摘要
字符识别是模式识别领域非常重要的一个应用领域.纳西东巴象形文字是世界上唯一活着的象形文字,在识别领域的研究较少.主要提取纳西东巴象形文字的粗网格特征和拓扑特征的组合,使用支持向量机方法,对纳西东巴文字进行识别.通过实验证明,采用组合特征、基于支持向量机方法的纳西东巴象形文字识别准确率比已有的采用粗网格特征和基于距离法的识别准确率更高,稳定性更好,可以在此基础上继续进行东巴象形文字的识别研究.
Character recognition is an important application area of pattern recognition. Naxi Dongba picto- graphs are the world＇s only living pictographs and there is little study on their recognition.Two kinds of character- istics are firstly extracted from the characters with one by the coarse grid method and the other by the topological method.Then the support vector machine （SVM） is used to identify those characters with the two kinds of charac- teristics compared with the nearest neighbor method. Experiments are designed and the results show that SVM method using the combination of two kinds of characteristics performs better than other methods.
出处
《云南大学学报（自然科学版）》
CAS
CSCD
北大核心
2016年第5期730-736,共7页
Journal of Yunnan University(Natural Sciences Edition)
基金
国家社科基金重大项目(12&ZD234)
北京市教委面上项目
关键词
纳西东巴
象形文
字符识别
支持向量机
Naxi Dongba
pictograph
character recognition
support vector machine
