Graph Matching: Fast Candidate Elimination Using Machine Learning Techniques

  • M. Lazarescu
  • H. Bunke
  • S. Venkatesh
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1876)


Graph matching is an important class of methods in pattern recognition. Typically, a graph representing an unknown pattern is matched with a database of models. If the database of model graphs is large, an additional factor in induced into the overall complexity of the matching process. Various techniques for reducing the influence of this additional factor have been described in the literature. In this paper we propose to extract simple features from a graph and use them to eliminate candidate graphs from the database. The most powerful set of features and a decision tree useful for candidate elimination are found by means of the C4.5 algorithm, which was originally proposed for inductive learning of classification rules. Experimental results are reported demonstrating that efficient candidate elimination can be achieved by the proposed procedure.

Key words

Structural pattern recognition graph matching graph isomorphism database retrieval database indexing machine learning C4.5 


  1. 1.
    L.G. Shapiro and R.M. Haralick. Structural descriptions and inexact matching. IEEE Trans. Pattern Analysis and Machine Intelligence, volume 3, pages 504–519, 1981.Google Scholar
  2. 2.
    A. Sanfeliu and K.S. Fu. A distance measure between attributed relational graphs for pattern recognition. In IEEE Trans. Systems, Man, and Cybernetics, volume 13, pages 353–363, 1983.zbMATHGoogle Scholar
  3. 3.
    B. Messmer and H. Bunke. A new algorithm for error-tolerant subgraph isomorphism detection. In IEEE Trans. Pattern Analysis and Machine Intelligence, volume 20, pages 493–505, 1998.CrossRefGoogle Scholar
  4. 4.
    S.W. Lu, Y. Ren, and C.Y. Suen. Hierarchical attributed graph represenation and recognition of handwritten Chinese characters. In Pattern Recognition, volume 24, pages 617–632, 1991.CrossRefGoogle Scholar
  5. 5.
    J. Rocha and T. Pavlidis. A shape analysis model with applications to a character recognition system. In IEEE Trans. Pattern Analysis and Machine Intelligence, volume 16, pages 393–404, 1994.CrossRefGoogle Scholar
  6. 6.
    S.W. Lee, J.H. Kim, and F.C.A Groen. Translation-, rotation-, and scale-invariant recognition of hand-drawn symbols in schematic diagrams. In Int’l J. Pattern Recognition and Artificial Intelligence, volume 4, no. 1, pages 1–15, 1990.CrossRefGoogle Scholar
  7. 7.
    H. Bunke, B. Messmer. Clustering and error-correcting matching of graphs for learning and recognition of symbols in engineering drawings. J. Hull and S. Taylor (eds.): Document Analysis Systems II, pages 102–117. World Scientific, 1998.Google Scholar
  8. 8.
    A. Pearce, T. Caelli, and W.F. Bischof. Rulegraphs for graph matching in pattern recognition. In Pattern Recognition, volume 27, no. 9, pages 1231–1246, 1994.CrossRefGoogle Scholar
  9. 9.
    E.K. Wong. Model matching in robot vision by subgraph isomorphism. In Pattern Recognition, volume 25, no. 3, pages 287–304, 1992.CrossRefGoogle Scholar
  10. 10.
    L.G. Shapiro and R.M. Haralick. Organization of relational models for scene analysis. In IEEE Trans. Pattern Analysis and Machine Intelligence, volume 3, pages 595–602, 1982.CrossRefGoogle Scholar
  11. 11.
    K. Sengupta and K.L. Boyer. Organizing large structural modelbases. In IEEE Trans. Pattern Analysis and Machine Intelligence, volume 17, 1995.Google Scholar
  12. 12.
    B. Messmer and H. Bunke. A decision tree approach to graph and subgraph isomorphism. In Pattern Recognition, volume 32, pages 1979–1998, 1999.CrossRefGoogle Scholar
  13. 13.
    J. R. Quinlan. C4.5: Programs for machine learning. Morgan Kaufmann Publishers, 1993.Google Scholar
  14. 14.
    J.R. Ullman. An algorithm for subgraph isomorphism. In JACM, volume 23(1), pages 31–42, 1976.zbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • M. Lazarescu
    • 1
    • 2
  • H. Bunke
    • 1
  • S. Venkatesh
    • 2
  1. 1.Computer Science DepartmentUniversity of BernSwitzerland
  2. 2.School of ComputingCurtin UniversityPerthAustralia

Personalised recommendations