Advertisement

Abstract

This paper presents a context driven segmentation and recognition method for handwritten Chinese characters. We follow a split-merge technique in character segmentation. In this process, a Chinese text line is first pre-segmented into a sequence of radicals, which are then merged according to a cost function combining both recognition confidence and contextual cost. Two strategies are also proposed for implementation: bi-gram based merging and lexicon driven merging. In the former one, we generate a set of merging paths which are then evaluated by Viterbi algorithm. The radicals’ best merging method is given by the path with the highest score. In the latter strategy, a lexicon is preset and compared with the radicals to determine both radicals’ merging and candidate character selection. Experiments show that contextual information plays a crucial role in Chinese character segmentation and could obviously improve the segmentation and recognition results.

Keywords

Chinese Character Text Line Viterbi Algorithm Segmentation Rate Character Segmentation 
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.

References

  1. 1.
    Casey, R.G., Lecolinet, E.: A Survey of Methods and Strategies in Character Segmentation. IEEE Trans. PAMI 18(7), 690–706 (1996)Google Scholar
  2. 2.
    Jimenez, V.M., Marzal, A.: Computing the K shortest paths: A new algorithm and an experimental comparison. In: Vitter, J.S., Zaroliagis, C.D. (eds.) WAE 1999. LNCS, vol. 1668, pp. 15–29. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  3. 3.
    Liu, C., Koga, M., Fujisawa, H.: Lexicon-driven Segmentation and Recognition of Handwritten Character Strings for Japanese Address Reading. IEEE Trans. PAMI 24(11), 1425–1437 (2002)Google Scholar
  4. 4.
    Liu, C., Nakagawa, M.: Precise Candidate Selection for Large Character Set Recognition by Confidence Evaluation. IEEE Trans. PAMI 22(6), 636–642 (2000)Google Scholar
  5. 5.
    Messelodi, S., Modena, C.M.: Context Driven Text Segmentation and Recognition. Pattern Recognition Letters 17(1), 47–56 (1996)CrossRefGoogle Scholar
  6. 6.
    Xue, J., Ding, X., et al.: Location and Interpretation of Destination Addresses on Handwritten Chinese Envelopes. Pattern Recognition Letters 22(6), 639–656 (2001)MATHCrossRefGoogle Scholar
  7. 7.
    Fukushima, T., Nakagawa, M.: On-line Writing-box-free Recognition of Handwritten Japanese Text Considering Character Size Variations. In: Proc. 15th ICPR, pp. 359–363Google Scholar
  8. 8.
    Lin, X.: Theory and Application of Confidence Analysis and Multiple Classifier Combination in Character Recognition. Ph.d. dissertation, Tsinghua University (1998)Google Scholar
  9. 9.
    Li, Y.: The Research on Chinese Character Recognition Using Contextual Information. Ph.d. dissertation, Tsinghua University (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Yan Jiang
    • 1
  • Xiaoqing Ding
    • 1
  • Qiang Fu
    • 1
  • Zheng Ren
    • 2
  1. 1.Department of Electronic EngineeringTsinghua UniversityBeijingChina
  2. 2.Siemens AGKonstanzGermany

Personalised recommendations