Self-organizing feature maps for image segmentation

  • René Natowicz
  • Robert Sokol
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 686)


A connectionist method for segmenting digital images in grey level is defined. This method relies on the topology preserving property of Kohonen's self-organizing feature maps. This method is adaptive in the sense that the most present on the image an interval of grey values is, the most accurate the segmentation in this range is. Segmentation of various pictures illustrates the method.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    T. Kohonen, “Self-organization and associative memory”, Springer-Verlag Berlin, 1984.Google Scholar
  2. [2]
    T. Kohonen, “The self-organizing feature map”, proceedings of the I.E.E.E., vol. 78, n∘ 9, September 1990.Google Scholar
  3. [3]
    N.M. Nasrabadi, Y. Feng, “Vector quantization of images based upon the Kohonen self-organizing feature map”, I.E.E.E. Int. Conf. on Neural Networks, pp. 101–108, San Diego California, 1988.Google Scholar
  4. [4]
    E. le Bail, A. Mitchie, “Quantification vectorielle par le réseau neuronal de Kohonen”, Traitement du Signal, vol. 6, n∘ 6, 1989.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1993

Authors and Affiliations

  • René Natowicz
    • 1
  • Robert Sokol
    • 1
    • 2
  1. 1.Laboratoire de Traitement de l'Information et des SystèmesE.S.I.E.ENoisy le Grand CedexFrance
  2. 2.Génie Biologique et MédicalUniversité de Paris XIICréteil CedexFrance

Personalised recommendations