Advertisement

Using A Synergetic Computer in an Industrial Classification Problem

  • T. Wagner
  • F. G. Boebel
  • U. Haßler
  • H. Haken
  • D. Seitzer

Abstract

Synergetic Computers (SCs) represent a class of new algorithms which can be used for different pattern recognition tasks. Due to their strong mathematical similarity with self-organized phenomena of physical nature they embody promising candidates for hardware realizations of classification systems. Until now there is still a lack of investigations concerning the importance of synergetic algorithms in the field of pattern recognition as well as concerning their practical performance. One of these synergetic algorithms (SCAP) will be examined in this paper with respect to pattern recognition capabilities. Its capacity of identifying wheels in an industrial environment is discussed. We show that with adequate preprocessing the SCAP reaches recognition rates of 99.3% under variable illumination conditions and even 100% with constant illumination. In addition to this, we try to specify the SCAP with respect to estabished pattern identification algorithms.

Keywords

Recognition Rate Learning Sample Constant Illumination Hardware Realization Pattern Recognition Task 
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]
    Haken H, ‘Synergetics. An Introduction’, Springer, Berlin, 1983.MATHGoogle Scholar
  2. [2]
    Haken H, ‘Synergetic Computers and Cognition. A Top-Down Approach to Neural Nets’, Springer, Berlin, 1991.MATHGoogle Scholar
  3. [3]
    Haken H and Stadler M (ed.), ‘Synergetics of Cognition’, Springer, Berlin, 1990.Google Scholar
  4. [4]
    Schramm U et al., ‘A Practical Comparison of Synergetic Computer, Restricted Coulomb Energy Networks and Multilayer Perceptron’, World Conference of Neural Networks, Portland, Oregon, 1993. (submitted)Google Scholar
  5. [5]
    Jähne B, ‘Digitale Bildverarbeitung’, 2nd ed., Springer, Berlin, 1991Google Scholar
  6. [6]
    Niemann H, ‘Klassifikation von Mustern’, Springer, Berlin 1983MATHGoogle Scholar
  7. [7]
    Schürmann J, ‘Neuronale Netze und die klassischen Methoden der Mustererkennung’, FhG-Berichte 1/91Google Scholar
  8. [8]
    Duda R and Hart P, ‘Pattern Classification and Scene Analysis’, Wiley & Sons, New York 1973MATHGoogle Scholar

Copyright information

© Springer-Verlag/Wien 1993

Authors and Affiliations

  • T. Wagner
    • 1
  • F. G. Boebel
    • 1
  • U. Haßler
    • 1
  • H. Haken
    • 2
  • D. Seitzer
    • 1
  1. 1.Fraunhofer-Institute for Integrated CircuitsErlangenGermany
  2. 2.Lehrstuhl für Theoretische Physik und SynergetikStuttgartGermany

Personalised recommendations