, if distributed over Internet, can cause serious consequences. Automatic identification of such photos, therefore, serves as an important initial step toward further privacy protection operations. The problem is, however, very challenging due to the large semantic similarity between covert and noncovert photos, the enormous diversity in the photographing process and environment of cover photos, and the difficulty to collect an effective data set for the study. Attacking these challenges, we make three consecutive contributions. First, we collect a large data set containing 2500 covert photos, each of them is verified rigorously and carefully. Second, we conduct a user study on how humans distinguish covert photos from noncovert ones. The user study not only provides an important evaluation baseline, but also suggests fusing heterogeneous information for an automatic solution. Our third contribution is a covert photo classification algorithm that fuses various image features and visual attributes in the multiple kernel learning framework. We evaluate the proposed approach on the collected data set in comparison with other modern image classifiers. The results show that our approach achieves an average classification rate (1-EER) of 0.8940, which significantly outperforms other competitors as well as human's performance. PMID:25966474

  16. Content Based Image Retrieval Using Combined Features (Color and Texture

    Directory of Open Access Journals (Sweden)

    Vijaylakshmi Sajwan

    2014-04-01

    Full Text Available Image Retrieval is the field of study concerned with searching and retrieving digital images from a collection of database. Image retrieval attracts interest among researchers in the fields of image processing, multimedia, digital libraries, remote sensing, astronomy, database applications and others associate area. An effectual image retrieval system is able to operate on the collection of images to retrieve the applicable images based on the query image which conforms as closely as possible to human perception

  17. A New Method of Semantic Feature Extraction for Medical Images Data

    Institute of Scientific and Technical Information of China (English)

    XIE Conghua; SONG Yuqing; CHANG Jinyi

    2006-01-01

    In order to overcome the disadvantages of color, shape and texture-based features definition for medical images, this paper defines a new kind of semantic feature and its extraction algorithm. We firstly use kernel density estimation statistical model to describe the complicated medical image data, secondly, define some typical representative pixels of images as feature and finally, take hill-climbing strategy of Artificial Intelligence to extract those semantic features. Results of a content-based medial image retrieve system show that our semantic features have better distinguishing ability than those color, shape and texture-based features and can improve the ratios of recall and precision of this system smartly.

  18. Feature Based Image Mosaic Using Steerable Filters and Harris Corner Detector

    Directory of Open Access Journals (Sweden)

    Mahesh

    2013-05-01

    Full Text Available Image mosaic is to be combine several views of a scene in to single wide angle view. This paper proposes the feature based image mosaic approach. The mosaic image system includes feature point detection, feature point descriptor extraction and matching. A RANSAC algorithm is applied to eliminate number of mismatches and obtain transformation matrix between the images. The input image is transformed with the correct mapping model for image stitching and same is estimated. In this paper, feature points are detected using steerable filters and Harris, and compared with traditional Harris, KLT, and FAST corner detectors.

  19. Application of image visual characterization and soft feature selection in content-based image retrieval

    Science.gov (United States)

    Jarrah, Kambiz; Kyan, Matthew; Lee, Ivan; Guan, Ling

    2006-01-01

    Fourier descriptors (FFT) and Hu's seven moment invariants (HSMI) are among the most popular shape-based image descriptors and have been used in various applications, such as recognition, indexing, and retrieval. In this work, we propose to use the invariance properties of Hu's seven moment invariants, as shape feature descriptors, for relevance identification in content-based image retrieval (CBIR) systems. The purpose of relevance identification is to find a collection of images that are statistically similar to, or match with, an original query image from within a large visual database. An automatic relevance identification module in the search engine is structured around an unsupervised learning algorithm, the self-organizing tree map (SOTM). In this paper we also proposed a new ranking function in the structure of the SOTM that exponentially ranks the retrieved images based on their similarities with respect to the query image. Furthermore, we propose to extend our studies to optimize the contribution of individual feature descriptors for enhancing the retrieval results. The proposed CBIR system is compatible with the different architectures of other CBIR systems in terms of its ability to adapt to different similarity matching algorithms for relevance identification purposes, whilst offering flexibility of choice for alternative optimization and weight estimation techniques. Experimental results demonstrate the satisfactory performance of the proposed CBIR system.

  20. Unsupervised Multi-Feature Tag Relevance Learning for Social Image Retrieval

    OpenAIRE

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

    2010-01-01

    Interpreting the relevance of a user-contributed tag with respect to the visual content of an image is an emerging problem in social image retrieval. In the literature this problem is tackled by analyzing the correlation between tags and images represented by specific visual features. Unfortunately, no single feature represents the visual content completely, e.g., global features are suitable for capturing the gist of scenes, while local features are better for depicting objects. To solve the...

  1. The brightness of colour.

    Directory of Open Access Journals (Sweden)

    David Corney

    Full Text Available BACKGROUND: The perception of brightness depends on spatial context: the same stimulus can appear light or dark depending on what surrounds it. A less well-known but equally important contextual phenomenon is that the colour of a stimulus can also alter its brightness. Specifically, stimuli that are more saturated (i.e. purer in colour appear brighter than stimuli that are less saturated at the same luminance. Similarly, stimuli that are red or blue appear brighter than equiluminant yellow and green stimuli. This non-linear relationship between stimulus intensity and brightness, called the Helmholtz-Kohlrausch (HK effect, was first described in the nineteenth century but has never been explained. Here, we take advantage of the relative simplicity of this 'illusion' to explain it and contextual effects more generally, by using a simple Bayesian ideal observer model of the human visual ecology. We also use fMRI brain scans to identify the neural correlates of brightness without changing the spatial context of the stimulus, which has complicated the interpretation of related fMRI studies. RESULTS: Rather than modelling human vision directly, we use a Bayesian ideal observer to model human visual ecology. We show that the HK effect is a result of encoding the non-linear statistical relationship between retinal images and natural scenes that would have been experienced by the human visual system in the past. We further show that the complexity of this relationship is due to the response functions of the cone photoreceptors, which themselves are thought to represent an efficient solution to encoding the statistics of images. Finally, we show that the locus of the response to the relationship between images and scenes lies in the primary visual cortex (V1, if not earlier in the visual system, since the brightness of colours (as opposed to their luminance accords with activity in V1 as measured with fMRI. CONCLUSIONS: The data suggest that perceptions

  2. Scalable High-Performance Image Registration Framework by Unsupervised Deep Feature Representations Learning.

    Science.gov (United States)

    Wu, Guorong; Kim, Minjeong; Wang, Qian; Munsell, Brent C; Shen, Dinggang

    2016-07-01

    Feature selection is a critical step in deformable image registration. In particular, selecting the most discriminative features that accurately and concisely describe complex morphological patterns in image patches improves correspondence detection, which in turn improves image registration accuracy. Furthermore, since more and more imaging modalities are being invented to better identify morphological changes in medical imaging data, the development of deformable image registration method that scales well to new image modalities or new image applications with little to no human intervention would have a significant impact on the medical image analysis community. To address these concerns, a learning-based image registration framework is proposed that uses deep learning to discover compact and highly discriminative features upon observed imaging data. Specifically, the proposed feature selection method uses a convolutional stacked autoencoder to identify intrinsic deep feature representations in image patches. Since deep learning is an unsupervised learning method, no ground truth label knowledge is required. This makes the proposed feature selection method more flexible to new imaging modalities since feature representations can be directly learned from the observed imaging data in a very short amount of time. Using the LONI and ADNI imaging datasets, image registration performance was compared to two existing state-of-the-art deformable image registration methods that use handcrafted features. To demonstrate the scalability of the proposed image registration framework, image registration experiments were conducted on 7.0-T brain MR images. In all experiments, the results showed that the new image registration framework consistently demonstrated more accurate registration results when compared to state of the art.

  3. Scalable High-Performance Image Registration Framework by Unsupervised Deep Feature Representations Learning.

    Science.gov (United States)

    Wu, Guorong; Kim, Minjeong; Wang, Qian; Munsell, Brent C; Shen, Dinggang

    2016-07-01

    Feature selection is a critical step in deformable image registration. In particular, selecting the most discriminative features that accurately and concisely describe complex morphological patterns in image patches improves correspondence detection, which in turn improves image registration accuracy. Furthermore, since more and more imaging modalities are being invented to better identify morphological changes in medical imaging data, the development of deformable image registration method that scales well to new image modalities or new image applications with little to no human intervention would have a significant impact on the medical image analysis community. To address these concerns, a learning-based image registration framework is proposed that uses deep learning to discover compact and highly discriminative features upon observed imaging data. Specifically, the proposed feature selection method uses a convolutional stacked autoencoder to identify intrinsic deep feature representations in image patches. Since deep learning is an unsupervised learning method, no ground truth label knowledge is required. This makes the proposed feature selection method more flexible to new imaging modalities since feature representations can be directly learned from the observed imaging data in a very short amount of time. Using the LONI and ADNI imaging datasets, image registration performance was compared to two existing state-of-the-art deformable image registration methods that use handcrafted features. To demonstrate the scalability of the proposed image registration framework, image registration experiments were conducted on 7.0-T brain MR images. In all experiments, the results showed that the new image registration framework consistently demonstrated more accurate registration results when compared to state of the art. PMID:26552069

  4. A combinatorial Bayesian and Dirichlet model for prostate MR image segmentation using probabilistic image features.

    Science.gov (United States)

    Li, Ang; Li, Changyang; Wang, Xiuying; Eberl, Stefan; Feng, Dagan; Fulham, Michael

    2016-08-21

    Blurred boundaries and heterogeneous intensities make accurate prostate MR image segmentation problematic. To improve prostate MR image segmentation we suggest an approach that includes: (a) an image patch division method to partition the prostate into homogeneous segments for feature extraction; (b) an image feature formulation and classification method, using the relevance vector machine, to provide probabilistic prior knowledge for graph energy construction; (c) a graph energy formulation scheme with Bayesian priors and Dirichlet graph energy and (d) a non-iterative graph energy minimization scheme, based on matrix differentiation, to perform the probabilistic pixel membership optimization. The segmentation output was obtained by assigning pixels with foreground and background labels based on derived membership probabilities. We evaluated our approach on the PROMISE-12 dataset with 50 prostate MR image volumes. Our approach achieved a mean dice similarity coefficient (DSC) of 0.90  ±  0.02, which surpassed the five best prior-based methods in the PROMISE-12 segmentation challenge. PMID:27461085

  5. A combinatorial Bayesian and Dirichlet model for prostate MR image segmentation using probabilistic image features

    Science.gov (United States)

    Li, Ang; Li, Changyang; Wang, Xiuying; Eberl, Stefan; Feng, Dagan; Fulham, Michael

    2016-08-01

    Blurred boundaries and heterogeneous intensities make accurate prostate MR image segmentation problematic. To improve prostate MR image segmentation we suggest an approach that includes: (a) an image patch division method to partition the prostate into homogeneous segments for feature extraction; (b) an image feature formulation and classification method, using the relevance vector machine, to provide probabilistic prior knowledge for graph energy construction; (c) a graph energy formulation scheme with Bayesian priors and Dirichlet graph energy and (d) a non-iterative graph energy minimization scheme, based on matrix differentiation, to perform the probabilistic pixel membership optimization. The segmentation output was obtained by assigning pixels with foreground and background labels based on derived membership probabilities. We evaluated our approach on the PROMISE-12 dataset with 50 prostate MR image volumes. Our approach achieved a mean dice similarity coefficient (DSC) of 0.90  ±  0.02, which surpassed the five best prior-based methods in the PROMISE-12 segmentation challenge.

  6. IMAGE LABELING FOR LIDAR INTENSITY IMAGE USING K-NN OF FEATURE OBTAINED BY CONVOLUTIONAL NEURAL NETWORK

    Directory of Open Access Journals (Sweden)

    M. Umemura

    2016-06-01

    Full Text Available We propose an image labeling method for LIDAR intensity image obtained by Mobile Mapping System (MMS using K-Nearest Neighbor (KNN of feature obtained by Convolutional Neural Network (CNN. Image labeling assigns labels (e.g., road, cross-walk and road shoulder to semantic regions in an image. Since CNN is effective for various image recognition tasks, we try to use the feature of CNN (Caffenet pre-trained by ImageNet. We use 4,096-dimensional feature at fc7 layer in the Caffenet as the descriptor of a region because the feature at fc7 layer has effective information for object classification. We extract the feature by the Caffenet from regions cropped from images. Since the similarity between features reflects the similarity of contents of regions, we can select top K similar regions cropped from training samples with a test region. Since regions in training images have manually-annotated ground truth labels, we vote the labels attached to top K similar regions to the test region. The class label with the maximum vote is assigned to each pixel in the test image. In experiments, we use 36 LIDAR intensity images with ground truth labels. We divide 36 images into training (28 images and test sets (8 images. We use class average accuracy and pixel-wise accuracy as evaluation measures. Our method was able to assign the same label as human beings in 97.8% of the pixels in test LIDAR intensity images.

  7. Image Labeling for LIDAR Intensity Image Using K-Nn of Feature Obtained by Convolutional Neural Network

    Science.gov (United States)

    Umemura, Masaki; Hotta, Kazuhiro; Nonaka, Hideki; Oda, Kazuo

    2016-06-01

    We propose an image labeling method for LIDAR intensity image obtained by Mobile Mapping System (MMS) using K-Nearest Neighbor (KNN) of feature obtained by Convolutional Neural Network (CNN). Image labeling assigns labels (e.g., road, cross-walk and road shoulder) to semantic regions in an image. Since CNN is effective for various image recognition tasks, we try to use the feature of CNN (Caffenet) pre-trained by ImageNet. We use 4,096-dimensional feature at fc7 layer in the Caffenet as the descriptor of a region because the feature at fc7 layer has effective information for object classification. We extract the feature by the Caffenet from regions cropped from images. Since the similarity between features reflects the similarity of contents of regions, we can select top K similar regions cropped from training samples with a test region. Since regions in training images have manually-annotated ground truth labels, we vote the labels attached to top K similar regions to the test region. The class label with the maximum vote is assigned to each pixel in the test image. In experiments, we use 36 LIDAR intensity images with ground truth labels. We divide 36 images into training (28 images) and test sets (8 images). We use class average accuracy and pixel-wise accuracy as evaluation measures. Our method was able to assign the same label as human beings in 97.8% of the pixels in test LIDAR intensity images.

  8. An Open Source Agenda for Research Linking Text and Image Content Features.

    Science.gov (United States)

    Goodrum, Abby A.; Rorvig, Mark E.; Jeong, Ki-Tai; Suresh, Chitturi

    2001-01-01

    Proposes methods to utilize image primitives to support term assignment for image classification. Proposes to release code for image analysis in a common tool set for other researchers to use. Of particular focus is the expansion of work by researchers in image indexing to include image content-based feature extraction capabilities in their work.…

  9. The gray run length and its statistical texture features of coal flotation froth image

    Energy Technology Data Exchange (ETDEWEB)

    Wang Yong; Yang Gong-xun; Lu Mai-xi; Gao Shu-hua [China University of Mining and Technology, Beijing (China). School of Mechanical Electronic and Information Engineering

    2006-07-01

    Aiming at the problem of statistical texture features of coal flotation froth image, many images of coal flotation froth were collected in laboratory. The types and features of froth image were analyzed. Method of extracting gray run length matrix was presented. The run length factors were extracted, which show visual feature of froth. Relationship of these features were studied with flotation time. The result shows that theses parameters show the texture features of coal flotation froth image, which has relationship with special types of froth. The information about froth was offered for visual supervision system of coal flotation. 6 refs., 7 figs.

  10. Detection of Brain Tumor and Extraction of Texture Features using Magnetic Resonance Images

    Directory of Open Access Journals (Sweden)

    Prof. Dilip Kumar Gandhi

    2012-10-01

    Full Text Available Brain Cancer Detection system is designed. Aim of this paper is to locate the tumor and determine the texture features from a Brain Cancer affected MRI. A computer based diagnosis is performed in order to detect the tumors from given Magnetic Resonance Image. Basic image processing techniques are used to locate the tumor region. Basic techniques consist of image enhancement, image bianarization, and image morphological operations. Texture features are computed using the Gray Level Co-occurrence Matrix. Texture features consists of five distinct features. Selective features or the combination of selective features will be used in the future to determine the class of the query image. Astrocytoma type of Brain Cancer affected images are used only for simplicity

  11. Imaging features of central nervous system fungal infections

    Directory of Open Access Journals (Sweden)

    Jain Krishan

    2007-01-01

    Full Text Available Fungal infections of the central nervous system (CNS are rare in the general population and are invariably secondary to primary focus elsewhere, usually in the lung or intestine. Except for people with longstanding diabetes, they are most frequently encountered in immunocompromised patients such as those with acquired immunodeficiency syndrome or after organ transplantation. Due to the lack of inflammatory response, neuroradiological findings are often nonspecific and are frequently mistaken for tuberculous meningitis, pyogenic abscess or brain tumor. Intracranial fungal infections are being identified more frequently due to the increased incidence of AIDS patients, better radiological investigations, more sensitive microbiological techniques and better critical care of moribund patients. Although almost any fungus may cause encephalitis, cryptococcal meningoencephalitis is most frequently seen, followed by aspergillosis and candidiasis. The biology, epidemiology and imaging features of the common fungal infections of the CNS will be reviewed. The radiographic appearance alone is often not specific, but the combination of the appropriate clinical setting along with computed tomography or magnetic resonance may help to suggest the correct diagnosis.

  12. KEYWORD AND IMAGE CONTENT FEATURES FOR IMAGE INDEXING AND RETRIEVAL WITHIN COMPRESSED DOMAIN

    Directory of Open Access Journals (Sweden)

    Irianto .

    2009-01-01

    Full Text Available The central problem of most Content Based Image Retrieval approaches is poor quality in terms of sensitivity (recall and specificity (precision. To overcome this problem, the semantic gap between high-level concepts and low-level features has been acknowledged. In this paper we introduce an approach to reduce the impact of the semantic gap by integrating high-level (semantic and low-level features to improve the quality of Image Retrieval queries. Our experiments have been carried out by applying two hierarchical procedures. The first approach is called keyword-content, and the second content-keyword. Our proposed approaches show better results compared to a single method (keyword or content based in term of recall and precision. The average precision has increased by up to 50%.

  13. Feature-point-extracting-based automatically mosaic for composite microscopic images

    Institute of Scientific and Technical Information of China (English)

    YIN YanSheng; ZHAO XiuYang; TIAN XiaoFeng; LI Jia

    2007-01-01

    Image mosaic is a crucial step in the three-dimensional reconstruction of composite materials to align the serial images. A novel method is adopted to mosaic two SiC/Al microscopic images with an amplification coefficient of 1000. The two images are denoised by Gaussian model, and feature points are then extracted by using Harris corner detector. The feature points are filtered through Canny edge detector. A 40x40 feature template is chosen by sowing a seed in an overlapped area of the reference image, and the homologous region in floating image is acquired automatically by the way of correlation analysis. The feature points in matched templates are used as feature point-sets. Using the transformational parameters acquired by SVD-ICP method, the two images are transformed into the universal coordinates and merged to the final mosaic image.

  14. Diabetic mastopathy: Imaging features and the role of image-guided biopsy in its diagnosis

    Energy Technology Data Exchange (ETDEWEB)

    Kim, Jong Hyeon; Kim, Eun Kyung; Kim, Min Jung; Moon, Hee Jung; Yoon, Jung Hyun [Dept. of Radiology, Research Institute of Radiological Science, Yonsei University College of Medicine, Seoul (Korea, Republic of)

    2016-03-15

    The goal of this study was to evaluate the imaging features of diabetic mastopathy (DMP) and the role of image-guided biopsy in its diagnosis. Two experienced radiologists retrospectively reviewed the mammographic and sonographic images of 19 pathologically confirmed DMP patients. The techniques and results of the biopsies performed in each patient were also reviewed. Mammograms showed negative findings in 78% of the patients. On ultrasonography (US), 13 lesions were seen as masses and six as non-mass lesions. The US features of the mass lesions were as follows: irregular shape (69%), oval shape (31%), indistinct margin (69%), angular margin (15%), microlobulated margin (8%), well-defined margin (8%), heterogeneous echogenicity (62%), hypoechoic echogenicity (38%), posterior shadowing (92%), parallel orientation (100%), the absence of calcifications (100%), and the absence of vascularity (100%). Based on the US findings, 17 lesions (89%) were classified as Breast Imaging Reporting and Data System category 4 and two (11%) as category 3. US-guided core biopsy was performed in 18 patients, and 10 (56%) were diagnosed with DMP on that basis. An additional vacuum-assisted biopsy was performed in seven patients and all were diagnosed with DMP. The US features of DMP were generally suspicious for malignancy, whereas the mammographic findings were often negative or showed only focal asymmetry. Core biopsy is an adequate method for initial pathological diagnosis. However, since it yields non-diagnostic results in a considerable number of cases, the evaluation of correlations between imaging and pathology plays an important role in the diagnostic process.

  15. An Algorithm of Image Contrast Enhancement Based on Pixels Neighborhood’s Local Feature

    Directory of Open Access Journals (Sweden)

    Chen Yan

    2013-12-01

    Full Text Available In this study, we proposed an algorithm of Image Contrast enhancement based on local feature to acquire edge information of image, remove Ray Imaging noise and overcome edge blurry and other defects. This method can extract edge features and finish contrast enhancement in varying degrees for pixels neighborhood with different characteristics by using neighborhood local variance and complexity function, which can achieve local features enhancement. The stimulation shows that the method can not only enhance the contrast of the entire image, but also effectively preserves image edge information and improve image quality.

  16. A new approach for 3D reconstruction from bright field TEM imaging: Beam precession assisted electron tomography

    International Nuclear Information System (INIS)

    The successful combination of electron beam precession and bright field electron tomography for 3D reconstruction is reported. Beam precession is demonstrated to be a powerful technique to reduce the contrast artifacts due to diffraction and curvature in thin foils. Taking advantage of these benefits, Precession assisted electron tomography has been applied to reconstruct the morphology of Sn precipitates embedded in an Al matrix, from a tilt series acquired in a range from +49o to -61o at intervals of 2o and with a precession angle of 0.6o in bright field mode. The combination of electron tomography and beam precession in conventional TEM mode is proposed as an alternative procedure to obtain 3D reconstructions of nano-objects without a scanning system or a high angle annular dark field detector. -- Highlights: → Electron beam precession reduces spurious diffraction contrast in bright field mode. → Bend contour related contrast depends on precession angle. → Electron beam precession is combined with bright field electron tomography. → Precession assisted BF tomography allowed 3D reconstruction of a Sn precipitate.

  17. Topographic Feature Extraction for Bengali and Hindi Character Images

    CERN Document Server

    Bag, Soumen; 10.5121/sipij.2011.2215

    2011-01-01

    Feature selection and extraction plays an important role in different classification based problems such as face recognition, signature verification, optical character recognition (OCR) etc. The performance of OCR highly depends on the proper selection and extraction of feature set. In this paper, we present novel features based on the topography of a character as visible from different viewing directions on a 2D plane. By topography of a character we mean the structural features of the strokes and their spatial relations. In this work we develop topographic features of strokes visible with respect to views from different directions (e.g. North, South, East, and West). We consider three types of topographic features: closed region, convexity of strokes, and straight line strokes. These features are represented as a shape-based graph which acts as an invariant feature set for discriminating very similar type characters efficiently. We have tested the proposed method on printed and handwritten Bengali and Hindi...

  18. MR imaging of the neonatal brain: Pathologic features

    International Nuclear Information System (INIS)

    Seventy-three neonates, aged 29-43 weeks since conception, were studied. US and/or CT correlations were obtained in most infants with pathology. In the first 4-5 days after hemorrhage, US and CT were superior to MR imaging, but after that time MR imaging was the single best modality for imaging blood. In early premature infants with very watery white matter, US detected infarction and brain edema that were poorly seen on both MR imaging and CT. However, in late premature and full-term infants, MR imaging was better than CT in distinguishing between normal white matter and infarction. Only MR imaging disclosed delayed myelination in 13 term infants with hydrocephalus and severe asphyxia. MR imaging with play an important role in imaging neonates once MR imaging-compatible monitors and neonatal head coils become widely available

  19. 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.

  20. Biomedical Imaging Modality Classification Using Combined Visual Features and Textual Terms

    Directory of Open Access Journals (Sweden)

    Xian-Hua Han

    2011-01-01

    extraction from medical images and fuses the different extracted visual features and textual feature for modality classification. To extract visual features from the images, we used histogram descriptor of edge, gray, or color intensity and block-based variation as global features and SIFT histogram as local feature. For textual feature of image representation, the binary histogram of some predefined vocabulary words from image captions is used. Then, we combine the different features using normalized kernel functions for SVM classification. Furthermore, for some easy misclassified modality pairs such as CT and MR or PET and NM modalities, a local classifier is used for distinguishing samples in the pair modality to improve performance. The proposed strategy is evaluated with the provided modality dataset by ImageCLEF 2010.

  1. Feature Coverage Indexes for Dual Homography Estimation in Constructing Panorama Image

    Directory of Open Access Journals (Sweden)

    Kyungkoo Jun

    2016-01-01

    Full Text Available Enlarged images can be obtained by various methods. Stitching is one of the efficient methods. It can produce panoramic images by stitching adjacent images which contain overlapping regions even though they are obtained through separate image sensors. Images that contain multiple different planes are hard to be stitched together because each plane has a different homography matrix for perspective warping. For this, a dual homography was proposed. However its performance varies depending on feature detectors which are used to find matching feature points between images. In this paper, we propose three feature coverage indexes which evaluate the stitching performance of feature detectors and predict the outcomes of the stitching. We evaluate four well-known feature detectors by the proposed indexes by applying them to the image stitching process and show that the prediction by the index values coincides with the stitching results.

  2. [Image Feature Extraction and Discriminant Analysis of Xinjiang Uygur Medicine Based on Color Histogram].

    Science.gov (United States)

    Hamit, Murat; Yun, Weikang; Yan, Chuanbo; Kutluk, Abdugheni; Fang, Yang; Alip, Elzat

    2015-06-01

    Image feature extraction is an important part of image processing and it is an important field of research and application of image processing technology. Uygur medicine is one of Chinese traditional medicine and researchers pay more attention to it. But large amounts of Uygur medicine data have not been fully utilized. In this study, we extracted the image color histogram feature of herbal and zooid medicine of Xinjiang Uygur. First, we did preprocessing, including image color enhancement, size normalizition and color space transformation. Then we extracted color histogram feature and analyzed them with statistical method. And finally, we evaluated the classification ability of features by Bayes discriminant analysis. Experimental results showed that high accuracy for Uygur medicine image classification was obtained by using color histogram feature. This study would have a certain help for the content-based medical image retrieval for Xinjiang Uygur medicine. PMID:26485983

  3. A novel registration method for retinal images based on local features

    OpenAIRE

    Chen, Jian; R Theodore Smith; Tian, Jie; Laine, Andrew F

    2008-01-01

    Sometimes it is very hard to automatically detect the bifurcations of vascular network in retinal images so that the general feature based registration methods will fail to register two images. In order to solve this problem, we developed a novel local feature based retinal image registration method. We first detect the corner points instead of bifurcations since corner points are sufficient and uniformly distributed in the overlaps. Second, a novel highly distinctive local feature is extract...

  4. The Matching Research of Strawberry Diseases Image Features Based on KD-Tree Search Method

    OpenAIRE

    Jianshu, Chen; Jianlun, Wang; Shuting, Wang; Hao, Liu

    2013-01-01

    International audience According to the problem of the low matching accuracy rate and the low speed in the matching technology for image search, we choose the image of the strawberry diseases as the object of the research, to extract the feature of strawberry diseases image and then do cluster analysis using SPSS, and choose the feature combination according to the clustering effect. Do search matching experiments on the feature combination by KD-Tree matching algorithm respectively, and d...

  5. Content-Based Digital Image Retrieval based on Multi-Feature Amalgamation

    Directory of Open Access Journals (Sweden)

    Linhao Li

    2013-12-01

    Full Text Available In actual implementation, digital image retrieval are facing all kinds of problems. There still exists some difficulty in measures and methods for application. Currently there is not a unambiguous algorithm which can directly shown the obvious feature of image content and satisfy the color, scale invariance and rotation invariance of feature simultaneously. So the related technology about image retrieval based on content is analyzed by us. The research focused on global features such as seven HU invariant moments, edge direction histogram and eccentricity. The method for blocked image is also discussed. During the process of image matching, the extracted image features are looked as the points in vector space. The similarity of two images is measured through the closeness between two points and the similarity is calculated by Euclidean distance and the intersection distance of histogram. Then a novel method based on multi-features amalgamation is proposed, to solve the problems in retrieval method for global feature and local feature. It extracts the eccentricity, seven HU invariant moments and edge direction histogram to calculate the similarity distance of each feature of the images, then they are normalized. Contraposing the interior of global feature the weighted feature distance is adopted to form similarity measurement function for retrieval. The features of blocked images are extracted with the partitioning method based on polar coordinate. Finally by the idea of hierarchical retrieval between global feature and local feature, the results are output through global features like invariant moments etc. These results will be taken as the input of local feature match for the second-layer retrieval, which can improve the accuracy of retrieval effectively.

  6. Image registration algorithm using Mexican hat function-based operator and grouped feature matching strategy.

    Directory of Open Access Journals (Sweden)

    Feng Jin

    Full Text Available Feature detection and matching are crucial for robust and reliable image registration. Although many methods have been developed, they commonly focus on only one class of image features. The methods that combine two or more classes of features are still novel and significant. In this work, methods for feature detection and matching are proposed. A Mexican hat function-based operator is used for image feature detection, including the local area detection and the feature point detection. For the local area detection, we use the Mexican hat operator for image filtering, and then the zero-crossing points are extracted and merged into the area borders. For the feature point detection, the Mexican hat operator is performed in scale space to get the key points. After the feature detection, an image registration is achieved by using the two classes of image features. The feature points are grouped according to a standardized region that contains correspondence to the local area, precise registration is achieved eventually by the grouped points. An image transformation matrix is estimated by the feature points in a region and then the best one is chosen through competition of a set of the transformation matrices. This strategy has been named the Grouped Sample Consensus (GCS. The GCS has also ability for removing the outliers effectively. The experimental results show that the proposed algorithm has high registration accuracy and small computational volume.

  7. A Partial Intensity Invariant Feature Descriptor for Multimodal Retinal Image Registration

    OpenAIRE

    Chen, Jian; Tian, Jie; Lee, Noah; Zheng, Jian; Smith, R. Theodore; Laine, Andrew F

    2010-01-01

    Detection of vascular bifurcations is a challenging task in multimodal retinal image registration. Existing algorithms based on bifurcations usually fail in correctly aligning poor quality retinal image pairs. To solve this problem, we propose a novel highly distinctive local feature descriptor named partial intensity invariant feature descriptor (PIIFD) and describe a robust automatic retinal image registration framework named Harris-PIIFD. PIIFD is invariant to image rotation, partially inv...

  8. Focal hepatic lesions with peripheral eosinophilia: imaging features of various disease

    Energy Technology Data Exchange (ETDEWEB)

    Seo, Joon Beom; Han, Joon Koo; Kim, Tae Kyoung; Choi, Byung Ihn; Han, Man Chung [Seoul National Univ. College of Medicine, Seoul (Korea, Republic of); Song, Chi Sung [Seoul City Boramae Hospital, Seoul (Korea, Republic of)

    1999-01-01

    Due to the recent advent of various imaging modalities such as ultrasonography, computed tomography and magnetic resonance imaging, as well as knowledge of the characteristic imaging features of hepatic lesions, radiologic examination plays a major role in the differential diagnosis of focal hepatic lesions. However, various 'nonspecific' or 'unusual' imaging features of focal hepatic lesions are occasionally encountered, and this makes correct diagnosis difficult. In such a situation, the presence of peripheral eosinophilia helps narrow the differential diagnoses. The aim of this pictorial essay is to describe the imaging features of various disease entities which cause focal hepatic lesions and peripheral eosinophilia.

  9. [Research on non-rigid medical image registration algorithm based on SIFT feature extraction].

    Science.gov (United States)

    Wang, Anna; Lu, Dan; Wang, Zhe; Fang, Zhizhen

    2010-08-01

    In allusion to non-rigid registration of medical images, the paper gives a practical feature points matching algorithm--the image registration algorithm based on the scale-invariant features transform (Scale Invariant Feature Transform, SIFT). The algorithm makes use of the image features of translation, rotation and affine transformation invariance in scale space to extract the image feature points. Bidirectional matching algorithm is chosen to establish the matching relations between the images, so the accuracy of image registrations is improved. On this basis, affine transform is chosen to complement the non-rigid registration, and normalized mutual information measure and PSO optimization algorithm are also chosen to optimize the registration process. The experimental results show that the method can achieve better registration results than the method based on mutual information.

  10. Fast Image Retrieval of Textile Industrial Accessory Based on Multi-Feature Fusion

    Institute of Scientific and Technical Information of China (English)

    沈文忠; 杨杰

    2004-01-01

    A hierarchical retrieval scheme of the accessory image database is proposed based on textile industrial accessory contour feature and region feature. At first smallest enclosed rectangle[1] feature (degree of accessory coordination) is used to filter the image database to decouple the image search scope. After the accessory contour information and region information are extracted, the fusion multi-feature of the centroid distance Fourier descriptor and distance distribution histogram is adopted to finish image retrieval accurately. All the features above are invariable under translation, scaling and rotation. Results from the test on the image database including 1,000 accessory images demonstrate that the method is effective and practical with high accuracy and fast speed.

  11. A novel high-contrast imaging technique based on optical tunneling to search for faint companions around bright stars at the limit of diffraction

    CERN Document Server

    Derigs, Dominik; Ghosh, Dhriti Sundar; Abel-Tibérini, Laëtitia

    2016-01-01

    We present a novel application of optical tunneling in the context of high-angular resolution, high-contrast techniques with the aim of improving direct imaging capabilities of faint companions in the vicinity of bright stars. In contrast to existing techniques like coronagraphy, we apply well-established techniques from integrated optics to exclusively extinct a very narrow angular direction coming from the sky. This extinction is achieved in the pupil plane and does not suffer from diffraction pattern residuals. We give a comprehensive presentation of the underlying theory as well as first laboratory results.

  12. A comparison study of textural features between FFDM and film mammogram images

    Science.gov (United States)

    Jing, Hao; Yang, Yongyi; Wernick, Miles N.; Yarusso, Laura M.; Nishikawa, Robert M.

    2011-03-01

    In this work, we conducted an imaging study to make a direct, quantitative comparison of image features measured by film and full-field digital mammography (FFDM). We acquired images of cadaver breast specimens containing simulated microcalcifications using both a GE digital mammography system and a screen-film system. To quantify the image features, we calculated and compared a set of 12 texture features derived from spatial gray-level dependence matrices. Our results demonstrate that there is a great degree of agreement between film and FFDM, with the correlation coefficient of the feature vector (formed by the 12 textural features) being 0.9569 between the two; in addition, a paired sign test reveals no significant difference between film and FFDM features. These results indicate that textural features may be interchangeable between film and FFDM for CAD algorithms.

  13. Feature Extraction with Ordered Mean Values for Content Based Image Classification

    Directory of Open Access Journals (Sweden)

    Sudeep Thepade

    2014-01-01

    Full Text Available Categorization of images into meaningful classes by efficient extraction of feature vectors from image datasets has been dependent on feature selection techniques. Traditionally, feature vector extraction has been carried out using different methods of image binarization done with selection of global, local, or mean threshold. This paper has proposed a novel technique for feature extraction based on ordered mean values. The proposed technique was combined with feature extraction using discrete sine transform (DST for better classification results using multitechnique fusion. The novel methodology was compared to the traditional techniques used for feature extraction for content based image classification. Three benchmark datasets, namely, Wang dataset, Oliva and Torralba (OT-Scene dataset, and Caltech dataset, were used for evaluation purpose. Performance measure after evaluation has evidently revealed the superiority of the proposed fusion technique with ordered mean values and discrete sine transform over the popular approaches of single view feature extraction methodologies for classification.

  14. Image Retrieval via Relevance Vector Machine with Multiple Features

    OpenAIRE

    Zemin Liu; Wei Zong

    2014-01-01

    With the fast development of computer network technique, there is large amount of image information every day. Researchers have paid more and more attention to the problem of how users quickly retrieving and identifying the images that they may interest. Meanwhile, with the rapid development of artificial intelligence and pattern recognition techniques, it provides people with new thought on the study on complex image retrieval while it’s very difficult for traditional machine learning ...

  15. Nasopharyngeal carcinoma: Imaging features of unusual cancer in children

    Directory of Open Access Journals (Sweden)

    Ayda A. Youssef

    2015-12-01

    Conclusion: Pediatric NPC is generally not suspected clinically until late into the disease process. Awareness that NPC can occur in children should prompt careful evaluation for distinctive radiographic features. Earlier diagnosis may then direct the patient to timely appropriate therapy when these key radiographic features are present and recognized.

  16. Unsupervised detection of abnormalities in medical images using salient features

    Science.gov (United States)

    Alpert, Sharon; Kisilev, Pavel

    2014-03-01

    In this paper we propose a new method for abnormality detection in medical images which is based on the notion of medical saliency. The proposed method is general and is suitable for a variety of tasks related to detection of: 1) lesions and microcalcifications (MCC) in mammographic images, 2) stenoses in angiographic images, 3) lesions found in magnetic resonance (MRI) images of brain. The main idea of our approach is that abnormalities manifest as rare events, that is, as salient areas compared to normal tissues. We define the notion of medical saliency by combining local patch information from the lightness channel with geometric shape local descriptors. We demonstrate the efficacy of the proposed method by applying it to various modalities, and to various abnormality detection problems. Promising results are demonstrated for detection of MCC and of masses in mammographic images, detection of stenoses in angiography images, and detection of lesions in brain MRI. We also demonstrate how the proposed automatic abnormality detection method can be combined with a system that performs supervised classification of mammogram images into benign or malignant/premalignant MCC's. We use a well known DDSM mammogram database for the experiment on MCC classification, and obtain 80% accuracy in classifying images containing premalignant MCC versus benign ones. In contrast to supervised detection methods, the proposed approach does not rely on ground truth markings, and, as such, is very attractive and applicable for big corpus image data processing.

  17. Multiple Myeloma: A Review of Imaging Features and Radiological Techniques

    Directory of Open Access Journals (Sweden)

    C. F. Healy

    2011-01-01

    Full Text Available The recently updated Durie/Salmon PLUS staging system published in 2006 highlights the many advances that have been made in the imaging of multiple myeloma, a common malignancy of plasma cells. In this article, we shall focus primarily on the more sensitive and specific whole-body imaging techniques, including whole-body computed tomography, whole-body magnetic resonance imaging, and positron emission computed tomography. We shall also discuss new and emerging imaging techniques and future developments in the radiological assessment of multiple myeloma.

  18. Multiple myeloma: a review of imaging features and radiological techniques.

    Science.gov (United States)

    Healy, C F; Murray, J G; Eustace, S J; Madewell, J; O'Gorman, P J; O'Sullivan, P

    2011-01-01

    The recently updated Durie/Salmon PLUS staging system published in 2006 highlights the many advances that have been made in the imaging of multiple myeloma, a common malignancy of plasma cells. In this article, we shall focus primarily on the more sensitive and specific whole-body imaging techniques, including whole-body computed tomography, whole-body magnetic resonance imaging, and positron emission computed tomography. We shall also discuss new and emerging imaging techniques and future developments in the radiological assessment of multiple myeloma.

  19. Analysis of mammographic microcalcifications using gray-level image structure features

    Energy Technology Data Exchange (ETDEWEB)

    Dhawan, A.P.; Chitre, Y.; Kaiser-Bonasso, C.; Moskowitz, M. [Univ. of Cincinnati, OH (United States)

    1996-06-01

    Most of the techniques used in the computerized analysis of mammographic microcalcifications use shape features on the segmented regions of microcalcifications extracted from the digitized mammograms. Since mammographic images usually suffer from poorly defined microcalcification features, the extraction of shape features based on a segmentation process may not accurately represent microcalcifications. In this paper, the authors define a set of image structure features for classification of malignancy. Two categories of correlated gray-level image structure features are defined for classification of difficult-to-diagnose cases. The first category of features includes second-order histogram statistics-based features representing the global texture and the wavelet decomposition-based features representing the local texture of the microcalcification area of interest. The second category of features represents the first-order gray-level histogram-based statistics of the segmented microcalcification regions and the size, number, and distance features of the segmented microcalcification cluster. Various features in each category were correlated with the biopsy examination results of 191 difficult-to-diagnose cases for selection of the best set of features representing the complete gray-level image structure information. The selection of the best features was performed using the multivariate cluster analysis as well as a genetic algorithm (GA)-based search method. The selected features were used for classification using backpropagation neural network and parametric statistical classifiers. Receiver operating characteristic (ROC) analysis was performed to compare the neural network-based classification with linear and k-nearest neighbor (KNN) classifiers.

  20. Change Detection in Uav Video Mosaics Combining a Feature Based Approach and Extended Image Differencing

    Science.gov (United States)

    Saur, Günter; Krüger, Wolfgang

    2016-06-01

    Change detection is an important task when using unmanned aerial vehicles (UAV) for video surveillance. We address changes of short time scale using observations in time distances of a few hours. Each observation (previous and current) is a short video sequence acquired by UAV in near-Nadir view. Relevant changes are, e.g., recently parked or moved vehicles. Examples for non-relevant changes are parallaxes caused by 3D structures of the scene, shadow and illumination changes, and compression or transmission artifacts. In this paper we present (1) a new feature based approach to change detection, (2) a combination with extended image differencing (Saur et al., 2014), and (3) the application to video sequences using temporal filtering. In the feature based approach, information about local image features, e.g., corners, is extracted in both images. The label "new object" is generated at image points, where features occur in the current image and no or weaker features are present in the previous image. The label "vanished object" corresponds to missing or weaker features in the current image and present features in the previous image. This leads to two "directed" change masks and differs from image differencing where only one "undirected" change mask is extracted which combines both label types to the single label "changed object". The combination of both algorithms is performed by merging the change masks of both approaches. A color mask showing the different contributions is used for visual inspection by a human image interpreter.

  1. Image mosaicking based on feature points using color-invariant values

    Science.gov (United States)

    Lee, Dong-Chang; Kwon, Oh-Seol; Ko, Kyung-Woo; Lee, Ho-Young; Ha, Yeong-Ho

    2008-02-01

    In the field of computer vision, image mosaicking is achieved using image features, such as textures, colors, and shapes between corresponding images, or local descriptors representing neighborhoods of feature points extracted from corresponding images. However, image mosaicking based on feature points has attracted more recent attention due to the simplicity of the geometric transformation, regardless of distortion and differences in intensity generated by camera motion in consecutive images. Yet, since most feature-point matching algorithms extract feature points using gray values, identifying corresponding points becomes difficult in the case of changing illumination and images with a similar intensity. Accordingly, to solve these problems, this paper proposes a method of image mosaicking based on feature points using color information of images. Essentially, the digital values acquired from a real digital color camera are converted to values of a virtual camera with distinct narrow bands. Values based on the surface reflectance and invariant to the chromaticity of various illuminations are then derived from the virtual camera values and defined as color-invariant values invariant to changing illuminations. The validity of these color-invariant values is verified in a test using a Macbeth Color-Checker under simulated illuminations. The test also compares the proposed method using the color-invariant values with the conventional SIFT algorithm. The accuracy of the matching between the feature points extracted using the proposed method is increased, while image mosaicking using color information is also achieved.

  2. An adequate approach to image retrieval based on local level feature extraction

    International Nuclear Information System (INIS)

    Image retrieval based on text annotation has become obsolete and is no longer interesting for scientists because of its high time complexity and low precision in results. Alternatively, increase in the amount of digital images has generated an excessive need for an accurate and efficient retrieval system. This paper proposes content based image retrieval technique at a local level incorporating all the rudimentary features. Image undergoes the segmentation process initially and each segment is then directed to the feature extraction process. The proposed technique is also based on image?s content which primarily includes texture, shape and color. Besides these three basic features, FD (Fourier Descriptors) and edge histogram descriptors are also calculated to enhance the feature extraction process by taking hold of information at the boundary. Performance of the proposed method is found to be quite adequate when compared with the results from one of the best local level CBIR (Content Based Image Retrieval) techniques. (author)

  3. An Adequate Approach to Image Retrieval Based on Local Level Feature Extraction

    Directory of Open Access Journals (Sweden)

    Sumaira Muhammad Hayat Khan

    2010-10-01

    Full Text Available Image retrieval based on text annotation has become obsolete and is no longer interesting for scientists because of its high time complexity and low precision in results. Alternatively, increase in the amount of digital images has generated an excessive need for an accurate and efficient retrieval system. This paper proposes content based image retrieval technique at a local level incorporating all the rudimentary features. Image undergoes the segmentation process initially and each segment is then directed to the feature extraction process. The proposed technique is also based on image?s content which primarily includes texture, shape and color. Besides these three basic features, FD (Fourier Descriptors and edge histogram descriptors are also calculated to enhance the feature extraction process by taking hold of information at the boundary. Performance of the proposed method is found to be quite adequate when compared with the results from one of the best local level CBIR (Content Based Image Retrieval techniques.

  4. Application of Fisher Score and mRMR Techniques for Feature Selection in Compressed Medical Images

    Directory of Open Access Journals (Sweden)

    Vamsidhar Enireddy

    2015-12-01

    Full Text Available In nowadays there is a large increase in the digital medical images and different medical imaging equipments are available for diagnoses, medical professionals are increasingly relying on computer aided techniques for both indexing these images and retrieving similar images from large repositories. To develop systems which are computationally less intensive without compromising on the accuracy from the high dimensional feature space is always challenging. In this paper an investigation is made on the retrieval of compressed medical images. Images are compressed using the visually lossless compression technique. Shape and texture features are extracted and best features are selected using the fisher technique and mRMR. Using these selected features RNN with BPTT was utilized for classification of the compressed images.

  5. A Novel Technique for Shape Feature Extraction Using Content Based Image Retrieval

    Directory of Open Access Journals (Sweden)

    Dhanoa Jaspreet Singh

    2016-01-01

    Full Text Available With the advent of technology and multimedia information, digital images are increasing very quickly. Various techniques are being developed to retrieve/search digital information or data contained in the image. Traditional Text Based Image Retrieval System is not plentiful. Since it is time consuming as it require manual image annotation. Also, the image annotation differs with different peoples. An alternate to this is Content Based Image Retrieval (CBIR system. It retrieves/search for image using its contents rather the text, keywords etc. A lot of exploration has been compassed in the range of Content Based Image Retrieval (CBIR with various feature extraction techniques. Shape is a significant image feature as it reflects the human perception. Moreover, Shape is quite simple to use by the user to define object in an image as compared to other features such as Color, texture etc. Over and above, if applied alone, no descriptor will give fruitful results. Further, by combining it with an improved classifier, one can use the positive features of both the descriptor and classifier. So, a tryout will be made to establish an algorithm for accurate feature (Shape extraction in Content Based Image Retrieval (CBIR. The main objectives of this project are: (a To propose an algorithm for shape feature extraction using CBIR, (b To evaluate the performance of proposed algorithm and (c To compare the proposed algorithm with state of art techniques.

  6. Image feature meaning for automatic key-frame extraction

    Science.gov (United States)

    Di Lecce, Vincenzo; Guerriero, Andrea

    2003-12-01

    Video abstraction and summarization, being request in several applications, has address a number of researches to automatic video analysis techniques. The processes for automatic video analysis are based on the recognition of short sequences of contiguous frames that describe the same scene, shots, and key frames representing the salient content of the shot. Since effective shot boundary detection techniques exist in the literature, in this paper we will focus our attention on key frames extraction techniques to identify the low level visual features of the frames that better represent the shot content. To evaluate the features performance, key frame automatically extracted using these features, are compared to human operator video annotations.

  7. Essential features of Chiari II malformation in MR imaging : an interobserver reliability study-part 1

    NARCIS (Netherlands)

    Geerdink, Niels; van der Vliet, Ton; Rotteveel, Jan J.; Feuth, Ton; Roeleveld, Nel; Mullaart, Reinier A.

    2012-01-01

    Brain MR imaging is essential in the assessment of Chiari II malformation in clinical and research settings concerning spina bifida. However, the interpretation of morphological features of the malformation on MR images may not always be straightforward. In an attempt to select those features that u

  8. Essential features of Chiari II malformation in MR imaging: an interobserver reliability study--part 1.

    NARCIS (Netherlands)

    Geerdink, N.; Vliet, T. van der; Rotteveel, J.J.; Feuth, T.; Roeleveld, N.; Mullaart, R.A.

    2012-01-01

    PURPOSE: Brain MR imaging is essential in the assessment of Chiari II malformation in clinical and research settings concerning spina bifida. However, the interpretation of morphological features of the malformation on MR images may not always be straightforward. In an attempt to select those featur

  9. Integrating Color and Spatial Feature for Content-Based Image Retrieval

    Institute of Scientific and Technical Information of China (English)

    2002-01-01

    In this paper, we present a novel and efficient scheme for extracting, indexing and retrieving color images. Our motivation was to reduce the space overhead of partition-based approaches taking advantage of the fact that only a relatively low number of distinct values of a particular visual feature is present in most images. To extract color feature and build indices into our image database we take into consideration factors such as human color perception and perceptual range, and the image is partitioned into a set of regions by using a simple classifying scheme. The compact color feature vector and the spatial color histogram, which are extracted from the seqmented image region, are used for representing the color and spatial information in the image. We have also developed the region-based distance measures to compare the similarity of two images. Extensive tests on a large image collection were conducted to demonstrate the effectiveness of the proposed approach.

  10. A HYBRID APPROACH BASED MEDICAL IMAGE RETRIEVAL SYSTEM USING FEATURE OPTIMIZED CLASSIFICATION SIMILARITY FRAMEWORK

    Directory of Open Access Journals (Sweden)

    Yogapriya Jaganathan

    2013-01-01

    Full Text Available For the past few years, massive upgradation is obtained in the pasture of Content Based Medical Image Retrieval (CBMIR for effective utilization of medical images based on visual feature analysis for the purpose of diagnosis and educational research. The existing medical image retrieval systems are still not optimal to solve the feature dimensionality reduction problem which increases the computational complexity and decreases the speed of a retrieval process. The proposed CBMIR is used a hybrid approach based on Feature Extraction, Optimization of Feature Vectors, Classification of Features and Similarity Measurements. This type of CBMIR is called Feature Optimized Classification Similarity (FOCS framework. The selected features are Textures using Gray level Co-occurrence Matrix Features (GLCM and Tamura Features (TF in which extracted features are formed as feature vector database. The Fuzzy based Particle Swarm Optimization (FPSO technique is used to reduce the feature vector dimensionality and classification is performed using Fuzzy based Relevance Vector Machine (FRVM to form groups of relevant image features that provide a natural way to classify dimensionally reduced feature vectors of images. The Euclidean Distance (ED is used as similarity measurement to measure the significance between the query image and the target images. This FOCS approach can get the query from the user and has retrieved the needed images from the databases. The retrieval algorithm performances are estimated in terms of precision and recall. This FOCS framework comprises several benefits when compared to existing CBMIR. GLCM and TF are used to extract texture features and form a feature vector database. Fuzzy-PSO is used to reduce the feature vector dimensionality issues while selecting the important features in the feature vector database in which computational complexity is decreased. Fuzzy based RVM is used for feature classification in which it increases the

  11. Feature Understanding and Target Detection for Sparse Microwave Synthetic Aperture Radar Images

    OpenAIRE

    Zhang Zenghui; Yu Wenxian

    2016-01-01

    Sparse microwave imaging using sparse priors of observed scenes in space, time, frequency, or polarization domain and echo data with sampling rate smaller than the traditional Nyquist rate as well as optimization algorithms for reconstructing the microwave images of observed scenes has many advantages over traditional microwave imaging systems. In sparse microwave imaging, image acquisition and representation vary; therefore, new feature analysis and cognitive interpretation theories and meth...

  12. Survey on Sparse Coded Features for Content Based Face Image Retrieval

    OpenAIRE

    Johnvictor, D.; Selvavinayagam, G.

    2014-01-01

    Content based image retrieval, a technique which uses visual contents of image to search images from large scale image databases according to users' interests. This paper provides a comprehensive survey on recent technology used in the area of content based face image retrieval. Nowadays digital devices and photo sharing sites are getting more popularity, large human face photos are available in database. Multiple types of facial features are used to represent discriminality on large scale hu...

  13. 3D Elastic Registration of Ultrasound Images Based on Skeleton Feature

    Institute of Scientific and Technical Information of China (English)

    LI Dan-dan; LIU Zhi-Yan; SHEN Yi

    2005-01-01

    In order to eliminate displacement and elastic deformation between images of adjacent frames in course of 3D ultrasonic image reconstruction, elastic registration based on skeleton feature was adopt in this paper. A new automatically skeleton tracking extract algorithm is presented, which can extract connected skeleton to express figure feature. Feature points of connected skeleton are extracted automatically by accounting topical curvature extreme points several times. Initial registration is processed according to barycenter of skeleton. Whereafter, elastic registration based on radial basis function are processed according to feature points of skeleton. Result of example demonstrate that according to traditional rigid registration, elastic registration based on skeleton feature retain natural difference in shape for organ's different part, and eliminate slight elastic deformation between frames caused by image obtained process simultaneously. This algorithm has a high practical value for image registration in course of 3D ultrasound image reconstruction.

  14. Kernel Density Feature Points Estimator for Content-Based Image Retrieval

    CERN Document Server

    Zuva, Tranos; Ojo, Sunday O; Ngwira, Seleman M

    2012-01-01

    Research is taking place to find effective algorithms for content-based image representation and description. There is a substantial amount of algorithms available that use visual features (color, shape, texture). Shape feature has attracted much attention from researchers that there are many shape representation and description algorithms in literature. These shape image representation and description algorithms are usually not application independent or robust, making them undesirable for generic shape description. This paper presents an object shape representation using Kernel Density Feature Points Estimator (KDFPE). In this method, the density of feature points within defined rings around the centroid of the image is obtained. The KDFPE is then applied to the vector of the image. KDFPE is invariant to translation, scale and rotation. This method of image representation shows improved retrieval rate when compared to Density Histogram Feature Points (DHFP) method. Analytic analysis is done to justify our m...

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

    KAUST Repository

    Wang, Jingyan

    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.

  16. Image Analysis of Soil Micromorphology: Feature Extraction, Segmentation, and Quality Inference

    Directory of Open Access Journals (Sweden)

    Petros Maragos

    2004-06-01

    Full Text Available We present an automated system that we have developed for estimation of the bioecological quality of soils using various image analysis methodologies. Its goal is to analyze soilsection images, extract features related to their micromorphology, and relate the visual features to various degrees of soil fertility inferred from biochemical characteristics of the soil. The image methodologies used range from low-level image processing tasks, such as nonlinear enhancement, multiscale analysis, geometric feature detection, and size distributions, to object-oriented analysis, such as segmentation, region texture, and shape analysis.

  17. COLOR IMAGE RETRIEVAL BASED ON FEATURE FUSION THROUGH MULTIPLE LINEAR REGRESSION ANALYSIS

    Directory of Open Access Journals (Sweden)

    K. Seetharaman

    2015-08-01

    Full Text Available This paper proposes a novel technique based on feature fusion using multiple linear regression analysis, and the least-square estimation method is employed to estimate the parameters. The given input query image is segmented into various regions according to the structure of the image. The color and texture features are extracted on each region of the query image, and the features are fused together using the multiple linear regression model. The estimated parameters of the model, which is modeled based on the features, are formed as a vector called a feature vector. The Canberra distance measure is adopted to compare the feature vectors of the query and target images. The F-measure is applied to evaluate the performance of the proposed technique. The obtained results expose that the proposed technique is comparable to the other existing techniques.

  18. STATISTICAL PROBABILITY BASED ALGORITHM FOR EXTRACTING FEATURE POINTS IN 2-DIMENSIONAL IMAGE

    Institute of Scientific and Technical Information of China (English)

    Guan Yepeng; Gu Weikang; Ye Xiuqing; Liu Jilin

    2004-01-01

    An algorithm for automatically extracting feature points is developed after the area of feature points in 2-dimensional (2D) imagebeing located by probability theory, correlated methods and criterion for abnormity. Feature points in 2D image can be extracted only by calculating standard deviation of gray within sampled pixels area in our approach statically. While extracting feature points, the limitation to confirm threshold by tentative method according to some a priori information on processing image can be avoided. It is proved that the proposed algorithm is valid and reliable by extracting feature points on actual natural images with abundant and weak texture, including multi-object with complex background, respectively. It can meet the demand of extracting feature points of 2D image automatically in machine vision system.

  19. Featured Image: Hubble's New Views of Debris Disks

    Science.gov (United States)

    Kohler, Susanna

    2016-09-01

    The Hubble image of a second circumstellar debris disk, HD 207917, and its best-fit model.This is a new deep observation made by Hubbles Space Telescope Imaging Spectrograph of the tilted debris disk surrounding the star HD 207129. In a recent study led by Glenn Schneider (Seward Observatory, University of Arizona), three known, nearby circumstellar disks were imaged by Hubble in order to gain a better understanding of the disks ring-like structure. The three central stars of these disks are all G-type solar analogs, and the debris rings bear many similarities to our own Kuiper belt. Imaging of debris disks like these can help us to learn more about how solar systems form around stars like our own. For more information, check out the paper below!CitationGlenn Schneider et al 2016 AJ 152 64. doi:10.3847/0004-6256/152/3/64

  20. An Image Retrieval Method Based on Color and Texture Features

    Institute of Scientific and Technical Information of China (English)

    2006-01-01

    The technique of image retrieval is widely used in science experiment, military affairs, public security,advertisement, family entertainment, library and so on. The existing algorithms are mostly based on the characteristics of color, texture, shape and space relationship. This paper introduced an image retrieval algorithm, which is based on the matching of weighted EMD(Earth Mover's Distance) distance and texture distance. EMD distance is the distance between the histograms of two images in HSV(Hue, Saturation, Value) color space, and texture distance is the L1 distance between the texture spectra of two images. The experimental results show that the retrieval rate can be increased obviously by using the proposed algorithm.

  1. Examplers based image fusion features for face recognition

    CERN Document Server

    James, Alex Pappachen

    2012-01-01

    Examplers of a face are formed from multiple gallery images of a person and are used in the process of classification of a test image. We incorporate such examplers in forming a biologically inspired local binary decisions on similarity based face recognition method. As opposed to single model approaches such as face averages the exampler based approach results in higher recognition accu- racies and stability. Using multiple training samples per person, the method shows the following recognition accuracies: 99.0% on AR, 99.5% on FERET, 99.5% on ORL, 99.3% on EYALE, 100.0% on YALE and 100.0% on CALTECH face databases. In addition to face recognition, the method also detects the natural variability in the face images which can find application in automatic tagging of face images.

  2. The imaging features of MACROLANETM in breast augmentation

    International Nuclear Information System (INIS)

    MacrolaneTM is an injectable, biocompatible, soft-tissue filler that has been available in the UK since 2008 and is promoted for use in breast augmentation. There are few data available on the long-term effects of this relatively new product and concerns have been raised about the implications for breast imaging, in particular breast screening. In this context we present a spectrum of imaging appearances and complications encountered to date.

  3. Imaging features of calcifying pseudoneoplasms of the neuraxis

    International Nuclear Information System (INIS)

    Objective: To identify the imaging characteristics of calcifying pseudoneoplasms of the neuraxis (CAPNON) and do literature review. Methods: Five patients of pathologically-proved CAPNON underwent preoperative MR examination,among which 4 underwent CT scan, 2 underwent DSA examination and 1 underwent SPECT. All imaging data were retrospectively analyzed with the emphasis on imaging characteristics.Results Five patients of CAPNON with the diameter of 1.5 to 5.0 cm were found in five patients (Male 4; Female 1; age 25 to 60 years old). Three lesions were located in the skull base, one was located in the cervical spine and one in the foramen magnum and upper cervical segment. All patients underwent MRI examination and 4 of them also took CT scanning. On plain CT, all lesions showed obvious calcification. On T1WI all masses showed hypointensity, and on T2WI 4 of the lesions showed iso- or hypointensity and 1 heterogeneous signal intensity. On contrast-enhanced MR images, peripheral enhancement was demonstrated in 3 lesions, homogeneous enhancement was found in case and one lesion showed no enhancement. The pathologic analysis indicated that inside the lesions were abundant calcification, fibroepithelial tissue and mucoid matrix and no edema was detected around the lesions. Conclusions: CAPNON displayed the predilection to male adults and the neuraxis was the predilection site. Calcification on CT images, hypointensity on MR images and peripheral enhancement will be helpful for the diagnosis of CAPNON, but the final confirmation still needs the pathologic results. (authors)

  4. Content-based retrieval of remote sensed images using a feature-based approach

    Science.gov (United States)

    Vellaikal, Asha; Dao, Son; Kuo, C.-C. Jay

    1995-01-01

    A feature-based representation model for content-based retrieval from a remote sensed image database is described in this work. The representation is formed by clustering spatially local pixels, and the cluster features are used to process several types of queries which are expected to occur frequently in the context of remote sensed image retrieval. Preliminary experimental results show that the feature-based representation provides a very promising tool for content-based access.

  5. Variability of textural features in FDG PET images due to different acquisition modes and reconstruction parameters

    DEFF Research Database (Denmark)

    Galavis, P.E.; Hollensen, Christian; Jallow, N.;

    2010-01-01

    reconstruction parameters. Lesions were segmented on a default image using the threshold of 40% of maximum SUV. Fifty different texture features were calculated inside the tumors. The range of variations of the features were calculated with respect to the average value. Results. Fifty textural features were...

  6. Rotation and Scale Invariant Wavelet Feature for Content-Based Texture Image Retrieval.

    Science.gov (United States)

    Lee, Moon-Chuen; Pun, Chi-Man

    2003-01-01

    Introduces a rotation and scale invariant log-polar wavelet texture feature for image retrieval. The underlying feature extraction process involves a log-polar transform followed by an adaptive row shift invariant wavelet packet transform. Experimental results show that this rotation and scale invariant wavelet feature is quite effective for image…

  7. A Combined Method of Fractal and GLCM Features for MRI and CT Scan Images Classification

    OpenAIRE

    Redouan Korchiyne; Sidi Mohamed Farssi; Abderrahmane Sbihi; Rajaa Touahni; Mustapha Tahiri Alaoui

    2014-01-01

    Fractal analysis has been shown to be useful in image processing for characterizing shape and gray-scale complexity. The fractal feature is a compact descriptor used to give a numerical measure of the degree of irregularity of the medical images. This descriptor property does not give ownership of the local image structure. In this paper, we present a combination of this parameter based on Box Counting with GLCM Features. This powerful combination has proved good results especiall...

  8. Scale space smoothing, image feature extraction and bessel filters

    OpenAIRE

    Mahmoodi S.; Gunn S.

    2011-01-01

    The Green function of Mumford-Shah functional in the absence of discontinuities is known to be a modified Bessel function of the second kind and zero degree. Such a Bessel function is regularized here and used as a filter for feature extraction. It is demonstrated in this paper that a Bessel filter does not follow the scale space smoothing property of bounded linear filters such as Gaussian filters. The features extracted by the Bessel filter are therefore scale invariant. Edges, blobs, and j...

  9. Feature Understanding and Target Detection for Sparse Microwave Synthetic Aperture Radar Images

    Directory of Open Access Journals (Sweden)

    Zhang Zenghui

    2016-02-01

    Full Text Available Sparse microwave imaging using sparse priors of observed scenes in space, time, frequency, or polarization domain and echo data with sampling rate smaller than the traditional Nyquist rate as well as optimization algorithms for reconstructing the microwave images of observed scenes has many advantages over traditional microwave imaging systems. In sparse microwave imaging, image acquisition and representation vary; therefore, new feature analysis and cognitive interpretation theories and methods should be developed based on current research results. In this study, we analyze the statistical properties of sparse Synthetic Aperture Radar (SAR images and changes in point, line and regional features induced by sparse reconstruction. For SAR images recovered by the spatial sparse model, the statistical distribution degrades, whereas points and lines can be accurately extracted by low sampling rates. Furthermore, the target detection method based on sparse SAR images is studied. Owing to a weak background noise, target detection is easier using sparse SAR images than traditional ones.

  10. MR imaging features of foot involvement in patients with psoriasis

    Energy Technology Data Exchange (ETDEWEB)

    Erdem, C. Zuhal [Department of Radiology, Zonguldak Karaelmas University, School of Medicine, Zonguldak (Turkey)], E-mail: sunarerdem@yahoo.com; Tekin, Nilgun Solak [Department of Dermatology, Zonguldak Karaelmas University, School of Medicine, Zonguldak (Turkey); Sarikaya, Selda [Department of Physical Therapy and Rehabilitation, Zonguldak Karaelmas University, School of Medicine, Zonguldak (Turkey); Erdem, L. Oktay; Gulec, Sezen [Department of Radiology, Zonguldak Karaelmas University, School of Medicine, Zonguldak (Turkey)

    2008-09-15

    Objective: To determine alterations of the soft tissues, tendons, cartilage, joint spaces, and bones of the foot using magnetic resonance (MR) imaging in patients with psoriasis. Materials and methods: Clinical and MR examination of the foot was performed in 26 consecutive patients (52 ft) with psoriasis. As a control group, 10 healthy volunteers (20 ft) were also studied. Joint effusion/synovitis, retrocalcaneal bursitis, retroachilles bursitis, Achilles tendonitis, soft-tissue edema, para-articular enthesophytes, bone marrow edema, sinus tarsi syndrome, enthesopathy at the Achilles attachment and at the plantar fascia attachment, plantar fasciitis, tenosynovitis, subchondral cysts, and bone erosions, joint space narrowing, subchondral signal changes, osteolysis, luxation, and sub-luxation were examined. Results: Clinical signs and symptoms (pain and swelling) due to foot involvement were present in none of the patients while frequency of involvement was 92% (24/26) by MR imaging. The most common MR imaging findings were Achilles tendonitis (acute and peritendinitis) (57%), retrocalcaneal bursitis (50%), joint effusion/synovitis (46%), soft-tissue edema (46%), and para-articular enthesophytes (38%). The most commonly involved anatomical region was the hindfoot (73%). Conclusion: Our data showed that the incidence of foot involvement was very high in asymptomatic patients with psoriasis on MR imaging. Further MR studies are needed to confirm these data. We conclude that MR imaging may be of importance especially in early diagnosis and treatment of inflammatory changes in the foot.

  11. The Machine Recognition for Population Feature of Wheat Images Based on BP Neural Network

    Institute of Scientific and Technical Information of China (English)

    LI Shao-kun; SUO Xing-mei; BAI Zhong-ying; QI Zhi-li; Liu Xiao-hong; GAO Shi-ju; ZHAO Shuang-ning

    2002-01-01

    Recognition and analysis of dynamic information about population images during wheat growth periods can be taken for the base of quantitative diagnosis for wheat growth. A recognition system based on self-learning BP neural network for feature data of wheat population images, such as total green areas and leaves areas was designed in this paper. In addition, some techniques to create favorable conditions for image recognition was discussed, which were as follows: (1) The method of collecting images by a digital camera and assistant equipment under natural conditions in fields. (2) An algorithm of pixei labeling was used to segment image and extract feature. (3)A high pass filter based on Laplacian was used to strengthen image information. The results showed that the ANN system was availability for image recognition of wheat population feature.

  12. Image Retrieval based on Integration between Color and Geometric Moment Features

    International Nuclear Information System (INIS)

    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.

  13. Bioluminescence: a versatile technique for imaging cellular and molecular features

    Science.gov (United States)

    Paley, Miranda A.

    2016-01-01

    Bioluminescence is a ubiquitous imaging modality for visualizing biological processes in vivo. This technique employs visible light and interfaces readily with most cell and tissue types, making it a versatile technology for preclinical studies. Here we review basic bioluminescence imaging principles, along with applications of the technology that are relevant to the medicinal chemistry community. These include noninvasive cell tracking experiments, analyses of protein function, and methods to visualize small molecule metabolites. In each section, we also discuss how bioluminescent tools have revealed insights into experimental therapies and aided drug discovery. Last, we highlight the development of new bioluminescent tools that will enable more sensitive and multi-component imaging experiments and, thus, expand our broader understanding of living systems.

  14. Abdominal Manifestations of Lymphoma: Spectrum of Imaging Features

    International Nuclear Information System (INIS)

    Non-Hodgkin and Hodgkin lymphomas frequently involve many structures in the abdomen and pelvis. Extranodal disease is more common with Non-Hodgkin's lymphoma than with Hodgkin's lymphoma. Though it may be part of a systemic lymphoma, single onset of nodal lymphoma is not rare. Extranodal lymphoma has been described in virtually every organ and tissue. In decreasing order of frequency, the spleen, liver, gastrointestinal tract, pancreas, abdominal wall, genitourinary tract, adrenal, peritoneal cavity, and biliary tract are involved. The purpose of this review is to discuss and illustrate the spectrum of appearances of nodal and extranodal lymphomas, including AIDS-related lymphomas, in the abdominopelvic region using a multimodality approach, especially cross-sectional imaging techniques. The most common radiologic patterns of involvement are illustrated. Familiarity with the imaging manifestations that are diagnostically specific for lymphoma is important because imaging plays an important role in the noninvasive management of disease

  15. A new method to extract stable feature points based on self-generated simulation images

    Science.gov (United States)

    Long, Fei; Zhou, Bin; Ming, Delie; Tian, Jinwen

    2015-10-01

    Recently, image processing has got a lot of attention in the field of photogrammetry, medical image processing, etc. Matching two or more images of the same scene taken at different times, by different cameras, or from different viewpoints, is a popular and important problem. Feature extraction plays an important part in image matching. Traditional SIFT detectors reject the unstable points by eliminating the low contrast and edge response points. The disadvantage is the need to set the threshold manually. The main idea of this paper is to get the stable extremums by machine learning algorithm. Firstly we use ASIFT approach coupled with the light changes and blur to generate multi-view simulated images, which make up the set of the simulated images of the original image. According to the way of generating simulated images set, affine transformation of each generated image is also known. Instead of the traditional matching process which contain the unstable RANSAC method to get the affine transformation, this approach is more stable and accurate. Secondly we calculate the stability value of the feature points by the set of image with its affine transformation. Then we get the different feature properties of the feature point, such as DOG features, scales, edge point density, etc. Those two form the training set while stability value is the dependent variable and feature property is the independent variable. At last, a process of training by Rank-SVM is taken. We will get a weight vector. In use, based on the feature properties of each points and weight vector calculated by training, we get the sort value of each feature point which refers to the stability value, then we sort the feature points. In conclusion, we applied our algorithm and the original SIFT detectors to test as a comparison. While in different view changes, blurs, illuminations, it comes as no surprise that experimental results show that our algorithm is more efficient.

  16. Malformations of cortical development:3T magnetic resonance imaging features

    Institute of Scientific and Technical Information of China (English)

    Bilal; Battal; Selami; Ince; Veysel; Akgun; Murat; Kocaoglu; Emrah; Ozcan; Mustafa; Tasar

    2015-01-01

    Malformation of cortical development(MCD) is a term representing an inhomogeneous group of central nervous system abnormalities, referring particularly to embriyological aspect as a consequence of any of the three developmental stages, i.e., cell proliferation, cell migration and cortical organization. These include cotical dysgenesis, microcephaly, polymicrogyria, schizencephaly, lissencephaly, hemimegalencephaly, heterotopia and focal cortical dysplasia. Since magnetic resonance imaging is the modality of choice that best identifies the structural anomalies of the brain cortex, we aimed to provide a mini review of MCD by using 3T magnetic resonance scanner images.

  17. Malformations of cortical development: 3T magnetic resonance imaging features

    Science.gov (United States)

    Battal, Bilal; Ince, Selami; Akgun, Veysel; Kocaoglu, Murat; Ozcan, Emrah; Tasar, Mustafa

    2015-01-01

    Malformation of cortical development (MCD) is a term representing an inhomogeneous group of central nervous system abnormalities, referring particularly to embriyological aspect as a consequence of any of the three developmental stages, i.e., cell proliferation, cell migration and cortical organization. These include cotical dysgenesis, microcephaly, polymicrogyria, schizencephaly, lissencephaly, hemimegalencephaly, heterotopia and focal cortical dysplasia. Since magnetic resonance imaging is the modality of choice that best identifies the structural anomalies of the brain cortex, we aimed to provide a mini review of MCD by using 3T magnetic resonance scanner images. PMID:26516429

  18. Adaptive Feature Selection and Extraction Approaches for Image Retrieval based on Region

    Directory of Open Access Journals (Sweden)

    Haiyu Song

    2010-02-01

    Full Text Available Image retrieval based on region is one of the most promising and active research directions in recent year's CBIR, while region segmentation, feature selection and feature extraction of region are key issues. However, the existing approaches always adopt a uniform approach of segmentation and feature extraction for all images in the same system. In this paper, we propose adaptive image segmentation and feature extraction approach according to different category image for image retrieval system. To improve performance, we propose adaptive segmentation approach according to different category image. Textured image is segmented by Gaussian Mixture Models (GMM, while non-textured image is segmented by our proposed block-based normalized cut. To accurately describe feature of region, we propose weight assignment method for centroid pixel and its neighbor by convolution with normal distribution when image segmentation by GMM. To improve generalization, we propose adaptive number of Fourier descriptors of shape signature which depends on the energy distribution of Fourier descriptors, instead of fixed number by experience. To simply and efficiently describe the spatial relationships of multi-object or multi-region in same image, we apply simplified topological relationships. The experiments demonstrate that proposed approaches are superior to the traditional approaches.

  19. Advantage in Bright-blood and Black-blood Magnetic Resonance Imaging with High-resolution for Analysis of Carotid Atherosclerotic Plaques

    Directory of Open Access Journals (Sweden)

    Mei Li

    2015-01-01

    Full Text Available Background: About 50% of the cerebral ischemia events are induced by intracranial and extracranial atherosclerosis. This study aimed to evaluate the feasibility and accuracy for displaying atherosclerotic plaques in carotid arteries and analyzing their ingredients by using high-resolution new magnetic resonance imaging (MRI techniques. Methods: Totally, 49 patients suspected of extracranial carotid artery stenosis were subjected to cranial MRI scan and magnetic resonance angiography (MRA examination on carotid arteries, and high-resolution bright-blood and black-blood MRI analysis was carried out within 1 week. Digital subtraction angiography (DSA examination was carried out for 16 patients within 1 month. Results: Totally, 103 plaques were detected in the 49 patients, which were characterized by localized or diffusive thickening of the vessel wall, with the intrusion of crescent-shaped abnormal signal into lumens. Fibrous cap was displayed as isointensity in T1-weighted image (T1WI and hyperintensities in proton density weighted image (PDWI and T2-weighted image (T2WI, lipid core was displayed as isointensity or slight hyperintensities in T1WI, isointensity, hyperintensities or hypointensity in PDWI, and hypointensity in T2WI. Calcification in plaques was detected in 11 patients. Eight patients were detected with irregular plaque surface or ulcerative plaques, which were characterized by irregular intravascular space surface in the black-blood sequences, black hypointensity band was not detected in three-dimensional time-of-flight, or the hypointensity band was not continuous, and intrusion of hyperintensities into plaques can be detected. Bright-blood and black-blood techniques were highly correlated with the diagnosis of contrast-enhanced MRA in angiostenosis degree, Rs = 0.97, P < 0.001. In comparison to DSA, the sensitivity, specificity, and accuracy of MRI diagnosis of stenosis for ≥50% were 88.9%, 100%, and 97.9%, respectively

  20. Relationship between Hyperuricemia and Haar-Like Features on Tongue Images

    Directory of Open Access Journals (Sweden)

    Yan Cui

    2015-01-01

    Full Text Available Objective. To investigate differences in tongue images of subjects with and without hyperuricemia. Materials and Methods. This population-based case-control study was performed in 2012-2013. We collected data from 46 case subjects with hyperuricemia and 46 control subjects, including results of biochemical examinations and tongue images. Symmetrical Haar-like features based on integral images were extracted from tongue images. T-tests were performed to determine the ability of extracted features to distinguish between the case and control groups. We first selected features using the common criterion P<0.05, then conducted further examination of feature characteristics and feature selection using means and standard deviations of distributions in the case and control groups. Results. A total of 115,683 features were selected using the criterion P<0.05. The maximum area under the receiver operating characteristic curve (AUC of these features was 0.877. The sensitivity of the feature with the maximum AUC value was 0.800 and specificity was 0.826 when the Youden index was maximized. Features that performed well were concentrated in the tongue root region. Conclusions. Symmetrical Haar-like features enabled discrimination of subjects with and without hyperuricemia in our sample. The locations of these discriminative features were in agreement with the interpretation of tongue appearance in traditional Chinese and Western medicine.

  1. Image processing based automatic diagnosis of glaucoma using wavelet features of segmented optic disc from fundus image.

    Science.gov (United States)

    Singh, Anushikha; Dutta, Malay Kishore; ParthaSarathi, M; Uher, Vaclav; Burget, Radim

    2016-02-01

    Glaucoma is a disease of the retina which is one of the most common causes of permanent blindness worldwide. This paper presents an automatic image processing based method for glaucoma diagnosis from the digital fundus image. In this paper wavelet feature extraction has been followed by optimized genetic feature selection combined with several learning algorithms and various parameter settings. Unlike the existing research works where the features are considered from the complete fundus or a sub image of the fundus, this work is based on feature extraction from the segmented and blood vessel removed optic disc to improve the accuracy of identification. The experimental results presented in this paper indicate that the wavelet features of the segmented optic disc image are clinically more significant in comparison to features of the whole or sub fundus image in the detection of glaucoma from fundus image. Accuracy of glaucoma identification achieved in this work is 94.7% and a comparison with existing methods of glaucoma detection from fundus image indicates that the proposed approach has improved accuracy of classification.

  2. Posteromedial impingement (POMI) of the ankle: MR imaging features

    International Nuclear Information System (INIS)

    Full text: The purpose of this study is to describe the normal MR Imaging appearance of the supporting ligaments of the first carpometacarpal joint in asymptomatic volunteers and the ligamentous injury in patients following dislocation. Three healthy volunteers underwent MR Imaging of the first carpometacarpal joint in order to describe the normal ligaments and optimise the scanning technique for assessment of this joint. Six patients underwent MR Imaging after injury to the ligament. All patients were injured after a fall in which the thumb was subluxed during hyperextension.The Anterior Oblique Ligament (AOL) was evaluated for abnormal morphology and signal intensity, including the site of the injury and the degree of tearing. Joint alignment was assessed for instability. The four ligaments felt to contribute to the stability of the first joint were reliably identified. The normal ligament is a continuous band of low signal running from one bone attachment to another. With injury, there is disruption of the ligament, hyperintensity and perforated stripping. The AOL was shown to be consistently injured after dislocation close to the metacarpal side. MR Imaging allows accurate evaluation of injuries of the AOL of the first carpometacarpal joint and identifies patients who would benefit from surgical reconstruction. Copyright (2002) Blackwell Science Pty Ltd

  3. MR imaging features of foot involvement in ankylosing spondylitis

    Energy Technology Data Exchange (ETDEWEB)

    Erdem, C. Zuhal E-mail: sunarerdem@yahoo.com; Sarikaya, Selda; Erdem, L. Oktay; Ozdolap, Senay; Gundogdu, Sadi

    2005-01-01

    Objective: To determine alterations of the soft tissue, tendon, cartilage, joint space, and bone of the foot using magnetic resonance (MR) imaging in ankylosing spondylitis (AS) patients. Materials and Method: Clinical and MR examination of the foot was performed in 23 AS patients (46 feet). Ten asymptomatic volunteers (20 feet) were studied on MR imaging, as a control group. MR imaging protocol included; T1-weighted spin-echo, T2-weighted fast-field echo (FFE) and fat-suppressed short tau inversion recovery (STIR) sequences in sagittal, sagittal oblique, and coronal planes using a head coil. Specifically, we examined: bone erosions, tendinitis (acute and chronic), para-articular enthesophyte, joint effusion, plantar fasciitis, joint space narrowing, soft tissue edema, bone marrow edema, enthesopathy in the Achilles tendon and plantar fascia attachment, subchondral signal intensity abnormalities (edema and sclerosis), tenosynovitis, retrocalcaneal bursitis, subchondral cysts, subchondral fissures, and bony ankylosis. Midfoot, hindfoot, and ankle were included in examined anatomic regions. Results: Clinical signs and symptoms (pain and swelling) due to foot involvement were present in 3 (13%) of the patients while frequency of involvement was 21 (91%) with MR imaging assessment. The MR imaging findings were bone erosions (65%), Achilles tendinitis (acute and chronic) (61%), para-articular enthesophyte (48%), joint effusion (43%), plantar fasciitis (40%), joint space narrowing (40%), subchondral sclerosis (35%), soft tissue edema (30%), bone marrow edema (30%), enthesopathy of the Achilles attachment (30%), subchondral edema (26%), enthesopathy in the plantar fascia attachment (22%), retrocalcaneal bursitis (22%), subchondral cysts (17%), subchondral fissures (17%), tendinitis and enthesopathy of the plantar ligament (13%), and bony ankylosis (9%). The most common involved anatomical region was the hindfoot (83%) following by midfoot (69% ) and ankle (22

  4. Magnetic resonance imaging features of papillary breast lesions

    Energy Technology Data Exchange (ETDEWEB)

    Sarica, Ozgur, E-mail: sozgur@yahoo.com; Uluc, Fatih, E-mail: drfatihuluc@yahoo.com; Tasmali, Deniz, E-mail: deniztasmali@hotmail.com

    2014-03-15

    Purpose: This study was aimed to assess the role of magnetic resonance imaging (MRI) in the evaluation of the papillary lesions of the breast and their morphological relationship with the mammary ducts. The potential diagnostic contributory role of ductal oriented protocols to conventional dynamic magnetic resonance examination was also explored. Materials and methods: Retrospective data were collected from 46 patients who had been diagnosed with papillary breast lesions and undergone magnetic resonance examination. The presence of dilated ducts and their morphological relation with the lesion were recorded. Lesions were classified as follows: papilloma, papillomatosis and malignant papillary lesion. Statistical difference between groups was studied for each morphological and dynamic lesion characteristic. Results: Dilated ducts and characteristics of intraductal material can be identified by magnetic resonance imaging. Certain MRI findings such as a mass with crescentic peripheral fluid or focal intraductal mass on T2 weighted images may suggest the presence of an intraductal/papillary lesion. In this respect, non-fatsat T2 weighted images appear particularly useful. There was a significant difference between papilloma and papillomatosis with regard to segmental and heterogeneous contrast enhancement (p < 0.05 for both comparisons). In addition, there was a significant difference between papillomas and carcinomas with regard to homogenous, heterogeneous and segmental contrast enhancement (p < 0.05 for all). On the other hand, papillomatosis and carcinoma did not differ significantly in terms of any of the morphological or dynamical MR criteria compared. Conclusion: Papillary lesions can be detected by MRI. Despite some overlaps in MRI findings between carcinoma, papilloma and papillomatosis, MRI may help differentiate these lesions. Major benefit of retroareolar imaging appears to arise from its ability to demonstrate ductal relation and extension of contrast

  5. Content-Based Image Retrieval using Color Moment and Gabor Texture Feature

    Directory of Open Access Journals (Sweden)

    K. Hemachandran

    2012-09-01

    Full Text Available Content based image retrieval (CBIR has become one of the most active research areas in the past few years. Many indexing techniques are based on global feature distributions. However, these global distributions have limited discriminating power because they are unable to capture local image information. In this paper, we propose a content-based image retrieval method which combines color and texture features. To improve the discriminating power of color indexing techniques, we encode a minimal amount of spatial information in the color index. As its color features, an image is divided horizontally into three equal non-overlapping regions. From each region in the image, we extract the first three moments of the color distribution, from each color channel and store them in the index i.e., for a HSV color space, we store 27 floating point numbers per image. As its texture feature, Gabor texture descriptors are adopted. We assign weights to each feature respectively and calculate the similarity with combined features of color and texture using Canberra distance as similarity measure. Experimental results show that the proposed method has higher retrieval accuracy than other conventional methods combining color moments and texture features based on global features approach.

  6. Classification of yeast cells from image features to evaluate pathogen conditions

    Science.gov (United States)

    van der Putten, Peter; Bertens, Laura; Liu, Jinshuo; Hagen, Ferry; Boekhout, Teun; Verbeek, Fons J.

    2007-01-01

    Morphometrics from images, image analysis, may reveal differences between classes of objects present in the images. We have performed an image-features-based classification for the pathogenic yeast Cryptococcus neoformans. Building and analyzing image collections from the yeast under different environmental or genetic conditions may help to diagnose a new "unseen" situation. Diagnosis here means that retrieval of the relevant information from the image collection is at hand each time a new "sample" is presented. The basidiomycetous yeast Cryptococcus neoformans can cause infections such as meningitis or pneumonia. The presence of an extra-cellular capsule is known to be related to virulence. This paper reports on the approach towards developing classifiers for detecting potentially more or less virulent cells in a sample, i.e. an image, by using a range of features derived from the shape or density distribution. The classifier can henceforth be used for automating screening and annotating existing image collections. In addition we will present our methods for creating samples, collecting images, image preprocessing, identifying "yeast cells" and creating feature extraction from the images. We compare various expertise based and fully automated methods of feature selection and benchmark a range of classification algorithms and illustrate successful application to this particular domain.

  7. MISD Compiler for Feature Vector Computation in Serial Input Images

    Directory of Open Access Journals (Sweden)

    Lucas Leiva

    2011-06-01

    Full Text Available In this paper a compiler capable of generate Multiple Instruction Single Data (MISD architectures for feature vector calculation is presented. The input is a high-level language, avoiding to developers to involve in low level design. Instead, the output is expressed in a Hardware Description Language (HDL, and can be used for FPGA configuration. A FPGA is a programmable device which allows parallelism, increasing the system speed up. The tool is intended to use in feature vector calculation of region of interest (ROI for real time video applications. These ROIs arrives serially. Also, is possible to evaluate the vector in design time, allowing system prototyping. The compiler optimizes the response time and the number of registers required to meet real time constraints.

  8. Detecting edges in the X-ray surface brightness of galaxy clusters

    CERN Document Server

    Sanders, J S; Russell, H R; Walker, S A; Blundell, K M

    2016-01-01

    The effects of many physical processes in the intracluster medium of galaxy clusters imprint themselves in X-ray surface brightness images. It is therefore important to choose optimal methods for extracting information from and enhancing the interpretability of such images. We describe in detail a gradient filtering edge detection method that we previously applied to images of the Centaurus cluster of galaxies. The Gaussian gradient filter measures the gradient in the surface brightness distribution on particular spatial scales. We apply this filter on different scales to Chandra X-ray observatory images of two clusters with AGN feedback, the Perseus cluster and M87, and a merging system, A3667. By combining filtered images on different scales using radial filters spectacular images of the edges in a cluster are produced. We describe how to assess the significance of features in filtered images. We find the gradient filtering technique to have significant advantages for detecting many kinds of features compar...

  9. In-situ Microwave Brightness Temperature Variability from Ground-based Radiometer Measurements at Dome C in Antarctica Induced by Wind-formed Features

    Science.gov (United States)

    Royer, A.; Picard, G.; Arnaud, L.; Brucker, L.; Fily, M..

    2014-01-01

    Space-borne microwave radiometers are among the most useful tools to study snow and to collect information on the Antarctic climate. They have several advantages over other remote sensing techniques: high sensitivity to snow properties of interest (temperature, grain size, density), subdaily coverage in the polar regions, and their observations are independent of cloud conditions and solar illumination. Thus, microwave radiometers are widely used to retrieve information over snow-covered regions. For the Antarctic Plateau, many studies presenting retrieval algorithms or numerical simulations have assumed, explicitly or not, that the subpixel-scale heterogeneity is negligible and that the retrieved properties were representative of whole pixels. In this presentation, we investigate the spatial variations of brightness temperature over arange of a few kilometers in the Dome C area (Antarctic Plateau).

  10. Spinal dural arteriovenous fistula: Imaging features and its mimics

    Energy Technology Data Exchange (ETDEWEB)

    Jeog, Ying; Ting, David Yen; Hsu, Hui Ling; Huang, Yen Lin; Chen, Chi Jen; Tseng, Ting Chi [Dept. of Radiology, aipei Medical University-Shuang Ho Hospital, New Taipei City, Taiwan (China)

    2015-10-15

    Spinal dural arteriovenous fistula (SDAVF) is the most common spinal vascular malformation, however it is still rare and underdiagnosed. Magnetic resonance imaging findings such as spinal cord edema and dilated and tortuous perimedullary veins play a pivotal role in the confirmation of the diagnosis. However, spinal angiography remains the gold standard in the diagnosis of SDAVF. Classic angiographic findings of SDAVF are early filling of radicular veins, delayed venous return, and an extensive network of dilated perimedullary venous plexus. A series of angiograms of SDAVF at different locations along the spinal column, and mimics of serpentine perimedullary venous plexus on MR images, are demonstrated. Thorough knowledge of SDAVF aids correct diagnosis and prevents irreversible complications.

  11. Feature Recognition of Low-resolution Fiber Image

    Institute of Scientific and Technical Information of China (English)

    YU Su-ping; ZENG Pei-feng; WU Xiong-ying; CHEN Jian-ping

    2006-01-01

    The interpolatory edge operator is applied to the recognition of cotton and ramie fibers. Its performance is studied in comparison with the Canny edge operator in the fiber's edge detection for cross-sectional image. The input image is interpolated other than Gaussian function smoothing. The quality of edge output is improved by the interpolatory edge operator. It produces edge output with good continuity for low-resolution input. The fine edge output, such as crossmarkings, can be distinguished clearly, so the interpolatory edge operator is suitable for the study of cotton and ramie fibers. Furthermore, the application of the interpolatory edge operator can cut the hardware cost, reduce the storage and speed up the data transmission.

  12. Imaging features of posterior mediastinal chordoma in a child

    Energy Technology Data Exchange (ETDEWEB)

    Soudack, Michalle; Guralnik, Ludmilla; Engel, Ahuva [Rambam Health Care Campus, Department of Diagnostic Imaging, Haifa (Israel); Ben-Nun, Alon [Rambam Health Care Campus, Department of Thoracic Surgery, Haifa (Israel); Berkowitz, Drora [Rambam Health Care Campus, Department of Pediatrics B, Haifa (Israel); Postovsky, Sergey [Rambam Health Care Campus, Department of Pediatric Hemato-Oncology, Haifa (Israel); Vlodavsky, Eugene [Rambam Health Care Campus, Department of Pathology, Haifa (Israel)

    2007-05-15

    A 51/2-year-old boy presented with repeated episodes of stridor and cough. Chest radiography demonstrated a widened mediastinum. Evaluation by CT revealed a low-density posterior mediastinal mass initially diagnosed as benign tumor. Histopathological analysis of the resected mass disclosed a malignant chordoma. Our radiological results are described with an analysis of the imaging findings in the medical literature. We present our suggestions for preoperative evaluation of posterior mediastinal tumors. (orig.)

  13. Precoccygeal epidermal inclusion cyst: ultrasound and MR imaging features.

    OpenAIRE

    Halefoglu, A.M.; Sen, E Y

    2012-01-01

    In this case report, we are presenting a 33 year-old pregnant woman who suffered from pelvic and coccygeal pain. Her medical examination and laboratory tests were found within normal limits. In order to explain her pain, initially a pelvic ultrasound was performed which revealed a huge hypoechoic cystic mass in the precoccygeal-presacral region. She then underwent a pelvic magnetic resonance imaging (MRI) examination in order to better delineate the characteristics and extension of this huge ...

  14. Two-dimensional electrophoresis analysis of proteomics based on image feature and mathematical morphology

    Institute of Scientific and Technical Information of China (English)

    SHEN; Peng; FAN; Xiaohui; ZENG; Zhen

    2005-01-01

    In this paper, a novel method to automatically detect protein spots on a two-dimensional (2-D) electrophoresis gel image is proposed to implement proteomics analysis of complex analyte.On the basis of the identifying spots results based on color variation and spot size features, morphological feature is introduced as a new criterion to distinguish protein spots from non-protein spots.Image-sharpening, edge-detecting and morphological feature extraction methods were consequently combined to detect protein spots on a 2-D electrophoresis gel image subject to strong disturbance.The proposed method was applied to detect the protein spots of proteomic gel images from E.coli cell, human kidney tissue and human serum.The results demonstrated that this method is more accurate and reliable than previous methods such as PDQuest 7.2 and ImageMaster 5.0 software for detecting protein spots on gel images with strong interferences.

  15. Image retrieval system based on machine learning and using color features

    OpenAIRE

    Demšar, Janez; Radolović, Dragan; Solina, Franc

    2014-01-01

    We describe an interactive system for content based image retrieval. The system presents the user with 15 randomly selected images from the database. The user grades the images with one of five possible grades (YES, yes, neutral, no, NO) according to what he is looking for. The system returns the first 15 images with the highest probability of YES grade. The attributes used are a combination of color features. Three different machine learning techniques are compared.

  16. Mathematical morphology-based approach to the enhancement of morphological features in medical images

    OpenAIRE

    Kimori, Yoshitaka

    2011-01-01

    Background Medical image processing is essential in many fields of medical research and clinical practice because it greatly facilitates early and accurate detection and diagnosis of diseases. In particular, contrast enhancement is important for optimal image quality and visibility. This paper proposes a new image processing method for enhancing morphological features of masses and other abnormalities in medical images. Method The proposed method involves two steps: (1) selective extraction o...

  17. Low surface brightness galaxies

    Science.gov (United States)

    Vanderhulst, J. M.; Deblok, W. J. G.; Mcgaugh, S. S.; Bothun, G. D.

    1993-01-01

    A program to investigate the properties of low surface brightness (LSB) galaxies involving surface photometry in U, B, V, R, I, and H-alpha, HI imaging with the Westerbork Synthesis Radio Telescope (WSRT) and the very large array (VLA) and spectrophotometry of H2 regions in LSB galaxies is underway. The goal is to verify the idea that LSB galaxies have low star formation rates because the local gas density falls below the critical density for star formation, and to study the stellar population and abundances in LSB galaxies. Such information should help understanding the evolutionary history of LSB galaxies. Some preliminary results are reported.

  18. A PCA Based Automatic Image Categorization Approach Using Dominant Color Features

    Institute of Scientific and Technical Information of China (English)

    WUChunming; QIANHui; WANGDonghui

    2005-01-01

    Automatic Image categorization is a universal problem in area of Content-based image retrieval (CBIR). The goal of automatic image categorization is to find a mapping between images and the predefined image categories. The difficulty of this problem is that how to describe image content and incorporate low-level features into semantic categories. As a solution, we propose a Principal component analysis (PCA) based approach. This approach assumes that the images in the same semantic category have the similar spatial distribution of color components and treats the images in the same category as a linear combination of a fixed set of dominant color blocks with special textural information. A three-step algorithm is designed: (1) extracting Dominant colors (DC) of images, which describe the major color information in an image; (2) Establishing a feature space based on DC blocks and its textural information; (3) using PCA to reduce dimensionality of feature space and using the basis vectors to categorize images. An experimental database containing nine categories including cars, flowers, houses, portraits, fish, bark, sunshine, leaves and fresco is constructed to test the algorithm based on our image categorization approach. The results show that this approach is effective and a reasonable compromise between accuracy and speed in practice.

  19. Dark blood versus bright blood T2* acquisition in cardiovascular magnetic resonance (CMR) for thalassaemia major (TM) patients: Evaluation of feasibility, reproducibility and image quality

    International Nuclear Information System (INIS)

    Objectives: To compare the effectiveness of dark blood (DB) versus bright blood (BB) sequences. To assess the intra and inter-observer variability and inter-study reproducibility between BB versus DB. To evaluate image quality level in the two sequences. Methods: In a setting of 138 patients we performed CMR using cardiac gated Gradient-multiecho single breath-hold BB and DB sequences in the middle ventricular septum. Each acquisition was repeated during the same exam. Truncation method was used to account for background noise. Image quality (IQ) was assessed using a 5 point grading scale and image analysis was conducted by 2 experienced observers. Results: Compared with the conventional BB acquisition, the coefficient of correlation and significance of the DB technique was superior for intra-observer reproducibility (p < 0.001), inter-observer reproducibility (p < 0.001) and inter-study reproducibility (p < 0.001). The variability is also lower for DB sequences for T2* values <14 ms. Assessment of artifacts showed a superior score for DB versus BB scans (4 versus 3, p < 0.001). Conclusions: Improvement in terms of inter observer and inter study variability using DB sequences was obtained. The greatest disparity between them was seen in inter-study reproducibility and higher IQ in DB was seen. Study demonstrates better performance of DB imaging compared to BB in presence of comparable effectiveness

  20. Dark blood versus bright blood T2* acquisition in cardiovascular magnetic resonance (CMR) for thalassaemia major (TM) patients: Evaluation of feasibility, reproducibility and image quality

    Energy Technology Data Exchange (ETDEWEB)

    Liguori, Carlo, E-mail: c.liguori@unicampus.it [Department of Diagnostic Imaging, Campus Bio Medico University, via Alvaro del Portillo 200, 00128 Rome (Italy); Di Giampietro, Ilenia; Pitocco, Francesca; De Vivo, Aldo Eros [Department of Diagnostic Imaging, Campus Bio Medico University, via Alvaro del Portillo 200, 00128 Rome (Italy); Schena, Emiliano [Unit of Measurements and Biomedical Instrumentation, Campus Bio Medico University, via Alvaro del Portillo 200, 00128 Rome (Italy); Mortato, Luca [Department of Diagnostic Imaging, Campus Bio Medico University, via Alvaro del Portillo 200, 00128 Rome (Italy); Pirro, Federica [Department of Biomaging and Radiological Sciences, Catholic University of Sacred Herart, Largo A. Gemelli 1, 00135 Rome (Italy); Cianciulli, Paolo [Thalassemia Unit, Ospedale Sant Eugenio, Piazzale dell’Umanesimo 10, 00143 Rome (Italy); Zobel, Bruno Beomonte [Department of Diagnostic Imaging, Campus Bio Medico University, via Alvaro del Portillo 200, 00128 Rome (Italy)

    2014-01-15

    Objectives: To compare the effectiveness of dark blood (DB) versus bright blood (BB) sequences. To assess the intra and inter-observer variability and inter-study reproducibility between BB versus DB. To evaluate image quality level in the two sequences. Methods: In a setting of 138 patients we performed CMR using cardiac gated Gradient-multiecho single breath-hold BB and DB sequences in the middle ventricular septum. Each acquisition was repeated during the same exam. Truncation method was used to account for background noise. Image quality (IQ) was assessed using a 5 point grading scale and image analysis was conducted by 2 experienced observers. Results: Compared with the conventional BB acquisition, the coefficient of correlation and significance of the DB technique was superior for intra-observer reproducibility (p < 0.001), inter-observer reproducibility (p < 0.001) and inter-study reproducibility (p < 0.001). The variability is also lower for DB sequences for T2* values <14 ms. Assessment of artifacts showed a superior score for DB versus BB scans (4 versus 3, p < 0.001). Conclusions: Improvement in terms of inter observer and inter study variability using DB sequences was obtained. The greatest disparity between them was seen in inter-study reproducibility and higher IQ in DB was seen. Study demonstrates better performance of DB imaging compared to BB in presence of comparable effectiveness.

  1. [Classification technique for hyperspectral image based on subspace of bands feature extraction and LS-SVM].

    Science.gov (United States)

    Gao, Heng-zhen; Wan, Jian-wei; Zhu, Zhen-zhen; Wang, Li-bao; Nian, Yong-jian

    2011-05-01

    The present paper proposes a novel hyperspectral image classification algorithm based on LS-SVM (least squares support vector machine). The LS-SVM uses the features extracted from subspace of bands (SOB). The maximum noise fraction (MNF) method is adopted as the feature extraction method. The spectral correlations of the hyperspectral image are used in order to divide the feature space into several SOBs. Then the MNF is used to extract characteristic features of the SOBs. The extracted features are combined into the feature vector for classification. So the strong bands correlation is avoided and the spectral redundancies are reduced. The LS-SVM classifier is adopted, which replaces inequality constraints in SVM by equality constraints. So the computation consumption is reduced and the learning performance is improved. The proposed method optimizes spectral information by feature extraction and reduces the spectral noise. The classifier performance is improved. Experimental results show the superiorities of the proposed algorithm.

  2. Compact Representation of High-Dimensional Feature Vectors for Large-Scale Image Recognition and Retrieval.

    Science.gov (United States)

    Zhang, Yu; Wu, Jianxin; Cai, Jianfei

    2016-05-01

    In large-scale visual recognition and image retrieval tasks, feature vectors, such as Fisher vector (FV) or the vector of locally aggregated descriptors (VLAD), have achieved state-of-the-art results. However, the combination of the large numbers of examples and high-dimensional vectors necessitates dimensionality reduction, in order to reduce its storage and CPU costs to a reasonable range. In spite of the popularity of various feature compression methods, this paper shows that the feature (dimension) selection is a better choice for high-dimensional FV/VLAD than the feature (dimension) compression methods, e.g., product quantization. We show that strong correlation among the feature dimensions in the FV and the VLAD may not exist, which renders feature selection a natural choice. We also show that, many dimensions in FV/VLAD are noise. Throwing them away using feature selection is better than compressing them and useful dimensions altogether using feature compression methods. To choose features, we propose an efficient importance sorting algorithm considering both the supervised and unsupervised cases, for visual recognition and image retrieval, respectively. Combining with the 1-bit quantization, feature selection has achieved both higher accuracy and less computational cost than feature compression methods, such as product quantization, on the FV and the VLAD image representations. PMID:27046897

  3. Reversible acute methotrexate leukoencephalopathy: atypical brain MR imaging features

    Energy Technology Data Exchange (ETDEWEB)

    Ziereisen, France; Damry, Nash; Christophe, Catherine [Queen Fabiola Children' s University Hospital, Department of Radiology, Brussels (Belgium); Dan, Bernard [Queen Fabiola Children' s University Hospital, Department of Neurology, Brussels (Belgium); Azzi, Nadira; Ferster, Alina [Queen Fabiola Children' s University Hospital, Department of Paediatrics, Brussels (Belgium)

    2006-03-15

    Unusual acute symptomatic and reversible early-delayed leukoencephalopathy has been reported to be induced by methotrexate (MTX). We aimed to identify the occurrence of such atypical MTX neurotoxicity in children and document its MR presentation. We retrospectively reviewed the clinical findings and brain MRI obtained in 90 children treated with MTX for acute lymphoblastic leukaemia or non-B malignant non-Hodgkin lymphoma. All 90 patients had normal brain imaging before treatment. In these patients, brain imaging was performed after treatment completion and/or relapse and/or occurrence of neurological symptoms. Of the 90 patients, 15 (16.7%) showed signs of MTX neurotoxicity on brain MRI, 9 (10%) were asymptomatic, and 6 (6.7%) showed signs of acute leukoencephalopathy. On the routine brain MRI performed at the end of treatment, all asymptomatic patients had classical MR findings of reversible MTX neurotoxicity, such as abnormal high-intensity areas localized in the deep periventricular white matter on T2-weighted images. In contrast, the six symptomatic patients had atypical brain MRI characterized by T2 high-intensity areas in the supratentorial cortex and subcortical white matter (n=6), cerebellar cortex and white matter (n=4), deep periventricular white matter (n=2) and thalamus (n=1). MR normalization occurred later than clinical recovery in these six patients. In addition to mostly asymptomatic classical MTX neurotoxicity, MTX may induce severe but reversible unusual leukoencephalopathy. It is important to recognize this clinicoradiological presentation in the differential diagnosis of acute neurological deterioration in children treated with MTX. (orig.)

  4. CONTENT BASED LEAF IMAGE RETRIEVAL (CBLIR USING SHAPE, COLOR AND TEXTURE FEATURES

    Directory of Open Access Journals (Sweden)

    B.SATHYA BAMA,

    2011-04-01

    Full Text Available This paper proposes an efficient computer-aided Plant Image Retrieval method based on plant leaf images using Shape, Color and Texturefeatures intended mainly for medical industry, botanical gardening and cosmetic industry. Here, we use HSV color space to extract thevarious features of leaves. Log-Gabor wavelet is applied to the input image for texture feature extraction. The Scale Invariant FeatureTransform (SIFT is incorporated to extract the feature points of the leaf image. Scale Invariant Feature Transform transforms an image intoa large collection of feature vectors, each of which is invariant to image translation, scaling, and rotation, partially invariant to illumination changes and robust to local geometric distortion. SIFT has four modules namely detection of scale space extrema, local extrema detection, orientation assignment and key point descriptor. Results on a database of 500 plant images belonging to 45 different types of plants with different orientations scales, and translations show that proposed method outperforms the recently developed methods by giving 97.9% of retrieval efficiency for 20, 50, 80 and 100 retrievals.

  5. Face Recognition from Still Images to Video Sequences: A Local-Feature-Based Framework

    Directory of Open Access Journals (Sweden)

    Chen Shaokang

    2011-01-01

    Full Text Available Although automatic faces recognition has shown success for high-quality images under controlled conditions, for video-based recognition it is hard to attain similar levels of performance. We describe in this paper recent advances in a project being undertaken to trial and develop advanced surveillance systems for public safety. In this paper, we propose a local facial feature based framework for both still image and video-based face recognition. The evaluation is performed on a still image dataset LFW and a video sequence dataset MOBIO to compare 4 methods for operation on feature: feature averaging (Avg-Feature, Mutual Subspace Method (MSM, Manifold to Manifold Distance (MMS, and Affine Hull Method (AHM, and 4 methods for operation on distance on 3 different features. The experimental results show that Multi-region Histogram (MRH feature is more discriminative for face recognition compared to Local Binary Patterns (LBP and raw pixel intensity. Under the limitation on a small number of images available per person, feature averaging is more reliable than MSM, MMD, and AHM and is much faster. Thus, our proposed framework—averaging MRH feature is more suitable for CCTV surveillance systems with constraints on the number of images and the speed of processing.

  6. Clinical and CT imaging features of abdominal fat necrosis

    International Nuclear Information System (INIS)

    Fat necrosis is a common pathological change at abdominal cross-sectional imaging, and it may cause abdominal pain, mimic pathological change of acute abdomen, or be asymptomatic and accompany other pathophysiologic processes. Fat necrosis is actually the result of steatosis by metabolism or mechanical injury. Common processes that are present in fat necrosis include epiploic appendagitis, infarction of the greater omentum, pancreatitis, and fat necrosis related to trauma or ischemia. As a common fat disease, fat necrosis should be known by clinicians and radiologists. Main content of this text is the clinical symptoms and CT findings of belly fat necrosis and related diseases. (authors)

  7. Differential diagnostic features of the radionuclide scrotal image

    Energy Technology Data Exchange (ETDEWEB)

    Mishkin, F.S.

    1977-01-01

    Differential diagnosis of scrotal lesions is aided by correlating radionuclide images with clinical findings. Subacute torsion is associated with peripheral hyperemia and can be mistaken for an inflammatory process; however, in a review of 128 studies, torsion and orchiectomy were the only processes encountered which had a center truly devoid of activity on the tissue phase compared to the normal side. Other lesions such as acute inflammation, abscess, hematoma, and hemorrhagic tumor may superficially appear to lack central activity but invariably contain at least as much activity when compared to the normal side.

  8. Imaging features of type-B Niemann-Pick disease

    Energy Technology Data Exchange (ETDEWEB)

    Muntaner, L. [Dept. of Radiology, Son Dureta University Hospital, Palma de Mallorca (Spain); Galmes, A. [Dept. of Hematology, Son Dureta University Hospital, Palma de Mallorca (Spain); Chabas, A. [Instituto de Bioquimica Clinica Corporacio Sanitaria, Barcelona (Spain); Herrera, M. [Dept. of Radiology, Son Dureta University Hospital, Palma de Mallorca (Spain)

    1997-04-01

    We report two cases of a mild form of type-B Niemann-Pick disease manifesting as an adult-onset chronic non-neuropathic clinical picture. Femoral T1- and T2-weighted low-intensity non-enhancing coarse bone marrow pattern was evident on femoral MR associated with splenic hypodense nodule(s) on abdominal CT. The role of imaging is discussed in relation to current techniques of confirmation of this entity based on demonstration of lipid-laden cells within marrow aspirates (which are often sea-blue histiocytes) and sphingomyelinase assay of cultured skin fibroblasts. (orig.). With 2 figs.

  9. Imaging features of type-B Niemann-Pick disease

    International Nuclear Information System (INIS)

    We report two cases of a mild form of type-B Niemann-Pick disease manifesting as an adult-onset chronic non-neuropathic clinical picture. Femoral T1- and T2-weighted low-intensity non-enhancing coarse bone marrow pattern was evident on femoral MR associated with splenic hypodense nodule(s) on abdominal CT. The role of imaging is discussed in relation to current techniques of confirmation of this entity based on demonstration of lipid-laden cells within marrow aspirates (which are often sea-blue histiocytes) and sphingomyelinase assay of cultured skin fibroblasts. (orig.). With 2 figs

  10. Imaging features of ductal plate malformations in adults

    Energy Technology Data Exchange (ETDEWEB)

    Venkatanarasimha, N., E-mail: nandashettykv@yahoo.com [Department of Radiology, Derriford Hospital, Plymouth (United Kingdom); Thomas, R.; Armstrong, E.M.; Shirley, J.F.; Fox, B.M.; Jackson, S.A. [Department of Radiology, Derriford Hospital, Plymouth (United Kingdom)

    2011-11-15

    Ductal plate malformations, also known as fibrocystic liver diseases, are a group of congenital disorders resulting from abnormal embryogenesis of the biliary ductal system. The abnormalities include choledochal cyst, Caroli's disease and Caroli's syndrome, adult autosomal dominant polycystic liver disease, and biliary hamartoma. The hepatic lesions can be associated with renal anomalies such as autosomal recessive polycystic kidney disease (ARPKD), medullary sponge kidney, and nephronophthisis. A clear knowledge of the embryology and pathogenesis of the ductal plate is central to the understanding of the characteristic imaging appearances of these complex disorders. Accurate diagnosis of ductal plate malformations is important to direct appropriate clinical management and prevent misdiagnosis.

  11. Coronal bright points associated with minifilament eruptions

    Energy Technology Data Exchange (ETDEWEB)

    Hong, Junchao; Jiang, Yunchun; Yang, Jiayan; Bi, Yi; Li, Haidong [Yunnan Observatories, Chinese Academy of Sciences, Kunming 650011 (China); Yang, Bo; Yang, Dan, E-mail: hjcsolar@ynao.ac.cn [Also at Graduate School of Chinese Academy of Sciences, Beijing, China. (China)

    2014-12-01

    Coronal bright points (CBPs) are small-scale, long-lived coronal brightenings that always correspond to photospheric network magnetic features of opposite polarity. In this paper, we subjectively adopt 30 CBPs in a coronal hole to study their eruptive behavior using data from the Atmospheric Imaging Assembly (AIA) and the Helioseismic and Magnetic Imager (HMI) on board the Solar Dynamics Observatory. About one-quarter to one-third of the CBPs in the coronal hole go through one or more minifilament eruption(s) (MFE(s)) throughout their lifetimes. The MFEs occur in temporal association with the brightness maxima of CBPs and possibly result from the convergence and cancellation of underlying magnetic dipoles. Two examples of CBPs with MFEs are analyzed in detail, where minifilaments appear as dark features of a cool channel that divide the CBPs along the neutral lines of the dipoles beneath. The MFEs show the typical rising movements of filaments and mass ejections with brightenings at CBPs, similar to large-scale filament eruptions. Via differential emission measure analysis, it is found that CBPs are heated dramatically by their MFEs and the ejected plasmas in the MFEs have average temperatures close to the pre-eruption BP plasmas and electron densities typically near 10{sup 9} cm{sup –3}. These new observational results indicate that CBPs are more complex in dynamical evolution and magnetic structure than previously thought.

  12. Coronal bright points associated with minifilament eruptions

    International Nuclear Information System (INIS)

    Coronal bright points (CBPs) are small-scale, long-lived coronal brightenings that always correspond to photospheric network magnetic features of opposite polarity. In this paper, we subjectively adopt 30 CBPs in a coronal hole to study their eruptive behavior using data from the Atmospheric Imaging Assembly (AIA) and the Helioseismic and Magnetic Imager (HMI) on board the Solar Dynamics Observatory. About one-quarter to one-third of the CBPs in the coronal hole go through one or more minifilament eruption(s) (MFE(s)) throughout their lifetimes. The MFEs occur in temporal association with the brightness maxima of CBPs and possibly result from the convergence and cancellation of underlying magnetic dipoles. Two examples of CBPs with MFEs are analyzed in detail, where minifilaments appear as dark features of a cool channel that divide the CBPs along the neutral lines of the dipoles beneath. The MFEs show the typical rising movements of filaments and mass ejections with brightenings at CBPs, similar to large-scale filament eruptions. Via differential emission measure analysis, it is found that CBPs are heated dramatically by their MFEs and the ejected plasmas in the MFEs have average temperatures close to the pre-eruption BP plasmas and electron densities typically near 109 cm–3. These new observational results indicate that CBPs are more complex in dynamical evolution and magnetic structure than previously thought.

  13. NOTE: Prostate cancer multi-feature analysis using trans-rectal ultrasound images

    Science.gov (United States)

    Mohamed, S. S.; Salama, M. M. A.; Kamel, M.; El-Saadany, E. F.; Rizkalla, K.; Chin, J.

    2005-08-01

    This note focuses on extracting and analysing prostate texture features from trans-rectal ultrasound (TRUS) images for tissue characterization. One of the principal contributions of this investigation is the use of the information of the images' frequency domain features and spatial domain features to attain a more accurate diagnosis. Each image is divided into regions of interest (ROIs) by the Gabor multi-resolution analysis, a crucial stage, in which segmentation is achieved according to the frequency response of the image pixels. The pixels with a similar response to the same filter are grouped to form one ROI. Next, from each ROI two different statistical feature sets are constructed; the first set includes four grey level dependence matrix (GLDM) features and the second set consists of five grey level difference vector (GLDV) features. These constructed feature sets are then ranked by the mutual information feature selection (MIFS) algorithm. Here, the features that provide the maximum mutual information of each feature and class (cancerous and non-cancerous) and the minimum mutual information of the selected features are chosen, yeilding a reduced feature subset. The two constructed feature sets, GLDM and GLDV, as well as the reduced feature subset, are examined in terms of three different classifiers: the condensed k-nearest neighbour (CNN), the decision tree (DT) and the support vector machine (SVM). The accuracy classification results range from 87.5% to 93.75%, where the performance of the SVM and that of the DT are significantly better than the performance of the CNN.

  14. AN INTEGRATED FRAMEWORK BASED ON TEXTURE FEATURES, CUCKOO SEARCH AND RELEVANCE VECTOR MACHINE FOR MEDICAL IMAGE RETRIEVAL SYSTEM

    Directory of Open Access Journals (Sweden)

    Yogapriya Jaganathan

    2013-01-01

    Full Text Available As medical images are widely used in healthcare applications, Content Based Medical Image Retrieval (CBMIR system is needed for physicians to convey effective decisions to patients and for medical research students to learn imaging characteristics for their extensive research based on visual features. However the performance of the retrieval is restricted due to high feature dimensionality of visual features. To reduce the high feature dimension, an integrated approach is proposed such as Visual feature extraction, Feature selection, Feature Classification and Similarity measurements. The selected feature is texture features by using Local Binary Patterns (LBP in which extracted texture features are designed as feature vector database. Fuzzy based Cuckoo Search (FCKS techniques are applied for feature selection to reduce the high feature vector dimensionality and addresses the difficulty of feature vectors being surrounded in local feature optima also the global optimum feature position to be special for all feature cuckoo hosts. Fuzzy based Relevance Vector Machine (FRVM classification is an proficient method to customize the collections of relevant image features that would classify dimensionally determined optimized feature vectors of images. The Euclidean Distance (ED is a standard technique for similarity measurement between the query image and the image database. The proposed system is implemented on thousands of medical images and achieved a high retrieval precision and recall compared with other two methods as validated through experiments.

  15. A Novel Feature Extraction Scheme for Medical X-Ray Images

    Directory of Open Access Journals (Sweden)

    Prachi.G.Bhende

    2016-02-01

    Full Text Available X-ray images are gray scale images with almost the same textural characteristic. Conventional texture or color features cannot be used for appropriate categorization in medical x-ray image archives. This paper presents a novel combination of methods like GLCM, LBP and HOG for extracting distinctive invariant features from Xray images belonging to IRMA (Image Retrieval in Medical applications database that can be used to perform reliable matching between different views of an object or scene. GLCM represents the distributions of the intensities and the information about relative positions of neighboring pixels of an image. The LBP features are invariant to image scale and rotation, change in 3D viewpoint, addition of noise, and change in illumination A HOG feature vector represents local shape of an object, having edge information at plural cells. These features have been exploited in different algorithms for automatic classification of medical X-ray images. Excellent experimental results obtained in true problems of rotation invariance, particular rotation angle, demonstrate that good discrimination can be achieved with the occurrence statistics of simple rotation invariant local binary patterns.

  16. Stress fractures: pathophysiology, clinical presentation, imaging features, and treatment options.

    Science.gov (United States)

    Matcuk, George R; Mahanty, Scott R; Skalski, Matthew R; Patel, Dakshesh B; White, Eric A; Gottsegen, Christopher J

    2016-08-01

    Stress fracture, in its most inclusive description, includes both fatigue and insufficiency fracture. Fatigue fractures, sometimes equated with the term "stress fractures," are most common in runners and other athletes and typically occur in the lower extremities. These fractures are the result of abnormal, cyclical loading on normal bone leading to local cortical resorption and fracture. Insufficiency fractures are common in elderly populations, secondary to osteoporosis, and are typically located in and around the pelvis. They are a result of normal or traumatic loading on abnormal bone. Subchondral insufficiency fractures of the hip or knee may cause acute pain that may present in the emergency setting. Medial tibial stress syndrome is a type of stress injury of the tibia related to activity and is a clinical syndrome encompassing a range of injuries from stress edema to frank-displaced fracture. Atypical subtrochanteric femoral fracture associated with long-term bisphosphonate therapy is also a recently discovered entity that needs early recognition to prevent progression to a complete fracture. Imaging recommendations for evaluation of stress fractures include initial plain radiographs followed, if necessary, by magnetic resonance imaging (MRI), which is preferred over computed tomography (CT) and bone scintigraphy. Radiographs are the first-line modality and may reveal linear sclerosis and periosteal reaction prior to the development of a frank fracture. MRI is highly sensitive with findings ranging from periosteal edema to bone marrow and intracortical signal abnormality. Additionally, a brief description of relevant clinical management of stress fractures is included. PMID:27002328

  17. 基于图像重建的Zernike矩形状特征评价%Image Zernike Moments Shape Feature Evaluation Based on Image Reconstruction

    Institute of Scientific and Technical Information of China (English)

    刘茂福; 何炎祥; 叶斌

    2007-01-01

    The evaluation approach to the accuracy of the image feature descriptors plays an important role in image feature extraction. We point out that the image shape feature can be described by the Zernike moments set while briefly introducing the basic concept of the Zernike moment. After talking about the image reconstruction technique based on the inverse transformation of Zernike moment, the evaluation approach to the accuracy of the Zernike moments shape feature via the dissimilarity degree and the reconstruction ratio between the original image and the reconstructed image is proposed. The experiment results demonstrate the feasibility of this evaluation approach to image Zernike moments shape feature.

  18. Two-Level Evaluation on Sensor Interoperability of Features in Fingerprint Image Segmentation

    Directory of Open Access Journals (Sweden)

    Ya-Shuo Li

    2012-03-01

    Full Text Available Features used in fingerprint segmentation significantly affect the segmentation performance. Various features exhibit different discriminating abilities on fingerprint images derived from different sensors. One feature which has better discriminating ability on images derived from a certain sensor may not adapt to segment images derived from other sensors. This degrades the segmentation performance. This paper empirically analyzes the sensor interoperability problem of segmentation feature, which refers to the feature’s ability to adapt to the raw fingerprints captured by different sensors. To address this issue, this paper presents a two-level feature evaluation method, including the first level feature evaluation based on segmentation error rate and the second level feature evaluation based on decision tree. The proposed method is performed on a number of fingerprint databases which are obtained from various sensors. Experimental results show that the proposed method can effectively evaluate the sensor interoperability of features, and the features with good evaluation results acquire better segmentation accuracies of images originating from different sensors.

  19. The SCUBA-2 Cosmology Legacy Survey: the nature of bright submm galaxies from 2 deg2 of 850-um imaging

    CERN Document Server

    Michałowski, Michał J; Koprowski, M P; Cirasuolo, M; Geach, J E; Bowler, R A A; Mortlock, A; Caputi, K I; Aretxaga, I; Arumugam, V; Chen, Chian-Chou; McLure, R J; Birkinshaw, M; Bourne, N; Farrah, D; Ibar, E; van der Werf, P; Zemcov, M

    2016-01-01

    We present physical properties [redshifts (z), star-formation rates (SFRs) and stellar masses (Mstar)] of nearly 2000 bright (S850 > 4 mJy) submm galaxies in the ~2 deg2 COSMOS and UDS fields selected with SCUBA-2 on the JCMT, representing the largest homogeneous sample of 850-um-selected sources to date. We check the reliability of our identifications, and the robustness of the SCUBA-2 fluxes by revisiting the recent ALMA follow-up. Considering > 4 mJy ALMA sources, our identification method has a completeness of ~86 per cent with a reliability of ~92 per cent, and only ~15-20 per cent of sources are significantly affected by multiplicity (when a secondary component is brighter than a third of the primary one). The impact of source blending on the 850-um source counts as determined with SCUBA-2 is modest; scaling the single-dish fluxes by ~0.9 reproduces the ALMA source counts. We find median values of z = 2.40+0.10-0.04, SFR = 287+-6 Mo yr-1, and log(Mstar/Mo) = 11.12+-0.02. These properties clearly locate ...

  20. Herschel and SCUBA-2 imaging and spectroscopy of a bright, lensed submillimetre galaxy at z = 2.3

    CERN Document Server

    Ivison, R J; Swinyard, B; Smail, Ian; Pearson, C P; Rigopoulou, D; Polehampton, E; Baluteau, J -P; Barlow, M J; Blain, A W; Bock, J; Clements, D L; Coppin, K; Cooray, A; Danielson, A; Dwek, E; Edge, A C; Franceschini, A; Fulton, T; Glenn, J; Griffin, M; Isaak, K; Leeks, S; Lim, T; Naylor, D; Oliver, S J; Page, M J; Perez-Fournon, I; Rowan-Robinson, M; Savini, G; Scott, D; Spencer, L; Valtchanov, I; Vigroux, L; Wright, G S

    2010-01-01

    We present a detailed analysis of the far-IR properties of the bright, lensed, z = 2.3, SMG, SMM J2135-0102, using new observations with Herschel, SCUBA-2 and the VLA. These data allow us to constrain the galaxy's SED and show that it has an intrinsic rest-frame 8-1000um luminosity, L(bol), of (2.3 +/- 0.2) x 10^12 L(sun) and a likely SFR of ~400 M(sun)/yr. The galaxy sits on the far-IR/radio correlation for far-IR-selected galaxies. At ~>70um, the SED can be described adequately by dust components with T(d) ~ 30 and 60K. Using SPIRE's Fourier Transform Spectrometer we report a detection of the [CII] 158um cooling line. If the [CII], CO and far-IR continuum arise in photo-dissociation regions, we derive a characteristic gas density, n ~ 10^3 cm^-3, and a far-UV radiation field, G_0, 10^3x stronger than the Milky Way. L([CII])/L(bol) is significantly higher than in local ULIRGs but similar to the values found in local star-forming galaxies and starburst nuclei. This is consistent with SMM J2135-0102 being powe...

  1. Unusual magnetic resonance imaging features in Menkes disease

    Energy Technology Data Exchange (ETDEWEB)

    Barnerias, C.; Desguerre, I.; Dulac, O.; Bahi-Buisson, N. [Hop Necker Enfants Malades, AP-HP, Dept Paediat Neurol and Metab Dis, F-75743 Paris 15 (France); Boddaert, N.; Hertz-Pannier, L. [Hop Necker Enfants Malad, AP-HP, Dept Pediat Radiol, F-75743 Paris (France); Boddaert, N. [CEA, Serv Hosp Frederic Joliot, INSERM, U797, F-91406 Orsay (France); Guiraud, P. [Univ Grenoble, Serv Biochim, Genet Hop, Grenoble (France); Hertz-Pannier, L.; Dulac, O.; Bahi-Buisson, N. [INSERM, U663, F-75015 Paris (France); Hertz-Pannier, L.; Dulac, O.; Bahi-Buisson, N. [Univ Paris 05, F-75005 Paris (France); De Lonlay, P. [Hop Necker Enfants Malades, AP-HP, Dept Paediat Neurol and Metab Dis, F-75743 Paris 15 (France); Hop Necker Enfants Malades, AP HP, Ctr Reference Malad Metab, F-75743 Paris 15 (France)

    2008-07-01

    We present a case of an inherited disorder of copper metabolism, Menkes disease in which MRI studies revealed the coexistence of T2 hyper-signal in the temporal white matter with an increase of apparent diffusion coefficient indicative of vasogenic oedema combined with T2 hyper-signal of the putamen and head of the caudate and decreased apparent diffusion coefficient indicative of cytotoxic oedema. These unusual MRI features emphasize the interest of newly developed techniques in early diagnosis in Menkes disease. The acute cerebral damage might result from the combined effects of acute metabolic stress due to infectious disease and prolonged status epilepticus, acting on a highly susceptible developing brain. Vasogenic oedema in the temporal white matter could be related to prolonged status epilepticus and vascular abnormalities. Cytotoxic oedema of the putamen and head caudate could result from energetic failure. (authors)

  2. Glioma grading using cell nuclei morphologic features in digital pathology images

    Science.gov (United States)

    Reza, Syed M. S.; Iftekharuddin, Khan M.

    2016-03-01

    This work proposes a computationally efficient cell nuclei morphologic feature analysis technique to characterize the brain gliomas in tissue slide images. In this work, our contributions are two-fold: 1) obtain an optimized cell nuclei segmentation method based on the pros and cons of the existing techniques in literature, 2) extract representative features by k-mean clustering of nuclei morphologic features to include area, perimeter, eccentricity, and major axis length. This clustering based representative feature extraction avoids shortcomings of extensive tile [1] [2] and nuclear score [3] based methods for brain glioma grading in pathology images. Multilayer perceptron (MLP) is used to classify extracted features into two tumor types: glioblastoma multiforme (GBM) and low grade glioma (LGG). Quantitative scores such as precision, recall, and accuracy are obtained using 66 clinical patients' images from The Cancer Genome Atlas (TCGA) [4] dataset. On an average ~94% accuracy from 10 fold crossvalidation confirms the efficacy of the proposed method.

  3. Multilevel binomial logistic prediction model for malignant pulmonary nodules based on texture features of CT image

    International Nuclear Information System (INIS)

    Purpose: To introduce multilevel binomial logistic prediction model-based computer-aided diagnostic (CAD) method of small solitary pulmonary nodules (SPNs) diagnosis by combining patient and image characteristics by textural features of CT image. Materials and methods: Describe fourteen gray level co-occurrence matrix textural features obtained from 2171 benign and malignant small solitary pulmonary nodules, which belongs to 185 patients. Multilevel binomial logistic model is applied to gain these initial insights. Results: Five texture features, including Inertia, Entropy, Correlation, Difference-mean, Sum-Entropy, and age of patients own aggregating character on patient-level, which are statistically different (P < 0.05) between benign and malignant small solitary pulmonary nodules. Conclusion: Some gray level co-occurrence matrix textural features are efficiently descriptive features of CT image of small solitary pulmonary nodules, which can profit diagnosis of earlier period lung cancer if combined patient-level characteristics to some extent.

  4. Digital Library ImageRetrieval usingScale Invariant Feature and Relevance Vector Machine

    Directory of Open Access Journals (Sweden)

    Hongtao Zhang

    2014-10-01

    Full Text Available With the advance of digital library, the digital content develops with rich information connotation. Traditional information retrieval methods based on external characteristic and text description are unable to sufficientlyreveal and express the substance and semantic relation of multimedia information, and unable to fully reveal and describe the representative characteristics of information. Because of the abundant connotation of image content and the people’s abstract subjectivity in studying image content, the visual feature of the image is difficult to be described by key words. Therefore, this method not always can meet people’s needs, and the study of digital library image retrieval technique based on content is important to both academic research and application. At present, image retrieval methods are mainly based on the text and content, etc. But these existing algorithms have shortages, such as large errors and slow speeds. Motivated by the above fact, we in this paper propose a new approach based on relevance vector machine (RVM. The proposed approach first extracts the patch-level scale invariant image feature (SIFT, and then constructs the global features for images. The image feature is then delivered into RVM for retrieval. We evaluate the proposed approach on Corel dataset. The experimental result shows that the proposed method in this text has high accuracy when retrieves images.

  5. Imaging Features of Pediatric Pentastomiasis Infection: a Case Report

    Energy Technology Data Exchange (ETDEWEB)

    Lai, Can; Wang, Xi Qun; Lin, Long; Gao, De Chun; Zhang, Hong Xi; Zhang, Yi Ying; Zhou, Yin Bao [Zhejiang University School of Medicine, Zhejiang (China)

    2010-08-15

    We report here a case of pentastomiasis infection in a 3-year-old girl who had high fever, abdominal pain, abdominal tension and anemia. Ultrasound scanning of the abdomen revealed disseminated hyperechoic nodules in the liver and a small amount of ascites. Abdominal MRI showed marked hepatomegaly with disseminated miliary nodules of high signal intensity throughout the hepatic parenchyma on T2-weighted images; retroperitoneal lymphadenopathy and disseminated miliary nodules on the peritoneum were also noted. Chest CT showed scattered small hyperdense nodules on both sides of the lungs. The laparoscopy demonstrated diffuse white nodules on the liver surface and the peritoneum. After the small intestinal wall and peritoneal biopsy, histological examination revealed parenchymal tubercles containing several larvae of pentastomids and a large amount of inflammatory cell infiltration around them. The pathological diagnosis was parasitic granuloma from pentastomiasis infection

  6. STUDY ON THE TECHNIQUE TO DETECT TEXTURE FEATURES IN SAR IMAGES

    Institute of Scientific and Technical Information of China (English)

    Fu Yusheng; Ding Dongtao; Hou Yinming

    2004-01-01

    This letter studies on the detection of texture features in Synthetic Aperture Radar (SAR) images. Through analyzing the feature detection method proposed by Lopes, an improved texture detection method is proposed, which can not only detect the edge and lines but also avoid stretching edge and suppressing lines of the former algorithm. Experimental results with both simulated and real SAR images verify the advantage and practicability of the improved method.

  7. A new approach to modeling the influence of image features on fixation selection in scenes

    OpenAIRE

    Nuthmann, Antje; Einhäuser, Wolfgang

    2015-01-01

    Which image characteristics predict where people fixate when memorizing natural images? To answer this question, we introduce a new analysis approach that combines a novel scene-patch analysis with generalized linear mixed models (GLMMs). Our method allows for (1) directly describing the relationship between continuous feature value and fixation probability, and (2) assessing each feature's unique contribution to fixation selection. To demonstrate this method, we estimated the relative contri...

  8. Extraction of Geometric Features of Wear Particles in Color Ferrograph Images Based on RGB Color Space

    Institute of Scientific and Technical Information of China (English)

    CHEN Gui-ming; WANG Han-gong; ZHANG Bao-jun; PAN Wei

    2003-01-01

    This paper analyzes the potential color formats of ferrograph images, and presents the algorithms of converting the formats to RGB(Red, Green, Blue) color space. Through statistical analysis of wear par-ticles' geometric features of color ferrograph images in the RGB color space, we give the differences of ferro-graph wear panicles' geometric features among RGB color spaces and gray scale space, and calculate their respective distributions.

  9. Unsupervised Skin cancer detection by combination of texture and shape features in dermoscopy images

    Directory of Open Access Journals (Sweden)

    Hamed aghapanah rudsari

    2014-05-01

    Full Text Available In this paper a novel unsupervised feature extraction method for detection of melanoma in skin images is presented. First of all, normal skin surrounding the lesion is removed in a segmentation process. In the next step, some shape and texture features are extracted from the output image of the first step: GLCM, GLRLM, the proposed directional-frequency features, and some parameters of Ripplet transform are used as texture features; Also, NRL features and Zernike moments are used as shape features. Totally, 63 texture features and 31 shape features are extracted. Finally, the number of extracted features is reduced using PCA method and a proposed method based on Fisher criteria. Extracted features are classified using the Perceptron Neural Networks, Support Vector Machine, 4-NN, and Naïve Bayes. The results show that SVM has the best performance. The proposed algorithm is applied on a database that consists of 160 labeled images. The overall results confirm the superiority of the proposed method in both accuracy and reliability over previous works.

  10. Orientation Modeling for Amateur Cameras by Matching Image Line Features and Building Vector Data

    Science.gov (United States)

    Hung, C. H.; Chang, W. C.; Chen, L. C.

    2016-06-01

    With the popularity of geospatial applications, database updating is getting important due to the environmental changes over time. Imagery provides a lower cost and efficient way to update the database. Three dimensional objects can be measured by space intersection using conjugate image points and orientation parameters of cameras. However, precise orientation parameters of light amateur cameras are not always available due to their costliness and heaviness of precision GPS and IMU. To automatize data updating, the correspondence of object vector data and image may be built to improve the accuracy of direct georeferencing. This study contains four major parts, (1) back-projection of object vector data, (2) extraction of image feature lines, (3) object-image feature line matching, and (4) line-based orientation modeling. In order to construct the correspondence of features between an image and a building model, the building vector features were back-projected onto the image using the initial camera orientation from GPS and IMU. Image line features were extracted from the imagery. Afterwards, the matching procedure was done by assessing the similarity between the extracted image features and the back-projected ones. Then, the fourth part utilized line features in orientation modeling. The line-based orientation modeling was performed by the integration of line parametric equations into collinearity condition equations. The experiment data included images with 0.06 m resolution acquired by Canon EOS Mark 5D II camera on a Microdrones MD4-1000 UAV. Experimental results indicate that 2.1 pixel accuracy may be reached, which is equivalent to 0.12 m in the object space.

  11. A Feature Subtraction Method for Image Based Kinship Verification under Uncontrolled Environments

    DEFF Research Database (Denmark)

    Duan, Xiaodong; Tan, Zheng-Hua

    2015-01-01

    The most fundamental problem of local feature based kinship verification methods is that a local feature can capture the variations of environmental conditions and the differences between two persons having a kin relation, which can significantly decrease the performance. To address this problem...... the feature distance between face image pairs with kinship and maximize the distance between non-kinship pairs. Based on the subtracted feature, the verification is realized through a simple Gaussian based distance comparison method. Experiments on two public databases show that the feature subtraction method...

  12. A Novel Semi-blind Watermarking Algorithm Based on Fractal Dimension and Image Feature

    Institute of Scientific and Technical Information of China (English)

    NIRongrong; RUANQiuqi

    2004-01-01

    This paper presents a novel semi-blind watermarking algorithm based on fractal dimension and image feature. An original image is divided into blocks with fixed size. According to the idea of the second generation watermarking[1], the image is analyzed using fractal dimension to attain its feature blocks containing edges and textures that are used in the later embedding process and used to form a feature label. The watermark that is the fusion of the feature label and a binary copyright symbol not only represents the copyright symbol, but also reflects the feature of the image. Arnold iteration transform is employed to increase the security of watermark. Then,DCT (Discrete cosine transform) is applied to the feature blocks. The secure watermark that is adaptive to the individual image is embedded into the relations between middle-frequency coefficients and corresponding DC coefficients. The detection and extraction procedure is a semiblind one which does not use the original image but the watermark. Only those who have the original watermarkand the key can detect and extract the right watermark.This makes the approach authentic and have high securitylevel. Experimental results show that this algorithm can get good perceptual invisibility, adaptability and security.And it is robust against cropping, scribbling, low or highpass filtering, adding noise and JPEG compression.

  13. A new approach to modeling the influence of image features on fixation selection in scenes.

    Science.gov (United States)

    Nuthmann, Antje; Einhäuser, Wolfgang

    2015-03-01

    Which image characteristics predict where people fixate when memorizing natural images? To answer this question, we introduce a new analysis approach that combines a novel scene-patch analysis with generalized linear mixed models (GLMMs). Our method allows for (1) directly describing the relationship between continuous feature value and fixation probability, and (2) assessing each feature's unique contribution to fixation selection. To demonstrate this method, we estimated the relative contribution of various image features to fixation selection: luminance and luminance contrast (low-level features); edge density (a mid-level feature); visual clutter and image segmentation to approximate local object density in the scene (higher-level features). An additional predictor captured the central bias of fixation. The GLMM results revealed that edge density, clutter, and the number of homogenous segments in a patch can independently predict whether image patches are fixated or not. Importantly, neither luminance nor contrast had an independent effect above and beyond what could be accounted for by the other predictors. Since the parcellation of the scene and the selection of features can be tailored to the specific research question, our approach allows for assessing the interplay of various factors relevant for fixation selection in scenes in a powerful and flexible manner. PMID:25752239

  14. UNLABELED SELECTED SAMPLES IN FEATURE EXTRACTION FOR CLASSIFICATION OF HYPERSPECTRAL IMAGES WITH LIMITED TRAINING SAMPLES

    Directory of Open Access Journals (Sweden)

    A. Kianisarkaleh

    2015-12-01

    Full Text Available Feature extraction plays a key role in hyperspectral images classification. Using unlabeled samples, often unlimitedly available, unsupervised and semisupervised feature extraction methods show better performance when limited number of training samples exists. This paper illustrates the importance of selecting appropriate unlabeled samples that used in feature extraction methods. Also proposes a new method for unlabeled samples selection using spectral and spatial information. The proposed method has four parts including: PCA, prior classification, posterior classification and sample selection. As hyperspectral image passes these parts, selected unlabeled samples can be used in arbitrary feature extraction methods. The effectiveness of the proposed unlabeled selected samples in unsupervised and semisupervised feature extraction is demonstrated using two real hyperspectral datasets. Results show that through selecting appropriate unlabeled samples, the proposed method can improve the performance of feature extraction methods and increase classification accuracy.

  15. Improving Image steganalysis performance using a graph-based feature selection method

    Directory of Open Access Journals (Sweden)

    Amir Nouri

    2016-05-01

    Full Text Available Steganalysis is the skill of discovering the use of steganography algorithms within an image with low or no information regarding the steganography algorithm or/and its parameters. The high-dimensionality of image data with small number of samples has presented a difficult challenge for the steganalysis task. Several methods have been presented to improve the steganalysis performance by feature selection. Feature selection, also known as variable selection, is one of the fundamental problems in the fields of machine learning, pattern recognition and statistics. The aim of feature selection is to reduce the dimensionality of image data in order to enhance the accuracy of Steganalysis task. In this paper, we have proposed a new graph-based blind steganalysis method for detecting stego images from the cover images in JPEG images using a feature selection technique based on community detection. The experimental results show that the proposed approach is easy to be employed for steganalysis purposes. Moreover, performance of proposed method is better than several recent and well-known feature selection-based Image steganalysis methods.

  16. Introduction: Feature Issue on Phantoms for the Performance Evaluation and Validation of Optical Medical Imaging Devices

    OpenAIRE

    Hwang, Jeeseong; Ramella-Roman, Jessica C.; Nordstrom, Robert

    2012-01-01

    The editors introduce the Biomedical Optics Express feature issue on “Phantoms for the Performance Evaluation and Validation of Optical Medical Imaging Devices.” This topic was the focus of a technical workshop that was held on November 7–8, 2011, in Washington, D.C. The feature issue includes 13 contributions from workshop attendees.

  17. FURTHER EVALUATION OF QUANTITATIVE NUCLEAR IMAGE FEATURES FOR CLASSIFICATION OF LUNG CARCINOMAS

    NARCIS (Netherlands)

    THUNNISSEN, FBJM; DIEGENBACH, PC; VANHATTUM, AH; TOLBOOM, J; VANDERSLUIS, DM; SCHAAFSMA, W; HOUTHOFF, HJ; BAAK, JPA

    1992-01-01

    The usefulness of quantitative nuclear image features (QNI) for the histological classification of lung carcinomas was investigated. As no clear distinction could be established between the distributions of these features for the nuclei of squamous cell, adenocarcinoma, and large cell carcinoma, the

  18. On the selection of optimal feature region set for robust digital image watermarking.

    Science.gov (United States)

    Tsai, Jen-Sheng; Huang, Win-Bin; Kuo, Yau-Hwang

    2011-03-01

    A novel feature region selection method for robust digital image watermarking is proposed in this paper. This method aims to select a nonoverlapping feature region set, which has the greatest robustness against various attacks and can preserve image quality as much as possible after watermarked. It first performs a simulated attacking procedure using some predefined attacks to evaluate the robustness of every candidate feature region. According to the evaluation results, it then adopts a track-with-pruning procedure to search a minimal primary feature set which can resist the most predefined attacks. In order to enhance its resistance to undefined attacks under the constraint of preserving image quality, the primary feature set is then extended by adding into some auxiliary feature regions. This work is formulated as a multidimensional knapsack problem and solved by a genetic algorithm based approach. The experimental results for StirMark attacks on some benchmark images support our expectation that the primary feature set can resist all the predefined attacks and its extension can enhance the robustness against undefined attacks. Comparing with some well-known feature-based methods, the proposed method exhibits better performance in robust digital watermarking.

  19. Image library approach to evaluating parametric uncertainty in metrology of isolated feature width

    Science.gov (United States)

    Potzick, James

    2009-03-01

    When measuring the width of an isolated line or space on a wafer or photomask, only the feature's image is measured, not the object itself. Often the largest contributors to measurement uncertainty are the uncertainties in the parameters which affect the image. Measurement repeatability is often smaller than the combined parametric uncertainty. An isolated feature's edges are far enough away from nearest edges of other features that its image does not change if this distance is increased (about 10 wavelengths in an optical microscope or exposure tool, or several effective-beam-widths in a SEM). When the leading and trailing edges of the same feature are not isolated from each other the metrology process becomes nonlinear. Isolated features may not be amenable to measurement by grating methods (e.g., scatterometry), and there is no hard lower limit to how small an isolated feature can be measured. There are several ways to infer the size of an isolated feature from its image in a microscope (SEM, AFM, optical,...), and they all require image modeling. Image modeling accounts for the influence of all of the parameters which can affect the image, and relates the apparent linewidth (in the image) to the true linewidth (on the object). The values of these parameters, however, have uncertainties and these uncertainties propagate through the model and lead to parametric uncertainty in the linewidth measurement, along with the scale factor uncertainty and the measurement repeatability. The combined measurement uncertainty is required in order to decide if the result is adequate for its intended purpose and to ascertain if it is consistent with other similar results. The parametric uncertainty for optical photomask measurements derived using an edge threshold approach has been described previously [1]; this paper describes an image library approach to this issue and shows results for optical photomask metrology over a linewidth and spacewidth range of 10 nm to 4 μm. The

  20. The Feature Extraction Based on Texture Image Information for Emotion Sensing in Speech

    Directory of Open Access Journals (Sweden)

    Kun-Ching Wang

    2014-09-01

    Full Text Available In this paper, we present a novel texture image feature for Emotion Sensing in Speech (ESS. This idea is based on the fact that the texture images carry emotion-related information. The feature extraction is derived from time-frequency representation of spectrogram images. First, we transform the spectrogram as a recognizable image. Next, we use a cubic curve to enhance the image contrast. Then, the texture image information (TII derived from the spectrogram image can be extracted by using Laws’ masks to characterize emotional state. In order to evaluate the effectiveness of the proposed emotion recognition in different languages, we use two open emotional databases including the Berlin Emotional Speech Database (EMO-DB and eNTERFACE corpus and one self-recorded database (KHUSC-EmoDB, to evaluate the performance cross-corpora. The results of the proposed ESS system are presented using support vector machine (SVM as a classifier. Experimental results show that the proposed TII-based feature extraction inspired by visual perception can provide significant classification for ESS systems. The two-dimensional (2-D TII feature can provide the discrimination between different emotions in visual expressions except for the conveyance pitch and formant tracks. In addition, the de-noising in 2-D images can be more easily completed than de-noising in 1-D speech.

  1. Scene Classification of Remote Sensing Image Based on Multi-scale Feature and Deep Neural Network

    Directory of Open Access Journals (Sweden)

    XU Suhui

    2016-07-01

    Full Text Available Aiming at low precision of remote sensing image scene classification owing to small sample sizes, a new classification approach is proposed based on multi-scale deep convolutional neural network (MS-DCNN, which is composed of nonsubsampled Contourlet transform (NSCT, deep convolutional neural network (DCNN, and multiple-kernel support vector machine (MKSVM. Firstly, remote sensing image multi-scale decomposition is conducted via NSCT. Secondly, the decomposing high frequency and low frequency subbands are trained by DCNN to obtain image features in different scales. Finally, MKSVM is adopted to integrate multi-scale image features and implement remote sensing image scene classification. The experiment results in the standard image classification data sets indicate that the proposed approach obtains great classification effect due to combining the recognition superiority to different scenes of low frequency and high frequency subbands.

  2. Review of Metaplastic Carcinoma of the Breast: Imaging Findings and Pathologic Features

    Directory of Open Access Journals (Sweden)

    Rebecca Leddy

    2012-01-01

    Full Text Available Metaplastic carcinoma (MPC, an uncommon but often aggressive breast cancer, can be challenging to differentiate from other types of breast cancer and even benign lesions based on the imaging appearance. It has a variable pathology classification system. These types of tumors are generally rapidly growing palpable masses. MPCs on imaging can present with imaging features similar to invasive ductal carcinoma and probably even benign lesions. The purpose of this article is to review MPC of the breast including the pathology subtypes, imaging features, and imaging pathology correlations. By understanding the clinical picture, pathology, and overlap in imaging characteristics of MPC with invasive ductal carcinoma and probably benign lesions can assist in diagnosing these difficult malignancies.

  3. IMAGING SPECTROSCOPY AND LIGHT DETECTION AND RANGING DATA FUSION FOR URBAN FEATURES EXTRACTION

    OpenAIRE

    Mohammed Idrees; Helmi Zulhaidi Mohd Shafri; Vahideh Saeidi

    2013-01-01

    This study presents our findings on the fusion of Imaging Spectroscopy (IS) and LiDAR data for urban feature extraction. We carried out necessary preprocessing of the hyperspectral image. Minimum Noise Fraction (MNF) transforms was used for ordering hyperspectral bands according to their noise. Thereafter, we employed Optimum Index Factor (OIF) to statistically select the three most appropriate bands combination from MNF result. The composite image was classified using unsupervised classifica...

  4. Item Popularity Prediction in E-commerce Using Image Quality Feature Vectors

    OpenAIRE

    Zakrewsky, Stephen; Aryafar, Kamelia; Shokoufandeh, Ali

    2016-01-01

    Online retail is a visual experience- Shoppers often use images as first order information to decide if an item matches their personal style. Image characteristics such as color, simplicity, scene composition, texture, style, aesthetics and overall quality play a crucial role in making a purchase decision, clicking on or liking a product listing. In this paper we use a set of image features that indicate quality to predict product listing popularity on a major e-commerce website, Etsy. We fir...

  5. Face Recognition from Still Images to Video Sequences: A Local-Feature-Based Framework

    OpenAIRE

    Shaokang Chen; Sandra Mau; Harandi, Mehrtash T.; Conrad Sanderson; Abbas Bigdeli; Lovell, Brian C.

    2011-01-01

    Although automatic faces recognition has shown success for high-quality images under controlled conditions, for video-based recognition it is hard to attain similar levels of performance. We describe in this paper recent advances in a project being undertaken to trial and develop advanced surveillance systems for public safety. In this paper, we propose a local facial feature based framework for both still image and video-based face recognition. The evaluation is performed on a still image d...

  6. MR Imaging of Pregnancy Luteoma: a Case Report and Correlation with the Clinical Features

    OpenAIRE

    Kao, Hung-Wen; Wu, Ching-Jiunn; Chung, Kuo-Teng; Wang, Sheng-Ru; Chen, Cheng-Yu

    2005-01-01

    We report here on a 26-year-old pregnant female who developed hirsutism and virilization during her third trimester along with a significantly elevated serum testosterone level. Abdominal US and MR imaging studies were performed, and they showed unique imaging features that may suggest the diagnosis of pregnancy luteoma in the clinical context. After the delivery, the serum testosterone level continued to decrease, and it returned to normal three weeks postpartum. The follow-up imaging findin...

  7. Effective palette indexing for image compression using self-organization of Kohonen feature map.

    Science.gov (United States)

    Pei, Soo-Chang; Chuang, Yu-Ting; Chuang, Wei-Hong

    2006-09-01

    The process of limited-color image compression usually involves color quantization followed by palette re-indexing. Palette re-indexing could improve the compression of color-indexed images, but it is still complicated and consumes extra time. Making use of the topology-preserving property of self-organizing Kohonen feature map, we can generate a fairly good color index table to achieve both high image quality and high compression, without re-indexing. Promising experiment results will be presented.

  8. Improved Block Based Feature Level Image Fusion Technique Using Contourlet with Neural Network

    Directory of Open Access Journals (Sweden)

    C.M.Sheela Rani

    2012-08-01

    Full Text Available As multisensory data is made available in many areas such as remote sensing, medical imaging, etc, the sensor fusion has become a new field for research. Multisensor image fusion mainly focuses on combining spatial information of a high resolution panchromatic (PAN image with spectral information of a low resolution multispectral image (MS to produce an image with highest spatial content while preserving spectral resolution. A geometrical transform called contourlet transform (CT is introduced, which represents images containing contours and textures. This paper derived an efficient block based feature level contourlet transform with neural network (BFCN model for image fusion. The proposed BFCN model integrates CT with neural network (NN, which plays a significant role in feature extraction and detection in machine learning applications. In the proposed BFCN model, the two fusion techniques, CT and NN are discussed for fusing the IRS-1D images using LISS III scanner about the locations Hyderabad, Vishakhapatnam, Mahaboobnagar and Patancheru in Andhra Pradesh, India. Also Landsat 7 image data and QuickBird image data are used to perform experiments on the proposed BFCN model. The features under study are contrast visibility, spatial frequency, energy of gradient, variance and edge information. Feed forward back propagation neural network is trained and tested for classification, since the learning capability of NN makes it feasible to customize the image fusion process. The trained NN is then used to fuse the pair of source images. The proposed BFCN model is compared with other techniques to assess the quality of the fused image. Experimental results clearly prove that the proposed BFCN model is an efficient and feasible algorithm for image fusion.

  9. Improved Block Based Feature Level Image Fusion Technique Using Contourlet with Neural Network

    Directory of Open Access Journals (Sweden)

    C.M.Sheela Rani

    2012-09-01

    Full Text Available As multisensory data is made available in many areas such as remote sensing, medical imaging, etc, thesensor fusion has become a new field for research. Multisensor image fusion mainly focuses on combining spatial information of a high resolution panchromatic (PAN image with spectral information of a low resolution multispectral image (MS to produce an image with highest spatial content while preserving spectral resolution. A geometrical transform called contourlet transform (CT is introduced, which represents images containing contours and textures. This paper derived an efficient block based feature level contourlet transform with neural network (BFCN model for image fusion. The proposed BFCN model integrates CT with neural network (NN, which plays a significant role in feature extraction and detection in machine learning applications. In the proposed BFCN model, the two fusion techniques, CT and NN are discussed for fusing the IRS-1D images using LISS III scanner about the locations Hyderabad, Vishakhapatnam, Mahaboobnagar and Patancheru in Andhra Pradesh, India. Also Landsat 7 image data and QuickBird image data are used to perform experiments on the proposed BFCN model. The features under study are contrast visibility, spatial frequency, energy of gradient, variance and edge information. Feed forward back propagation neural network is trained and tested for classification, since the learning capability of NN makes it feasible to customize the image fusion process. The trained NN is then used to fuse the pair of source images. The proposed BFCN model is compared with other techniques to assess the quality of the fused image. Experimental results clearly prove that the proposed BFCN model is an efficient and feasible algorithm for image fusion.

  10. A unified framework of image latent feature learning on Sina microblog

    Science.gov (United States)

    Wei, Jinjin; Jin, Zhigang; Zhou, Yuan; Zhang, Rui

    2015-10-01

    Large-scale user-contributed images with texts are rapidly increasing on the social media websites, such as Sina microblog. However, the noise and incomplete correspondence between the images and the texts give rise to the difficulty in precise image retrieval and ranking. In this paper, a hypergraph-based learning framework is proposed for image ranking, which simultaneously utilizes visual feature, textual content and social link information to estimate the relevance between images. Representing each image as a vertex in the hypergraph, complex relationship between images can be reflected exactly. Then updating the weight of hyperedges throughout the hypergraph learning process, the effect of different edges can be adaptively modulated in the constructed hypergraph. Furthermore, the popularity degree of the image is employed to re-rank the retrieval results. Comparative experiments on a large-scale Sina microblog data-set demonstrate the effectiveness of the proposed approach.

  11. Using machine learning to classify image features from canine pelvic radiographs

    DEFF Research Database (Denmark)

    McEvoy, Fintan; Amigo Rubio, Jose Manuel

    2013-01-01

    %, and 100%. Findings indicated that statistical classification of veterinary images is feasible and has the potential for grouping and classifying images or image features, especially when a large number of well-classified images are available for model training.......As the number of images per study increases in the field of veterinary radiology, there is a growing need for computer-assisted diagnosis techniques. The purpose of this study was to evaluate two machine learning statistical models for automatically identifying image regions that contain the canine...... hip joint on ventrodorsal pelvis radiographs. A training set of images (120 of the hip and 80 from other regions) was used to train a linear partial least squares discriminant analysis (PLS-DA) model and a nonlinear artificial neural network (ANN) model to classify hip images. Performance...

  12. Unexpected diagnosis of superficial neurofibroma in a lesion with imaging features of a vascular malformation

    Energy Technology Data Exchange (ETDEWEB)

    O' Keefe, Patrick; Reid, Janet; Morrison, Stuart [Cleveland Clinic Foundation, Department of Radiology, Cleveland, OH (United States); Vidimos, Allison [Cleveland Clinic Foundation, Department of Dermatology, Cleveland, OH (United States); DiFiore, John [Cleveland Clinic Foundation, Department of Pediatric Surgery, Cleveland, OH (United States)

    2005-12-01

    Plexiform neurofibroma is a pathognomonic, often disabling feature of neurofibromatosis type I. Although the target-like appearance of deep plexiform neurofibroma on T2-weighted MRI has been well-described, a second superficial form of plexiform neurofibroma has differing imaging features. We report a 15-year-old boy who presented with multiple cutaneous lesions exhibiting clinical and imaging characteristics of a venolymphatic malformation. These lesions were histologically proved to represent superficial plexiform neurofibromas. We wish to emphasize the unique MR findings of superficial plexiform neurofibromas; these findings are different from the imaging characteristics of the deep form and can be confused with a low-flow vascular malformation. (orig.)

  13. A Fast Feature Extraction Method Based on Integer Wavelet Transform for Hyperspectral Images

    Institute of Scientific and Technical Information of China (English)

    GUYanfeng; ZHANGYe; YUShanshan

    2004-01-01

    Hyperspectral remote sensing provides high-resolution spectral data and the potential for remote discrimination between subtle differences in ground covers. However, the high-dimensional data space generated by the hyperspectral sensors creates a new challenge for conventional spectral data analysis techniques. A challenging problem in using hyperspectral data is to eliminate redundancy and preserve useful spectral information for applications. In this paper, a Fast feature extraction (FFE) method based on integer wavelet transform is proposed to extract useful features and reduce dimensionality of hyperspectral images. The FFE method can be directly used to extract useful features from spectral vector of each pixel resident in the hyperspectral images. The FFE method has two main merits: high computational efficiency and good ability to extract spectral features. In order to better testify the effectiveness and the performance of the proposed method, classification experiments of hyperspectral images are performed on two groups of AVIRIS (Airborne visible/infrared imaging spectrometer) data respectively. In addition, three existing methods for feature extraction of hyperspectral images, i.e. PCA, SPCT and Wavelet Transform, are performed on the same data for comparison with the proposed method. The experimental investigation shows that the efficiency of the FFE method for feature extraction outclasses those of the other three methods mentioned above.

  14. IMAGE INFORMATION RETRIEVAL FROM INCOMPLETE QUERIES USING COLOR AND SHAPE FEATURES

    Directory of Open Access Journals (Sweden)

    Bikesh Kumar Singh

    2012-01-01

    Full Text Available Content based image retrieval (CBIR is the task of searching digital images from a large database basedon the extraction of features, such as color, texture and shape of the image. Most of the research in CBIRhas been carried out with complete queries which were present in the database. This paper investigatesutility of CBIR techniques for retrieval of incomplete and distorted queries. Studies were made in twocategories of the query: first is complete and second is incomplete. The query image is considered to bedistorted or incomplete image if it has some missing information, some undesirable objects, blurring, noisedue to disturbance at the time of image acquisition etc. Color (hue, saturation and value (HSV color spacemodel and shape (moment invariants and Fourier descriptor features are used to represent the image.The algorithm was tested on database consisting of 1875 images. The results show that retrieval accuracyof incomplete queries is highly increased by fusing color and shape features giving precision of 79.87%.MATLAB ® 7.01 and its image processing toolbox have been used to implement the algorithm.

  15. Image Information Retrieval From Incomplete Queries Using Color and Shape Features

    Directory of Open Access Journals (Sweden)

    Bikesh Kumar Singh

    2011-12-01

    Full Text Available Content based image retrieval (CBIR is the task of searching digital images from a large database basedon the extraction of features, such as color, texture and shape of the image. Most of the research in CBIRhas been carried out with complete queries which were present in the database. This paper investigatesutility of CBIR techniques for retrieval of incomplete and distorted queries. Studies were made in twocategories of the query: first is complete and second is incomplete. The query image is considered to bedistorted or incomplete image if it has some missing information, some undesirable objects, blurring, noisedue to disturbance at the time of image acquisition etc. Color (hue, saturation and value (HSV color spacemodel and shape (moment invariants and Fourier descriptor features are used to represent the image.The algorithm was tested on database consisting of 1875 images. The results show that retrieval accuracyof incomplete queries is highly increased by fusing color and shape features giving precision of 79.87%.MATLAB ® 7.01 and its image processing toolbox have been used to implement the algorithm.

  16. Hyperspectral image classification based on spatial and spectral features and sparse representation

    Institute of Scientific and Technical Information of China (English)

    Yang Jing-Hui; Wang Li-Guo; Qian Jin-Xi

    2014-01-01

    To minimize the low classification accuracy and low utilization of spatial information in traditional hyperspectral image classification methods, we propose a new hyperspectral image classification method, which is based on the Gabor spatial texture features and nonparametric weighted spectral features, and the sparse representation classification method (Gabor–NWSF and SRC), abbreviated GNWSF–SRC. The proposed (GNWSF–SRC) method first combines the Gabor spatial features and nonparametric weighted spectral features to describe the hyperspectral image, and then applies the sparse representation method. Finally, the classification is obtained by analyzing the reconstruction error. We use the proposed method to process two typical hyperspectral data sets with different percentages of training samples. Theoretical analysis and simulation demonstrate that the proposed method improves the classification accuracy and Kappa coefficient compared with traditional classification methods and achieves better classification performance.

  17. Image Enhancement Techniques for Quantitative Investigations of Morphological Features in Cometary Comae: A Comparative Study

    CERN Document Server

    Samarasinha, Nalin

    2014-01-01

    Many cometary coma features are only a few percent above the ambient coma (i.e., the background) and therefore coma enhancement techniques are needed to discern the morphological structures present in cometary comae. A range of image enhancement techniques widely used by cometary scientists is discussed by categorizing them and carrying out a comparative analysis. The enhancement techniques and the corresponding characteristics are described in detail and the respective mathematical representations are provided. As the comparative analyses presented in this paper make use of simulated images with known coma features, the feature identifications as well as the artifacts caused by enhancement provide an objective and definitive assessment of the various techniques. Examples are provided which highlight contrasting capabilities of different techniques to pick out qualitatively distinct features of widely different strengths and spatial scales. On account of this as well as serious image artifacts and spurious fe...

  18. CT and MR imaging features of oral and maxillofacial hemangioma and vascular malformation

    International Nuclear Information System (INIS)

    Purpose: To present CT and MR images and compare CT and MRI features of oral and maxillofacial hemangioma and vascular malformation. Material and methods: The clinical materials consisted of nine vascular tumors from nine patients examined by both CT and MR scanners between November 1996 and March 2002. Both CT and MR images were retrospectively evaluated. The following features were evaluated: detectability of the lesion, border of the lesion, tumor margin, inner nature of the lesion, contrast between the lesion and surrounding tissues, degree of CT value or signal intensity of the lesion, enhancement of contrast medium, inner nature of the lesion after contrast medium injection, detectability of phleboliths and detectability of bone resorption. Results: In two patients, we could not detect lesions in any of the CT images because of artifacts from the teeth and/or dental restorations. In contrast, we could detect all lesions on T2-weighted MR images and contrast enhanced T1-weighted MR images. On T2-weighted images with the fat suppression technique, tumors tended to show higher contrast compared to surrounding tissues. Conclusion: T2-weighted images with the fat suppression technique and contrast enhanced T1-weighted images with the fat suppression technique were very useful for the detection of vascular lesions. Observation from optional directions (axial, coronal and sagittal images) seemed appropriate for delineating the extension of the tumor. Phleboliths detectability on CT images was superior to that on MR images

  19. Robust Image Watermarking Using Local Invariant Features and Independent Component Analysis

    Institute of Scientific and Technical Information of China (English)

    ZHANG Hanling; LIU Jie

    2006-01-01

    This paper proposes a novel robust image watermarking scheme for digital images using local invariant features and Independent Component Analysis(ICA). Most present watermarking algorithms are unable to resist geometric distortions that desynchronize the location. The method we propose here is robust to geometric attacks. In order to resist geometric distortions, we use a local invariant feature of the image called the scale invariant feature transform, which is invariant to translation and scaling distortions. The watermark is inserted into the circular patches generated by scale-invariant key point extractor. Rotation invariance is achieved using the translation property of the polar-mapped circular patches. Our method belongs to the blind watermark category, because we use Independent Component Analysis for detection that does not need the original image during detection. Experimental results show that our method is robust against geometric distortion attacks as well as signal-processing attacks.

  20. Vehicle detection from high-resolution aerial images based on superpixel and color name features

    Science.gov (United States)

    Chen, Ziyi; Cao, Liujuan; Yu, Zang; Chen, Yiping; Wang, Cheng; Li, Jonathan

    2016-03-01

    Automatic vehicle detection from aerial images is emerging due to the strong demand of large-area traffic monitoring. In this paper, we present a novel framework for automatic vehicle detection from the aerial images. Through superpixel segmentation, we first segment the aerial images into homogeneous patches, which consist of the basic units during the detection to improve efficiency. By introducing the sparse representation into our method, powerful classification ability is achieved after the dictionary training. To effectively describe a patch, the Histogram of Oriented Gradient (HOG) is used. We further propose to integrate color information to enrich the feature representation by using the color name feature. The final feature consists of both HOG and color name based histogram, by which we get a strong descriptor of a patch. Experimental results demonstrate the effectiveness and robust performance of the proposed algorithm for vehicle detection from aerial images.

  1. A Fast Image Retrieval Algorithm with Multi-Channel Textural Features in PACS

    Institute of Scientific and Technical Information of China (English)

    ZHANG Dong; YANG Yan; QIN Qian-qing

    2005-01-01

    The paper presents a fast algorithm for image retrieval using multi-channel textural features in medical picture archiving and communication system (PACS). By choosing different linear or nonlinear operators in prediction and update lifting step, the linear or nonlinear M-band wavelet decomposition can be achieved in Mband lifting. It provides the advantages such as fast transform, in-place calculation and integer-integer transform. The set of wavelet moment forms multi-channel textural feature vector related to the texture distribution of each wavelet images. The experimental results of CT image database show that the retrieval approach of multi-channel textural features is effective for image indexing and has lower computational complexity and less memory. It is much easier to implement in hardware and suitable for the applications of real time medical processing system.

  2. Vehicle Detection in Still Images by Using Boosted Local Feature Detector

    Institute of Scientific and Technical Information of China (English)

    Qing LIN; Young-joon HAN; Hern-soo HAHN

    2010-01-01

    Vehicle detection in still images is a comparatively difficult task.This paper presents a method for this task by using boosted local pattem detector constructed from two local features including Haar-like and oriented gradient features.The whole process is composed of three stages.In the first stage,local appearance features of vehicles and non-vehicle objects are extracted.Haar-like and oriented gradient features arc extracted separately in this stage as local features.In the second stage,Adaboost algorithm is used to select the mast discriminative features as weak detectors from the two local feature sets,and a strong local pattern detector is built by the weighted combination of these selected weak detectors.Finally,vehicle detection can be performed in still images by using the boosted strong local feature detector.Experiment results show that the local pattern detectur constructed in this way combines the advantages of Haar-like and oriented gradient features,and can achieve better detection results than the datector by using single Haar-like features.

  3. Computer-aided breast MR image feature analysis for prediction of tumor response to chemotherapy

    International Nuclear Information System (INIS)

    Purpose: To identify a new clinical marker based on quantitative kinetic image features analysis and assess its feasibility to predict tumor response to neoadjuvant chemotherapy. Methods: The authors assembled a dataset involving breast MR images acquired from 68 cancer patients before undergoing neoadjuvant chemotherapy. Among them, 25 patients had complete response (CR) and 43 had partial and nonresponse (NR) to chemotherapy based on the response evaluation criteria in solid tumors. The authors developed a computer-aided detection scheme to segment breast areas and tumors depicted on the breast MR images and computed a total of 39 kinetic image features from both tumor and background parenchymal enhancement regions. The authors then applied and tested two approaches to classify between CR and NR cases. The first one analyzed each individual feature and applied a simple feature fusion method that combines classification results from multiple features. The second approach tested an attribute selected classifier that integrates an artificial neural network (ANN) with a wrapper subset evaluator, which was optimized using a leave-one-case-out validation method. Results: In the pool of 39 features, 10 yielded relatively higher classification performance with the areas under receiver operating characteristic curves (AUCs) ranging from 0.61 to 0.78 to classify between CR and NR cases. Using a feature fusion method, the maximum AUC = 0.85 ± 0.05. Using the ANN-based classifier, AUC value significantly increased to 0.96 ± 0.03 (p < 0.01). Conclusions: This study demonstrated that quantitative analysis of kinetic image features computed from breast MR images acquired prechemotherapy has potential to generate a useful clinical marker in predicting tumor response to chemotherapy

  4. Computer-aided breast MR image feature analysis for prediction of tumor response to chemotherapy

    Energy Technology Data Exchange (ETDEWEB)

    Aghaei, Faranak; Tan, Maxine; Liu, Hong; Zheng, Bin, E-mail: Bin.Zheng-1@ou.edu [School of Electrical and Computer Engineering, University of Oklahoma, Norman, Oklahoma 73019 (United States); Hollingsworth, Alan B. [Mercy Women’s Center, Mercy Health Center, Oklahoma City, Oklahoma 73120 (United States); Qian, Wei [Department of Electrical and Computer Engineering, University of Texas, El Paso, Texas 79968 (United States)

    2015-11-15

    Purpose: To identify a new clinical marker based on quantitative kinetic image features analysis and assess its feasibility to predict tumor response to neoadjuvant chemotherapy. Methods: The authors assembled a dataset involving breast MR images acquired from 68 cancer patients before undergoing neoadjuvant chemotherapy. Among them, 25 patients had complete response (CR) and 43 had partial and nonresponse (NR) to chemotherapy based on the response evaluation criteria in solid tumors. The authors developed a computer-aided detection scheme to segment breast areas and tumors depicted on the breast MR images and computed a total of 39 kinetic image features from both tumor and background parenchymal enhancement regions. The authors then applied and tested two approaches to classify between CR and NR cases. The first one analyzed each individual feature and applied a simple feature fusion method that combines classification results from multiple features. The second approach tested an attribute selected classifier that integrates an artificial neural network (ANN) with a wrapper subset evaluator, which was optimized using a leave-one-case-out validation method. Results: In the pool of 39 features, 10 yielded relatively higher classification performance with the areas under receiver operating characteristic curves (AUCs) ranging from 0.61 to 0.78 to classify between CR and NR cases. Using a feature fusion method, the maximum AUC = 0.85 ± 0.05. Using the ANN-based classifier, AUC value significantly increased to 0.96 ± 0.03 (p < 0.01). Conclusions: This study demonstrated that quantitative analysis of kinetic image features computed from breast MR images acquired prechemotherapy has potential to generate a useful clinical marker in predicting tumor response to chemotherapy.

  5. Feature-based registration of historical aerial images by Area Minimization

    Science.gov (United States)

    Nagarajan, Sudhagar; Schenk, Toni

    2016-06-01

    The registration of historical images plays a significant role in assessing changes in land topography over time. By comparing historical aerial images with recent data, geometric changes that have taken place over the years can be quantified. However, the lack of ground control information and precise camera parameters has limited scientists' ability to reliably incorporate historical images into change detection studies. Other limitations include the methods of determining identical points between recent and historical images, which has proven to be a cumbersome task due to continuous land cover changes. Our research demonstrates a method of registering historical images using Time Invariant Line (TIL) features. TIL features are different representations of the same line features in multi-temporal data without explicit point-to-point or straight line-to-straight line correspondence. We successfully determined the exterior orientation of historical images by minimizing the area formed between corresponding TIL features in recent and historical images. We then tested the feasibility of the approach with synthetic and real data and analyzed the results. Based on our analysis, this method shows promise for long-term 3D change detection studies.

  6. Flatbed scanners as a source of imaging. Brightness assessment and additives determination in a nickel electroplating bath.

    Science.gov (United States)

    Vidal, M; Amigo, J M; Bro, R; Ostra, M; Ubide, C; Zuriarrain, J

    2011-05-23

    Desktop flatbed scanners are very well-known devices that can provide digitized information of flat surfaces. They are practically present in most laboratories as a part of the computer support. Several quality levels can be found in the market, but all of them can be considered as tools with a high performance and low cost. The present paper shows how the information obtained with a scanner, from a flat surface, can be used with fine results for exploratory and quantitative purposes through image analysis. It provides cheap analytical measurements for assessment of quality parameters of coated metallic surfaces and monitoring of electrochemical coating bath lives. The samples used were steel sheets nickel-plated in an electrodeposition bath. The quality of the final deposit depends on the bath conditions and, especially, on the concentration of the additives in the bath. Some additives become degraded with the bath life and so is the quality of the plate finish. Analysis of the scanner images can be used to follow the evolution of the metal deposit and the concentration of additives in the bath. Principal component analysis (PCA) is applied to find significant differences in the coating of sheets, to find directions of maximum variability and to identify odd samples. The results found are favorably compared with those obtained by means of specular reflectance (SR), which is here used as a reference technique. Also the concentration of additives SPB and SA-1 along a nickel bath life can be followed using image data handled with algorithms such as partial least squares (PLS) regression and support vector regression (SVR). The quantitative results obtained with these and other algorithms are compared. All this opens new qualitative and quantitative possibilities to flatbed scanners.

  7. Joint Applied Optics and Chinese Optics Letters Feature Introduction: Digital Holography and 3D Imaging

    Institute of Scientific and Technical Information of China (English)

    Ting-Chung Poon; Changhe Zhou; Toyohiko Yatagai; Byoungho Lee; Hongchen Zhai

    2011-01-01

    This feature issue is the fifth installment on digital holography since its inception four years ago.The last four issues have been published after the conclusion of each Topical Meeting "Digital Holography and 3D imaging (DH)." However,this feature issue includes a new key feature-Joint Applied Optics and Chinese Optics Letters Feature Issue.The DH Topical Meeting is the world's premier forum for disseminating the science and technology geared towards digital holography and 3D information processing.Since the meeting's inception in 2007,it has steadily and healthily grown to 130 presentations this year,held in Tokyo,Japan,May 2011.

  8. Low Surface Brightness Imaging of the Magellanic System: Imprints of Tidal Interactions between the Clouds in the Stellar Periphery

    Science.gov (United States)

    Besla, Gurtina; Martínez-Delgado, David; van der Marel, Roeland P.; Beletsky, Yuri; Seibert, Mark; Schlafly, Edward F.; Grebel, Eva K.; Neyer, Fabian

    2016-07-01

    We present deep optical images of the Large and Small Magellanic Clouds (LMC and SMC) using a low cost telephoto lens with a wide field of view to explore stellar substructure in the outskirts of the stellar disk of the LMC (history with and impact parameter of the SMC. More generally, we find that such asymmetric structures should be ubiquitous about pairs of dwarfs and can persist for 1-2 Gyr even after the secondary merges entirely with the primary. As such, the lack of a companion around a Magellanic Irregular does not disprove the hypothesis that their asymmetric structures are driven by dwarf-dwarf interactions.

  9. Learning representative features for facial images based on a modified principal component analysis

    Science.gov (United States)

    Averkin, Anton; Potapov, Alexey

    2013-05-01

    The paper is devoted to facial image analysis and particularly deals with the problem of automatic evaluation of the attractiveness of human faces. We propose a new approach for automatic construction of feature space based on a modified principal component analysis. Input data sets for the algorithm are the learning data sets of facial images, which are rated by one person. The proposed approach allows one to extract features of the individual subjective face beauty perception and to predict attractiveness values for new facial images, which were not included into a learning data set. The Pearson correlation coefficient between values predicted by our method for new facial images and personal attractiveness estimation values equals to 0.89. This means that the new approach proposed is promising and can be used for predicting subjective face attractiveness values in real systems of the facial images analysis.

  10. Rough-fuzzy clustering and unsupervised feature selection for wavelet based MR image segmentation.

    Directory of Open Access Journals (Sweden)

    Pradipta Maji

    Full Text Available Image segmentation is an indispensable process in the visualization of human tissues, particularly during clinical analysis of brain magnetic resonance (MR images. For many human experts, manual segmentation is a difficult and time consuming task, which makes an automated brain MR image segmentation method desirable. In this regard, this paper presents a new segmentation method for brain MR images, integrating judiciously the merits of rough-fuzzy computing and multiresolution image analysis technique. The proposed method assumes that the major brain tissues, namely, gray matter, white matter, and cerebrospinal fluid from the MR images are considered to have different textural properties. The dyadic wavelet analysis is used to extract the scale-space feature vector for each pixel, while the rough-fuzzy clustering is used to address the uncertainty problem of brain MR image segmentation. An unsupervised feature selection method is introduced, based on maximum relevance-maximum significance criterion, to select relevant and significant textural features for segmentation problem, while the mathematical morphology based skull stripping preprocessing step is proposed to remove the non-cerebral tissues like skull. The performance of the proposed method, along with a comparison with related approaches, is demonstrated on a set of synthetic and real brain MR images using standard validity indices.

  11. Multi-parametric imaging of tumor spheroids with ultra-bright and tunable nanoparticle O2 probes

    Science.gov (United States)

    Dmitriev, Ruslan I.; Borisov, Sergey M.; Jenkins, James; Papkovsky, Dmitri B.

    2015-03-01

    Multi-modal probes allow for flexible choice of imaging equipment when performing quenched-phosphorescence O2 measurements: one- or two-photon, PLIM or intensity-based ratiometric read-outs. Spectral and temporal (e.g. FLIMPLIM) discrimination can be used to image O2 together with pH, Ca2+, mitochondrial membrane potential, cell death markers or cell/organelle specific markers. However, the main challenge of existing nanoparticle probes is their limited diffusion across thick (> 20-50 μm) 3D cell models such as tumor spheroids. Here, we present new class of polymeric nanoparticle probes having tunable size, charge, cell-penetrating ability, and reporter dyes. Being spectrally similar to the recently described MM2, PA2 and other O2 probes, they are 5-10 times brighter, demonstrate improved ratiometric response and their surface chemistry can be easily modified. With cultures of 2D and 3D cell models (fibroblasts, PC12 aggregates, HCT116 human colon cancer spheroids) we found cell-specific staining by these probes. However, the efficient staining of model of interest can be tuned by changing number of positive and negative surface groups at nanoparticle, to allow most efficient loading. We also demonstrate how real-time monitoring of oxygenation can be used to select optimal spheroid production with low variability in size and high cell viability.

  12. Rosai-Dorfman Disease with Epidural and Spinal Bone Marrow Involvement: Magnetic Resonance Imaging and Diffusion-Weighted Imaging Features

    Energy Technology Data Exchange (ETDEWEB)

    Oner, A.Y.; Akpek, S.; Tali, T. [Dept. of Radiology, Gazi Univ. School of Medicine. Besevler-Ankara (Turkey)

    2007-04-15

    Sinus histiocytosis with massive lymphadenopathy (SHML), or Rosai-Dorfman disease, is a rare histiocytic disorder that typically presents with chronic, self-limiting cervical lymphadenopathy. Although this disease mainly affects histiocytes, there are a few reports of bone marrow infiltration. Diffusion-weighted imaging (DWI) is a promising technology in differentiating between various bone marrow pathologies. We here present conventional magnetic resonance imaging and DWI features of a patient with SHML and bone marrow involvement.

  13. [Determination of Soluble Solid Content in Strawberry Using Hyperspectral Imaging Combined with Feature Extraction Methods].

    Science.gov (United States)

    Ding, Xi-bin; Zhang, Chu; Liu, Fei; Song, Xing-lin; Kong, Wen-wen; He, Yong

    2015-04-01

    Hyperspectral imaging combined with feature extraction methods were applied to determine soluble sugar content (SSC) in mature and scatheless strawberry. Hyperspectral images of 154 strawberries covering the spectral range of 874-1,734 nm were captured and the spectral data were extracted from the hyperspectral images, and the spectra of 941~1,612 nm were preprocessed by moving average (MA). Nineteen samples were defined as outliers by the residual method, and the remaining 135 samples were divided into the calibration set (n = 90) and the prediction set (n = 45). Successive projections algorithm (SPA), genetic algorithm partial least squares (GAPLS) combined with SPA, weighted regression coefficient (Bw) and competitive adaptive reweighted sampling (CARS) were applied to select 14, 17, 24 and 25 effective wavelengths, respectively. Principal component analysis (PCA) and wavelet transform (WT) were applied to extract feature information with 20 and 58 features, respectively. PLS models were built based on the full spectra, the effective wavelengths and the features, respectively. All PLS models obtained good results. PLS models using full-spectra and features extracted by WT obtained the best results with correlation coefficient of calibration (r(c)) and correlation coefficient of prediction (r(p)) over 0.9. The overall results indicated that hyperspectral imaging combined with feature extraction methods could be used for detection of SSC in strawberry. PMID:26197594

  14. Passive Forensics for Region Duplication Image Forgery Based on Harris Feature Points and Local Binary Patterns

    Directory of Open Access Journals (Sweden)

    Jie Zhao

    2013-01-01

    Full Text Available Nowadays the demand for identifying the authenticity of an image is much increased since advanced image editing software packages are widely used. Region duplication forgery is one of the most common and immediate tampering attacks which are frequently used. Several methods to expose this forgery have been developed to detect and locate the tampered region, while most methods do fail when the duplicated region undergoes rotation or flipping before being pasted. In this paper, an efficient method based on Harris feature points and local binary patterns is proposed. First, the image is filtered with a pixelwise adaptive Wiener method, and then dense Harris feature points are employed in order to obtain a sufficient number of feature points with approximately uniform distribution. Feature vectors for a circle patch around each feature point are extracted using local binary pattern operators, and the similar Harris points are matched based on their representation feature vectors using the BBF algorithm. Finally, RANSAC algorithm is employed to eliminate the possible erroneous matches. Experiment results demonstrate that the proposed method can effectively detect region duplication forgery, even when an image was distorted by rotation, flipping, blurring, AWGN, JPEG compression, and their mixed operations, especially resistant to the forgery with the flat area of little visual structures.

  15. Bright Spots on Ceres and Implications for Subsurface Composition and Structure

    Science.gov (United States)

    Stein, Nathaniel; Ehlmann, Bethany; Ammannito, Eleonora; Palomba, Ernesto; De Sanctis, Maria Cristina; Jaumann, Ralf; Nathues, Andreas; Raymond, Carol; Hiesinger, Harald; Schenk, Paul M.; Longobardo, Andrea; Dawn Team

    2016-10-01

    Images from the Dawn spacecraft show anomalously bright spots dotting Ceres' surface. Here we perform global mapping with FC data and find the spots can be classified into three geologic settings: 1) large crater floors, 2) rims/walls of craters of all sizes, or 3) the unique surface feature Ahuna Mons. There are at least 300 bright spots in total, over 200 of which are located on crater rims and walls. We examine controls on (1) and (2) as a function of crater diameter (D) and depth (d).Floor bright spots occur only in D>15 km craters, and bright spots associated with the central pit and peak complex are restricted to D>30 km. 7 of 9 craters with d>4 km (D: 70-165 km) host floor bright spots, though 30 craters with D>75 km do not contain floor bright spots, thus indicating that diameter is a weaker control on bright spot occurrence than depth. Craters with bright spots have a high d/D for their size bin, and rim/wall bright spots in craters of all sizes occur preferentially in and around the largest craters. The chief control on crater depth is presumed to be age, with shallowing due to relaxation. Thus, data suggest that previously emplaced bright materials may be removed or obscured over time via relaxation-driven burial, impact-driven lateral mixing, sublimation, or space weathering. Analyses from Dawn's VIR instrument show that some large floor bright spots are comprised of materials enriched in carbonates and other salts [e.g., 1]. The presence of bright material in many deep craters is consistent with their formation via impact-induced subsurface processes, though formation via endogenous, heterogeneously distributed subsurface processes cannot be excluded [1, 2].Here we use the Ceres production function [3] to construct a simple model in which only large (D>75 km) craters form central bright spots. These materials are then modified by later impacts. Initial results indicate that the excavation of previously emplaced bright material could explain the current

  16. AUTOMATIC SHIP DETECTION IN SINGLE-POL SAR IMAGES USING TEXTURE FEATURES IN ARTIFICIAL NEURAL NETWORKS

    Directory of Open Access Journals (Sweden)

    E. Khesali

    2015-12-01

    Full Text Available This paper presents a novel method for detecting ships from high-resolution synthetic aperture radar (SAR images. This method categorizes ship targets from single-pol SAR images using texture features in artificial neural networks. As such, the method tries to overcome the lack of an operational solution that is able to reliably detect ships with one SAR channel. The method has the following three main stages: 1 feature extraction; 2 feature selection; and 3 ship detection. The first part extracts different texture features from SAR image. These textures include occurrence and co occurrence measures with different window sizes. Then, best features are selected. Finally, the artificial neural network is used to extract ship pixels from sea ones. In post processing stage some morphological filters are used to improve the result. The effectiveness of the proposed method is verified using Sentinel-1 data in VV polarization. Experimental results indicate that the proposed algorithm can be implemented with time-saving, high precision ship extraction, feature analysis, and detection. The results also show that using texture features the algorithm properly discriminates speckle noise from ships.

  17. Face Recognition for Access Control Systems Combining Image-Difference Features Based on a Probabilistic Model

    Science.gov (United States)

    Miwa, Shotaro; Kage, Hiroshi; Hirai, Takashi; Sumi, Kazuhiko

    We propose a probabilistic face recognition algorithm for Access Control System(ACS)s. Comparing with existing ACSs using low cost IC-cards, face recognition has advantages in usability and security that it doesn't require people to hold cards over scanners and doesn't accept imposters with authorized cards. Therefore face recognition attracts more interests in security markets than IC-cards. But in security markets where low cost ACSs exist, price competition is important, and there is a limitation on the quality of available cameras and image control. Therefore ACSs using face recognition are required to handle much lower quality images, such as defocused and poor gain-controlled images than high security systems, such as immigration control. To tackle with such image quality problems we developed a face recognition algorithm based on a probabilistic model which combines a variety of image-difference features trained by Real AdaBoost with their prior probability distributions. It enables to evaluate and utilize only reliable features among trained ones during each authentication, and achieve high recognition performance rates. The field evaluation using a pseudo Access Control System installed in our office shows that the proposed system achieves a constant high recognition performance rate independent on face image qualities, that is about four times lower EER (Equal Error Rate) under a variety of image conditions than one without any prior probability distributions. On the other hand using image difference features without any prior probabilities are sensitive to image qualities. We also evaluated PCA, and it has worse, but constant performance rates because of its general optimization on overall data. Comparing with PCA, Real AdaBoost without any prior distribution performs twice better under good image conditions, but degrades to a performance as good as PCA under poor image conditions.

  18. AN INTEGRATED FRAMEWORK BASED ON TEXTURE FEATURES, CUCKOO SEARCH AND RELEVANCE VECTOR MACHINE FOR MEDICAL IMAGE RETRIEVAL SYSTEM

    OpenAIRE

    Yogapriya Jaganathan; Ila Vennila

    2013-01-01

    As medical images are widely used in healthcare applications, Content Based Medical Image Retrieval (CBMIR) system is needed for physicians to convey effective decisions to patients and for medical research students to learn imaging characteristics for their extensive research based on visual features. However the performance of the retrieval is restricted due to high feature dimensionality of visual features. To reduce the high feature dimension, an integrated approach is proposed such as Vi...

  19. A partial intensity invariant feature descriptor for multimodal retinal image registration.

    Science.gov (United States)

    Chen, Jian; Tian, Jie; Lee, Noah; Zheng, Jian; Smith, R Theodore; Laine, Andrew F

    2010-07-01

    Detection of vascular bifurcations is a challenging task in multimodal retinal image registration. Existing algorithms based on bifurcations usually fail in correctly aligning poor quality retinal image pairs. To solve this problem, we propose a novel highly distinctive local feature descriptor named partial intensity invariant feature descriptor (PIIFD) and describe a robust automatic retinal image registration framework named Harris-PIIFD. PIIFD is invariant to image rotation, partially invariant to image intensity, affine transformation, and viewpoint/perspective change. Our Harris-PIIFD framework consists of four steps. First, corner points are used as control point candidates instead of bifurcations since corner points are sufficient and uniformly distributed across the image domain. Second, PIIFDs are extracted for all corner points, and a bilateral matching technique is applied to identify corresponding PIIFDs matches between image pairs. Third, incorrect matches are removed and inaccurate matches are refined. Finally, an adaptive transformation is used to register the image pairs. PIIFD is so distinctive that it can be correctly identified even in nonvascular areas. When tested on 168 pairs of multimodal retinal images, the Harris-PIIFD far outperforms existing algorithms in terms of robustness, accuracy, and computational efficiency.

  20. DEVELOPING AN IMAGE PROCESSING APPLICATION THAT SUPPORTS NEW FEATURES OF JPEG2000 STANDARD

    Directory of Open Access Journals (Sweden)

    Evgin GÖÇERİ

    2007-03-01

    Full Text Available In recent years, developing technologies in multimedia brought the importance of image processing and compression. Images that are reduced in size using lossless and lossy compression techniques without degrading the quality of the image to an unacceptable level take up much less space in memory. This enables them to be sent and received over the Internet or mobile devices in much shorter time. The wavelet-based image compression standard JPEG2000 has been created by the Joint Photographic Experts Group (JPEG committee to superseding the former JPEG standard. Works on various additions to this standard are still under development. In this study, an Application has been developed in Visual C# 2005 which implies important image processing techniques such as edge detection and noise reduction. The important feature of this Application is to support JPEG2000 standard as well as supporting other image types, and the implementation does not only apply to two-dimensional images, but also to multi-dimensional images. Modern software development platforms that support image processing have also been compared and several features of the developed software have been identified.

  1. Flotation bubble seed image filling algorithm based on boundary point features

    Institute of Scientific and Technical Information of China (English)

    Zhu Hong; Zhang Guoying; Liu Guanzhou; Sun Qi

    2012-01-01

    Bubble seed image filling is an important prerequisite for the image segmentation of flotation bubble that can be used to improve flotation automatic control.These common image filling algorithms in dealing with complex bubble image exists under-filling and over-filling problems.A new filling algorithm based on boundary point feature and scan lines (PFSL) is proposed in the paper.The filling algorithm describes these boundary points of image objects by means of chain codes.The features of each boundary point,including convex points,concave points,left points and right points,are defined by the point's entrancing chain code and leaving chain code.The algorithm firstly finds out all double-matched boundary points based on the features of boundary points,and fill image objects by these double matched boundary points on scan lines.Experimental results of bubble seed image filling show that under-filling and over-filling problem can be eliminated by the proposed algorithm.

  2. SU-E-J-261: The Importance of Appropriate Image Preprocessing to Augment the Information of Radiomics Image Features

    International Nuclear Information System (INIS)

    Purpose: To investigate how different image preprocessing techniques, their parameters, and the different boundary handling techniques can augment the information of features and improve feature’s differentiating capability. Methods: Twenty-seven NSCLC patients with a solid tumor volume and no visually obvious necrotic regions in the simulation CT images were identified. Fourteen of these patients had a necrotic region visible in their pre-treatment PET images (necrosis group), and thirteen had no visible necrotic region in the pre-treatment PET images (non-necrosis group). We investigated how image preprocessing can impact the ability of radiomics image features extracted from the CT to differentiate between two groups. It is expected the histogram in the necrosis group is more negatively skewed, and the uniformity from the necrosis group is less. Therefore, we analyzed two first order features, skewness and uniformity, on the image inside the GTV in the intensity range [−20HU, 180HU] under the combination of several image preprocessing techniques: (1) applying the isotropic Gaussian or anisotropic diffusion smoothing filter with a range of parameter(Gaussian smoothing: size=11, sigma=0:0.1:2.3; anisotropic smoothing: iteration=4, kappa=0:10:110); (2) applying the boundaryadapted Laplacian filter; and (3) applying the adaptive upper threshold for the intensity range. A 2-tailed T-test was used to evaluate the differentiating capability of CT features on pre-treatment PT necrosis. Result: Without any preprocessing, no differences in either skewness or uniformity were observed between two groups. After applying appropriate Gaussian filters (sigma>=1.3) or anisotropic filters(kappa >=60) with the adaptive upper threshold, skewness was significantly more negative in the necrosis group(p<0.05). By applying the boundary-adapted Laplacian filtering after the appropriate Gaussian filters (0.5 <=sigma<=1.1) or anisotropic filters(20<=kappa <=50), the uniformity was

  3. Comparative Analysis of Feature Extraction Methods for the Classification of Prostate Cancer from TRUS Medical Images

    Directory of Open Access Journals (Sweden)

    Manavalan Radhakrishnan

    2012-01-01

    Full Text Available Diagnosing Prostate cancer is a challenging task for Urologists, Radiologists, and Oncologists. Ultrasound imaging is one of the hopeful techniques used for early detection of prostate cancer. The Region of interest (ROI is identified by different methods after preprocessing. In this paper, DBSCAN clustering with morphological operators is used to extort the prostate region. The evaluation of texture features is important for several image processing applications. The performance of the features extracted from the various texture methods such as histogram, Gray Level Cooccurrence Matrix (GLCM, Gray-Level Run-Length Matrix (GRLM, are analyzed separately. In this paper, it is proposed to combine histogram, GLRLM and GLCM in order to study the performance. The Support Vector Machine (SVM is adopted to classify the extracted features into benign or malignant. The performance of texture methods are evaluated using various statistical parameters such as sensitivity, specificity and accuracy. The comparative analysis has been performed over 5500 digitized TRUS images of prostate.

  4. Low Surface Brightness Imaging of the Magellanic System: Imprints of Tidal Interactions between the Clouds in the Stellar Periphery

    CERN Document Server

    Besla, Gurtina; van der Marel, Roeland P; Beletsky, Yuri; Seibert, Mark; Schlafly, Edward F; Grebel, Eva K; Neyer, Fabian

    2016-01-01

    We present deep optical images of the Large and Small Magellanic Clouds (LMC and SMC) using a low cost telephoto lens with a wide field of view to explore stellar substructure in the outskirts of the stellar disk of the LMC (r < 10 degrees from the center). These data have higher resolution than existing star count maps, and highlight the existence of stellar arcs and multiple spiral arms in the northern periphery, with no comparable counterparts in the South. We compare these data to detailed simulations of the LMC disk outskirts, following interactions with its low mass companion, the SMC. We consider interaction in isolation and with the inclusion of the Milky Way tidal field. The simulations are used to assess the origin of the northern structures, including also the low density stellar arc recently identified in the DES data by Mackey et al. 2015 at ~ 15 degrees. We conclude that repeated close interactions with the SMC are primarily responsible for the asymmetric stellar structures seen in the periph...

  5. Image Retrieval and Classification Method Based on Euclidian Distance Between Normalized Features Including Wavelet Descriptor

    Directory of Open Access Journals (Sweden)

    Kohei Arai

    2013-10-01

    Full Text Available Image retrieval method based on Euclidian distance between normalized features with their mean and variance in feature space is proposed. Effectiveness of the normalization is evaluated together with a validation of the proposed image retrieval method. The proposed method is applied for discrimination and identifying dangerous red tide species based on wavelet utilized classification methods together with texture and color features. Through experiments, it is found that classification performance with the proposed wavelet derived shape information extracted from the microscopic view of the phytoplankton is effective for identifying dangerous red tide species among the other red tide species rather than the other conventional texture, color information. Moreover, it is also found that the proposed normalization of features is effective to improve identification performance.

  6. Selection of the best features for leukocytes classification in blood smear microscopic images

    Science.gov (United States)

    Sarrafzadeh, Omid; Rabbani, Hossein; Talebi, Ardeshir; Banaem, Hossein Usefi

    2014-03-01

    Automatic differential counting of leukocytes provides invaluable information to pathologist for diagnosis and treatment of many diseases. The main objective of this paper is to detect leukocytes from a blood smear microscopic image and classify them into their types: Neutrophil, Eosinophil, Basophil, Lymphocyte and Monocyte using features that pathologists consider to differentiate leukocytes. Features contain color, geometric and texture features. Colors of nucleus and cytoplasm vary among the leukocytes. Lymphocytes have single, large, round or oval and Monocytes have singular convoluted shape nucleus. Nucleus of Eosinophils is divided into 2 segments and nucleus of Neutrophils into 2 to 5 segments. Lymphocytes often have no granules, Monocytes have tiny granules, Neutrophils have fine granules and Eosinophils have large granules in cytoplasm. Six color features is extracted from both nucleus and cytoplasm, 6 geometric features only from nucleus and 6 statistical features and 7 moment invariants features only from cytoplasm of leukocytes. These features are fed to support vector machine (SVM) classifiers with one to one architecture. The results obtained by applying the proposed method on blood smear microscopic image of 10 patients including 149 white blood cells (WBCs) indicate that correct rate for all classifiers are above 93% which is in a higher level in comparison with previous literatures.

  7. 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.

  8. Texture based feature extraction methods for content based medical image retrieval systems.

    Science.gov (United States)

    Ergen, Burhan; Baykara, Muhammet

    2014-01-01

    The developments of content based image retrieval (CBIR) systems used for image archiving are continued and one of the important research topics. Although some studies have been presented general image achieving, proposed CBIR systems for archiving of medical images are not very efficient. In presented study, it is examined the retrieval efficiency rate of spatial methods used for feature extraction for medical image retrieval systems. The investigated algorithms in this study depend on gray level co-occurrence matrix (GLCM), gray level run length matrix (GLRLM), and Gabor wavelet accepted as spatial methods. In the experiments, the database is built including hundreds of medical images such as brain, lung, sinus, and bone. The results obtained in this study shows that queries based on statistics obtained from GLCM are satisfied. However, it is observed that Gabor Wavelet has been the most effective and accurate method. PMID:25227014

  9. Chordoid glioma with intraventricular dissemination: A case report with perfusion MR imaging features

    Energy Technology Data Exchange (ETDEWEB)

    Ki, So Yeon; Kim, Seul Kee; Heo, Tae Wook; Baek, Byung Hyun; Kim, Hyung Seok; Yoon, Woong [Chonnam National University Medical School, Chonnam National University Hospital, Gwangju (Korea, Republic of)

    2016-02-15

    Chordoid glioma is a rare low grade tumor typically located in the third ventricle. Although a chordoid glioma can arise from ventricle with tumor cells having features of ependymal differentiation, intraventricular dissemination has not been reported. Here we report a case of a patient with third ventricular chordoid glioma and intraventricular dissemination in the lateral and fourth ventricles. We described the perfusion MR imaging features of our case different from a previous report.

  10. An Improved Management Model for Tracking Missing Features in Computer Vision Long Image Sequences

    OpenAIRE

    Pinho, Raquel R.; João Manuel R. S. Tavares; Correia, Miguel V.

    2006-01-01

    In this paper we present a management model to deal with the problem of tracking missing features during long image sequences using Computational Vision. Some usual difficulties related with missing features are that they may be temporarily occluded or might even have disappeared definitively, and the computational cost involved should always be reduced to the strictly necessary. The proposed Net Present Value (NPV) model, based on the economic Theory of Capital, considers the tracking of eac...

  11. A Global Image Feature Construction Metho d Based on Local Jet Structure

    Institute of Scientific and Technical Information of China (English)

    XIE Jin; CAI Zi-Xing

    2014-01-01

    This article presents a novel and robust feature descriptor called the multi-scale autoconvolution on local jet structure (MSALJS), which is quasi-invariant to affine transformation. The MSALJS, a global image feature descriptor, is based on the deriva-tives that describe the image local structure to compute the multi-scale autoconvolution moment. Experimental data demonstrate that the MSALJS can be used in practical applications in which the object is deformed in various ways, such as particular occlusion, view angle change, and so on.

  12. Automatic Target Recognition in Synthetic Aperture Sonar Images Based on Geometrical Feature Extraction

    Directory of Open Access Journals (Sweden)

    J. Del Rio Vera

    2009-01-01

    Full Text Available This paper presents a new supervised classification approach for automated target recognition (ATR in SAS images. The recognition procedure starts with a novel segmentation stage based on the Hilbert transform. A number of geometrical features are then extracted and used to classify observed objects against a previously compiled database of target and non-target features. The proposed approach has been tested on a set of 1528 simulated images created by the NURC SIGMAS sonar model, achieving up to 95% classification accuracy.

  13. Concealing the Level-3 features of Fingerprint in a Facial Image

    Directory of Open Access Journals (Sweden)

    Dr.R.Seshadri,

    2010-11-01

    Full Text Available individual based on their physical, chemical and behavioral characteristics of the person. Biometrics is increasingly being used for authentication and protection purposes and this has generated considerable interest from many parts of the information technology people. In this paper we proposed facial image Watermarking methods that can embedded fingerprint level-3 features information into host facial images. This scheme has the advantage that in addition to facial matching, the recovered fingerprint level-3 features during the decoding can be used to establish the authentication. Here the proposed system concealing of vital information human being for identification and at the same time the system protect themselves fromattackers.

  14. Soft sensor design by multivariate fusion of image features and process measurements

    DEFF Research Database (Denmark)

    Lin, Bao; Jørgensen, Sten Bay

    2011-01-01

    is obtained by filtering the original data block augmented with time lagged variables such that improved predictive performance of the quality variable results. Key issues regarding data preprocessing and extraction of suitable image features are discussed with a case study, the on-line estimation of nitrogen......This paper presents a multivariate data fusion procedure for design of dynamic soft sensors where suitably selected image features are combined with traditional process measurements to enhance the performance of data-driven soft sensors. A key issue of fusing multiple sensor data, i.e. to determine...

  15. Quality Control in Automated Manufacturing Processes – Combined Features for Image Processing

    Directory of Open Access Journals (Sweden)

    B. Kuhlenkötter

    2006-01-01

    Full Text Available In production processes the use of image processing systems is widespread. Hardware solutions and cameras respectively are available for nearly every application. One important challenge of image processing systems is the development and selection of appropriate algorithms and software solutions in order to realise ambitious quality control for production processes. This article characterises the development of innovative software by combining features for an automatic defect classification on product surfaces. The artificial intelligent method Support Vector Machine (SVM is used to execute the classification task according to the combined features. This software is one crucial element for the automation of a manually operated production process. 

  16. Imaging Features of AlloDerm® Used in Postmastectomy Breast Reconstructions

    Directory of Open Access Journals (Sweden)

    Christine U Lee

    2014-01-01

    Full Text Available The purpose of this pictorial essay is to demonstrate the imaging features (ultrasound, mammogram, and magnetic resonance imaging (MRI of AlloDerm® (LifeCell Corp.; Branchburg, NJ, an acellular dermal matrix sometimes used in both primary and reconstructive breast surgeries. AlloDerm® is derived from cadaveric dermis and provides an immunologically inert scaffold in tissue reconstruction. Since there is little literature on the imaging of this substance, radiologists may be unfamiliar with its appearance in breast imaging. For this manuscript, ex vivo and in vivo images of AlloDerm® in postmastectomy patients were evaluated using different imaging modalities. The appearance of AlloDerm® can vary based on length of time postsurgery and incorporation into the host. AlloDerm® appears as an isodense to glandular tissue on a mammogram and isoechoic to glandular tissue on ultrasound imaging. On MRI, in comparison with normal breast parenchyma, AlloDerm® is hyperintense on T2-weighted imaging and isointense on T1-weighted imaging and demonstrates mild enhancement. To the best of the authors′ knowledge, this is the first multimodality imaging description of AlloDerm® used in postmastectomy patients. The conformation of AlloDerm® at surgical placement and the degree of host cell migration and neoangiogenesis are factors to take into consideration when performing diagnostic evaluations; and, familiarity with the various imaging appearances of AlloDerm® can be helpful to exclude residual or recurrent disease.

  17. GRADIENT OF REFERENCE DIFFERENCE BASED MATCHING ALGORITHM FOR IMAGE FEATURE POINT

    Institute of Scientific and Technical Information of China (English)

    Guan Yepeng; Gu Weikang; Ye Xiuqing; Liu Jilin

    2004-01-01

    During matching on feature point, gray correlation matching technology is utilized to extract multi-peaks as a coarse matching set. A pair of given corresponding reference points within the left and right images is used to calculate gradients of reference difference between the reference points and each feature point within the multi-peaks set. The unique correspondence is determined by criterion of minimal gradients of reference difference. The obtained correspondence is taken as a new pair of reference points to update the reference points continuously until all feature points in the left (or right) image being matched with the right (or left) image. The gradients of reference difference can be calculated easily by means of pre-setting a pair of obvious feature points in the left and right images as a pair of corresponding reference points. Besides, the efficiency of matching can be improved greatly by taking the obtained matching point as a new pair of reference points, and by updating the reference point continuously. It is proved that the proposed algorithm is valid and reliable by 3D reconstruction on two pairs of actual natural images with abundant and weak texture, respectively.

  18. Feature selection and classification of multiparametric medical images using bagging and SVM

    Science.gov (United States)

    Fan, Yong; Resnick, Susan M.; Davatzikos, Christos

    2008-03-01

    This paper presents a framework for brain classification based on multi-parametric medical images. This method takes advantage of multi-parametric imaging to provide a set of discriminative features for classifier construction by using a regional feature extraction method which takes into account joint correlations among different image parameters; in the experiments herein, MRI and PET images of the brain are used. Support vector machine classifiers are then trained based on the most discriminative features selected from the feature set. To facilitate robust classification and optimal selection of parameters involved in classification, in view of the well-known "curse of dimensionality", base classifiers are constructed in a bagging (bootstrap aggregating) framework for building an ensemble classifier and the classification parameters of these base classifiers are optimized by means of maximizing the area under the ROC (receiver operating characteristic) curve estimated from their prediction performance on left-out samples of bootstrap sampling. This classification system is tested on a sex classification problem, where it yields over 90% classification rates for unseen subjects. The proposed classification method is also compared with other commonly used classification algorithms, with favorable results. These results illustrate that the methods built upon information jointly extracted from multi-parametric images have the potential to perform individual classification with high sensitivity and specificity.

  19. NEURO FUZZY MODEL FOR FACE RECOGNITION WITH CURVELET BASED FEATURE IMAGE

    OpenAIRE

    SHREEJA R,; KHUSHALI DEULKAR,; SHALINI BHATIA

    2011-01-01

    A facial recognition system is a computer application for automatically identifying or verifying a person from a digital image or a video frame from a video source. One of the ways to do this is by comparing selected facial features from the image and a facial database. It is typically used in security systems and can be compared to other biometric techniques such as fingerprint or iris recognition systems. Every face has approximately 80 nodal points like (Distance between the eyes, Width of...

  20. A new approach to modeling the influence of image features on fixation selection in scenes

    OpenAIRE

    Nuthmann, Antje; Einhäuser, Wolfgang

    2015-01-01

    Which image characteristics predict where people fixate when memorizing natural images? To answer this question, we introduce a new analysis approach that combines a novel scene-patch analysis with generalized linear mixed models (GLMM). Our method allows for (1) directly describing the relationship between continuous feature value and fixation probability, and (2) assessing each feature’s unique contribution to fixation selection. To demonstrate this method, we estimated the relative contrib...