Hybrid Genetic Algorithm and Procrustes Analysis for Enhancing the Matching of Graphs Generated from Shapes

  • Gerard Sanromà
  • Francesc Serratosa
  • René Alquézar
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5342)

Abstract

Typically, graphs generated via skeletonization of shape images are small and present low structural constraints. This fact constitutes a source of ambiguities for structural matching methods. Hybrid Genetic Algorithms have been effectively used for graph matching. This paper presents a new method which combines Hybrid Genetic Search with an enhanced model for graph matching. This enhanced model is based on the cliques model by Wilson and Hancock but introduces Procrustes Analysis over positional information in order to eliminate ambiguities. Comparative results are presented of the performance of the Hybrid Genetic algorithm with both the original cliques model and the enhanced model.

Keywords

graph matching hybrid genetic algorithm procrustes analysis shape analysis cliques model 

References

  1. 1.
    Luo, B., Hancock, E.R.: Structural graph matching using the em algorithm and singular value decomposition. Pattern Analysis and Machine Intelligence 23(10) (October 2001)Google Scholar
  2. 2.
    Wilson, R.C., Hancock, E.R.: Structural matching by discrete relaxation. Pattern Analysis and Machine Intelligence 19(6) (June 1997)Google Scholar
  3. 3.
    Gold, S., Rangarajan, A.: A graduated assignment algorithm for graph matching. Pattern Analysis and Machine Intelligence 18(4) (April 1996)Google Scholar
  4. 4.
    Dryden, I.L., Mardia, K.V.: Statistical Shape Analysis. John Wiley and Sons, Chichester (1998)MATHGoogle Scholar
  5. 5.
    Whitley, D., Beveridge, R., Graves, C., Mathias, K.: Test driving three 1995 genetic algorithms: New test functions and geometric matching. J. Heurist 1 (June 1995)Google Scholar
  6. 6.
    Cross, A.D.J., Wilson, R.C., Hancock, E.R.: Inexact graph matching using genetic search. Pattern Recognition 30(6) (1997)Google Scholar
  7. 7.
    Myers, R., Hancock, E.R.: Least-commitment graph matching with genetic algorithms. Pattern recognition 34 (October 1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Gerard Sanromà
    • 1
  • Francesc Serratosa
    • 1
  • René Alquézar
    • 2
  1. 1.Departament d’Enginyeria Informàtica i MatemàtiquesUniversitat Rovira i VirgiliSpain
  2. 2.Departament de Llenguatges i Sistemes InformàticsUniversitat Politècnica de CatalunyaSpain

Personalised recommendations