A graph network for image segmentation

  • Herbert Jahn
Conference paper
Part of the Advances in Computing Science book series (ACS)


Image segmentation as one of the oldest problems in image processing and computer vision is, despite of various attempts to solve it [1], not yet solved satisfactorily. Having in mind the huge capability of the human visual system, highly parallel and pipelined computation seems to be necessary for success in this field. According to Uhr [2] parallel-serial layered architectures are best suited for image analysis. In this sense, a new Layered Graph Network (LGN) was developed [3], which is presented and applied to the processing of simulated and real world images.


Image Segmentation Segmentation Result Human Visual System Segmented Image Real World Image 
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.
    Haralick, R.M., Shapiro, L.G.: Image Segmentation Techniques. CVGIP 29, pp. 100–132 (1985)Google Scholar
  2. 2.
    Uhr, L.: Psychological Motivation and Underlying Concepts. In: Tanimoto,S., Klinger, A. (Eds.). Structured Computer Vision. New York: Academic Press 1980Google Scholar
  3. 3.
    Jahn, H.: Image Segmentation with a Layered Graph Network. SPIE Proceedings, Vol. 2662, pp. 217–228 (1996)CrossRefGoogle Scholar
  4. 4.
    Levine, M.D.: Vision in Man and Machine. New York: Mc Graw-Hill 1985Google Scholar
  5. 5.
    Pavlidis, T.: Structural Pattern Recognition. Berlin: Springer-Verlag 1977MATHGoogle Scholar
  6. 6.
    Jolion, J.M., Rosenfeld, A.: A Pyramid Framework for Early Vision. Dordrecht: Kluwer Academic Publishers 1994CrossRefGoogle Scholar
  7. 7.
    Jahn, H.: Eine Methode zur Clusterbildung in metrischen Räumen. Bild & Ton 39, pp. 362–370 (1986)Google Scholar

Copyright information

© Springer-Verlag/Wien 1997

Authors and Affiliations

  • Herbert Jahn

There are no affiliations available

Personalised recommendations