Spatial Repulsion Between Markers Improves Watershed Performance

  • Vaïa Machairas
  • Etienne Decencière
  • Thomas Walter
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9082)


The Watershed Transformation is a powerful segmentation tool from Mathematical Morphology. Here we focus on the markers selection step. We hypothesize that introducing some kind of repulsion between them leads to improved segmentation results when dealing with natural images. To do so, we compare the usual watershed transformation to waterpixels, i.e. regular superpixels based on the watershed transformation which include a regularity constraint on the spatial distribution of their markers. Both methods are evaluated on the Berkeley segmentation database.


Watershed Waterpixels Superpixels Segmentation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Beucher, S., Lantujoul, C.: Use of watershed in contour detection. In: International Workshop on Image Processing: Real-Time Edge and Motion Estimation (1979)Google Scholar
  2. 2.
    Beucher, S., Meyer, F.: The morphological approach to segmentation: the watershed transformation. In: Dougherty, E. (ed.) Mathematical Morphology in Image Processing, pp. 433–481 (1993)Google Scholar
  3. 3.
    Meyer, F.: Un algorithme optimal pour la ligne de partage des eaux. 8ème congrès de reconnaissance des formes et intelligence artificielle, Lyon, France, vol. 2, pp. 847-857 (November 1991)Google Scholar
  4. 4.
    Vincent, L., Soille, P.: Watersheds in digital spaces: An efficient algorithm based on immersion simulations. IEEE Transactions on Pattern Analysis and Machine Intelligence 13(6), 583–598 (1991)CrossRefGoogle Scholar
  5. 5.
    Andres, B., Köthe, U., Helmstaedter, M., Denk, W., Hamprecht, F.: Segmentation of SBFSEM Volume Data of Neural Tissue by Hierarchical Classification. In: Pattern Recognition, vol. D, pp. 142–152 (2008)Google Scholar
  6. 6.
    Stawiaski, J., Decencière, E.: Interactive liver tumor segmentation using watershed and graph cuts. In: Segmentation in the Clinic: A Grand Challenge II (MICCAI 2008 Workshop), New York, USA (2008)Google Scholar
  7. 7.
    Meyer, F., Beucher, S.: Morphological segmentation. JVCIR 1(1), 21–46 (1950)Google Scholar
  8. 8.
    Angulo, J., Jeulin, D.: Stochastic watershed segmentation. In: Banon, G., et al. (eds.) Proc. Int. Symp. Mathematical Morphology, ISSM 2007, pp. 265–276 (2007)Google Scholar
  9. 9.
    Vachier, C., Meyer, F.: Extinction Values: A New Measurement of Persistence. In: IEEE Workshop on Non Linear Signal/Image Processing, pp. 254-257 (1995)Google Scholar
  10. 10.
    Machairas, V., Faessel, M., Cárdenas-Peña, D., Chabardes, T., Walter, T., Decenciére, E.: Waterpixels. In: Under revision for IEEE Transaction on Image Processing (2015)Google Scholar
  11. 11.
    Machairas, V., Walter, T., Decenciére, E., Waterpixels: Superpixels based on the watershed transformation. In: International Conference on Image Processing (ICIP), pp. 4343–4347 (October 2014)Google Scholar
  12. 12.
    Ren, X., Malik, J.: Learning a classification model for segmentation. In: International Conference on Computer Vision, vol. 1, pp. 10–17 (2003)Google Scholar
  13. 13.
    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: Int. Conf. on Computer Vision, vol. 2, pp. 416–423 (July 2001)Google Scholar
  14. 14.
    Kulesza, A., Taskar, B.: Determinantal point processes for machine learning. Foundations and Trends in Machine Learning 5(2-3), 123–286 (2013)CrossRefGoogle Scholar
  15. 15.
    Erkut: The discrete p-dispersion problem. European Journal of Operational Research, 6, 48–60 (1990)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Vaïa Machairas
    • 1
  • Etienne Decencière
    • 1
  • Thomas Walter
    • 2
    • 3
    • 4
  1. 1.Center for Mathematical MorphologyMINES ParisTech, PSL Research UniversityFontainebleauFrance
  2. 2.CBIO-Centre for Computational BiologyMINES ParisTech, PSL-Research UniversityFontainebleauFrance
  3. 3.Institut CurieParis CedexFrance
  4. 4.INSERM U900Paris CedexFrance

Personalised recommendations