Advertisement

Frontiers of Computer Science in China

, Volume 1, Issue 2, pp 137–155 | Cite as

Offline Chinese handwriting recognition: an assessment of current technology

  • Sargur N. Srihari
  • Xuanshen Yang
  • Gregory R. Ball
Review Article

Abstract

Offline Chinese handwriting recognition (OCHR) is a typically difficult pattern recognition problem. Many authors have presented various approaches to recognizing its different aspects. We present a survey and an assessment of relevant papers appearing in recent publications of relevant conferences and journals, including those appearing in ICDAR, SDIUT, IWFHR, ICPR, PAMI, PR, PRL, SPIEDRR, and IJDAR. The methods are assessed in the sense that we document their technical approaches, strengths, and weaknesses, as well as the data sets on which they were reportedly tested and on which results were generated. We also identify a list of technology gaps with respect to Chinese handwriting recognition and identify technical approaches that show promise in these areas as well as identify the leading researchers for the applicable topics, discussing difficulties associated with any given approach.

Keywords

Chinese recognition OCR document analysis survey assessment line segmentation OCR architecture 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Shi D M, Damper R I, Gunn S R. Offline handwritten Chinese character recognition by radical decomposition. ACM Transactions on Asian Language Information Processing. 2003, 1: 27–48CrossRefGoogle Scholar
  2. 2.
    Kim I J, Kim J H. Statistical character structure modeling and its application to handwritten Chinese character recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2003, 25: 1422–1436CrossRefGoogle Scholar
  3. 3.
    Lu Y, Shridhar M. Character segmentation in handwritten words-An overview. Pattern Recognition. 1996, 29: 77–96CrossRefGoogle Scholar
  4. 4.
    Wei X H, Ma S P, Jin Y J. Segmentation of connected Chinese characters based on genetic algorithm. In: ICDAR’05: Proceedings of the Ninth International Conference on Document Analysis and Recognition, Seoul, Korea, Vol 1. IEEE Computer Society, 2005, 645–649Google Scholar
  5. 5.
    Liang Z Z, Shi P F. A metasynthetic approach for segmenting handwritten Chinese character strings. Pattern Recognition Letters. 2005, 26: 1498–1511CrossRefGoogle Scholar
  6. 6.
    Zhao S Y, Chi Z R, Shi P F, et al. Two-stage segmentation of unconstrained handwritten Chinese characters. Pattern Recognition, 2003, 36: 145–156zbMATHCrossRefGoogle Scholar
  7. 7.
    Zhao S Y, Chi Z R, Shi P F, et al. Handwritten Chinese character segmentation using a two-stage approach. In: Proceedings of the sixth International Conference on Document Analysis and Recognition (ICDAR’01),Seattle, WA, Vol 1. IEEE Computer Society, 2001, 179–183CrossRefGoogle Scholar
  8. 8.
    Tseng Y H, Lee H J. Recognition-based handwritten Chinese character segmentation using a probabilistic Viterbi algorithm. Pattern Recognition Letters. 1999, 20: 791–806CrossRefGoogle Scholar
  9. 9.
    Tseng L Y, Chen R C. Segmenting handwritten Chinese characters based on heuristic merging of stroke bounding boxes and dynamic programming. Pattern Recognition Letters. 1998, 19: 963–973CrossRefGoogle Scholar
  10. 10.
    Dong J X, Krzyzak A, Suen C Y. An improved handwritten Chinese character recognition system using support vector machine. Pattern Recognition Letters. 2005, 26: 1849–1856CrossRefGoogle Scholar
  11. 11.
    Liu C L, Marukawa K M. Pseudo two-dimensional shape normalization methods for handwritten Chinese character recognition. Pattern Recognition. 2005, 38: 2242–2255CrossRefGoogle Scholar
  12. 12.
    Tseng Y H, Lee H J. Interfered-character recognition by removing interfering-lines and adjusting feature weights. In: Proceedings of Fourteenth International Conference on Pattern Recognition. 1998, Vol 2. 1865–1867CrossRefGoogle Scholar
  13. 13.
    Chiu H P, Tseng D C. A feature-preserved thinning algorithm for handwritten Chinese characters. In: Proceedings of 13th International Conference on Pattern Recognition, 1996, Vol 3. 235–239CrossRefGoogle Scholar
  14. 14.
    Gao J, Ding X q, Wu Y S. A segmentation algorithm for handwritten Chinese character strings. In: Proceedings of the Fifth International Conference on Document Analysis and Recognition(ICDAR’99), India, Vol 1. IEEE Computer Society. 1999, 633–636Google Scholar
  15. 15.
    Wang Q, Chi Z R, Feng D D, et al. Match between normalization schemes and feature sets for handwritten Chinese character recognition. In: Proceedings of the Sixth International Conference on Document Analysis and Recognition(ICDAR’01), Seattle, Vol 1. IEEE Computer Society, 2001, 551–555CrossRefGoogle Scholar
  16. 16.
    Liu C L, Sako H, Fujisawa H. Handwritten Chinese character recognition: alternatives to nonlinear normalization. In: Proceedings of the Seventh International Conference on Document Analysis and Recognition(ICDAR’03), Scotland, Vol 1. IEEE Computer Society, 2003, 524–528CrossRefGoogle Scholar
  17. 17.
    Liu C L, Marukawa K. Global shape normalization for handwritten Chinese character recognition: a new method. In: Ninth International Workshop on Frontiers in Handwriting Recognition, Tokyo, Japan, Vol 1. 2004, 300–305CrossRefGoogle Scholar
  18. 18.
    Liu C L. Handwriting Chinese character recognition: Effects of shape normalization and feature extraction. In: Summit on Arabic and Chinese Handwriting, College Park, USA. 2006, 13Google Scholar
  19. 19.
    Shi D, Gunn S R, Damper R I. Handwritten Chinese radical recognition using nonlinear active shape models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25: 277–280CrossRefGoogle Scholar
  20. 20.
    Shi D M, Gunn S R, Damper R I. Handwritten Chinese character recognition using nonlinear active shape models and the Viterbi algorithm. Pattern Recognition Letters, 2002, 23: 1853–1862zbMATHCrossRefGoogle Scholar
  21. 21.
    Ng G S, Shi D, Gunn S R, et al. Nonlinear active handwriting models and their applications to handwritten Chinese radical recognition. In: ICDAR’03: Proceedings of the Seventh International Conference on Document Analysis and Recognition, Edinburgh, Scotland, Vol 1. IEEE Computer Society, 2003, 534–538CrossRefGoogle Scholar
  22. 22.
    Shi D, Gunn S R, Damper R I. A radical approach to handwritten Chinese character recognition using active handwriting models. In: Proceedings of 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol 1. 2001, 670Google Scholar
  23. 23.
    Shi D, Gunn S R, Damper R I. Active radical modelling for handwritten Chinese characters. In: ICDAR’01: Proceedings of the sixth International Conference on Document Analysis and Recognition, Seattle, WA, Vol 1. IEEE Computer Society, 2001, 236–240CrossRefGoogle Scholar
  24. 24.
    Wang A B, Fan K C, Wu W H. A recursive hierarchical scheme for radical extraction of handwritten Chinese characters. In: Proceedings of 13th International Conference on Pattern Recognition, Vol 3. 1996, 240–244CrossRefGoogle Scholar
  25. 25.
    Lin F, Tang X O. Off-line handwritten Chinese character stroke extraction. In: Proceedings of 16th International Conference on Pattern Recognition, Vol 3. 2002, 249–252Google Scholar
  26. 26.
    Su Y M, Wang J F. Decomposing Chinese characters into stroke segments using SOGD filters and orientation normalization. In: Proceedings of the 17th International Conference on Pattern Recognition, Vol 2. 2004, 351–354CrossRefGoogle Scholar
  27. 27.
    Su Y M, Wang J F. A novel stroke extraction method for Chinese characters using Gabor filters. Pattern Recognition, 2003, 36: 635–647CrossRefGoogle Scholar
  28. 28.
    Cao R N, Tan C L. A model of stroke extraction from Chinese character images. In: Proceedings of 15th International Conference on Pattern Recognition, Vol 4. 2000, 368–371Google Scholar
  29. 29.
    Fan K C, Wu W H. A run-length coding based approach to stroke extraction of Chinese characters. In: Proceedings of 15th International Conference on Pattern Recognition, Vol 2. 2000, 565–568Google Scholar
  30. 30.
    Chiu H P, Tseng D C. A novel stroke-based feature extraction for handwritten Chinese character recognition. Pattern Recognition, 1999, 32: 1947–1959CrossRefGoogle Scholar
  31. 31.
    Kim J W, Kim K I, Choi B J, et al. Decomposition of Chinese character into strokes using mathematical morphology. Pattern Recognition Letters, 1999, 20: 285–292zbMATHCrossRefGoogle Scholar
  32. 32.
    Zeng J, Liu Z Q. Markov random fields for handwritten Chinese character recognition. In: ICDAR’05: Proceedings of the Ninth International Conference on Document Analysis and Recognition, Korea, Vol 1. IEEE Computer Society, 2005, 101–105Google Scholar
  33. 33.
    Wang Q, Chi Z r, Feng D D, et al. Hidden Markov random field based approach for off-line handwritten Chinese character recognition. In: Proceedings of 15th International Conference on Pattern Recognition, Vol 2. 2000, 347–350Google Scholar
  34. 34.
    Chen Z, Lee Ch W, Cheng R H. Handwritten Chinese character analysis and preclassification using stroke structural sequence. In: Proceedings of 13th International Conference on Pattern Recognition, Vol 3. 1996, 89–93CrossRefGoogle Scholar
  35. 35.
    Kim I J, Liu C L, Kim J H. Stroke-guided pixel matching for handwritten Chinese character recognition. In: ICDAR’99: Proceedings of the Fifth International Conference on Document Analysis and Recognition,India, Vol 1. IEEE Computer Society, 1999, 665–668Google Scholar
  36. 36.
    Liu C L, Kim I J, Kim J H. Model-based stroke extraction and matching for handwritten Chinese character recognition. Pattern Recognition, 2001, 34: 2339–2352zbMATHCrossRefGoogle Scholar
  37. 37.
    Ge Y, Huo Q. A comparative study of several modeling approaches for large vocabulary offline recognition of handwritten Chinese characters. In:Proceedings of 16th International Conference on Pattern Recognition, Vol 3. 2002, 85–88Google Scholar
  38. 38.
    Ge Y, Huo Q. A study on the use of CDHMM for large vocabulary off-line recognition of handwritten Chinese characters. In: Proceedings of Eighth International Workshop on Frontiers in Handwriting Recognition, Canada, Vol 1. 2002, 334–338Google Scholar
  39. 39.
    Ge Y, Huo Q, Feng Z D. Offline recognition of handwritten Chinese characters using Gabor features, CDHMM modeling and MCE training. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol 1. 2002, I-1053–I-1056Google Scholar
  40. 40.
    Kato N, Suzuki M, Omachi S, et al. A handwritten character recognition system using directional element feature and asymmetric Mahalanobis distance. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999, 21: 258–262CrossRefGoogle Scholar
  41. 41.
    Liu H L, Ding X Q. Handwritten character recognition using gradient feature and quadratic classifier with multiple discrimination schemes. In: Proceedings of the Ninth International Conference on Document Analysis and Recognition, Korea, Vol 1. IEEE Computer Society, 2005, 19–23Google Scholar
  42. 42.
    Feng B, Ding X Q, Wu Y S. Chinese handwriting recognition using hidden Markov models. In: Proceedings of 16th International Conference on Pattern Recognition, Vol 3. 2002, 212–215Google Scholar
  43. 43.
    Zhang R, Ding X Q. Minimum classification error training for handwritten character recognition. In: Proceedings of 16th International Conference on Pattern Recognition, Vol 1. 2002, 580–583Google Scholar
  44. 44.
    Wu M R, Zhang B, Zhang L. A neural network based classifier for handwritten Chinese character recognition. In: Proceedings of 15th International Conference on Pattern Recognition, Vol 2.2000, 561–564Google Scholar
  45. 45.
    Wang C H, Xiao B H, Dai R W. A new integration scheme with multilayer perceptron networks for handwritten Chinese character recognition. In: Proceedings of 15th International Conference on Pattern Recognition, Vol 2. 2000, 961–964Google Scholar
  46. 46.
    Tsang C K Y, Chung F L. Development of a structural deformable model for handwriting recognition. In: Proceedings of Fourteenth International Conference on Pattern Recognition, Vol 2. 1998, 1130–1133CrossRefGoogle Scholar
  47. 47.
    Tsang C K Y, Chung F L. A structural deformable model with application to post-recognition of handwriting. In: Proceedings of 15th International Conference on Pattern Recognition, Vol 2. 2000, 129–132Google Scholar
  48. 48.
    Xiao B H, Wang C H, Dai R W. Adaptive combination of classifiers and its application to handwritten Chinese character recognition. In: Proceedings of 15th International Conference on Pattern Recognition, Vol 2. 2000, 327–330Google Scholar
  49. 49.
    Zhang J Y, Ding X Q, Liu C S. Multi-scale feature extraction and nested-subset classifier design for high accuracy handwritten character recognition. In: Proceedings of 15th International Conference on Pattern Recognition, Vol 2. 2000, 581–584Google Scholar
  50. 50.
    Shioyama T, Wu H Y, Nojima T. Recognition algorithm based on wavelet transform for handprinted Chinese characters. In: Proceedings of Fourteenth International Conference on Pattern Recognition, Vol 1. 1998, 229–232CrossRefGoogle Scholar
  51. 51.
    Tseng D C, Chiu H P. Fuzzy ring data for invariant handwritten Chinese character recognition. In: Proceedings of 13th International Conference on Pattern Recognition, Vol 3. 1996, 94–98CrossRefGoogle Scholar
  52. 52.
    Shioyama T, Hamanaka J. Recognition algorithm for handprinted Chinese characters by 2D-FFT. In: Proceedings of 13th International Conference on Pattern Recognition, Vol 3. 1996, 225–229CrossRefGoogle Scholar
  53. 53.
    Mizukami Y. A handwritten Chinese character recognition system using hierarchical displacement extraction based on directional features. Pattern Recognition Letters, 1998, 19: 595–604zbMATHCrossRefGoogle Scholar
  54. 54.
    Guo F J, Zhen L X, Ge Y, et al. An efficient candidate set size reduction method for coarse-classifier of Chinese handwriting recognition. In: Summit on Arabic and Chinese Handwriting, College Park, USA. 2006, 41–46Google Scholar
  55. 55.
    Fu C. Techniques for solving the large-scale classification problem in Chinese handwriting recognition. In: Summit on Arabic and Chinese Handwriting, College Park, USA. 2006, 87–92Google Scholar
  56. 56.
    Xiong Y, Huo Q, Chan C K. A discrete contextual stochastic model for the off-line recognition of handwritten Chinese characters. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23: 774–782CrossRefGoogle Scholar
  57. 57.
    Wang C H, Hotta Y, Suwa M, et al. Handwritten Chinese address recognition. In: Proceedings of Ninth International Workshop on Frontiers in Handwriting Recognition, Tokyo, Japan, Vol 1. 2004, 539–544CrossRefGoogle Scholar
  58. 58.
    Han Z, Liu C P, Yin X C. A two-stage handwritten character segmentation approach in mail address recognition. In: Proceedings of the Ninth International Conference on Document Analysis and Recognition, Korea, Vol 1. IEEE Computer Society, 2005, 111–115Google Scholar
  59. 59.
    Fu Q, Ding X Q, Liu C S, et al. A hidden Markov model based segmentation and recognition algorithm for Chinese handwritten address character strings. In: Proceedings of the Ninth International Conference on Document Analysis and Recognition, Seoul, Korea, Vol 2. IEEE Computer Society, 2005, 590–594Google Scholar
  60. 60.
    Tang H S, Augustin E, Suen C Y, et al. Spiral recognition methodology and its application for recognition of Chinese bank checks. In: Proceedings of Ninth International Workshop on Frontiers in Handwriting Recognition, 2004, Tokyo, Japan, Vol 1. 2004, 263–268CrossRefGoogle Scholar
  61. 61.
    Lin X f, Ding X q, Chen M, et al. Adaptive confidence transform based classifier combination for Chinese character recognition. Pattern Recognition Letters, 1998, 19: 975–988CrossRefGoogle Scholar
  62. 62.
    Hung K Y, Luk R W P, Yeung D S, et al. A multiple classifier approach to detect Chinese character recognition errors. Pattern Recognition, 2005, 38: 723–738CrossRefGoogle Scholar
  63. 63.
    Wu T L, Ma S P. Feature extraction by hierarchical overlapped elastic meshing for handwritten Chinese character recognition. In: Proceedings of the Seventh International Conference on Document Analysis and Recognition, Edinburgh, Scotland, Vol 1. IEEE Computer Society, 2003, 529–533CrossRefGoogle Scholar
  64. 64.
    Ding X Q, Liu H L. Segmentation-driven offline handwritten Chinese and Arabic script recognition. In: Summit on Arabic and Chinese Handwriting, 2006, College Park, USA. 2006, 61–73Google Scholar
  65. 65.
    Huang L, Huang X. Multiresolution recognition of offline handwritten Chinese characters with wavelet transform. In: Proceedings of the sixth International Conference on Document Analysis and Recognition, Seattle, WA, Vol 1. IEEE Computer Society, 2001, 631–634CrossRefGoogle Scholar
  66. 66.
    Wang A B, Fan K C. Optical recognition of handwritten Chinese characters by hierarchical radical matching method. Pattern Recognition, 2001, 34: 15–35Google Scholar
  67. 67.
    Li Y X, Tan C L. An empirical study of statistical language models for contextual post-processing of Chinese script recognition. In: Proceedings of Ninth International Workshop on Frontiers in Handwriting Recognition, Tokyo, Japan, Vol 1. 2004, 257–262MathSciNetGoogle Scholar
  68. 68.
    Li Yuan-Xiang, Tan Chew Lim. Influence of language models and candidate set size on contextual post-processing for Chinese script recognition. In: Proceedings of the 17th International Conference on Pattern Recognition, 2004, Vol 2. 2004, 537–540CrossRefGoogle Scholar
  69. 69.
    Natarajan P, Saleem S, Prasad R, et al. Multi-lingual offline handwriting recognition using Markov models. In: Summit on Arabic and Chinese Handwriting, 2006, College Park, USA. 2006, 177–187Google Scholar

Copyright information

© Higher Education Press and Springer-Verlag 2007

Authors and Affiliations

  • Sargur N. Srihari
    • 1
  • Xuanshen Yang
    • 1
  • Gregory R. Ball
    • 1
  1. 1.Center of Excellence for Document Analysis and Recognition (CEDAR), Department of Computer Science and Engineering, University at BuffaloState University of New YorkAmherstUSA

Personalised recommendations