Texture segmentation by minimizing vector-valued energy functionals: The Coupled-Membrane model

  • Tai Sing Lee
  • David Mumford
  • Alan Yuille
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 588)


This paper presents a computational model that segments images based on the textural properties of object surfaces. The proposed Coupled-Membrane model applies the weak membrane approach to an image WI(σ,θ, x, y), derived from the power responses of a family of selfsimilar quadrature Gabor wavelets. While segmentation breaks are allowed in x and y only, coupling is introduced to in all 4 dimensions. The resulting spatial and spectral diffusion prevents minor variations in local textures from producing segmentation boundaries. Experiments showed that the model is adequate in segmenting a class of synthetic and natural texture images.


Gabor Filter Boundary Detection Gabor Wavelet Texture Segmentation Spectral Diffusion 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Blake, A. & Zisserman, A. (1987) Visual Reconstruction. The MIT Press, Cambridge, Massachusetts.Google Scholar
  2. 2.
    Bovik, A.C., Clark, M. & Geisler, W.S. (1990) Multichannel Texture Analysis Using Localized Spatial Filters. IEEE Transections on Pattern Analysis and Machine Intelligence, Vol. 12, No. 1, January.Google Scholar
  3. 3.
    Brodatz, P. (1966) Texture — A Photographic Album for Artists and Designers. New York: Dover.Google Scholar
  4. 4.
    Daugman, J.G. (1985) Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. J. Opt. soc. Amer., Vol. 2, No. 7, pp 1160–1169.Google Scholar
  5. 5.
    Fogel, I. & Sagi, D. (1989) Gabor Filters as Texture Discriminator. Biological Cybernatics 61, 103–113.Google Scholar
  6. 6.
    Geiger, D. & Yuille, A. (1991) A Common Framework for Image Segmentation. Intl. Journal of Computer Vision, 6:3,227–243.Google Scholar
  7. 7.
    Geman, D., Geman, S., Graffigne, C., & Dong, P. (1990) Boundary Detection by Constrained Optimization. IEEE Transections on Pattern Analysis and Machine Intelligence, Vol 12, No. 7, July.Google Scholar
  8. 8.
    Gibson, J.J. (1979) The Ecological Approach to Visual Perception, Houghton-Mifflin.Google Scholar
  9. 9.
    Heeger, D.J. (1989) Computational Model of Cat Striate Physiology. MIT Media Laboratory Technical Report 125. October, 1989.Google Scholar
  10. 10.
    Hubel, D.H., & Wiesel, T.N. (1977) Functional Architecture of macaque monkey visual cortex. Proc. R. Soc. Lond. B. 198.Google Scholar
  11. 11.
    Kirkpatrick, S., Gelatt, C.D. & Vecchi, M.P. (1983) Optimization by simulated annealing. Science,220. 671–680Google Scholar
  12. 12.
    Lee, T.S., Mumford, D. & Yuille, A. (1991) Texture Segmentation by Minimizing Vector-Valued Energy Functionals: The Couple-Membrane Model. Harvard Robotics Laboratory Technical Report no. 91-22.Google Scholar
  13. 13.
    Malik, J. & Perona, P. (1989) A computational model for texture segmentation. IEEE CVPR Conference Proceedings.Google Scholar
  14. 14.
    Marroquin, J.L. (1984). Surface Reconstruction Preserving Discontinuities (Artificial Intelligence Lab. Memo 792). MIT, Cambridge, MA. A more refined version “ A Probabilistic Approach to Computational Vision” appeared in Image Understanding 1989. Ed. by Ullman, S. & Whitman Richards. Ablex Publishing Corporation, New Jersey 1990.Google Scholar
  15. 15.
    Mumford, D. & Shah, J.(1985) Boundary Detection by Minimizing Functionals, I. IEEE CVPR Conference Proceedings June 19–23. A more detailed and refined version appeared in Image Understanding 1989. Ed. by Ullman,S. & Whitman Richards. Ablex Publishing Corporation, New Jersey 1990.Google Scholar
  16. 16.
    Pollen, D.A. & Gaska, J.P. & Jacobson, L.D. (1989) Physiological Constraints on Models of Visual Cortical Function. in Models of Brain Function, Ed. Rodney, M.J. Cotterill. Cambridge University Press, England.Google Scholar
  17. 17.
    Reed, T.R. & Wechsler, H. (1990) Segmentation of Textured Images and Gestalt Organization Using Spatial/Spatial-Frequency Representation. IEEE Transections on Pattern Analysis and Machine Intelligence, Vol. 12, No. 1, January.Google Scholar
  18. 18.
    Silverman, M.S., Grosof, D.H., De Valois, R.L., & Elfar, S.D. (1989) Spatial-frequency Organization in Primate Striate Cortex. Proc. Natl. Acad. Sci. U.S.A., Vol. 86, January.Google Scholar
  19. 19.
    Voorhees, H. & T. Poggio. (1988) Computing texture boundaries in images. Nature, 555:364–367. A detailed version exists as Voorhees’ master thesis, “Finding Texture Boundaries in Images”. MIT AI Lab Technical Report No. 968, June 1987.Google Scholar
  20. 20.
    Webster, M.A. & De Valois, R.L. (1985) Relationship between Spatial-frequency and Orientation tuning of Striate-Cortex Cells. J. Opt. Soc. Am. A Vol 2, No. 7 July 1985.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • Tai Sing Lee
    • 1
  • David Mumford
    • 1
  • Alan Yuille
    • 1
  1. 1.Harvard Robotics Laboratory, Division of Applied SciencesHarvard UniversityCambridge

Personalised recommendations