A Markov Random Field Model for Combining Optimum-Path Forest Classifiers Using Decision Graphs and Game Strategy Approach

  • Moacir P. PontiJr.
  • João Paulo Papa
  • Alexandre L. M. Levada
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7042)

Abstract

The research on multiple classifiers systems includes the creation of an ensemble of classifiers and the proper combination of the decisions. In order to combine the decisions given by classifiers, methods related to fixed rules and decision templates are often used. Therefore, the influence and relationship between classifier decisions are often not considered in the combination schemes. In this paper we propose a framework to combine classifiers using a decision graph under a random field model and a game strategy approach to obtain the final decision. The results of combining Optimum-Path Forest (OPF) classifiers using the proposed model are reported, obtaining good performance in experiments using simulated and real data sets. The results encourage the combination of OPF ensembles and the framework to design multiple classifier systems.

Keywords

Majority Vote Markov Random Field Star Graph Markov Random Field Model Decision Graph 
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.

References

  1. 1.
    Breiman, L.: Bagging predictors. Machine Learning Journal 2(24), 123–140 (1996)MATHGoogle Scholar
  2. 2.
    Brown, G., Kuncheva, L.I.: “Good” and “Bad” diversity in majority vote ensembles. In: El Gayar, N., Kittler, J., Roli, F. (eds.) MCS 2010. LNCS, vol. 5997, pp. 124–133. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  3. 3.
    Frank, A., Asuncion, A.: UCI machine learning repository (2010), http://archive.ics.uci.edu/ml
  4. 4.
    Freund, T.: Boosting: a weak learning algorithm by majority. Information and Computation 121(2), 256–285 (1995)MathSciNetCrossRefMATHGoogle Scholar
  5. 5.
    Georgiou, H., Mavroforakis, M., Theodoridis, S.: A game-theoretic approach to weighted majority voting for combining SVM classifiers. In: Kollias, S.D., Stafylopatis, A., Duch, W., Oja, E. (eds.) ICANN 2006. LNCS, vol. 4131, pp. 284–292. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  6. 6.
    Ho, T.: The random subspace method for constructing decision forests. IEEE Trans. Pattern Analysis and Machine Intelligence 20(8), 832–844 (1998)CrossRefGoogle Scholar
  7. 7.
    Kaluza, B., Mirchevska, V., Dovgan, E., Lustrek, M., Gams, M.: An agent-based approach to care in independent living. In: Int. Joint Conf. on Ambient Intelligence (AML 2010), Malaga, Spain (2010)Google Scholar
  8. 8.
    Kittler, J., Hatef, M., Duin, R., Matas, J.: On combining classifiers. IEEE Trans. Pattern Analysis and Machine Intelligence 20(3), 226–239 (1998)CrossRefGoogle Scholar
  9. 9.
    Levada, A.L.M., Mascarenhas, N.D.A., Tannús, A.: A novel MAP-MRF approach for multispectral image contextual classification using combination of suboptimal iterative algorithms. Pattern Recognition Letters 31(13), 1795–1808 (2010)CrossRefGoogle Scholar
  10. 10.
    Li, J., Wang, J.Z.: Automatic linguistic indexing of pictures by a statistical modeling approach. IEEE Trans. Pattern Analysis and Machine Intelligence 25(9), 1075–1088 (2003)CrossRefGoogle Scholar
  11. 11.
    Nash, J.F.: Equilibrium points in n-person games. Proceedings of the National Academy of Sciences 36(1), 48–49 (1950)MathSciNetCrossRefMATHGoogle Scholar
  12. 12.
    Papa, J., Falcão, A.X., Suzuki, C.T.N.: Supervised pattern classification based on optimum-path forest. Int. J. Imaging Systems and Technology 19(2), 120–131 (2009)CrossRefGoogle Scholar
  13. 13.
    Ponti Jr., M.P., Papa, J.P.: Improving accuracy and speed of optimum-path forest classifier using combination of disjoint training subsets. In: Sansone, C. (ed.) MCS 2011. LNCS, vol. 6713, pp. 237–248. Springer, Heidelberg (2011)Google Scholar
  14. 14.
    Yamazaki, T., Gingras, D.: Image classification using spectral and spatial information based on mrf models. IEEE Trans. on Image Processing 4(9), 1333–1339 (1995)CrossRefGoogle Scholar
  15. 15.
    Yu, S., Berthod, M.: A game strategy approach for image labelling. Computer Vision and Image Understanding 61(1), 32–37 (1995)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Moacir P. PontiJr.
    • 1
  • João Paulo Papa
    • 2
  • Alexandre L. M. Levada
    • 3
  1. 1.Institute of Mathematical and Computer SciencesUniversity of São Paulo (ICMC/USP)São CarlosBrazil
  2. 2.Department of ComputingUNESP — Univ Estadual PaulistaBauruBrazil
  3. 3.Computing DepartmentFederal University of São Carlos (DC/UFSCar)São CarlosBrazil

Personalised recommendations