Cluster Approach to Pattern Recognition

  • Makoto Kaburagi
  • Yasunori Motomura
  • Qiong Ou
  • Kazuhiro Ohtsuki
  • Atsuo Ono


This paper deals with the mathematical morphology as a cluster approach to image processing and the Hough transformation as an object of statistical physics. It is shown that the operation in mathematical morphology is equivalent to a single step of dynamics in a special neural network. We investigate dynamics of an image (the neural network) and examine the relation between the time interval to reach to an associative memory and the threshold. As for the Hough transformation, we derive the free energy expression for the transformation and proposed the Gaussian sum method.


Partition Function Cluster Approach Associative Memory Image Restoration Mathematical Morphology 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    R. Kikuchi, Phys. Rev. 81, 988 (1951).MathSciNetMATHCrossRefADSGoogle Scholar
  2. 2.
    T. Morita, J. Phys. Soc. Jpn. 12, 753 (1972).CrossRefADSGoogle Scholar
  3. 3.
    See for example, Foundations and Applications of Cluster Variation Method and Path Probability Method, edited by T. Morita, M. Suzuki, K. Wada, and M. Kaburagi, Progr. Theor. Phys. Suppl. 113 (1994).Google Scholar
  4. 4.
    K. Fukunaga, Introduction to Statistical Pttern Recognition, (Academic Press, New York, 1972).Google Scholar
  5. 5.
    T. Geszti, Physical Models of Neural Network, (World Scientfìc, Singapore, 1990).Google Scholar
  6. 6.
    S. Amari and K. Maginu, Neural Networks 1, 63 (1988).CrossRefGoogle Scholar
  7. 7.
    H. Nishimori and T. Ozeki, J. Phys. A: Math. Gen. 26, 859 (1993).MathSciNetMATHCrossRefADSGoogle Scholar
  8. 8.
    A. C. C. Coolen and D. Sherrington, Phys. Rev. E 49, 1921 (1994).ADSGoogle Scholar
  9. 9.
    A. Rosenfeld, Picture processing by computer, (Academic Press, New York, 1969).MATHGoogle Scholar
  10. 10.
    K. Tanaka, in Theory and Application of the Cluster Variation and Path Probability Methods, edited by J. L. Morán-López and J. M. Sanchez (Plenum, New York, 1996), p. 345.Google Scholar
  11. 11.
    J. Serra, Image Analysis and Mathematical Morphology, Vol. 1, (Academic Press, New York, 1989).Google Scholar
  12. 12.
    P. Margos and R. W. Schafer, Proc. IEEE 78, 690 (1990).CrossRefGoogle Scholar
  13. 13.
    P. V. C. Hough and B. M. Powell, Nuovo Cimento 18, 1184 (1960).CrossRefGoogle Scholar
  14. 14.
    P. V. C. Hough, U. S. Patent 3069654 (1962).Google Scholar
  15. 15.
    R. O. Duda and P. E. Hart, Commun. ACM 15, 11 (1972).CrossRefGoogle Scholar
  16. 16.
    Y. Noguchi and A. Ono, Nucl. Instr. A253, 27 (1986).ADSGoogle Scholar
  17. 17.
    Q. Ou and A. Ono, preprint.Google Scholar
  18. 18.
    P. L. Palmer, M. Petrou, and J. Kittler, CVGIP: Image Understanding 58, 221 (1993).CrossRefGoogle Scholar

Copyright information

© Plenum Press, New York 1996

Authors and Affiliations

  • Makoto Kaburagi
    • 1
    • 2
  • Yasunori Motomura
    • 2
  • Qiong Ou
    • 2
  • Kazuhiro Ohtsuki
    • 1
  • Atsuo Ono
    • 1
    • 2
  1. 1.Faculty of Cross-Cultural-StudiesKobe UniversityNada, KobeJapan
  2. 2.Graduate School of Science and TechnologyKobe UniversityNada, KobeJapan

Personalised recommendations