Optical Position Converter for Target Tracking and Neural Network

  • Alain Bergeron
  • Henri H. Arsenault
  • Michel Doucet
  • Denis Gingras

Abstract

Optic is widely recognized in information processing for its inherent parallelism. This potential has made optics a promising technology for applications such as pattern recognition1, neural network2,3 and target tracking. The systems developed for these applications often take advantage of the so-called Vander Lugt correlator4 architecture which permits the recognition of an input pattern with translation invariance. The output is simply a maximum peak correlation where the object to be recognized is located. Cross correlations of lower intensities also appear in the presence of other patterns or of noise.

Keywords

Input Image Associative Memory Target Tracking Correlation Peak Binary Mask 
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-.
    J. L. Horner, P. D. Gianino, Phase-only matched filtering, Appl. Opt., 23:812 (1984).CrossRefGoogle Scholar
  2. 2-.
    N. H. Farhat, D. Psaltis, A. Prata and E. Paek, Optical implementation of associative memory based on Hopfield model, Appl Opt, 24:1469 (1985).CrossRefGoogle Scholar
  3. 3-.
    B. Kosko, Adaptative bidirectional associative memories, Appl Opt., 26:4947 (1987).CrossRefGoogle Scholar
  4. 4-.
    Van der Lugt A., Signal detection by complex riltering, IEEE Trans. Inform. Theory, 10:139 (1964).CrossRefMATHGoogle Scholar
  5. 5-.
    E. Paek and D. Psaltis, Optical associative memory using Fourier transform holograms, Opt. Eng., 26:428 (1987).CrossRefGoogle Scholar
  6. 6-.
    B. Javidi, G. Zhang, A. H. Fazlollahi, U. Efron, Applications of a wire-grid-mirror liquid-crystal light valve in a nonlinear joint transform correlator, Appl Opt., 33:2834 (1994).CrossRefGoogle Scholar
  7. 7-.
    A. Bergeron, H. H. Arsenault, E. Eustache, D. Gingras, Optoelectronic thresholding module for winner-take-all operations in optical neural networks, Appl Opt., 33:1463 (1994).CrossRefGoogle Scholar
  8. 8-.
    S. Jin-Yuan, Z. Yan-Xin, Optical pattern recognition system based on a winner-take-all model of a neural network, Opt. Eng., 32:1053 (1993).CrossRefGoogle Scholar
  9. 9-.
    H. Dammann, K. Görtier, High-efficiency in-line multiple imaging by means of multiple phase holograms, Opt. Com., 3:312 (1971).CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 1997

Authors and Affiliations

  • Alain Bergeron
    • 1
    • 2
  • Henri H. Arsenault
    • 2
  • Michel Doucet
    • 1
  • Denis Gingras
    • 1
  1. 1.National Optics Institute/Institut national d’optiqueSainte-FoyCanada
  2. 2.COPLUniversité LavalSainte-FoyCanada

Personalised recommendations