Climbing: A Unified Approach for Global Constraints on Hierarchical Segmentation

  • Bangalore Ravi Kiran
  • Jean Serra
  • Jean Cousty
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7585)


The paper deals with global constraints for hierarchical segmentations. The proposed framework associates, with an input image, a hierarchy of segmentations and an energy, and the subsequent optimization problem. It is the first paper that compiles the different global constraints and unifies them as Climbing energies. The transition from global optimization to local optimization is attained by the h-increasingness property, which allows to compare parent and child partition energies in hierarchies. The laws of composition of such energies are established and examples are given over the Berkeley Dataset for colour and texture segmentation.


Global Constraint Texture Segmentation Binary Energy Optimal Segmentation Partial Partition 
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.
    Cousty, J., Najman, L.: Incremental Algorithm for Hierarchical Minimum Spanning Forests and Saliency of Watershed Cuts. In: Soille, P., Pesaresi, M., Ouzounis, G.K. (eds.) ISMM 2011. LNCS, vol. 6671, pp. 272–283. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  2. 2.
    Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 33, 898–916 (2011)CrossRefGoogle Scholar
  3. 3.
    Russell, B.C., Freeman, W.T., Efros, A.A., Sivic, J., Zisserman, A.: Using multiple segmentations to discover objects and their extent in image collections. In: Proceedings of the 2006 IEEE CVPR, vol. 2, pp. 1605–1614 (2006)Google Scholar
  4. 4.
    Cardelino, J., Caselles, V., Bertalmío, M., Randall, G.: A contrario hierarchical image segmentation. In: ICIP, pp. 4041–4044 (2009)Google Scholar
  5. 5.
    Salembier, P., Garrido, L.: Binary partition tree as an efficient representation for image processing, segmentation, and information retrieval. IEEE Transactions on Image Processing 9, 561–576 (2000)CrossRefGoogle Scholar
  6. 6.
    Guigues, L., Cocquerez, J.P., Men, H.L.: Scale-sets image analysis. International Journal of Computer Vision 68, 289–317 (2006)CrossRefGoogle Scholar
  7. 7.
    Soille, P.: Constrained connectivity for hierarchical image partitioning and simplification. IEEE Transactions on Pattern Analysis and Machine Intelligence 30, 1132–1145 (2008)CrossRefGoogle Scholar
  8. 8.
    Zanoguera, M.F., Marcotegui, B., Meyer, F.: A toolbox for interactive segmentation based on nested partitions. In: ICIP (1), pp. 21–25 (1999)Google Scholar
  9. 9.
    Akcay, H.G., Aksoy, S.: Automatic detection of geospatial objects using multiple hierarchical segmentations. IEEE T. Geoscience and Remote Sensing 46, 2097–2111 (2008)CrossRefGoogle Scholar
  10. 10.
    Serra, J.: Hierarchies and Optima. In: Debled-Rennesson, I., Domenjoud, E., Kerautret, B., Even, P. (eds.) DGCI 2011. LNCS, vol. 6607, pp. 35–46. Springer, Heidelberg (2011)Google Scholar
  11. 11.
    Lucchi, A., Li, Y., Bosch, X.B., Smith, K., Fua, P.: Are spatial and global constraints really necessary for segmentation? In: ICCV, pp. 9–16 (2011)Google Scholar
  12. 12.
    Ronse, C.: Partial partitions, partial connections and connective segmentation. J. Math. Imaging Vis. 32, 97–125 (2008)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Najman, L., Schmitt, M.: Geodesic saliency of watershed contours and hierarchical segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 18, 1163–1173 (1996)CrossRefGoogle Scholar
  14. 14.
    Serra, J., Kiran, B.R.: Climbing on pyramids. CoRR abs/1204.5383 (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Bangalore Ravi Kiran
    • 1
  • Jean Serra
    • 1
  • Jean Cousty
    • 1
  1. 1.Laboratoire d’Informatique Gaspard-Monge, A3SI, ESIEEUniversité Paris-EstFrance

Personalised recommendations