Abstract

We propose and evaluate a versatile scheme for image pre-segmentation that generates a partition of the image into a selectable number of patches (’superpixels’), under the constraint of obtaining maximum homogeneity of the ’texture’ inside of each patch, and maximum accordance of the contours with both the image content as well as a Gibbs-Markov random field model. In contrast to current state-of-the art approaches to superpixel segmentation, ’homogeneity’ does not limit itself to smooth region-internal signals and high feature value similarity between neighboring pixels, but is applicable also to highly textured scenes. The energy functional that is to be maximized for this purpose has only a very small number of design parameters, depending on the particular statistical model used for the images.

The capability of the resulting partitions to deform according to the image content can be controlled by a single parameter. We show by means of an extensive comparative experimental evaluation that the compactness-controlled contour-relaxed superpixels method outperforms the state-of-the art superpixel algorithms with respect to boundary recall and undersegmentation error while being faster or on a par with respect to runtime.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ren, X., Malik, J.: Learning a classification model for segmentation. In: ICCV (2003)Google Scholar
  2. 2.
    Ochs, P., Brox, T.: Object segmentation in video: A hierarchical variational approach for turning point trajectories into dense regions. In: ICCV (2011)Google Scholar
  3. 3.
    Wang, S., Lu, H., Yang, F., Yang, M.: Superpixel tracking. In: ICCV (2011)Google Scholar
  4. 4.
    Gorelick, L., Delong, A., Veksler, O., Boykov, Y.: Recursive MDL via graph cuts: Application to segmentation. In: ICCV (2011)Google Scholar
  5. 5.
    Mori, G., Ren, X., Efros, A.A., Malik, J.: Recovering human body configurations: combining segmentation and recognition. In: CVPR, pp. 326–333 (2004)Google Scholar
  6. 6.
    Comaniciu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. PAMI 24, 603–619 (2002)CrossRefGoogle Scholar
  7. 7.
    Vincent, L., Soille, P.: Watersheds in digital spaces: an efficient algorithm based on immersion simulations. PAMI 13, 583–598 (1991)CrossRefGoogle Scholar
  8. 8.
    Levinshtein, A., Stere, A., Kutulakos, K., Fleet, D., Dickinson, S., Siddiqi, K.: Turbopixels: Fast superpixels using geometric flows. PAMI (2009)Google Scholar
  9. 9.
    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
  10. 10.
    Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Suesstrunk, S.: SLIC Superpixels. Technical Report Nr. 149300, EPFL, Lausanne (CH) (2010)Google Scholar
  11. 11.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. TPAMI 22 (2000)Google Scholar
  12. 12.
    Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. IJCV (2004)Google Scholar
  13. 13.
    Moore, A., Prince, S., Warrell, J., Mohammed, U., Jones, G.: Superpixel lattices. In: CVPR (2008)Google Scholar
  14. 14.
    Zhang, Y., Hartley, R., Mashford, J., Burn, S.: Superpixels via pseudo-boolean optimization. In: ICCV (2011)Google Scholar
  15. 15.
    Mester, R., Conrad, C., Guevara, A.: Multichannel segmentation using contour relaxation: Fast super-pixels and temporal propagation. In: Heyden, A., Kahl, F. (eds.) SCIA 2011. LNCS, vol. 6688, pp. 250–261. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  16. 16.
    Guevara, A., Conrad, C., Mester, R.: Boosting segmentation results by contour relaxation. In: ICIP (2011)Google Scholar
  17. 17.
    Besag, J.: On the statistical analysis of dirty pictures. Journal of the Royal Statistical Society, Series B 48, 259–302 (1986)MathSciNetMATHGoogle Scholar
  18. 18.
    Besag, J.: Spatial interaction and the statistical analysis of lattice systems. Journal of the RSS, Series B 36, 192–236 (1974)MathSciNetMATHGoogle Scholar
  19. 19.
    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: ICCV, vol. 2, pp. 416–423. IEEE (2001)Google Scholar
  20. 20.
    Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. TPAMI (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Christian Conrad
    • 1
  • Matthias Mertz
    • 1
  • Rudolf Mester
    • 1
    • 2
  1. 1.VSI Lab, CS Dept.Goethe University FrankfurtGermany
  2. 2.Computer Vision Laboratory, ISYLinköping UniversitySweden

Personalised recommendations