Character Segmentation of Chinese Rubbing Images Using Total Variation Preprocess

Abstract:

Stone tablet is one of the important historical and cultural heritages of China. It is not only an important carrier of China ancient civilization, but also is a classical template to research and learn the art of calligraphy. Chinese calligraphy tablet documents that obtained through rubbing were featured by many fuzzy details, bad effect and so on, so it might lose more details in the traditional handling process. In this paper, a total variation (TV) based denoising pre-processing methods for rubbing image has been used, and then a segmentation algorithm based on mathematical morphology is applied. Experiments show this algorithm overcomes the shortcomings of traditional method and weakens the contradiction between the noise suppression and the accuracy of detecting edge details, so it has better practicality.

• Periodical: Applied Mechanics and Materials (Volume 734)
• Pages: 590-595
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.734.590
• Online since: February 2015
• Authors: Han Huang*, Zhi Kai Huang, Mou You Lin, Ling Ying Hou
• Keywords: Chinese Calligraphy Image, Image Denoising, Image Segmentation, Total Variation

References

[1] Zhang X F, Zhuang Y T, Wu J Q, et al. Hierarchical approximate matching for retrieval of Chinese historical calligraphy character. Journal of Computer Science and Technology, 2007, 22(4): 633-640.

DOI: 10.1007/s11390-007-9077-8

[2] 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, 645-649.

DOI: 10.1109/icdar.2005.209

[3] Liang Z Z, Shi P F. A metasynthetic approach for segmenting handwritten Chinese character strings. Pattern Recognition Letters. 2005, 26: 1498-1511.

DOI: 10.1016/j.patrec.2004.12.001

[4] 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: 963-973.

DOI: 10.1016/s0167-8655(98)00073-7

[5] S. Basu , C. Chaudhuri , M. Kundu , M. Nasipuri and D. K. Basu, Text line extraction from multi-skewed handwritten documents, Pattern Recognition, vol. 40(6), 2007, June, pp.1825-1839.

DOI: 10.1016/j.patcog.2006.10.002

[6] Y. Li, Y. Zheng, D. Doermann and S. Jaeger, A new algorithm for detecting text line in handwritten documents, In Proc. 10th IWFHR, 2006, pp.35-40.

[7] A. Zahour, B. Taconet, P. Mercy and S. Ramdane, Arabic hand-written text-line extraction, In Proc. 6th ICDAR, 2001, pp.281-285.

DOI: 10.1109/icdar.2001.953799

[8] Kay S M. Fundamentals of statistical signal processing, Volume III: Practical Algorithm Development. Pearson Education, (2013).

[9] L. Rudin, P. -L. Lions, and S. Osher. Geometric Level Set Methods in Imaging, Vision, and Graphics, chapter Multiplicative Denoising and Deblurring: Theory and Algorithms. Springer-Verlag, New York, (2003).

DOI: 10.1007/0-387-21810-6_6

[10] Chan S H, Khoshabeh R, Gibson K B, et al. An augmented Lagrangian method for total variation video restoration. Image Processing, IEEE Transactions on, 2011, 20(11): 3097-3111.

DOI: 10.1109/tip.2011.2158229

[11] Chan T F, Osher S, Shen J. The digital TV filter and nonlinear denoising. Image Processing, IEEE Transactions on, 2001, 10(2): 231-241.

DOI: 10.1109/83.902288

[12] He K, Sun J, Tang X. Guided image filtering, Computer Vision–ECCV 2010. Springer Berlin Heidelberg, 2010: 1-14.

[13] http: /kanji. zinbun. kyoto-u. ac. jp/db-machine/imgsrv/takuhon/type_a/html/tou0002x. html (accessed 21/10/2014).

[14] J. Serra. Image analysis and mathematical morphology. Academic Press, (1982).

[15] P. Soille. Geodesic transformations in mathematical morphology: an Overview. Technical Report, School of Mines of Paris, N-24/94/MM, (1994).

[16] http: /archive. fieldmuseum. org/chineserubbings/introduction_2. asp (accessed 21/10/2014).

[17] Huang Z K, Chau K W. A new image thresholding method based on Gaussian mixture model. Applied Mathematics and Computation, 2008, 205(2): 899-907.

DOI: 10.1016/j.amc.2008.05.130