Advertisement

Neural Networks, Fuzziness and Image Processing

  • Eduardo R. Caianiello
  • Alfredo Petrosino

Abstract

A fuzzy neural network system suitable for image analysis is proposed. Each neuron is connected to a windowed area of neurons in the previous layer. The operations involved follow a method for representing and manipulating fuzzy sets, called Composite Calculus. The local features extracted by the consecutive layers are combined in the output layer in order to separate the output neurons in groups in a self-organizing manner by minimizing the fuzziness of the output layer. In this paper we focalize our attention on the application of the proposed model to the edge detection based segmentation, reporting results on real images and investigating the robustness of the system with noisy data.

Keywords

Neural Network Hide Layer Output Layer Membership Degree Fuzzy Neural Network 
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.
    E.R. Caianiello, Outline of a theory of thought processes and thinking machines, Journal of Theoretical Biology, Vol.1, p. 209 (1961).CrossRefGoogle Scholar
  2. 2.
    E.R. Caianiello, A. De Benedictis, A. Petrosino, and R. Tagliaferri, Neural associative memories with minimum connectivity, Neural Networks, Vol.5, pp. 433–439 (1992).CrossRefGoogle Scholar
  3. 3.
    E.R. Caianiello, M. Ceccarelli, and M. Marinaro, Can spurious states be useful?, Complex Systems, Vol.5, pp. 1–12 (1992).Google Scholar
  4. 4.
    J.J. Hopfield, Neural networks and physical systems with emergent collective computational abilities, Proc. National Academy of Sciences USA, Vol.79, pp. 2445–2558 (1982).CrossRefGoogle Scholar
  5. 5.
    T. Kohonen, The self-organizing map, Proc. IEEE, Vol.78, No.9, pp. 1464–1481 (1990).CrossRefGoogle Scholar
  6. 6.
    G.A. Carpenter and S. Grossberg, A massively parallel architecture for a self-organizing neural pattern recognition machine, Computer Vision, Graphics and Image Processing, Vol.37, pp. 54–115 (1987).CrossRefGoogle Scholar
  7. 7.
    D.E. Rumelhart, G.E. Hinton, and R.J. Williams, Learning internal representations by error propagations, Parallel Distributed Processing: Explorations in the Microstructure of Cognition, D.E. Rumelhart and J.L. McClelland eds., Vol. 1, MIT Press, Cambridge, MA (1986).Google Scholar
  8. 8.
    K. Fukushima, A hierarchical neural network capable of visual pattern recognition, Neural Networks, Vol. 1, pp. 119–130 (1988).CrossRefGoogle Scholar
  9. 9.
    Y.H. Pao, Adaptive Pattern Recognition and Neural Networks, Addison-Wesley, Reading, MA (1990).Google Scholar
  10. 10.
    R.P. Lippman, Review of neural networks for speech recognition, Neural Computation, Vol.2 (1989).Google Scholar
  11. 11.
    S. Lee and E. Lee, Fuzzy neural networks, Math. Biosci., Vol.23, pp. 151–177 (1975).CrossRefGoogle Scholar
  12. 12.
    G. Carpenter, S. Grossberg, and D. Rosen, Fuzzy ART: fast stable learning and categorization of analog patterns by an adaptive resonance system, Neural Networks, Vol.4, pp. 759–771 (1991).CrossRefGoogle Scholar
  13. 13.
    P.K. Simpson, Fuzzy min-max neural networks-Part I: classification, IEEE Trans. Neural Networks, Vol.3, pp. 776–786 (1992).CrossRefGoogle Scholar
  14. 14.
    A. Rosenfeld and A.C. Kak, Digital Picture Processing, Academic Press, New York, NY (1992).Google Scholar
  15. 15.
    R.C. Gonzalez and P. Wintz, Digital Image Processing, Addison-Wesley, Reading, MA (1977).Google Scholar
  16. 16.
    L.S. Davis, A survey of edge detection techniques, Computer Vision, Graphics and Image Processing, Vol. 4, pp. 248–270 (1975).CrossRefGoogle Scholar
  17. 17.
    N.R. Pal and S.K. Pal, A review on image segmentation techniques, Pattern Recognition, Vol.26, No.9, pp. 1277–1294 (1993).CrossRefGoogle Scholar
  18. 18.
    J. Shah, Parameter estimation, multiscale representation and algorithm for energy-minimizing segmentation, Proc. Int. Conf. Pattern Recognition, pp. 815-819 (1990).Google Scholar
  19. 19.
    S. Lu and A. Szeto, Hierarchical artficial neural networks for edge enhancement, Pattern Recognition, Vol.26, pp. 1149–1163 (1993).CrossRefGoogle Scholar
  20. 20.
    J.K. Paik, J.C. Brailean, and A.K. Katsaggelos, An edge detection algorithm using multi-state ADALINES, Pattern Recognition, Vol.25, No.12, pp. 1495–1504 (1992).CrossRefGoogle Scholar
  21. 21.
    S.K. Pal and D.D. Majumder, Fuzzy Mathematical Approach to Pattern Recognition, John Wiley, Halsted Press, New York, NY (1986).Google Scholar
  22. 22.
    J. Serra, Image Analysis and Mathematical Morphology, Academic Press, New York, NY (1982).Google Scholar
  23. 23.
    R.M. Haralick, S.R. Sternberg, and X. Zhuang, Image analysis using mathematical morphology, IEEE Trans. Pattern Anal. Mach. Intell., Vol.9, pp. 32–550 (1987).Google Scholar
  24. 24.
    E.R. Caianiello, A calculus of hierarchical systems, Proc. Int. Conf. Pattern Recognition, Washington DC (1973).Google Scholar
  25. 25.
    A. Apostolico, E.R. Caianiello, E. Fischietti, and S. Vitulano, C-calculus: an elementary approach to some problems in pattern recognition, Pattern Recognition, Vol.10, pp. 375–387 (1978).CrossRefGoogle Scholar
  26. 26.
    E.R. Caianiello and A. Ventre, A model for C-calculus, Intern. Journ. General Systems, Vol.11, pp. 153–161 (1985).CrossRefGoogle Scholar
  27. 27.
    L.A. Zadeh, Fuzzy sets, Information and Control, Vol.8, pp. 338–353 (1965).CrossRefGoogle Scholar
  28. 28.
    A. Kandel, Fuzzy Mathematical Techniques with Applications, Addison-Wesley, New-York, NY (1986).Google Scholar
  29. 29.
    A. Petrosino and F. Pan, A fuzzy hierarchical neural network for image analysis, Proc. IEEE Conf. System, Man and Cybernetics, Vol.2, pp. 657–662 (1993).CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 1994

Authors and Affiliations

  • Eduardo R. Caianiello
    • 1
  • Alfredo Petrosino
    • 1
  1. 1.Facoltà di ScienzeUniversità di SalernoBaronissi (SA)Italy

Personalised recommendations