Substructure shape analysis for Kanji character recognition

  • Jairo Rocha
  • Hiromichi Fujisawa
Handwritten and Printed Character Recognition
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1121)


A method towards analytical recognition of Chinese characters is described. Basic character components (substructures) of any size are recognized anywhere on a Kanji string, even if they touch other components. The algorithm performs skeleton extraction, skeleton grouping, indexing of structural features on a previously generated look-up table, structural verification of hypothesis using model graphs, and geometrical verification by an array of neural nets, each one specialized on the geometry of each model. The system retrieves 98 % of substructures with 91% precision rate.


  1. 1.
    N. Babaguchi et al. Identification and extraction of radicals from handprinted Kanji by segment correspondence method. Trans. IECE Japan, PRL, 83(59), 1983.Google Scholar
  2. 2.
    G. Boccignone et al. Recovering dynamic information from static handwriting. Pattern Recognition, 26(3):409–418, 1993.Google Scholar
  3. 3.
    A. Califano and R. Mohan. Multidimensional indexing for recognizing visual shapes. IEEE Trans. PAMI, 6(4):373–392, 1994.Google Scholar
  4. 4.
    R. Cheng, C. Lee, and Z. Chen. Preclassification of handwritten chinese characters based on basic stroke substructures. In The 4th International Workshop on Frontiers in Handwriting Recognition, pages 176–184, Taiwan, RoC, 1994.Google Scholar
  5. 5.
    S. Chou and W. Tsai. Recognizing handwritten chinese characters by stroke-segment matching using an iteration scheme. In P. Wang, editor, Character and Handwriting Recognition, volume 30, pages 175–198. World Scientific Series in Computer Science, 1991.Google Scholar
  6. 6.
    S. Dickinson, A. Pentland, and A. Rosenfeld. From volumes to views: An approach to 3-d object recognition. CVGIP: Image Understanding, 55(2):130–154, 1992.Google Scholar
  7. 7.
    H. Fujisawa and K. Marukawa. Full-text search and document recognition of japanese text. In 4th International Symposium on Document Analysis and Information Retrieval, Las Vegas, Nevada, April 1995.Google Scholar
  8. 8.
    F. Harary. Graph Theory. Addison-Wesley, 1972.Google Scholar
  9. 9.
    X. Huang, J. Gu, and Y. Wu. A constrained approach to multifont chinese character recognition. IEEE trans. on PAMI, 15(8):838–843, 1993.Google Scholar
  10. 10.
    G. Lorette and Y. Lecourtier. Is recognition and interpretation of handwritten texts a scene analysis problem? In Proc. of 3d Intern. Workshop on Frontiers in Handwiting Recognition, pages 184–196, Buffalo, New York, May 1993.Google Scholar
  11. 11.
    S. Lu, Y. Ren, and C. Suen. Hierarchical attributed graph representation and recognition of handwritten chinese characters. Pattern Recognition, 24(7):617–632, 1991.Google Scholar
  12. 12.
    S. Mori, C. Suen, and K. Yamamoto. Historical review of OCR reseach and development. In IEEE Proceedings, volume 80, pages 1029–1058, July 1992.Google Scholar
  13. 13.
    J. Rocha and T. Pavlidis. A shape analysis model with applications to a character recognition system. IEEE trans. on PAMI, 16(4):393–404, Apr 1994.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Jairo Rocha
    • 1
  • Hiromichi Fujisawa
    • 1
  1. 1.Central Research LaboratoryHitachi, Ltd.TokyoJapan

Personalised recommendations