Unsupervised Texture Segmentation with Nonparametric Neighborhood Statistics

  • Suyash P. Awate
  • Tolga Tasdizen
  • Ross T. Whitaker
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3952)


This paper presents a novel approach to unsupervised texture segmentation that relies on a very general nonparametric statistical model of image neighborhoods. The method models image neighborhoods directly, without the construction of intermediate features. It does not rely on using specific descriptors that work for certain kinds of textures, but is rather based on a more generic approach that tries to adaptively capture the core properties of textures. It exploits the fundamental description of textures as images derived from stationary random fields and models the associated higher-order statistics nonparametrically. This general formulation enables the method to easily adapt to various kinds of textures. The method minimizes an entropy-based metric on the probability density functions of image neighborhoods to give an optimal segmentation. The entropy minimization drives a very fast level-set scheme that uses threshold dynamics, which allows for a very rapid evolution towards the optimal segmentation during the initial iterations. The method does not rely on a training stage and, hence, is unsupervised. It automatically tunes its important internal parameters based on the information content of the data. The method generalizes in a straightforward manner from the two-region case to an arbitrary number of regions and incorporates an efficient multi-phase level-set framework. This paper presents numerous results, for both the two-texture and multiple-texture cases, using synthetic and real images that include electron-microscopy images.


Neighborhood Size Texture Region Texture Synthesis Entropy Minimization Threshold Dynamic 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Awate, S.P., Whitaker, R.T.: Unsupervised, Information-Theoretic, Adaptive Image Filtering for Image Restoration. IEEE Trans. Pattern Anal. Mach. Intell (PAMI) 28(3), 364–376 (2006)CrossRefGoogle Scholar
  2. 2.
    Bigun, J., Granlund, G.H., Wiklund, J.: Multidimensional orientation estimation with applications to texture analysis and optical flow. IEEE Trans. Pattern Anal. Mach. Intell. 13(8), 775–790 (1991)CrossRefGoogle Scholar
  3. 3.
    Boomgaard, R., Weijer, J.: Robust estimation of orientation for texture analysis. In: 2nd Int. Workshop on Texture Analysis and Synthesis (2002)Google Scholar
  4. 4.
    de Bonet, J.S., Viola, P.: Texture recognition using a non-parametric multi-scale statistical model. In: Proc. IEEE Conf. on Comp. Vision and Pattern Recog, pp. 641–647 (1998)Google Scholar
  5. 5.
    de Silva, V., Carlsson, G.: Topological estimation using witness complexes. In: Symposium on Point-Based Graphics (2004)Google Scholar
  6. 6.
    Doretto, G., Cremers, D., Favaro, P., Soatto, S.: Dynamic texture segmentation. In: Proc. Int. Conf. Computer Vision, pp. 1236–1242 (2003)Google Scholar
  7. 7.
    Dougherty, E.: Random Processes for Image and Signal Processing. Wiley, Chichester (1998)CrossRefMATHGoogle Scholar
  8. 8.
    Duda, R., Hart, P., Stork, D.: Pattern Classification. Wiley, Chichester (2001)MATHGoogle Scholar
  9. 9.
    Efros, A.A., Leung, T.K.: Texture synthesis by non-parametric sampling. In: Int. Conf. Computer Vision, pp. 1033–1038 (1999)Google Scholar
  10. 10.
    Esedoglu, S., Ruuth, S., Tsai, R.: Threshold dynamics for shape reconstruction and disocclusion. In: Proc. Int. Conf. Image Processing, pp. 502–505 (2005)Google Scholar
  11. 11.
    Esedoglu, S., Tsai, Y.-H.R.: Threshold dynamics for the piecewise constant mumford-shah functional. Number CAM-04-63 (2004)Google Scholar
  12. 12.
    Jehan-Besson, S., Barlaud, M., Aubert, G.: DREAMS: Deformable regions driven by an eulerian accurate minimization method for image and video segmentation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 365–380. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  13. 13.
    Julesz, B.: Visual pattern discrimination. IRE Trans. Info. Theory IT(8), 84–92 (1962)CrossRefGoogle Scholar
  14. 14.
    Kadir, T., Brady, M.: Unsupervised non-parametric region segmentation using level sets. In: Proc. of IEEE Int. Conf. Comp. Vision, pp. 1267–1274 (2003)Google Scholar
  15. 15.
    Kim, J., Fisher, J.W., Yezzi, A., Cetin, M., Willsky, A.S.: Nonparametric methods for image segmentation using information theory and curve evolution. In: Proc. IEEE Int. Conf. on Image Processing, pp. 797–800 (2002)Google Scholar
  16. 16.
    Lee, A., Pedersen, K., Mumford, D.: The nonlinear statistics of high-contrast patches in natural images. Int. J. Comput. Vision 54(1-3), 83–103 (2003)CrossRefMATHGoogle Scholar
  17. 17.
    Merriman, B., Bence, J.K., Osher, S.: Motion of multiple junctions: A level set approach, Technical Report CAM-93-19, Dept. Mathematics, UCLA (1993)Google Scholar
  18. 18.
    Mumford, D., Shah, J.: Optimal approximations by piecewise smooth functions and associated variational problems. Com. Pure and App. Math. 42, 577–685 (1989)MathSciNetCrossRefMATHGoogle Scholar
  19. 19.
    Paragios, N., Deriche, R.: Geodesic active regions and level set methods for supervised texture segmentation. Int. J. Comput. Vision 46(3), 223–247 (2002)CrossRefMATHGoogle Scholar
  20. 20.
    Popat, K., Picard, R.: Cluster based probability model and its application to image and texture processing. IEEE Trans. Image Processing 6(2), 268–284 (1997)CrossRefGoogle Scholar
  21. 21.
    Portilla, J., Simoncelli, E.: A parametric texture model based on joint statistics of complex wavelet coefficients. Int. J. Comput. Vision 40(1), 49–70 (2000)CrossRefMATHGoogle Scholar
  22. 22.
    Rousson, M., Brox, T., Deriche, R.: Active unsupervised texture segmentation on a diffusion based feature space. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 699–706. IEEE Computer Society Press, Los Alamitos (2003)Google Scholar
  23. 23.
    Sagiv, C., Sochen, N.A., Zeevi, Y.Y.: Texture segmentation via a diffusion segmentation scheme in the gabor feature space. In: 2nd Int. Workshop on Texture Analysis and Synthesis (2002)Google Scholar
  24. 24.
    Sandberg, B., Chan, T., Vese, L.: A level-set and gabor-based active contour algorithm for segmenting textured images. Technical Report CAM-02-39, Dept. Mathematics, UCLA (2002)Google Scholar
  25. 25.
    Scott, D.W.: Multivariate Density Estimation. Wiley, Chichester (1992)CrossRefMATHGoogle Scholar
  26. 26.
    Sethian, J.: Level Set Methods and Fast Marching Methods. Cambridge University Press, Cambridge (1999)MATHGoogle Scholar
  27. 27.
    Silverman, B.: Density Estimation for Statistics and Data Analysis. Chapman and Hall, Boca Raton (1986)CrossRefMATHGoogle Scholar
  28. 28.
    Varma, M., Zisserman, A.: Texture classification: Are filter banks necessary? In: Proc. IEEE Conf. on Comp. Vision and Pattern Recog., pp. 691–698 (2003)Google Scholar
  29. 29.
    Vese, L., Chan, T.: A multiphase level set framework for image segmentation using the mumford and shah model. Technical Report CAM-01-25, Dept. Mathematics, UCLA (2001)Google Scholar
  30. 30.
    Viola, P., Wells, W.: Alignment by maximization of mutual information. In: Int. Conf. Comp. Vision, pp. 16–23 (1995)Google Scholar
  31. 31.
    Wei, L., Levoy, M.: Order-independent texture synthesis. Stanford University Computer Science Department Tech. Report TR-2002-01 (2002)Google Scholar
  32. 32.
    Weickert, J.: Coherence-enhancing diffusion filtering. Int. J. Comp. Vis. 31, 111–127 (1999)CrossRefGoogle Scholar
  33. 33.
    Yang, C., Duraiswami, R., Gumerov, N., Davis, L.: Improved fast gauss transform and efficient kernel density estimation. In: Int. Conf. Comp. Vision, pp. 464–471 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Suyash P. Awate
    • 1
  • Tolga Tasdizen
    • 1
  • Ross T. Whitaker
    • 1
  1. 1.Scientific Computing and Imaging Institute, School of ComputingUniversity of UtahSalt Lake CityUSA

Personalised recommendations