基于多结构特征的纸币字符识别算法  

RMB Character Recognition Algorithm Based on Multiple Structural Features

作　　者：鲁超[1] 滕国伟[1] 邹雪妹[1] 安平[1] 

机构地区：[1]上海大学通信与信息工程学院,上海200444

出　　处：《电视技术》2015年第12期95-98,103,共5页Video Engineering

基　　金：国家自然科学基金项目(61172096;61271212);上海市科委重点资助项目(12511502502)

摘　　要：针对现有人民币冠字号字符识别算法对严重污染磨损的人民币冠字号字符识别率低的难题,提出了一种将模板匹配法与多种字符结构特征(字符轮廓、区域密度)相结合的人民币冠字号字符识别算法。通过定位分割、分类识别、验证纠错3个步骤完成字符的识别,实验结果表明,该算法具有较高的识别率和较强的鲁棒性。Considering the problem that the recognition rate of existing RMB character recognition algorithms for serious polluted RMB characters is too low, a RMB character recognition algorithm combining the template matching with multiple structural features（areal density, character contour）is put forward. The algorithm is divided into three steps： locating, recognition and error correction. The experimental resuhs show that the algorithm has high recognition efficiency and strong robustness.

关 键 词：字符识别 模板匹配 区域密度 字符轮廓 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]