Search results for "Visual Object Recognition"

showing 10 items of 50 documents

A Neural Architecture for Segmentation and Modelling of Range Data

2003

A novel, two stage, neural architecture for the segmentation of range data and their modeling with undeformed superquadrics is presented. The system is composed by two distinct neural stages: a SOM is used to perform data segmentation, and, for each segment, a multi-layer feed-forward network performs model estimation. The topology preserving nature of the SOM algorithm makes this architecture suited to cluster data with respect to sudden curvature variations. The second stage is designed to model and compute the inside-outside function of an undeformed superquadric in whatever attitude, starting form the (x, y, z) data triples. The network has been trained using backpropagation, and the we…

Robot visionArtificial neural networkComputer sciencesuperquadricsPattern recognition (psychology)SuperquadricsCognitive neuroscience of visual object recognitionSegmentationGeometric primitiveCurvatureVisual servoingAlgorithmBackpropagation
researchProduct

Spherical nonlinear correlations for global invariant three-dimensional object recognition

2007

We define a nonlinear filtering based on correlations on unit spheres to obtain both rotation- and scale-invariant three-dimensional (3D) object detection. Tridimensionality is expressed in terms of range images. The phase Fourier transform (PhFT) of a range image provides information about the orientations of the 3D object surfaces. When the object is sequentially rotated, the amplitudes of the different PhFTs form a unit radius sphere. On the other hand, a scale change is equivalent to a multiplication of the amplitude of the PhFT by a constant factor. The effect of both rotation and scale changes for 3D objects means a change in the intensity of the unit radius sphere. We define a 3D fil…

RotationMaterials Science (miscellaneous)3D single-object recognitionStatistics as TopicInformation Storage and RetrievalSensitivity and SpecificityFacial recognition systemIndustrial and Manufacturing EngineeringPattern Recognition Automatedsymbols.namesakeImaging Three-DimensionalOpticsArtificial IntelligenceImage Interpretation Computer-AssistedBusiness and International ManagementInvariant (mathematics)Physicsbusiness.industryCognitive neuroscience of visual object recognitionReproducibility of ResultsImage EnhancementObject detectionNonlinear systemFourier transformAmplitudeNonlinear DynamicssymbolsbusinessAlgorithmsApplied Optics
researchProduct

A cooperating strategy for objects recognition

1999

The paper describes an object recognition system, based on the co-operation of several visual modules (early vision, object detector, and object recognizer). The system is active because the behavior of each module is tuned on the results given by other modules and by the internal models. This solution allows to detect inconsistencies and to generate a feedback process. The proposed strategy has shown good performance especially in case of complex scene analysis, and it has been included in the visual system of the DAISY robotics system. Experimental results on real data are also reported.

Settore INF/01 - InformaticaComputer sciencebusiness.industry3D single-object recognitionComputer ScienceProcess (computing)Cognitive neuroscience of visual object recognitionComputer visionRoboticsArtificial intelligencebusinessObject (computer science)Theoretical Computer Science
researchProduct

Video object recognition and modeling by SIFT matching optimization

2014

In this paper we present a novel technique for object modeling and object recognition in video. Given a set of videos containing 360 degrees views of objects we compute a model for each object, then we analyze short videos to determine if the object depicted in the video is one of the modeled objects. The object model is built from a video spanning a 360 degree view of the object taken against a uniform background. In order to create the object model, the proposed techniques selects a few representative frames from each video and local features of such frames. The object recognition is performed selecting a few frames from the query video, extracting local features from each frame and looki…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniComputer sciencebusiness.industry3D single-object recognitionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONDeep-sky objectCognitive neuroscience of visual object recognitionObject Modeling Video Query Object Recognition.Object (computer science)Object-oriented designObject-class detectionVideo trackingObject modelComputer visionArtificial intelligencebusiness
researchProduct

Entropy-based Localization of Textured Regions

2011

Appearance description is a relevant field in computer vision that enables object recognition in domains as re-identification, retrieval and classification. Important cues to describe appearance are colors and textures. However, in real cases, texture detection is challenging due to occlusions and to deformations of the clothing while person's pose changes. Moreover, in some cases, the processed images have a low resolution and methods at the state of the art for texture analysis are not appropriate. In this paper, we deal with the problem of localizing real textures for clothing description purposes, such as stripes and/or complex patterns. Our method uses the entropy of primitive distribu…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniTexture atlasComputer sciencebusiness.industryLocal binary patternsLow resolutionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONCognitive neuroscience of visual object recognitionLatent Dirichlet allocationsymbols.namesakesymbolsEntropy (information theory)SegmentationComputer visionArtificial intelligencebusinessimage analysis textureComputingMethodologies_COMPUTERGRAPHICS
researchProduct

Views selection for SIFT based object modeling and recognition

2016

In this paper we focus on automatically learning object models in the framework of keypoint based object recognition. The proposed method uses a collection of views of the objects to build the model. For each object the collection is composed of N×M views obtained rotating the object around its vertical and horizontal axis. As keypoint based object recognition using a complete set of views is computationally expensive, we focused on the definition of a selection method that creates, for each object, a subset of the initial views that visually summarize the characteristics of the object and should be suited for recognition. We select the views by determining maxima and minima of a function, …

Similarity (geometry)Computer science3D single-object recognitionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONLearning objectScale-invariant feature transform02 engineering and technologySIFT0202 electrical engineering electronic engineering information engineeringMedia TechnologyComputer vision060201 languages & linguisticsObject RecognitionSettore ING-INF/05 - Sistemi Di Elaborazione Delle Informazionibusiness.industryFeature matchingCognitive neuroscience of visual object recognitionPattern recognition06 humanities and the artsObject (computer science)Object Modeling0602 languages and literatureSignal ProcessingObject model020201 artificial intelligence & image processingViola–Jones object detection frameworkArtificial intelligencebusiness
researchProduct

PORE Algorithm for Object Recognition in Photo Layers based on Parametric Characteristics of the Object Edges

2016

PORE stands for Photo-Object Recognition based on the Edges. Coincidentally, PORE means to examine something carefully and with due attention, so "we pore over the object layers in search for information about their characteristics with the aim at improving image recognition process". Therefore, this study presents a novel approach to object recognition based on the pattern by using photo layers and by defining the objects' specific characteristics. We select and introduce the parameters which determine a higher efficiency of image retrieval of the image objects. In this paper, we describe how the same photos are recognized in a process of classical retrieval compared to our model by analyz…

Similarity (geometry)Matching (graph theory)Computer sciencebusiness.industry3D single-object recognitionpattern recognitionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONCognitive neuroscience of visual object recognitionImage processingPattern recognitionoptimization algorithmObject (computer science)bitmapsimage retrievalimage processingPattern recognition (psychology)computational intelligenceComputer visionArtificial intelligencebusinessImage retrievalAlgorithm
researchProduct

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

Salient Spin Images: A Descriptor for 3D Object Recognition

2018

In the last decades a wide range of algorithms have been devoted to recognize 3D free-from objects under real conditions such as occlusions, clutters, rotation, scale and translation. Spin image is one of these algorithms known to be robust to rotation, translation, occlusions up to 70% and clutters up to 60%, but still suffer from scaling, resolution changes and it is time consuming. In this paper we present a novel approach based on spin images, called salient spin images (SSI). This method enhances spin images algorithm based on its limits. Particularly, it decreases significantly the complexity of the algorithm using DoG detector, it shows a higher performance due to the relevant locali…

Spin imageComputer sciencebusiness.industryDetectorComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONCognitive neuroscience of visual object recognition[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]02 engineering and technology[INFO.INFO-CG]Computer Science [cs]/Computational Geometry [cs.CG]01 natural sciences[INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR]010309 opticsRobustness (computer science)SalientComputer Science::Computer Vision and Pattern Recognition0103 physical sciences0202 electrical engineering electronic engineering information engineeringClutter020201 artificial intelligence & image processingComputer visionArtificial intelligencebusinessTrue positive rateScalingComputingMilieux_MISCELLANEOUS
researchProduct

Entire reflective object surface structure understanding based on reflection motion estimation

2015

An sub-segmentation method for the reflective surface structure understanding.The use of reflection motion features as spatiotemporal coherence for video segmentation.Straightforward implementation.A building block for object recognition. The presence of reflection on a surface has been a long-standing problem for object recognition since it brings negative effects on object's color, texture and structural information. Because of that, it is not a trivial task to recognize the surface structure affected by the reflection, especially when the object is entirely reflective. Most of the cases, reflection is considered as noise. In this paper, we propose a novel method for entire reflective obj…

Surface (mathematics)business.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONCognitive neuroscience of visual object recognitionObject (computer science)Artificial IntelligenceMotion estimationSignal ProcessingComputer visionComputer Vision and Pattern RecognitionNoise (video)Specular reflectionArtificial intelligenceReflection (computer graphics)businessSoftwareComputingMethodologies_COMPUTERGRAPHICSCoherence (physics)MathematicsPattern Recognition Letters
researchProduct