Improved simulated annealing, Boltzmann machine, and attributed graph matching

  • Lei Xu
  • Erkki Oja
Part II Theory, Algorithms
Part of the Lecture Notes in Computer Science book series (LNCS, volume 412)


By separating the search control and the solution updating of the commonly used simulated annealing technique, we propose a revised version of the simulated annealing method which produces better solutions and can reduce the computation time. We also use it to improve the performance of the Boltzmann machine. Furthermore, we present a simple combinatorial optimization model for solving the attributed graph matching problem of e.g. computer vision and give two algorithms to solve the model, one using our improved simulated annealing method directly, the other using it via the Boltzmann machine. Computer simulations have been conducted on the model using both the revised and the original simulated annealing and the Boltzmann machine. The advantages of our revised methods are shown by the results.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    S. Kirkpatrick et al, Science, Vol.220, No. 4598, 1983, pp671–680.Google Scholar
  2. [2]
    E.H.L. Aarts et al, Philips J Res. Vol.40, No.4, 1985, pp193–226.Google Scholar
  3. [3]
    L. Xu, Proc. of 9th ICPR, Vol. II, Rome, Italy, Nov. 1988, pp1040–1042.Google Scholar
  4. [4]
    G.E.Hinton et al, ”Boltzmann Machines: Constraint Satisfaction Networks that learn”, Tech. Rep. No. CMU-CS-84-119, Carnegie-Mellon Univ.Google Scholar
  5. [5]
    J. Hopfield et al, Biological Cybernetics, Vol.52, 1985, pp141–152.Google Scholar
  6. [6]
    J. Ramanujam, Proc. of 1988 IEEE ICNN, Vol.II, pp325–332. San Diego, California, 1988.Google Scholar
  7. [7]
    Y.P.Simon Foo, i.b.i.d., pp275–290.Google Scholar
  8. [8]
    L. Xu, ”An Improved Simulated Annealing method and Its Application to Clustering Analysis”, to appear on Information and Control, a Journal of Chinese Society of Automation (in Chinese).Google Scholar
  9. [9]
    L. Xu, ”An Improvement on Simulated Annealing and Boltzmann Machine”, Proc. of IJCNN'90, Washington D.C., Jan. 1990.Google Scholar
  10. [10]
    W.H.Tsai and K.S.Fu, IEEE Trans. Vol. SMC-9, No.12, 1979Google Scholar
  11. [11]
    W.H. Tsai and K.S. Fu, IEEE Trans. Vol. SMC-13, No.1., 1983, pp48–62.Google Scholar
  12. [12]
    M. You and K.C. Wang, Proc. of 7th IJCPR, Vol.1, 1984, pp314–319.Google Scholar
  13. [13]
    C.C. Shen and W.H. Tsai, IEEE Trans. Vol. C-34, No.3, 1985, pp197–203.Google Scholar
  14. [14]
    L.Xu and E.Oja, ”Neural Networks for Attributed Graph Matching in Machine Vision”, Tech. Rep., Lappeenranta Univ. Tech., Oct., 1989.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1990

Authors and Affiliations

  • Lei Xu
    • 1
  • Erkki Oja
    • 1
  1. 1.Department of Information TechnologyLappeenranta University of TechnologyLappeenrantaFinland

Personalised recommendations