| 印刷体藏文文字识别技术研究 |
| |
| 引用本文： | 欧珠,普次仁,大罗桑朗杰,赵栋才,刘芳,边巴旺堆. 印刷体藏文文字识别技术研究[J]. 计算机工程与应用, 2009, 45(24): 165-169. DOI: 10.3778/j.issn.1002-8331.2009.24.049 |
| |
| 作者姓名： | 欧珠 普次仁 大罗桑朗杰 赵栋才 刘芳 边巴旺堆 |
| |
| 作者单位： | 西藏大学工学院,拉萨,850000;西藏大学工学院计算机科学系,拉萨,850000 |
| |
| 基金项目： | 教育部科技创新工程重大项目培育资金项目 |
| |
| 摘 要： | 藏文字因其结构的特殊性，在应用传统文字识别方法进行识别时正确识别率较低，识别效果较差。在深入分析以印刷体藏文文字特征的基础上，提出了一系列可以在干扰情况下提高识别率的方法，包括局部自适应二值化算法、基于连通域的切分、基于网格的模糊笔划特征提取等。实验结果说明，这些方法可提高印刷体藏文文字识别系统的正确识别率和抗干扰能力。
|
| 关 键 词： | 印刷体藏文字符 切分 藏文文字识别 光学字符识别 |
| 收稿时间： | 2009-01-08 |
| 修稿时间： | 2009-3-18 |
Study on printed Tibetan character recognition |
| |
| Ngodrup,Putseren,Daluosanglangjie,ZHAO Dong-cai,LIU Fang,Bianbawangdui. Study on printed Tibetan character recognition[J]. Computer Engineering and Applications, 2009, 45(24): 165-169. DOI: 10.3778/j.issn.1002-8331.2009.24.049 |
| |
| Authors: | Ngodrup Putseren Daluosanglangjie ZHAO Dong-cai LIU Fang Bianbawangdui |
| |
| Affiliation: | 1.School of Engineering，Tibet University，Lhasa 850000，China 2.Department of Computer Science，School of Engineering，Tibet University，Lhasa 850000，China |
| |
| Abstract: | Owing to the special structure of Tibetan characters,the recognition of traditional Tibetan characters encounters the problems of low recognition rates and poor recognition effects.Through an in-depth study on features of the printed Tibetan characters,this paper develops a series of methods to increase recognition rate and improve the recognition effects of Tibetan characters even in the case of jamming.These methods include local self-adaptive binary algorithm,segmentation based on the connected domain,gr... |
| |
| Keywords: | printed Tibetan character segmentation Tibetan character recognition Optical Character Recognition（OCR）
|
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载免费的PDF全文 |
