朝鲜文是一种由元音和辅音构成的字母文字。因此经常使用的一种朝鲜文识别方法是:从朝鲜文字符中分离出每一个字母,然后对这些字母进行识别,最后确定识别字符。本文结合结构分析法,通过对字符图像背景进行细化处理,找到字母之间的分割线分离出了每个字母,并且利用两层外围距离特征对这些字母进行了识别。在对4种经常使用的朝鲜文印刷字体进行初步实验的结果表明,字母分割正确率平均达到了97.4% ,而字母样本集识别率为99%以上。
Abstract
Hangul is composed of graphemes of characters which represent. consonants and vowels in korean. One important Hangul character recognition method is thus the approach of separating each grapheme of character and identifying the separated graphemes independently. For separating graphemes , this paper proposes a background - thinning technique combining structural information of characters. Then ,the separated graphemes are recognized by a statistical method using peripheral features. In a test case with machine printed Hanguls of 4 fonts , the proposed approach achieved 97.4% of grapheme segmentation rate , and over 99% of grapheme recognition rate.
关键词
人工智能 /
模式识别 /
字母分割 /
字母识别 /
朝鲜文字符识别
{{custom_keyword}} /
Key words
artificial intelligence /
pattern recognition /
grapheme segmentation /
grapheme recognition /
Hangul character recognition
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] P. H. Lee , H. D. Jang , A study on printed Hangul recognition with dynamic Jaso segmentation and neural network [J] . Journal of Korean Institute of Communication , 1994 , (19) 11 :2133 - 2145.
[2] Kyung-Won Kang and Jin H. Kim. Handwritten Hangul Character Recognition with Hierarchical Stochastic Character Representation[A] . In : the 7th ICDAR[C] . Washington , USA: IEEE Computer Society , 2003 ,1 :212 - 217.
[3] Ching Y. Suen , Shunji Mori , Soo H. Kim and Cheung H. Leung.Analysis and Recognition of Asian Scripts - the State of Art [A] . In : the 7th ICDAR [C] . Washington , USA: IEEE Computer Society , 2003 ,2 :866 - 879.
[4] H. Y. Kim and J. Kim. Hierarchical Random Graph Representation of Handwritten Characters and its Application to Hangul Recognition [J] . Pattern Recognition ,2001 ,34 (2) :187 - 201.
[5] 李根寿. Recognition of Printed Hangul Using Fuzzy Reasoning[D] . Seoul , Korea :崇实大学校大学院博士学位请求论文,June 1993.
[6] 古丽拉·阿东别克,米吉提·阿布力米提. 维吾尔词语切分方法初探[J]. 中文信息学报,2004 ,18(6) :61 - 65.
[7] 李丰林. 韩谚文相似字判决方法的研究[D] . 北京:中国科学院计算技术研究所硕士学位论文,1999.
[8] M. K. Kim , O. S. Kwon , and Y. B. Kwon. Hangul character type clustering based on the structural shapes and the combination rules of vowels[J] . Journal of Korea Information Science Society , 1998 ,25 (4) :685 - 695.
[9] C. J. Hilditch. Comparison of thinning algorithms on a parallel processor[J] . Image and Vision Computing , 1983 ,1 (3) :115 - 132.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家863计划资助项目(DH02H01)
{{custom_fund}}
PDF(427 KB)
