International Journal of Contents

The Korea Contents Association (한국콘텐츠학회)
권호 표지
DOI QR코드

DOI QR Code

Character Segmentation in Chinese Handwritten Text Based on Gap and Character Construction Estimation

  • Zhang, Cheng Dong (Department of Electronics and Computer Engineering Chonnam National University) ;
  • Lee, Guee-Sang (Department of Electronics and Computer Engineering Chonnam National University)
  • Received : 2011.08.29
  • Accepted : 2012.01.09
  • Published : 2012.03.28
Download PDF
⟨ Previous Next ⟩

Abstract

Character segmentation is a preprocessing step in many offline handwriting recognition systems. In this paper, Chinese characters are categorized into seven different structures. In each structure, the character size with the range of variations is estimated considering typical handwritten samples. The component removal and merge criteria are presented to remove punctuation symbols or to merge small components which are part of a character. Finally, the criteria for segmenting the adjacent characters concerning each other or overlapped are proposed.

Keywords

References

  1. Y. Lu. "Machine printed character segmentation: an overview," PR journal, vol.28, 1995, pp. 67-80.
  2. Y. Lu and M. Shridhar. "Character segmentation in handwritten characters: an overview," PR journal, vol.29, Sep, 1996, pp. 77-96.
  3. L.Y. Tseng, R. C. Chen. "Segmenting handwritten Chinese characters based on heuristic merging of stroke bounding boxes and dynamic programming," PRL journal, vol.19, Oct, 1998, pp. 963-973.
  4. Q.S Chen, L.X Zhen. "Character segmentation in handwritten Chinese text image based on component clustering techniques," Proc . TENCON '02, pp. 435-440.
  5. Y. Jiang, X. Ding, Z. Ren. "Substring Alignment Method for Lexicon-Based Handwritten Chinese String Recognition and its Application to Address Line Recognition," Proc. ICPR' 06, 2006, pp. 683-686.
  6. C. Hong, G. Loudon, Y. Wu, et al. "Segmentation and Recognition of Continuous Handwritten Chinese Text," PRAI journal, vol.12, Feb.1998, pp. 223-232.
  7. Y.H Tseng, H.J Lee. "Recognition-Based Handwritten Chinese Character Segmentation Using a Probabilistic Viterbi Algorithm," PRL journal, vol.20, Aug.1999, pp. 791-806.
  8. J. Gao, X. Ding, Y. Wu. "A Segmentation Algorithm for Handwritten Chinese Character Strings," Proc. ICDAR 09, 1999, pp.633-636.
  9. S.Y Zhao, Z.R Chi, P.F Shi, et al. "Two-stage Segmentation of Unconstrained Handwritten Chinese Characters," PR journal vol.36, Jan, 2003, pp.145-156.
  10. N. Ezaki, M. Bulacu, and L. Schomaker, "Text detection from natural scene images: towards a system for visually impaired persons," Proc. ICPR'04, 2004, pp.683-686
  11. R.G Lasey and E. Lecolinet, "A survey of methods and strategies in character segmentation," Tran. PAMI'06, vol.18, no.7, 1996, pp.690-706.
  12. G. Seni and E. Cohen, "External word segmentation of off-line handwritten text lines," PR journal, vol.27, 1994, pp. 41-52.
  13. C.C Chiang and S.S Yu, "An iterative character segmentation method for irregularly formatted Chinese documents," Proc. OCRDA'96, 1996, pp.61-67.
  14. H.H Kuo and J.F Wang, "A new method for the segmentation of mixed hand printed Chinese/English characters," Proc.ICDAR'93, 1993, pp. 810-813.
  15. L.Y. Tseng, R. C. Chen. "Segmenting handwritten Chinese characters based on heuristic merging of stroke bounding boxes and dynamic programming," PRL journal, vol.19, Oct, 1998, pp. 963-973.
  16. Q.S Chen, L.X Zhen. "Character segmentation in handwritten Chinese text image based on component clustering techniques," Proc . TENCON '02, pp. 435-440.
  17. T.H Su, T.W Zhang, et al. "Corpus-based HIT-MW database for offline recognition of general-purpose Chinese handwritten text," DAR journal, vol.10, no.1, Oct, 2007, pp. 27-38.
  18. T.H Su, T.W Zhang and D.J Guan. "HIT-MW dataset for Offline Chinese Handwritten Text Recognition," Proc. ICFHR'06, 2006.