Finding boundaries in natural images: A new method using point descriptors and area completion

  • Serge Belongie
  • Jitendra Malik
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1406)


We develop an approach to image segmentation for natural scenes containing image texture. One general methodology which shows promise for solving this problem is to characterize textured regions via their responses to a set of filters. However, this approach brings with it many open questions, including how to combine texture and intensity information into a common descriptor and how to deal with the fact that filter responses inside textured regions are generally spatially inhomogeneous. Our goal in this paper is to introduce two new ideas which address these open questions and to demonstrate the application of these ideas to the segmentation of natural images. The first idea consists of a novel means of describing points in natural images and an associated distance function for comparing these descriptors. This distance function is aided in textured regions by the use of the second idea, a new process introduced here which we have termed area completion. Experimental segmentation results which incorporate our proposed approach into the Normalized Cut framework of Shi and Malik are provided for a variety of natural images.


Feature Vector Natural Image Connection Weight Texture Region Filter Response 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    T.D. Alter. The Role of Saliency and Error Propagation in Visual Object Recognition. PhD Thesis, MIT, 1995.Google Scholar
  2. 2.
    D.H. Ballard. Cortical connections and parallel processing: Structure and function. The Behavioral and Brain Sciences, 9:67–120, 1986.CrossRefGoogle Scholar
  3. 3.
    J. Bigün and J.M. Hans du Buf. N-folded symmetries by complex moments in gabor space and their application to unsupervised texture segmentation. IEEE Trans. Pattern Anal. Mach. Intell., 16(1):80–87, 1994.CrossRefGoogle Scholar
  4. 4.
    A. Bovik, M. Clark, and W.S. Geisler. Multichannel texture analysis using localized spatial filters. IEEE Trans. Pattern Anal. Mach. Intell., 12(1):55–73, 1990.CrossRefGoogle Scholar
  5. 5.
    M. Carandini and D.J. Heeger. Summation and division by neurons in primate visual cortex. Science, 264:1333–1336, 1994.Google Scholar
  6. 6.
    S. Casadei, S. Mitter, and P. Perona. Boundary detection in piecewise homogeneous images. In Proc. 2nd Europ. Conf. Comput. Vision, G. Sandini (Ed.), LNCS-Series Vol. 588, Springer-Verlag, pages 174–183, 1992.Google Scholar
  7. 7.
    J.W. Demmel. Applied Numerical Linear Algebra. SIAM, 1997.Google Scholar
  8. 8.
    R. DeValois and K. DeValois. Spatial Vision. Oxford University Press, 1988.Google Scholar
  9. 9.
    J.H. Elder and S.W. Zucker. Computing Contour Closure. Fourth European Conf. Computer Vision, 1996, Cambridge, England.Google Scholar
  10. 10.
    J.N. Franklin. Matrix Theory. Prentice-Hall, 1968.Google Scholar
  11. 11.
    W. Freeman and E. Adelson. The design and use of steerable filters. IEEE Trans. Pattern Anal. Mach. Intell., 13:891–906, 1991.CrossRefGoogle Scholar
  12. 12.
    H. Greenspan, S. Belongie, P. Perona, and R. Goodman. Rotation-Invariant Texture Recognition Using a Steerable Pyramid. 12th Int. Conf. Patt. Rec., 1994.Google Scholar
  13. 13.
    D. J. Heeger and J.R. Bergen. Pyramid-based texture analysis/synthesis. Computer Graphics: SIGGRAPH, pages 229–238, 1995.Google Scholar
  14. 14.
    D.W. Jacobs. Finding Salient Convex Groups. In I.J. Cox, P. Hansen, and B Julesz, eds., Partitioning Data Sets, vol. 19 of DIMACS (Series in Discrete Mathematics and Theoretical Computer Science). 1995.Google Scholar
  15. 15.
    A.K. Jain and F. Farrokhnia. Unsupervised texture segmentation using gabor filters. Pattern Recognition, 24(12):1167–1186, 1991.CrossRefGoogle Scholar
  16. 16.
    D. Jones and J. Malik. Computational framework for determining stereo correspondence from a set of linear spatial filters. Image and Vision Computing, 10(10), 1992.Google Scholar
  17. 17.
    H. Knutsson and G.H. Granlund. Texture analysis using two-dimensional quadrature filters. In Workshop on Computer Architecture for Pattern Analysis and Image Database Management, pages 206–213. IEEE Computer Society, 1983.Google Scholar
  18. 18.
    J.J. Koenderink. Operational significance of receptive field assemblies. Biol. Cybern., 58:163–171, 1988.zbMATHMathSciNetCrossRefGoogle Scholar
  19. 19.
    J.J. Koenderink and A.J. van Doorn. Representation of local geometry in the visual system. Biol. Cybern., 55:367–375, 1987.zbMATHCrossRefGoogle Scholar
  20. 20.
    T. Lindeberg. Scale-Space Theory in Computer Vision. Kluwer, 1994.Google Scholar
  21. 21.
    J. Malik and P. Perona. Preattentive texture discrimination with early vision mechanisms. J. Opt Soc. Am. A, 7(5):923–932, 1990.CrossRefGoogle Scholar
  22. 22.
    B.S. Manjunath and W.Y. Ma. Texture features for browsing and retrieval of image data. IEEE Trans. Pattern Anal. Mach. Intell., 18(8):837–842, 1996.CrossRefGoogle Scholar
  23. 23.
    J. Puzicha, T. Hofmann, and J.M. Buhmann. Non-parametric similarity measures for unsupervised texture segmentation and image retrieval. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, pages 267–272, 1997.Google Scholar
  24. 24.
    F. Reif. Statistical Physics. McGraw-Hill, 1965.Google Scholar
  25. 25.
    J. Shi and J. Malik. Normalized cuts and image segmentation. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, pages 731–737, 1997.Google Scholar
  26. 26.
    M.R. Turner. Texture discrimination by gabor functions. Biol. Cybern., 55:71–82, 1986.Google Scholar
  27. 27.
    M. Wertheimer. Laws of organization in perceptual forms(partial translation). In W.B. Ellis, editor, A Sourcebook of Gestalt Psycychology, pages 71–88. Harcourt, Brace and Company, 1938.Google Scholar
  28. 28.
    S.C. Zhu, Y. Wu, and D. Mumford. Frame: Filters, random fields, and minimax entropy. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, pages 686–693, 1996.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Serge Belongie
    • 1
  • Jitendra Malik
    • 1
  1. 1.Department of Electrical Engineering and Computer SciencesUniversity of California at BerkeleyBerkeleyUSA

Personalised recommendations