Self-training Strategies for Handwriting Word Recognition

  • Volkmar Frinken
  • Horst Bunke
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5633)

Abstract

Handwriting recognition is an emerging subfield of human-computer interaction that has many potential industrial applications, e.g. in postal automation, bank check processing, and automatic form reading. Training a recognizer, however, requires a substantial amount of training examples together with their corresponding ground truth, which needs to be created by humans. A promising way to significantly reduce this effort, and hence cut system development costs, is offered by semi-supervised learning, in which both text with and text without transcription is used for training. However, until today there is no straightforward and established way of semi-supervised learning, particularly not for handwriting recognition. In the self-training approach, an initially trained recognition system creates a new training set from unlabeled data. Using this set, a new recognizer is created. The creation of the training set is done by selecting elements from the unlabeled set, according to their recognition confidence. The success of self-training depends crucially on the data selected. In this paper, we test and compare different rules used to select new training data for single word recognition with and without additional language information in the form of a dictionary. We demonstrate that it is possible to substantially increase the recognition accuracy for both systems.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    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)CrossRefGoogle Scholar
  2. 2.
    Palacios, R., Gupta, A., Wang, P.S.: Handwritten Bank Check Recognition Of Courtesy Amounts. Int’l Journal of Image and Graphics 4(2), 1–20 (2004)Google Scholar
  3. 3.
    Ye, M., Viola, P.A., Raghupathy, S., Sutanto, H., Li, C.: Learning to Group Text Lines and Regions in Freeform Handwritten Notes. In: Ninth Int’l Conf. on Document Analysis and Recognition, pp. 28–32. IEEE Computer Society Press, Los Alamitos (2007)Google Scholar
  4. 4.
    Govindaraju, V., Xue, H.: Fast Handwriting Recognition for Indexing Historical Documents. In: First Int’l Workshop on Document Image Analysis for Libraries, pp. 314–320. IEEE Computer Society Press, Los Alamitos (2004)Google Scholar
  5. 5.
    Bunke, H.: Recognition of Cursive Roman Handwriting - Past, Present and Future. In: Proc. 7th Int’l Conf. on Document Analysis and Recognition, August 2003, vol. 1, pp. 448–459 (2003)Google Scholar
  6. 6.
    Vinciarelli, A.: A Survey On Off-Line Cursive Word Recognition. Pattern Recognition 35(7), 1433–1446 (2002)CrossRefMATHGoogle Scholar
  7. 7.
    Chapelle, O., Schölkopf, B., Zien, A.: Semi-Supervised Learning. MIT Press, Cambridge (2006)CrossRefGoogle Scholar
  8. 8.
    Zhu, X.: Semi-Supervised Learning Literature Survey. Technical Report 1530, Computer Science, University of Wisconsin-Madison (2005), http://www.cs.wisc.edu/~jerryzhu/pub/ssl_survey.pdf
  9. 9.
    Seeger, M.: Learning with Labeled and Unlabeled Data. Technical Report, University of Edinburgh, 5 Forest Hill, Edinburgh, EH1 2QL (2002)Google Scholar
  10. 10.
    Ji, S., Watson, L.T., Carin, L.: Semisupervised Learning of Hidden Markov Models via a Homotopy Method. IEEE Transactions on Pattern Analysis and Machine Intelligence 31(2), 275–287 (2009)CrossRefGoogle Scholar
  11. 11.
    Inoue, M., Ueda, N.: Exploitation of Unlabeled Sequences in Hidden Markov Models. IEEE Transactions on Pattern Analysis and Machine Intelligence 25(12), 1570–1581 (2003)CrossRefGoogle Scholar
  12. 12.
    Ball, G.R., Srihari, S.: Prototype Integration in Off-Line Handwriting Recognition Adaptation. In: Proc. Int’l. Conf. on Frontiers in Handwriting Recognition, pp. 529–534 (2008)Google Scholar
  13. 13.
    Frinken, V., Bunke, H.: Evaluating Retraining Rules for Semi-Supervised Learning in Neural Network Based Cursive Word Recognition. In: 9th Int’l Conference on Document Analysis and Recognition (accepted for publication) (2009)Google Scholar
  14. 14.
    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)CrossRefMATHGoogle Scholar
  15. 15.
    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
  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.
    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
  18. 18.
    Bertolami, R., Zimmermann, M., Bunke, H.: Rejection Strategies for Off-Line Handwritten Text Line Recognition. Pattern Recognition Letters 27(16), 2005–2012 (2006)CrossRefGoogle Scholar
  19. 19.
    Blum, A., Mitchell, T.: Combining Labeled and Unlabeled Data with Co-Training. In: COLT 1998: Proc. of the 11th annual Conference on Computational Learning Theory, pp. 92–100. ACM, New York (1998)Google Scholar
  20. 20.
    Scudder, H.J.: Probability of Error of Some Adaptive Pattern-Recognition Machines. IEEE Transaction on information Theory 11, 363–371 (1965)MathSciNetCrossRefMATHGoogle Scholar
  21. 21.
    Nigam, K., Ghani, R.: Analyzing the Effectiveness and Applicability of Co-Training. In: 9th Int’l Conf. on Information and Knowledge Management CIKM, pp. 86–93 (2000)Google Scholar
  22. 22.
    Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum Likelihood from Incomplete Data via the EM Algorithm. Journal of the Royal Statistical Society, Series B 39(1), 1–38 (1977)MathSciNetMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Volkmar Frinken
    • 1
  • Horst Bunke
    • 1
  1. 1.Institute of Computer Science and Applied MathematicsUniversity of BernBernSwitzerland

Personalised recommendations