On the perceptual organization of texture and shading flows: From a geometrical model to coherence computation

Ohad Ben-Shahar, Steven W. Zucker

Research output: Contribution to journalConference articlepeer-review

21 Scopus citations

Abstract

Locally parallel dense patterns - sometimes called texture flows - define a perceptually coherent structure which is important to image segmentation, edge classification, shading analysis, and shape interpretation. This paper develops the notion of texture flow from a geometrical point of view to argue that local measurements of such structures must incorporate two curvatures. We show how basic theoretical considerations lead to a unique model for the local behavior of the flow and allow for the specification of consistency constraints between nearby measurements. The computation of globally coherent structure via neighborhood relationships is demonstrated on synthetic and natural images, and is compared to orientation diffusion.

Original languageEnglish
Pages (from-to)I1048-I1055
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume1
StatePublished - 1 Dec 2001
Externally publishedYes
Event2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Kauai, HI, United States
Duration: 8 Dec 200114 Dec 2001

Fingerprint

Dive into the research topics of 'On the perceptual organization of texture and shading flows: From a geometrical model to coherence computation'. Together they form a unique fingerprint.

Cite this