Jump to ContentJump to Main Navigation
Bayesian BrainProbabilistic Approaches to Neural Coding$
Users without a subscription are not able to see the full content.
Bayesian Brain: Probabilistic Approaches to Neural Coding

Kenji Doya, Shin Ishii, Alexandre Pouget, and Rajesh P.N. Rao

Print publication date: 2006

Print ISBN-13: 9780262042383

Published to MIT Press Scholarship Online: August 2013

DOI: 10.7551/mitpress/9780262042383.001.0001

Show Summary Details
Page of

PRINTED FROM MIT PRESS SCHOLARSHIP ONLINE (www.mitpress.universitypressscholarship.com). (c) Copyright The MIT Press, 2021. All Rights Reserved. An individual user may print out a PDF of a single chapter of a monograph in MITSO for personal use.date: 19 January 2022

Efficient Coding of Visual Scenes by Grouping and Segmentation

Efficient Coding of Visual Scenes by Grouping and Segmentation

Chapter:
(p.144) (p.145) 8 Efficient Coding of Visual Scenes by Grouping and Segmentation
Source:
Bayesian Brain
Author(s):

Tai Sing Lee

Alan L. Yuille

Publisher:
The MIT Press
DOI:10.7551/mitpress/9780262042383.003.0008

Image segmentation is a process that partitions image into regions which can correspond to 3D surfaces in the visual scene or parts of a 3D surface defined by texture or color. This chapter presents computational theories that perform image segmentation in terms of efficient encoding of regions, and also discusses some neurophysiological experiments which suggest the relevance of the function and mechanism of the primary visual cortex in image segmentation.

Keywords:   image segmentation, visual scene, computational theories, encoding, visual cortex

MIT Press Scholarship Online requires a subscription or purchase to access the full text of books within the service. Public users can however freely search the site and view the abstracts and keywords for each book and chapter.

Please, subscribe or login to access full text content.

If you think you should have access to this title, please contact your librarian.

To troubleshoot, please check our FAQs, and if you can't find the answer there, please contact us.