Fusion Graphs, Region Merging and Watersheds

  • Jean Cousty
  • Gilles Bertrand
  • Michel Couprie
  • Laurent Najman
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4245)

Abstract

Region merging methods consist of improving an initial segmentation by merging some pairs of neighboring regions. We consider a segmentation as a set of connected regions, separated by a frontier. If the frontier set cannot be reduced without merging some regions then we call it a watershed. In a general graph framework, merging two regions is not straightforward. We define four classes of graphs for which we prove that some of the difficulties for defining merging procedures are avoided. Our main result is that one of these classes is the class of graphs in which any watershed is thin. None of the usual adjacency relations on ℤ2 and ℤ3 allows a satisfying definition of merging. We introduce the perfect fusion grid on ℤ n , a regular graph in which merging two neighboring regions can always be performed by removing from the frontier set all the points adjacent to both regions.

References

  1. 1.
    Rosenfeld, A., Kak, A.: 10. In: Digital picture processing, vol. 2, Academic Press, London (1982); Section 10.4.2.d (region merging)Google Scholar
  2. 2.
    Pavlidis, T.: 4–5. In: Structural Pattern Recognition. Springer Series in Electrophysics, vol. 1, pp. 90–123. Springer, Heidelberg (1977) (segmentation techniques)Google Scholar
  3. 3.
    Beucher, S., Lantuéjoul, C.: Use of watersheds in contour detection. In: Procs. Int. Workshop on Image Processing Real-Time Edge and Motion Detection/Estimation (1979)Google Scholar
  4. 4.
    Vincent, L., Soille, P.: Watersheds in digital spaces: An efficient algorithm based on immersion simulations. PAMI 13(6), 583–598 (1991)Google Scholar
  5. 5.
    Meyer, F.: Un algorithme optimal de ligne de partage des eaux. In: Actes du 8ème Congrès AFCET, Lyon-Villeurbanne, France, pp. 847–859 (1991)Google Scholar
  6. 6.
    Couprie, M., Bertrand, G.: Topological grayscale watershed transform. In: SPIE Vision Geometry V Proceedings, vol. 3168, pp. 136–146 (1997)Google Scholar
  7. 7.
    Bertrand, G.: On topological watersheds. JMIV 22(2-3), 217–230 (2005)CrossRefMathSciNetGoogle Scholar
  8. 8.
    Couprie, M., Najman, L., Bertrand, G.: Quasi-linear algorithms for the topological watershed. JMIV 22(2-3), 231–249 (2005)CrossRefMathSciNetGoogle Scholar
  9. 9.
    Najman, L., Couprie, M., Bertrand, G.: Watersheds, mosaics and the emergence paradigm. DAM 147(2-3), 301–324 (2005)MATHMathSciNetGoogle Scholar
  10. 10.
    Jasiobedzki, P., Taylor, C., Brunt, J.: Automated analysis of retinal images. IVC 1(3), 139–144 (1993)Google Scholar
  11. 11.
    Cousty, J., Bertrand, G., Couprie, M., Najman, L.: Fusion graphs: merging properties and watershed. CVIU (submitted, 2006), also in technical report IGM2005-04, http://igm.univ-mlv.fr/LabInfo/rapportsInternes/2005/04.pdf
  12. 12.
    Beineke, L.: On derived graphs and digraphs. In: Sachs, H., Voss, H., Walther, H. (eds.) Beiträge zur graphen theorie, pp. 17–23 (1968)Google Scholar
  13. 13.
    Cousty, J., Couprie, M., Najman, L., Bertrand, G.: Grayscale watersheds on perfect fusion graphs. In: Reulke, R., Eckardt, U., Flach, B., Knauer, U., Polthier, K. (eds.) IWCIA 2006. LNCS, vol. 4040, pp. 60–73. Springer, Heidelberg (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Jean Cousty
    • 1
  • Gilles Bertrand
    • 1
  • Michel Couprie
    • 1
  • Laurent Najman
    • 1
  1. 1.Laboratoire A2SI, Groupe ESIEEInstitut Gaspard-MongeNoisy-le-GrandFrance

Personalised recommendations