International Journal of Computer Vision

, Volume 43, Issue 1, pp 7–27

Contour and Texture Analysis for Image Segmentation

Authors

  • Jitendra Malik
    • Computer Science DivisionUniversity of California at Berkeley
  • Serge Belongie
    • Computer Science DivisionUniversity of California at Berkeley
  • Thomas Leung
    • Computer Science DivisionUniversity of California at Berkeley
  • Jianbo Shi
    • Computer Science DivisionUniversity of California at Berkeley
Article

DOI: 10.1023/A:1011174803800

Cite this article as:
Malik, J., Belongie, S., Leung, T. et al. International Journal of Computer Vision (2001) 43: 7. doi:10.1023/A:1011174803800

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.

segmentationtexturegroupingcue integrationtextonnormalized cut

Copyright information

© Kluwer Academic Publishers 2001