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. Study of Three-Dimensional Image Brightness Loss in Stereoscopy

    Directory of Open Access Journals (Sweden)

    Hsing-Cheng Yu

    2015-10-01

    Full Text Available When viewing three-dimensional (3D images, whether in cinemas or on stereoscopic televisions, viewers experience the same problem of image brightness loss. This study aims to investigate image brightness loss in 3D displays, with the primary aim being to quantify the image brightness degradation in the 3D mode. A further aim is to determine the image brightness relationship to the corresponding two-dimensional (2D images in order to adjust the 3D-image brightness values. In addition, the photographic principle is used in this study to measure metering values by capturing 2D and 3D images on television screens. By analyzing these images with statistical product and service solutions (SPSS software, the image brightness values can be estimated using the statistical regression model, which can also indicate the impact of various environmental factors or hardware on the image brightness. In analysis of the experimental results, comparison of the image brightness between 2D and 3D images indicates 60.8% degradation in the 3D image brightness amplitude. The experimental values, from 52.4% to 69.2%, are within the 95% confidence interval

  4. 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.

  5. Kinematics of Magnetic Bright Features in the Solar Photosphere

    Science.gov (United States)

    Jafarzadeh, S.; Solanki, S. K.; Cameron, R. H.; Barthol, P.; Blanco Rodríguez, J.; del Toro Iniesta, J. C.; Gandorfer, A.; Gizon, L.; Hirzberger, J.; Knölker, M.; Martínez Pillet, V.; Orozco Suárez, D.; Riethmüller, T. L.; Schmidt, W.; van Noort, M.

    2017-03-01

    Convective flows are known as the prime means of transporting magnetic fields on the solar surface. Thus, small magnetic structures are good tracers of 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, γ =1.0), travelers with constant speeds over a supergranule (γ =1.9{--}2.0), and decelerating movers in the vicinity of flux emergence and/or within active regions (γ =1.4{--}1.5). The three types of regions host MBFs with mean diffusion coefficients of 130 km2 s‑1, 80–90 km2 s‑1, and 25–70 km2 s‑1, respectively. The MBFs in these three types of regions are found to display a distinct kinematic behavior at a confidence level in excess of 95%.

  6. 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...

  7. 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

  8. Multispectral Image Feature Points

    Directory of Open Access Journals (Sweden)

    Cristhian Aguilera

    2012-09-01

    Full Text Available This paper presents a novel feature point descriptor for the multispectral image case: Far-Infrared and Visible Spectrum images. It allows matching interest points on images of the same scene but acquired in different spectral bands. Initially, points of interest are detected on both images through a SIFT-like based scale space representation. Then, these points are characterized using an Edge Oriented Histogram (EOH descriptor. Finally, points of interest from multispectral images are matched by finding nearest couples using the information from the descriptor. The provided experimental results and comparisons with similar methods show both the validity of the proposed approach as well as the improvements it offers with respect to the current state-of-the-art.

  9. 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.

  10. The Bright Ages Survey. I. Imaging Data

    CERN Document Server

    Colbert, J W; Rich, R M; Frogel, J A; Salim, S; Teplitz, H; Colbert, James W.; Malkan, Matthew A.; Frogel, Jay A.; Salim, Samir; Teplitz, Harry

    2006-01-01

    This is the first paper in a series presenting and analyzing data for a K-selected sample of galaxies collected in order to identify and study galaxies at moderate to high redshift in rest-wavelength optical light. The sample contains 842 objects over 6 separate fields covering 75.6 arcmin^2 down to K=20-20.5. We combine the K-band with UBVRIzJH multi-band imaging, reaching depths of R~26. Two of the fields studied also have deep HST WFPC2 imaging, totaling more than 60 hours in the F300W, F450W, F606W, and F814W filters. Using artificial galaxy modeling and extraction we measure 85% completeness limits down to K=19.5-20, depending on the field examined. The derived K-band number counts are in good agreement with previous studies. We find a density for Extremely Red Objects(EROs; R-K>5) of 1.55+/-0.16 arcmin^{-2} for K<19.7, dominated by the 1714+5015 field (centered on 53w002), with an ERO number density more than 3 times that of the other sample fields. If we exclude the counts for 1714+5015, our density...

  11. 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.

  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. Identifying Image Manipulation Software from Image Features

    Science.gov (United States)

    2015-03-26

    an overview of the DCT based encoding process [5]. When an image is processed by lossless compression, a file’s size is reduced while still...IDENTIFYING IMAGE MANIPULATION SOFTWARE FROM IMAGE FEATURES THESIS Devlin T. Boyter, CPT, USA AFIT-ENG-MS-15-M-051 DEPARTMENT OF THE AIR FORCE AIR...to copyright protection in the United States. AFIT-ENG-MS-15-M-051 IDENTIFYING IMAGE MANIPULATION SOFTWARE FROM IMAGE FEATURES THESIS Presented to

  14. 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.

  15. 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...

  16. 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.

  17. Imaging features of thalassemia

    Energy Technology Data Exchange (ETDEWEB)

    Tunaci, M.; Tunaci, A.; Engin, G.; Oezkorkmaz, B.; Acunas, G.; Acunas, B. [Dept. of Radiology, Istanbul Univ. (Turkey); Dincol, G. [Dept. of Internal Medicine, Istanbul Univ. (Turkey)

    1999-07-01

    Thalassemia is a kind of chronic, inherited, microcytic anemia characterized by defective hemoglobin synthesis and ineffective erythropoiesis. In all thalassemias clinical features that result from anemia, transfusional, and absorptive iron overload are similar but vary in severity. The radiographic features of {beta}-thalassemia are due in large part to marrow hyperplasia. Markedly expanded marrow space lead to various skeletal manifestations including spine, skull, facial bones, and ribs. Extramedullary hematopoiesis (ExmH), hemosiderosis, and cholelithiasis are among the non-skeletal manifestations of thalassemia. The skeletal X-ray findings show characteristics of chronic overactivity of the marrow. In this article both skeletal and non-skeletal manifestations of thalassemia are discussed with an overview of X-ray findings, including MRI and CT findings. (orig.)

  18. Diabetes insipidus in pediatric germinomas of the suprasellar region: characteristic features and significance of the pituitary bright spot.

    Science.gov (United States)

    Kilday, John-Paul; Laughlin, Suzanne; Urbach, Stacey; Bouffet, Eric; Bartels, Ute

    2015-01-01

    The pituitary bright spot is acknowledged to indicate functional integrity of the posterior pituitary gland, whilst its absence supports a diagnosis of central diabetes insipidus (DI). This feature was evaluated, together with the incidence and clinical characteristics of DI in children with suprasellar/neurohypophyseal germinomas. We performed a review of all suprasellar (SS) or bifocal (BF) germinoma pediatric patients treated in Toronto since 2000. Demographics, symptomatology, treatment outcome and imaging were evaluated. Nineteen patients fulfilled inclusion criteria (10 SS, 9 BF; median age 12.5 years (6.2-16.8 years)). All remained alive at 6.4 years median follow-up (1.2-13.7 years) after receiving chemotherapy and radiotherapy (13 focal/ventricular, four whole brain, two neuraxis), with only one progression. All had symptoms of DI at presentation with a symptom interval above one year in eight cases (42 %). Desmopressin was commenced and maintained in 16 patients (84 %). The pituitary bright spot was lost in most diagnostic interpretable cases, but was appreciated in three patients (18 %) who had normal serum sodium values compared to 'absent' cases (p = 0.013). For two such cases, spots remained visible until last follow-up (range 0.4-3.3 years), with one still receiving desmopressin. No case of bright spot recovery was observed following therapy. Protracted symptom intervals for germinoma-induced central DI may reflect poor clinical awareness. Explanations for persistence of the pituitary bright spot in symptomatic patients remain elusive. Desmopressin seldom reverses the clinical features of germinoma-induced DI to allow discontinuation, nor does treatment cause bright spot recovery.

  19. 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.

  20. 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...

  1. Smart image sensor with adaptive correction of brightness

    Science.gov (United States)

    Paindavoine, Michel; Ngoua, Auguste; Brousse, Olivier; Clerc, Cédric

    2012-03-01

    Today, intelligent image sensors require the integration in the focal plane (or near the focal plane) of complex algorithms for image processing. Such devices must meet the constraints related to the quality of acquired images, speed and performance of embedded processing, as well as low power consumption. To achieve these objectives, analog pre-processing are essential, on the one hand, to improve the quality of the images making them usable whatever the light conditions, and secondly, to detect regions of interest (ROIs) to limit the amount of pixels to be transmitted to a digital processor performing the high-level processing such as feature extraction for pattern recognition. To show that it is possible to implement analog pre-processing in the focal plane, we have designed and implemented in 130nm CMOS technology, a test circuit with groups of 4, 16 and 144 pixels, each incorporating analog average calculations.

  2. An ultraviolet imager to study bright UV sources

    Science.gov (United States)

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

    2016-07-01

    We have designed and developed a compact ultraviolet imaging payload to y 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 electrical design of the instrument. We have adopted an all spherical optical design which would make the system less complex to realize and a cost effective solution compared to other telescope configuration. The structural design has been chosen in such a way that it will ensure that the instrument could withstand all the launch load vibrations. An FPGA based electronics board is used for the data acquisition, processing and CCD control. We will also brie y discuss about the hardware implementation of the detector interface and algorithms for the detector readout and data processing.

  3. Identification and recovery of discontinuous synoptic features in satellite-retrieved brightness temperatures using a radiative transfer model

    Science.gov (United States)

    White, G. A., III; Mcguirk, J. P.; Thompson, A. H.

    1988-01-01

    An attempt is made to recover and identify discontinuous synoptic features from satellite-retrieved brightness temperatures, with attention to near-discontinuities in temperature and moisture that are typically found in fronts and inversions. Efforts are made to ascertain whether the vectors of satellite channel brightness temperatures can be classified according to synoptic source, and whether those sources are amenable to quantification.

  4. Featured Image: A Comet's Coma

    Science.gov (United States)

    Kohler, Susanna

    2016-11-01

    This series of images (click for the full view!) features the nucleus of comet 67P/Churymov-Gerasimenko. The images were taken with the Wide Angle Camera of RosettasOSIRIS instrument asRosetta orbited comet 67P. Each column represents a different narrow-band filter that allows us to examine the emission of a specific fragment species, and the images progress in time from January 2015 (top) to June 2015 (bottom). In a recent study, Dennis Bodewits (University of Maryland) and collaborators used these images to analyze the comets inner coma, the cloud of gas and dust produced around the nucleus as ices sublime. OSIRISs images allowed the team to explore how the 67Ps inner coma changed over time as the comet approached the Sun marking the first time weve been able to study such an environment at this level of detail. To read more about what Bodewits and collaborators learned, you can check out their paper below!CitationD. Bodewits et al 2016 AJ 152 130. doi:10.3847/0004-6256/152/5/130

  5. Image feature localization by multiple hypothesis testing of Gabor features.

    Science.gov (United States)

    Ilonen, Jarmo; Kamarainen, Joni-Kristian; Paalanen, Pekka; Hamouz, Miroslav; Kittler, Josef; Kälviäinen, Heikki

    2008-03-01

    Several novel and particularly successful object and object category detection and recognition methods based on image features, local descriptions of object appearance, have recently been proposed. The methods are based on a localization of image features and a spatial constellation search over the localized features. The accuracy and reliability of the methods depend on the success of both tasks: image feature localization and spatial constellation model search. In this paper, we present an improved algorithm for image feature localization. The method is based on complex-valued multi resolution Gabor features and their ranking using multiple hypothesis testing. The algorithm provides very accurate local image features over arbitrary scale and rotation. We discuss in detail issues such as selection of filter parameters, confidence measure, and the magnitude versus complex representation, and show on a large test sample how these influence the performance. The versatility and accuracy of the method is demonstrated on two profoundly different challenging problems (faces and license plates).

  6. Infrared image mosaic using point feature operators

    Science.gov (United States)

    Huang, Zhen; Sun, Shaoyuan; Shen, Zhenyi; Hou, Junjie; Zhao, Haitao

    2016-10-01

    In this paper, we study infrared image mosaic around a single point of rotation, aiming at expanding the narrow view range of infrared images. We propose an infrared image mosaic method using point feature operators including image registration and image synthesis. Traditional mosaic algorithms usually use global image registration methods to extract the feature points in the global image, which cost too much time as well as considerable matching errors. To address this issue, we first roughly calculate the image shift amount using phase correlation and determine the overlap region between images, and then extract image features in overlap region, which shortens the registration time and increases the quality of feature points. We improve the traditional algorithm through increasing constraints of point matching based on prior knowledge of image shift amount based on which the weighted map is computed using fade in-out method. The experimental results verify that the proposed method has better real time performance and robustness.

  7. Medical Image Feature, Extraction, Selection And Classification

    Directory of Open Access Journals (Sweden)

    M.VASANTHA,

    2010-06-01

    Full Text Available Breast cancer is the most common type of cancer found in women. It is the most frequent form of cancer and one in 22 women in India is likely to suffer from breast cancer. This paper proposes a image classifier to classify the mammogram images. Mammogram image is classified into normal image, benign image and malignant image. Totally 26 features including histogram intensity features and GLCM features are extracted from mammogram image. A hybrid approach of feature selection is proposed in this paper which reduces 75% of the features. Decision tree algorithms are applied to mammography lassification by using these reduced features. Experimental results have been obtained for a data set of 113 images taken from MIAS of different types. This technique of classification has not been attempted before and it reveals the potential of Data mining in medical treatment.

  8. FRACTAL IMAGE FEATURE VECTORS WITH APPLICATIONS IN FRACTOGRAPHY

    Directory of Open Access Journals (Sweden)

    Hynek Lauschmann

    2011-05-01

    Full Text Available The morphology of fatigue fracture surface (caused by constant cycle loading is strictly related to crack growth rate. This relation may be expressed, among other methods, by means of fractal analysis. Fractal dimension as a single numerical value is not sufficient. Two types of fractal feature vectors are discussed: multifractal and multiparametric. For analysis of images, the box-counting method for 3D is applied with respect to the non-homogeneity of dimensions (two in space, one in brightness. Examples of application are shown: images of several fracture surfaces are analyzed and related to crack growth rate.

  9. 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.

  10. Imaging features in Hirayama disease

    Directory of Open Access Journals (Sweden)

    Sonwalkar Hemant

    2008-01-01

    Full Text Available Purpose: To evaluate the MR findings in clinically suspected cases of Hirayama disease. Materials and Methods: The pre and post contrast neutral and flexion position cervical MR images of eight patients of clinically suspected Hirayama disease were evaluated for the following findings: localized lower cervical cord atrophy, asymmetric cord flattening, abnormal cervical curvature, loss of attachment between the posterior dural sac and subjacent lamina, anterior shifting of the posterior wall of the cervical dural canal and enhancing epidural component with flow voids. The distribution of the above features in our patient population was noted and correlated with their clinical presentation and electromyography findings. Observations: Although lower cervical cord atrophy was noted in all eight cases of suspected Hirayama disease, the rest of the findings were variably distributed with asymmetric cord flattening, abnormal cervical curvature, anterior shifting of the posterior wall of the cervical dural canal and enhancing epidural component seen in six out of eight (75% cases. An additional finding of thoracic extension of the enhancing epidural component was also noted in five out of eight cases. Conclusion: Dynamic post contrast MRI evaluation of cervicothoracic spine is an accurate method for the diagnosis of Hirayama disease.

  11. 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.

  12. Dynamics of annular bright field imaging in scanning transmission electron microscopy

    Energy Technology Data Exchange (ETDEWEB)

    Findlay, S.D., E-mail: scott@sigma.t.u-tokyo.ac.jp [Institute of Engineering Innovation, The University of Tokyo, Tokyo 116-0013 (Japan); Shibata, N. [Institute of Engineering Innovation, The University of Tokyo, Tokyo 116-0013 (Japan); PRESTO, Japan Science and Technology Agency, Saitama 332-0012 (Japan); Sawada, H.; Okunishi, E.; Kondo, Y. [JEOL Ltd., Tokyo 196-8558 (Japan); Ikuhara, Y. [Institute of Engineering Innovation, The University of Tokyo, Tokyo 116-0013 (Japan); Nanostructures Research Laboratory, Japan Fine Ceramics Center, Nagoya 456-8587 (Japan); WPI Advanced Institute for Materials Research, Tohoku University, Sendai 980-8577 (Japan)

    2010-06-15

    We explore the dynamics of image formation in the so-called annular bright field mode in scanning transmission electron microscopy, whereby an annular detector is used with detector collection range lying within the cone of illumination, i.e. the bright field region. We show that this imaging mode allows us to reliably image both light and heavy columns over a range of thickness and defocus values, and we explain the contrast mechanisms involved. The role of probe and detector aperture sizes is considered, as is the sensitivity of the method to intercolumn spacing and local disorder.

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

    Directory of Open Access Journals (Sweden)

    Akira Tomie

    2016-01-01

    Full Text Available 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.

  14. 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. PMID:27738428

  15. 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.

  16. 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.

  17. Wilson’s disease: Atypical imaging features

    Directory of Open Access Journals (Sweden)

    Venugopalan Y Vishnu

    2016-10-01

    Full Text Available Wilson’s disease is a genetic movement disorder with characteristic clinical and imaging features. We report a 17- year-old boy who presented with sialorrhea, hypophonic speech, paraparesis with repeated falls and recurrent seizures along with cognitive decline. He had bilateral Kayser Flescher rings. Other than the typical features of Wilson’s disease in cranial MRI, there were extensive white matter signal abnormalities (T2 and FLAIR hyperintensities and gyriform contrast enhancement which are rare imaging features in Wilson's disease. A high index of suspicion is required to diagnose Wilson’s disease when atypical imaging features are present.

  18. 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.

  19. 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.

  20. Bright field microscopy as an alternative to whole cell fluorescence in automated analysis of macrophage images.

    Directory of Open Access Journals (Sweden)

    Jyrki Selinummi

    Full Text Available BACKGROUND: Fluorescence microscopy is the standard tool for detection and analysis of cellular phenomena. This technique, however, has a number of drawbacks such as the limited number of available fluorescent channels in microscopes, overlapping excitation and emission spectra of the stains, and phototoxicity. METHODOLOGY: We here present and validate a method to automatically detect cell population outlines directly from bright field images. By imaging samples with several focus levels forming a bright field -stack, and by measuring the intensity variations of this stack over the -dimension, we construct a new two dimensional projection image of increased contrast. With additional information for locations of each cell, such as stained nuclei, this bright field projection image can be used instead of whole cell fluorescence to locate borders of individual cells, separating touching cells, and enabling single cell analysis. Using the popular CellProfiler freeware cell image analysis software mainly targeted for fluorescence microscopy, we validate our method by automatically segmenting low contrast and rather complex shaped murine macrophage cells. SIGNIFICANCE: The proposed approach frees up a fluorescence channel, which can be used for subcellular studies. It also facilitates cell shape measurement in experiments where whole cell fluorescent staining is either not available, or is dependent on a particular experimental condition. We show that whole cell area detection results using our projected bright field images match closely to the standard approach where cell areas are localized using fluorescence, and conclude that the high contrast bright field projection image can directly replace one fluorescent channel in whole cell quantification. Matlab code for calculating the projections can be downloaded from the supplementary site: http://sites.google.com/site/brightfieldorstaining.

  1. 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.

  2. 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.)

  3. 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.

  4. Multi Feature Content Based Image Retrieval

    Directory of Open Access Journals (Sweden)

    Rajshree S. Dubey,

    2010-09-01

    Full Text Available There are numbers of methods prevailing for Image Mining Techniques. This Paper includes the features of four techniques I,e Color Histogram, Color moment, Texture, and Edge Histogram Descriptor. The nature of the Image is basically based on the Human Perception of the Image. The Machine interpretation of the Image is based on the Contours and surfaces of the Images. The study of the Image Mining is a very challenging task because it involves the Pattern Recognition which is a very important tool for the Machine Vision system. A combination of four feature extraction methods namely color istogram, Color Moment, texture, and Edge Histogram Descriptor. There is a provision to add new features in future for better retrievalefficiency. In this paper the combination of the four techniques are used and the Euclidian distances are calculated of the every features are added and the averages are made .The user interface is provided by the Mat lab. The image properties analyzed in this work are by using computer vision and image processing algorithms. For colorthe histogram of images are computed, for texture co occurrence matrix based entropy, energy, etc, are calculated and for edge density it is Edge Histogram Descriptor (EHD that is found. For retrieval of images, the averages of the four techniques are made and the resultant Image is retrieved.

  5. 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.

  6. 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.

  7. 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.

  8. Automatic Cell Detection in Bright-Field Microscope Images Using SIFT, Random Forests, and Hierarchical Clustering.

    Science.gov (United States)

    Mualla, Firas; Scholl, Simon; Sommerfeldt, Bjorn; Maier, Andreas; Hornegger, Joachim

    2013-12-01

    We present a novel machine learning-based system for unstained cell detection in bright-field microscope images. The system is fully automatic since it requires no manual parameter tuning. It is also highly invariant with respect to illumination conditions and to the size and orientation of cells. Images from two adherent cell lines and one suspension cell line were used in the evaluation for a total number of more than 3500 cells. Besides real images, simulated images were also used in the evaluation. The detection error was between approximately zero and 15.5% which is a significantly superior performance compared to baseline approaches.

  9. An Image Retrieval Method Using DCT Features

    Institute of Scientific and Technical Information of China (English)

    樊昀; 王润生

    2002-01-01

    In this paper a new image representation for compressed domain image re-trieval and an image retrieval system are presented. To represent images compactly and hi-erarchically, multiple features such as color and texture features directly extracted from DCTcoefficients are structurally organized using vector quantization. To train the codebook, a newMinimum Description Length vector quantization algorithm is used and it automatically decidesthe number of code words. To compare two images using the proposed representation, a newefficient similarity measure is designed. The new method is applied to an image database with1,005 pictures. The results demonstrate that the method is better than two typical histogrammethods and two DCT-based image retrieval methods.

  10. 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...

  11. 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

  12. 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.

  13. 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.

  14. MR imaging features of craniodiaphyseal dysplasia

    Energy Technology Data Exchange (ETDEWEB)

    Marden, Franklin A. [Mallinckrodt Institute of Radiology, Washington University Medical Center, 510 South Kingshighway Blvd., MO 63110, St. Louis (United States); Department of Radiology, St. Louis Children' s Hospital, Children' s Place, MO 63110, St. Louis (United States); Wippold, Franz J. [Mallinckrodt Institute of Radiology, Washington University Medical Center, 510 South Kingshighway Blvd., MO 63110, St. Louis (United States); Department of Radiology, St. Louis Children' s Hospital, Children' s Place, MO 63110, St. Louis (United States); Department of Radiology/Nuclear Medicine, F. Edward Hebert School of Medicine, Uniformed Services University of the Health Sciences, MD 20814, Bethesda (United States)

    2004-02-01

    We report the magnetic resonance (MR) imaging findings in a 4-year-old girl with characteristic radiographic and computed tomography (CT) features of craniodiaphyseal dysplasia. MR imaging exquisitely depicted cranial nerve compression, small foramen magnum, hydrocephalus, and other intracranial complications of this syndrome. A syrinx of the cervical spinal cord was demonstrated. We suggest that MR imaging become a routine component of the evaluation of these patients. (orig.)

  15. On the Active Region Bright Grains Observed in the Transition Region Imaging Channels of IRIS

    CERN Document Server

    Skogsrud, H; De Pontieu, B

    2015-01-01

    The Interface Region Imaging Spectrograph (IRIS) provides spectroscopy and narrow band slit-jaw (SJI) imaging of the solar chromosphere and transition region at unprecedented spatial and temporal resolution. Combined with high-resolution context spectral imaging of the photosphere and chromosphere as provided by the Swedish 1-m Solar Telescope (SST), we can now effectively trace dynamic phenomena through large parts of the solar atmosphere in both space and time. IRIS SJI 1400 images from active regions, which primarily sample the transition region with the Si IV 1394 and 1403 {\\AA} lines, reveal ubiquitous bright "grains" which are short-lived (2-5 min) bright roundish small patches of sizes 0.5-1.7" that generally move limbward with velocities up to about 30 km s$^{-1}$. In this paper we show that many bright grains are the result of chromospheric shocks impacting the transition region. These shocks are associated with dynamic fibrils (DFs), most commonly observed in H{\\alpha}. We find that the grains show ...

  16. Exact feature probabilities in images with occlusion

    CERN Document Server

    Pitkow, Xaq

    2010-01-01

    To understand the computations of our visual system, it is important to understand also the natural environment it evolved to interpret. Unfortunately, existing models of the visual environment are either unrealistic or too complex for mathematical description. Here we describe a naturalistic image model and present a mathematical solution for the statistical relationships between the image features and model variables. The world described by this model is composed of independent, opaque, textured objects which occlude each other. This simple structure allows us to calculate the joint probability distribution of image values sampled at multiple arbitrarily located points, without approximation. This result can be converted into probabilistic relationships between observable image features as well as between the unobservable properties that caused these features, including object boundaries and relative depth. Using these results we explain the causes of a wide range of natural scene properties, including high...

  17. 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...

  18. Automatic extraction of planetary image features

    Science.gov (United States)

    LeMoigne-Stewart, Jacqueline J. (Inventor); Troglio, Giulia (Inventor); Benediktsson, Jon A. (Inventor); Serpico, Sebastiano B. (Inventor); Moser, Gabriele (Inventor)

    2013-01-01

    A method for the extraction of Lunar data and/or planetary features is provided. The feature extraction method can include one or more image processing techniques, including, but not limited to, a watershed segmentation and/or the generalized Hough Transform. According to some embodiments, the feature extraction method can include extracting features, such as, small rocks. According to some embodiments, small rocks can be extracted by applying a watershed segmentation algorithm to the Canny gradient. According to some embodiments, applying a watershed segmentation algorithm to the Canny gradient can allow regions that appear as close contours in the gradient to be segmented.

  19. 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

  20. 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.

  1. 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.

  2. 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.

  3. 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.

  4. 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.

  5. 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...

  6. 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.

  7. Imaging features of benign adrenal cysts

    Energy Technology Data Exchange (ETDEWEB)

    Sanal, Hatice Tuba [Department of Radiology, Gulhane Military Medical Academy, Ankara (Turkey)]. E-mail: tubasanal@yahoo.com; Kocaoglu, Murat [Department of Radiology, Gulhane Military Medical Academy, Ankara (Turkey); Yildirim, Duzgun [Department of Radiology, Gulhane Military Medical Academy, Ankara (Turkey); Bulakbasi, Nail [Department of Radiology, Gulhane Military Medical Academy, Ankara (Turkey); Guvenc, Inanc [Department of Radiology, Gulhane Military Medical Academy, Ankara (Turkey); Tayfun, Cem [Department of Radiology, Gulhane Military Medical Academy, Ankara (Turkey); Ucoz, Taner [Department of Radiology, Gulhane Military Medical Academy, Ankara (Turkey)

    2006-12-15

    Benign adrenal gland cysts (BACs) are rare lesions with a variable histological spectrum and may mimic not only each other but also malignant ones. We aimed to review imaging features of BACs which can be helpful in distinguishing each entity and determining the subsequent appropriate management.

  8. Prospects for lithium imaging using annular bright field scanning transmission electron microscopy: A theoretical study

    Energy Technology Data Exchange (ETDEWEB)

    Findlay, S.D., E-mail: scott@sigma.t.u-tokyo.ac.jp [Institute of Engineering Innovation, The University of Tokyo, Tokyo 116-0013 (Japan); Lugg, N.R. [School of Physics, University of Melbourne, Parkville, Victoria 3010 (Australia); Shibata, N. [Institute of Engineering Innovation, The University of Tokyo, Tokyo 116-0013 (Japan); PRESTO, Japan Science and Technology Agency, Saitama 332-0012 (Japan); Allen, L.J. [School of Physics, University of Melbourne, Parkville, Victoria 3010 (Australia); Ikuhara, Y. [Institute of Engineering Innovation, The University of Tokyo, Tokyo 116-0013 (Japan); Nanostructures Research Laboratory, Japan Fine Ceramic Center, Nagoya 456-8587 (Japan); WPI Advanced Institute for Materials Research, Tohoku University, Sendai 980-8577 (Japan)

    2011-07-15

    There is strong interest in lithium imaging, particularly because of its significance in battery materials. However, light atoms only scatter electrons weakly and atomic resolution direct imaging of lithium has proven difficult. This paper explores theoretically the conditions under which lithium columns can be expected to be directly visible using annular bright field scanning transmission electron microscopy. A detailed discussion is given of the controllable parameters and the conditions most favourable for lithium imaging. -- Highlights: {yields} Optimum conditions to image Li columns in Li-bearing materials with ABF are explored. {yields} Higher accelerating voltages give better contrast at a given resolution. {yields} Aperture size must compromise between resolution and good coupling to the column. {yields} Samples with small along-column interatomic spacing between Li atoms are best. {yields} The trends observed are consistent with prediction based on the s-state model.

  9. Clinical and imaging features of fludarabine neurotoxicity.

    Science.gov (United States)

    Lee, Michael S; McKinney, Alexander M; Brace, Jeffrey R; Santacruz, Karen

    2010-03-01

    Neurotoxicity from intravenous fludarabine is a rare but recognized clinical entity. Its brain imaging features have not been extensively described. Three patients received 38.5 mg or 40 mg/m per day fludarabine in a 5-day intravenous infusion before bone marrow transplantation in treatment of hematopoietic malignancies. Several weeks later, each patient developed progressive neurologic decline, including retrogeniculate blindness, leading to coma and death. Brain MRI showed progressively enlarging but mild T2/FLAIR hyperintensities in the periventricular white matter. The lesions demonstrated restricted diffusion but did not enhance. Because the neurotoxicity of fludarabine appears long after exposure, neurologic decline in this setting is likely to be attributed to opportunistic disease. However, the imaging features are distinctive in their latency and in being mild relative to the profound clinical features. The safe dose of fludarabine in this context remains controversial.

  10. ON THE ACTIVE REGION BRIGHT GRAINS OBSERVED IN THE TRANSITION REGION IMAGING CHANNELS OF IRIS

    Energy Technology Data Exchange (ETDEWEB)

    Skogsrud, H.; Voort, L. Rouppe van der; Pontieu, B. De [Institute of Theoretical Astrophysics, University of Oslo, P.O. Box 1029 Blindern, NO-0315 Oslo (Norway)

    2016-02-01

    The Interface Region Imaging Spectrograph (IRIS) provides spectroscopy and narrow band slit-jaw (SJI) imaging of the solar chromosphere and transition region at unprecedented spatial and temporal resolutions. Combined with high-resolution context spectral imaging of the photosphere and chromosphere as provided by the Swedish 1 m Solar Telescope (SST), we can now effectively trace dynamic phenomena through large parts of the solar atmosphere in both space and time. IRIS SJI 1400 images from active regions, which primarily sample the transition region with the Si iv 1394 and 1403 Å lines, reveal ubiquitous bright “grains” which are short-lived (two to five minute) bright roundish small patches of sizes 0.″5–1.″7 that generally move limbward with velocities up to about 30 km s{sup −1}. In this paper, we show that many bright grains are the result of chromospheric shocks impacting the transition region. These shocks are associated with dynamic fibrils (DFs), most commonly observed in Hα. We find that the grains show the strongest emission in the ascending phase of the DF, that the emission is strongest toward the top of the DF, and that the grains correspond to a blueshift and broadening of the Si iv lines. We note that the SJI 1400 grains can also be observed in the SJI 1330 channel which is dominated by C ii lines. Our observations show that a significant part of the active region transition region dynamics is driven from the chromosphere below rather than from coronal activity above. We conclude that the shocks that drive DFs also play an important role in the heating of the upper chromosphere and lower transition region.

  11. 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.

  12. 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.

  13. Special feature on imaging systems and techniques

    Science.gov (United States)

    Yang, Wuqiang; Giakos, George

    2013-07-01

    The IEEE International Conference on Imaging Systems and Techniques (IST'2012) was held in Manchester, UK, on 16-17 July 2012. The participants came from 26 countries or regions: Austria, Brazil, Canada, China, Denmark, France, Germany, Greece, India, Iran, Iraq, Italy, Japan, Korea, Latvia, Malaysia, Norway, Poland, Portugal, Sweden, Switzerland, Taiwan, Tunisia, UAE, UK and USA. The technical program of the conference consisted of a series of scientific and technical sessions, exploring physical principles, engineering and applications of new imaging systems and techniques, as reflected by the diversity of the submitted papers. Following a rigorous review process, a total of 123 papers were accepted, and they were organized into 30 oral presentation sessions and a poster session. In addition, six invited keynotes were arranged. The conference not only provided the participants with a unique opportunity to exchange ideas and disseminate research outcomes but also paved a way to establish global collaboration. Following the IST'2012, a total of 55 papers, which were technically extended substantially from their versions in the conference proceeding, were submitted as regular papers to this special feature of Measurement Science and Technology . Following a rigorous reviewing process, 25 papers have been finally accepted for publication in this special feature and they are organized into three categories: (1) industrial tomography, (2) imaging systems and techniques and (3) image processing. These papers not only present the latest developments in the field of imaging systems and techniques but also offer potential solutions to existing problems. We hope that this special feature provides a good reference for researchers who are active in the field and will serve as a catalyst to trigger further research. It has been our great pleasure to be the guest editors of this special feature. We would like to thank the authors for their contributions, without which it would

  14. 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.)

  15. 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

  16. 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.

  17. Mass-like extramedullary hematopoiesis: imaging features

    Energy Technology Data Exchange (ETDEWEB)

    Ginzel, Andrew W. [Synergy Radiology Associates, Houston, TX (United States); Kransdorf, Mark J.; Peterson, Jeffrey J.; Garner, Hillary W. [Mayo Clinic, Department of Radiology, Jacksonville, FL (United States); Murphey, Mark D. [American Institute for Radiologic Pathology, Silver Spring, MD (United States)

    2012-08-15

    To report the imaging appearances of mass-like extramedullary hematopoiesis (EMH), to identify those features that are sufficiently characteristic to allow a confident diagnosis, and to recognize the clinical conditions associated with EMH and the relative incidence of mass-like disease. We retrospectively identified 44 patients with EMH; 12 of which (27%) had focal mass-like lesions and formed the study group. The study group consisted of 6 male and 6 female subjects with a mean age of 58 years (range 13-80 years). All 12 patients underwent CT imaging and 3 of the 12 patients had undergone additional MR imaging. The imaging characteristics of the extramedullary hematopoiesis lesions in the study group were analyzed and recorded. The patient's clinical presentation, including any condition associated with extramedullary hematopoiesis, was also recorded. Ten of the 12 (83%) patients had one or more masses located along the axial skeleton. Of the 10 patients with axial masses, 9 (90%) had multiple masses and 7 (70%) demonstrated internal fat. Eight patients (80%) had paraspinal masses and 4 patients (40%) had presacral masses. Seven patients (70%) had splenomegaly. Eleven of the 12 patients had a clinical history available for review. A predisposing condition for extramedullary hematopoiesis was present in 10 patients and included various anemias (5 cases; 45%), myelofibrosis/myelodysplastic syndrome (4 cases; 36%), and marrow proliferative disorder (1 case; 9%). One patient had no known predisposing condition. Mass-like extramedullary hematopoiesis most commonly presents as multiple, fat-containing lesions localized to the axial skeleton. When these imaging features are identified, extramedullary hematopoiesis should be strongly considered, particularly when occurring in the setting of a predisposing medical condition. (orig.)

  18. Imaging internal features of whole, unfixed bacteria.

    Science.gov (United States)

    Thomson, Nicholas M; Channon, Kevin; Mokhtar, Noor Azlin; Staniewicz, Lech; Rai, Ranjana; Roy, Ipsita; Sato, Shun; Tsuge, Takeharu; Donald, Athene M; Summers, David; Sivaniah, Easan

    2011-01-01

    Wet scanning-transmission electron microscopy (STEM) is a technique that allows high-resolution transmission imaging of biological samples in a hydrated state, with minimal sample preparation. However, it has barely been used for the study of bacterial cells. In this study, we present an analysis of the advantages and disadvantages of wet STEM compared with standard transmission electron microscopy (TEM). To investigate the potential applications of wet STEM, we studied the growth of polyhydroxyalkanoate and triacylglycerol carbon storage inclusions. These were easily visible inside cells, even in the early stages of accumulation. Although TEM produces higher resolution images, wet STEM is useful when preservation of the sample is important or when studying the relative sizes of different features, since samples do not need to be sectioned. Furthermore, under carefully selected conditions, it may be possible to maintain cell viability, enabling new types of experiments to be carried out. To our knowledge, internal features of bacterial cells have not been imaged previously by this technique.

  19. NEAR-IR IMAGING POLARIMETRY TOWARD A BRIGHT-RIMMED CLOUD: MAGNETIC FIELD IN SFO 74

    Energy Technology Data Exchange (ETDEWEB)

    Kusune, Takayoshi; Sugitani, Koji [Graduate School of Natural Sciences, Nagoya City University, Mizuho-ku, Nagoya 467-8501 (Japan); Miao, Jingqi [Centre for Astrophysics and Planetary Science, School of Physical Sciences, University of Kent, Canterbury, Kent CT2 7NR (United Kingdom); Tamura, Motohide; Kwon, Jungmi [Department of Astronomy, University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-0033 (Japan); Sato, Yaeko [National Astronomical Observatory, 2-21-1 Osawa, Mikata, Tokyo 181-8588 (Japan); Watanabe, Makoto [Department of Cosmosciences, Hokkaido University, Kita 10, Nishi 8, Kita-ku, Sapporo, Hokkaido 060-0810 (Japan); Nishiyama, Shogo [Faculty of Education, Miyagi University of Education, Sendai 980-0845 (Japan); Nagayama, Takahiro [Department of Physics, Kagoshima University, 1-21-35 Korimoto, Kagoshima 890-0065 (Japan); Sato, Shuji [Department of Astrophysics, Nagoya University, Chikusa-ku, Nagoya 464-8602 (Japan)

    2015-01-01

    We have made near-infrared (JHK {sub s}) imaging polarimetry of a bright-rimmed cloud (SFO 74). The polarization vector maps clearly show that the magnetic field in the layer just behind the bright rim is running along the rim, quite different from its ambient magnetic field. The direction of the magnetic field just behind the tip rim is almost perpendicular to that of the incident UV radiation, and the magnetic field configuration appears to be symmetric as a whole with respect to the cloud symmetry axis. We estimated the column and number densities in the two regions (just inside and far inside the tip rim) and then derived the magnetic field strength, applying the Chandrasekhar-Fermi method. The estimated magnetic field strength just inside the tip rim, ∼90 μG, is stronger than that far inside, ∼30 μG. This suggests that the magnetic field strength just inside the tip rim is enhanced by the UV-radiation-induced shock. The shock increases the density within the top layer around the tip and thus increases the strength of the magnetic field. The magnetic pressure seems to be comparable to the turbulent one just inside the tip rim, implying a significant contribution of the magnetic field to the total internal pressure. The mass-to-flux ratio was estimated to be close to the critical value just inside the tip rim. We speculate that the flat-topped bright rim of SFO 74 could be formed by the magnetic field effect.

  20. 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.)

  1. 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

  2. Near-IR Imaging Polarimetry toward a Bright-Rimmed Cloud: Magnetic Field in SFO 74

    CERN Document Server

    Kusune, Takayoshi; Miao, Jingqi; Tamura, Motohide; Sato, Yaeko; Kwon, Jungmi; Watanabe, Makoto; Nishiyama, Shogo; Nagayama, Takahiro; Sato, Shuji

    2014-01-01

    We have made near-infrared (JHKs) imaging polarimetry of a bright-rimmed cloud (SFO 74). The polarization vector maps clearly show that the magnetic field in the layer just behind the bright rim is running along the rim, quite different from its ambient magnetic field. The direction of the magnetic field just behind the tip rim is almost perpendicular to that of the incident UV radiation, and the magnetic field configuration appears to be symmetric as a whole with respect to the cloud symmetry axis. We estimated the column and number densities in the two regions (just inside and far inside the tip rim), and then derived the magnetic field strength, applying the Chandrasekhar-Fermi method. The estimated magnetic field strength just inside the tip rim, ~90 uG, is stronger than that far inside, ~30 uG. This suggests that the magnetic field strength just inside the tip rim is enhanced by the UV radiation induced shock. The shock increases the density within the top layer around the tip, and thus increases the str...

  3. 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.

  4. 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.

  5. 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.

  6. Toward Automated Feature Detection in UAVSAR Images

    Science.gov (United States)

    Parker, J. W.; Donnellan, A.; Glasscoe, M. T.

    2014-12-01

    Edge detection identifies seismic or aseismic fault motion, as demonstrated in repeat-pass inteferograms obtained by the Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) program. But this identification is not robust at present: it requires a flattened background image, interpolation into missing data (holes) and outliers, and background noise that is either sufficiently small or roughly white Gaussian. Identification and mitigation of nongaussian background image noise is essential to creating a robust, automated system to search for such features. Clearly a robust method is needed for machine scanning of the thousands of UAVSAR repeat-pass interferograms for evidence of fault slip, landslides, and other local features.Empirical examination of detrended noise based on 20 km east-west profiles through desert terrain with little tectonic deformation for a suite of flight interferograms shows nongaussian characteristics. Statistical measurement of curvature with varying length scale (Allan variance) shows nearly white behavior (Allan variance slope with spatial distance from roughly -1.76 to -2) from 25 to 400 meters, deviations from -2 suggesting short-range differences (such as used in detecting edges) are often freer of noise than longer-range differences. At distances longer than 400 m the Allan variance flattens out without consistency from one interferogram to another. We attribute this additional noise afflicting difference estimates at longer distances to atmospheric water vapor and uncompensated aircraft motion.Paradoxically, California interferograms made with increasing time intervals before and after the El Mayor Cucapah earthquake (2008, M7.2, Mexico) show visually stronger and more interesting edges, but edge detection methods developed for the first year do not produce reliable results over the first two years, because longer time spans suffer reduced coherence in the interferogram. The changes over time are reflecting fault slip and block

  7. 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.

  8. Atmospheric Imaging Assembly Response Functions: Solving the Fe VIII Problems with Hinode EIS Bright Point Data

    CERN Document Server

    Schmelz, Joan T; Kimble, Jason A; 10.1007/s11207-012-0208-1

    2013-01-01

    The Atmospheric Imaging Assembly (AIA) onboard the Solar Dynamics Observatory is a state-of-the-art imager with the potential to do unprecedented time-dependent multi-thermal analysis at every pixel on scales short compared to the radiative and conductive cooling times. Recent results, however, have identified missing spectral lines in the CHIANTI atomic physics data base, which is used to construct the instrument response functions. We have done differential emission measure analysis using simultaneous AIA and Hinode/EIS observations of six X-ray bright points. Our results not only support the conclusion that CHIANTI is incomplete near 131 angstroms, but more importantly, suggest that the peak temperature of the Fe VIII emissivity/response is likely to be closer to log T = 5.8 than to the current value of log T = 5.7. Using a revised emissivity/response calculation for Fe VIII, we find that the observed AIA 131-angstrom flux can be underestimated by about 1.25, which is smaller than previous comparisons.

  9. 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.

  10. 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.

  11. Imaging systems and applications: introduction to the feature.

    Science.gov (United States)

    Imai, Francisco H; Linne von Berg, Dale C; Skauli, Torbjørn; Tominaga, Shoji; Zalevsky, Zeev

    2014-05-01

    Imaging systems have numerous applications in industrial, military, consumer, and medical settings. Assembling a complete imaging system requires the integration of optics, sensing, image processing, and display rendering. This issue features original research ranging from design of stimuli for human perception, optics applications, and image enhancement to novel imaging modalities in both color and infrared spectral imaging, gigapixel imaging as well as a systems perspective to imaging.

  12. 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.

  13. 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.

  14. 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. .

  15. Ultra-bright and -stable red and near-infrared squaraine fluorophores for in vivo two-photon imaging.

    Science.gov (United States)

    Podgorski, Kaspar; Terpetschnig, Ewald; Klochko, Oleksii P; Obukhova, Olena M; Haas, Kurt

    2012-01-01

    Fluorescent dyes that are bright, stable, small, and biocompatible are needed for high-sensitivity two-photon imaging, but the combination of these traits has been elusive. We identified a class of squaraine derivatives with large two-photon action cross-sections (up to 10,000 GM) at near-infrared wavelengths critical for in vivo imaging. We demonstrate the biocompatibility and stability of a red-emitting squaraine-rotaxane (SeTau-647) by imaging dye-filled neurons in vivo over 5 days, and utility for sensitive subcellular imaging by synthesizing a specific peptide-conjugate label for the synaptic protein PSD-95.

  16. Ultra-bright and -stable red and near-infrared squaraine fluorophores for in vivo two-photon imaging.

    Directory of Open Access Journals (Sweden)

    Kaspar Podgorski

    Full Text Available Fluorescent dyes that are bright, stable, small, and biocompatible are needed for high-sensitivity two-photon imaging, but the combination of these traits has been elusive. We identified a class of squaraine derivatives with large two-photon action cross-sections (up to 10,000 GM at near-infrared wavelengths critical for in vivo imaging. We demonstrate the biocompatibility and stability of a red-emitting squaraine-rotaxane (SeTau-647 by imaging dye-filled neurons in vivo over 5 days, and utility for sensitive subcellular imaging by synthesizing a specific peptide-conjugate label for the synaptic protein PSD-95.

  17. 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.

  18. 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.

  19. 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.

  20. 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

  1. Evaluation of textural features for multispectral images

    Science.gov (United States)

    Bayram, Ulya; Can, Gulcan; Duzgun, Sebnem; Yalabik, Nese

    2011-11-01

    Remote sensing is a field that has wide use, leading to the fact that it has a great importance. Therefore performance of selected features plays a great role. In order to gain some perspective on useful textural features, we have brought together state-of-art textural features in recent literature, yet to be applied in remote sensing field, as well as presenting a comparison with traditional ones. Therefore we selected most commonly used textural features in remote sensing that are grey-level co-occurrence matrix (GLCM) and Gabor features. Other selected features are local binary patterns (LBP), edge orientation features extracted after applying steerable filter, and histogram of oriented gradients (HOG) features. Color histogram feature is also used and compared. Since most of these features are histogram-based, we have compared performance of bin-by-bin comparison with a histogram comparison method named as diffusion distance method. During obtaining performance of each feature, k-nearest neighbor classification method (k-NN) is applied.

  2. 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.

  3. 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.

  4. [Multiple transmission electron microscopic image stitching based on sift features].

    Science.gov (United States)

    Li, Mu; Lu, Yanmeng; Han, Shuaihu; Wu, Zhuobin; Chen, Jiajing; Liu, Zhexing; Cao, Lei

    2015-08-01

    We proposed a new stitching method based on sift features to obtain an enlarged view of transmission electron microscopic (TEM) images with a high resolution. The sift features were extracted from the images, which were then combined with fitted polynomial correction field to correct the images, followed by image alignment based on the sift features. The image seams at the junction were finally removed by Poisson image editing to achieve seamless stitching, which was validated on 60 local glomerular TEM images with an image alignment error of 62.5 to 187.5 nm. Compared with 3 other stitching methods, the proposed method could effectively reduce image deformation and avoid artifacts to facilitate renal biopsy pathological diagnosis.

  5. 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.

  6. Registration of multitemporal aerial optical images using line features

    Science.gov (United States)

    Zhao, Chenyang; Goshtasby, A. Ardeshir

    2016-07-01

    Registration of multitemporal images is generally considered difficult because scene changes can occur between the times the images are obtained. Since the changes are mostly radiometric in nature, features are needed that are insensitive to radiometric differences between the images. Lines are geometric features that represent straight edges of rigid man-made structures. Because such structures rarely change over time, lines represent stable geometric features that can be used to register multitemporal remote sensing images. An algorithm to establish correspondence between lines in two images of a planar scene is introduced and formulas to relate the parameters of a homography transformation to the parameters of corresponding lines in images are derived. Results of the proposed image registration on various multitemporal images are presented and discussed.

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

    Science.gov (United States)

    Pety, J.; Lucas, R.; Liszt, H. S.

    2008-10-01

    Aims: 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). Methods: We used the IRAM 30 m Telescope and Plateau de Bure Interferometer to make two series of images of the host gas: i) 22.5'' resolution single-dish maps of 12CO J = 1-0 and 2-1 emission over a 220'' by 220'' field; ii) a hybrid (interferometer+singledish) aperture synthesis mosaic of 12CO J = 1-0 emission at 5.8'' resolution over a 90''-diameter region. Results: At 22.5'' resolution, the CO J = 1-0 emission toward NRAO150 is 30-100% brighter at some velocities than seen previously with 1' resolution, and there are some modest systematic velocity gradients over the 220'' field. Of the five CO components seen in the absorption spectra, the weakest ones are absent in emission toward NRAO150 but appear more strongly at the edges of the region mapped in emission. The overall spatial variations in the strongly emitting gas have Poisson statistics with rms fluctuations about equal to the mean emission level in the line wings and much of the line cores. The J = 2-1/J = 1-0 line ratios calculated pixel-by-pixel cluster around 0.7. At 6'' resolution, disparity between the absorption and emission profiles of the stronger components has been largely ameliorated. The 12CO J = 1-0 emission exhibits i) remarkably bright peaks, {T}_mb = 12-13 K, even as 4'' from NRAO150; ii) smaller relative levels of spatial fluctuation in the line cores, but a very broad range of possible intensities at every velocity; and iii) striking kinematics whereby the monotonic velocity shifts and supersonically broadened lines in 22.5'' spectra are decomposed into much stronger velocity gradients and abrupt velocity reversals of intense but narrow, probably subsonic, line cores. Conclusions: CO components that are observed in absorption at a moderate

  8. 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.

  9. Mining Mid-level Features for Image Classification

    OpenAIRE

    Fernando, Basura; Fromont, Elisa; Tuytelaars, Tinne

    2014-01-01

    International audience; Mid-level or semi-local features learnt using class-level information are potentially more distinctive than the traditional low-level local features constructed in a purely bottom-up fashion. At the same time they preserve some of the robustness properties with respect to occlusions and image clutter. In this paper we propose a new and effective scheme for extracting mid-level features for image classification, based on relevant pattern mining. In par- ticular, we mine...

  10. 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).

  11. Feature extraction for an image retrieving scheme

    OpenAIRE

    Fuertes García, José Manuel; Lucena López, Manuel José; Pérez de la Blanca Capilla, Nicolás; Fernández Valdivia, Joaquín

    1999-01-01

    In this paper we present two basic modules whithin the designed scheme for retrieving images of a database from the object colour and shape in the scenes. On the one hand, we desing a new method to detect edges in colour images. We offer a new approach to the perceptual space (H,S,I) (an Uniform Chromatic Scale space) About wich we describe its properties as well as the metric to work in it. On the other hand, we develop an information simplifying process to form a graphic structure en wich t...

  12. 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.

  13. 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

  14. 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.

  15. 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...

  16. Feature extraction for magnetic domain images of magneto-optical recording films using gradient feature segmentation

    Science.gov (United States)

    Quanqing, Zhu; Xinsai, Wang; Xuecheng, Zou; Haihua, Li; Xiaofei, Yang

    2002-07-01

    In this paper, we present a method to realize feature extraction on low contrast magnetic domain images of magneto-optical recording films. The method is based on the following three steps: first, Lee-filtering method is adopted to realize pre-filtering and noise reduction; this is followed by gradient feature segmentation, which separates the object area from the background area; finally the common linking method is adopted and the characteristic parameters of magnetic domain are calculated. We describe these steps with particular emphasis on the gradient feature segmentation. The results show that this method has advantages over other traditional ones for feature extraction of low contrast images.

  17. 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.

  18. 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.

  19. 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.

  20. 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.

  1. Feature Selection for Image Retrieval based on Genetic Algorithm

    Directory of Open Access Journals (Sweden)

    Preeti Kushwaha

    2016-12-01

    Full Text Available This paper describes the development and implementation of feature selection for content based image retrieval. We are working on CBIR system with new efficient technique. In this system, we use multi feature extraction such as colour, texture and shape. The three techniques are used for feature extraction such as colour moment, gray level co- occurrence matrix and edge histogram descriptor. To reduce curse of dimensionality and find best optimal features from feature set using feature selection based on genetic algorithm. These features are divided into similar image classes using clustering for fast retrieval and improve the execution time. Clustering technique is done by k-means algorithm. The experimental result shows feature selection using GA reduces the time for retrieval and also increases the retrieval precision, thus it gives better and faster results as compared to normal image retrieval system. The result also shows precision and recall of proposed approach compared to previous approach for each image class. The CBIR system is more efficient and better performs using feature selection based on Genetic Algorithm.

  2. 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.

  3. 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.

  4. 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.

  5. 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...

  6. Ship Targets Discrimination Algorithm in SAR Images Based on Hu Moment Feature and Texture Feature

    Directory of Open Access Journals (Sweden)

    Liu Lei

    2016-01-01

    Full Text Available To discriminate the ship targets in SAR images, this paper proposed the method based on combination of Hu moment feature and texture feature. Firstly,7 Hu moment features should be extracted, while gray level co-occurrence matrix is then used to extract the features of mean, variance, uniformity, energy, entropy, inertia moment, correlation and differences. Finally the k-neighbour classifier was used to analysis the 15 dimensional feature vectors. The experimental results show that the method of this paper has a good effect.

  7. Segmentation of MR images using multiple-feature vectors

    Science.gov (United States)

    Cole, Orlean I. B.; Daemi, Mohammad F.

    1996-04-01

    Segmentation is an important step in the analysis of MR images (MRI). Considerable progress has been made in this area, and numerous reports on 3D segmentation, volume measurement and visualization have been published in recent years. The main purpose of our study is to investigate the power and use of fractal techniques in extraction of features from MR images of the human brain. These features which are supplemented by other features are used for segmentation, and ultimately for the extraction of a known pathology, in our case multiple- sclerosis (MS) lesions. We are particularly interested in the progress of the lesions and occurrence of new lesions which in a typical case are scattered within the image and are sometimes difficult to identify visually. We propose a technique for multi-channel segmentation of MR images using multiple feature vectors. The channels are proton density, T1-weighted and T2-weighted images containing multiple-sclerosis (MS) lesions at various stages of development. We first represent each image as a set of feature vectors which are estimated using fractal techniques, and supplemented by micro-texture features and features from the gray-level co-occurrence matrix (GLCM). These feature vectors are then used in a feature selection algorithm to reduce the dimension of the feature space. The next stage is segmentation and clustering. The selected feature vectors now form the input to the segmentation and clustering routines and are used as the initial clustering parameters. For this purpose, we have used the classical K-means as the initial clustering method. The clustered image is then passed into a probabilistic classifier to further classify and validate each region, taking into account the spatial properties of the image. Initially, segmentation results were obtained using the fractal dimension features alone. Subsequently, a combination of the fractal dimension features and the supplementary features mentioned above were also obtained

  8. 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.

  9. Featured Image: The Birth of Spiral Arms

    Science.gov (United States)

    Kohler, Susanna

    2017-01-01

    In this figure, the top panels show three spiral galaxies in the Virgo cluster, imaged with the Sloan Digital Sky Survey. The bottom panels provide a comparison with three morphologically similar galaxies generated insimulations. The simulations run by Marcin Semczuk, Ewa okas, and Andrs del Pino (Nicolaus Copernicus Astronomical Center, Poland) were designed to examine how the spiral arms of galaxies like the Milky Way may have formed. In particular, the group exploredthe possibility that so-called grand-design spiral arms are caused by tidal effects as a Milky-Way-like galaxy orbits a cluster of galaxies. The authors show that the gravitational potential of the cluster can trigger the formation of two spiral arms each time the galaxy passes through the pericenter of its orbit around the cluster. Check out the original paper below for more information!CitationMarcin Semczuk et al 2017 ApJ 834 7. doi:10.3847/1538-4357/834/1/7

  10. 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.

  11. The analysis of image feature robustness using cometcloud

    Directory of Open Access Journals (Sweden)

    Xin Qi

    2012-01-01

    Full Text Available The robustness of image features is a very important consideration in quantitative image analysis. The objective of this paper is to investigate the robustness of a range of image texture features using hematoxylin stained breast tissue microarray slides which are assessed while simulating different imaging challenges including out of focus, changes in magnification and variations in illumination, noise, compression, distortion, and rotation. We employed five texture analysis methods and tested them while introducing all of the challenges listed above. The texture features that were evaluated include co-occurrence matrix, center-symmetric auto-correlation, texture feature coding method, local binary pattern, and texton. Due to the independence of each transformation and texture descriptor, a network structured combination was proposed and deployed on the Rutgers private cloud. The experiments utilized 20 randomly selected tissue microarray cores. All the combinations of the image transformations and deformations are calculated, and the whole feature extraction procedure was completed in 70 minutes using a cloud equipped with 20 nodes. Center-symmetric auto-correlation outperforms all the other four texture descriptors but also requires the longest computational time. It is roughly 10 times slower than local binary pattern and texton. From a speed perspective, both the local binary pattern and texton features provided excellent performance for classification and content-based image retrieval.

  12. 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.

  13. Convolutional neural network features based change detection in satellite images

    Science.gov (United States)

    Mohammed El Amin, Arabi; Liu, Qingjie; Wang, Yunhong

    2016-07-01

    With the popular use of high resolution remote sensing (HRRS) satellite images, a huge research efforts have been placed on change detection (CD) problem. An effective feature selection method can significantly boost the final result. While hand-designed features have proven difficulties to design features that effectively capture high and mid-level representations, the recent developments in machine learning (Deep Learning) omit this problem by learning hierarchical representation in an unsupervised manner directly from data without human intervention. In this letter, we propose approaching the change detection problem from a feature learning perspective. A novel deep Convolutional Neural Networks (CNN) features based HR satellite images change detection method is proposed. The main guideline is to produce a change detection map directly from two images using a pretrained CNN. This method can omit the limited performance of hand-crafted features. Firstly, CNN features are extracted through different convolutional layers. Then, a concatenation step is evaluated after an normalization step, resulting in a unique higher dimensional feature map. Finally, a change map was computed using pixel-wise Euclidean distance. Our method has been validated on real bitemporal HRRS satellite images according to qualitative and quantitative analyses. The results obtained confirm the interest of the proposed method.

  14. 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

  15. Brightness-equalized quantum dots

    Science.gov (United States)

    Lim, Sung Jun; Zahid, Mohammad U.; Le, Phuong; Ma, Liang; Entenberg, David; Harney, Allison S.; Condeelis, John; Smith, Andrew M.

    2015-10-01

    As molecular labels for cells and tissues, fluorescent probes have shaped our understanding of biological structures and processes. However, their capacity for quantitative analysis is limited because photon emission rates from multicolour fluorophores are dissimilar, unstable and often unpredictable, which obscures correlations between measured fluorescence and molecular concentration. Here we introduce a new class of light-emitting quantum dots with tunable and equalized fluorescence brightness across a broad range of colours. The key feature is independent tunability of emission wavelength, extinction coefficient and quantum yield through distinct structural domains in the nanocrystal. Precise tuning eliminates a 100-fold red-to-green brightness mismatch of size-tuned quantum dots at the ensemble and single-particle levels, which substantially improves quantitative imaging accuracy in biological tissue. We anticipate that these materials engineering principles will vastly expand the optical engineering landscape of fluorescent probes, facilitate quantitative multicolour imaging in living tissue and improve colour tuning in light-emitting devices.

  16. 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

  17. Featured Image: A Looping Stellar Stream

    Science.gov (United States)

    Kohler, Susanna

    2016-11-01

    This negative image of NGC 5907 (originally published inMartinez-Delgadoet al. 2008; click for the full view!) reveals the faint stellar stream that encircles the galaxy, forming loops around it a fossil of a recent merger. Mergers between galaxies come in several different flavors: major mergers, in which the merging galaxies are within a 1:5 ratio in stellar mass; satellite cannibalism, in which a large galaxy destroys a small satellite less than a 50th of its size; and the in-between case of minor mergers, in which the merging galaxieshave stellar mass ratios between 1:5 and 1:50. These minor mergers are thought to be relatively common, and they can have a significant effect on the dynamics and structure of the primary galaxy. A team of scientists led by Seppo Laine (Spitzer Science Center Caltech) has recently analyzed the metallicity and age of the stellar population in the stream around NGC 5907. By fitting these observations with a stellar population synthesis model, they conclude that this stream is an example of a massive minor merger, with a stellar mass ratio of at least 1:8. For more information, check out the paper below!CitationSeppo Laine et al 2016 AJ 152 72. doi:10.3847/0004-6256/152/3/72

  18. Robust Tomato Recognition for Robotic Harvesting Using Feature Images Fusion

    Directory of Open Access Journals (Sweden)

    Yuanshen Zhao

    2016-01-01

    Full Text Available Automatic recognition of mature fruits in a complex agricultural environment is still a challenge for an autonomous harvesting robot due to various disturbances existing in the background of the image. The bottleneck to robust fruit recognition is reducing influence from two main disturbances: illumination and overlapping. In order to recognize the tomato in the tree canopy using a low-cost camera, a robust tomato recognition algorithm based on multiple feature images and image fusion was studied in this paper. Firstly, two novel feature images, the  a*-component image and the I-component image, were extracted from the L*a*b* color space and luminance, in-phase, quadrature-phase (YIQ color space, respectively. Secondly, wavelet transformation was adopted to fuse the two feature images at the pixel level, which combined the feature information of the two source images. Thirdly, in order to segment the target tomato from the background, an adaptive threshold algorithm was used to get the optimal threshold. The final segmentation result was processed by morphology operation to reduce a small amount of noise. In the detection tests, 93% target tomatoes were recognized out of 200 overall samples. It indicates that the proposed tomato recognition method is available for robotic tomato harvesting in the uncontrolled environment with low cost.

  19. 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.)

  20. 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.

  1. 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.

  2. 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.)

  3. 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.

  4. 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.

  5. 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.

  6. 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.

  7. Face recognition with multi-resolution spectral feature images.

    Directory of Open Access Journals (Sweden)

    Zhan-Li Sun

    Full Text Available The one-sample-per-person problem has become an active research topic for face recognition in recent years because of its challenges and significance for real-world applications. However, achieving relatively higher recognition accuracy is still a difficult problem due to, usually, too few training samples being available and variations of illumination and expression. To alleviate the negative effects caused by these unfavorable factors, in this paper we propose a more accurate spectral feature image-based 2DLDA (two-dimensional linear discriminant analysis ensemble algorithm for face recognition, with one sample image per person. In our algorithm, multi-resolution spectral feature images are constructed to represent the face images; this can greatly enlarge the training set. The proposed method is inspired by our finding that, among these spectral feature images, features extracted from some orientations and scales using 2DLDA are not sensitive to variations of illumination and expression. In order to maintain the positive characteristics of these filters and to make correct category assignments, the strategy of classifier committee learning (CCL is designed to combine the results obtained from different spectral feature images. Using the above strategies, the negative effects caused by those unfavorable factors can be alleviated efficiently in face recognition. Experimental results on the standard databases demonstrate the feasibility and efficiency of the proposed method.

  8. 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.

  9. 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.

  10. 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.

  11. 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.

  12. 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

  13. 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

  14. Refocusing a scanned laser projector for small and bright images: simultaneously controlling the profile of the laser beam and the boundary of the image.

    Science.gov (United States)

    Horvath, Samantha; Galeotti, John; Siegel, Mel; Stetten, George

    2014-08-20

    This paper describes a projection system for augmenting a scanned laser projector to create very small, very bright images for use in a microsurgical augmented reality system. Normal optical design approaches are insufficient because the laser beam profile differs optically from the aggregate image. We propose a novel arrangement of two lens groups working together to simultaneously adjust both the laser beam of the projector (individual pixels) and the spatial envelope containing them (the entire image) to the desired sizes. The present work models such a system using paraxial beam equations and ideal lenses to demonstrate that there is an "in-focus" range, or depth of field, defined by the intersection of the resulting beam-waist radius curve and the ideal pixel radius for a given image size. Images within this depth of field are in focus and can be adjusted to the desired size by manipulating the lenses.

  15. 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.

  16. Hybrid edge and feature-based single-image superresolution

    Science.gov (United States)

    Islam, Mohammad Moinul; Islam, Mohammed Nazrul; Asari, Vijayan K.; Karim, Mohammad A.

    2016-07-01

    A neighborhood-dependent component feature learning method for regression analysis in single-image superresolution is presented. Given a low-resolution input, the method uses a directional Fourier phase feature component to adaptively learn the regression kernel based on local covariance to estimate the high-resolution image. The unique feature of the proposed method is that it uses image features to learn about the local covariance from geometric similarity between the low-resolution image and its high-resolution counterpart. For each patch in the neighborhood, we estimate four directional variances to adapt the interpolated pixels. This gives us edge information and Fourier phase gives features, which are combined to interpolate using kernel regression. In order to compare quantitatively with other state-of-the-art techniques, root-mean-square error and measure mean-square similarity are computed for the example images, and experimental results show that the proposed algorithm outperforms similar techniques available in the literature, especially at higher resolution scales.

  17. 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.

  18. 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.

  19. 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.

  20. 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...

  1. Hdr Imaging for Feature Detection on Detailed Architectural Scenes

    Science.gov (United States)

    Kontogianni, G.; Stathopoulou, E. K.; Georgopoulos, A.; Doulamis, A.

    2015-02-01

    3D reconstruction relies on accurate detection, extraction, description and matching of image features. This is even truer for complex architectural scenes that pose needs for 3D models of high quality, without any loss of detail in geometry or color. Illumination conditions influence the radiometric quality of images, as standard sensors cannot depict properly a wide range of intensities in the same scene. Indeed, overexposed or underexposed pixels cause irreplaceable information loss and degrade digital representation. Images taken under extreme lighting environments may be thus prohibitive for feature detection/extraction and consequently for matching and 3D reconstruction. High Dynamic Range (HDR) images could be helpful for these operators because they broaden the limits of illumination range that Standard or Low Dynamic Range (SDR/LDR) images can capture and increase in this way the amount of details contained in the image. Experimental results of this study prove this assumption as they examine state of the art feature detectors applied both on standard dynamic range and HDR images.

  2. HDR IMAGING FOR FEATURE DETECTION ON DETAILED ARCHITECTURAL SCENES

    Directory of Open Access Journals (Sweden)

    G. Kontogianni

    2015-02-01

    Full Text Available 3D reconstruction relies on accurate detection, extraction, description and matching of image features. This is even truer for complex architectural scenes that pose needs for 3D models of high quality, without any loss of detail in geometry or color. Illumination conditions influence the radiometric quality of images, as standard sensors cannot depict properly a wide range of intensities in the same scene. Indeed, overexposed or underexposed pixels cause irreplaceable information loss and degrade digital representation. Images taken under extreme lighting environments may be thus prohibitive for feature detection/extraction and consequently for matching and 3D reconstruction. High Dynamic Range (HDR images could be helpful for these operators because they broaden the limits of illumination range that Standard or Low Dynamic Range (SDR/LDR images can capture and increase in this way the amount of details contained in the image. Experimental results of this study prove this assumption as they examine state of the art feature detectors applied both on standard dynamic range and HDR images.

  3. 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.

  4. 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.

  5. 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.

  6. Feature extraction with LIDAR data and aerial images

    Science.gov (United States)

    Mao, Jianhua; Liu, Yanjing; Cheng, Penggen; Li, Xianhua; Zeng, Qihong; Xia, Jing

    2006-10-01

    Raw LIDAR data is a irregular spacing 3D point cloud including reflections from bare ground, buildings, vegetation and vehicles etc., and the first task of the data analyses of point cloud is feature extraction. However, the interpretability of LIDAR point cloud is often limited due to the fact that no object information is provided, and the complex earth topography and object morphology make it impossible for a single operator to classify all the point cloud precisely 100%. In this paper, a hierarchy method for feature extraction with LIDAR data and aerial images is discussed. The aerial images provide us information of objects figuration and spatial distribution, and hierarchic classification of features makes it easy to apply automatic filters progressively. And the experiment results show that, using this method, it was possible to detect more object information and get a better result of feature extraction than using automatic filters alone.

  7. Feature element theory for image recognition and retrieval

    Science.gov (United States)

    Xu, Yin; Zhang, Yujin

    2001-12-01

    Traditional systems of image retrieval work as black boxes. The concrete process and result data or coefficients are not the real care point. Thus it brings the problem: these systems cannot fulfill general semantic application. To overcome the problem we turn to psychology and neuroscience to study the cognition mechanism of human brain. Based on the analysis of experiments and evidences, a new hypothesis - element presence theory is proposed to explain the truth of the whole visual cognition. As its basic level that deals with low-level feature data from camera or retina, feature element theory is illustrated in details. Besides, the evaluation on feature elements is discussed and the illustration on feature element theory based image retrieval system is also given.

  8. 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.

  9. Ultra-fast bright field and fluorescence imaging of the dynamics of micrometer-sized objects

    NARCIS (Netherlands)

    Chen, X.C.; Wang, J.J.; Versluis, M.; Jong, de N.; Villanueva, F.S.

    2013-01-01

    High speed imaging has application in a wide area of industry and scientific research. In medical research, high speed imaging has the potential to reveal insight into mechanisms of action of various therapeutic interventions. Examples include ultrasound assisted thrombolysis, drug delivery, and gen

  10. 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.

  11. 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.

  12. 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.

  13. 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.

  14. 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.

  15. 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

  16. Feature statistic analysis of ultrasound images of liver cancer

    Science.gov (United States)

    Huang, Shuqin; Ding, Mingyue; Zhang, Songgeng

    2007-12-01

    In this paper, a specific feature analysis of liver ultrasound images including normal liver, liver cancer especially hepatocellular carcinoma (HCC) and other hepatopathy is discussed. According to the classification of hepatocellular carcinoma (HCC), primary carcinoma is divided into four types. 15 features from single gray-level statistic, gray-level co-occurrence matrix (GLCM), and gray-level run-length matrix (GLRLM) are extracted. Experiments for the discrimination of each type of HCC, normal liver, fatty liver, angioma and hepatic abscess have been conducted. Corresponding features to potentially discriminate them are found.

  17. 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.

  18. Investigation of efficient features for image recognition by neural networks.

    Science.gov (United States)

    Goltsev, Alexander; Gritsenko, Vladimir

    2012-04-01

    In the paper, effective and simple features for image recognition (named LiRA-features) are investigated in the task of handwritten digit recognition. Two neural network classifiers are considered-a modified 3-layer perceptron LiRA and a modular assembly neural network. A method of feature selection is proposed that analyses connection weights formed in the preliminary learning process of a neural network classifier. In the experiments using the MNIST database of handwritten digits, the feature selection procedure allows reduction of feature number (from 60 000 to 7000) preserving comparable recognition capability while accelerating computations. Experimental comparison between the LiRA perceptron and the modular assembly neural network is accomplished, which shows that recognition capability of the modular assembly neural network is somewhat better.

  19. 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.

  20. Computational optical sensing and imaging: introduction to feature issue.

    Science.gov (United States)

    Gerwe, David R; Harvey, Andrew; Gehm, Michael E

    2013-04-01

    The 2012 Computational Optical Sensing and Imaging (COSI) conference of the Optical Society of America was one of six colocated meetings composing the Imaging and Applied Optics Congress held in Monterey, California, 24-28 June. COSI, together with the Imaging Systems and Applications, Optical Sensors, Applied Industrial Optics, and Optical Remote Sensing of the Environment conferences, brought together a diverse group of scientists and engineers sharing a common interest in measuring and processing of information carried by optical fields. This special feature includes several papers based on presentations given at the 2012 COSI conference as well as independent contributions, which together highlight several important trends.

  1. Two-level hierarchical feature learning for image classification

    Institute of Scientific and Technical Information of China (English)

    Guang-hui SONG; Xiao-gang JIN; Gen-lang CHEN; Yan NIE

    2016-01-01

    In some image classifi cation tasks, similarities among different categories are different and the samples are usually misclassifi ed as highly similar categories. To distinguish highly similar categories, more specifi c features are required so that the classifi er can improve the classifi cation performance. In this paper, we propose a novel two-level hierarchical feature learning framework based on the deep convolutional neural network (CNN), which is simple and effective. First, the deep feature extractors of different levels are trained using the transfer learning method that fi ne-tunes the pre-trained deep CNN model toward the new target dataset. Second, the general feature extracted from all the categories and the specifi c feature extracted from highly similar categories are fused into a feature vector. Then the fi nal feature representation is fed into a linear classifi er. Finally, experiments using the Caltech-256, Oxford Flower-102, and Tasmania Coral Point Count (CPC) datasets demonstrate that the expression ability of the deep features resulting from two-level hierarchical feature learning is powerful. Our proposed method effectively increases the classifi cation accuracy in comparison with fl at multiple classifi cation methods.

  2. 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...

  3. 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...

  4. 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

  5. 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.

  6. No-reference face image assessment based on deep features

    Science.gov (United States)

    Liu, Guirong; Xu, Yi; Lan, Jinpeng

    2016-09-01

    Face quality assessment is important to improve the performance of face recognition system. For instance, it is required to select images of good quality to improve recognition rate for the person of interest. Current methods mostly depend on traditional image assessment, which use prior knowledge of human vision system. As a result, the quality score of face images shows consistency with human vision perception but deviates from the processing procedure of a real face recognition system. It is the fact that the state-of-art face recognition systems are all built on deep neural networks. Naturally, it is expected to propose an efficient quality scoring method of face images, which should show high consistency with the recognition rate of face images from current face recognition systems. This paper proposes a non-reference face image assessment algorithm based on the deep features, which is capable of predicting the recognition rate of face images. The proposed face image assessment algorithm provides a promising tool to filter out the good input images for the real face recognition system to achieve high recognition rate.

  7. 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.

  8. Characterisation of Feature Points in Eye Fundus Images

    Science.gov (United States)

    Calvo, D.; Ortega, M.; Penedo, M. G.; Rouco, J.

    The retinal vessel tree adds decisive knowledge in the diagnosis of numerous opthalmologic pathologies such as hypertension or diabetes. One of the problems in the analysis of the retinal vessel tree is the lack of information in terms of vessels depth as the image acquisition usually leads to a 2D image. This situation provokes a scenario where two different vessels coinciding in a point could be interpreted as a vessel forking into a bifurcation. That is why, for traking and labelling the retinal vascular tree, bifurcations and crossovers of vessels are considered feature points. In this work a novel method for these retinal vessel tree feature points detection and classification is introduced. The method applies image techniques such as filters or thinning to obtain the adequate structure to detect the points and sets a classification of these points studying its environment. The methodology is tested using a standard database and the results show high classification capabilities.

  9. 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.

  10. 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.

  11. 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.

  12. 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.

  13. Image Recognition and Feature Detection in Solar Physics

    Science.gov (United States)

    Martens, Petrus C.

    2012-05-01

    The Solar Dynamics Observatory (SDO) data repository will dwarf the archives of all previous solar physics missions put together. NASA recognized early on that the traditional methods of analyzing the data -- solar scientists and grad students in particular analyzing the images by hand -- would simply not work and tasked our Feature Finding Team (FFT) with developing automated feature recognition modules for solar events and phenomena likely to be observed by SDO. Having these metadata available on-line will enable solar scientist to conduct statistical studies involving large sets of events that would be impossible now with traditional means. We have followed a two-track approach in our project: we have been developing some existing task-specific solar feature finding modules to be "pipe-line" ready for the stream of SDO data, plus we are designing a few new modules. Secondly, we took it upon us to develop an entirely new "trainable" module that would be capable of identifying different types of solar phenomena starting from a limited number of user-provided examples. Both approaches are now reaching fruition, and I will show examples and movies with results from several of our feature finding modules. In the second part of my presentation I will focus on our “trainable” module, which is the most innovative in character. First, there is the strong similarity between solar and medical X-ray images with regard to their texture, which has allowed us to apply some advances made in medical image recognition. Second, we have found that there is a strong similarity between the way our trainable module works and the way our brain recognizes images. The brain can quickly recognize similar images from key characteristics, just as our code does. We conclude from that that our approach represents the beginning of a more human-like procedure for computer image recognition.

  14. 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.

  15. 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.

  16. 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.

  17. GPU Accelerated Automated Feature Extraction From Satellite Images

    Directory of Open Access Journals (Sweden)

    K. Phani Tejaswi

    2013-04-01

    Full Text Available The availability of large volumes of remote sensing data insists on higher degree of automation in featureextraction, making it a need of thehour. Fusingdata from multiple sources, such as panchromatic,hyperspectraland LiDAR sensors, enhances the probability of identifying and extracting features such asbuildings, vegetation or bodies of water by using a combination of spectral and elevation characteristics.Utilizing theaforementioned featuresin remote sensing is impracticable in the absence ofautomation.Whileefforts are underway to reduce human intervention in data processing, this attempt alone may notsuffice. Thehuge quantum of data that needs to be processed entailsaccelerated processing to be enabled.GPUs, which were originally designed to provide efficient visualization,arebeing massively employed forcomputation intensive parallel processing environments. Image processing in general and hence automatedfeatureextraction, is highly computation intensive, where performance improvements have a direct impacton societal needs. In this context, an algorithm has been formulated for automated feature extraction froma panchromatic or multispectral image based on image processing techniques.Two Laplacian of Guassian(LoGmasks were applied on the image individually followed by detection of zero crossing points andextracting the pixels based on their standard deviationwiththe surrounding pixels. The two extractedimages with different LoG masks were combined together which resulted in an image withthe extractedfeatures and edges.Finally the user is at liberty to apply the image smoothing step depending on the noisecontent in the extracted image.The image ispassed through a hybrid median filter toremove the salt andpepper noise from the image.This paper discusses theaforesaidalgorithmforautomated featureextraction, necessity of deployment of GPUs for thesame;system-level challenges and quantifies thebenefits of integrating GPUs in such environment. The

  18. Weighted feature fusion for content-based image retrieval

    Science.gov (United States)

    Soysal, Omurhan A.; Sumer, Emre

    2016-07-01

    The feature descriptors such as SIFT (Scale Invariant Feature Transform), SURF (Speeded-up Robust Features) and ORB (Oriented FAST and Rotated BRIEF) are known as the most commonly used solutions for the content-based image retrieval problems. In this paper, a novel approach called "Weighted Feature Fusion" is proposed as a generic solution instead of applying problem-specific descriptors alone. Experiments were performed on two basic data sets of the Inria in order to improve the precision of retrieval results. It was found that in cases where the descriptors were used alone the proposed approach yielded 10-30% more accurate results than the ORB alone. Besides, it yielded 9-22% and 12-29% less False Positives compared to the SIFT alone and SURF alone, respectively.

  19. 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.

  20. 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).

  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. 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.

  3. Feature Based Correspondence: A Comparative Study on Image Matching Algorithms

    Directory of Open Access Journals (Sweden)

    Munim Tanvir

    2016-03-01

    Full Text Available Image matching and recognition are the crux of computer vision and have a major part to play in everyday lives. From industrial robots to surveillance cameras, from autonomous vehicles to medical imaging and from missile guidance to space exploration vehicles computer vision and hence image matching is embedded in our lives. This communication presents a comparative study on the prevalent matching algorithms, addressing their restrictions and providing a criterion to define the level of efficiency likely to be expected from an algorithm. The study includes the feature detection and matching techniques used by these prevalent algorithms to allow a deeper insight. The chief aim of the study is to deliver a source of comprehensive reference for the researchers involved in image matching, regardless of specific applications.

  4. Adaptive feature-specific imaging: a face recognition example.

    Science.gov (United States)

    Baheti, Pawan K; Neifeld, Mark A

    2008-04-01

    We present an adaptive feature-specific imaging (AFSI) system and consider its application to a face recognition task. The proposed system makes use of previous measurements to adapt the projection basis at each step. Using sequential hypothesis testing, we compare AFSI with static-FSI (SFSI) and static or adaptive conventional imaging in terms of the number of measurements required to achieve a specified probability of misclassification (Pe). The AFSI system exhibits significant improvement compared to SFSI and conventional imaging at low signal-to-noise ratio (SNR). It is shown that for M=4 hypotheses and desired Pe=10(-2), AFSI requires 100 times fewer measurements than the adaptive conventional imager at SNR= -20 dB. We also show a trade-off, in terms of average detection time, between measurement SNR and adaptation advantage, resulting in an optimal value of integration time (equivalent to SNR) per measurement.

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

    NARCIS (Netherlands)

    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.

    2014-01-01

    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 d

  6. 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...

  7. 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.

  8. 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.

  9. 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.

  10. 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.

  11. Imaging features of intraosseous ganglia: a report of 45 cases

    Energy Technology Data Exchange (ETDEWEB)

    Williams, H.J.; Davies, A.M.; Allen, G.; Evans, N. [Royal Orthopaedic Hospital, Department of Radiology, Birmingham (United Kingdom); Mangham, D.C. [Royal Orthopaedic Hospital, Department of Pathology, Birmingham (United Kingdom)

    2004-10-01

    The aim of this study is to report the spectrum of imaging findings of intraosseous ganglia (IG) with particular emphasis on the radiographic and magnetic resonance (MR) features. Forty-five patients with a final diagnosis of IG were referred to a specialist orthopaedic oncology service with the presumptive diagnosis of either a primary or secondary bone tumour. The diagnosis was established by histology in 25 cases. In the remainder, the imaging features were considered characteristic and the lesion was stable on follow-up radiographic examination. Radiographs were available for retrospective review in all cases and MR imaging in 29. There was a minor male preponderance with a wide adult age range. Three quarters were found in relation to the weight-bearing long bones of the lower limb, particularly round the knee. On radiographs all were juxta-articular and osteolytic; 74% were eccentric in location, 80% had a sclerotic endosteal margin and 60% of cases showed a degree of trabeculation. Periosteal new bone formation and matrix mineralization were not present. Of the 29 cases that underwent MR imaging, 66% were multiloculated. On T1-weighted images the IG contents were isointense or mildly hypointense in 90% cases. Forty-one per cent of the cases showed a slightly hyperintense rim lining that enhanced with a gadolinium chelate. Thirty-eight per cent were associated with soft tissue extension and 17% with a defect of the adjacent articular cortex. Fifty-five per cent showed surrounding marrow oedema on T2-weighted or STIR images and two cases (7%) a fluid-fluid level prior to any surgical intervention. The authors contend that it is semantics to differentiate between an IG and a degenerate subchondral cyst as, while the initial pathogenesis may vary, the histological endpoint is identical, as are the imaging features apart from the degree of associated degenerative joint disease. IGs, particularly when large, may be mistaken for a bone tumour. Correlation of the

  12. Cervical spine injury in the elderly: imaging features

    Energy Technology Data Exchange (ETDEWEB)

    Ehara, S. [Dept. of Radiology, Iwate Medical University School of Medicine, Morioka (Japan); Shimamura, Tadashi [Dept. of Orthopedic Surgery, Iwate Medical University School of Medicine, Morioka (Japan)

    2001-01-01

    An increase in the elderly population has resulted in an increased incidence of cervical spine injury in this group. No specific type of cervical spine trauma is seen in the elderly, although dens fractures are reported to be common. Hyperextension injuries due to falling and the resultant central cord syndrome in the mid and lower cervical segments due to decreased elasticity as a result of spondylosis may be also characteristic. The imaging features of cervical spine injury are often modified by associated spondylosis deformans, DISH and other systemic disorders. The value of MR imaging in such cases is emphasized. (orig.)

  13. 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...

  14. 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.

  15. Silica nanoparticles for micro-particle imaging velocimetry: fluorosurfactant improves nanoparticle stability and brightness of immobilized iridium(III) complexes.

    Science.gov (United States)

    Lewis, David J; Dore, Valentina; Rogers, Nicola J; Mole, Thomas K; Nash, Gerard B; Angeli, Panagiota; Pikramenou, Zoe

    2013-11-26

    To establish highly luminescent nanoparticles for monitoring fluid flows, we examined the preparation of silica nanoparticles based on immobilization of a cyclometalated iridium(III) complex and an examination of the photophysical studies provided a good insight into the Ir(III) microenvironment in order to reveal the most suitable silica nanoparticles for micro particle imaging velocimetry (μ-PIV) studies. Iridium complexes covalently incorporated at the surface of preformed silica nanoparticles, [Ir-4]@Si500-Z, using a fluorinated polymer during their preparation, demonstrated better stability than those without the polymer, [Ir-4]@Si500, as well as an increase in steady state photoluminescence intensity (and therefore particle brightness) and lifetimes which are increased by 7-fold compared with nanoparticles with the same metal complex attached covalently throughout their core, [Ir-4]⊂Si500. Screening of the nanoparticles in fluid flows using epi-luminescence microscopy also confirm that the brightest, and therefore most suitable particles for microparticle imaging velocimetry (μ-PIV) measurements are those with the Ir(III) complex immobilized at the surface with fluorosurfactant, that is [Ir-4]@Si500-Z. μ-PIV studies demonstrate the suitability of these nanoparticles as nanotracers in microchannels.

  16. Design Approach for Content-based Image Retrieval using Gabor-Zernike features

    Directory of Open Access Journals (Sweden)

    Abhinav Deshpande

    2012-04-01

    Full Text Available The process of extraction of different features from an image is known as Content-based Image Retrieval.Color,Texture and Shape are the major features of an image and play a vital role in the representation of an image..In this paper, a novel method is proposed to extract the region of interest(ROI from an image,prior to extraction of salient features of an image.The image is subjected to normalization so that the noise components due to Gaussian or other types of noises which are present in the image are eliminated and thesuccessfull extraction of various features of an image can be accomplished. Gabor Filters are used to extract the texture feature from an image whereas Zernike Moments can be used to extract the shape feature.The combination of Gabor feature and Zernike feature can be combined to extract Gabor-Zernike Features from an image.

  17. 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.

  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. Feature-Enhanced, Model-Based Sparse Aperture Imaging

    Science.gov (United States)

    2008-03-01

    obtain a sharp estimate of the spatial spectrum that exhibits super-resolution. We propose to use the singular value decomposition ( SVD ) of the data...application in a variety of problems, including image reconstruction and restoration [5], wavelet denoising [6], feature selection in machine learning...on the singular value decomposition ( SVD ) to combine multiple samples and the use of second-order cone programming for optimization of the resulting

  20. 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.)

  1. Photoacoustic imaging features of intraocular tumors: Retinoblastoma and uveal melanoma

    Science.gov (United States)

    Xu, Guan; Xue, Yafang; Özkurt, Zeynep Gürsel; Slimani, Naziha; Hu, Zizhong; Wang, Xueding; Xia, Kewen; Ma, Teng; Zhou, Qifa; Demirci, Hakan

    2017-01-01

    The purpose of this study is to examine the capability of photoacoustic (PA) imaging (PAI) in assessing the unique molecular and architectural features in ocular tumors. A real-time PA and ultrasonography (US) parallel imaging system based on a research US platform was developed to examine retinoblastoma in mice in vivo and human retinoblastoma and uveal melanoma ex vivo. PA signals were generated by optical illumination at 720, 750, 800, 850, 900 and 950 nm delivered through a fiber optical bundle. The optical absorption spectra of the tumors were derived from the PA images. The optical absorption spectrum of each tumor was quantified by fitting to a polynomial model. The microscopic architectures of the tumors were quantified by frequency domain analysis of the PA signals. Both the optical spectral and architectural features agree with the histological findings of the tumors. The mouse and human retinoblastoma showed comparable total optical absorption spectra at a correlation of 0.95 (p<0.005). The quantitative PAI features of human retinoblastoma and uveal melanoma have shown statistically significant difference in two tailed t-tests (p<0.05). Fully compatible with the concurrent procedures, PAI could be a potential tool complementary to other diagnostic modalities for characterizing intraocular tumors. PMID:28231293

  2. 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.

  3. Variations in the Bivariate Brightness Distribution with different galaxy types

    CERN Document Server

    Cross, N; Lemon, D; Liske, J; Cross, Nicholas; Driver, Simon; Lemon, David; Liske, Jochen

    2002-01-01

    We present Bivariate Brightness Distributions (BBDs) for four spectral types discriminated by the 2dFGRS. We discuss the photometry and completeness of the 2dFGRS using a deep, wide-field CCD imaging survey. We find that there is a strong luminosity-surface brightness correlation amongst galaxies with medium to strong emission features, with gradient $\\beta_{\\mu}=0.25\\pm0.05$ and width $\\sigma_{\\mu}=0.56\\pm0.01$. Strong absorption line galaxies, show a bimodal distribution, with no correlation between luminosity and surface brightness.

  4. FEATURE EXTRACTION OF RETINAL IMAGE FOR DIAGNOSIS OF ABNORMAL EYES

    Directory of Open Access Journals (Sweden)

    S. Praveenkumar

    2011-05-01

    Full Text Available Currently, medical image processing draws intense interests of scien- tists and physicians to aid in clinical diagnosis. The retinal Fundus image is widely used in the diagnosis and treatment of various eye diseases such as Diabetic Retinopathy, glaucoma etc. If these diseases are detected and treated early, many of the visual losses can be pre- vented. This paper presents the methods to detect main features of Fundus images such as optic disk, fovea, exudates and blood vessels. To determine the optic Disk and its centre we find the brightest part of the Fundus. The candidate region of fovea is defined an area circle. The detection of fovea is done by using its spatial relationship with optic disk. Exudates are found using their high grey level variation and their contours are determined by means of morphological recon- struction techniques. The blood vessels are highlighted using bottom hat transform and morphological dilation after edge detection. All the enhanced features are then combined in the Fundus image for the detection of abnormalities in eye.

  5. 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.

  6. Image Watermarking Using Visual Perception Model and Statistical Features

    Directory of Open Access Journals (Sweden)

    Mrs.C.Akila

    2010-06-01

    Full Text Available This paper presents an effective method for the image watermarking using visual perception model based on statistical features in the low frequency domain. In the image watermarking community watermark resistance to geometric attacks is an important issue. Most countermeasures proposed in the literature usually focus on the problem of global affine transforms such as rotation, scaling and translation (RST, but few are resistant to challenging cropping and random bending attacks (RBAs. Normally in the case of watermarking there may be an occurrence of distortion in the form of artifacts. A visual perception model is proposed to quantify the localized tolerance to noise for arbitrary imagery which achieves the reduction of artifacts. As a result, the watermarking system provides a satisfactory performance for those content-preserving geometric deformations and image processing operations, including JPEG ompression, low pass filtering, cropping and RBAs.

  7. 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.

  8. 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.

  9. 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.

  10. 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.

  11. 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.

  12. 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...

  13. Ultra-bright emission from hexagonal boron nitride defects as a new platform for bio-imaging and bio-labelling

    Science.gov (United States)

    Elbadawi, Christopher; Tran, Trong Toan; Shimoni, Olga; Totonjian, Daniel; Lobo, Charlene J.; Grosso, Gabriele; Moon, Hyowan; Englund, Dirk R.; Ford, Michael J.; Aharonovich, Igor; Toth, Milos

    2016-12-01

    Bio-imaging requires robust ultra-bright probes without causing any toxicity to the cellular environment, maintain their stability and are chemically inert. In this work we present hexagonal boron nitride (hBN) nanoflakes which exhibit narrowband ultra-bright single photon emitters1. The emitters are optically stable at room temperature and under ambient environment. hBN has also been noted to be noncytotoxic and seen significant advances in functionalization with biomolecules2,3. We further demonstrate two methods of engineering this new range of extremely robust multicolour emitters across the visible and near infrared spectral ranges for large scale sensing and biolabeling applications.

  14. 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.

  15. Brightness temperatures of the lunar surface: Calibration and analysis of Clementine long-wave infrared camera images

    Science.gov (United States)

    Lawson, Stefanie Lyn

    2000-10-01

    This dissertation presents the calibration and analysis of the Clementine long-wave infrared (LWIR) camera images. The scientific payload on the Clementine spacecraft included a LWIR camera with a single passband centered at a wavelength of 8.75 μm. The Clementine orbit deviated by +/-30° from Sun synchronous, and for two lunar months, dayside nadir-looking images were obtained near local noon. During the systematic mapping phase of the Clementine mission, approximately 220,000 thermal-infrared images of the lunar surface were obtained. I have completed the calibration of the LWIR camera. Here I present the various steps involved in the calibration routine and the associated uncertainty analysis. The LWIR calibration routine can be outlined as follows: convert measured data number values to radiance via a calibration equation; subtract a zero-flux background image from each lunar image; divide by a flatfield frame; identify bad pixels; smooth over only bad pixels; adjust radiances to reflect the absolute calibration; and convert radiances to brightness temperatures via the Planck function. Observed LWIR radiances can be converted to brightness temperatures, which provide information on various physical properties of the lunar surface. I also present here the LWIR global data set. The LWIR data from noontime orbits demonstrate that the Lambertian temperature model of cos1/4 (i) is a fair approximation for nadir-looking temperatures, rather than the cos1/6(i) behavior observed for ground-based measurements of the full Moon. Deviations from the Lambertian model are likely due to surface roughness effects. In an effort to understand the influence of large-scale topography on remote lunar surface measurements, I constructed a model which calculates the correlation between reflectance and temperature for a macroscopically rough surface with varying albedo. In this dissertation, LWIR temperatures are directly compared to Clementine ultraviolet-visible (UVVIS) camera 750

  16. Hubble Space Telescope Imaging of Bright Galactic X-Ray Binaries in Crowded Fields

    Science.gov (United States)

    Deutsch, Eric W.; Margon, Bruce; Wachter, Stefanie; Anderson, Scott F.

    1996-01-01

    We report high spatial resolution HST imagery and photometry of three well-studied, intense Galactic X-ray binaries, X2129+470, CAL 87, and GX 17+2. All three sources exhibit important anomalies that are not readily interpreted by conventional models. Each source also lies in a severely crowded field, and in all cases the anomalies would be removed if much of the light observed from the ground in fact came from a nearby, thus far unresolved superposed companion. For V1727 Cyg (X2129+470), we find no such companion. We also present an HST FOS spectrum and broadband photometry which is consistent with a single, normal star. The supersoft LMC X-ray source CAL 87 was already known from ground-based work to have a companion separated by O.9 minutes from the optical counterpart; our HST images clearly resolve these objects and yield the discovery of an even closer, somewhat fainter additional companion. Our photometry indicates that contamination is not severe outside eclipse, where the companions only contribute 20% of the light in V, but during eclipse more than half of the V light comes from the companions. The previously determined spectral type of the CAL 87 secondary may need to be reevaluated due to this significant contamination, with consequences on inferences of the mass of the components. We find no companions to NP Ser (= X1813-14, = GX 17+2). However, for this object we point out a small but possibly significant astrometric discrepancy between the position of the optical object and that of the radio source which is the basis for the identification. This discrepancy needs to be clarified.

  17. 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

  18. 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.

  19. MRI and PET Image Fusion Using Fuzzy Logic and Image Local Features

    Directory of Open Access Journals (Sweden)

    Umer Javed

    2014-01-01

    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.

  20. Feature detection on 3D images of dental imprints

    Science.gov (United States)

    Mokhtari, Marielle; Laurendeau, Denis

    1994-09-01

    A computer vision approach for the extraction of feature points on 3D images of dental imprints is presented. The position of feature points are needed for the measurement of a set of parameters for automatic diagnosis of malocclusion problems in orthodontics. The system for the acquisition of the 3D profile of the imprint, the procedure for the detection of the interstices between teeth, and the approach for the identification of the type of tooth are described, as well as the algorithm for the reconstruction of the surface of each type of tooth. A new approach for the detection of feature points, called the watershed algorithm, is described in detail. The algorithm is a two-stage procedure which tracks the position of local minima at four different scales and produces a final map of the position of the minima. Experimental results of the application of the watershed algorithm on actual 3D images of dental imprints are presented for molars, premolars and canines. The segmentation approach for the analysis of the shape of incisors is also described in detail.

  1. A novel point cloud registration using 2D image features

    Science.gov (United States)

    Lin, Chien-Chou; Tai, Yen-Chou; Lee, Jhong-Jin; Chen, Yong-Sheng

    2017-01-01

    Since a 3D scanner only captures a scene of a 3D object at a time, a 3D registration for multi-scene is the key issue of 3D modeling. This paper presents a novel and an efficient 3D registration method based on 2D local feature matching. The proposed method transforms the point clouds into 2D bearing angle images and then uses the 2D feature based matching method, SURF, to find matching pixel pairs between two images. The corresponding points of 3D point clouds can be obtained by those pixel pairs. Since the corresponding pairs are sorted by their distance between matching features, only the top half of the corresponding pairs are used to find the optimal rotation matrix by the least squares approximation. In this paper, the optimal rotation matrix is derived by orthogonal Procrustes method (SVD-based approach). Therefore, the 3D model of an object can be reconstructed by aligning those point clouds with the optimal transformation matrix. Experimental results show that the accuracy of the proposed method is close to the ICP, but the computation cost is reduced significantly. The performance is six times faster than the generalized-ICP algorithm. Furthermore, while the ICP requires high alignment similarity of two scenes, the proposed method is robust to a larger difference of viewing angle.

  2. Sparse coding based feature representation method for remote sensing images

    Science.gov (United States)

    Oguslu, Ender

    In this dissertation, we study sparse coding based feature representation method for the classification of multispectral and hyperspectral images (HSI). The existing feature representation systems based on the sparse signal model are computationally expensive, requiring to solve a convex optimization problem to learn a dictionary. A sparse coding feature representation framework for the classification of HSI is presented that alleviates the complexity of sparse coding through sub-band construction, dictionary learning, and encoding steps. In the framework, we construct the dictionary based upon the extracted sub-bands from the spectral representation of a pixel. In the encoding step, we utilize a soft threshold function to obtain sparse feature representations for HSI. Experimental results showed that a randomly selected dictionary could be as effective as a dictionary learned from optimization. The new representation usually has a very high dimensionality requiring a lot of computational resources. In addition, the spatial information of the HSI data has not been included in the representation. Thus, we modify the framework by incorporating the spatial information of the HSI pixels and reducing the dimension of the new sparse representations. The enhanced model, called sparse coding based dense feature representation (SC-DFR), is integrated with a linear support vector machine (SVM) and a composite kernels SVM (CKSVM) classifiers to discriminate different types of land cover. We evaluated the proposed algorithm on three well known HSI datasets and compared our method to four recently developed classification methods: SVM, CKSVM, simultaneous orthogonal matching pursuit (SOMP) and image fusion and recursive filtering (IFRF). The results from the experiments showed that the proposed method can achieve better overall and average classification accuracies with a much more compact representation leading to more efficient sparse models for HSI classification. To further

  3. Hurricane Imaging Radiometer (HIRAD) Observations of Brightness Temperatures and Ocean Surface Wind Speed and Rain Rate During NASA's GRIP and HS3 Campaigns

    Science.gov (United States)

    Miller, Timothy L.; James, M. W.; Roberts, J. B.; Jones, W. L.; Biswas, S.; Ruf, C. S.; Uhlhorn, E. W.; Atlas, R.; Black, P.; Albers, C.

    2012-01-01

    HIRAD flew on high-altitude aircraft over Earl and Karl during NASA s GRIP (Genesis and Rapid Intensification Processes) campaign in August - September of 2010, and plans to fly over Atlantic tropical cyclones in September of 2012 as part of the Hurricane and Severe Storm Sentinel (HS3) mission. HIRAD is a new C-band radiometer using a synthetic thinned array radiometer (STAR) technology to obtain spatial resolution of approximately 2 km, out to roughly 30 km each side of nadir. By obtaining measurements of emissions at 4, 5, 6, and 6.6 GHz, observations of ocean surface wind speed and rain rate can be retrieved. The physical retrieval technique has been used for many years by precursor instruments, including the Stepped Frequency Microwave Radiometer (SFMR), which has been flying on the NOAA and USAF hurricane reconnaissance aircraft for several years to obtain observations within a single footprint at nadir angle. Results from the flights during the GRIP and HS3 campaigns will be shown, including images of brightness temperatures, wind speed, and rain rate. Comparisons will be made with observations from other instruments on the campaigns, for which HIRAD observations are either directly comparable or are complementary. Features such as storm eye and eye-wall, location of storm wind and rain maxima, and indications of dynamical features such as the merging of a weaker outer wind/rain maximum with the main vortex may be seen in the data. Potential impacts on operational ocean surface wind analyses and on numerical weather forecasts will also be discussed.

  4. 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

  5. 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.

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

    Directory of Open Access Journals (Sweden)

    Eu Hyun Kim

    2014-10-01

    Full Text Available

    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.

  7. 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.

  8. Feature identification for image-guided transcatheter aortic valve implantation

    Science.gov (United States)

    Lang, Pencilla; Rajchl, Martin; McLeod, A. Jonathan; Chu, Michael W.; Peters, Terry M.

    2012-02-01

    Transcatheter aortic valve implantation (TAVI) is a less invasive alternative to open-heart surgery, and is critically dependent on imaging for accurate placement of the new valve. Augmented image-guidance for TAVI can be provided by registering together intra-operative transesophageal echo (TEE) ultrasound and a model derived from pre-operative CT. Automatic contour delineation on TEE images of the aortic root is required for real-time registration. This study develops an algorithm to automatically extract contours on simultaneous cross-plane short-axis and long-axis (XPlane) TEE views, and register these features to a 3D pre-operative model. A continuous max-flow approach is used to segment the aortic root, followed by analysis of curvature to select appropriate contours for use in registration. Results demonstrate a mean contour boundary distance error of 1.3 and 2.8mm for the short and long-axis views respectively, and a mean target registration error of 5.9mm. Real-time image guidance has the potential to increase accuracy and reduce complications in TAVI.

  9. Image Retrieval based on combined features of image sub-blocks

    OpenAIRE

    Ch.Kavitha,; Dr. B.Prabhakara Rao,; Dr. A. Govardhan3

    2011-01-01

    In this paper we propose a new and efficient technique to retrieve images based on sum of the values of Local Histogram and GLCM (Gray Level Co-occurrence Matrix) texture of image sub-blocks to enhance theretrieval performance. The image is divided into sub blocks of equal size. Then the color and texture features of each sub-block are computed. Most of the image retrieval techniques used Histograms for indexing. Histograms describe global intensity distribution. They are very easy to compute...

  10. 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.

  11. Feature selection applied to ultrasound carotid images segmentation.

    Science.gov (United States)

    Rosati, Samanta; Molinari, Filippo; Balestra, Gabriella

    2011-01-01

    The automated tracing of the carotid layers on ultrasound images is complicated by noise, different morphology and pathology of the carotid artery. In this study we benchmarked four methods for feature selection on a set of variables extracted from ultrasound carotid images. The main goal was to select those parameters containing the highest amount of information useful to classify the pixels in the carotid regions they belong to. Six different classes of pixels were identified: lumen, lumen-intima interface, intima-media complex, media-adventitia interface, adventitia and adventitia far boundary. The performances of QuickReduct Algorithm (QRA), Entropy-Based Algorithm (EBR), Improved QuickReduct Algorithm (IQRA) and Genetic Algorithm (GA) were compared using Artificial Neural Networks (ANNs). All methods returned subsets with a high dependency degree, even if the average classification accuracy was about 50%. Among all classes, the best results were obtained for the lumen. Overall, the four methods for feature selection assessed in this study return comparable results. Despite the need for accuracy improvement, this study could be useful to build a pre-classifier stage for the optimization of segmentation performance in ultrasound automated carotid segmentation.

  12. 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.

  13. Analysis and Reliability Performance Comparison of Different Facial Image Features

    Directory of Open Access Journals (Sweden)

    J. Madhavan

    2014-11-01

    Full Text Available This study performs reliability analysis on the different facial features with weighted retrieval accuracy on increasing facial database images. There are many methods analyzed in the existing papers with constant facial databases mentioned in the literature review. There were not much work carried out to study the performance in terms of reliability and also how the method will perform on increasing the size of the database. In this study certain feature extraction methods were analyzed on the regular performance measure and also the performance measures are modified to fit the real time requirements by giving weight ages for the closer matches. In this study four facial feature extraction methods are performed, they are DWT with PCA, LWT with PCA, HMM with SVD and Gabor wavelet with HMM. Reliability of these methods are analyzed and reported. Among all these methods Gabor wavelet with HMM gives more reliability than other three methods performed. Experiments are carried out to evaluate the proposed approach on the Olivetti Research Laboratory (ORL face database.

  14. 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.

  15. Schizencephaly: clinical and imaging features in 30 infantile cases.

    Science.gov (United States)

    Denis, D; Chateil, J F; Brun, M; Brissaud, O; Lacombe, D; Fontan, D; Flurin, V; Pedespan, J

    2000-12-01

    Schizencephaly is an uncommon structural disorder of cerebral cortical development, characterized by congenital clefts spanning the cerebral hemispheres from the pial surface to the lateral ventricles and lined by cortical gray matter. Either an antenatal environmental incident or a genetic origin could be responsible for this lesion which occurs between the third and fourth month of gestation. We report the clinical and cranial imaging features of 30 children, of whom 15 had unilateral and 15 had bilateral lesions. Their ages at the time of the first presentation ranged from 1 month to 10 years. They were thoroughly studied from clinical, epileptical, imaging and electroencephalographic (EEG) viewpoints. Five patients were investigated by cranial computed tomography (CT), eight by cranial magnetic resonance (MR) imaging, and 17 by both methods. The clinical features consisted of mild hemiparesis in 17 cases (57%), 12/17 were related to a unilateral phenotype (80% of all unilateral forms) and 5/17 to a bilateral phenotype. A tetraparesis was present in nine cases, all of which were due to a bilateral cleft. Bilateral forms were significantly associated with tetraparesis, whereas unilateral forms were associated with hemiparesis. Mental retardation was observed in 17 cases (57%), and was observed significantly more often in bilateral clefts (80%). When both hemispheres are involved, an absence of reorganization of the brain function between the two hemispheres leads to severe mental deficits, in addition to the cerebral anomaly itself. Eleven patients had seizures (seven from unilateral and three from bilateral forms). The degree of malformation was not related to the severity of epilepsy. Migration disorders, such as dysplasia or heterotopia, were observed in 30% of cases and are also important etiopathogenetic factors. The septum pellucidum was absent in 13 cases (43%), with septo-optical dysplasia in two cases. Corpus callosum dysgenesis was noted in 30% of cases

  16. 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.

  17. Cystic synovial sarcomas: imaging features with clinical and histopathologic correlation

    Energy Technology Data Exchange (ETDEWEB)

    Nakanishi, Hirofumi; Araki, Nobuhito [Department of Orthopedic Surgery, Osaka Medical Center for Cancer and Cardiovascular Diseases, 1-3-3, Nakamichi, Higashinari-Ku, 537-8511, Osaka (Japan); Sawai, Yuka [Department of Radiology, Osaka Medical Center for Cancer and Cardiovascular Diseases, Osaka (Japan); Kudawara, Ikuo [Department of Orthopedic Surgery, Osaka National Hospital, Osaka (Japan); Mano, Masayuki; Ishiguro, Shingo [Department of Pathology, Osaka Medical Center for Cancer and Cardiovascular Diseases, Osaka (Japan); Ueda, Takafumi; Yoshikawa, Hideki [Department of Orthopedic Surgery, Osaka University Graduate School of Medicine, Suita, Osaka (Japan)

    2003-12-01

    To characterize the radiological and clinicopathologic features of cystic synovial sarcoma. Seven patients with primary cystic synovial sarcoma were evaluated. Computed tomography (CT) and magnetic resonance (MR) imaging were undertaken at the first presentation. The diagnosis of synovial sarcoma was made on the basis of histological examinations followed by molecular analysis. Radiological and clinicopathologic findings were reviewed. CT showed well-defined soft tissue mass without cortical bone erosion and invasion. Calcification was seen at the periphery of the mass in three cases. T2-weighted MR images showed multilocular inhomogeneous intensity mass in all cases, five of which showed fluid-fluid levels. On gross appearance, old and/or fresh hematomas were detected in six cases. In the one remaining case, microscopic hemorrhage in the cystic lumen was proven. Four cases had poorly differentiated areas. In five cases prominent hemangiopericytomatous vasculature was observed. Histologic grade was intermediate in one tumor and high in six. One case had a history of misdiagnosis for tarsal tunnel syndrome, one for lymphadenopathy, two for sciatica and two for hematoma. All cystic synovial sarcomas demonstrated multilocularity with well-circumscribed walls and internal septae. Synovial sarcoma should be taken into consideration in patients with deeply situated multicystic mass with triple signal intensity on T2-weighted MR imaging. (orig.)

  18. SU-E-J-237: Image Feature Based DRR and Portal Image Registration

    Energy Technology Data Exchange (ETDEWEB)

    Wang, X; Chang, J [NY Weill Cornell Medical Ctr, NY (United States)

    2014-06-01

    Purpose: Two-dimensional (2D) matching of the kV X-ray and digitally reconstructed radiography (DRR) images is an important setup technique for image-guided radiotherapy (IGRT). In our clinics, mutual information based methods are used for this purpose on commercial linear accelerators, but with often needs for manual corrections. This work proved the feasibility that feature based image transform can be used to register kV and DRR images. Methods: The scale invariant feature transform (SIFT) method was implemented to detect the matching image details (or key points) between the kV and DRR images. These key points represent high image intensity gradients, and thus the scale invariant features. Due to the poor image contrast from our kV image, direct application of the SIFT method yielded many detection errors. To assist the finding of key points, the center coordinates of the kV and DRR images were read from the DICOM header, and the two groups of key points with similar relative positions to their corresponding centers were paired up. Using these points, a rigid transform (with scaling, horizontal and vertical shifts) was estimated. We also artificially introduced vertical and horizontal shifts to test the accuracy of our registration method on anterior-posterior (AP) and lateral pelvic images. Results: The results provided a satisfactory overlay of the transformed kV onto the DRR image. The introduced vs. detected shifts were fit into a linear regression. In the AP image experiments, linear regression analysis showed a slope of 1.15 and 0.98 with an R2 of 0.89 and 0.99 for the horizontal and vertical shifts, respectively. The results are 1.2 and 1.3 with R2 of 0.72 and 0.82 for the lateral image shifts. Conclusion: This work provided an alternative technique for kV to DRR alignment. Further improvements in the estimation accuracy and image contrast tolerance are underway.

  19. 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).

  20. 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.

  1. 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.

  2. 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.

  3. 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

  4. 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.

  5. Histological Image Feature Mining Reveals Emergent Diagnostic Properties for Renal Cancer.

    Science.gov (United States)

    Kothari, Sonal; Phan, John H; Young, Andrew N; Wang, May D

    2011-11-01

    Computer-aided histological image classification systems are important for making objective and timely cancer diagnostic decisions. These systems use combinations of image features that quantify a variety of image properties. Because researchers tend to validate their diagnostic systems on specific cancer endpoints, it is difficult to predict which image features will perform well given a new cancer endpoint. In this paper, we define a comprehensive set of common image features (consisting of 12 distinct feature subsets) that quantify a variety of image properties. We use a data-mining approach to determine which feature subsets and image properties emerge as part of an "optimal" diagnostic model when applied to specific cancer endpoints. Our goal is to assess the performance of such comprehensive image feature sets for application to a wide variety of diagnostic problems. We perform this study on 12 endpoints including 6 renal tumor subtype endpoints and 6 renal cancer grade endpoints. Keywords-histology, image mining, computer-aided diagnosis.

  6. 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.

  7. Feature Extraction in Sequential Multimedia Images: with Applications in Satellite Images and On-line Videos

    Science.gov (United States)

    Liang, Yu-Li

    Multimedia data is increasingly important in scientific discovery and people's daily lives. Content of massive multimedia is often diverse and noisy, and motion between frames is sometimes crucial in analyzing those data. Among all, still images and videos are commonly used formats. Images are compact in size but do not contain motion information. Videos record motion but are sometimes too big to be analyzed. Sequential images, which are a set of continuous images with low frame rate, stand out because they are smaller than videos and still maintain motion information. This thesis investigates features in different types of noisy sequential images, and the proposed solutions that intelligently combined multiple features to successfully retrieve visual information from on-line videos and cloudy satellite images. The first task is detecting supraglacial lakes above ice sheet in sequential satellite images. The dynamics of supraglacial lakes on the Greenland ice sheet deeply affect glacier movement, which is directly related to sea level rise and global environment change. Detecting lakes above ice is suffering from diverse image qualities and unexpected clouds. A new method is proposed to efficiently extract prominent lake candidates with irregular shapes, heterogeneous backgrounds, and in cloudy images. The proposed system fully automatize the procedure that track lakes with high accuracy. We further cooperated with geoscientists to examine the tracked lakes and found new scientific findings. The second one is detecting obscene content in on-line video chat services, such as Chatroulette, that randomly match pairs of users in video chat sessions. A big problem encountered in such systems is the presence of flashers and obscene content. Because of various obscene content and unstable qualities of videos capture by home web-camera, detecting misbehaving users is a highly challenging task. We propose SafeVchat, which is the first solution that achieves satisfactory

  8. 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.

  9. 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.

  10. Multi-scale contrast enhancement of oriented features in 2D images using directional morphology

    Science.gov (United States)

    Das, Debashis; Mukhopadhyay, Susanta; Praveen, S. R. Sai

    2017-01-01

    This paper presents a multi-scale contrast enhancement scheme for improving the visual quality of directional features present in 2D gray scale images. Directional morphological filters are employed to locate and extract the scale-specific image features with different orientations which are subsequently stored in a set of feature images. The final enhanced image is constructed by weighted combination of these feature images with the original image. While construction, the feature images corresponding to progressively smaller scales are made to have higher proportion of contribution through the use of progressively larger weights. The proposed method has been formulated, implemented and executed on a set of real 2D gray scale images with oriented features. The experimental results visually establish the efficacy of the method. The proposed method has been compared with other similar methods both on subjective and objective basis and the overall performance is found to be satisfactory.

  11. Two-level evaluation on sensor interoperability of features in fingerprint image segmentation.

    Science.gov (United States)

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

    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, 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.

  12. Segmentation and classification of medical images using texture-primitive features: Application of BAM-type artificial neural network.

    Science.gov (United States)

    Sharma, Neeraj; Ray, Amit K; Sharma, Shiru; Shukla, K K; Pradhan, Satyajit; Aggarwal, Lalit M

    2008-07-01

    The objective of developing this software is to achieve auto-segmentation and tissue characterization. Therefore, the present algorithm has been designed and developed for analysis of medical images based on hybridization of syntactic and statistical approaches, using artificial neural network (ANN). This algorithm performs segmentation and classification as is done in human vision system, which recognizes objects; perceives depth; identifies different textures, curved surfaces, or a surface inclination by texture information and brightness. The analysis of medical image is directly based on four steps: 1) image filtering, 2) segmentation, 3) feature extraction, and 4) analysis of extracted features by pattern recognition system or classifier. In this paper, an attempt has been made to present an approach for soft tissue characterization utilizing texture-primitive features with ANN as segmentation and classifier tool. The present approach directly combines second, third, and fourth steps into one algorithm. This is a semisupervised approach in which supervision is involved only at the level of defining texture-primitive cell; afterwards, algorithm itself scans the whole image and performs the segmentation and classification in unsupervised mode. The algorithm was first tested on Markov textures, and the success rate achieved in classification was 100%; further, the algorithm was able to give results on the test images impregnated with distorted Markov texture cell. In addition to this, the output also indicated the level of distortion in distorted Markov texture cell as compared to standard Markov texture cell. Finally, algorithm was applied to selected medical images for segmentation and classification. Results were in agreement with those with manual segmentation and were clinically correlated.

  13. Segmentation and classification of medical images using texture-primitive features: Application of BAM-type artificial neural network

    Directory of Open Access Journals (Sweden)

    Sharma Neeraj

    2008-01-01

    Full Text Available The objective of developing this software is to achieve auto-segmentation and tissue characterization. Therefore, the present algorithm has been designed and developed for analysis of medical images based on hybridization of syntactic and statistical approaches, using artificial neural network (ANN. This algorithm performs segmentation and classification as is done in human vision system, which recognizes objects; perceives depth; identifies different textures, curved surfaces, or a surface inclination by texture information and brightness. The analysis of medical image is directly based on four steps: 1 image filtering, 2 segmentation, 3 feature extraction, and 4 analysis of extracted features by pattern recognition system or classifier. In this paper, an attempt has been made to present an approach for soft tissue characterization utilizing texture-primitive features with ANN as segmentation and classifier tool. The present approach directly combines second, third, and fourth steps into one algorithm. This is a semisupervised approach in which supervision is involved only at the level of defining texture-primitive cell; afterwards, algorithm itself scans the whole image and performs the segmentation and classification in unsupervised mode. The algorithm was first tested on Markov textures, and the success rate achieved in classification was 100%; further, the algorithm was able to give results on the test images impregnated with distorted Markov texture cell. In addition to this, the output also indicated the level of distortion in distorted Markov texture cell as compared to standard Markov texture cell. Finally, algorithm was applied to selected medical images for segmentation and classification. Results were in agreement with those with manual segmentation and were clinically correlated.

  14. 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.

  15. 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.

  16. 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.

  17. 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.

  18. 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.…

  19. 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

  20. Magnetic resonance imaging features of asymptomatic bipartite patella

    Energy Technology Data Exchange (ETDEWEB)

    O' Brien, J., E-mail: juliemobrien@gmail.com [Department of Radiology, Adelaide and Meath Incorporating National Children' s Hospital, Tallaght, Dublin 24 (Ireland); Murphy, C.; Halpenny, D.; McNeill, G.; Torreggiani, W.C. [Department of Radiology, Adelaide and Meath Incorporating National Children' s Hospital, Tallaght, Dublin 24 (Ireland)

    2011-06-15

    Objective: The purpose of our study was to describe the magnetic resonance imaging (MRI) features of bipartite patella in asymptomatic patients. Materials and methods: The study was prospective in type and performed following institutional ethical committees approval. In total, 25 subjects were recruited into the study and informed consent obtained in each case. The local radiology database was utilised in conjunction with a clinical questionnaire to identify patients who had asymptomatic bipartite patella. Any patient with a history of trauma or symptomatic disease was excluded from the study. MRI imaging was performed in each case on a 1.5 T system using a dedicated knee coil and a standardised knee protocol. The images obtained were then analysed by two musculoskeletal radiologists in consensus. Results: Of the 25 subjects, there were 8 females and 17 males. The mean age was 34.6 years. All but one of the bipartite fragments were located on the superolateral aspect of the patella. In 23 cases, one fragment was identified. The average transverse diameter of the fragment was 12.8 mm. The average distance between the fragment and the adjacent patella in the axial plane was 1.46 mm. In addition, the cartilage overlying the patella and accessory fragment was intact in all cases. The average thickness of the patella cartilage at its border to the fragment was 2.4 mm with an average ratio of the cartilage thickness of the fragment as compared with the cartilage thickness of the patella of 0.72. There was no evidence of high signal or bone marrow oedema on fluid sensitive sequences within either the patella or the fragment in any of the patients. Fluid was identified in the cleft between the patella and the fragment in the majority of cases. Conclusions: Asymptomatic bipartite patella is characterised by intact but thinned cartilage along the border between the patella and the fragment, fluid between the cleft and a lack of any bone marrow oedema or high signal within

  1. A Novel Feature Extraction Scheme for Medical X-Ray Images

    OpenAIRE

    Prachi.G.Bhende; Dr.A.N.Cheeran

    2016-01-01

    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 obje...

  2. 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%.

  3. 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.

  4. 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.

  5. 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.

  6. 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.

  7. Retrieving soil surface temperature under snowpack using special sensor microwave/imager brightness temperature in forested areas of Heilongjiang, China: an improved method

    Science.gov (United States)

    Zheng, Xingming; Li, Xiaofeng; Jiang, Tao; Ding, Yanling; Wu, Lili; Zhang, Shiyi; Zhao, Kai

    2016-04-01

    Soil surface temperature (Ts) is an important indicator of global temperature change and a key input parameter for retrieving land surface variables using remote sensing techniques. Due to the masking in the thermal infrared band and the scattering in the microwave band of snow, the temperature of soil surfaces covered by snow is difficult to infer from remote sensing data. We attempted to estimate Ts under snow cover using brightness temperature data from the special sensor microwave/imager. Ts under snow cover was underestimated due to the strong scattering effect of snow on upward soil microwave emissions at 37 GHz. The underestimated portion of Ts is related to snow properties, such as depth, grain size, and moisture. Based on the microwave emission model of layered snowpacks, the simulated results revealed a linear relationship between the underestimated Ts and the brightness temperature difference (TBD) at 19 and 37 GHz. When TBDs at 19 and 37 GHz were introduced to the Ts estimation method, accuracy improved, i.e., the root mean square error and bias of the estimated Ts decreased greatly, especially for dry snow. This improvement allows Ts estimation of snow-covered surfaces from 37 GHz microwave brightness temperature.

  8. Image mining and Automatic Feature extraction from Remotely Sensed Image (RSI using Cubical Distance Methods

    Directory of Open Access Journals (Sweden)

    S.Sasikala

    2013-04-01

    Full Text Available Information processing and decision support system using image mining techniques is in advance drive with huge availability of remote sensing image (RSI. RSI describes inherent properties of objects by recording their natural reflectance in the electro-magnetic spectral (ems region. Information on such objects could be gathered by their color properties or their spectral values in various ems range in the form of pixels. Present paper explains a method of such information extraction using cubical distance method and subsequent results. Thismethod is one among the simpler in its approach and considers grouping of pixels on the basis of equal distance from a specified point in the image or selected pixel having definite attribute values (DN in different spectral layers of the RSI. The color distance and the occurrence pixel distance play a vital role in determining similarobjects as clusters aid in extracting features in the RSI domain.

  9. 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.

  10. 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...

  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. Performance Evaluation of Content Based Image Retrieval on Feature Optimization and Selection Using Swarm Intelligence

    Directory of Open Access Journals (Sweden)

    Kirti Jain

    2016-03-01

    Full Text Available The diversity and applicability of swarm intelligence is increasing everyday in the fields of science and engineering. Swarm intelligence gives the features of the dynamic features optimization concept. We have used swarm intelligence for the process of feature optimization and feature selection for content-based image retrieval. The performance of content-based image retrieval faced the problem of precision and recall. The value of precision and recall depends on the retrieval capacity of the image. The basic raw image content has visual features such as color, texture, shape and size. The partial feature extraction technique is based on geometric invariant function. Three swarm intelligence algorithms were used for the optimization of features: ant colony optimization, particle swarm optimization (PSO, and glowworm optimization algorithm. Coral image dataset and MatLab software were used for evaluating performance.

  13. FEATURE DIMENSION REDUCTION FOR EFFICIENT MEDICAL IMAGE RETRIEVAL SYSTEM USING UNIFIED FRAMEWORK

    Directory of Open Access Journals (Sweden)

    Yogapriya Jaganathan

    2013-01-01

    Full Text Available Feature dimensionality reduction problem is a major issue in Content Based Medical Image Retrieval (CBMIR for the effective management of medical images with the support of visual features for the purpose of diagnosis and educational research field. However, high dimensional features would be an origin for substantial challenges in retrieval. The proposed CBMIR is used a unified approach based on extraction of visual features, optimized feature selection, classification of optimized features and similarity measurements. However, high dimensional features would be an origin for substantial challenges in retrieval. The Texture features are selected using Gray Level Co-occurrence Matrix (GLCM, Tamura Features (TF and Gabor Filter (GF in which pull out of features are formed a feature vector database. Fuzzy based PSO (FPSO is applied for Feature selection to overcome the difficulty of feature vectors being surrounded in local optima of original PSO. This procedure also integrates a smart policymaking structure of ACO procedure into the novel FPSO where the global optimum position to be exclusive for every feature particle. The Fuzzy based Particle Swarm Optimization and Ant Colony Optimization (FPSO-ACO technique is used to trim down the feature vector dimensionality and classification is accomplished using an extensive Fuzzy based Relevance Vector Machine (FRVM to form collections of relevant image features that would provide an accepted way to classify dimensionally concentrated feature vectors of images. The Euclidean Distance (ED is recognized as finest for similarity measurement between the medical query image and the medical image database. This proposed approach can acquire the query from the user and had retrieved the desired images from the database. The retrieval performance would be assessed based on precision and recall. This proposed CBMIR is used to provide comfort to the physician to obtain more assurance in their decisions for

  14. 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.

  15. Medical Image Fusion Algorithm Based on Nonlinear Approximation of Contourlet Transform and Regional Features

    Directory of Open Access Journals (Sweden)

    Hui Huang

    2017-01-01

    Full Text Available According to the pros and cons of contourlet transform and multimodality medical imaging, here we propose a novel image fusion algorithm that combines nonlinear approximation of contourlet transform with image regional features. The most important coefficient bands of the contourlet sparse matrix are retained by nonlinear approximation. Low-frequency and high-frequency regional features are also elaborated to fuse medical images. The results strongly suggested that the proposed algorithm could improve the visual effects of medical image fusion and image quality, image denoising, and enhancement.

  16. Cardiac tumors: CT and MR imaging features; Tumeurs cardiaques: aspects en scanner et en IRM

    Energy Technology Data Exchange (ETDEWEB)

    Moskovitch, G.; Chabbert, V.; Escourrou, G.; Desloques, L.; Otal, P.; Glock, Y.; Rousseau, H. [Centre Hospitalier Universitaire de Rangueil, Service de Radiologie Generale, 31 - Toulouse (France)

    2010-09-15

    The CT and MR imaging features of the main cardiac tumors will be reviewed. Cross-sectional imaging features may help differentiate between cardiac tumors and pseudo-tumoral lesions and identify malignant features. Based on clinical features, imaging findings are helpful to further characterize the nature of the lesion. CT and MR imaging can demonstrate the relationship of the tumor with adjacent anatomical structures and are invaluable in the pre-surgical work-up and post-surgical follow-up. (authors)

  17. Importance of the texture features in a query from a spectral image database

    Science.gov (United States)

    Kohonen, Oili; Hauta-Kasari, Markku

    2006-01-01

    A new, semantically meaningful technique for querying the images from a spectral image database is proposed. The technique is based on the use of both color- and texture features. The color features are calculated from spectral images by using the Self-Organizing Map (SOM) when methods of Gray Level Co-occurrence Matrix (GLCM) and Local Binary Pattern (LBP) are used for constructing the texture features. The importance of texture features in a querying is seen in experimental results, which are given by using a real spectral image database. Also the differences between the results gained by the use of co-occurrence matrix and LBP are introduced.

  18. Emotional textile image classification based on cross-domain convolutional sparse autoencoders with feature selection

    Science.gov (United States)

    Li, Zuhe; Fan, Yangyu; Liu, Weihua; Yu, Zeqi; Wang, Fengqin

    2017-01-01

    We aim to apply sparse autoencoder-based unsupervised feature learning to emotional semantic analysis for textile images. To tackle the problem of limited training data, we present a cross-domain feature learning scheme for emotional textile image classification using convolutional autoencoders. We further propose a correlation-analysis-based feature selection method for the weights learned by sparse autoencoders to reduce the number of features extracted from large size images. First, we randomly collect image patches on an unlabeled image dataset in the source domain and learn local features with a sparse autoencoder. We then conduct feature selection according to the correlation between different weight vectors corresponding to the autoencoder's hidden units. We finally adopt a convolutional neural network including a pooling layer to obtain global feature activations of textile images in the target domain and send these global feature vectors into logistic regression models for emotional image classification. The cross-domain unsupervised feature learning method achieves 65% to 78% average accuracy in the cross-validation experiments corresponding to eight emotional categories and performs better than conventional methods. Feature selection can reduce the computational cost of global feature extraction by about 50% while improving classification performance.

  19. [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.

  20. 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.

  1. Age Estimation Based on AAM and 2D-DCT Features of Facial Images

    Directory of Open Access Journals (Sweden)

    Asuman Günay

    2015-02-01

    Full Text Available This paper proposes a novel age estimation method - Global and Local feAture based Age estiMation (GLAAM - relying on global and local features of facial images. Global features are obtained with Active Appearance Models (AAM. Local features are extracted with regional 2D-DCT (2- dimensional Discrete Cosine Transform of normalized facial images. GLAAM consists of the following modules: face normalization, global feature extraction with AAM, local feature extraction with 2D-DCT, dimensionality reduction by means of Principal Component Analysis (PCA and age estimation with multiple linear regression. Experiments have shown that GLAAM outperforms many methods previously applied to the FG-NET database.

  2. 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.

  3. Discriminative feature representation: an effective postprocessing solution to low dose CT imaging

    Science.gov (United States)

    Chen, Yang; Liu, Jin; Hu, Yining; Yang, Jian; Shi, Luyao; Shu, Huazhong; Gui, Zhiguo; Coatrieux, Gouenou; Luo, Limin

    2017-03-01

    This paper proposes a concise and effective approach termed discriminative feature representation (DFR) for low dose computerized tomography (LDCT) image processing, which is currently a challenging problem in medical imaging field. This DFR method assumes LDCT images as the superposition of desirable high dose CT (HDCT) 3D features and undesirable noise-artifact 3D features (the combined term of noise and artifact features induced by low dose scan protocols), and the decomposed HDCT features are used to provide the processed LDCT images with higher quality. The target HDCT features are solved via the DFR algorithm using a featured dictionary composed by atoms representing HDCT features and noise-artifact features. In this study, the featured dictionary is efficiently built using physical phantom images collected from the same CT scanner as the target clinical LDCT images to process. The proposed DFR method also has good robustness in parameter setting for different CT scanner types. This DFR method can be directly applied to process DICOM formatted LDCT images, and has good applicability to current CT systems. Comparative experiments with abdomen LDCT data validate the good performance of the proposed approach. This research was supported by National Natural Science Foundation under grants (81370040, 81530060), the Fundamental Research Funds for the Central Universities, and the Qing Lan Project in Jiangsu Province.

  4. 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.

  5. 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.

  6. 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.

  7. 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.

  8. 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.

  9. 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.

  10. 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.

  11. 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.

  12. 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

  13. 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.

  14. 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

  15. 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

  16. 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

  17. Fuzzy zoning for feature matching technique in 3D reconstruction of nasal endoscopic images.

    Science.gov (United States)

    Rattanalappaiboon, Surapong; Bhongmakapat, Thongchai; Ritthipravat, Panrasee

    2015-12-01

    3D reconstruction from nasal endoscopic images greatly supports an otolaryngologist in examining nasal passages, mucosa, polyps, sinuses, and nasopharyx. In general, structure from motion is a popular technique. It consists of four main steps; (1) camera calibration, (2) feature extraction, (3) feature matching, and (4) 3D reconstruction. Scale Invariant Feature Transform (SIFT) algorithm is normally used for both feature extraction and feature matching. However, SIFT algorithm relatively consumes computational time particularly in the feature matching process because each feature in an image of interest is compared with all features in the subsequent image in order to find the best matched pair. A fuzzy zoning approach is developed for confining feature matching area. Matching between two corresponding features from different images can be efficiently performed. With this approach, it can greatly reduce the matching time. The proposed technique is tested with endoscopic images created from phantoms and compared with the original SIFT technique in terms of the matching time and average errors of the reconstructed models. Finally, original SIFT and the proposed fuzzy-based technique are applied to 3D model reconstruction of real nasal cavity based on images taken from a rigid nasal endoscope. The results showed that the fuzzy-based approach was significantly faster than traditional SIFT technique and provided similar quality of the 3D models. It could be used for creating a nasal cavity taken by a rigid nasal endoscope.

  18. 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.

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

    KAUST Repository

    Wang, Jim Jing-Yan

    2012-01-01

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

  20. Non-rigid registration of medical images based on ordinal feature and manifold learning

    Science.gov (United States)

    Li, Qi; Liu, Jin; Zang, Bo

    2015-12-01

    With the rapid development of medical imaging technology, medical image research and application has become a research hotspot. This paper offers a solution to non-rigid registration of medical images based on ordinal feature (OF) and manifold learning. The structural features of medical images are extracted by combining ordinal features with local linear embedding (LLE) to improve the precision and speed of the registration algorithm. A physical model based on manifold learning and optimization search is constructed according to the complicated characteristics of non-rigid registration. The experimental results demonstrate the robustness and applicability of the proposed registration scheme.

  1. 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.

  2. Face image analysis using a multiple features fitting strategy

    OpenAIRE

    Romdhani, Sami

    2005-01-01

    The main contribution of this thesis is a novel algorithm for fitting a Three-Dimensional Morphable Model of faces to a 2D input image. This fitting algorithm enables the estimation of the 3D shape, the texture, the 3D pose and the light direction from a single input image. Generally, the algorithms tackling the problem of 3D shape estimation from image data use only the pixels intensity as input to drive the estimation process. This was previously achieved using either a simple model, such as ...

  3. 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.

  4. 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.

  5. Change detection in high resolution SAR images based on multiscale texture features

    Science.gov (United States)

    Wen, Caihuan; Gao, Ziqiang

    2011-12-01

    This paper studied on change detection algorithm of high resolution (HR) Synthetic Aperture Radar (SAR) images based on multi-scale texture features. Firstly, preprocessed multi-temporal Terra-SAR images were decomposed by 2-D dual tree complex wavelet transform (DT-CWT), and multi-scale texture features were extracted from those images. Then, log-ratio operation was utilized to get difference images, and the Bayes minimum error theory was used to extract change information from difference images. Lastly, precision assessment was done. Meanwhile, we compared with the result of method based on texture features extracted from gray-level cooccurrence matrix (GLCM). We had a conclusion that, change detection algorithm based on multi-scale texture features has a great more improvement, which proves an effective method to change detect of high spatial resolution SAR images.

  6. Caroli's disease: magnetic resonance imaging features

    Energy Technology Data Exchange (ETDEWEB)

    Guy, France; Cognet, Francois; Dranssart, Marie; Cercueil, Jean-Pierre; Conciatori, Laurent; Krause, Denis [Department of Radiology and Imaging, Dijon Le Bocage University Hospital, 2 Blvd. Marechal de Lattre de Tassigny, BP 1542, 21034 Dijon Cedex (France)

    2002-11-01

    Our objective was to describe the main aspects of MR imaging in Caroli's disease. Magnetic resonance cholangiography with a dynamic contrast-enhanced study was performed in nine patients with Caroli's disease. Bile duct abnormalities, lithiasis, dot signs, hepatic enhancement, renal abnormalities, and evidence of portal hypertension were evaluated. Three MR imaging patterns of Caroli's disease were found. In all but two patients, MR imaging findings were sufficient to confirm the diagnosis. Moreover, MR imaging provided information about the severity, location, and extent of liver involvement. This information was useful in planning the best therapeutic strategy. Magnetic resonance cholangiography with a dynamic contrast-enhanced study is a good screening tool for Caroli's disease. Direct cholangiography should be reserved for confirming doubtful cases. (orig.)

  7. 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.

  8. 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.

  9. 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...

  10. Interpretation of archaeological small-scale features in spectral images

    DEFF Research Database (Denmark)

    Grøn, Ole; Palmer, Susanna; Stylegar, Frans-Arne;

    2011-01-01

    The paper's focus is the use of spectral images for the distinction of small archaeological anomalies on the basis of the authors work. Special attention is given to the ground-truthing perspective in the discussion of a number of cases from Norway. Different approaches to pattern-recognition are......-recognition are considered in the light of the increasing availability of hyper-spectral images that are difficult to analyse using visual inspection alone....

  11. 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.

  12. New feature of the neutron color image intensifier

    Science.gov (United States)

    Nittoh, Koichi; Konagai, Chikara; Noji, Takashi; Miyabe, Keisuke

    2009-06-01

    We developed prototype neutron color image intensifiers with high-sensitivity, wide dynamic range and long-life characteristics. In the prototype intensifier (Gd-Type 1), a terbium-activated Gd 2O 2S is used as the input-screen phosphor. In the upgraded model (Gd-Type 2), Gd 2O 3 and CsI:Na are vacuum deposited to form the phosphor layer, which improved the sensitivity and the spatial uniformity. A europium-activated Y 2O 2S multi-color scintillator, emitting red, green and blue photons with different intensities, is utilized as the output screen of the intensifier. By combining this image intensifier with a suitably tuned high-sensitive color CCD camera, higher sensitivity and wider dynamic range could be simultaneously attained than that of the conventional P20-phosphor-type image intensifier. The results of experiments at the JRR-3M neutron radiography irradiation port (flux: 1.5×10 8 n/cm 2/s) showed that these neutron color image intensifiers can clearly image dynamic phenomena with a 30 frame/s video picture. It is expected that the color image intensifier will be used as a new two-dimensional neutron sensor in new application fields.

  13. Erythrocyte Features for Malaria Parasite Detection in Microscopic Images of Thin Blood Smear: A Review

    Directory of Open Access Journals (Sweden)

    Salam Shuleenda Devi

    2016-12-01

    Full Text Available Microscopic image analysis of blood smear plays a very important role in characterization of erythrocytes in screening of malaria parasites. The characteristics feature of erythrocyte changes due to malaria parasite infection. The microscopic features of the erythrocyte include morphology, intensity and texture. In this paper, the different features used to differentiate the non- infected and malaria infected erythrocyte have been reviewed.

  14. 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

    Background. Characterization of textural features (spatial distributions of image intensity levels) has been considered as a tool for automatic tumor segmentation. The purpose of this work is to study the variability of the textural features in PET images due to different acquisition modes...... 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...... classified based on the range of variation in three categories: small, intermediate and large variability. Features with small variability (range 30%). Conclusion. Textural features such as entropy-first order, energy, maximal correlation coefficient, and low-gray level run emphasis exhibited small...

  15. Spectrum Feature Retrieval and Comparison of Remote Sensing Images Using Improved ISODATA Algorithm

    Institute of Scientific and Technical Information of China (English)

    刘磊; 敬忠良; 肖刚

    2004-01-01

    Due to the large quantities of data and high relativity of the spectra of remote sensing images, K-L transformation is used to eliminate the relativity. An improved ISODATA(Interative Self-Organizing Data Analysis Technique A) algorithm is used to extract the spectrum features of the images. The computation is greatly reduced and the dynamic arguments are realized. The comparison of features between two images is carried out, and good results are achieved in simulation.

  16. Hyperspectral Image Classification Based on the Weighted Probabilistic Fusion of Multiple Spectral-spatial Features

    Directory of Open Access Journals (Sweden)

    ZHANG Chunsen

    2015-08-01

    Full Text Available A hyperspectral images classification method based on the weighted probabilistic fusion of multiple spectral-spatial features was proposed in this paper. First, the minimum noise fraction (MNF approach was employed to reduce the dimension of hyperspectral image and extract the spectral feature from the image, then combined the spectral feature with the texture feature extracted based on gray level co-occurrence matrix (GLCM, the multi-scale morphological feature extracted based on OFC operator and the end member feature extracted based on sequential maximum angle convex cone (SMACC method to form three spectral-spatial features. Afterwards, support vector machine (SVM classifier was used for the classification of each spectral-spatial feature separately. Finally, we established the weighted probabilistic fusion model and applied the model to fuse the SVM outputs for the final classification result. In order to verify the proposed method, the ROSIS and AVIRIS image were used in our experiment and the overall accuracy reached 97.65% and 96.62% separately. The results indicate that the proposed method can not only overcome the limitations of traditional single-feature based hyperspectral image classification, but also be superior to conventional VS-SVM method and probabilistic fusion method. The classification accuracy of hyperspectral images was improved effectively.

  17. 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.

  18. 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.

  19. Use of Wavelet-Fuzzy Features with PCA for Image Registration

    Directory of Open Access Journals (Sweden)

    Safia Sadruddin

    2014-01-01

    Full Text Available In this paper, we discuss an Image Registration system based on neural network, which uses Wavelet-fuzzy features of an image. In this system, Wavelet-fuzzy features are extracted from an image and then reduced using Principal Component Analysis (PCA. The reduced feature set is then used for training the neural network for image registration. The geometric transformation between the reference and sensed image sets are evaluated using affine transformation parameters. The trained neural network produces registration parameters (translation, rotation and scaling with respect to reference and sensed image. Two parameters namely Mean Absolute Registration Error and Mutual Information are used as evaluation parameters. Experimentally, we show that the proposed technique for image registration is accurate and robust for distorted and noisy inputs.

  20. Improved Feature Detection in Fused Intensity-Range Images with Complex SIFT (ℂSIFT

    Directory of Open Access Journals (Sweden)

    Boris Jutzi

    2011-09-01

    Full Text Available The real and imaginary parts are proposed as an alternative to the usual Polar representation of complex-valued images. It is proven that the transformation from Polar to Cartesian representation contributes to decreased mutual information, and hence to greater distinctiveness. The Complex Scale-Invariant Feature Transform (ℂSIFT detects distinctive features in complex-valued images. An evaluation method for estimating the uniformity of feature distributions in complex-valued images derived from intensity-range images is proposed. In order to experimentally evaluate the proposed methodology on intensity-range images, three different kinds of active sensing systems were used: Range Imaging, Laser Scanning, and Structured Light Projection devices (PMD CamCube 2.0, Z+F IMAGER 5003, Microsoft Kinect.

  1. 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).

  2. 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.

  3. Similar Reference Image Quality Assessment: A New Database and A Trial with Local Feature Matching

    Science.gov (United States)

    Lu, Qingbo; Zhou, Wengang; Li, Houqiang

    2016-12-01

    Conventionally, the reference image for image quality assessment (IQA) is completely available (full-reference IQA) or unavailable (no-reference IQA). Even for reduced-reference IQA, the features that are used to predict image quality are still extracted from the pristine reference image. However, the pristine reference image is always unavailable in many real scenarios. In contrast, it is convenient to obtain a number of similar reference images via retrieval from the Internet. These similar reference images may share similar contents and scenes with the image to be assessed. In this paper, we attempt to discuss the image quality assessment problem from the view of similar images, i.e. similar reference IQA. Although the similar reference images share similar contents with the degraded image, the difference between them still cannot be ignored. Therefore, we propose an IQA framework based on local feature matching, which can help to identify the similar regions and structures. Then the IQA features are computed only from these similar regions to predict the final image quality score. Besides, since there is no IQA databases for the similar reference IQA problem, we establish a novel IQA database that consists of 272 images from four scenes. The experiments demonstrate that the performance of our scheme goes beyond state-of-the-art no-reference IQA methods and some full-reference IQA algorithms.

  4. 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.

  5. Color and Texture Feature for Remote Sensing - Image Retrieval System: A Comparative Study

    Directory of Open Access Journals (Sweden)

    Retno Kusumaningrum

    2011-09-01

    Full Text Available In this study, we proposed score fusion technique to improve the performance of remote sensing image retrieval system (RS-IRS using combination of several features. The representation of each feature is selected based on their performance when used as single feature in RS-IRS. Those features are color moment using L*a*b* color space, edge direction histogram extracted from Saturation channel, GLCM and Gabor Wavelet represented using standard deviation, and local binary pattern using 8-neighborhood. The score fusion is performed by computing the value of image similarity between an image in the database and query, where the image similarity value is sum of all features similarity, where each of feature similarity has been divided by SVD value of feature similarity between all images in the database and query from related feature. The feature similarity is measured by histogram intersection for local binary pattern, whereas the color moment, edge direction histogram, GLCM, and Gabor are measured by Euclidean Distance. The final result shows that the best performance of remote sensing image retrieval in this study is a system which uses the combination of color and texture features (i.e. color moment, edge direction histogram, GLCM, Gabor wavelet, and local binary pattern and uses score fusion in measuring the image similarity between query and images in the database. This system outperforms the other five individual feature with average precision rates 3%, 20%, 13%, 11%, and 9%, respectively, for color moment, edge direction histogram, GLCM, Gabor wavelet, and LBP. Moreover, this system also increase 17% compared to system without score fusion, simple-sum technique.

  6. Ensemble classification of colon biopsy images based on information rich hybrid features.

    Science.gov (United States)

    Rathore, Saima; Hussain, Mutawarra; Aksam Iftikhar, Muhammad; Jalil, Abdul

    2014-04-01

    In recent years, classification of colon biopsy images has become an active research area. Traditionally, colon cancer is diagnosed using microscopic analysis. However, the process is subjective and leads to considerable inter/intra observer variation. Therefore, reliable computer-aided colon cancer detection techniques are in high demand. In this paper, we propose a colon biopsy image classification system, called CBIC, which benefits from discriminatory capabilities of information rich hybrid feature spaces, and performance enhancement based on ensemble classification methodology. Normal and malignant colon biopsy images differ with each other in terms of the color distribution of different biological constituents. The colors of different constituents are sharp in normal images, whereas the colors diffuse with each other in malignant images. In order to exploit this variation, two feature types, namely color components based statistical moments (CCSM) and Haralick features have been proposed, which are color components based variants of their traditional counterparts. Moreover, in normal colon biopsy images, epithelial cells possess sharp and well-defined edges. Histogram of oriented gradients (HOG) based features have been employed to exploit this information. Different combinations of hybrid features have been constructed from HOG, CCSM, and Haralick features. The minimum Redundancy Maximum Relevance (mRMR) feature selection method has been employed to select meaningful features from individual and hybrid feature sets. Finally, an ensemble classifier based on majority voting has been proposed, which classifies colon biopsy images using the selected features. Linear, RBF, and sigmoid SVM have been employed as base classifiers. The proposed system has been tested on 174 colon biopsy images, and improved performance (=98.85%) has been observed compared to previously reported studies. Additionally, the use of mRMR method has been justified by comparing the

  7. 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.

  8. 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.

  9. Medical image retrieval based on texture and shape feature co-occurrence

    Science.gov (United States)

    Zhou, Yixiao; Huang, Yan; Ling, Haibin; Peng, Jingliang

    2012-03-01

    With the rapid development and wide application of medical imaging technology, explosive volumes of medical image data are produced every day all over the world. As such, it becomes increasingly challenging to manage and utilize such data effectively and efficiently. In particular, content-based medical image retrieval has been intensively researched in the past decade or so. In this work, we propose a novel approach to content-based medical image retrieval utilizing the co-occurrence of both the texture and the shape features in contrast to most previous algorithms that use purely the texture or the shape feature. Specifically, we propose a novel form of representation for the co-occurrence of the texture and the shape features in an image, i.e., the gray level and edge direction co-occurrence matrix (GLEDCOM). Based on GLEDCOM, we define eleven features forming a feature vector that is used to measure the similarity between images. As a result, it consistently yields outstanding performance on both images rich in texture (e.g., image of brain) and images with dominant smooth regions and sharp edges (e.g., image of bladder). As demonstrated by experiments, the mean precision of retrieval with GLEDCOM algorithm outperforms a set of representative algorithms including the gray level co-occurrence matrix (GLCM) based, the Hu's seven moment invariants (HSMI) based, the uniformity estimation method (UEM) based and the the modified Zernike moments (MZM) based algorithms by 10%-20%.

  10. 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.

  11. Image indexing using composite color and shape invariant features

    NARCIS (Netherlands)

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

    1998-01-01

    New sets of color models are proposed for object recognition invariant to a change in view point, object geometry and illumination. Further, computational methods are presented to combine color and shape invariants to produce a high-dimensional invariant feature set for discriminatory object recogni

  12. 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.

  13. Feature exploration for biometric recognition using millimetre wave body images

    OpenAIRE

    2015-01-01

    The electronic version of this article is the complete one and can be found online at: http://dx.doi.org/10.1186/s13640-015-0084-3 The use of millimetre wave images has been proposed recently in the biometric field to overcome certain limitations when using images acquired at visible frequencies. Furthermore, the security community has started using millimetre wave screening scanners in order to detect concealed objects. We believe we can exploit the use of these devices by incorporating b...

  14. X-ray image enhancement via determinant based feature selection.

    Science.gov (United States)

    Tappenden, R; Hegarty, J; Broughton, R; Butler, A; Coope, I; Renaud, P

    2013-12-01

    Previous work has investigated the feasibility of using Eigenimage-based enhancement tools to highlight abnormalities on chest X-rays (Butler et al in J Med Imaging Radiat Oncol 52:244-253, 2008). While promising, this approach has been limited by computational restrictions of standard clinical workstations, and uncertainty regarding what constitutes an adequate sample size. This paper suggests an alternative mathematical model to the above referenced singular value decomposition method, which can significantly reduce both the required sample size and the time needed to perform analysis. Using this approach images can be efficiently separated into normal and abnormal parts, with the potential for rapid highlighting of pathology.

  15. 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

  16. 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...

  17. 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 ...

  18. Hyperspectral Image Classification Based on the Combination of Spatial-spectral Feature and Sparse Representation

    Directory of Open Access Journals (Sweden)

    YANG Zhaoxia

    2015-07-01

    Full Text Available In order to avoid the problem of being over-dependent on high-dimensional spectral feature in the traditional hyperspectral image classification, a novel approach based on the combination of spatial-spectral feature and sparse representation is proposed in this paper. Firstly, we extract the spatial-spectral feature by reorganizing the local image patch with the first d principal components(PCs into a vector representation, followed by a sorting scheme to make the vector invariant to local image rotation. Secondly, we learn the dictionary through a supervised method, and use it to code the features from test samples afterwards. Finally, we embed the resulting sparse feature coding into the support vector machine(SVM for hyperspectral image classification. Experiments using three hyperspectral data show that the proposed method can effectively improve the classification accuracy comparing with traditional classification methods.

  19. 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.

  20. 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

  1. Second order Statistical Texture Features from a New CSLBPGLCM for Ultrasound Kidney Images Retrieval

    Directory of Open Access Journals (Sweden)

    Chelladurai CALLINS CHRISTIYANA

    2013-12-01

    Full Text Available This work proposes a new method called Center Symmetric Local Binary Pattern Grey Level Co-occurrence Matrix (CSLBPGLCM for the purpose of extracting second order statistical texture features in ultrasound kidney images. These features are then feed into ultrasound kidney images retrieval system for the point of medical applications. This new GLCM matrix combines the benefit of CSLBP and conventional GLCM. The main intention of this CSLBPGLCM is to reduce the number of grey levels in an image by not simply accumulating the grey levels but incorporating another statistical texture feature in it. The proposed approach is cautiously evaluated in ultrasound kidney images retrieval system and has been compared with conventional GLCM. It is experimentally proved that the proposed method increases the retrieval efficiency, accuracy and reduces the time complexity of ultrasound kidney images retrieval system by means of second order statistical texture features.

  2. 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; CHENG Yiyu

    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.

  3. Edge-Based Feature Extraction Method and Its Application to Image Retrieval

    Directory of Open Access Journals (Sweden)

    G. Ohashi

    2003-10-01

    Full Text Available We propose a novel feature extraction method for content-bases image retrieval using graphical rough sketches. The proposed method extracts features based on the shape and texture of objects. This edge-based feature extraction method functions by representing the relative positional relationship between edge pixels, and has the advantage of being shift-, scale-, and rotation-invariant. In order to verify its effectiveness, we applied the proposed method to 1,650 images obtained from the Hamamatsu-city Museum of Musical Instruments and 5,500 images obtained from Corel Photo Gallery. The results verified that the proposed method is an effective tool for achieving accurate retrieval.

  4. Hepatic CT Image Query Based on Threshold-based Classification Scheme with Gabor Features

    Institute of Scientific and Technical Information of China (English)

    JIANG Li-jun; LUO Yong-zing; ZHAO Jun; ZHUANG Tian-ge

    2008-01-01

    Hepatic computed tomography (CT) images with Gabor function were analyzed.Then a thresholdbased classification scheme was proposed using Gabor features and proceeded with the retrieval of the hepatic CT images.In our experiments,a batch of hepatic CT images containing several types of CT findings was used and compared with the Zhao's image classification scheme,support vector machines (SVM) scheme and threshold-based scheme.

  5. 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.

  6. Featured Image: Violent History of the Toothbrush Cluster

    Science.gov (United States)

    Kohler, Susanna

    2016-03-01

    This stunning composite image shows the components of the galaxy cluster RX J0603.3+4214, located at a redshift of z=0.225. This image contains Chandra X-ray data (red), radio data from the Giant Metrewave Radio Telescope (green), and optical from the Subaru Telescope (background). The shape of the enormous (6.5 million light-years across!) radio relic, shown in green, gives this collection of galaxies its nickname: the Toothbrush Cluster. A team of scientists led by Myungkook James Jee (Yonsei University and University of California, Davis) used Hubble and Subaru to study weak gravitational lensing by the Toothbrush Cluster, in order to determine how the clusters mass is distributed. Jee and collaborators found that most of the dark-matter mass is located in two large clumps on a north-south axis (shown by the white contours overlaid on the image), suggesting that the Toothbrush Cluster is the result of a past merger between two clusters. This violent merger is likely what caused the enormous Toothbrush radio relic. Check out the paper below for more information!CitationM. James Jee et al 2016 ApJ 817 179. doi:10.3847/0004-637X/817/2/179

  7. 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.

  8. A Content based CT Lung Image Retrieval by DCT Matrix and Feature Vector Technique

    Directory of Open Access Journals (Sweden)

    J.Bridget Nirmala

    2012-03-01

    Full Text Available Most of the image retrieval systems are still incapable of providing retrieval result with high retrieval accuracy and less computational complexity. Image Retrieval technique to retrieve similar and relevant Computed Tomography (CT images of lung from a large database of images. During the process of retrieval, a query image which contains the affected area / abnormal region is given as an input to retrieve similar images which contain affected area/abnormal region from the database. DCT Matrix (DCTM is a kind of commonly used color feature representation in image retrieval. This paper describes a content based image retrieval (CBIR that represent each image in database by a vector of feature values called DCT vector matrix(8x8. Using this DCTM row and column feature vector values considered as a query image which is compared with existing database to cull out more similar and relevant images. The experimental result shows that 97% of images can be retrieved correctly using this technique

  9. [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.

  10. Efficient and robust model-to-image alignment using 3D scale-invariant features.

    Science.gov (United States)

    Toews, Matthew; Wells, William M

    2013-04-01

    This paper presents feature-based alignment (FBA), a general method for efficient and robust model-to-image alignment. Volumetric images, e.g. CT scans of the human body, are modeled probabilistically as a collage of 3D scale-invariant image features within a normalized reference space. Features are incorporated as a latent random variable and marginalized out in computing a maximum a posteriori alignment solution. The model is learned from features extracted in pre-aligned training images, then fit to features extracted from a new image to identify a globally optimal locally linear alignment solution. Novel techniques are presented for determining local feature orientation and efficiently encoding feature intensity in 3D. Experiments involving difficult magnetic resonance (MR) images of the human brain demonstrate FBA achieves alignment accuracy similar to widely-used registration methods, while requiring a fraction of the memory and computation resources and offering a more robust, globally optimal solution. Experiments on CT human body scans demonstrate FBA as an effective system for automatic human body alignment where other alignment methods break down.

  11. Automatic classification of hepatocellular carcinoma images based on nuclear and structural features

    Science.gov (United States)

    Kiyuna, Tomoharu; Saito, Akira; Marugame, Atsushi; Yamashita, Yoshiko; Ogura, Maki; Cosatto, Eric; Abe, Tokiya; Hashiguchi, Akinori; Sakamoto, Michiie

    2013-03-01

    Diagnosis of hepatocellular carcinoma (HCC) on the basis of digital images is a challenging problem because, unlike gastrointestinal carcinoma, strong structural and morphological features are limited and sometimes absent from HCC images. In this study, we describe the classification of HCC images using statistical distributions of features obtained from image analysis of cell nuclei and hepatic trabeculae. Images of 130 hematoxylin-eosin (HE) stained histologic slides were captured at 20X by a slide scanner (Nanozoomer, Hamamatsu Photonics, Japan) and 1112 regions of interest (ROI) images were extracted for classification (551 negatives and 561 positives, including 113 well-differentiated positives). For a single nucleus, the following features were computed: area, perimeter, circularity, ellipticity, long and short axes of elliptic fit, contour complexity and gray level cooccurrence matrix (GLCM) texture features (angular second moment, contrast, homogeneity and entropy). In addition, distributions of nuclear density and hepatic trabecula thickness within an ROI were also extracted. To represent an ROI, statistical distributions (mean, standard deviation and percentiles) of these features were used. In total, 78 features were extracted for each ROI and a support vector machine (SVM) was trained to classify negative and positive ROIs. Experimental results using 5-fold cross validation show 90% sensitivity for an 87.8% specificity. The use of statistical distributions over a relatively large area makes the HCC classifier robust to occasional failures in the extraction of nuclear or hepatic trabecula features, thus providing stability to the system.

  12. Entropy based unsupervised Feature Selection in digital mammogram image using rough set theory.

    Science.gov (United States)

    Velayutham, C; Thangavel, K

    2012-01-01

    Feature Selection (FS) is a process, which attempts to select features, which are more informative. In the supervised FS methods various feature subsets are evaluated using an evaluation function or metric to select only those features, which are related to the decision classes of the data under consideration. However, for many data mining applications, decision class labels are often unknown or incomplete, thus indicating the significance of unsupervised FS. However, in unsupervised learning, decision class labels are not provided. The problem is that not all features are important. Some of the features may be redundant, and others may be irrelevant and noisy. In this paper, a novel unsupervised FS in mammogram image, using rough set-based entropy measures, is proposed. A typical mammogram image processing system generally consists of mammogram image acquisition, pre-processing of image, segmentation, features extracted from the segmented mammogram image. The proposed method is used to select features from data set, the method is compared with the existing rough set-based supervised FS methods and classification performance of both methods are recorded and demonstrates the efficiency of the method.

  13. 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.

  14. 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.)

  15. 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.

  16. 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.

  17. 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.

  18. Design of vector quantizer for image compression using self-organizing feature map and surface fitting.

    Science.gov (United States)

    Laha, Arijit; Pal, Nikhil R; Chanda, Bhabatosh

    2004-10-01

    We propose a new scheme of designing a vector quantizer for image compression. First, a set of codevectors is generated using the self-organizing feature map algorithm. Then, the set of blocks associated with each code vector is modeled by a cubic surface for better perceptual fidelity of the reconstructed images. Mean-removed vectors from a set of training images is used for the construction of a generic codebook. Further, Huffman coding of the indices generated by the encoder and the difference-coded mean values of the blocks are used to achieve better compression ratio. We proposed two indices for quantitative assessment of the psychovisual quality (blocking effect) of the reconstructed image. Our experiments on several training and test images demonstrate that the proposed scheme can produce reconstructed images of good quality while achieving compression at low bit rates. Index Terms-Cubic surface fitting, generic codebook, image compression, self-organizing feature map, vector quantization.

  19. Featured Image: A Pulsar Is Obscured by a Solar Explosion

    Science.gov (United States)

    Kohler, Susanna

    2016-12-01

    This series of images (click for the full view!), taken by the Solar and Heliospheric Observatory satellite (SOHO) in August 2015, reveals a tremendous outburst of plasma and magnetic field from the Sun: a coronal mass ejection (CME). If you look closely, youll note that as the CME expands from the Suns surface, it passes in front of a dot highlighted in yellow. This dot marks the location of a distant background pulsar, PSR B0950+08. In a recent study led by Tim Howard (Southwest Research Institute), a team of scientists studied the change observed in the radio emission of this pulsar as the CME passed by in the foreground. The team used these observations to estimate the CMEs density and magnetic field measurements that can tell us more about the nature of the magnetic field in the Suns corona and the solar wind.You can check out the animation of this CME, also taken with SOHOs LASCO instrument, below (the CME starts around 20 seconds in), or you can find out more from the original paper!http://cdn.iopscience.com/images/0004-637X/831/2/208/Full/apjaa35ecf1_video.mp4CitationT. A. Howard et al 2016 ApJ 831 208. doi:10.3847/0004-637X/831/2/208

  20. Joint Applied Optics and Chinese Optics Letters feature introduction: digital holography and three-dimensional imaging.

    Science.gov (United States)

    Poon, Ting-Chung

    2011-12-01

    This feature issue serves as a pilot issue promoting the joint issue of Applied Optics and Chinese Optics Letters. It focuses upon topics of current relevance to the community working in the area of digital holography and 3-D imaging.

  1. Identification of natural images and computer-generated graphics based on statistical and textural features.

    Science.gov (United States)

    Peng, Fei; Li, Jiao-ting; Long, Min

    2015-03-01

    To discriminate the acquisition pipelines of digital images, a novel scheme for the identification of natural images and computer-generated graphics is proposed based on statistical and textural features. First, the differences between them are investigated from the view of statistics and texture, and 31 dimensions of feature are acquired for identification. Then, LIBSVM is used for the classification. Finally, the experimental results are presented. The results show that it can achieve an identification accuracy of 97.89% for computer-generated graphics, and an identification accuracy of 97.75% for natural images. The analyses also demonstrate the proposed method has excellent performance, compared with some existing methods based only on statistical features or other features. The method has a great potential to be implemented for the identification of natural images and computer-generated graphics.

  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. 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)

  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. 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.

  6. Image quality assessment method based on nonlinear feature extraction in kernel space

    Institute of Scientific and Technical Information of China (English)

    Yong DING‡; Nan LI; Yang ZHAO; Kai HUANG

    2016-01-01

    To match human perception, extracting perceptual features effectively plays an important role in image quality assessment. In contrast to most existing methods that use linear transformations or models to represent images, we employ a complex mathematical expression of high dimensionality to reveal the statistical characteristics of the images. Furthermore, by introducing kernel methods to transform the linear problem into a nonlinear one, a full-reference image quality assessment method is proposed based on high-dimensional nonlinear feature extraction. Experiments on the LIVE, TID2008, and CSIQ databases demonstrate that nonlinear features offer competitive performance for image inherent quality representation and the proposed method achieves a promising performance that is consistent with human subjective evaluation.

  7. 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.

  8. Featured Image: A Search for Stellar Bow Shock Nebulae

    Science.gov (United States)

    Kohler, Susanna

    2017-02-01

    These dynamic infrared images (click for the full view!) reveal what are known as bow shock nebulae nebulae that form at the interface between the interstellar medium and the stellar wind from a high-speed star zipping through the galaxy (the arrows show the direction of motion of the star). When the relative speed between the two is supersonic, an arc-shaped bow shock forms ahead of the star, like the six prototypical ones pictured here. A team of scientists led by Henry Kobulnicky (University of Wyoming) has recently searched through survey data from the Spitzer Space Telescope and the Wide Field Infrared Explorer (WISE) to build a catalog of more than 700 such bow-shock nebula candidates, the vast majority of which are new discoveries. To find out more about their sample, check out the paper below!CitationHenry A. Kobulnicky et al 2016 ApJS 227 18. doi:10.3847/0067-0049/227/2/18

  9. 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.

  10. 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...

  11. 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.

  12. 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.

  13. 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.

  14. Profiles of US and CT imaging features with a high probability of appendicitis

    NARCIS (Netherlands)

    van Randen, A.; Lameris, W.; van Es, H. W.; ten Hove, W.; Bouma, W. H.; van Leeuwen, M. S.; van Keulen, E. M.; van der Hulst, V. P. M.; Henneman, O. D.; Bossuyt, P. M.; Boermeester, M. A.; Stoker, J

    2010-01-01

    To identify and evaluate profiles of US and CT features associated with acute appendicitis. Consecutive patients presenting with acute abdominal pain at the emergency department were invited to participate in this study. All patients underwent US and CT. Imaging features known to be associated with

  15. Introduction: feature issue on phantoms for the performance evaluation and validation of optical medical imaging devices.

    Science.gov (United States)

    Hwang, Jeeseong; Ramella-Roman, Jessica C; Nordstrom, Robert

    2012-06-01

    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.

  16. 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

  17. Automated classification of patients with coronary artery disease using grayscale features from left ventricle echocardiographic images.

    Science.gov (United States)

    Acharya, U Rajendra; Sree, S Vinitha; Muthu Rama Krishnan, M; Krishnananda, N; Ranjan, Shetty; Umesh, Pai; Suri, Jasjit S

    2013-12-01

    Coronary Artery Disease (CAD), caused by the buildup of plaque on the inside of the coronary arteries, has a high mortality rate. To efficiently detect this condition from echocardiography images, with lesser inter-observer variability and visual interpretation errors, computer based data mining techniques may be exploited. We have developed and presented one such technique in this paper for the classification of normal and CAD affected cases. A multitude of grayscale features (fractal dimension, entropies based on the higher order spectra, features based on image texture and local binary patterns, and wavelet based features) were extracted from echocardiography images belonging to a huge database of 400 normal cases and 400 CAD patients. Only the features that had good discriminating capability were selected using t-test. Several combinations of the resultant significant features were used to evaluate many supervised classifiers to find the combination that presents a good accuracy. We observed that the Gaussian Mixture Model (GMM) classifier trained with a feature subset made up of nine significant features presented the highest accuracy, sensitivity, specificity, and positive predictive value of 100%. We have also developed a novel, highly discriminative HeartIndex, which is a single number that is calculated from the combination of the features, in order to objectively classify the images from either of the two classes. Such an index allows for an easier implementation of the technique for automated CAD detection in the computers in hospitals and clinics.

  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. 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.

  20. 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.

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

    Energy Technology Data Exchange (ETDEWEB)

    Galavis, Paulina E.; Jallow, Ngoneh; Paliwal, Bhudatt; Jeraj, Robert (Dept. of Medical Physics, Univ. of Wisconsin, Madison, WI (United States)), E-mail: galavis@wisc.edu; Hollensen, Christian (Dept. of Informatics and Mathematical Models, Technical Univ. of Denmark, Copenhagen (Denmark))

    2010-10-15

    Background. Characterization of textural features (spatial distributions of image intensity levels) has been considered as a tool for automatic tumor segmentation. The purpose of this work is to study the variability of the textural features in PET images due to different acquisition modes and reconstruction parameters. Material and methods. Twenty patients with solid tumors underwent PET/CT scans on a GE Discovery VCT scanner, 45-60 minutes post-injection of 10 mCi of [18F]FDG. Scans were acquired in both 2D and 3D modes. For each acquisition the raw PET data was reconstructed using five different 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 classified based on the range of variation in three categories: small, intermediate and large variability. Features with small variability (range = 5%) were entropy-first order, energy, maximal correlation coefficient (second order feature) and low-gray level run emphasis (high-order feature). The features with intermediate variability (10% = range = 25%) were entropy-GLCM, sum entropy, high gray level run emphasis, gray level non-uniformity, small number emphasis, and entropy-NGL. Forty remaining features presented large variations (range > 30%). Conclusion. Textural features such as entropy-first order, energy, maximal correlation coefficient, and low-gray level run emphasis exhibited small variations due to different acquisition modes and reconstruction parameters. Features with low level of variations are better candidates for reproducible tumor segmentation. Even though features such as contrast-NGTD, coarseness, homogeneity, and busyness have been previously used, our data indicated that these features presented large variations, therefore they could not be

  2. Featured Image: The Simulated Collapse of a Core

    Science.gov (United States)

    Kohler, Susanna

    2016-11-01

    This stunning snapshot (click for a closer look!) is from a simulation of a core-collapse supernova. Despite having been studied for many decades, the mechanism driving the explosions of core-collapse supernovae is still an area of active research. Extremely complex simulations such as this one represent best efforts to include as many realistic physical processes as is currently computationally feasible. In this study led by Luke Roberts (a NASA Einstein Postdoctoral Fellow at Caltech at the time), a core-collapse supernova is modeled long-term in fully 3D simulations that include the effects of general relativity, radiation hydrodynamics, and even neutrino physics. The authors use these simulations to examine the evolution of a supernova after its core bounce. To read more about the teams findings (and see more awesome images from their simulations), check out the paper below!CitationLuke F. Roberts et al 2016 ApJ 831 98. doi:10.3847/0004-637X/831/1/98

  3. 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.

  4. Learning effective color features for content based image retrieval in dermatology

    NARCIS (Netherlands)

    Bunte, Kerstin; Biehl, Michael; Jonkman, Marcel F.; Petkov, Nicolai

    2011-01-01

    We investigate the extraction of effective color features for a content-based image retrieval (CBIR) application in dermatology. Effectiveness is measured by the rate of correct retrieval of images from four color classes of skin lesions. We employ and compare two different methods to learn favorabl

  5. 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.

  6. Classifying content-based Images using Self Organizing Map Neural Networks Based on Nonlinear Features

    Directory of Open Access Journals (Sweden)

    Ebrahim Parcham

    2014-07-01

    Full Text Available Classifying similar images is one of the most interesting and essential image processing operations. Presented methods have some disadvantages like: low accuracy in analysis step and low speed in feature extraction process. In this paper, a new method for image classification is proposed in which similarity weight is revised by means of information in related and unrelated images. Based on researchers’ idea, most of real world similarity measurement systems are nonlinear. Thus, traditional linear methods are not capable of recognizing nonlinear relationship and correlation in such systems. Undoubtedly, Self Organizing Map neural networks are strongest networks for data mining and nonlinear analysis of sophisticated spaces purposes. In our proposed method, we obtain images with the most similarity measure by extracting features of our target image and comparing them with the features of other images. We took advantage of NLPCA algorithm for feature extraction which is a nonlinear algorithm that has the ability to recognize the smallest variations even in noisy images. Finally, we compare the run time and efficiency of our proposed method with previous proposed methods.

  7. An Image Denoising Method with Enhancement of the Directional Features Based on Wavelet and SVD Transforms

    Directory of Open Access Journals (Sweden)

    Min Wang

    2015-01-01

    Full Text Available This paper proposes an image denoising method, using the wavelet transform and the singular value decomposition (SVD, with the enhancement of the directional features. First, use the single-level discrete 2D wavelet transform to decompose the noised image into the low-frequency image part and the high-frequency parts (the horizontal, vertical, and diagonal parts, with the edge extracted and retained to avoid edge loss. Then, use the SVD to filter the noise of the high-frequency parts with image rotations and the enhancement of the directional features: to filter the diagonal part, one needs first to rotate it 45 degrees and rotate it back after filtering. Finally, reconstruct the image from the low-frequency part and the filtered high-frequency parts by the inverse wavelet transform to get the final denoising image. Experiments show the effectiveness of this method, compared with relevant methods.

  8. 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.

  9. 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.

  10. Automatic Registration of SAR Images with the Integrated Complementary Invariant Feature

    Directory of Open Access Journals (Sweden)

    Xiao-hua Wang

    2014-01-01

    Full Text Available The accurate Synthetic Aperture Radar (SAR image registration is important for exact analyses of mine deformation and ecological environment change. Currently, many image registration algorithms have been proposed, but these registration algorithms cannot be directly applied to SAR image, so an integrated registration approach is presented in this paper. Firstly, it is the coarse matching with Canny edge dividing regions; secondly, it is the fine matching by SIFT algorithm with improved Canny edge features; finally, obtain accurate registration SAR image. This approach has fewer computations than that simply using SIFT feature matching. Experimental analyses with SAR images of Yanzhou Mine demonstrate the efficiency and the accuracy of this approach for mine SAR image registration, which provides a simple and effective tool in SAR monitoring of mining deformation and ecological changes

  11. Study on Situation-oriented Classification of Sightseeing Images Based on Visual and Metadata Features

    OpenAIRE

    Chen, Chia-Huang

    2014-01-01

    This thesis proposes a method for classifying sightseeing images into different situations based on their visual and metadata features. The widespread use of digital cameras and smart phones has brought about a situation where tourists take lots of photos of memorable moments during their travels and upload these photos to web albums such as Flickr or Picasa. These sightseeing images then become useful resources for others who plan to visit the places shown in the images. As scenes of sightse...

  12. 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.

  13. 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

  14. Application of Texture Characteristics for Urban Feature Extraction from Optical Satellite Images

    Directory of Open Access Journals (Sweden)

    D.Shanmukha Rao

    2014-12-01

    Full Text Available Quest of fool proof methods for extracting various urban features from high resolution satellite imagery with minimal human intervention has resulted in developing texture based algorithms. In view of the fact that the textural properties of images provide valuable information for discrimination purposes, it is appropriate to employ texture based algorithms for feature extraction. The Gray Level Co-occurrence Matrix (GLCM method represents a highly efficient technique of extracting second order statistical texture features. The various urban features can be distinguished based on a set of features viz. energy, entropy, homogeneity etc. that characterize different aspects of the underlying texture. As a preliminary step, notable numbers of regions of interests of the urban feature and contrast locations are identified visually. After calculating Gray Level Co-occurrence matrices of these selected regions, the aforementioned texture features are computed. These features can be used to shape a high-dimensional feature vector to carry out content based retrieval. The insignificant features are eliminated to reduce the dimensionality of the feature vector by executing Principal Components Analysis (PCA. The selection of the discriminating features is also aided by the value of Jeffreys-Matusita (JM distance which serves as a measure of class separability Feature identification is then carried out by computing these chosen feature vectors for every pixel of the entire image and comparing it with their corresponding mean values. This helps in identifying and classifying the pixels corresponding to urban feature being extracted. To reduce the commission errors, various index values viz. Soil Adjusted Vegetation Index (SAVI, Normalized Difference Vegetation Index (NDVI and Normalized Difference Water Index (NDWI are assessed for each pixel. The extracted output is then median filtered to isolate the feature of interest after removing the salt and pepper

  15. Computed Tomography and Magnetic Resonance Imaging Features of the Temporomandibular Joint in Two Normal Camels

    Directory of Open Access Journals (Sweden)

    Alberto Arencibia

    2012-01-01

    Full Text Available Computed tomography (CT and magnetic resonance (MR image features of the temporomandibular joint (TMJ and associated structures in two mature dromedary camels were obtained with a third-generation equipment CT and a superconducting magnet RM at 1.5 Tesla. Images were acquired in sagittal and transverse planes. Medical imaging processing with imaging software was applied to obtain postprocessing CT and MR images. Relevant anatomic structures were identified and labelled. The resulting images provided excellent anatomic detail of the TMJ and associated structures. Annotated CT and MR images from this study are intended as an anatomical reference useful in the interpretation for clinical CT and MR imaging studies of the TMJ of the dromedary camels.

  16. 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.)

  17. 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.

  18. 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.

  19. Profiles of US and CT imaging features with a high probability of appendicitis

    Science.gov (United States)

    Laméris, W.; van Es, H. W.; ten Hove, W.; Bouma, W. H.; van Leeuwen, M. S.; van Keulen, E. M.; van der Hulst, V. P. M.; Henneman, O. D.; Bossuyt, P. M.; Boermeester, M. A.; Stoker, J.

    2010-01-01

    Objectives To identify and evaluate profiles of US and CT features associated with acute appendicitis. Methods Consecutive patients presenting with acute abdominal pain at the emergency department were invited to participate in this study. All patients underwent US and CT. Imaging features known to be associated with appendicitis, and an imaging diagnosis were prospectively recorded by two independent radiologists. A final diagnosis was assigned after 6 months. Associations between appendiceal imaging features and a final diagnosis of appendicitis were evaluated with logistic regression analysis. Results Appendicitis was assigned to 284 of 942 evaluated patients (30%). All evaluated features were associated with appendicitis. Imaging profiles were created after multivariable logistic regression analysis. Of 147 patients with a thickened appendix, local transducer tenderness and peri-appendiceal fat infiltration on US, 139 (95%) had appendicitis. On CT, 119 patients in whom the appendix was completely visualised, thickened, with peri-appendiceal fat infiltration and appendiceal enhancement, 114 had a final diagnosis of appendicitis (96%). When at least two of these essential features were present on US or CT, sensitivity was 92% (95% CI 89–96%) and 96% (95% CI 93–98%), respectively. Conclusion Most patients with appendicitis can be categorised within a few imaging profiles on US and CT. When two of the essential features are present the diagnosis of appendicitis can be made accurately. PMID:20119730

  20. Profiles of US and CT imaging features with a high probability of appendicitis

    Energy Technology Data Exchange (ETDEWEB)

    Randen, A. van; Lameris, W. [University of Amsterdam, Department of Radiology, Academic Medical Center, Amsterdam (Netherlands); University of Amsterdam, Department of Surgery, Academic Medical Center, Amsterdam (Netherlands); Es, H.W. van [St Antonius Hospital, Department of Radiology, Nieuwegein (Netherlands); Hove, W. ten; Bouma, W.H. [Gelre Hospitals, Department of Surgery, Apeldoorn (Netherlands); Leeuwen, M.S. van [University Medical Centre, Department of Radiology, Utrecht (Netherlands); Keulen, E.M. van [Tergooi Hospitals, Department of Radiology, Hilversum (Netherlands); Hulst, V.P.M. van der [Onze Lieve Vrouwe Gasthuis, Department of Radiology, Amsterdam (Netherlands); Henneman, O.D. [Bronovo Hospital, Department of Radiology, The Hague (Netherlands); Bossuyt, P.M. [University of Amsterdam, Department of Clinical Epidemiology, Biostatistics, and Bioinformatics, Academic Medical Center, Amsterdam (Netherlands); Boermeester, M.A. [University of Amsterdam, Department of Surgery, Academic Medical Center, Amsterdam (Netherlands); Stoker, J. [University of Amsterdam, Department of Radiology, Academic Medical Center, Amsterdam (Netherlands)

    2010-07-15

    To identify and evaluate profiles of US and CT features associated with acute appendicitis. Consecutive patients presenting with acute abdominal pain at the emergency department were invited to participate in this study. All patients underwent US and CT. Imaging features known to be associated with appendicitis, and an imaging diagnosis were prospectively recorded by two independent radiologists. A final diagnosis was assigned after 6 months. Associations between appendiceal imaging features and a final diagnosis of appendicitis were evaluated with logistic regression analysis. Appendicitis was assigned to 284 of 942 evaluated patients (30%). All evaluated features were associated with appendicitis. Imaging profiles were created after multivariable logistic regression analysis. Of 147 patients with a thickened appendix, local transducer tenderness and peri-appendiceal fat infiltration on US, 139 (95%) had appendicitis. On CT, 119 patients in whom the appendix was completely visualised, thickened, with peri-appendiceal fat infiltration and appendiceal enhancement, 114 had a final diagnosis of appendicitis (96%). When at least two of these essential features were present on US or CT, sensitivity was 92% (95% CI 89-96%) and 96% (95% CI 93-98%), respectively. Most patients with appendicitis can be categorised within a few imaging profiles on US and CT. When two of the essential features are present the diagnosis of appendicitis can be made accurately. (orig.)

  1. 3D-2D Deformable Image Registration Using Feature-Based Nonuniform Meshes.

    Science.gov (United States)

    Zhong, Zichun; Guo, Xiaohu; Cai, Yiqi; Yang, Yin; Wang, Jing; Jia, Xun; Mao, Weihua

    2016-01-01

    By using prior information of planning CT images and feature-based nonuniform meshes, this paper demonstrates that volumetric images can be efficiently registered with a very small portion of 2D projection images of a Cone-Beam Computed Tomography (CBCT) scan. After a density field is computed based on the extracted feature edges from planning CT images, nonuniform tetrahedral meshes will be automatically generated to better characterize the image features according to the density field; that is, finer meshes are generated for features. The displacement vector fields (DVFs) are specified at the mesh vertices to drive the deformation of original CT images. Digitally reconstructed radiographs (DRRs) of the deformed anatomy are generated and compared with corresponding 2D projections. DVFs are optimized to minimize the objective function including differences between DRRs and projections and the regularity. To further accelerate the above 3D-2D registration, a procedure to obtain good initial deformations by deforming the volume surface to match 2D body boundary on projections has been developed. This complete method is evaluated quantitatively by using several digital phantoms and data from head and neck cancer patients. The feature-based nonuniform meshing method leads to better results than either uniform orthogonal grid or uniform tetrahedral meshes.

  2. 3D-2D Deformable Image Registration Using Feature-Based Nonuniform Meshes

    Directory of Open Access Journals (Sweden)

    Zichun Zhong

    2016-01-01

    Full Text Available By using prior information of planning CT images and feature-based nonuniform meshes, this paper demonstrates that volumetric images can be efficiently registered with a very small portion of 2D projection images of a Cone-Beam Computed Tomography (CBCT scan. After a density field is computed based on the extracted feature edges from planning CT images, nonuniform tetrahedral meshes will be automatically generated to better characterize the image features according to the density field; that is, finer meshes are generated for features. The displacement vector fields (DVFs are specified at the mesh vertices to drive the deformation of original CT images. Digitally reconstructed radiographs (DRRs of the deformed anatomy are generated and compared with corresponding 2D projections. DVFs are optimized to minimize the objective function including differences between DRRs and projections and the regularity. To further accelerate the above 3D-2D registration, a procedure to obtain good initial deformations by deforming the volume surface to match 2D body boundary on projections has been developed. This complete method is evaluated quantitatively by using several digital phantoms and data from head and neck cancer patients. The feature-based nonuniform meshing method leads to better results than either uniform orthogonal grid or uniform tetrahedral meshes.

  3. 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...

  4. 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.

  5. Analysis of mammogram images based on texture features of curvelet sub-bands

    Science.gov (United States)

    Gardezi, Syed Jamal Safdar; Faye, Ibrahima; Eltoukhy, Mohamed Meselhy

    2014-01-01

    Image texture analysis plays an important role in object detection and recognition in image processing. The texture analysis can be used for early detection of breast cancer by classifying the mammogram images into normal and abnormal classes. This study investigates breast cancer detection using texture features obtained from the grey level cooccurrence matrices (GLCM) of curvelet sub-band levels combined with texture feature obtained from the image itself. The GLCM were constructed for each sub-band of three curvelet decomposition levels. The obtained feature vector presented to the classifier to differentiate between normal and abnormal tissues. The proposed method is applied over 305 region of interest (ROI) cropped from MIAS dataset. The simple logistic classifier achieved 86.66% classification accuracy rate with sensitivity 76.53% and specificity 91.3%.

  6. Breast Cancer Classification From Histological Images with Multiple Features and Random Subspace Classifier Ensemble

    Science.gov (United States)

    Zhang, Yungang; Zhang, Bailing; Lu, Wenjin

    2011-06-01

    Histological image is important for diagnosis of breast cancer. In this paper, we present a novel automatic breaset cancer classification scheme based on histological images. The image features are extracted using the Curvelet Transform, statistics of Gray Level Co-occurence Matrix (GLCM) and Completed Local Binary Patterns (CLBP), respectively. The three different features are combined together and used for classification. A classifier ensemble approach, called Random Subspace Ensemble (RSE), are used to select and aggregate a set of base neural network classifiers for classification. The proposed multiple features and random subspace ensemble offer the classification rate 95.22% on a publically available breast cancer image dataset, which compares favorably with the previously published result 93.4%.

  7. 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.

  8. 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.

  9. 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.

  10. 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.

  11. Measuring Biometric Sample Quality in terms of Biometric Feature Information in Iris Images

    Directory of Open Access Journals (Sweden)

    R. Youmaran

    2012-01-01

    Full Text Available This paper develops an approach to measure the information content in a biometric feature representation of iris images. In this context, the biometric feature information is calculated using the relative entropy between the intraclass and interclass feature distributions. The collected data is regularized using a Gaussian model of the feature covariances in order to practically measure the biometric information with limited data samples. An example of this method is shown for iris templates processed using Principal-Component Analysis- (PCA- and Independent-Component Analysis- (ICA- based feature decomposition schemes. From this, the biometric feature information is calculated to be approximately 278 bits for PCA and 288 bits for ICA iris features using Masek's iris recognition scheme. This value approximately matches previous estimates of iris information content.

  12. Comparison of Image Transform-Based Features for Visual Speech Recognition in Clean and Corrupted Videos

    Directory of Open Access Journals (Sweden)

    Ji Ming

    2008-03-01

    Full Text Available We present results of a study into the performance of a variety of different image transform-based feature types for speaker-independent visual speech recognition of isolated digits. This includes the first reported use of features extracted using a discrete curvelet transform. The study will show a comparison of some methods for selecting features of each feature type and show the relative benefits of both static and dynamic visual features. The performance of the features will be tested on both clean video data and also video data corrupted in a variety of ways to assess each feature type's robustness to potential real-world conditions. One of the test conditions involves a novel form of video corruption we call jitter which simulates camera and/or head movement during recording.

  13. 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...

  14. 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.

  15. 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.

  16. Image Generation Using Bidirectional Integral Features for Face Recognition with a Single Sample per Person.

    Directory of Open Access Journals (Sweden)

    Yonggeol Lee

    Full Text Available In face recognition, most appearance-based methods require several images of each person to construct the feature space for recognition. However, in the real world it is difficult to collect multiple images per person, and in many cases there is only a single sample per person (SSPP. In this paper, we propose a method to generate new images with various illuminations from a single image taken under frontal illumination. Motivated by the integral image, which was developed for face detection, we extract the bidirectional integral feature (BIF to obtain the characteristics of the illumination condition at the time of the picture being taken. The experimental results for various face databases show that the proposed method results in improved recognition performance under illumination variation.

  17. SAR Images Unsupervised Change Detection Based on Combination of Texture Feature Vector with Maximum Entropy Principle

    Directory of Open Access Journals (Sweden)

    ZHUANG Huifu

    2016-03-01

    Full Text Available Generally, spatial-contextual information would be used in change detection because there is significant speckle noise in synthetic aperture radar(SAR images. In this paper, using the rich texture information of SAR images, an unsupervised change detection approach to high-resolution SAR images based on texture feature vector and maximum entropy principle is proposed. The difference image is generated by using the 32-dimensional texture feature vector of gray-level co-occurrence matrix(GLCM. And the automatic threshold is obtained by maximum entropy principle. In this method, the appropriate window size to change detection is 11×11 according to the regression analysis of window size and precision index. The experimental results show that the proposed approach is better could both reduce the influence of speckle noise and improve the detection accuracy of high-resolution SAR image effectively; and it is better than Markov random field.

  18. An efficient fractal image coding algorithm using unified feature and DCT

    Energy Technology Data Exchange (ETDEWEB)

    Zhou Yiming [Department of Automation, Tsinghua University, Beijing 100084 (China)], E-mail: zhouym02@mails.tsinghua.edu.cn; Zhang Chao; Zhang Zengke [Department of Automation, Tsinghua University, Beijing 100084 (China)

    2009-02-28

    Fractal image compression is a promising technique to improve the efficiency of image storage and image transmission with high compression ratio, however, the huge time consumption for the fractal image coding is a great obstacle to the practical applications. In order to improve the fractal image coding, efficient fractal image coding algorithms using a special unified feature and a DCT coder are proposed in this paper. Firstly, based on a necessary condition to the best matching search rule during fractal image coding, the fast algorithm using a special unified feature (UFC) is addressed, and it can reduce the search space obviously and exclude most inappropriate matching subblocks before the best matching search. Secondly, on the basis of UFC algorithm, in order to improve the quality of the reconstructed image, a DCT coder is combined to construct a hybrid fractal image algorithm (DUFC). Experimental results show that the proposed algorithms can obtain good quality of the reconstructed images and need much less time than the baseline fractal coding algorithm.

  19. Learning with distribution of optimized features for recognizing common CT imaging signs of lung diseases

    Science.gov (United States)

    Ma, Ling; Liu, Xiabi; Fei, Baowei

    2017-01-01

    Common CT imaging signs of lung diseases (CISLs) are defined as the imaging signs that frequently appear in lung CT images from patients. CISLs play important roles in the diagnosis of lung diseases. This paper proposes a novel learning method, namely learning with distribution of optimized feature (DOF), to effectively recognize the characteristics of CISLs. We improve the classification performance by learning the optimized features under different distributions. Specifically, we adopt the minimum spanning tree algorithm to capture the relationship between features and discriminant ability of features for selecting the most important features. To overcome the problem of various distributions in one CISL, we propose a hierarchical learning method. First, we use an unsupervised learning method to cluster samples into groups based on their distribution. Second, in each group, we use a supervised learning method to train a model based on their categories of CISLs. Finally, we obtain multiple classification decisions from multiple trained models and use majority voting to achieve the final decision. The proposed approach has been implemented on a set of 511 samples captured from human lung CT images and achieves a classification accuracy of 91.96%. The proposed DOF method is effective and can provide a useful tool for computer-aided diagnosis of lung diseases on CT images.

  20. 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.

  1. Study on image feature extraction and classification for human colorectal cancer using optical coherence tomography

    Science.gov (United States)

    Huang, Shu-Wei; Yang, Shan-Yi; Huang, Wei-Cheng; Chiu, Han-Mo; Lu, Chih-Wei

    2011-06-01

    Most of the colorectal cancer has grown from the adenomatous polyp. Adenomatous lesions have a well-documented relationship to colorectal cancer in previous studies. Thus, to detect the morphological changes between polyp and tumor can allow early diagnosis of colorectal cancer and simultaneous removal of lesions. OCT (Optical coherence tomography) has been several advantages including high resolution and non-invasive cross-sectional image in vivo. In this study, we investigated the relationship between the B-scan OCT image features and histology of malignant human colorectal tissues, also en-face OCT image and the endoscopic image pattern. The in-vitro experiments were performed by a swept-source optical coherence tomography (SS-OCT) system; the swept source has a center wavelength at 1310 nm and 160nm in wavelength scanning range which produced 6 um axial resolution. In the study, the en-face images were reconstructed by integrating the axial values in 3D OCT images. The reconstructed en-face images show the same roundish or gyrus-like pattern with endoscopy images. The pattern of en-face images relate to the stages of colon cancer. Endoscopic OCT technique would provide three-dimensional imaging and rapidly reconstruct en-face images which can increase the speed of colon cancer diagnosis. Our results indicate a great potential for early detection of colorectal adenomas by using the OCT imaging.

  2. 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.

  3. Breast tissue classification in digital tomosynthesis images based on global gradient minimization and texture features

    Science.gov (United States)

    Qin, Xulei; Lu, Guolan; Sechopoulos, Ioannis; Fei, Baowei

    2014-03-01

    Digital breast tomosynthesis (DBT) is a pseudo-three-dimensional x-ray imaging modality proposed to decrease the effect of tissue superposition present in mammography, potentially resulting in an increase in clinical performance for the detection and diagnosis of breast cancer. Tissue classification in DBT images can be useful in risk assessment, computer-aided detection and radiation dosimetry, among other aspects. However, classifying breast tissue in DBT is a challenging problem because DBT images include complicated structures, image noise, and out-of-plane artifacts due to limited angular tomographic sampling. In this project, we propose an automatic method to classify fatty and glandular tissue in DBT images. First, the DBT images are pre-processed to enhance the tissue structures and to decrease image noise and artifacts. Second, a global smooth filter based on L0 gradient minimization is applied to eliminate detailed structures and enhance large-scale ones. Third, the similar structure regions are extracted and labeled by fuzzy C-means (FCM) classification. At the same time, the texture features are also calculated. Finally, each region is classified into different tissue types based on both intensity and texture features. The proposed method is validated using five patient DBT images using manual segmentation as the gold standard. The Dice scores and the confusion matrix are utilized to evaluate the classified results. The evaluation results demonstrated the feasibility of the proposed method for classifying breast glandular and fat tissue on DBT images.

  4. 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.

  5. Research on texture feature of RS image based on cloud model

    Science.gov (United States)

    Wang, Zuocheng; Xue, Lixia

    2008-10-01

    This paper presents a new method applied to texture feature representation in RS image based on cloud model. Aiming at the fuzziness and randomness of RS image, we introduce the cloud theory into RS image processing in a creative way. The digital characteristics of clouds well integrate the fuzziness and randomness of linguistic terms in a unified way and map the quantitative and qualitative concepts. We adopt texture multi-dimensions cloud to accomplish vagueness and randomness handling of texture feature in RS image. The method has two steps: 1) Correlativity analyzing of texture statistical parameters in Grey Level Co-occurrence Matrix (GLCM) and parameters fuzzification. GLCM can be used to representing the texture feature in many aspects perfectly. According to the expressive force of texture statistical parameters and by Correlativity analyzing of texture statistical parameters, we can abstract a few texture statistical parameters that can best represent the texture feature. By the fuzziness algorithm, the texture statistical parameters can be mapped to fuzzy cloud space. 2) Texture multi-dimensions cloud model constructing. Based on the abstracted texture statistical parameters and fuzziness cloud space, texture multi-dimensions cloud model can be constructed in micro-windows of image. According to the membership of texture statistical parameters, we can achieve the samples of cloud-drop. By backward cloud generator, the digital characteristics of texture multi-dimensions cloud model can be achieved and the Mathematical Expected Hyper Surface(MEHS) of multi-dimensions cloud of micro-windows can be constructed. At last, the weighted sum of the 3 digital characteristics of micro-window cloud model was proposed and used in texture representing in RS image. The method we develop is demonstrated by applying it to texture representing in many RS images, various performance studies testify that the method is both efficient and effective. It enriches the cloud

  6. 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.

  7. Soft sensor design by multivariate fusion of image features and process measurements

    DEFF Research Database (Denmark)

    Lin, Bao; Jørgensen, Sten Bay

    2011-01-01

    the weight of each regressor, is achieved through multivariate regression. The framework is described and illustrated with applications to cement kiln systems that are characterized by off-line quality measurements and on-line analyzers with limited reliability. Image features are extracted...... with a multivariate analysis technique from RGB pictures. The color information is also transformed to hue, saturation and intensity components. Both sets of image features are combined with traditional process measurements to obtain an inferential model by partial least squares (PLS) regression. A dynamic PLS model...... 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...

  8. Automatic segmentation of closed-contour features in ophthalmic images using graph theory and dynamic programming.

    Science.gov (United States)

    Chiu, Stephanie J; Toth, Cynthia A; Bowes Rickman, Catherine; Izatt, Joseph A; Farsiu, Sina

    2012-05-01

    This paper presents a generalized framework for segmenting closed-contour anatomical and pathological features using graph theory and dynamic programming (GTDP). More specifically, the GTDP method previously developed for quantifying retinal and corneal layer thicknesses is extended to segment objects such as cells and cysts. The presented technique relies on a transform that maps closed-contour features in the Cartesian domain into lines in the quasi-polar domain. The features of interest are then segmented as layers via GTDP. Application of this method to segment closed-contour features in several ophthalmic image types is shown. Quantitative validation experiments for retinal pigmented epithelium cell segmentation in confocal fluorescence microscopy images attests to the accuracy of the presented technique.

  9. Multiscale registration of remote sensing image using robust SIFT features in Steerable-Domain

    Directory of Open Access Journals (Sweden)

    Xiangzeng Liu

    2011-12-01

    Full Text Available This paper proposes a multiscale registration technique using robust Scale Invariant Feature Transform (SIFT features in Steerable-Domain, which can deal with the large variations of scale, rotation and illumination between images. First, a new robust SIFT descriptor is presented, which is invariant under affine transformation. Then, an adaptive similarity measure is developed according to the robust SIFT descriptor and the adaptive normalized cross correlation of feature point’s neighborhood. Finally, the corresponding feature points can be determined by the adaptive similarity measure in Steerable-Domain of the two input images, and the final refined transformation parameters determined by using gradual optimization are adopted to achieve the registration results. Quantitative comparisons of our algorithm with the related methods show a significant improvement in the presence of large scale, rotation changes, and illumination contrast. The effectiveness of the proposed method is demonstrated by the experimental results.

  10. 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.

  11. 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.

  12. 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.

  13. 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.

  14. Identity Recognition Algorithm Using Improved Gabor Feature Selection of Gait Energy Image

    Science.gov (United States)

    Chao, LIANG; Ling-yao, JIA; Dong-cheng, SHI

    2017-01-01

    This paper describes an effective gait recognition approach based on Gabor features of gait energy image. In this paper, the kernel Fisher analysis combined with kernel matrix is proposed to select dominant features. The nearest neighbor classifier based on whitened cosine distance is used to discriminate different gait patterns. The approach proposed is tested on the CASIA and USF gait databases. The results show that our approach outperforms other state of gait recognition approaches in terms of recognition accuracy and robustness.

  15. 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.

  16. 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. 

  17. 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.

  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. Matching suitable feature construction for SAR images based on evolutionary synthesis strategy

    Institute of Scientific and Technical Information of China (English)

    Bu Yanlong; Tang Geshi; Liu Hongfu; Pan Liang

    2013-01-01

    In the paper, a set of algorithms to construct synthetic aperture radar (SAR) matching suitable features are firstly proposed based on the evolutionary synthesis strategy. During the pro-cess, on the one hand, the indexes of primary matching suitable features (PMSFs) are designed based on the characteristics of image texture, SAR imaging and SAR matching algorithm, which is a process involving expertise;on the other hand, by designing a synthesized operation expression tree based on PMSFs, a much more flexible expression form of synthesized features is built, which greatly expands the construction space. Then, the genetic algorithm-based optimized searching process is employed to search the synthesized matching suitable feature (SMSF) with the highest efficiency, largely improving the optimized searching efficiency. In addition, the experimental results of the airborne synthetic aperture radar ortho-images of C-band and P-band show that the SMSFs gained via the algorithms can reflect the matching suitability of SAR images accurately and the matching probabilities of selected matching suitable areas of ortho-images could reach 99 ± 0.5%.

  20. Classification of photographed document images based on deep-learning features

    Science.gov (United States)

    Zhong, Guoqiang; Yao, Hui; Liu, Yutong; Hong, Chen; Pham, Tuan

    2017-02-01

    In this paper, we propose two new problems related to classification of photographed document images, and based on deep learning methods, present the baseline solutions for these two problems. The first problem is that, for some photographed document images, which book do they belong to? The second one is, for some photographed document images, what is the type of the book they belong to? To address these two problems, we apply "AexNet" to the collected document images. Using the pre-trained "AlexNet" on the ImageNet data set directly, we obtain 92.57% accuracy for the book-name classification and 93.33% accuracy for the book-type one. After fine-tuning on the training set of the photographed document images, the accuracy of the book-name classification increases to 95.54% and that of the booktype one to 95.42%. To our best knowledge, although there exist many image classification algorithm, no previous work has targeted to these two challenging problems. In addition, the experiments demonstrate that deep-learning features outperform features extracted with traditional image descriptors on these two problems.

  1. Least-Squares Estimation of Imaging Parameters for an Ultrasonic Array Using Known Geometric Image Features

    NARCIS (Netherlands)

    Hunter, A.J.; Drinkwater, B.W.; Wilcox, P.D.

    2011-01-01

    Ultrasonic array images are adversely affected by errors in the assumed or measured imaging parameters. For non-destructive testing and evaluation, this can result in reduced defect detection and characterization performance. In this paper, an autofocus algorithm is presented for estimating and corr

  2. Content-Based Image Retrieval using Local Features Descriptors and Bag-of-Visual Words

    Directory of Open Access Journals (Sweden)

    Mohammed Alkhawlani

    2015-09-01

    Full Text Available Image retrieval is still an active research topic in the computer vision field. There are existing several techniques to retrieve visual data from large databases. Bag-of-Visual Word (BoVW is a visual feature descriptor that can be used successfully in Content-based Image Retrieval (CBIR applications. In this paper, we present an image retrieval system that uses local feature descriptors and BoVW model to retrieve efficiently and accurately similar images from standard databases. The proposed system uses SIFT and SURF techniques as local descriptors to produce image signatures that are invariant to rotation and scale. As well as, it uses K-Means as a clustering algorithm to build visual vocabulary for the features descriptors that obtained of local descriptors techniques. To efficiently retrieve much more images relevant to the query, SVM algorithm is used. The performance of the proposed system is evaluated by calculating both precision and recall. The experimental results reveal that this system performs well on two different standard datasets.

  3. Dengue encephalitis with predominant cerebellar involvement: Report of eight cases with MR and CT imaging features

    Energy Technology Data Exchange (ETDEWEB)

    Hegde, Vinay; Bhat, Maya; Prasad, Chandrajit; Gupta, A.K.; Saini, Jitender [National Institute of Mental Health and Neurosciences, Department of Neuroimaging and Interventional Radiology, Bangalore, Karnataka (India); Aziz, Zarina [Sri Sathya Sai Institute of Medical Science, Department of Radiology, Bangalore (India); Kumar, Sharath [Apollo Hospital, Department of Neuroradiology, Bangalore (India); Netravathi, M. [National Institute of Mental Health and Neurosciences, Department of Neurology, Bangalore (India)

    2014-11-01

    CNS dengue infection is a rare condition and the pattern of brain involvement has not been well described. We report the MR imaging (MRI) features in eight cases of dengue encephalitis. We retrospectively searched cases of dengue encephalitis in which imaging was performed. Eight cases (three men, five women; age range: 8-42 years) diagnosed with dengue encephalitis were included in the study. MR studies were performed on 3-T and 1.5-T MR clinical systems. Two neuroradiologists retrospectively reviewed the MR images and analysed the type of lesions, as well as their distribution and imaging features. All eight cases exhibited MRI abnormalities and the cerebellum was involved in all cases. In addition, MRI signal changes were also noted in the brainstem, thalamus, basal ganglia, internal capsule, insula, mesial temporal lobe, and cortical and cerebral white matter. Areas of susceptibility, diffusion restriction, and patchy post-contrast enhancement were the salient imaging features in our cohort of cases. A pattern of symmetrical cerebellar involvement and presence of microbleeds/haemorrhage may serve as a useful imaging marker and may help in the diagnosis of dengue encephalitis. (orig.)

  4. Spectrum and Image Texture Features Analysis for Early Blight Disease Detection on Eggplant Leaves

    Directory of Open Access Journals (Sweden)

    Chuanqi Xie

    2016-05-01

    Full Text Available This study investigated both spectrum and texture features for detecting early blight disease on eggplant leaves. Hyperspectral images for healthy and diseased samples were acquired covering the wavelengths from 380 to 1023 nm. Four gray images were identified according to the effective wavelengths (408, 535, 624 and 703 nm. Hyperspectral images were then converted into RGB, HSV and HLS images. Finally, eight texture features (mean, variance, homogeneity, contrast, dissimilarity, entropy, second moment and correlation based on gray level co-occurrence matrix (GLCM were extracted from gray images, RGB, HSV and HLS images, respectively. The dependent variables for healthy and diseased samples were set as 0 and 1. K-Nearest Neighbor (KNN and AdaBoost classification models were established for detecting healthy and infected samples. All models obtained good results with the classification rates (CRs over 88.46% in the testing sets. The results demonstrated that spectrum and texture features were effective for early blight disease detection on eggplant leaves.

  5. Local texton XOR patterns: A new feature descriptor for content-based image retrieval

    Directory of Open Access Journals (Sweden)

    Anu Bala

    2016-03-01

    Full Text Available In this paper, a novel feature descriptor, local texton XOR patterns (LTxXORP is proposed for content-based image retrieval. The proposed method collects the texton XOR pattern which gives the structure of the query image or database image. First, the RGB (red, green, blue color image is converted into HSV (hue, saturation and value color space. Second, the V color space is divided into overlapping subblocks of size 2 × 2 and textons are collected based on the shape of the textons. Then, exclusive OR (XOR operation is performed on the texton image between the center pixel and its surrounding neighbors. Finally, the feature vector is constructed based on the LTxXORPs and HSV histograms. The performance of the proposed method is evaluated by testing on benchmark database, Corel-1K, Corel-5K and Corel-10K in terms of precision, recall, average retrieval precision (ARP and average retrieval rate (ARR. The results after investigation show a significant improvement as compared to the state-of-the-art features for image retrieval.

  6. Geometrically robust image watermarking using scale-invariant feature transform and Zernike moments

    Institute of Scientific and Technical Information of China (English)

    Leida Li; Baolong Guo; Kai Shao

    2007-01-01

    In order to resist geometric attacks, a robust image watermarking algorithm is proposed using scaleinvariant feature transform (SIFT) and Zernike moments. As SIFT features are invariant to rotation and scaling, we employ SIFT to extract feature points. Then circular patches are generated using the most robust points. An invariant watermark is generated from each circular patch based on Zernike moments.The watermark is embedded into multiple patches for resisting locally cropping attacks. Experimental results show that the proposed scheme is robust to both geometric attacks and signal processing attacks.

  7. Satellite Imagery Cadastral Features Extractions using Image Processing Algorithms: A Viable Option for Cadastral Science

    Directory of Open Access Journals (Sweden)

    Usman Babawuro

    2012-07-01

    Full Text Available Satellite images are used for feature extraction among other functions. They are used to extract linear features, like roads, etc. These linear features extractions are important operations in computer vision. Computer vision has varied applications in photogrammetric, hydrographic, cartographic and remote sensing tasks. The extraction of linear features or boundaries defining the extents of lands, land covers features are equally important in Cadastral Surveying. Cadastral Surveying is the cornerstone of any Cadastral System. A two dimensional cadastral plan is a model which represents both the cadastral and geometrical information of a two dimensional labeled Image. This paper aims at using and widening the concepts of high resolution Satellite imagery data for extracting representations of cadastral boundaries using image processing algorithms, hence minimizing the human interventions. The Satellite imagery is firstly rectified hence establishing the satellite imagery in the correct orientation and spatial location for further analysis. We, then employ the much available Satellite imagery to extract the relevant cadastral features using computer vision and image processing algorithms. We evaluate the potential of using high resolution Satellite imagery to achieve Cadastral goals of boundary detection and extraction of farmlands using image processing algorithms. This method proves effective as it minimizes the human demerits associated with the Cadastral surveying method, hence providing another perspective of achieving cadastral goals as emphasized by the UN cadastral vision. Finally, as Cadastral science continues to look to the future, this research aimed at the analysis and getting insights into the characteristics and potential role of computer vision algorithms using high resolution satellite imagery for better digital Cadastre that would provide improved socio economic development.

  8. A graph lattice approach to maintaining and learning dense collections of subgraphs as image features.

    Science.gov (United States)

    Saund, Eric

    2013-10-01

    Effective object and scene classification and indexing depend on extraction of informative image features. This paper shows how large families of complex image features in the form of subgraphs can be built out of simpler ones through construction of a graph lattice—a hierarchy of related subgraphs linked in a lattice. Robustness is achieved by matching many overlapping and redundant subgraphs, which allows the use of inexpensive exact graph matching, instead of relying on expensive error-tolerant graph matching to a minimal set of ideal model graphs. Efficiency in exact matching is gained by exploitation of the graph lattice data structure. Additionally, the graph lattice enables methods for adaptively growing a feature space of subgraphs tailored to observed data. We develop the approach in the domain of rectilinear line art, specifically for the practical problem of document forms recognition. We are especially interested in methods that require only one or very few labeled training examples per category. We demonstrate two approaches to using the subgraph features for this purpose. Using a bag-of-words feature vector we achieve essentially single-instance learning on a benchmark forms database, following an unsupervised clustering stage. Further performance gains are achieved on a more difficult dataset using a feature voting method and feature selection procedure.

  9. IMAGING SPECTROSCOPY AND LIGHT DETECTION AND RANGING DATA FUSION FOR URBAN FEATURES EXTRACTION

    Directory of Open Access Journals (Sweden)

    Mohammed Idrees

    2013-01-01

    Full Text Available 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 classification (k-mean algorithm and the accuracy of the classification assessed. Digital Surface Model (DSM and LiDAR intensity were generated from the LiDAR point cloud. The LiDAR intensity was filtered to remove the noise. Hue Saturation Intensity (HSI fusion algorithm was used to fuse the imaging spectroscopy and DSM as well as imaging spectroscopy and filtered intensity. The fusion of imaging spectroscopy and DSM was found to be better than that of imaging spectroscopy and LiDAR intensity quantitatively. The three datasets (imaging spectrocopy, DSM and Lidar intensity fused data were classified into four classes: building, pavement, trees and grass using unsupervised classification and the accuracy of the classification assessed. The result of the study shows that fusion of imaging spectroscopy and LiDAR data improved the visual identification of surface features. Also, the classification accuracy improved from an overall accuracy of 84.6% for the imaging spectroscopy data to 90.2% for the DSM fused data. Similarly, the Kappa Coefficient increased from 0.71 to 0.82. on the other hand, classification of the fused LiDAR intensity and imaging spectroscopy data perform poorly quantitatively with overall accuracy of 27.8% and kappa coefficient of 0.0988.

  10. Burkina Faso - BRIGHT II

    Data.gov (United States)

    Millennium Challenge Corporation — Millennium Challenge Corporation hired Mathematica Policy Research to conduct an independent evaluation of the BRIGHT II program. The three main research questions...

  11. Aircraft Detection from VHR Images Based on Circle-Frequency Filter and Multilevel Features

    Directory of Open Access Journals (Sweden)

    Feng Gao

    2013-01-01

    Full Text Available Aircraft automatic detection from very high-resolution (VHR images plays an important role in a wide variety of applications. This paper proposes a novel detector for aircraft detection from very high-resolution (VHR remote sensing images. To accurately distinguish aircrafts from background, a circle-frequency filter (CF-filter is used to extract the candidate locations of aircrafts from a large size image. A multi-level feature model is then employed to represent both local appearance and spatial layout of aircrafts by means of Robust Hue Descriptor and Histogram of Oriented Gradients. The experimental results demonstrate the superior performance of the proposed method.

  12. Aircraft Detection from VHR Images Based on Circle-Frequency Filter and Multilevel Features

    Science.gov (United States)

    Gao, Feng; Li, Bo

    2013-01-01

    Aircraft automatic detection from very high-resolution (VHR) images plays an important role in a wide variety of applications. This paper proposes a novel detector for aircraft detection from very high-resolution (VHR) remote sensing images. To accurately distinguish aircrafts from background, a circle-frequency filter (CF-filter) is used to extract the candidate locations of aircrafts from a large size image. A multi-level feature model is then employed to represent both local appearance and spatial layout of aircrafts by means of Robust Hue Descriptor and Histogram of Oriented Gradients. The experimental results demonstrate the superior performance of the proposed method. PMID:24163637

  13. Mean shift texture surface detection based on WT and COM feature image selection

    Institute of Scientific and Technical Information of China (English)

    HAN Yan-fang; SHI Peng-fei

    2006-01-01

    Mean shift is a widely used clustering algorithm in image segmentation. However, the segmenting results are not so good as expected when dealing with the texture surface due to the influence of the textures. Therefore, an approach based on wavelet transform (WT), co-occurrence matrix (COM) and mean shift is proposed in this paper. First, WT and COM are employed to extract the optimal resolution approximation of the original image as feature image. Then, mean shift is successfully used to obtain better detection results. Finally, experiments are done to show this approach is effective.

  14. An Image Denoising Method with Enhancement of the Directional Features Based on Wavelet and SVD Transforms

    OpenAIRE

    Min Wang; Zhen Li; Xiangjun Duan; Wei Li

    2015-01-01

    This paper proposes an image denoising method, using the wavelet transform and the singular value decomposition (SVD), with the enhancement of the directional features. First, use the single-level discrete 2D wavelet transform to decompose the noised image into the low-frequency image part and the high-frequency parts (the horizontal, vertical, and diagonal parts), with the edge extracted and retained to avoid edge loss. Then, use the SVD to filter the noise of the high-frequency parts with i...

  15. IMAGING DIAGNOSIS-MAGNETIC RESONANCE IMAGING FEATURES OF CRANIOMANDIBULAR OSTEOPATHY IN AN AIREDALE TERRIER.

    Science.gov (United States)

    Matiasovic, Matej; Caine, Abby; Scarpante, Elena; Cherubini, Giunio Bruto

    2016-05-01

    An Airedale Terrier was presented for evaluation of depression and reluctance to be touched on the head. Magnetic resonance (MR) imaging of the head was performed. The images revealed bone lesions affecting the calvarium at the level of the coronal suture and left mandibular ramus, with focal cortical destruction, expansion, and reactive new bone formation. Skull lesions were hypointense on T1-weighted sequences, hyperintense on T2-weighted sequences, and showed an intense and homogeneous enhancement after gadolinium administration. Reactive new bone formation and periosteal proliferation were confirmed histopathologically. The clinical signs, imaging findings, and histopathological examination were consistent with craniomandibular osteopathy.

  16. Variations in the Fe mineralogy of bright Martian soil

    Science.gov (United States)

    Murchie, Scott; Mustard, John; Erard, Stephane; Geissler, Paul; Singer, Robert

    1993-01-01

    Bright regions on Mars are interpreted as 'soil' derived by chemical alteration of crustal rocks, whose main pigmentary component is ferric oxide or oxyhydroxide. The mineralogy and mineralogic variability of ferric iron are important evidence for the evolution of Martian soil: mineralogy of ferric phases is sensitive to chemical conditions in their genetic environments, and the spatial distributions of different ferric phases would record a history of both chemical environments and physical mixing. Reflectance spectroscopic studies provide several types of evidence that discriminate possible pigmentary phases, including the position of a crystal field absorption near 0.9 microns and position and strengths of absorptions in the UV-visible wavelength region. Recent telescopic spectra and laboratory measurements of Mars soil analogs suggest that spectral features of bright soil can be explained based on a single pigmentary phase, hematite (alpha-Fe2O3), occurring in both 'nanophase' and more crystalline forms. Here we report on a systematic investigation of Martian bright regions using ISM imaging spectrometer data, in which we examined spatial variations in the position and shape of the approximately 0.9 microns absorption. We found both local and regional heterogeneities that indicate differences in Fe mineralogy. These results demonstrate that bright soils do not represent a single lithology that has been homogenized by eolian mixing, and suggest that weathering of soils in different geologic settings has followed different physical and chemical pathways.

  17. Imaging Features of Radiofrequency Ablation with Heat-Deployed Liposomal Doxorubicin in Hepatic Tumors

    Energy Technology Data Exchange (ETDEWEB)

    Hong, Cheng William, E-mail: williamhongcheng@gmail.com; Chow, Lucy, E-mail: lucychow282@gmail.com [National Institutes of Health, Center for Interventional Oncology, Clinical Center (United States); Turkbey, Evrim B., E-mail: evrimbengi@yahoo.com [National Institutes of Health, Radiology and Imaging Sciences, Clinical Center (United States); Lencioni, Riccardo, E-mail: riccardo.lencioni@med.unipi.it [Pisa University Hospital, Division of Diagnostic Imaging and Intervention, Department of Hepatology and Liver Transplantation (Italy); Libutti, Steven K., E-mail: slibutti@montefiore.org [Albert Einstein College of Medicine, Montefiore-Einstein Center for Cancer Care, Department of Surgery (United States); Wood, Bradford J., E-mail: bwood@nih.gov [National Institutes of Health, Center for Interventional Oncology, Clinical Center (United States)

    2016-03-15

    IntroductionThe imaging features of unresectable hepatic malignancies in patients who underwent radiofrequency ablation (RFA) in combination with lyso-thermosensitive liposomal doxorubicin (LTLD) were determined.Materials and MethodsA phase I dose escalation study combining RFA with LTLD was performed with peri- and post- procedural CT and MRI. Imaging features were analyzed and measured in terms of ablative zone size and surrounding penumbra size. The dynamic imaging appearance was described qualitatively immediately following the procedure and at 1-month follow-up. The control group receiving liver RFA without LTLD was compared to the study group in terms of imaging features and post-ablative zone size dynamics at follow-up.ResultsPost-treatment scans of hepatic lesions treated with RFA and LTLD have distinctive imaging characteristics when compared to those treated with RFA alone. The addition of LTLD resulted in a regular or smooth enhancing rim on T1W MRI which often correlated with increased attenuation on CT. The LTLD-treated ablation zones were stable or enlarged at follow-up four weeks later in 69 % of study subjects as opposed to conventional RFA where the ablation zone underwent involution compared to imaging acquired immediately after the procedure.ConclusionThe imaging features following RFA with LTLD were different from those after standard RFA and can mimic residual or recurrent tumor. Knowledge of the subtle findings between the two groups can help avoid misinterpretation and proper identification of treatment failure in this setting. Increased size of the LTLD-treated ablation zone after RFA suggests the ongoing drug-induced biological effects.

  18. Development of estimation system of knee extension strength using image features in ultrasound images of rectus femoris

    Science.gov (United States)

    Murakami, Hiroki; Watanabe, Tsuneo; Fukuoka, Daisuke; Terabayashi, Nobuo; Hara, Takeshi; Muramatsu, Chisako; Fujita, Hiroshi

    2016-04-01

    The word "Locomotive syndrome" has been proposed to describe the state of requiring care by musculoskeletal disorders and its high-risk condition. Reduction of the knee extension strength is cited as one of the risk factors, and the accurate measurement of the strength is needed for the evaluation. The measurement of knee extension strength using a dynamometer is one of the most direct and quantitative methods. This study aims to develop a system for measuring the knee extension strength using the ultrasound images of the rectus femoris muscles obtained with non-invasive ultrasonic diagnostic equipment. First, we extract the muscle area from the ultrasound images and determine the image features, such as the thickness of the muscle. We combine these features and physical features, such as the patient's height, and build a regression model of the knee extension strength from training data. We have developed a system for estimating the knee extension strength by applying the regression model to the features obtained from test data. Using the test data of 168 cases, correlation coefficient value between the measured values and estimated values was 0.82. This result suggests that this system can estimate knee extension strength with high accuracy.

  19. SEGMENTATION OF POLARIMETRIC SAR IMAGES USIG WAVELET TRANSFORMATION AND TEXTURE FEATURES

    Directory of Open Access Journals (Sweden)

    A. Rezaeian

    2015-12-01

    Full Text Available Polarimetric Synthetic Aperture Radar (PolSAR sensors can collect useful observations from earth’s surfaces and phenomena for various remote sensing applications, such as land cover mapping, change and target detection. These data can be acquired without the limitations of weather conditions, sun illumination and dust particles. As result, SAR images, and in particular Polarimetric SAR (PolSAR are powerful tools for various environmental applications. Unlike the optical images, SAR images suffer from the unavoidable speckle, which causes the segmentation of this data difficult. In this paper, we use the wavelet transformation for segmentation of PolSAR images. Our proposed method is based on the multi-resolution analysis of texture features is based on wavelet transformation. Here, we use the information of gray level value and the information of texture. First, we produce coherency or covariance matrices and then generate span image from them. In the next step of proposed method is texture feature extraction from sub-bands is generated from discrete wavelet transform (DWT. Finally, PolSAR image are segmented using clustering methods as fuzzy c-means (FCM and k-means clustering. We have applied the proposed methodology to full polarimetric SAR images acquired by the Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR L-band system, during July, in 2012 over an agricultural area in Winnipeg, Canada.

  20. Benign Conditions That Mimic Prostate Carcinoma: MR Imaging Features with Histopathologic Correlation.

    Science.gov (United States)

    Kitzing, Yu Xuan; Prando, Adilson; Varol, Celi; Karczmar, Gregory S; Maclean, Fiona; Oto, Aytekin

    2016-01-01

    Multiparametric magnetic resonance (MR) imaging combines anatomic and functional imaging techniques for evaluating the prostate and is increasingly being used in diagnosis and management of prostate cancer. A wide spectrum of anatomic and pathologic processes in the prostate may masquerade as prostate cancer, complicating the imaging interpretation. The histopathologic and imaging findings of these potential mimics are reviewed. These entities include the anterior fibromuscular stroma, surgical capsule, central zone, periprostatic vein, periprostatic lymph nodes, benign prostatic hyperplasia (BPH), atrophy, necrosis, calcification, hemorrhage, and prostatitis. An understanding of the prostate zonal anatomy is helpful in distinguishing the anatomic entities from prostate cancer. The anterior fibromuscular stroma, surgical capsule, and central zone are characteristic anatomic features of the prostate with associated low T2 signal intensity due to dense fibromuscular tissue or complex crowded glandular tissue. BPH, atrophy, necrosis, calcification, and hemorrhage all have characteristic features with one or more individual multiparametric MR imaging modalities. Prostatitis constitutes a heterogeneous group of infective and inflammatory conditions including acute and chronic bacterial prostatitis, infective and noninfective granulomatous prostatitis, and malacoplakia. These entities are associated with variable clinical manifestations and are characterized by the histologic hallmark of marked inflammatory cellular infiltration. In some cases, these entities are indistinguishable from prostate cancer at multiparametric MR imaging and may even exhibit extraprostatic extension and lymphadenopathy, mimicking locally advanced prostate cancer. It is important for the radiologists interpreting prostate MR images to be aware of these pitfalls for accurate interpretation. Online supplemental material is available for this article.

  1. Nasopharyngeal adenoid cystic carcinoma: magnetic resonance imaging features in ten cases

    Institute of Scientific and Technical Information of China (English)

    Xue-Wen Liu; Pei-Hong Wu; Chuan-Miao Xie; Hui Li; Rong Zhang; Zhi-Jun Geng; Yun-Xian Mo; Jing Zhao; Mu-Yan Cai; Yan-Chun Lv

    2012-01-01

    Nasopharyngeal adenoid cystic carcinoma (NACC) is a rare malignancy with high local invasiveness.To date,there is no consensus on the imaging characteristics of NACC.To address this,we retrospectively reviewed 10 cases of NACC and summarized the magnetic resonance imaging (MRI) features.MR images of 10 patients with histologically validated NACC were reviewed by two experienced radiologists.The location,shape,margin,signal intensity,lesion texture,contrast enhancement patterns,local invasion,and cervical lymphadenopathy of all tumors were evaluated.Clinical and pathologic records were also reviewed.No patients were positive for antibodies against Epstein-Barr virus (EBV).The imaging patterns of primary tumors were classified into two types as determined by location,shape,and margin.Of all patients,7 had tumors with a type 1 imaging pattern and 3 had tumors with a type 2 imaging pattern.The 4 tubular NACCs were all homogeneous tumors,whereas 3 (60%) of 5 cribriform NACCs and the sole solid NACC were heterogeneous tumors with separations or central necrosis on MR images.Five patients had perineural infiltration and intracranial involvement,and only 2 had cervical lymphadenopathy.Based on these results,we conclude that NACC is a local,aggressive neoplasm that is often negative for EBV infection and associated with a low incidence of cervical lymphadenopathy.Furthermore,MRI features of NACC vary in locations and histological subtypes.

  2. Automatic Fusion of Hyperspectral Images and Laser Scans Using Feature Points

    Directory of Open Access Journals (Sweden)

    Xiao Zhang

    2015-01-01

    Full Text Available Automatic fusion of different kinds of image datasets is so intractable with diverse imaging principle. This paper presents a novel method for automatic fusion of two different images: 2D hyperspectral images acquired with a hyperspectral camera and 3D laser scans obtained with a laser scanner, without any other sensor. Only a few corresponding feature points are used, which are automatically extracted from a scene viewed by the two sensors. Extraction method of feature points relies on SURF algorithm and camera model, which can convert a 3D laser scan into a 2D laser image with the intensity of the pixels defined by the attributes in the laser scan. Moreover, Collinearity Equation and Direct Linear Transformation are used to create the initial corresponding relationship of the two images. Adjustment is also used to create corrected values to eliminate errors. The experimental result shows that this method is successfully validated with images collected by a hyperspectral camera and a laser scanner.

  3. Oblique low-altitude image matching using robust perspective invariant features

    Science.gov (United States)

    He, Haiqing; Du, Jing; Chen, Xiaoyong; Wang, Yuqian

    2017-01-01

    Compared with vertical photogrammtry, oblique photogrammetry is radically different for images acquired from sensor with big yaw, pitch, and roll angles. Image matching is a vital step and core problem of oblique low-altitude photogrammetric process. Among the most popular oblique images matching methods are currently SIFT/ASIFT and many affine invariant feature-based approaches, which are mainly used in computer vision, while these methods are unsuitable for requiring evenly distributed corresponding points and high efficiency simultaneously in oblique photogrammetry. In this paper, we present an oblique low-altitude images matching approach using robust perspective invariant features. Firstly, the homography matrix is estimated by a few corresponding points obtained from top pyramid images matching in several projective simulation. Then images matching are implemented by sub-pixel Harris corners and descriptors after shape perspective transforming on the basis of homography matrix. Finally, the error or gross error matched points are excluded by epipolar geometry, RANSAC algorithm and back projection constraint. Experimental results show that the proposed approach can achieve more excellent performances in oblique low-altitude images matching than the common methods, including SIFT and SURF. And the proposed approach can significantly improve the computational efficiency compared with ASIFT and Affine-SURF.

  4. Sensitivity of Image Features to Noise in Conventional and Respiratory-Gated PET/CT Images of Lung Cancer: Uncorrelated Noise Effects.

    Science.gov (United States)

    Oliver, Jasmine A; Budzevich, Mikalai; Hunt, Dylan; Moros, Eduardo G; Latifi, Kujtim; Dilling, Thomas J; Feygelman, Vladimir; Zhang, Geoffrey

    2016-08-08

    The effect of noise on image features has yet to be studied in depth. Our objective was to explore how significantly image features are affected by the addition of uncorrelated noise to an image. The signal-to-noise ratio and noise power spectrum were calculated for a positron emission tomography/computed tomography scanner using a Ge-68 phantom. The conventional and respiratory-gated positron emission tomography/computed tomography images of 31 patients with lung cancer were retrospectively examined. Multiple sets of noise images were created for each original image by adding Gaussian noise of varying standard deviation equal to 2.5%, 4.0%, and 6.0% of the maximum intensity for positron emission tomography images and 10, 20, 50, 80, and 120 Hounsfield units for computed tomography images. Image features were extracted from all images, and percentage differences between the original image and the noise image feature values were calculated. These features were then categorized according to the noise sensitivity. The contour-dependent shape descriptors averaged below 4% difference in positron emission tomography and below 13% difference in computed tomography between noise and original images. Gray level size zone matrix features were the most sensitive to uncorrelated noise exhibiting average differences >200% for conventional and respiratory-gated images in computed tomography and 90% in positron emission tomography. Image feature differences increased as the noise level increased for shape, intensity, and gray-level co-occurrence matrix features in positron emission tomography and for gray-level co-occurrence matrix and gray-level size zone matrix features in conventional computed tomography. Investigators should be aware of the noise effects on image features.

  5. On Feature Relevance in Image-Based Prediction Models: An Empirical Study

    DEFF Research Database (Denmark)

    Konukoglu, E.; Ganz, Melanie; Van Leemput, Koen;

    2013-01-01

    as binary classification of Alzheimer’s Disease (AD) from brain Magnetic Resonance Imaging (MRI) data. Our experiments demonstrate that aging-related and AD-related variations are widespread and the initial sets of relevant features discovered by the methods are not exhaustive. Our findings show...

  6. Joint Applied Optics and Chinese Optics Letters feature introduction: digital holography and three-dimensional imaging

    OpenAIRE

    Poon, Ting-Chung

    2011-01-01

    This feature issue serves as a pilot issue promoting the joint issue of Applied Optics and Chinese Optics Letters. It focuses upon topics of current relevance to the community working in the area of digital holography and 3-D imaging. (C) 2011 Optical Society of America

  7. Photoacoustic imaging of blood vessels with a double-ring sensor featuring a narrow angular aperture

    NARCIS (Netherlands)

    Kolkman, Roy G.M.; Hondebrink, Erwin; Steenbergen, Wiendelt; Leeuwen, van Ton G.; Mul, de Frits F.M.

    2004-01-01

    A photoacoustic double-ring sensor, featuring a narrow angular aperture, is developed for laser-induced photoacoustic imaging of blood vessels. An integrated optical fiber enables reflection-mode detection of ultrasonic waves. By using the cross-correlation between the signals detected by the two ri

  8. An alternative to scale-space representation for extracting local features in image recognition

    DEFF Research Database (Denmark)

    Andersen, Hans Jørgen; Nguyen, Phuong Giang

    2012-01-01

    In image recognition, the common approach for extracting local features using a scale-space representation has usually three main steps; first interest points are extracted at different scales, next from a patch around each interest point the rotation is calculated with corresponding orientation...

  9. Clinical, electrophysiological and brain imaging features during recurrent ictal cortical blindness associated with chronic liver failure.

    Science.gov (United States)

    van Pesch, V; Hernalsteen, D; van Rijckevorsel, K; Duprez, Th; Boschi, A; Ivanoiu, A; Sindic, C J M

    2006-12-01

    Transient neuroimaging features indicating primary cortical and secondary subcortical white matter cytotoxic oedema have been described in association with prolonged or intense seizures. We describe the unusual condition of recurrent ictal cortical blindness due to focal occipital status epilepticus, in the context of chronic hepatic failure. There was a close association between the onset and disappearance of clinical, electrophysiological and magnetic resonance imaging abnormalities.

  10. Mosaic of the Curved Human Retinal Images Based on the Scale-Invariant Feature Transform

    Institute of Scientific and Technical Information of China (English)

    LI Ju-peng; CHEN Hou-jin; ZHANG Xin-yuan; YAO Chang

    2008-01-01

    .To meet the needs in the fundus examination, including outlook widening, pathology tracking, etc., this paper describes a robust feature-based method for fully-automatic mosaic of the curved human retinal images photographed by a fundus microscope. The kernel of this new algorithm is the scale-, rotation-and illumination-invariant interest point detector & feature descriptor-Scale-Invariant Feature Transform. When matched interest points according to second-nearest-neighbor strategy, the parameters of the model are estimated using the correct matches of the interest points,extracted by a new inlier identification scheme based on Sampson distance from putative sets. In order to preserve image features, bilinear warping and multi-band blending techniques are used to create panoramic retinal images. Experiments show that the proposed method works well with rejection error in 0.3 pixels, even for those cases where the retinal images without discernable vascular structure in contrast to the state-of-the-art algorithms.

  11. Classification of Infrared Monitor Images of Coal Using an Feature Texture Statistics and Improved BP Network

    Institute of Scientific and Technical Information of China (English)

    2007-01-01

    It is very important to accurately recognize and locate pulverized and block coal seen in a coal mine's infrared image monitoring system.Infrared monitor images of pulverized and block coal were sampled in the roadway of a coal mine.Texture statistics from the grey level dependence matrix were selected as the criterion for classification.The distributions of the texture statistics were calculated and analysed.A normalizing function was added to the front end of the BP network with one hidden layer.An additional classification layer is joined behind the linear layer.The recognition of pulverized from block coal images was tested using the improved BP network.The results of the experiment show that texture variables from the grey level dependence matrix can act as recognizable features of the image.The innovative improved BP network can then recognize the pulverized and block coal images.

  12. Feature-based fusion of infrared and visible dynamic images using target detection

    Institute of Scientific and Technical Information of China (English)

    Congyi Liu; Zhongliang Jing; Gang Xiao; Bo Yang

    2007-01-01

    We employ the target detection to improve the performance of the feature-based fusion of infrared and visible dynamic images, which forms a novel fusion scheme. First, the target detection is used to segment the source image sequences into target and background regions. Then, the dual-tree complex wavelet transform (DT-CWT) is proposed to decompose all the source image sequences. Different fusion rules are applied respectively in target and background regions to preserve the target information as much as possible. Real world infrared and visible image sequences are used to validate the performance of the proposed novel scheme. Compared with the previous fusion approaches of image sequences, the improvements of shift invariance, temporal stability and consistency, and computation cost are all ensured.

  13. Separation of malignant and benign masses using image and segmentation features

    Science.gov (United States)

    Kinnard, Lisa M.; Lo, Shih-Chung B.; Wang, Paul C.; Freedman, Matthew T.; Chouikha, Mohamed F.

    2003-05-01

    The purpose of this study is to investigate the efficacy of image features versus likelihood features of tumor boundaries for differentiating benign and malignant tumors and to compare the effectiveness of two neural networks in the classification study: (1) circular processing-based neural network and (2) conventional Multilayer Perceptron (MLP). The segmentation method used is an adaptive region growing technique coupled with a fuzzy shadow approach and maximum likelihood analyzer. Intensity, shape, texture, and likelihood features were calculated for the extracted Region of Interest (ROI). We performed these studies: experiment number 1 utilized image features used as inputs and the MLP for classification, experiment number 2 utilized image features used as inputs and the neural net with circular processing for classification, and experiment number 3 used likelihood values as inputs and the MLP for classification. The experiments were validated using an ROC methodology. We have tested these methods on 51 mammograms using a leave-one-case-out experiment (i.e., Jackknife procedure). The Az values for the four experiments were as follows: 0.66 in experiment number 1, 0.71 in experiment number 2, and 0.84 in experiment number 3.

  14. Large Scale Near-Duplicate Celebrity Web Images Retrieval Using Visual and Textual Features

    Directory of Open Access Journals (Sweden)

    Fengcai Qiao

    2013-01-01

    Full Text Available Near-duplicate image retrieval is a classical research problem in computer vision toward many applications such as image annotation and content-based image retrieval. On the web, near-duplication is more prevalent in queries for celebrities and historical figures which are of particular interest to the end users. Existing methods such as bag-of-visual-words (BoVW solve this problem mainly by exploiting purely visual features. To overcome this limitation, this paper proposes a novel text-based data-driven reranking framework, which utilizes textual features and is combined with state-of-art BoVW schemes. Under this framework, the input of the retrieval procedure is still only a query image. To verify the proposed approach, a dataset of 2 million images of 1089 different celebrities together with their accompanying texts is constructed. In addition, we comprehensively analyze the different categories of near duplication observed in our constructed dataset. Experimental results on this dataset show that the proposed framework can achieve higher mean average precision (mAP with an improvement of 21% on average in comparison with the approaches based only on visual features, while does not notably prolong the retrieval time.

  15. Large scale near-duplicate celebrity web images retrieval using visual and textual features.

    Science.gov (United States)

    Qiao, Fengcai; Wang, Cheng; Zhang, Xin; Wang, Hui

    2013-01-01

    Near-duplicate image retrieval is a classical research problem in computer vision toward many applications such as image annotation and content-based image retrieval. On the web, near-duplication is more prevalent in queries for celebrities and historical figures which are of particular interest to the end users. Existing methods such as bag-of-visual-words (BoVW) solve this problem mainly by exploiting purely visual features. To overcome this limitation, this paper proposes a novel text-based data-driven reranking framework, which utilizes textual features and is combined with state-of-art BoVW schemes. Under this framework, the input of the retrieval procedure is still only a query image. To verify the proposed approach, a dataset of 2 million images of 1089 different celebrities together with their accompanying texts is constructed. In addition, we comprehensively analyze the different categories of near duplication observed in our constructed dataset. Experimental results on this dataset show that the proposed framework can achieve higher mean average precision (mAP) with an improvement of 21% on average in comparison with the approaches based only on visual features, while does not notably prolong the retrieval time.

  16. A Method of Road Extraction from High-resolution Remote Sensing Images Based on Shape Features

    Directory of Open Access Journals (Sweden)

    LEI Xiaoqi

    2016-02-01

    Full Text Available Road extraction from high-resolution remote sensing image is an important and difficult task.Since remote sensing images include complicated information,the methods that extract roads by spectral,texture and linear features have certain limitations.Also,many methods need human-intervention to get the road seeds(semi-automatic extraction,which have the great human-dependence and low efficiency.The road-extraction method,which uses the image segmentation based on principle of local gray consistency and integration shape features,is proposed in this paper.Firstly,the image is segmented,and then the linear and curve roads are obtained by using several object shape features,so the method that just only extract linear roads are rectified.Secondly,the step of road extraction is carried out based on the region growth,the road seeds are automatic selected and the road network is extracted.Finally,the extracted roads are regulated by combining the edge information.In experiments,the images that including the better gray uniform of road and the worse illuminated of road surface were chosen,and the results prove that the method of this study is promising.

  17. High-speed video imaging and digital analysis of microscopic features in contracting striated muscle cells

    Science.gov (United States)

    Roos, Kenneth P.; Taylor, Stuart R.

    1993-02-01

    The rapid motion of microscopic features such as the cross striations of single contracting muscle cells are difficult to capture with conventional optical microscopes, video systems, and image processing approaches. An integrated digital video imaging microscope system specifically designed to capture images from single contracting muscle cells at speeds of up to 240 Hz and to analyze images to extract features critical for the understanding of muscle contraction is described. This system consists of a brightfield microscope with immersion optics coupled to a high-speed charge-coupled device (CCD) video camera, super-VHS (S- VHS) and optical media disk video recording (OMDR) systems, and a semiautomated digital image analysis system. Components are modified to optimize spatial and temporal resolution to permit the evaluation of submicrometer features in real physiological time. This approach permits the critical evaluation of the magnitude, time course, and uniformity of contractile function throughout the volume of a single living cell with higher temporal and spatial resolutions than previously possible.

  18. Multi-Modal Ultra-Widefield Imaging Features in Waardenburg Syndrome

    Science.gov (United States)

    Choudhry, Netan; Rao, Rajesh C.

    2015-01-01

    Background Waardenburg syndrome is characterized by a group of features including; telecanthus, a broad nasal root, synophrys of the eyebrows, piedbaldism, heterochromia irides, and deaf-mutism. Hypopigmentation of the choroid is a unique feature of this condition examined with multi-modal Ultra-Widefield Imaging in this report. Material/Methods Report of a single case. Results Bilateral symmetric choroidal hypopigmentation was observed with hypoautofluorescence in the region of hypopigmentation. Fluorescein angiography revealed a normal vasculature, however a thickened choroid was seen on Enhanced-Depth Imaging Spectral-Domain OCT (EDI SD-OCT). Conclusion(s) Choroidal hypopigmentation is a unique feature of Waardenburg syndrome, which can be visualized with ultra-widefield fundus autofluorescence. The choroid may also be thickened in this condition and its thickness measured with EDI SD-OCT. PMID:26114849

  19. Digital Image Forgery Detection Using JPEG Features and Local Noise Discrepancies

    Directory of Open Access Journals (Sweden)

    Bo Liu

    2014-01-01

    Full Text Available Wide availability of image processing software makes counterfeiting become an easy and low-cost way to distort or conceal facts. Driven by great needs for valid forensic technique, many methods have been proposed to expose such forgeries. In this paper, we proposed an integrated algorithm which was able to detect two commonly used fraud practices: copy-move and splicing forgery in digital picture. To achieve this target, a special descriptor for each block was created combining the feature from JPEG block artificial grid with that from noise estimation. And forehand image quality assessment procedure reconciled these different features by setting proper weights. Experimental results showed that, compared to existing algorithms, our proposed method is effective on detecting both copy-move and splicing forgery regardless of JPEG compression ratio of the input image.

  20. MRI of Creutzfeldt-Jakob disease: Imaging features and recommended MRI protocol

    Energy Technology D