Efficient Combination of Probabilistic Sampling Approximations for Robust Image Segmentation

  • Jens Keuchel
  • Daniel Küttel
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4174)


Methods based on pairwise similarity relations have been successfully applied to unsupervised image segmentation problems. One major drawback of such approaches is their computational demand which scales quadratically with the number of pixels. Adaptations to increase the efficiency have been presented, but the quality of the results obtained with those techniques tends to decrease. The contribution of this work is to address this tradeoff for a recent convex relaxation approach for image partitioning. We propose a combination of two techniques that results in a method which is both efficient and yields robust segmentations. The main idea is to use a probabilistic sampling method in a first step to obtain a fast segmentation of the image by approximating the solution of the convex relaxation. Repeating this process several times for different samplings, we obtain multiple different partitionings of the same image. In the second step we combine these segmentations by using a meta-clustering algorithm, which gives a robust final result that does not critically depend on the selected sample points.


Image Segmentation Convex Relaxation Cluster Ensemble Hierarchical Segmentation Graph Partitioning Problem 
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.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. PAMI 22(8), 888–905 (2000)Google Scholar
  2. 2.
    Hofmann, T., Puzicha, J., Buhmann, J.M.: Unsupervised texture segmentation in a deterministic annealing framework. IEEE Trans. PAMI 20(8), 803–818 (1998)Google Scholar
  3. 3.
    Shental, N., Zomet, A., Hertz, T., Weiss, Y.: Learning and inferring image segmentations using the GBP typical cut algorithm. In: Proc. ICCV, pp. 1243–1250. IEEE Comp. Soc., Los Alamitos (2003)Google Scholar
  4. 4.
    Keuchel, J., Schnörr, C., Schellewald, C., Cremers, D.: Binary partitioning, perceptual grouping, and restoration with semidefinite programming. IEEE Trans. PAMI 25(11), 1364–1379 (2003)Google Scholar
  5. 5.
    Fowlkes, C., Belongie, S., Chung, F., Malik, J.: Spectral grouping using the Nyström method. IEEE Trans. PAMI 26(2), 214–225 (2004)Google Scholar
  6. 6.
    Sarkar, S., Soundararajan, P.: Supervised learning of large perceptual organization: Graph spectral partitioning and learning automata. IEEE Trans. PAMI 22(5), 504–525 (2000)Google Scholar
  7. 7.
    Wu, Z., Leahy, R.: An optimal graph theoretic approach to data clustering: Theory and its application to image segmentation. IEEE T-PAMI 15(11), 1101–1113 (1993)Google Scholar
  8. 8.
    Wang, S., Siskind, J.M.: Image segmentation with ratio cut. IEEE Trans. PAMI 25(6), 675–690 (2003)Google Scholar
  9. 9.
    Williams, C.K.I., Seeger, M.: Using the Nyström method to speed up kernel machines. NIPS 13, 682–688 (2001)Google Scholar
  10. 10.
    Drineas, P., Mahoney, M.: On the Nyström method for approximating a Gram matrix for improved kernel-based learning. J. Mach. Learning Res. 6, 2153–2175 (2005)MathSciNetGoogle Scholar
  11. 11.
    Keuchel, J., Schnörr, C.: Efficient graph cuts for unsupervised image segmentation using probabilistic sampling and SVD-based approximation. In: 3rd International Workshop on Statistical and Computational Theories of Vision, Nice, France (2003)Google Scholar
  12. 12.
    Arora, S., Hazan, E., Kale, S.: Fast algorithms for approximate semidefinite programming using the multiplicative weights update method. In: Proc. FOCS, pp. 339–348 (2005)Google Scholar
  13. 13.
    Strehl, A., Ghosh, J.: Cluster ensembles — a knowledge reuse framework for combining multiple partitions. J. Mach. Learning Res. 3, 583–617 (2003)MATHCrossRefMathSciNetGoogle Scholar
  14. 14.
    Fischer, B., Buhmann, J.M.: Bagging for path-based clustering. IEEE Trans. PAMI 25(11), 1411–1415 (2003)Google Scholar
  15. 15.
    Lange, T., Buhmann, J.M.: Combining partitions by probabilistic label aggregation. In: Proc. KDD, pp. 147–156 (2005)Google Scholar
  16. 16.
    Fred, A.L., Jain, A.K.: Data clustering using evidence accumulation. ICPR (4), 276–280 (2002)Google Scholar
  17. 17.
    de Klerk, E.: Aspects of Semidefinite Programming. Kluwer Academic Pub., Dordrecht (2002)MATHGoogle Scholar
  18. 18.
    Goemans, M.X., Williamson, D.P.: Improved approximation algorithms for maximum cut and satisfiability problems using semidefinite programming. Journal of the ACM 42(6), 1115–1145 (1995)MATHCrossRefMathSciNetGoogle Scholar
  19. 19.
    Frieze, A.M., Kannan, R., Vempala, S.: Fast Monte-Carlo algorithms for finding low-rank approximations. In: Proc. on FOCS, pp. 370–378 (1998)Google Scholar
  20. 20.
    Karypis, G., Kumar, V.: A fast and high quality multilevel scheme for partitioning irregular graphs. SIAM J. Sci. Comput. 20(1), 359–392 (1998)CrossRefMathSciNetGoogle Scholar
  21. 21.
    Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proc. ICCV, pp. 416–423. IEEE Comp. Soc., Los Alamitos (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Jens Keuchel
    • 1
  • Daniel Küttel
    • 1
  1. 1.Institute of Computational ScienceETH ZurichZurichSwitzerland

Personalised recommendations