English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Visual Segmentation without Classification in a Model of the Primary Visual Cortex

Li, Z.(1997). Visual Segmentation without Classification in a Model of the Primary Visual Cortex (AIM-1613). Cambridge, MA, USA: Massachusetts Institute of Technology (MIT).

Item is

Files

show Files

Locators

show
hide
Locator:
https://dspace.mit.edu/handle/1721.1/7247 (Publisher version)
Description:
-

Creators

show
hide
 Creators:
Li, Z1, Author              
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: Stimuli outside classical receptive fields significantly influence the neurons' activities in primary visual cortex. We propose that such contextual influences are used to segment regions by detecting the breakdown of homogeneity or translation invariance in the input, thus computing global region boundaries using local interactions. This is implemented in a biologically based model of V1, and demonstrated in examples of texture segmentation and figure-ground segregation. By contrast with traditional approaches, segmentation occurs without classification or comparison of features within or between regions and is performed by exactly the same neural circuit responsible for the dual problem of the grouping and enhancement of contours.

Details

show
hide
Language(s):
 Dates: 1997-08
 Publication Status: Published in print
 Pages: 8
 Publishing info: Cambridge, MA, USA : Massachusetts Institute of Technology (MIT)
 Table of Contents: -
 Rev. Type: -
 Identifiers: Report Nr.: AIM-1613
Report Nr.: CBCL-153
 Degree: -

Event

show

Legal Case

show

Project information

show

Source

show