Contour and Texture Analysis for Image Segmentation

DMCA

Contour and Texture Analysis for Image Segmentation (2001)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Jitendra Malik , Serge Belongie , Thomas Leung , Jianbo Shi

Citations:

400 - 28 self

BibTeX

@MISC{Malik01contourand,
    author = {Jitendra Malik and Serge Belongie and Thomas Leung and Jianbo Shi},
    title = {Contour and Texture Analysis for Image Segmentation},
    year = {2001}
}

OpenURL

Abstract

This paper provides an algorithm for partitioning grayscale images into disjoint regions of coherent brightness and texture. Natural images contain both textured and untextured regions, so the cues of contour and texture differences are exploited simultaneously. Contours are treated in the intervening contour framework, while texture is analyzed using textons. Each of these cues has a domain of applicability, so to facilitate cue combination we introduce a gating operator based on the texturedness of the neighborhood at a pixel. 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.

Keyphrases

texture analysis image segmentation texture difference normalized cut contour framework untextured region coherent brightness grayscale image cue combination local measure natural image coherent texture disjoint region wide range nearby pixel spectral graph theoretic framework experimental result gating operator

DMCA