摘要
随着信息技术的迅速发展和计算机软件技术的不断成熟,维吾尔文信息处理也取得了很大的进步。字符切分是字符识别的基础,文章在分析维吾尔文字母的结构特点的基础上,对维吾尔文单词的切分进行了一些研究,根据对字符的高度,宽度,相邻字符块的间距,笔画分布规律等特征进行分析,提出了一种切分方法。
With the development of information technology and the incessant growing of computer software,we have made great progress in the information processing of Uighur.Character segmentation is the groundwork of character recognition,on the basis of the structure of Uighur character,this paper investigates the segmentation of Uighur character,and a method of segmentation is introduced according to the height,the width,the interval of the neighboring characters,the stroke feature and some other features of the characters.
出处
《新疆师范大学学报(自然科学版)》
2010年第4期72-76,共5页
Journal of Xinjiang Normal University(Natural Sciences Edition)
基金
陕西省自然科学基础研究计划资助项目(2009JQ8019)
ISN国家重点实验室基金(ISN090302)
关键词
维吾尔文
字符特征
字符切分
Uighur
Character features
Character segmentation.