Textons, contours and regions: Cue integration in image segmentation (1999)
Cached
Download Links
| Venue: | In International Conference on Computer Vision |
| Citations: | 110 - 8 self |
BibTeX
@INPROCEEDINGS{Malik99textons,contours,
author = {Jitendra Malik and Serge Belongie and Jianbo Shi and Thomas Leung},
title = {Textons, contours and regions: Cue integration in image segmentation},
booktitle = {In International Conference on Computer Vision},
year = {1999}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
This paper makes two contributions. It provides (1) an operational definition of textons, the putative elementary units of texture perception, and (2) an algorithm for partitioning the image into disjoint regions of coherent brightness and texture, where boundaries of regions are defined by peaks in contour orientation energy and differences in texton densities across the contour. Julesz introduced the term texton, analogous to a phoneme in speech recognition, but did not provide an operational definition for gray-level images. Here we re-invent textons as frequently co-occurring combinations of oriented linear filter outputs. These can be learned using a K-means approach. By mapping each pixel to its nearest texton, the image can be analyzed into texton channels, each of which is a point set where discrete techniques such as Voronoi diagrams become applicable. Local histograms of texton frequencies can be used with a � test for significant differences to find texture boundaries. Natural images contain both textured and untextured regions, so we combine this cue with that of the presence of peaks of contour energy derived from outputs of odd- and even-symmetric oriented Gaussian derivative filters. Each of these cues has a domain of applicability, so to facilitate cue combination we introduce a gating operator based on a statistical test for isotropy of Delaunay neighbors. Having obtained a local measure of how likely two nearby pixels are to belong to the same region, we use the spectral graph theoretic framework of normalized cuts to find partitions of the image into regions of coherent texture and brightness. Experimental results on a wide range of images are shown. 1
Keyphrases
cue integration image segmentation operational definition gray-level image nearby pixel experimental result re-invent textons putative elementary unit significant difference speech recognition contour orientation energy local histogram co-occurring combination term texton even-symmetric oriented gaussian derivative filter texton frequency disjoint region wide range texton channel normalized cut cue combination local measure natural image gating operator coherent brightness statistical test texton density k-means approach delaunay neighbor spectral graph theoretic framework contour energy texture boundary oriented linear filter output untextured region discrete technique coherent texture texture perception
