Adaptive Visualization of Segmented Digital Ink Texts in Chinese based on Context

Xi-Wen Zhang, Hao Bai, Yong-Gang Fu

2012

Abstract

Digital ink texts in Chinese can neither be converted into users’ desired layouts nor be recognized until they are segmented correctly. There are many errors in automatically segmented results because the texts are free forms and mixed with other languages, as well as their Chinese characters have small gaps and complex structures. Paragraphs, text lines, and characters (recognizable language symbols) may be wrongly extracted. It is a prerequisite to visualize segmented results for further correcting wrong extracted objects using human-computer interaction. Thus, an adaptive approach based on context is proposed to visualize segmented digital ink texts in Chinese. Each extracted object is adaptively visualized by shape and colour labels according to relations between it and its neighbours. Confidences of extracted objects are also visualized with bounding shapes with different line widths. Each object’s contexts are constructed from it and other objects invoked by it, where an optimum visualization is identified. We have conducted experiments using real-life segmented digital ink texts in Chinese and compared the proposed approach with others. Experimental results demonstrate that the proposed approach is feasible, flexible, and effective.

References

  1. Anquetil, Eric, Lorette, Guy, 2006. New advances and new challenges in online handwriting recognition & electronic ink management, B. B. Chaudhuri (ed.), Digital Document Processing: Major Directions and Recent Advances (Advances in Pattern Recognition). Springer Verlag, German, pp: 143-164.
  2. Ao, Xiang, Li, Junfeng, Wang, XuGang, Dai, Guozhong, 2006. Structuralizing digital ink for efficient selection, Proceedings of the 11th International Conference on Intelligent User Interfaces. January 29- February 1, Sydney, Australia, pp: 148-154.
  3. Basu, S., Chaudhuri, C., Kundu, M., Nasipuri, Basu, M., D.K., 2007. Text line extraction from multi-skewed handwritten documents, Pattern Recognition, 40 (6): 1825-1839.
  4. Berg, Mark de, Cheong, Otfried, Kreveld, Marc van, Mark, 2008. Computational Geometry Algorithms and Applications, Springer-Verlag Berlin Heidelberg. Third Edition, pp: 243-258.
  5. Bhaskarabhatla, A. S., Madhvanath S., Pavan Kumar, M. N. S. S. K., Balasubramanian, A., Jawahar, C. V., 2004. Representation and annotation of online handwritten data, Ninth International Workshop on Frontiers in Handwriting Recognition (IWFHR), September, pp: 136-141.
  6. Castleman, Kenneth R., 1996. Digital Image Processing, Prentice Hall, Inc., pp: 492.
  7. Chang, Fu, Chu, Shih-Yu, Chen, Chi-Yen, 2005. Chinese document layout analysis using an adaptive regrouping strategy, Pattern Recognition, 38 (2): 261- 271.
  8. Laurence, Likforman-Sulem, Abderrazak, Zahour, Bruno, Taconet, 2007. Text line segmentation of historical documents: a survey, International Journal on Document Analysis and Recognition, 9 (2-4):123-138.
  9. Maxell, 2012. The Maxell Digital Pen, http://www.maxell.co.jp/e/products/industrial/digitalpe n/index.html.
  10. Microsoft, 2005. Microsoft Windows XP Tablet PC Edition Software Development Kit 1.7, http://www.microsoft.com/downloads/.
  11. Shilman, Michael, Tan, Desney S., Patrice, 2006. CueTIP: a mixedinitiative interface for correcting handwriting errors, The nineteenth annual ACM Symposium on User Interface Software and Technology. October 15- 18, 2006, Montreux, Switzerland, pp: 323-332.
  12. Shilman, Michael, Wei, Zile, Raghupathy, Sashi, Simard, Patrice, Jones, David, 2003. Discerning structure from freeform handwritten notes, Proceedings of Seventh International Conference on Document Analysis and Recognition. 3-6 Aug., vol.1, pp: 60-65.
  13. W3, 2012. Ink Markup Language, http://www.w3.org/ TR/InkML/.
  14. Wang, An-Bang, Fan, Kuo-Chin, 2001. Optical recognition of handwritten Chinese characters by hierarchical radical matching method, Pattern Recognition, 34 (1): 15-35.
  15. Zhang, Xi-Wen, Lyu, Michael R., and Dai, Guo-Zhong, 2007. Extraction and segmentation of tables from Chinese ink documents based on a matrix model, Pattern Recognition, 40 (7): 1855-1867.
Download


Paper Citation


in Harvard Style

Zhang X., Bai H. and Fu Y. (2012). Adaptive Visualization of Segmented Digital Ink Texts in Chinese based on Context . In Proceedings of the International Conference on Signal Processing and Multimedia Applications and Wireless Information Networks and Systems - Volume 1: SIGMAP, (ICETE 2012) ISBN 978-989-8565-25-9, pages 227-232. DOI: 10.5220/0004020102270232


in Bibtex Style

@conference{sigmap12,
author={Xi-Wen Zhang and Hao Bai and Yong-Gang Fu},
title={Adaptive Visualization of Segmented Digital Ink Texts in Chinese based on Context},
booktitle={Proceedings of the International Conference on Signal Processing and Multimedia Applications and Wireless Information Networks and Systems - Volume 1: SIGMAP, (ICETE 2012)},
year={2012},
pages={227-232},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004020102270232},
isbn={978-989-8565-25-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Signal Processing and Multimedia Applications and Wireless Information Networks and Systems - Volume 1: SIGMAP, (ICETE 2012)
TI - Adaptive Visualization of Segmented Digital Ink Texts in Chinese based on Context
SN - 978-989-8565-25-9
AU - Zhang X.
AU - Bai H.
AU - Fu Y.
PY - 2012
SP - 227
EP - 232
DO - 10.5220/0004020102270232