Skip to main content
Log in

An over-segmentation method for single-touching Chinese handwriting with learning-based filtering

  • Original Paper
  • Published:
International Journal on Document Analysis and Recognition (IJDAR) Aims and scope Submit manuscript

Abstract

The segmentation of touching characters is still a challenging task, posing a bottleneck for offline Chinese handwriting recognition. In this paper, we propose an effective over-segmentation method with learning-based filtering using geometric features for single-touching Chinese handwriting. First, we detect candidate cuts by skeleton and contour analysis to guarantee a high recall rate of character separation. A filter is designed by supervised learning and used to prune implausible cuts to improve the precision. Since the segmentation rules and features are independent of the string length, the proposed method can deal with touching strings with more than two characters. The proposed method is evaluated on both the character segmentation task and the text line recognition task. The results on two large databases demonstrate the superiority of the proposed method in dealing with single-touching Chinese handwriting.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16

Similar content being viewed by others

References

  1. Casey, R.G., Lecolinet, E.: A survey of methods and strategies in character segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 18(7), 690–706 (1996)

    Article  Google Scholar 

  2. Liu, C.-L., Koga, M., Fujisawa, H.: Lexicon-driven segmentation and recognition of handwritten character strings for Japanese address reading. IEEE Trans. Pattern Anal. Mach. Intell. 24(11), 1425–1437 (2002)

    Article  Google Scholar 

  3. Wang, Q.-F., Yin, F., Liu, C.-L.: Handwritten Chinese text recognition by integrating multiple contexts. IEEE Trans. Pattern Anal. Mach. Intell. 34(8), 1469–1481 (2012)

    Article  Google Scholar 

  4. Ribas, F.C., Oliveira, L.S., Britto, A.S., Jr., Sabourin, R.: Handwitten digit segmentation: a comparative study. Int. J. Doc. Anal. Recognit. (published online) (2013)

  5. Alginahi, Y.M.: A survey on Arabic character segmentation. Int. J. Doc. Anal. Recognit. (published online) (2013)

  6. Lee, H., Verman, B.: Binary segmentation algorithm for English cursive handwriting recognition. Pattern Recognit. 45(4), 1306–1317 (2012)

    Article  Google Scholar 

  7. Ikeda, H., Ogawa, Y., Koga, M., Nishimura, H., Sako, H., Fujisawa, H.: A recognition method for touching Japanese handwritten characters. In: Proceedings of 5th International Conference on Document Analysis and Recognition, pp. 641–644 (1999)

  8. Han, Z., Liu, C.-P., Yin, X.-C.: A two-stage handwritten character segmentation approach in mail address recognition. In: Proceedings of 8th International Conference on Document Analysis and Recognition, pp. 111–115 (2005)

  9. Yu, M.L., Kwok, P.C.K., Leung, C.H., Tse, K.W.: Segmentation and recognition of Chinese bank check amounts. Int. J. Doc. Anal. Recognit. 3(4), 207–217 (2001)

    Article  Google Scholar 

  10. Tseng, L.Y., Chen, R.C.: Segmenting handwritten Chinese characters based on heuristic merging of stroke bounding boxes and dynamic programming. Pattern Recognit. Lett. 19(10), 963–973 (1998)

    Article  Google Scholar 

  11. Tseng, Y.-H., Lee, H.-J.: Recognition-based handwritten Chinese character segmentation using a probabilistic Viterbi algorithm. Pattern Recognit. Lett. 20(8), 791–806 (1999)

    Article  Google Scholar 

  12. Gao, J., Ding, X., Wu, Y.: A segmentation algorithm for handwritten Chinese character strings. In: Proceedings of 5th International Conference on Document Analysis and Recognition, pp. 633–636 (1999)

  13. Yamaguchi, T., Yoshikawa, T., Shinogi, T., Tsuruoka, S., Teramoto, M.: A segmentation method for touching Japanese handwritten characters based on connecting condition of line. In: Proceedings of 6th International Conference on Document Analysis and Recognition, pp. 837–841 (2001)

  14. Yamaguchi, T., Tsuruoka, S., Yoshikawa, T., Shinogi, T., Makimoto, E., Ogata, H., Shridhar, M.: A segmentation system for touching handwritten Japanese characters. In: Proceedings of 8th International Workshop on Frontiers in Handwriting Recognition, pp. 407–412 (2002)

  15. Suwa, M.: Segmentation of touching handwritten Japanese characters using the graph theory method. In: Proceedings of 8th International Conference on Document Recognition and Retrieval, pp. 280–289 (2001)

  16. Wang, R., Ding, X., Liu, C.: Handwritten Chinese address segmentation and recognition based on merging strokes. Qinghua Daxue Xuebao/J. Tsinghua Univ. 44(4), 498–502 (2004) (in Chinese)

    Google Scholar 

  17. Li, N.-X., Gao, X., Jin, L.-W.: Curved segmentation path generation for unconstrained handwritten Chinese text lines. In: Proceedings of the IEEE Asia Pacific Conference on Circuits and Systems, pp. 501–505 (2008)

  18. Bunke, H.: Recognition of cursive Roman handwriting-past, present and future. In: Proceedings of 7th International Conference on Document Analysis and Recognition, pp. 448–459 (2003)

  19. Bayer, T., Kressel, U.: Cut classification for segmentation. In: Proceedings of 2nd International Conference on Document Analysis and Recognition, pp. 565–568 (1993)

  20. Vellasques, E., Oliveira, L.S., Britto Jr, A.S., Koerich, A.L., Sabourin, R.: Filtering segmentation cuts for digit string recognition. Pattern Recognit. 41(10), 3044–3053 (2008)

    Article  MATH  Google Scholar 

  21. Zhao, S., Chi, Z., Shi, P., Yan, H.: Two-stage segmentation of unconstrained handwritten Chinese characters. Pattern Recognit. 36(1), 145–156 (2003)

    Article  MATH  Google Scholar 

  22. Suen, C.Y., Mori, S., Kim, S.-H., Leung, C.H.: Analysis and recognition of Asian scripts-the state of the art. In: Proceedings of 7th International Conference on Document Analysis and Recognition, pp. 866–878 (2003)

  23. Srihari, S., Yang, X., Ball, G.: Offline Chinese handwriting recognition: an assessment of current technology. Frontiers Comput. Sci. China 1(2), 137–155 (2007)

    Article  Google Scholar 

  24. Su, T., Zhang, T., Guan, D., Huang, H.: Off-line recognition of realistic Chinese handwriting using segmentation-free strategy. Pattern Recognit. 42(1), 167–182 (2009)

    Article  MATH  Google Scholar 

  25. Xu, L., Yin, F., Wang, Q.-F., Liu, C.-L.: A touching character database from Chinese handwriting for assessing segmentation algorithms. In: Proceedings of 12th International Conference on Frontiers in Handwriting Recognition, pp. 89–94 (2012)

  26. Liu, C.-L., Yin, F., Wang, D.-H., Wang, Q.-F.: CASIA online and offline Chinese handwriting databases. In: Proceedings of 11th International Conference on Document Analysis and Recognition, pp. 37–41 (2011)

  27. Xu, L., Yin, F., Wang, Q.-F., Liu, C.-L.: Touching character separation in Chinese handwriting using visibility-based foreground analysis. In: Proceedings of 11th International Conference on Document Analysis and Recognition, pp. 859–863 (2011)

  28. Liang, Z., Shi, P.: A metasynthetic approach for segmenting handwritten Chinese character strings. Pattern Recognit. Lett. 26(10), 1498–1511 (2005)

    Article  Google Scholar 

  29. Strathy, N.W., Suen, C.Y., Kryzyzak, A.: Segmentation of handwritten digits using contour features. In: Proceedings of 2nd International Conference on Document Analysis and Recognition, pp. 577–580 (1993)

  30. Ha, T.M., Zimmermann, M., Bunke, H.: Off-line handwritten numeral string recognition by combining segmentation-based and segmentation-free methods. Pattern Recognit. 31(3), 257–272 (1998)

    Article  Google Scholar 

  31. Chen, Y.-K., Wang, J.-F.: Segmentation of single- or multiple-touching handwritten numeral string using background and foreground analysis. IEEE Trans. Pattern Anal. Mach. Intell. 22(11), 1304–1317 (2000)

    Article  Google Scholar 

  32. Oliveira, L.S., Lethelier, E., Bortolozzi, F., Sabourin, R.: A new segmentation approach for handwritten digits. In: Proceedings of 15th International Conference on, Pattern Recognition, pp. 2323–2326 (2000)

  33. Sadri, J., Suen, C.Y., Bui, T.D.: Automatic segmentation of unconstrained handwritten numeral strings. In: Proceedings of 9th International Workshop on Frontiers in Handwriting Recognition, pp. 317–322 (2004)

  34. Suzuki, S., Abe, K.: Binary picture thinning by an iterative parallel two-subcycle operation. Pattern Recognit. 10(3), 297–307 (1987)

    Article  Google Scholar 

  35. Rosenfeld, A., Johnston, E.: Angle detection on digital curves. IEEE Trans. Comput. 22, 875–878 (1976)

    Google Scholar 

  36. Ramer, U.: An iterative procedure for the polygonal approximation of plane closed curves. Comput. Graph. Image Process 1, 244–256 (1972)

    Article  Google Scholar 

  37. Liu, C.-L., Kim, I.-J., Kim, J.H.: Model-based stroke extraction and matching for handwritten Chinese character recognition. Pattern Recognit. 34(12), 2339–2352 (2001)

    Article  MATH  Google Scholar 

  38. Yin, F., Wang, Q.-F., Liu, C.-L.: Integrating geometric context for text alignment of handwritten Chinese documents. In: Proceedings of 11th International Conference on Frontiers in Handwriting Recognition, pp. 7–12 (2010)

  39. Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, chap. 2. Wiley, New York (2001)

  40. Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, New York (1995)

  41. Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 1–27 (2011). Software available at http://www.csie.ntu.edu.tw/cjlin/libsvm

  42. Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. J. Mach. Learn. Res. 3, 1157–1182 (2003)

    MATH  Google Scholar 

  43. Kimura, F., Takashina, K., Tsuruoka, S., Miyake, Y.: Modified quadratic discriminant functions and the application to Chinese character recognition. IEEE Trans. Pattern Anal. Mach. Intell. 9(1), 149–153 (1987)

    Article  Google Scholar 

Download references

Acknowledgments

This work was supported by the National Natural Science Foundation of China (NSFC) grants 60933010 and 61175021. The authors thank Prof. Horst Bunke, Dr. TongHua Su, Yan-Wei Wang and Xu-Yao Zhang for helpful discussions.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Liang Xu.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Xu, L., Yin, F., Wang, QF. et al. An over-segmentation method for single-touching Chinese handwriting with learning-based filtering. IJDAR 17, 91–104 (2014). https://doi.org/10.1007/s10032-013-0208-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10032-013-0208-1

Keywords

Navigation