纸币识别系统设计与实现  

The Design and Realization of Paper Currency Recognition System

作　　者：多滨[1] 王旭峰[1] 

机构地区：[1]哈尔滨理工大学测控技术与通信工程学院,黑龙江哈尔滨150040

出　　处：《哈尔滨理工大学学报》2008年第4期10-13,共4页Journal of Harbin University of Science and Technology

摘　　要：介绍了一种纸币识别系统的硬件设计及其对应识别方法.在硬件设计上,将高速数字信号处理(DSP)技术与复杂可编程逻辑器件(CPLD)和接触式图像传感器(CIS)相结合;在识别方法上,应用图像处理技术与改进的SOFM神经网络方法识别纸币.通过实验测试,系统可在40ms内完成对一张纸币的处理.有拒识情况下,面值识别率100%,识别面向准确率为99.8%,新旧识别率约90%.We introduce a kind of paper currency recognition system and the way of recognition. We combine CPLD and CIS with the technology of DSP, which is based on the design of hardware; we apply the method of picture processing technique and modified SOFM nerve network to recognize 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.

关 键 词：纸币图像识别 SOFM网络 图像处理 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]