Handwritten Word Recognition Using Multi-view Analysis

  • J. J. de OliveiraJr.
  • C. O. de A. Freitas
  • J. M. de Carvalho
  • R. Sabourin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5856)


This paper brings a contribution to the problem of efficiently recognizing handwritten words from a limited size lexicon. For that, a multiple classifier system has been developed that analyzes the words from three different approximation levels, in order to get a computational approach inspired on the human reading process. For each approximation level a three-module architecture composed of a zoning mechanism (pseudo-segmenter), a feature extractor and a classifier is defined. The proposed application is the recognition of the Portuguese handwritten names of the months, for which a best recognition rate of 97.7% was obtained, using classifier combination.


Hide Markov Model Perceptual Feature Word Context Word Image Forward Algorithm 
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.


  1. 1.
    Schomaker, L., Segers, E.: A Method for the Determination of Features used in Human Reading of Cursive Handwriting. In: IWFHR 1998, The Netherlands, pp. 157–168 (1998)Google Scholar
  2. 2.
    Kapp, M.N., de Almendra Freitas, C.O., Sabourin, R.: Methodology for the Design of NN-based Month-Word Recognizers Written on Brazilian Bank Checks. International Journal on Image and Vision Computing 25(1), 40–49 (2007)CrossRefGoogle Scholar
  3. 3.
    de Almendra Freitas, C.O., Oliveira, L.S., Aires, S.K., Bortolozzi, F.: Handwritten Character Recognition Using Non-Symmetrical Perceptual Zoning. International Journal on Pattern Recognition and Artificial Intelligence 21(1), 1–21 (2007)CrossRefGoogle Scholar
  4. 4.
    de Almendra Freitas, C.O., Bortolozzi, F., Sabourin, R.: Study of Perceptual Similarity Between Different Lexicons. International Journal on Pattern Recognition and Artificial Intelligence 18(7), 1321–1338 (2004)CrossRefGoogle Scholar
  5. 5.
    Madhvanath, S., Govindaraju, V.: The Role of Holistic Paradigms in Handwritten Word Recognition. IEEE Trans. on PAMI 23(2), 149–164 (2001)Google Scholar
  6. 6.
    Oh, I., Suen, C.-Y.: A Class-Modular Feedforward Neural Network for Handwriting Recognition. Pattern Recognition 35(1), 229–244 (2002)zbMATHCrossRefGoogle Scholar
  7. 7.
    de Almendra Freitas, C.O., Bortolozzi, F., Sabourin, R.: Handwritten Isolated Word Recognition: An Approach Based on Mutual Information for Feature Set Validation. In: ICDAR 2001, Seattle - USA, pp. 665–669 (2001)Google Scholar
  8. 8.
    Kittler, J., Hatef, M., Duin, R.P.W., Matas, J.: On Combining Classifiers. IEEE Trans. on PAMI 20(3), 226–239 (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • J. J. de OliveiraJr.
    • 1
  • C. O. de A. Freitas
    • 2
  • J. M. de Carvalho
    • 3
  • R. Sabourin
    • 4
  1. 1.UFRN - Universidade Federal do Rio Grande do Norte 
  2. 2.PUC-PR - Pontíficia Universidade Católica do Paraná 
  3. 3.UFCG - Universidade Federal de Campina Grande 
  4. 4.ÉTS - École de Technologie Supérieure 

Personalised recommendations