General geometric good continuation: A biologically plausible network

Ohad Ben-Shahar, Steven W. Zucker

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

Abstract

Good continuation is the Gestalt observation that parts often to form coherent wholes. Perceptual integration of edges, for involves orientation continuation, and has been widely computationally. But local-global relationships, such as for shading, elusive. While Taylor's certain ness criteria, the consideration of levelset geometry a different principles we derive, for the first time, a of to all visual structures can be abstracted as scalar functions over the Our model yields a coupled system of partial equations, which to a class of harmonic a network-based for structure inference which we apply to shading and intensity distributions. We demonstrate how this approach eliminates spurious measurements while preserving both singularities and regular structure, a property that facilitates higher level processes which so on both of structures.

Original languageEnglish
Title of host publicationProceedings of 2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05
Pages1184-1191
Number of pages8
StatePublished - 1 Dec 2005
Event2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05 - Beijing, China
Duration: 13 Oct 200515 Oct 2005

Publication series

NameProceedings of 2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05
Volume2

Conference

Conference2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05
Country/TerritoryChina
CityBeijing
Period13/10/0515/10/05

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'General geometric good continuation: A biologically plausible network'. Together they form a unique fingerprint.

Cite this