CaltechAUTHORS
  A Caltech Library Service

A computational model of texture segmentation

Malik, Jitendra and Perona, Pietro (1989) A computational model of texture segmentation. In: 1989 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Proceedings. IEEE Computer Society Press , Los Alamitos, CA, pp. 326-332. ISBN 0-8186-1952-x http://resolver.caltech.edu/CaltechAUTHORS:20120510-140804386

[img]
Preview
PDF - Published Version
See Usage Policy.

680Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20120510-140804386

Abstract

An algorithm for finding texture boundaries in images is developed on the basis of a computational model of human texture perception. The model consists of three stages: (1) the image is convolved with a bank of even-symmetric linear filters followed by half-wave rectification to give a set of responses; (2) inhibition, localized in space, within and among the neural response profiles results in the suppression of weak responses when there are strong responses at the same or nearby locations; and (3) texture boundaries are detected using peaks in the gradients of the inhibited response profiles. The model is precisely specified, equally applicable to grey-scale and binary textures, and is motivated by detailed comparison with psychophysics and physiology. It makes predictions about the degree of discriminability of different texture pairs which match very well with experimental measurements of discriminability in human observers. From a machine-vision point of view, the scheme is a high-quality texture-edge detector which works equally on images of artificial and natural scenes. The algorithm makes the use of simple local and parallel operations, which makes it potentially real-time.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1109/CVPR.1989.37868DOIUNSPECIFIED
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=37868PublisherUNSPECIFIED
Additional Information:© 1989 IEEE. Date of Current Version: 06 August 2002. We thank Martin Banks, Bela Julesz and Paul Kube for their useful comments. In particular, we would like to thank Dr. Julesz for suggesting the comparison of our model with Krose's psychophysical data. This research was funded by an IBM Faculty Development award and by DARPA contract N00039-88-C-0292.
Funders:
Funding AgencyGrant Number
IBM Faculty Development AwardUNSPECIFIED
Defense Advanced Research Projects Agency (DARPA)N00039-88-C-0292
Other Numbering System:
Other Numbering System NameOther Numbering System ID
INSPEC Accession Number3484892
Record Number:CaltechAUTHORS:20120510-140804386
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20120510-140804386
Official Citation:Malik, J.; Perona, P.; , "A computational model of texture segmentation," Computer Vision and Pattern Recognition, 1989. Proceedings CVPR '89., IEEE Computer Society Conference on , vol., no., pp.326-332, 4-8 Jun 1989 doi: 10.1109/CVPR.1989.37868 URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=37868&isnumber=1531
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:31419
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:10 May 2012 21:27
Last Modified:26 Dec 2012 15:11

Repository Staff Only: item control page