一种基于特征结构的纸币号码识别方法  

Study on recognition method of paper currency numbers based on characteristic structure

作　　者：冯鑫[1] 吴庆洪[1] 

机构地区：[1]辽宁科技大学电子与信息工程学院,辽宁鞍山114051

出　　处：《辽宁科技大学学报》2013年第4期385-388,共4页Journal of University of Science and Technology Liaoning

摘　　要：为了准确识别纸币号码,对纸币号码图像识别算法进行了研究。在去除噪声、放大、二值化、定位等基础上,利用字符结构特征的识别方法进行纸币号码识别,给出了上交点类字符树形分类方法,并通过MATLAB进行仿真实验。结果表明,所提出的算法具有良好的稳定性,识别率大于95%。In order to accurately identify the numbers on the paper currency, the number recognition method for RMB notes is studied. On the basis of noise removal, amplification, binarization and character positioning, a method of character recognition is proposed based on the structure characters and proved by MATLAB simulation. The results show that this method has a good stability and a high recognition rate of greater than 95%.

关 键 词：号码识别 图像处理 字符定位 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]