Combining Character Level Classifier and Probabilistic Lexicons in Handwritten Word Recognition – Comparative Analysis of Methods

  • Marek Kurzynski
  • Jerzy Sas
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3691)


In this paper the probabilistic aproach to handwritten words recognition is described. The decision is performed using results of character classification based on a character image analysis and probabilistic lexicon treated as a special kind of soft classifier. The novel approach to combining these both classifiers is proposed, where fusion procedure interleaves soft outcomes of both classifiers so as to obtain the best recognition quality. The proposed algorithms were experimentally investigated and results of recognition of polish handwritten surnames and names are given.


Word Recognition Character Recognition Handwritten Character Handwritten Document Handwritten Digit Recognition 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Liu, C., Nakashima, K., Sako, H., Fujisawa, H.: Handwritten Digit Recognition: Benchmarking of State-of-the-Art Techniques. Pattern Recognition 36, 2271–2285 (2003)zbMATHCrossRefGoogle Scholar
  2. 2.
    Lu, Y., Gader, P., Tan, C.: Combination of Multiple Classifiers Using Probabilistic Dictionary and its Application to Postcode Generation. Pattern Recognition 35, 2823–2832 (2002)zbMATHCrossRefGoogle Scholar
  3. 3.
    Kuncheva, L.: Combining Classifiers: Soft Computing Solutions. In: Pal, S., Pal, A. (eds.) Pattern Recognition: from Classical to Modern Approaches, pp. 427–451. World Scientific, Singapore (2001)CrossRefGoogle Scholar
  4. 4.
    Sas, J., Kurzynski, M.: Multilevel Recognition of Structured Handwritten Documents - Probabilistic Approach. In: Proc. 4th Int. Conf. on Computer Recognition Systems, pp. 723–730. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  5. 5.
    Sas, J., Kurzynski, M.: Application of Statistic Properties of Letter Succession in Polish Language to Handprint Recognition. In: Proc. 4th Int. Conf. on Computer Recognition Systems, pp. 731–739. Springer, HeidelbergGoogle Scholar
  6. 6.
    Sas, J.: Handwritten Laboratory Test Order Form Recognition Module for Distributed Clinic. J. of Medical Informatics and Technologies 8, 59–68 (2004)Google Scholar
  7. 7.
    Sas, J.: Three-Level Lexicon Based Handwritten Form Recognition Method. In: Klopotek, M., Tchorzewski, J. (eds.) Proc. VI Int. Conf. on Artificial Intelligence, vol. 1, pp. 113–124 (2004)Google Scholar
  8. 8.
    Devroye, L., Gyorfi, P., Lugossi, G.: A Probabilistic Theory of Pattern Recognition. Springer, New York (1996)zbMATHGoogle Scholar
  9. 9.
    Duda, R., Hart, P., Stork, D.: Pattern Classification. John Wiley and Sons, Chichester (2001)zbMATHGoogle Scholar
  10. 10.
    Woods, K., Kegelmeyer, W.: Combination of Multiple Classifiers Using Local Accuracy Estimates. IEEE Trans. on PAMI 19, 405–410 (1997)Google Scholar
  11. 11.
    Vinciarelli, A., et al.: Offline Recognition of Unconstrained Handwritten Text Using HMMs and Statistical Language Models. IEEE Trans. on PAMI 26, 709–720 (2004)Google Scholar
  12. 12.
    Xu, L., Krzyzak, A., Suen, C.: Methods of Combining of Multiple Classifiers and Their Applications to Handwriting Recognition. IEEE Trans. on SMC 22, 418–435 (1992)Google Scholar
  13. 13.
    Kapur, J., Kesavan, H.: Entropy Optimization Principles with Applications. Academic Press, London (1992)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Marek Kurzynski
    • 1
  • Jerzy Sas
    • 2
  1. 1.Faculty of Electronics, Chair of Systems and Computer NetworksWroclaw University of TechnologyWroclawPoland
  2. 2.Institute of Applied InformaticsWroclaw University of TechnologyWroclawPoland

Personalised recommendations