No Access

Handwritten Chinese Character Font Generation Based on Stroke Correspondence

Graduate School of Computer Science and Engineering, University of Aizu, Aizu-Wakamatsu City, Fukushima, 965-8580, Japan

Search for more papers by this author

KAZUNORI SUZUKI

Graduate School of Computer Science and Engineering, University of Aizu, Aizu-Wakamatsu City, Fukushima, 965-8580, Japan

Search for more papers by this author

, and

ATSUSHI HASEGAWA

Graduate School of Computer Science and Engineering, University of Aizu, Aizu-Wakamatsu City, Fukushima, 965-8580, Japan

Search for more papers by this author

https://doi.org/10.1142/S0219427905001316Cited by:2 (Source: Crossref)

Abstract

In this paper, we investigate a novel method for an individual's handwritten Chinese character font generation, using stroke correspondence between the reference character database and the compressed character database, by vector quantization. Chinese characters are composed of a combination of radicals. A radical may be separated into several strokes, with each stroke corresponding to two or more common strokes. By paying attention to the characteristics of Chinese characters and the strokes that form them, we consider each stroke to be a vector and compress the stroke pattern using vector quantization. A compression rate of 1.27% is achieved by the vector quantization. We performed the evaluation experiments using both subjective and objective criteria involving 26 subjects and demonstrated that fonts generated successfully reflect the user's individual handwriting.

Keywords:

References

H. Yamada, IEICE Trans. E79-D(5), 423 (1996). Google Scholar
M. Hamanaka, K. Yamada and J. Tsukumo, IEICE Trans. E77-D(7), 825 (1994). Google Scholar
Y. Waizumiet al., IEICE Trans. J86-D-II(10), 391 (2003). Google Scholar
M. Suzukiet al., IEICE Trans. J84-D-II(11), 353 (2001). Google Scholar
M. Shiono, IEICE Trans. J74-D-II(2), 209 (1991). Google Scholar
H. Choi, S. Cho and J. H. Kim, Generation of handwritten characters with Bayesian network based on-line handwriting recognizers, ICDAR, 2003, pp. 995–999 . Google Scholar
M. Yasumoto, T. Ikeda and H. Horii, IEICE Trans. J80-D-II(11), 2930 (1997). Google Scholar
M. Yasumoto, T. Ikeda, J. Ying and K. Toyokura, A generation method of handwritten style font with individuality from example base, International Conference on Chinese Computing '96, System and Software, 1996, pp. 361–368 . Google Scholar
S. Ando, J. Takashima and M. Nakajima, Automatic handwritten-like font creation that reflects individual writing habit, The Seventh Symposium on Sensing via Image Information Trans., 2001, pp. 177–180 . Google Scholar
S. Ando, T. Harada and M. Nakajima, Development of writing habit including character font generator, The Eighth Symposium on Sensing via Image Information Trans., 2002, pp. 191–196 . Google Scholar
J. Shin, A study of the compression method for a reference character dictionary used for on-line character recognition, Proceedings of the Seventh International Conference on Knowledge-Based Intelligent Information, 2003, pp. 300–309 . Google Scholar
CHISE Project, Database of the component structure of Chinese characters, http://www.kanji.zinbun.kyoto-u.ac.jp/projects/chise/ids/index.html.ja.iso-2022-jp . Google Scholar
H. Kasuga, H. Yamamoto and M. Okamoto, IEICE Trans. J82-D-II(7), 1120 (1999). Google Scholar
C. T. Zahn and R. Z. Roskies, IEEE Trans. Computers C-21, 269 (1972). Crossref, Google Scholar
G. H. Granlund, IEEE Trans. Computers C-21, 195 (1972). Crossref, Google Scholar
Y. Uesaka, IEICE Trans. J67-A(3), 166 (1984). Google Scholar