Filters








4,172 Hits in 4.9 sec

A Perceptual Grouping Hierarchy for Appearance-Based 3D Object Recognition

Andrea Selinger, Randal C. Nelson
1999 Computer Vision and Image Understanding  
Instead, we argue that recognition must utilize a hierarchy of perceptual grouping processes, and describe an appearance-based system that uses four distinct levels of perceptual grouping, the upper two  ...  In this report we consider the problem of 3D object recognition, and the role that perceptual grouping processes must play.  ...  We have described a framework for keyed appearance-based 3-D recognition, based on a perceptual grouping hierarchy.  ... 
doi:10.1006/cviu.1999.0788 fatcat:ly2rpor4vvbw3ikmqhketr4wmu

Author Index

2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
Object Reacquisition for Mobile Manipulation Fuchs, Thomas Neuron Geometry Extraction by Perceptual Grouping in ssTEM Images Fujiyoshi, Hironobu Workshop: Feature Co-occurrence Representation Based  ...  Liao, Shu A Novel Markov Random Field Based Deformable Model for Face Recognition Liebelt, Joerg Multi-View Object Class Detection with a 3D Geometric Model Lim, Jongwoo Egomotion using Assorted  ... 
doi:10.1109/cvpr.2010.5539913 fatcat:y6m5knstrzfyfin6jzusc42p54

Diagnostic recognition: task constraints, object information, and their interactions

Philippe G Schyns
1998 Cognition  
To this end, the paper develops diagnostic recognition, a framework which formulates recognition performance as an interaction of task constraints and object information.  ...  It is the main objective of this paper to lay out the basis of a dialogue between object recognition and categorization research, with the hope of raising issues that could cross-fertilize both domains  ...  Acknowledgements The author wishes to thank Michael Burton, Simon Garrod, Frédéric Gosselin, Gregory Murphy, Martin Pickering and two anonymous reviewers for helpful comments on an earlier version of this  ... 
doi:10.1016/s0010-0277(98)00016-x pmid:9735539 fatcat:2smkqkrkhbgfxmpwaolhnfun3i

Perceptual Organization and Recognition of Indoor Scenes from RGB-D Images

Saurabh Gupta, Pablo Arbelaez, Jitendra Malik
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
We also propose a generic method for long-range amodal completion of surfaces and show its effectiveness in grouping.  ...  We also show how our approach can be used for scene classification, and how this contextual information in turn improves object recognition.  ...  We are also thankful to Jon Barron, Bharath Hariharan, and Pulkit Agrawal for the useful discussions.  ... 
doi:10.1109/cvpr.2013.79 dblp:conf/cvpr/GuptaAM13 fatcat:63tfcapxhjdnnjdihdqzlfvnmu

Shape from Contour: Computation and Representation

James H. Elder
2018 Annual Review of Vision Science  
Research suggests that a successful model will account for our acute sensitivity to four key perceptual dimensions of shape: topology, symmetry, composition, and deformation.  ...  While feedforward discriminative deep neural network models currently produce the best predictions of object selectivity in higher areas of the object pathway, a generative model may be required to account  ...  On the positive front, the decades-long debate between 2D view-based and 3D object-based theories of object recognition appears to be settling toward a more nuanced and principled understanding that, in  ... 
doi:10.1146/annurev-vision-091517-034110 pmid:30222530 fatcat:mwhcyypwpvehxk5l5i7bc2rkbi

Perceptual grouping for generic recognition

Parag Havaldar, G�rard Medioni, Fridtjof Stein
1996 International Journal of Computer Vision  
We address the problem of recognition of generic objects from a single intensity image.  ...  Since many groups are created, we also perform selection of relevant groups by organizing them into sets of similar perceptual content.  ...  We want to extend the feature hierarchy by including perceptual organization between high level features. So far we use only proximity and closure to generate high level groups.  ... 
doi:10.1007/bf00144117 fatcat:aoqa3usga5hkbpx3teciqc45iq

Serial grouping of 2D-image regions with object-based attention in humans

Danique Jeurissen, Matthew W Self, Pieter R Roelfsema
2016 eLife  
of object-based attention.  ...  We discuss how the visual cortical hierarchy can implement this scale-dependent spread of object-based attention, leveraging the different receptive field sizes in distinct cortical areas.  ...  Acknowledgements The authors thank Heiko Neumann for helpful comments on a earlier draft of the manuscript, Marita Rokx, Kaushik Lakshminarasimhan, Klaudia Ambroziak, and Sasa Kozelj for help with collecting  ... 
doi:10.7554/elife.14320 pmid:27291188 pmcid:PMC4905743 fatcat:3cpdwbj6a5bblluojhnamrcc7i

Using 3D contours and their relations for cognitive vision and robotics

Emre Baseski, Leon Bodenhagen, Nicolas Pugeault, Sinan Kalkan, Justus Piater, Norbert Kruger
2009 2009 24th International Symposium on Computer and Information Sciences  
In this work, we make use of 3D visual contours carrying geometric as well as appearance information.  ...  Secondly, the contours can be seen as one stage in a visual hierarchy bridging between local symbolic descriptors to higher level stages of processing such as object coding and grasping.  ...  We also showed that the same space provides a useful basis for learning, by improving the success rate of grasping of unknown objects based on these relations.  ... 
doi:10.1109/iscis.2009.5291815 dblp:conf/iscis/BaseskiBPKPK09 fatcat:et7hpyq5irgbhjgyjstls5c6qm

Image-based object recognition in man, monkey and machine

Michael J Tarr, Heinrich H Bülthoff
1998 Cognition  
Theories of visual object recognition must solve the problem of recognizing 3D objects given that perceivers only receive 2D patterns of light on their retinae.  ...  Thus, the most viable model of object recognition may be one that incorporates the most appealing aspects of both image-based and structural-description theories.  ...  This work was supported by a TRANSCOOP grant to MJT and HHB  ... 
doi:10.1016/s0010-0277(98)00026-2 pmid:9735534 fatcat:lhaxxn2x4rgofiwqii7aolwwsq

Generic object recognition using multiple representations

Subhodev Das, Bir Bhanu, Chih-Cheng Ho
1996 Image and Vision Computing  
It also presents a refocused matching algorithm that uses a hierarchically structured model database to facilitate generic object recognition.  ...  Real-world image understanding tasks often involve complex object models which are not adequately represented by a single representational scheme for the various recognition scenarios encountered in practice  ...  By and large, these CAD-based IU systems use a single representation scheme for the models, and a matching technique based on that representation for object recognition.  ... 
doi:10.1016/0262-8856(96)89798-8 fatcat:m56ordb55jbnrhmakfic72wz5q

Generic object recognition using multiple representations

S Das
1996 Image and Vision Computing  
It also presents a refocused matching algorithm that uses a hierarchically structured model database to facilitate generic object recognition.  ...  Real-world image understanding tasks often involve complex object models which are not adequately represented by a single representational scheme for the various recognition scenarios encountered in practice  ...  By and large, these CAD-based IU systems use a single representation scheme for the models, and a matching technique based on that representation for object recognition.  ... 
doi:10.1016/0262-8856(95)01064-5 fatcat:atte6zqehvf2jfdivgmm54if5e

Object Categorization

Axel Pinz
2005 Foundations and Trends in Computer Graphics and Vision  
Categorization aims for the recognition of generic classes of objects, and thus has also been termed 'generic object recognition'.  ...  It turns out that several techniques which are useful for specific recognition can also be adapted to categorization, but there are also a number of recent developments in learning, representation and  ...  Research in perceptual grouping proceeds in a similar manner [167] .  ... 
doi:10.1561/0600000003 fatcat:k3yfurwpwbbhrp22d2ec5hweve

Indoor Objects and Outdoor Urban Scenes Recognition by 3D Visual Primitives [chapter]

Junsheng Fu, Joni-Kristian Kämäräinen, Anders Glent Buch, Norbert Krüger
2015 Lecture Notes in Computer Science  
The 3D promoted primitives represent both structure and appearance. For recognition, we propose a fast and effective correspondence matching using random sampling.  ...  Object detection, recognition and pose estimation in 3D images have gained momentum due to availability of 3D sensors (RGB-D) and increase of large scale 3D data, such as city maps.  ...  Lixin Fan for the valuable discussions.  ... 
doi:10.1007/978-3-319-16628-5_20 fatcat:bxvcn543hvb2vi2hdaaf3kziwq

Using naming time to evaluate quality predictors for model simplification

Benjamin Watson, Alinda Friedman, Aaron McGaffey
2000 Proceedings of the SIGCHI conference on Human factors in computing systems - CHI '00  
Our standard of comparison is naming time, a well established measure of recognition from cognitive psychology. Thirty participants named models of familiar objects at three levels of simplification.  ...  Correlations indicate that view-dependent image quality predictors are most effective for drastic simplifications, while view-independent three-dimensional predictors are better for more moderate simplifications  ...  We thank Greg Turk for his models and geometry filters. Peter Lindstrom participated with a thought provoking correspondence, and by assisting in finding relevant code.  ... 
doi:10.1145/332040.332414 dblp:conf/chi/WatsonFM00 fatcat:srosuvc7hvhonfzlokpnybd6za

On the Relative Salience of Euclidean, Affine, and Topological Structure for 3-D Form Discrimination

James T Todd, Lin Chen, J Farley Norman
1998 Perception  
These findings suggest that the relative perceptual salience of object properties may be systematically related to their structural stability under change, in a manner that is similar to the Klein hierarchy  ...  A match-to-sample task was performed, in which observers compared configurations of line segments presented stereoscopically in different 3D orientations.  ...  information for the perceptual analysis of 3D form.  ... 
doi:10.1068/p270273 pmid:9775311 fatcat:k5sy7q2jbzfmhpfhkvdi2hcvtq
« Previous Showing results 1 — 15 out of 4,172 results