Effective radical segmentation of offline handwritten Chinese characters towards constructing personal handwritten fonts

ABSTRACT

Effective radical segmentation of handwritten Chinese characters can greatly facilitate the subsequent character processing tasks, such as Chinese handwriting recognition/identification and the generation of Chinese handwritten fonts. In this paper, a popular snake model is enhanced by considering the guided image force and optimized by Genetic Algorithm, such that it achieves a significant improvement in terms of both accuracy and efficiency when applied to segment the radicals in handwritten Chinese characters. The proposed radical segmentation approach consists of three stages: constructing guide information, Genetic Algorithm optimization and post-embellishment. Testing results show that the proposed approach can effectively decompose radicals with overlaps and connections from handwritten Chinese characters with various layout structures. The segmentation accuracy reaches 94.91% for complicated samples with overlapped and connected radicals and the segmentation speed is 0.05 second per character. For demonstrating the advantages of the approach, radicals extracted from the user input samples are reused to construct personal Chinese handwritten font library. Experiments show that the constructed characters well maintain the handwriting style of the user and have good enough performance. In this way, the user only needs to write a small number of samples for obtaining his/her own handwritten font library. This method greatly reduces the cost of existing solutions and makes it much easier for people to use computers to write letters/e-mails, diaries/blogs, even magazines/books in their own handwriting.

References

1. R. Casey and G. Nagy. Recognition of printed chinese characters. Electronic Computers, IEEE Transactions on, (1):91--101, 1966.
2. F. Cheng and W. Hsu. Partial pattern extraction and matching algorithm for chinese characters. 1985.
3. F. GHENG and H. Wen-Hsing. Radical extraction from handwritten Chinese characters by background thinning method. IEICE TRANSACTIONS (1976--1990), 71(1):88--98, 1988.
4. O. Ibánez, N. Barreira, J. Santos, and M. Penedo. Genetic approaches for topological active nets optimization. Pattern Recognition, 42(5):907--917, 2009.
5. W. Ip, K. Chung, and D. Yeung. Offline handwritten chinese character recognition via radical extraction and recognition. In Document Analysis and Recognition, 1997., Proceedings of the Fourth International Conference on, volume 1, pages 185--189. IEEE, 1997.
6. P. Lai, D. Yeung, and M. Pong. A heuristic search approach to chinese glyph generation using hierarchical character composition. Computer Processing of Oriental Languages, 10(3):307--323, 1996.
7. S. Lay, C. Lee, N. Cheng, C. Tseng, B. Jeng, P. Ting, Q. Wu, and M. Day. On-line chinese character recognition with effective candidate radical and candidate character selections. Pattern recognition, 29(10):1647--1659, 1996.
8. P. Liu, L. Ma, and F. Soong. Radical based fine trajectory hmms of online handwritten characters. In Pattern Recognition, 2008. ICPR 2008. 19th International Conference on, pages 1--4. IEEE, 2008.
9. D. Shi, R. Damper, and S. Gunn. Offline handwritten chinese character recognition by radical decomposition. ACM Transactions on Asian Language Information Processing (TALIP), 2(1):27--48, 2003.
10. J. Shin, K. Suzuki, and A. Hasegawa. Handwritten chinese character font generation based on stroke correspondence. International Journal of Computer Processing of Oriental Languages (IJCPOL), 18(3), 2005.
11. A. Wang and K. Fan. Optical recognition of handwritten chinese characters by hierarchical radical matching method. Pattern Recognition, 34(1):15--35, 2001.
12. A. Wang, K. Fan, and W. Wu. Recursive hierarchical radical extraction for handwritten chinese characters. Pattern recognition, 30(7):1213--1227, 1997.
13. A. Wang, J. Huang, and J. Fan. Optical recognition of handwritten chinese characters by partial matching. In Document Analysis and Recognition, 1993., Proceedings of the Second International Conference on, pages 822--823. IEEE, 1993.
14. X. Wei, S. Ma, and Y. Jin. Segmentation of connected chinese characters based on genetic algorithm. In Document Analysis and Recognition, 2005. Proceedings. Eighth International Conference on, pages 645--649. IEEE, 2005.
15. H. B. Xing. Feature analysis and computing research of Modern Chinese characters. The Commercial Press, Beijing, China, 2007.
16. C. Xu and J. Prince. Snakes, shapes, and gradient vector flow. Image Processing, IEEE Transactions on, 7(3):359--369, 1998.
17. S. Xu, T. Jin, H. Jiang, and F. Lau. Automatic generation of personal chinese handwriting by capturing the characteristics of personal handwriting. In Twenty-First IAAI Conference, 2009.
18. S. Xu, F. Lau, W. Cheung, and Y. Pan. Automatic generation of artistic chinese calligraphy. Intelligent Systems, IEEE, 20(3):32--39, 2005.
19. S. Zhao and P. Shi. Segmentation of connected handwritten chinese characters based on stroke analysis and background thinning. PRICAI 2000 Topics in Artificial Intelligence, pages 608--616, 2000.
20. B. Zhou, W. Wang, and Z. Chen. Easy generation of personal chinese handwritten fonts. In Multimedia and Expo (ICME), 2011 IEEE International Conference on, pages 1--6. IEEE, 2011.

Index Terms

• Computing methodologies

  • Artificial intelligence

    • Computer vision

      • Computer vision problems

        • Image segmentation

        • Video segmentation