Active Graph Matching Based on Pairwise Probabilities between Nodes

  • Xavier Cortés
  • Francesc Serratosa
  • Albert Solé-Ribalta
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7626)

Abstract

We propose a method to perform active graph matching in which the active learner queries one of the nodes of the first graph and the oracle feedback is the corresponding node of the other graph. The method uses any graph matching algorithm that iteratively updates a probability matrix between nodes (Graduated Assignment, Expectation Maximisation or Probabilistic Relaxation). The oracle’s feedback is used to update the costs between nodes and arcs of both graphs. We present and validate four different active strategies based on the probability matrix between nodes. It is not needed to modify the code of the graph-matching algorithms, since our method simply needs to read the probability matrix and to update the costs between nodes and arcs. Practical validation shows that with few oracle’s feedbacks, the algorithm finds the labelling that the user considers optimal because imposing few labellings the other ones are corrected automatically.

Keywords

Machine Learning Active Graph Matching Interactive Graph Matching Least Confident Maximum Entropy Expected Model Change 

References

  1. 1.
    Mitchell, T.: Machine Learning. Mcgraw-Hill International Edit (1997) ISBN-13: 978-0071154673Google Scholar
  2. 2.
    Conte, D., Foggia, P., Sansone, C., Vento, M.: Thirty Years Of Graph Matching In Pattern Recognition. International Journal of Pattern Recognition and Artificial Intelligence 18(3), 265–298 (2004)CrossRefGoogle Scholar
  3. 3.
    Settles, B.: Active Learning Literature Survey. Computer Science Technical Report 1648, University of Wisconsin-MadisonGoogle Scholar
  4. 4.
    Wang, R., Kwong, S., Chen, D.: Inconsistency-based active learning for support vector machines. Pattern Recognition 45(10), 3751–3767 (2012)CrossRefGoogle Scholar
  5. 5.
    Gorisse, D., Cord, M., Precioso, F.: SALSAS: Sub-linear active learning strategy with approximate k-NN search. Pattern Recognition 44(10-11), 2343–2357 (2011)MATHCrossRefGoogle Scholar
  6. 6.
    Yu, D., Varadarajan, B., Deng, L., Acero, A.: Active learning and semi-supervised learning for speech recognition: A unified framework using the global entropy reduction maximization criterion. Computer Speech & Language 24(3), 433–444 (2010)CrossRefGoogle Scholar
  7. 7.
    Zhang, Q., Shiliang: Sun Multiple-view multiple-learner active learning. Pattern Recognition 43(9), 3113–3119 (2010)MATHCrossRefGoogle Scholar
  8. 8.
    Wang, Z., Yan, S., Zhang, C.: Active learning with adaptive regularization. Pattern Recognition 44(10-11), 2375–2383 (2011)MATHCrossRefGoogle Scholar
  9. 9.
    Patra, S., Bruzzone, L.: A cluster-assumption based batch mode active learning technique. Pattern Recognition Letters 33(9), 1042–1048 (2012)CrossRefGoogle Scholar
  10. 10.
    Zhang, D., Wang, F., Shi, Z., Zhang, C.: Interactive localized content based image retrieval with multiple-instance active learning. Pattern Recognition 43(2), 478–484 (2010)MATHCrossRefGoogle Scholar
  11. 11.
    Kanamori, T.: Pool-based active learning with optimal sampling distribution and its information geometrical interpretation. Neurocomputing 71(1-3), 353–362 (2007)CrossRefGoogle Scholar
  12. 12.
    Baranes, A., Oudeyer, P.-Y.: Active learning of inverse models with intrinsically motivated goal exploration in robots. Robotics and Autonomous Systems (available online, 2012)Google Scholar
  13. 13.
    Cord, M., Gosselin, P.H., Philipp-Foliguet, S.: Stochastic exploration and active learning for image retrieval. Image and Vision Computing 25(1), 14–23 (2007)CrossRefGoogle Scholar
  14. 14.
    Lughofer, E.: Hybrid active learning for reducing the annotation effort of operators in classification systems. Pattern Recognition 45(2), 884–896 (2012)CrossRefGoogle Scholar
  15. 15.
    Cheng, J., Wang, K.: Active learning for image retrieval with Co-SVM. Pattern Recognition 40(1), 330–334 (2007)MATHCrossRefGoogle Scholar
  16. 16.
    da Silva, A.T., Falcão, A.X., Magalhães, L.P.: Active learning paradigms for CBIR systems based on optimum-path forest classification. Pattern Recognition 44(12), 2971–2978 (2011)CrossRefGoogle Scholar
  17. 17.
    Gosselin, P.H., Precioso, F., Philipp-Foliguet, S.: Incremental kernel learning for active image retrieval without global dictionaries. Pattern Recognition 44(10-11), 2244–2254 (2011)CrossRefGoogle Scholar
  18. 18.
    King, R.D., et al.: Functional genomic hypothesis generation and experimentation by a robot scientist. Nature 427(6971), 247–252 (2004)CrossRefGoogle Scholar
  19. 19.
    Yu, H.: SVM selective sampling for ranking with application to data retrieval. In: Proceedings of the International Conference on Knowledge Discovery and Data Mining (KDD), pp. 354–363. ACM Press (2005)Google Scholar
  20. 20.
    Kotsiantis, S.B.: Supervised Machine Learning: A Review of Classification Techniques. Informatica 31, 249–268 (2007)MathSciNetMATHGoogle Scholar
  21. 21.
    Sanchís, A., Juan, A., Vidal, E.: A Word-Based Naïve Bayes Classifier for Confidence Estimation in Speech Recognition. IEEE Transactions on Audio, Speech & Language Processing 20(2), 565–574 (2012)Google Scholar
  22. 22.
    Toselli, A.H., Romero, V., Pastor, M., Vidal, E.: Multimodal interactive transcription of text images. Pattern Recognition 43(5), 1814–1825 (2010)MATHCrossRefGoogle Scholar
  23. 23.
    Fekete, G., Eklundh, J.O., Rosenfeld, A.: Relaxation: Evaluation and Applications. IEEE Transactions on Pattern Analysis and Machine Intelligence 3(4), 459–469 (1981)CrossRefGoogle Scholar
  24. 24.
    Gold, S., Rangarajan, A.: A Graduated Assignment Algorithm for Graph Matching. IEEE Transactions on Pattern Analysis and Machine Intelligence 18(4), 377–388 (1996)CrossRefGoogle Scholar
  25. 25.
    Luo, B., Hancock, E.R.: Structural graph matching using the EM algorithm and singular value decomposition. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(10), 1120–1136 (2001)CrossRefGoogle Scholar
  26. 26.
    Sanromà, G., Alquézar, R., Serratosa, F., Herrera, B.: Smooth Point-set Registration using Neighbouring Constraints. Available on line Pattern Recognition Letters (2012)Google Scholar
  27. 27.
    Sanromà, G., Alquézar, R., Serratosa, F.: A New Graph Matching Method for Point-Set Correspondence using the EM Algorithm and Softassign. Computer Vision and Image Understanding 116(2), 292–304 (2012)CrossRefGoogle Scholar
  28. 28.
    Romero, V., Toselli, A.H., Vidal, E.: Multimodal interactive handwritten text transcription. Word Scientific (2012)Google Scholar
  29. 29.
    Caetano, T.S., Caelli, T., Schuurmans, D., Barone, D.A.C.: Graphical Models and Point Pattern Matching. IEEE Trans. Pattern Analysis and Machine Intelligence 28(10), 1646–1663 (2006)CrossRefGoogle Scholar
  30. 30.
    Kuhn, H.W.: The Hungarian method for the assignment problem Export. Naval Research Logistics Quarterly 2(1-2), 83–97 (1955)MathSciNetCrossRefGoogle Scholar
  31. 31.
    Serratosa, F., Cortés, X., Solé-Ribalta, A.: Interactive Graph Matching by means of Imposing the Pairwise Costs. In: International Conference on Pattern Recognition, ICPR 2012, Tsukuba, Japan (accepted for publication, 2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Xavier Cortés
    • 1
  • Francesc Serratosa
    • 1
  • Albert Solé-Ribalta
    • 1
  1. 1.Departament d’Enginyeria Informàtica i MatemàtiquesUniversitat Rovira i VirgiliSpain

Personalised recommendations