Efficient Pixel-Grouping Based on Dempster’s Theory of Evidence for Image Segmentation

  • Björn Scheuermann
  • Markus Schlosser
  • Bodo Rosenhahn
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7724)


In this paper we propose an algorithm for image segmentation using graph cuts which can be used to efficiently solve labeling problems on high resolution images or image sequences. The basic idea of our method is to group large homogeneous regions to one single variable. Therefore we combine the appearance and the task specific similarity with Dempster’s theory of evidence to compute the basic belief that two pixels/groups will have the same label in the minimum energy state. Experiments on image and video segmentation show that our grouping leads to a significant speedup and memory reduction of the labeling problem. Thus large-scale labeling problems can be solved in an efficient manner with a low approximation loss.


Energy Function Image Segmentation Segmentation Result Basic Belief Evidence Theory 
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.
    Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. TPAMI 26, 1124–1137 (2004)CrossRefGoogle Scholar
  2. 2.
    Blake, A., Rother, C., Brown, M., Perez, P., Torr, P.: Interactive Image Segmentation Using an Adaptive GMMRF Model. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 428–441. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  3. 3.
    Boykov, Y., Kolmogorov, V.: Computing geodesics and minimal surfaces via graph cuts. In: ICCV, pp. 26–33 (2003)Google Scholar
  4. 4.
    Lempitsky, V., Boykov, Y.: Global optimization for shape fitting. In: CVPR, pp. 1–8 (2007)Google Scholar
  5. 5.
    Kohli, P., Torr, P.H.S.: Efficiently solving dynamic markov random fields using graph cuts. In: ICCV, vol. 2, pp. 922–929 (2005)Google Scholar
  6. 6.
    Rother, C., Kolmogorov, V., Blake, A.: Grabcut: interactive foreground extraction using iterated graph cuts. SIGGRAPH 23, 309–314 (2004)CrossRefGoogle Scholar
  7. 7.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. TPAMI 23, 1222–1239 (2002)CrossRefGoogle Scholar
  8. 8.
    Delong, A., Boykov, Y.: A scalable graph-cut algorithm for N-D grids. In: CVPR (2008)Google Scholar
  9. 9.
    Kim, T., Nowozin, S., Kohli, P., Yoo, C.D.: Variable grouping for energy minimization. In: CVPR, pp. 1913–1920 (2011)Google Scholar
  10. 10.
    Bhusnurmath, A., Taylor, C.: Graph cuts via l 1 norm minimization. TPAMI 30, 1866–1871 (2008)CrossRefGoogle Scholar
  11. 11.
    Komodakis, N.: Towards More Efficient and Effective LP-Based Algorithms for MRF Optimization. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol. 6312, pp. 520–534. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  12. 12.
    Boykov, Y., Jolly, M.: Interactive graph cuts for optimal boundary & region segmentation of objects in ND images. In: ICCV, vol. 1, pp. 105–112 (2001)Google Scholar
  13. 13.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. IJCV 59, 167–181 (2004)CrossRefGoogle Scholar
  14. 14.
    Comaniciu, D., Meer, P., Member, S.: Mean shift: a robust approach toward feature space analysis. TPAMI 24, 603–619 (2002)CrossRefGoogle Scholar
  15. 15.
    Levinshtein, A., Stere, A., Kutulakos, K.N., Fleet, D.J., Dickinson, S.J., Siddiqi, K.: TurboPixels: fast superpixels using geometric flows. TPAMI 31, 2290–2297 (2009)CrossRefGoogle Scholar
  16. 16.
    Veksler, O., Boykov, Y., Mehrani, P.: Superpixels and Supervoxels in an Energy Optimization Framework. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 211–224. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  17. 17.
    Scheuermann, B., Rosenhahn, B.: SlimCuts: GraphCuts for High Resolution Images Using Graph Reduction. In: Boykov, Y., Kahl, F., Lempitsky, V., Schmidt, F.R. (eds.) EMMCVPR 2011. LNCS, vol. 6819, pp. 219–232. Springer, Heidelberg (2011)Google Scholar
  18. 18.
    Lermé, N., Létocart, L., Malgouyres, F.: Reduced graphs for min-cut/max-flow approaches in image segmentation. ENDM 37, 63–68 (2011)Google Scholar
  19. 19.
    Puzicha, J., Buhmann, J.: Multiscale annealing for grouping and unsupervised texture segmentation. IJCVIU 76, 213–230 (1999)Google Scholar
  20. 20.
    Kohli, P., Lempitsky, V., Rother, C.: Uncertainty Driven Multi-scale Optimization. In: Goesele, M., Roth, S., Kuijper, A., Schiele, B., Schindler, K. (eds.) Pattern Recognition. LNCS, vol. 6376, pp. 242–251. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  21. 21.
    Sinop, A.K., Grady, L.: Accurate Banded Graph Cut Segmentation of Thin Structures Using Laplacian Pyramids. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4191, pp. 896–903. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  22. 22.
    Dempster, A.P.: A generalization of Bayesian inference. Journal of the Royal Statistical Society 30, 205–247 (1968)MathSciNetzbMATHGoogle Scholar
  23. 23.
    Shafer, G.: A mathematical theory of evidence. Princeton university press (1976)Google Scholar
  24. 24.
    Adamek, T., O’Connor, N.E.: Using Dempster-Shafer theory to fuse multiple information sources in region-based segmentation. In: ICIP, pp. 269–272 (2007)Google Scholar
  25. 25.
    Chaabane, S.B., Sayadi, M., Fnaiech, F., Brassart, E.: Dempster-Shafer evidence theory for image segmentation: application in cells images. IJSP (2009)Google Scholar
  26. 26.
    Schüldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local SVM approach. In: ICPR, pp. 32–36 (2004)Google Scholar
  27. 27.
    Sand, P., Teller, S.J.: Particle video: long-range motion estimation using point trajectories. In: CVPR, pp. 2195–2202 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Björn Scheuermann
    • 1
  • Markus Schlosser
    • 2
  • Bodo Rosenhahn
    • 1
  1. 1.Leibniz Universität HannoverGermany
  2. 2.Technicolor Research & Innovation HannoverGermany

Personalised recommendations