Cursive Handwritten Word Recognition by Integrating Multiple Classifiers

  • Kenichi Maruyama
  • Makoto Kobayashi
  • Yasuaki Nakano
  • Hirobumi Yamada
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1655)


This paper proposes a methodf or cursive handwritten word recognition. In the traditional research, many cursive handwritten word recognition systems useda single methodfor character recognition. In this research, we propose a methodi ntegrating multiple character classifier to improve wordre cognition rate combining the results of them. As a result of the experiment using two classifiers, wordre cognition rate is improvedt han from those using a single character classifier.


Hide Markov Model Word Recognition Recognition Rate Pattern Match Character 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.


  1. 1.
    Rice, S. et al: A Report on the Accuracy of OCR Devices. ISRI Technical Report. Information Science Research Institute. University of Nevada. Las Vegas (1992) 1–6Google Scholar
  2. 2.
    Matsui, T. et al: State of the Art of Handwritten Numeral Recognition in Japan.Proc. 2ndI nt. Conference on Document Analysis and Recognition (1993) 391–396Google Scholar
  3. 3.
    P. Sinha and J. Mao: Combining Multiple OCRs for OptimizingWord Recognition. Proc.14th ICPR. Brisbane, Australia (1998) 436–438Google Scholar
  4. 4.
    Hirobumi Yamada and Yasuaki Nakano: Cursive Handwritten Word Recognition Using Multiple Segmentation Determinedb y Contour Analysis. IEICE Trans.INF&SYSTE. vol.E79-D-5 (1996)Google Scholar
  5. 5.
    S. Mori, C. Y. Suen and K. Yamamoto: Historical Review of OCR Research and Development. Proc. IEEE. 80 (7) (1992) 1029–1058CrossRefGoogle Scholar
  6. 6.
    G. E. Kopec and P. A. Chou: Document Image Decording Using Malkov Source Models. IEEE Trans. on PAMI. 16 (6) (1994) 602–617Google Scholar
  7. 7.
    Lawrence R. Rabiner: A Tutrial on Hidden Markov Models and Selected Applications in Speech Recognition. Proc.IEEE. 77 (2) (1989) 257–286CrossRefGoogle Scholar
  8. 8.
    J. C. Simon: Off-line cursive word recognition. Proc. IEEE 80 (7) (1992) 1150–1161CrossRefGoogle Scholar
  9. 9.
    R. M. Bozinovic and S. N. Srihari: Off-line cursive footnote word recognition. IEEE Trans. on PAMI. j11 (1) (1989) 68–83Google Scholar
  10. 10.
    A. Kundu and P. Bahl: Recognition of Handwritten Script: A Hidden Markov Model Based Approach. Proc. Int. Conf. on Acoustics. Speech. and Signal Processing. New York City. USA. (1998) 928–931Google Scholar
  11. 11.
    H.–S. Park and S.–W. Lee: Off–line Recognition of Large-set Handwritten Characters with Multiple Hidden Markov Models. Pattern Recognition. 29 (2) (1996) 231–244CrossRefGoogle Scholar
  12. 12.
    H.–S. Park and S.–W. Lee: A truly 2–D hidden Markov model for off–line handwritten character recognition. Pattern Recognition. 31 (12) (1998) 1849–1864CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Kenichi Maruyama
    • 1
  • Makoto Kobayashi
    • 1
  • Yasuaki Nakano
    • 2
  • Hirobumi Yamada
    • 1
  1. 1.Dept. of Information EngineeringShinshu UniversityNaganoJapan
  2. 2.Faculty of EngineeringToyohashi University of TechnologyToyohashi, AichiJapan

Personalised recommendations