Search results for "RECOGNITION"

showing 10 items of 3607 documents

Weighted Adaptive Neighborhood HypergraphPartitioning for Image Segmentation

2005

International audience; The aim of this paper is to present an improvement of a previously published algorithm. The proposed approach is performed in two steps. In the first step, we generate the Weighted Adaptive Neighborhood Hypergraph (WAINH) of the given gray-scale image. In the second step, we partition the WAINH using a multilevel hypergraph partitioning technique. To evaluate the algorithm performances, experiments were carried out on medical and natural images. The results show that the proposed segmentation approach is more accurate than the graph based segmentation algorithm using normalized cut criteria.Key words hypergraph, neighborhood hypergraph, hypergraph partitioning, image…

[ INFO ] Computer Science [cs]Computer Science::Computer Vision and Pattern RecognitionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION[INFO]Computer Science [cs][INFO] Computer Science [cs]MathematicsofComputing_DISCRETEMATHEMATICS
researchProduct

Neighborhood Hypergraph Partitioning for Image Segmentation

2005

International audience; The aim of this paper is to introduce a multilevel neighborhoodhypergraph partitioning for image segmentation. Our proposedapproach uses the image neighborhood hypergraph model introduced inour last works and the algorithm of multilevel hypergraphpartitioning introduced by George Karypis. To evaluate the algorithmperformance, experiments were carried out on a group of gray scaleimages. The results show that the proposed segmentation approachfind the region properly from images as compared to imagesegmentation algorithm using normalized cut criteria.Key words :Graph, Hypergraph, Neighborhood hypergraph, multilevel hypergraph partitioning, image segmentation, edge dete…

[ INFO ] Computer Science [cs]Computer Science::Computer Vision and Pattern RecognitionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION[INFO]Computer Science [cs][INFO] Computer Science [cs]MathematicsofComputing_DISCRETEMATHEMATICS
researchProduct

An Image Segmentation Algorithm based on Community Detection

2016

International audience; With the recent advances in complex networks, image segmentation becomes one of the most appropriate application areas. In this context, we propose in this paper a new perspective of image segmentation by applying two efficient community detection algorithms. By considering regions as communities, these methods can give an over-segmented image that has many small regions. So, the proposed algorithms are improved to automatically merge those neighboring regions agglomerative to achieve the highest modularity/stability. To produce sizable regions and detect homogeneous communities, we use the combination of a feature based on the Histogram of Oriented Gradients of the …

[ INFO ] Computer Science [cs]Computer scienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONScale-space segmentation02 engineering and technology[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]Minimum spanning tree-based segmentationImage texture0202 electrical engineering electronic engineering information engineeringcommunity detection[INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO]Segmentation[INFO]Computer Science [cs][ INFO.INFO-AI ] Computer Science [cs]/Artificial Intelligence [cs.AI]modularityImage segmentationSegmentation-based object categorizationbusiness.industry[ INFO.INFO-RB ] Computer Science [cs]/Robotics [cs.RO]Pattern recognitionImage segmentationcomplex networksHistogram of oriented gradientsRegion growing020201 artificial intelligence & image processingArtificial intelligencebusiness
researchProduct

Automated Characterization of Mouth Activity for Stress and Anxiety Assessment

2016

International audience; Non-verbal information portrayed by human facial expression, apart from emotional cues also encompasses information relevant to psychophysical status. Mouth activities in particular have been found to correlate with signs of several conditions; depressed people smile less, while those in fatigue yawn more. In this paper, we present a semi-automated, robust and efficient algorithm for extracting mouth activity from video recordings based on Eigen-features and template-matching. The algorithm was evaluated for mouth openings and mouth deformations, on a minimum specification dataset of 640x480 resolution and 15 fps. The extracted features were the signals of mouth expa…

[ INFO ] Computer Science [cs]Computer scienceSpeech recognitionFeature extractionautomatic assessmentComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONImage processing02 engineering and technologymouth gesture recognition[ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Yawn[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]Correlation03 medical and health sciencesstress0302 clinical medicineRobustness (computer science)Stress (linguistics)[ INFO.INFO-TI ] Computer Science [cs]/Image Processing0202 electrical engineering electronic engineering information engineeringmedicine[INFO]Computer Science [cs][ INFO.INFO-AI ] Computer Science [cs]/Artificial Intelligence [cs.AI]Facial expression[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]anxietyimage processingRecognition[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV][SPI.OPTI]Engineering Sciences [physics]/Optics / PhotonicAnxiety020201 artificial intelligence & image processing[ SPI.OPTI ] Engineering Sciences [physics]/Optics / Photonicmedicine.symptom030217 neurology & neurosurgery
researchProduct

Maximum likelihood difference scaling of image quality in compression-degraded images.

2007

International audience; Lossy image compression techniques allow arbitrarily high compression rates but at the price of poor image quality. We applied maximum likelihood difference scaling to evaluate image quality of nine images, each compressed via vector quantization to ten different levels, within two different color spaces, RGB and CIE 1976 L(*)a(*)b(*). In L(*)a(*)b(*) space, images could be compressed on average by 32% more than in RGB space, with little additional loss in quality. Further compression led to marked perceptual changes. Our approach permits a rapid, direct measurement of the consequences of image compression for human observers.

[ INFO ] Computer Science [cs]Image qualityColorImage processing[INFO] Computer Science [cs]Color space050105 experimental psychology03 medical and health sciences0302 clinical medicineOpticsImage Processing Computer-Assisted[INFO]Computer Science [cs]0501 psychology and cognitive sciences[SDV.MHEP.OS]Life Sciences [q-bio]/Human health and pathology/Sensory OrgansImage resolutionMathematicsColor imagebusiness.industry05 social sciencesVector quantizationData CompressionAtomic and Molecular Physics and OpticsElectronic Optical and Magnetic Materials[SDV.MHEP.OS] Life Sciences [q-bio]/Human health and pathology/Sensory Organs[ SDV.MHEP.OS ] Life Sciences [q-bio]/Human health and pathology/Sensory OrgansRGB color modelComputer Vision and Pattern RecognitionArtifactsbusiness030217 neurology & neurosurgeryImage compression
researchProduct

Une approche structurelle pour la reconnaissance de notices bibliographiques

1995

National audience; Cet article présente un système de reconnaissance de la structure logique de notices bibliographiques en vue de la conversion rétrospective de catalogues de bibliothèques. Le système est guidé par un modèle de structures de la classe des notices, construit sur la base de spécifications détaillées par la bibliothèque. Le modèle fait intervenir aussi bien des connaissances sur la macro-structure des notices que sur la micro-structure de leur contenu. La reconnaissance de la structure d'une notice consiste à retrouver, à partir d'un flux OCR (Optical Character Recognition), sa structure logique spécifique, conformément aux descriptions du modèle. Le résultat est un flux stru…

[ INFO.INFO-DL ] Computer Science [cs]/Digital Libraries [cs.DL]NoticeDocument structureBibliographySGMLFormat UNIMARCTechnical instructionsUNIMARC formatReconnaissance formePattern recognitionDocument analysis[INFO.INFO-DL]Computer Science [cs]/Digital Libraries [cs.DL]Analyse documentaire[INFO.INFO-DL] Computer Science [cs]/Digital Libraries [cs.DL]Structure documentBibliographie
researchProduct

Automatic classification of tissues using T1 and T2 relaxation times from prostate MRI: a step toward generation of PET/MR attenuation map

2015

This paper presents a new methodology providing the first step towards generating attenuation maps for PET/MR systems based solely on MR information. The new method segments and classifies the attenuation-differing regions of the patient's pelvis based on acquired T 1 - and T 2 -weighted MR data sets and anatomical-based knowledge by computing the tissue specific T 1 and T 2 relaxation times, using a robust implementation of the weighted fuzzy C-means algorithm and applying a novel process to detect bones. We have demonstrated the feasibility of this approach by correctly segmenting and classifying six differing regions of structural and anatomical importance: fat, muscle, prostate, air, ba…

[ INFO.INFO-IM ] Computer Science [cs]/Medical ImagingComputer sciencebusiness.industryAttenuation[INFO.INFO-IM] Computer Science [cs]/Medical ImagingRelaxation (iterative method)Pattern recognition030218 nuclear medicine & medical imaging03 medical and health sciences0302 clinical medicinemedicine.anatomical_structure[INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV]ProstateT2 relaxation[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV][ INFO.INFO-TI ] Computer Science [cs]/Image Processingmedicine[INFO.INFO-IM]Computer Science [cs]/Medical ImagingArtificial intelligencebusiness030217 neurology & neurosurgeryComputingMilieux_MISCELLANEOUS
researchProduct

Cardiac motion tracking using a deformable 2D-mesh modeling

2001

International audience; Abstract: The work reported here deals with movement tracking in sequences of medical images in order to quantify the general movements and deformations of the heart For this purpose, we partition the first image into triangular patches in order that each object of the image corresponds to a set of triangles. Then, the nodes of the mesh are tracked across the image sequence giving a mesh which warps with the images. The method is applied to cardiac image sequences where the study of the deformation of the triangles is applied to the determination of the movement of the ventricles

[ INFO.INFO-IM ] Computer Science [cs]/Medical ImagingMovement (music)business.industryComputer sciencePhysics::Medical Physics[INFO.INFO-IM] Computer Science [cs]/Medical ImagingComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION02 engineering and technologyImage segmentationDeformation (meteorology)Tracking (particle physics)030218 nuclear medicine & medical imagingImage (mathematics)Set (abstract data type)03 medical and health sciences0302 clinical medicineComputer Science::Computer Vision and Pattern Recognition0202 electrical engineering electronic engineering information engineeringMedical imaging[INFO.INFO-IM]Computer Science [cs]/Medical Imaging020201 artificial intelligence & image processingComputer visionArtificial intelligencebusinessComputingMethodologies_COMPUTERGRAPHICS
researchProduct

A Supervised Learning Framework for Automatic Prostate Segmentation in Trans Rectal Ultrasound Images

2012

International audience; Heterogeneous intensity distribution inside the prostate gland, significant variations in prostate shape, size, inter dataset contrast variations, and imaging artifacts like shadow regions and speckle in Trans Rectal Ultrasound (TRUS) images challenge computer aided automatic or semi-automatic segmentation of the prostate. In this paper, we propose a supervised learning schema based on random forest for automatic initialization and propagation of statistical shape and appearance model. Parametric representation of the statistical model of shape and appearance is derived from principal component analysis (PCA) of the probability distribution inside the prostate and PC…

[ INFO.INFO-IM ] Computer Science [cs]/Medical Imagingbusiness.industryComputer sciencePosterior probabilitySupervised learning[INFO.INFO-IM] Computer Science [cs]/Medical ImagingStatistical modelPattern recognition02 engineering and technology030218 nuclear medicine & medical imagingRandom forestActive appearance model03 medical and health sciences0302 clinical medicinePoint distribution model0202 electrical engineering electronic engineering information engineering[INFO.INFO-IM]Computer Science [cs]/Medical Imaging020201 artificial intelligence & image processingComputer visionSegmentationArtificial intelligencebusinessParametric statistics
researchProduct

Multiple Mean Models of Statistical Shape and Probability Priors for Automatic Prostate Segmentation

2011

International audience; Low contrast of the prostate gland, heterogeneous intensity distribution inside the prostate region, imaging artifacts like shadow regions, speckle and significant variations in prostate shape, size and in- ter dataset contrast in Trans Rectal Ultrasound (TRUS) images challenge computer aided automatic or semi-automatic segmentation of the prostate. In this paper, we propose a probabilistic framework for automatic initialization and propagation of multiple mean parametric models derived from principal component analysis of shape and posterior probability information of the prostate region to segment the prostate. Unlike traditional statistical models of shape and int…

[ INFO.INFO-IM ] Computer Science [cs]/Medical Imagingbusiness.industryPosterior probability[INFO.INFO-IM] Computer Science [cs]/Medical ImagingProbabilistic logicInitializationStatistical modelPattern recognition02 engineering and technology030218 nuclear medicine & medical imaging03 medical and health sciences0302 clinical medicinePrior probabilityParametric modelPrincipal component analysis[INFO.INFO-IM]Computer Science [cs]/Medical Imaging0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingSegmentationArtificial intelligencebusinessMathematics
researchProduct