Advertisement

Recognition of Complex Scenes. Scene-Selective Attention

  • Hermann Haken
Part of the Springer Series in Synergetics book series (SSSYN, volume 50)

Abstract

In this brief chapter we deal with the recognition of prototype patterns within complex scenes. To be most explicit, we consider test patterns such as that shown in Fig. 9.1. The prototype patterns to be identified are those of Fig. 6.1 a. Since the patterns corresponding to the prototype patterns are spatially shifted with respect to each other, we first make the process invariant with respect to translation by means of the procedure described in Sect. 8.1. In addition, we let the attention parameter λ in (5.13) and (5.33) depend on the index k which labels the specific prototype pattern. For instance k = 1 corresponds to a particular face in Fig. 6.1 a, k = 2 to a second one, and so on.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. A. Fuchs, H. Haken: Biol. Cybern. 60, 17–22 (1988a)MathSciNetzbMATHGoogle Scholar
  2. R. A. Altes: J. Acoust. Soc. Am. 63, 174 —183 (1978)Google Scholar
  3. J. Altmann, H. J. P. Reitböck: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. Pami-6, no. 1 (1984)Google Scholar
  4. B. Fischer: Vision Res. 13, 2113 — 2120 (1973)Google Scholar
  5. H. J. Reitböck, J. Altmann: Biol. Cybern. 51, 113 —121 (1984)Google Scholar
  6. H.J. Reitböck, T.P. Brody: Information and Control 15, 130–154 (1969)MathSciNetzbMATHCrossRefGoogle Scholar
  7. E. L. Schwarz: Biol. Cybern. 25, 181–194 (1977)CrossRefGoogle Scholar
  8. G. West, H. J. Reitböck: Elektronische Informationsverarbeitung und Kybernetik 15, 10, 507 —512 (1979)Google Scholar
  9. A. Fuchs, H. Haken: Biol. Cybern. 60, 107–109 (1988b)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Hermann Haken
    • 1
  1. 1.Institut für Theoretische Physik und SynergetikUniversität StuttgartStuttgartGermany

Personalised recommendations