Improved Handwriting Recognition by Combining Two Forms of Hidden Markov Models and a Recurrent Neural Network

  • Volkmar Frinken
  • Tim Peter
  • Andreas Fischer
  • Horst Bunke
  • Trinh-Minh-Tri Do
  • Thierry Artieres
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5702)

Abstract

Handwritten word recognition has received a substantial amount of attention in the past. Neural Networks as well as discriminatively trained Maximum Margin Hidden Markov Models have emerged as cutting-edge alternatives to the commonly used Hidden Markov Models. In this paper, we analyze the combination of these classifiers with respect to their potential for improving recognition performance. It is shown that a significant improvement can in fact be achieved, although the individual recognizers are highly optimized state-of-the-art systems. Also, it is demonstrated that the diversity of the recognizers has a profound impact on the improvement that can be achieved by the combination.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Vinciarelli, A.: A Survey On Off-Line Cursive Word Recognition. Pattern Recognition 35(7), 1433–1446 (2002)MATHCrossRefGoogle Scholar
  2. 2.
    Brakensiek, A., Rigoll, G.: Handwritten Address Recognition Using Hidden Markov Models. In: Dengel, A.R., Junker, M., Weisbecker, A. (eds.) Reading and Learning. LNCS, vol. 2956, pp. 103–122. Springer, Heidelberg (2004)Google Scholar
  3. 3.
    Kim, G., Govindaraju, V., Srihari, S.N.: An architecture for handwritten text recognition systems. Int’l Journal on Document Analysis and Recognition 2(1), 37–44 (1999)CrossRefGoogle Scholar
  4. 4.
    Do, T.-M.-T., Artieres, T.: Maximum Margin Training of Gaussian HMMs for Handwriting Recognition. In: 10th Int’l Conference on Document Analysis and Recognition (2009)Google Scholar
  5. 5.
    Graves, A., Fernández, S., Gomez, F., Schmidhuber, J.: Connectionist Temporal Classification: Labelling Unsegmented Sequential Data with Recurrent Neural Networks. In: 23rd Int’l Conf. on Machine Learning, pp. 369–376 (2006)Google Scholar
  6. 6.
    Kittler, J., Roli, F. (eds.): MCS 2000. LNCS, vol. 1857. Springer, Heidelberg (2000)Google Scholar
  7. 7.
    Kuncheva, L.I.: Combining Pattern Classifiers: Methods and Algorithms. Wiley-Interscience, Hoboken (2004)MATHCrossRefGoogle Scholar
  8. 8.
    Günter, S., Bunke, H.: Ensembles of Classifiers for Handwritten Word Recognition. Int’l Journal on Document Analysis and Recognition 5(4), 224–232 (2003)CrossRefGoogle Scholar
  9. 9.
    Verma, B.K., Gader, P.D., Chen, W.-T.: Fusion of multiple handwritten word recognition techniques. Pattern Recognition Letters 22(9), 991–998 (2001)MATHCrossRefGoogle Scholar
  10. 10.
    Wang, W., Brakensiek, A., Rigoll, G.: Combination of Multiple Classifiers for Handwritten Word Recognition. In: Int’l Workshop on Frontiers in Handwriting Recognition, pp. 117–122 (2002)Google Scholar
  11. 11.
    Marti, U.-V., Bunke, H.: The IAM-Database: An English Sentence Database for Offline Handwriting Recognition. Int’l Journal on Document Analysis and Recognition 5, 39–46 (2002)MATHCrossRefGoogle Scholar
  12. 12.
    Marti, U.-V., Bunke, H.: Using a Statistical Language Model to Improve the Performance of an HMM-Based Cursive Handwriting Recognition System. Int’l Journal of Pattern Recognition and Artificial Intelligence 15, 65–90 (2001)CrossRefGoogle Scholar
  13. 13.
    Yu, D., Deng, L.: Large-Margin Discriminative Training of Hidden Markov Models for Speech Recognition. In: First IEEE Int’l Conference on Semantic Computing, pp. 429–438 (2007)Google Scholar
  14. 14.
    Sha, F., Saul, L.K.: Large Margin Hidden Markov Models for Automatic Speech Recognition. In: NIPS. MIT Press, Cambridge (2007)Google Scholar
  15. 15.
    Do, T.-M.-T., Artieres, T.: Large Margin Trainng for Hidden Markov Models with Partially Observed States. In: 26th Int’l Conference on Machine Learning (2009)Google Scholar
  16. 16.
    Graves, A., Liwicki, M., Fernández, S., Bertolami, R., Bunke, H., Schmidhuber, J.: A Novel Connectionist System for Unconstrained Handwriting Recognition. IEEE Transaction on Pattern Analysis and Machine Intelligence (accepted for publication)Google Scholar
  17. 17.
    Kuncheva, L.I., Whitaker, C.J.: Measures of Diversity in Classifier Ensembles and Their Relationship with the Ensemble Accuracy. Machine Learning 51(2), 181–207 (2003)MATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Volkmar Frinken
    • 1
  • Tim Peter
    • 1
  • Andreas Fischer
    • 1
  • Horst Bunke
    • 1
  • Trinh-Minh-Tri Do
    • 2
  • Thierry Artieres
    • 2
  1. 1.Institute of Computer Science and Applied MathematicsUniversity of BernBernSwitzerland
  2. 2.LIP6 - Université Pierre et Marie CurieParisFrance

Personalised recommendations