Handwritten Chinese characters recognition by greedy matching with geometric constraint

NCU Institutional Repository > 資訊電機學院 > 資訊工程研究所 > 期刊論文 > Item 987654321/29218

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/29218

题名:	Handwritten Chinese characters recognition by greedy matching with geometric constraint
作者:	Hsieh,AJ;Fan,KC;Fan,TI
贡献者:	資訊工程研究所
关键词:	RELAXATION;GRAPH
日期:	1996
上传时间:	2010-06-29 20:16:40 (UTC+8)
出版者:	中央大學
摘要:	In this paper, a greedy matching algorithm with geometric constraint for solving the polygonal arcs matching (boundary line segments matching) is proposed. Assume the matched cost and the unmatched penalty of each line segment are given, as well as any two matched pairs in the matching which preserves the geometric relation. Our goal is to find a matching such that (1) the sum of costs of matched line segments and the penalties of unmatched line segments is minimum, and (2) the matching preserves the geometric relation. The proposed greedy matching algorithm consists of two main modules. The first is an optimal matching module, which utilizes the optimization matching method to find an optimal matching without the geometric constraint. The second module is an evaluation and update module, which deletes the matched pair with a geometric relation having the maximum inconsistency after each matched pair has been evaluated, and a new matching is found again. The algorithm continues until a stable matching is found. To verify the validity of the proposed algorithm, we implement it to recognize handwritten Chinese postal characters. We selected 51 Chinese postal characters as the prototype characters, and the experiments are conducted on 2550 samples, with each category containing 50 variations. The recognition rate is 91.8%. Experimental results reveal the feasibility of our proposed method in recognizing handwritten Chinese postal characters.
關聯:	IMAGE AND VISION COMPUTING
显示于类别:	[資訊工程研究所] 期刊論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	433	检视/开启

在NCUIR中所有的数据项都受到原著作权保护.

社群 sharing

数据加载中.....