Advertisement

ICANN ’93 pp 922-925 | Cite as

Identification of Underwater Sonar Images Using Fuzzy-Neural Architecture FuNe I

  • S. K. Halgamuge
  • W. Poechmueller
  • S. Ting
  • M. Hoehn
  • M. Glesner
Conference paper

Abstract

FuNe I is a Classificator based on a Fuzzy-Neural Architecture. Physically interpretable fuzzy linguistic rules are generated from numerical sample data using supervised learning in the first phase and the antecedent membership functions are tuned in the second phase. The posteriori reduction of input features and the possibility of integrating partial apriori knowledge into the trained network are the special features of FuNe I.

Identification of underwater images in realistic situations is a tedious task. This paper describes the application of FuNe I for identification of underwater sonar images. The images are preprocessed into numerical data sets before classification. Authors also present results of conventional classifiers and a multilayer perceptron for comparison.

Keywords

Membership Function Fuzzy Variable Sonar Data Underwater Image Near Neighbour Classifier 
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]
    T. Kohonen Self-Organization and Associative Memory, Springer Verlag, 1989.Google Scholar
  2. [2]
    H. Surmann, B. Moeller, K. Goser, “A Distributed Self-Organizing Fuzzy Rule Based System”, Proceedings of the Neuro Nimes 92, Nimes, France, November 1992.Google Scholar
  3. [3]
    D.E. Rumelhart, J.L. McClelland, Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Volume 1, The MIT Press, 1986.Google Scholar
  4. [4]
    R.P. Gorman, T.J. Sejnowski, “Learned Classification of Sonar Targets Using a Massively Parallel Network”, IEEE Transactions on Acoustics, Speech, and Signal Processing, Volume 36, No. 7, July 1988Google Scholar
  5. [5]
    N. Ramani, P.H. Patrick, W.G. Hanson, H. Anderson, “Fish Detection and Classification Using a Neural-Network-Based Active Sonar System — Preliminary Results”, Proceedings of the International Joint Conference on Neural Networks IJCNN’90, Volume II, pp. 527–530, Washington, U.S.A., 1990Google Scholar
  6. [6]
    B. Kosko, Neural Networks and Fuzzy Systems, Prentice-Hall, 1992.Google Scholar
  7. [7]
    S.K. Halgamuge, M. Glesner, “A fuzzy-neural approach for pattern classification with the generation of rules based on supervised learning”, Proceedings of the Neuro Nimes 92, Nimes, France, November 1992.Google Scholar
  8. [8]
    S.K. Halgamuge, W. Poechmueller, M. Glesner, “A Rule based Prototype System for Automatic Classification in Industrial Quality Control”, ICNN’93, Volume I, pp. 238–243, San Fransisco, U.S.A., March/April 1993Google Scholar

Copyright information

© Springer-Verlag London Limited 1993

Authors and Affiliations

  • S. K. Halgamuge
    • 1
  • W. Poechmueller
    • 1
  • S. Ting
    • 1
  • M. Hoehn
    • 1
  • M. Glesner
    • 1
  1. 1.Institute of Microelectronic SystemsDarmstadt University of TechnologyDarmstadtGermany

Personalised recommendations