Saliency and segregation without feature gradient: New insights for segmentation from orientation-defined textures

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

The analysis of texture patterns, and texture segregation in particular, are at the heart of perceptual organization. In this paper we question the widely accepted view that the detection (both perceptual and computational) of salient perceptual singularities between perceptually coherent texture regions is tightly dependent upon feature gradients. Specifically, we study smooth orientation-defined textures (ODTs) and show that they exhibit striking perceptual singularities even without any outstanding gradients in their defining feature, namely orientation. We further show how these generic singularities are not only unpredictable from the orientation gradient, but that they also defy popular segmentation algorithms and neural models. We then examine smooth ODTs from a (differential) geometric point of view and develop a theory that fully predicts their perceptual singularities from two ODT curvatures. The computational results exhibit striking correspondence to segregation performed by human subjects and provide a conclusive evidence for the role of curvature in texture segregation. Extensions and implications of our results are developed for various aspects of visual processing.

Original languageEnglish
Title of host publication2006 Conference on Computer Vision and Pattern Recognition Workshop
PublisherInstitute of Electrical and Electronics Engineers
Pages175-182
Number of pages8
ISBN (Print)0769526462, 9780769526461
DOIs
StatePublished - 1 Jan 2006
Event2006 Conference on Computer Vision and Pattern Recognition Workshops - New York, NY, United States
Duration: 17 Jun 200622 Jun 2006

Publication series

Name2006 Conference on Computer Vision and Pattern Recognition Workshops
Volume2006

Conference

Conference2006 Conference on Computer Vision and Pattern Recognition Workshops
Country/TerritoryUnited States
CityNew York, NY
Period17/06/0622/06/06

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Saliency and segregation without feature gradient: New insights for segmentation from orientation-defined textures'. Together they form a unique fingerprint.

Cite this