Handwritten Chinese character recognition using displacement extraction based on directional features

  • Yoshiki Mizukami
  • Kazutoshi Koga
Poster Session D: Biomedical Applications, Detection, Control & Surveillance, Inspection, Optical Character Recognition
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1311)


This paper presents a recognition method for handwritten Chinese characters using displacement extraction based on directional features. In the proposed method, after extracting the features from an input image, the displacement is extracted by the minimization of an energy functional, which consists of the Euclidean distance and the smoothness of the extracted displacement. Experiments are performed on a set of handwritten Chinese characters (ETL-8B). The improvement of the recognition performance of the proposed method is achieved as compared with the method without the displacement extraction.


  1. Trier, Ø. D., Jain, A. K. and Taxt, T.: Feature extraction methods for character recognition — A survey. Pattern Recognition, 29 (1996) 641–662CrossRefGoogle Scholar
  2. Saito, T., Yamada, H. and Yamamoto, K.: An analysis of handprinted Chinese characters by directional pattern matching approach. Trans. IECE (Japan), J65-D (1982) 550–557, in JapaneseGoogle Scholar
  3. Kimura, F. and Shridhar, M.: Handwritten numerical recognition based on multiple algorithms. Pattern Recognition, 24 (1991) pp. 969–983CrossRefGoogle Scholar
  4. Jain, A. K. and Chandrasekaran, B.: Dimensionality and sample size considerations in pattern recognition practice. Handbook of Statistics, Krishnaiah, P. R. and Kanal, L. N., eds, 2 (1982), North-Holland, AmsterdamGoogle Scholar
  5. Wakahara, T.: Shape matching using LAT and its application to handwritten numeral recognition. IEEE Trans. Pattern Anal. Mach. Intell., 16 (1994) 618–629CrossRefGoogle Scholar
  6. Daffertshofer, A. and Haken, H.: A new approach to recognition of deformed patterns. Pattern Recognition, 27 (1994) 1697–1705CrossRefGoogle Scholar
  7. Mizukami, Y. and Koga, K.: A Handwritten character recognition system using hierarchical displacement extraction algorithm. in Proc. 13th Int. Conf. Pattern Recognition, 3 (1996) 160–164CrossRefGoogle Scholar
  8. Yokoya, N.: Dense matching of two views with large displacement. in Prc. 1th Int. Conf. Image Processing, 1 (1994) 213–217CrossRefGoogle Scholar
  9. Yamada, H., Yamamoto, K. and Saito, T.: A nonlinear normalization method for handprinted Kanji character recognition — line density equalization. Pattern Recognition, 23 (1990) 1023–1029CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Yoshiki Mizukami
    • 1
  • Kazutoshi Koga
    • 1
  1. 1.Faculty of EngineeringYamaguchi UniversityYamaguchiJapan

Personalised recommendations