摘要： 针对银行支票大写金额识别工作中的手写体和印刷体辨识，抽取了4组分类特征，较好地体现了印刷体字符和手写体字符的区别。并且在构造分类器时，介绍了求取各分类特征对识别结果影响大小的权值向量的方法。在银行提供的大量真实票据上进行了验证，并且应用于实际的银行自动支票处理系统，取得了很好的效果。

关键词: OCR, 印刷体, 手写体, 分类特征

Abstract: This paper introduces a method to distinguish the printed and handwritten legal amount on Chinese bank check. Four sets of classifying features that show discrimination between printed and handwritten characters are well presented. When making classifier, a weighted vector method to get the effect on distinguishing results is proposed. The approach was applied to an automatic check processing system and tested on about 9031 checks. The recognition rate is more than 99.5%.

中图分类号: 

• TP391.41