Learning confidence transformation for handwritten Chinese text recognition

  • Da-Han Wang
  • Cheng-Lin LiuEmail author
Original Paper


Handwritten text recognition systems commonly combine character classification confidence scores and context models for evaluating candidate segmentation-recognition paths, and the classification confidence is usually optimized at character level. In this paper, we investigate into different confidence-learning methods for handwritten Chinese text recognition and propose a string-level confidence-learning method, which estimates confidence parameters by directly optimizing the performance of character string recognition. We first compare the performances of parametric (class-dependent and class-independent parameters) and nonparametric (isotonic regression) confidence-learning methods. Then, we propose two regularized confidence estimation methods and particularly, a string-level confidence-learning method under the minimum classification error criterion. In experiments of online handwritten Chinese text recognition, the string-level confidence-learning method is shown to effectively improve the string recognition performance. Using three character classifiers, the character correct rates are improved from 92.39, 90.24 and 88.69 % to 92.76, 90.91 and 89.93 %, respectively.


Handwritten text recognition Confidence learning Parametric and nonparametric Class-dependent and class-independent String-level learning 



This work was supported by the National Natural Science Foundation of China (NSFC) Grant 60933010. The authors would like to thank Xu-Yao Zhang for helpful discussions. The work of Da-Han Wang was partly accomplished at the Institute of Automation of Chinese Academy of Sciences.


  1. 1.
    Liu, C.-L., Jaeger, S., Nakagawa, M.: Online handwritten Chinese character recognition: the state of the art. IEEE Trans. Pattern Anal. Mach. Intell. 26(2), 198–213 (2004)CrossRefGoogle Scholar
  2. 2.
    Cheriet, M., Kharma, N., Liu, C.-L., Suen, C.Y.: Character Recognition Systems: A Guide for Students and Practitioners. Wiley, New Jersey (2007)CrossRefGoogle Scholar
  3. 3.
    Liu, C.-L.: Classifier combination based on confidence transformation. Pattern Recognit. 38(1), 11–28 (2005)CrossRefzbMATHGoogle Scholar
  4. 4.
    Li, Y.X., Tan, C.L., Ding, X.: A hybrid post-processing system for offline handwritten Chinese script recognition. Pattern Anal. Appl. 8, 272–286 (2005)CrossRefMathSciNetGoogle Scholar
  5. 5.
    Jiang, Y., Ding, X., Fu, Q., Ren, Z.: Context driven Chinese string segmentation and recognition. Struct. Struct. Syntactic Stat. Pattern Recognit. 4109, 127–135 (2006)CrossRefGoogle Scholar
  6. 6.
    Wang, Q.-F., Yin, F., Liu, C.-L.: Improving handwritten Chinese text recognition by confidence transformation. In: Proceedings of the 11th ICDAR, pp. 518–522 (2011)Google Scholar
  7. 7.
    Lin, X., Ding, X., Chen, M., Zhang, R., Wu, Y.: Adaptive confidence transform based on classifier combination for Chinese character recognition. Pattern Recognit. Lett. 19(10), 975–988 (1998)CrossRefGoogle Scholar
  8. 8.
    Gillick, L., Ito, Y., Young, J.: A probabilistic approach to confidence estimation and evaluation. In: Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, Munich, Germany, pp. 879–882 (1997)Google Scholar
  9. 9.
    Platt, J.: Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In: Smola, A.J., Bartlett, P., Schölkpf, D., Schuurmanns, D. (eds.) Advances in Large Margin Classifiers, pp. 61–74. MIT Press, Cambridge, MA (1999)Google Scholar
  10. 10.
    Schürmann, J.: Pattern Classification: A Unified View of Statistical and Neural Approaches. Wiley, New York (1996)Google Scholar
  11. 11.
    Barnett, J.A.: Computational methods for a mathematical theory of evidence. In: Proceedings of the 7th IJCAI, pp. 868–875 (1981)Google Scholar
  12. 12.
    Liu, C.-L., Sako, H., Fujisawa, H.: Effects of classifier structures and training regimes on integrated segmentation and recognition of handwritten numeral strings. IEEE Trans. Pattern Anal. Mach. Intell. 26(11), 1395–1407 (2004)CrossRefGoogle Scholar
  13. 13.
    Zadrozny, B., Elkan, C.: Learning and making decisions when costs and probabilities are both unknown. In: Proceedings of the 7th ACM SIGKDD, pp. 204–213 (2001)Google Scholar
  14. 14.
    Robertson, T., Wright, F., Dykstra, R.: Order restricted statistical inference, chap. 1. Wiley, New York (1988)Google Scholar
  15. 15.
    Zadrozny, B., Elkan, C.: Transforming classifier scores into accurate multiclass probability estimates. In: Proceedings of the 8th SIGKDD (2002)Google Scholar
  16. 16.
    Ayer, M., Brunk, H., Ewing, G., Reid, W., Silverman, E.: An empirical distribution function for sampling with incomplete information. Ann. Math. Stat. 26(4), 641–647 (1955)CrossRefzbMATHMathSciNetGoogle Scholar
  17. 17.
    Juang, B.-H., Chou, W., Lee, C.-H.: Minimum classification error rate methods for speech recognition. IEEE Trans. Speech Audio Process. 5(3), 257–265 (1997)CrossRefGoogle Scholar
  18. 18.
    Liu, C.-L., Yin, F., Wang, D.-H., Wang, Q.-F.: CASIA online and offline Chinese handwriting databases. In: Proceedings of the 11th ICDAR, pp. 37–41 (2011) Google Scholar
  19. 19.
    Wang, D.-H., Liu, C.-L.: String-level learning of confidence transformation for Chinese handwritten text recognition. In: Proceedings of the 21th ICPR, pp. 3208–3211 (2012)Google Scholar
  20. 20.
    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)CrossRefGoogle Scholar
  21. 21.
    Chen, M.-Y., Kundu, A., Srihari, S.N.: Variable duration hidden Markov model and morphological segmentation for handwritten word recognition. IEEE Trans. Image Process. 4(12), 1675–1688 (1995)CrossRefGoogle Scholar
  22. 22.
    Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat. 22, 400–407 (1951)CrossRefzbMATHMathSciNetGoogle Scholar
  23. 23.
    Chou, W.: Discriminant-function-based minimum recognition error pattern-recognition approach to speech recognition. Proc. IEEE 88(8), 1201–1223 (2000)CrossRefGoogle Scholar
  24. 24.
    Chen, W.-T., Gader, P.: Word level discriminative training for handwritten word recognition. In: Proceedings of the 7th IWFHR, Amsterdam, pp. 393–402 (2000)Google Scholar
  25. 25.
    Liu, C.-L., Marukawa, K.: Handwritten numeral string recognition: character-level training versus string-level training. In: Proceedings of the 17th ICPR, Cambridge, UK, pp. 405–408 (2004)Google Scholar
  26. 26.
    Biem, A.: Minimum classification error training for online handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. 28(7), 1041–1051 (2006)CrossRefGoogle Scholar
  27. 27.
    Wang, D.-H., Liu, C.-L., Zhou, X.-D.: An approach for real-time recognition of online Chinese handwritten sentences. Pattern Recognit. 45(10), 3661–3675 (2012)CrossRefGoogle Scholar
  28. 28.
    Liu, C.-L., Fujisawa, H.: Classification and learning in character recognition: advances and remaining problems. In: Marinai, S., Fujisawa, H. (eds.) Machine Learning in Document Analysis and Recognition, pp. 139–161. Springer, Berlin (2008)CrossRefGoogle Scholar
  29. 29.
    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)CrossRefGoogle Scholar
  30. 30.
    Jin, X.-B., Liu, C.-L., Hou, X.: Regularized margin-based conditional log-likelihood loss for prototype learning. Pattern Recognit. 43(7), 2428–2438 (2010)CrossRefzbMATHGoogle Scholar
  31. 31.
    Liu, C.-L.: One-vs-all training of prototype classifier for pattern classification and retrieval. In: Proceedings of the 20th ICPR, pp. 3328–3331 (2010)Google Scholar
  32. 32.
    Liu, C.-L., Zhou, X.-D.: Online Japanese character recognition using trajectory-based normalization and direction feature extraction. In: Proceedings of the 10th IWFHR, pp. 217–222 (2006)Google Scholar
  33. 33.
    Yin, F., Wang, Q.-F., Liu, C.-L.: Integrating geometric context for text alignment of handwritten Chinese documents. In: Proceedings of the 12th ICFHR, pp. 7–12 (2010)Google Scholar
  34. 34.
    Rabiner, L.R.: A tutorial on hidden Markov models and selective applications in speech recognition. Proc. IEEE 77, 257–286 (1989)CrossRefGoogle Scholar
  35. 35.
    Su, T.-H., Zhang, T.-W., Guan, D.-J., Huang, H.-J.: Off-line recognition of realistic Chinese handwriting using segmentation-free strategy. Pattern Recognit. 42(1), 167–182 (2009)CrossRefzbMATHGoogle Scholar
  36. 36.
    Zhou, X.-D., Yu, J.-L., Liu, C.-L., Nagasaki, T., Marukawa, K.: Online handwritten Japanese character string recognition incorporating geometric context. In: Proceedings of the 9th ICDAR, Curitiba, Brazil, pp. 48–52 (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.Center for Pattern Analysis and Machine Intelligence, School of Information Science and EngineeringXiamen UniversityFujianChina
  2. 2.National Laboratory of Pattern Recognition, Institute of AutomationChinese Academy of SciencesBeijingChina

Personalised recommendations