Document Detail


Quantification of local symmetry: application to texture discrimination.
MedLine Citation:
PMID:  7772555     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
Symmetry is one of the most prominent cues in visual perception as well as in computer vision. We have recently presented a Generalized Symmetry Transform that receives as input an edge map, and outputs a symmetry map, where every point marks the intensity and orientation of the local generalized symmetry. In the context of computer vision, this map emphasizes points of high symmetry, which, in turn, are used to detect regions of interest for active vision systems. Many psychophysical experiments in texture discrimination use images that consist of various micro-patterns. Since the Generalized Symmetry Transform captures local spatial relations between image edges, it has been used here to predict human performance in discrimination tasks. Applying the transform to micro-patterns in some well-studied quantitative experiments of human texture discrimination, it is shown that symmetry, as characterized by the present computational scheme, can account for most of them.
Authors:
Y Bonneh; D Reisfeld; Y Yeshurun
Related Documents :
8213265 - Model of visual localization.
20072215 - Geometric optical image aberrations of single and double mirrors.
3257015 - The role of eye movements and masking in monocular rivalry.
18229525 - Theoretical role of square wavelet analysis in stereopsis and binocular rivalry: a math...
8601805 - Photopigment transmittance imaging of the primate photoreceptor mosaic.
20089475 - A robust fuzzy local information c-means clustering algorithm.
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  Spatial vision     Volume:  8     ISSN:  0169-1015     ISO Abbreviation:  Spat Vis     Publication Date:  1994  
Date Detail:
Created Date:  1995-07-11     Completed Date:  1995-07-11     Revised Date:  2004-11-17    
Medline Journal Info:
Nlm Unique ID:  8602662     Medline TA:  Spat Vis     Country:  NETHERLANDS    
Other Details:
Languages:  eng     Pagination:  515-30     Citation Subset:  IM; S    
Affiliation:
Department of Computer Science, Tel Aviv University, Israel.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Form Perception / physiology*
Humans
Mathematics
Pattern Recognition, Visual*
Psychophysics
Space Perception / physiology*

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  A continuum of non-Gaussian self-similar image ensembles with white power spectra.
Next Document:  Galactomannans from Brazilian seeds: characterization of the oligosaccharides produced by mild acid ...