Robust Chinese Character Recognition by Selection of Binary-Based and Grayscale-Based Classifier

  • Yoshinobu Hotta
  • Jun Sun
  • Yutaka Katsuyama
  • Satoshi Naoi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3872)


As the spread of digital videos, digital cameras, and camera phones, lots of researches are reported about degraded character recognition. It is found that while the grayscale-based classifier is powerful for degraded character, the performance for clear character is not so good as binary-based classifier. In this paper, a dynamic classifier selection method is proposed to combine the two classifiers based on an estimation of the degradation level and the recognition reliability of the input character images. Experimental results show that the proposed method can achieve better recognition performance than the two individual ones.


Recognition Rate Recognition Accuracy Character Recognition Camera Phone Degradation Level 
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.
    Omachi, S., Sun, F., Aso, H.: A Noise-Adaptive Discriminant Function and Its Application to Blurred Machine-Printed Kanji Recognition. IEEE Trans. PAMI 22(3), 314–319 (2000)Google Scholar
  2. 2.
    Shiku, O., Nakamura, A., Miyahara, S., Ohyama, T.: Blurred Character Recognition by Complementing Features of Blurred Regions. IEICE D-II J87-D-II(3), 808–817 (2004) (in Japanese)Google Scholar
  3. 3.
    Ishida, H., Yanadume, S., Takahashi, T., Ide, I., Mekada, Y., Murase, H.: Recognition of Low-Resolution Characters by a Generative Learning Method. In: Proc. of the 1st Int’l Workshop on Camera-Based Document Analysis and Recognition (CBDAR 2005), pp. 45–51 (2005)Google Scholar
  4. 4.
    Sun, J., Hotta, Y., Katsuyama, Y., Naoi, S.: Low Resolution Character Recognition by Dual Eigenspace and Synthetic Degraded Patterns. In: Proc. of the 1st ACM Workshop on Hardcopy Document Processing, pp. 15–22 (2004)Google Scholar
  5. 5.
    Sawaki, M., Murase, H., Hagita, N.: Character Recognition in Bookshelf Images by Automatic Template Selection. In: Proc. of ICPR 1998, vol. 2, pp. 1117–1120 (1998)Google Scholar
  6. 6.
    Yam, H.S., Smith, E.H.B.: Estimating Degradation Model Parameters from Character Images. In: Proc. of Seventh ICDAR, pp. 710–714 (2003)Google Scholar
  7. 7.
    Iijima, T.: Theory of Pattern Recognition. Series of basic information technology 6, Morikita Publishing Company Ltd. (1989)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Yoshinobu Hotta
    • 1
  • Jun Sun
    • 2
  • Yutaka Katsuyama
    • 1
  • Satoshi Naoi
    • 1
  2. 2.FUJITSU R&D CENTER Co.,Ltd.BeijingP.R. China

Personalised recommendations