| 二级印刷体汉字的识别 |
| |
| 引用本文： | 朱夏宁,吴佑寿,丁晓青.二级印刷体汉字的识别[J].清华大学学报(自然科学版),1987(1). |
| |
| 作者姓名： | 朱夏宁 吴佑寿 丁晓青 |
| |
| 作者单位： | 无线电电子学系
(朱夏宁，吴佑寿)，无线电电子学系(丁晓青) |
| |
| 摘 要： | 本文提出了一种利用数学形态学提取汉字结构特征进行汉字识别的方法。该方法模仿人的认字过程，根据汉字构造的基本规律选取字的边框特征和局部特征，所取特征可适用于多体印刷体汉字的识别。用传真机输入的６７６３个二级汉字进行了实验，分类稳定，正确识别率为９５．２％。
|
| 关 键 词： | 模式识别 图像处理 计算机应用 汉字识别 |
The Recognition of 6763 Printed Chinese Characters |
| |
| Zhu Xianing,Wu Youshou,Ding Xiaoqing.The Recognition of 6763 Printed Chinese Characters[J].Journal of Tsinghua University(Science and Technology),1987(1). |
| |
| Authors: | Zhu Xianing Wu Youshou Ding Xiaoqing |
| |
| Institution: | Department of Radio Electronics |
| |
| Abstract: | The paper presents a new method for the recognition of 6763 printed Chinese characters. The recognition scheme is based on the structure of the characters and the recognition process simulates that of human beings. Two sets of structural characteristics are proposed for preliminary classification which divides 6763 Chinese characters into 112 subgroups. Mathematical morphology is used to extract these characteristics. Experimental results show that the preliminary classification is stable, and the recognition accuracy is 95.2%. It is show that the method proposed can also be used for the recognition of multi-font printed Chinese characters. |
| |
| Keywords: | pattern recognition image processing computer application Chinese character recognition |
| 本文献已被 CNKI 等数据库收录！ |
