Advertisement

Contour segmentation with recurrent neural networks of pulse-coding neurons

  • L. Weitzel
  • K. Kopecz
  • C. Spengler
  • R. Eckhorn
  • H. J. Reitboeck
Segmentation and Grouping
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1296)

Abstract

The performance of technical and biological vision systems crucially relies on powerful processing capabilities. Robust object recognition must be based on representations of segmented object candidates which are kept stable and sparse despite the highly variable nature of the environment. Here, we propose a network of pulse-coding neurons based on biological principles which establishs such representations using contour information. The system solves the task of grouping and figureground segregation by creating flexible temporal correlations among contour extracting units. In contrast to similar previous approaches, we explicitly address the problem of processing grey value images. In our multi-layer architecture, the extracted contour features are edges, line endings and vertices which interact by introducing facilatory and inhibitory couplings among feature extracting neurons. As the result of the network dynamics, individual mutually occluding objects become defined by temporally correlated activity on contour representations.

Keywords

Receptive Field Recurrent Neural Network Line Ending Occlude Object Contrast Polarity 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    R. Eckhorn, R. Bauer, W. Jordan, et al. Coherent oscillation: A mechanism of feature linking in the visual cortex. Biol. Cyb., 60:121–130, 1988.Google Scholar
  2. 2.
    R Eckhorn, HJ Reitboeck, M Arndt, et al. Feature linking via synchronization among distributed assemblies: Simulations of results from cat visual cortex. Neural Comp., 2:293–307, 1990.Google Scholar
  3. 3.
    G Frank and G Hartman. An artificial neural network accelerator for pulse-coded model neurons. In Proc. ICNN 1995, (CD-ROM). IEEE, 1995.Google Scholar
  4. 4.
    HJ Reitboeck. A multi-electrode matrix for studies of temporal signal correlations within neural assemblies. In Basar et al., (ed.), Synergetics of the Brain, 174–181. Springer, Berlin, 1983.Google Scholar
  5. 5.
    S Sarkar and KL Boyer. A computational structure for preattentive perceptual organization. IEEE Trans Sys Man Cybern, 24:246–266, 1994.CrossRefGoogle Scholar
  6. 6.
    C von der Maisburg. The correlation theory of brain function. Technical Report Internal Report 81-2, MPI für Biophysikalische Chemie, Göttingen, 1981.Google Scholar
  7. 7.
    C. von der Malsburg and J Buhmann. Sensory segmentation with coupled neural oscillators. Biol. Cybern., 67:233–242, 1992.CrossRefPubMedGoogle Scholar
  8. 8.
    M Wertheimer. Untersuchungen zur Lehre von der Gestalt II. Psychologische Forschung, 4:301–350, 1923.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • L. Weitzel
    • 1
  • K. Kopecz
    • 1
  • C. Spengler
    • 1
  • R. Eckhorn
    • 1
  • H. J. Reitboeck
    • 1
  1. 1.Dept. of NeurophysicsUniversity of MarburgGermany

Personalised recommendations