Search results for "object category recognition"

showing 2 items of 2 documents

3D objects descriptors methods: Overview and trends

2017

International audience; Object recognition or object's category recognition under varying conditions is one of the most astonishing capabilities of human visual system. The scientists in computer vision have been trying for decades to reproduce this ability by implementing algorithms and providing computers with appropriate tools. Hence, several intelligent systems have been proposed. To act in this field, numerous approaches have been proposed. In this paper we present an overview of the current trend in 3D objects recognition and describe some representative state of the art methods, highlighting their limits and complexity.

Sketch recognitionComputer science3D single-object recognition[INFO.INFO-GR] Computer Science [cs]/Graphics [cs.GR]02 engineering and technology[INFO.INFO-CG]Computer Science [cs]/Computational Geometry [cs.CG]Field (computer science)object recognitionhuman visual systemcomputer vision[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV][INFO.INFO-TS]Computer Science [cs]/Signal and Image ProcessingHuman–computer interactionobject category recognition0202 electrical engineering electronic engineering information engineeringskeletonComputer vision3D objects descriptors methodsVisualization3D objects recognitionintelligent systemsNon-Controlled Indexingbusiness.industryCognitive neuroscience of visual object recognitionIntelligent decision support system[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Shape020207 software engineeringComputational modelingObject (computer science)Keypoints3D objects[INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR]VisualizationRecognition[INFO.INFO-CG] Computer Science [cs]/Computational Geometry [cs.CG]Human visual system modelSolid modelingThree-dimensional displays020201 artificial intelligence & image processingArtificial intelligencebusiness
researchProduct

GESTALT-INSPIRED FEATURES EXTRACTION FOR OBJECT CATEGORY RECOGNITION

2013

International audience; We propose a methodology inspired by Gestalt laws to ex- tract and combine features and we test it on the object cat- egory recognition problem. Gestalt is a psycho-visual the- ory of Perceptual Organization that aims to explain how vi- sual information is organized by our brain. We interpreted its laws of homogeneity and continuation in link with shape and color to devise new features beyond the classical proxim- ity and similarity laws. The shape of the object is analyzed based on its skeleton (good continuation) and as a measure of homogeneity, we propose self-similarity enclosed within shape computed at super-pixel level. Furthermore, we pro- pose a framework to …

Visual perceptionSimilarity (geometry)[ INFO.INFO-TS ] Computer Science [cs]/Signal and Image ProcessingComputer science[INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing3D single-object recognitionmedia_common.quotation_subjectFeature extractionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION02 engineering and technology[ SPI.SIGNAL ] Engineering Sciences [physics]/Signal and Image processingSkeleton (category theory)[ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Gestalt[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV][INFO.INFO-TS]Computer Science [cs]/Signal and Image ProcessingPerceptionobject category recognition0202 electrical engineering electronic engineering information engineeringmedia_common[SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processingCaltech 101business.industryCognitive neuroscience of visual object recognition[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]020207 software engineeringPattern recognitionRegion Self-SimilarityObject (computer science)Semantic GroupingIEEEGestalt psychology020201 artificial intelligence & image processingArtificial intelligencebusiness[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
researchProduct