Rapid Correspondence Finding in Networks of Cortical Columns

  • Jörg Lücke
  • Christoph von der Malsburg
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4131)


We describe a neural network able to rapidly establish correspondence between neural fields. The network is based on a cortical columnar model described earlier. It realizes dynamic links with the help of specialized columns that evaluate similarities between the activity distributions of local feature cell populations, are subject to a topology constraint, and gate the transfer of feature information between the neural fields. Correspondence finding requires little time (estimated to 10-40 ms in physiological terms) and is robust to noise in feature signals.


Feature Vector Dynamic Link Neural Field Control Column Topology Term 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Zhu, J., von der Malsburg, C.: Maplets for correspondence-based object recognition. Neural Networks, Special Issue New Developments in Self-Organizing Systems 17/8–9, 1311–1326 (2004)Google Scholar
  2. 2.
    Philips, P.J., Moon, H., Rizvi, S.A., Rauss, P.J.: The FERET evaluation methodology for face-recognition algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence 22(10), 1090–1104 (2000)CrossRefGoogle Scholar
  3. 3.
    Messer, K., et al.: Face authentication test on the BANCA database. In: Proceedings of ICPR 2004, Cambridge, vol. 4, pp. 523–532 (2004)Google Scholar
  4. 4.
    Thorpe, S., Fize, D., Marlot, C.: Speed of processing in the human visual system. Nature 381, 520–522 (1996)CrossRefGoogle Scholar
  5. 5.
    Wiskott, L., von der Malsburg, C.: Face recognition by dynamic link matching. In: Sirosh, J., Miikkulainen, R., Choe, Y. (eds.) Lateral Interactions in the Cortex: Structure and Function, ch. 4, (1995) WorldWideWeb, www.cs.utexas.edu/users/nn/book/bwdraft.html, ISBN 0-9647060-0-8
  6. 6.
    Olshausen, B.A., Anderson, C.H., Van Essen, D.C.: A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information. The Journal of Neuroscience 13(11), 4700–4719 (1993)Google Scholar
  7. 7.
    Lücke, J.: Dynamics of cortical columns – sensitive decision making. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) ICANN 2005. LNCS, vol. 3696, pp. 25–30. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  8. 8.
    Wiskott, L.: The role of topographical constraints in face recognition. Pattern Recognition Letters 20(1), 89–96 (1999)MATHCrossRefGoogle Scholar
  9. 9.
    Lücke, J., Bouecke, J.D.: Dynamics of cortical columns – self-organization of receptive fields. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) ICANN 2005. LNCS, vol. 3696, pp. 31–37. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  10. 10.
    Mountcastle, V.B.: The columnar organization of the neocortex. Brain 120, 701–722 (1997)CrossRefGoogle Scholar
  11. 11.
    Lücke, J., von der Malsburg, C.: Rapid processing and unsupervised learning in a model of the cortical macrocolumn. Neural Computation 16, 501–533 (2004)MATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Jörg Lücke
    • 1
    • 2
  • Christoph von der Malsburg
    • 2
    • 3
    • 4
  1. 1.Gatsby Computational Neuroscience UnitUCLLondonUK
  2. 2.Institut für NeuroinformatikRuhr-UniversitätBochumGermany
  3. 3.Frankfurt Institute for Advanced StudiesFrankfurt a. M.Germany
  4. 4.Computer Science Dept.University of Southern CaliforniaUSA

Personalised recommendations