摘要
通过Matlab编程,实现了一个可以识别扫描到计算机里图片上的英文字母及阿拉伯数字的字符识别系统,以最小距离法为判决规则,系统的识别对象为不规整的印刷体。系统识别通过对样本进行处理和训练,对识别对象的识别率可达到近百分之九十。
Through Matlab programming, the paper show the design of character recognition system, which can recognize the Let-ters and Arabic numbers from the scaned image that save into computer. The system sets Minimum Distance method as tis decisionrule, and the object recognition of the system is printed and irregular. The ratio of identification can reach nearly eighty percent,when the object recognition trained and handled by the system.
作者
冼学辉
郭少坤
XIAN Xue-hui, GUO Shao-kun （1.Information ＆ Network Management Center, North China Electric Power University, Baoding 071003, China; 2. The library of North China Electric Power University, Baoding 071003, China）
出处
《电脑知识与技术》
2015年第5期184-186,共3页
Computer Knowledge and Technology
关键词
MATLAB编程
字符识别
最小距离法
图像预处理
特征提取
Matlab programming
character recognition
minimum distance method
image preprocessing
feature extraction
