基于嵌入式纸币识别系统的设计与实现  

Designing and Realization of Bill Acceptor System based on Embed system

作　　者：党长青[1] 田树华[1] 张景辉[1] 

机构地区：[1]唐山学院信息工程二系,063020

出　　处：《微计算机信息》2008年第19期261-263,共3页Control & Automation

基　　金：河北省自然科学基金资助(F2007000682)

摘　　要：设计研究人民币纸币识别系统的主要模块,如图像特征采集﹑处理和识别。实时特征采集是基于嵌入式纸币识别系统的关键,结合uClinux操作系统和S3C4510B的特点,设计了以中断方式实现的实时特征采集系统,提升纸币识别系统的并发处理能力。在软件识别部分选取预处理之后的纸币图像的尺寸特征用模糊逻辑推理方法识别图像的面值,提取矩作为特征,采用RBF神经网络来识别纸币的正反面和正反向,并通过实验证明该系统的有效性和可行性。The main modules, such as image sampling, processing and identification, in identification system of RMB paper currency are designed and studied. Designing and applying of real-tlme data acquisition system of bill characteristic is a key issue of bill acceptor system based on embedded system. According to the Characteristic of uclinux and S3C4510B, A real-time data acquisition system which uses interrupt is designed. And it can greatly improve the ability of concurrent processing of this bill acceptor system. size feature is chosen to identify the value of RMB paper currency images by the method of fuzzy reasoning which have been preprocessed Moment invariants are selected as features to recognize the orientation of RMB paper currency by RBF neural network .The validity and feasibility of the system are proved by experiments.

关 键 词：ucnnux 纸币识别系统 实时采集系统 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]