Multichannel Segmentation Using Contour Relaxation: Fast Super-Pixels and Temporal Propagation

  • Rudolf Mester
  • Christian Conrad
  • Alvaro Guevara
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6688)


The contribution describes a statistical framework for image segmentation that is characterized by the following features: It allows to model scalar as well as multi-channel images (color, texture feature sets, depth, ...) in a region-based manner, including a Gibbs-Markov random field model that describes the spatial (and temporal) cohesion tendencies of ’real’ label fields. It employs a principled target function resulting from a statistical image model and maximum-a-posteriori estimation, and combines it with a computationally very efficient way (’contour relaxation’) for determining a (local) optimum of the target function. We show in many examples that even these local optima provide very reasonable and useful partitions of the image area into regions. A very attractive feature of the proposed method is that a reasonable partition is reached within some few iterations even when starting from a ’blind’ initial partition (e.g. for ’superpixels’), or when — in sequence segmentation — the segmentation result of the previous image is used as starting point for segmenting the current image.


Image Segmentation Segmentation Result Foreground Object Initial Segmentation Label Image 
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.
    Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Suesstrunk, S.: SLIC Superpixels. Tech. Rep. Nr. 149300, EPFL, Lausanne (CH) (June 2010)Google Scholar
  2. 2.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. PAMI 23(11), 1222–1239 (2002)CrossRefGoogle Scholar
  3. 3.
    Brox, T., Cremers, D.: On local region models and a statistical interpretation of the piecewise smooth Mumford-Shah functional. IJCV 84(2), 184–193 (2009)CrossRefGoogle Scholar
  4. 4.
    Chellappa, R., Chatterjee, S.: Classification of textures using Gaussian Markov random fields. IEEE Trans. ASSP 33(4), 959–963 (1985)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Cremers, D., Rousson, M., Deriche, R.: A review of statistical approaches to level set segmentation: integrating color, texture, motion and shape. International Journal of Computer Vision 72(2), 195–215 (2007)CrossRefGoogle Scholar
  6. 6.
    Derin, H., Cole, W.: Segmentation of textured images using Gibbs random fields. Computer Vision, Graphics, and Image Processing, pp. 72–98 (1986)Google Scholar
  7. 7.
    Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. IJCV 59(2), 167–181 (2004)CrossRefGoogle Scholar
  8. 8.
  9. 9.
    Levinshtein, A., Stere, A., Kutulakos, K., Fleet, D., Dickinson, S., Siddiqi, K.: Turbopixels: Fast superpixels using geometric flows. PAMI 31(12), 2290–2297 (2009)CrossRefGoogle Scholar
  10. 10.
    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 2001, vol. 2, pp. 416–423 (2001)Google Scholar
  11. 11.
    Mester, R., Franke, U.: Statistical model based image segmentation using region growing, contour relaxation and classification. In: Proc. SPIE Visual Communications and Image Processing, Cambridge, MA, pp. 616–624 (1988)Google Scholar
  12. 12.
    Ren, X.R., Malik, J.: Learning a classification model for segmentation. In: Proc. ICCV, vol. 1, pp. 10–17. IEEE Computer Society Press, Los Alamitos (2003)Google Scholar
  13. 13.
    Rother, C.: Tutorial on map inference in discrete models. In: ICCV (2009)Google Scholar
  14. 14.
    Sclove, S.L.: Application of the conditional population-mixture model to image segmentation. IEEE Trans. PAMI 5, 428–433 (1983)CrossRefzbMATHGoogle Scholar
  15. 15.
    Therrien, C.W.: An estimation-theoretic approach to terrain image segmentation. Computer Vision, Graphics, and Image Processing 22(3), 313–326 (1983)CrossRefGoogle Scholar
  16. 16.
    Unnikrishnan, R., Pantofaru, C., Hebert, M.: Toward objective evaluation of image segmentation algorithms. IEEE Trans. PAMI, 929–944 (2007)Google Scholar
  17. 17.
    Veksler, O., Boykov, Y., Mehrani, P.: Superpixels and supervoxels in an energy optimization framework. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6315, pp. 211–224. Springer, Heidelberg (2010)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Rudolf Mester
    • 1
    • 2
  • Christian Conrad
    • 1
  • Alvaro Guevara
    • 1
  1. 1.VSI Lab, Computer Science Dept.Goethe UniversityFrankfurtGermany
  2. 2.Computer Vision Laboratory, Dept. EELinköping UniversitySweden

Personalised recommendations