首页 | 本学科首页   官方微博 | 高级检索  
     

一种实时纸币识别方法的研究
引用本文:刘家锋,刘松波,唐降龙.一种实时纸币识别方法的研究[J].计算机研究与发展,2003,40(7):1057-1061.
作者姓名:刘家锋  刘松波  唐降龙
作者单位:哈尔滨工业大学计算机科学与技术学院,哈尔滨,150001
摘    要:纸币清分是银行的一项重要业务,目前人民币的机器清分技术还是我国的一项空白.提出了一种用于高速纸币清分机的实时人民币识别方法,该方法提取了纸币图像的方向块特征,将人民币的长度和宽度作为识别特征,采用了改进的Kohonen网络设计了识别分类器.实验结果表明,提出的方法取得了较高的识别率,并且满足了实时性的要求,并且已经在一个实际的系统中得到应用.

关 键 词:纸币识别  Kohonen网络  自组织特征映射  纸币清分  银行

An Algorithm of Real-Time Paper Currency Recongnition
LIU Jia Feng,LIU Song Bo,and TANG Xiang Long.An Algorithm of Real-Time Paper Currency Recongnition[J].Journal of Computer Research and Development,2003,40(7):1057-1061.
Authors:LIU Jia Feng  LIU Song Bo  and TANG Xiang Long
Abstract:Paper currency sorting is an important operation in the bank, and the technique for Chinese paper currency sortor is still a lacuna in China A real time paper currency recognition method is proposed in this paper, which extracts the directional block characteristics and the size information of a currency image as the recognition features A modified Kohonen network is constructed for the recognition of Chinese paper currency The experiment reveals that this method achieves a high recognition rate and fast recognition speed The proposed method has been applied to a practical sorting system
Keywords:paper currency recognition  kohonen network  self organization feature map
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号