Significantly different textures: A computational model of pre-attentive texture segmentation

Ruth Rosenholtz


Abstract

Recent human vision research suggests modelling preattentive texture segmentation by taking a set of feature samples from a local region on each side of a hypothesized edge, and then performing standard statistical tests to determine if the two samples differ significantly in their mean or variance. If the difference is significant at a specified level of confidence, a human observer will tend to pre-attentively see a texture edge at that location. I present an algorithm based upon these results, with a well specified decision stage and intuitive, easily fit parameters. Previous models of pre-attentive texture segmentation have poorly specified decision stages, more unknown free parameters, and in some cases incorrectly model human performance. The algorithm uses heuristics for guessing the orientation of a texture edge at a given location, thus improving computational efficiency by performing the statistical tests at only one orientation for each spatial location.

Information

title:
Significantly different textures: A computational model of pre-attentive texture segmentation
author:
R. Rosenholtz
citation:
Proc. European Conference on Computer Vision, D. Vernon (Ed.), Springer Ver lag, LNCS 1843, Dublin, Ireland, pp. 197-211
shortcite:
ECCV
year:
2000
created:
2000-01-01
summary:
textureeccv00
keyword:
rosenholtz
pdf:
http://web.mit.edu/rruth/www/Papers/TextureSegmentation.pdf
pageid:
textureeccv00
type:
publication