用户名: 密码: 验证码:
人民币纸币面额的机器视觉识别方法研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
纸币面额识别是自动存款机和自动售货机等许多金融设备一个必不可少的功能模块。近年来,随着我国国民经济的迅猛发展,国内对自动化纸币清分机等金融设备的需求也变得十分迫切。本文在广泛查阅国内外相关参考文献的基础上,针对我国人民币纸币自身的特征,设计了基于图像处理和神经网络技术的面额识别方法。
     本文方法在先期获得人民币纸币图像的基础上,由噪声滤除、图像倾斜校正、图像定位分割、特征提取和面额识别等几个主要部分组成。①倾斜校正是本文方法中比较关键的一个环节,在倾斜校正过程中,采用了直线拟合的方法计算出纸币边框上边界所在直线的斜率,从而计算出纸币图像的倾斜角度,然后再进行图像旋转,使图像位置归一化。②在图像定位分割中采用了灰度投影的方法,根据背景图像和目标图像的明显差异,从而准确定位出纸币的上下和左右边界,使目标图像和背景分离开来,然后对目标图像进行幅面归一化。③在纸币的特征提取过程中,根据纸币图像的特殊性,采用类似轴对称掩膜方法提取人民币图像特征,减少了输入神经网络的模式类别。④在纸币的识别过程中,本文充分利用神经网络的并行分布处理和高的容错性特点,将BP神经网络算法应用于纸币的面额识别,不仅能够识别新币和感染轻微噪声的纸币,而且对符合流通要求的残币、旧币仍具有很强的鲁棒性,较好地实现了人民币面额的准确识别。
     通过对由扫描仪获得的一定数量的人民币图像进行识别实验,在允许有少量拒识现象发生的情况下,本文方法的正确识别率可达100%,完全满足当前国内对人民币面额的自动识别要求,具有很好的实际应用前景。
Identifying of banknote denomination is a necessary function module on all financial equipments. In recent years, with rapid development of China's national economy, the demand of automatic banknote detaching-machine and other financial equipments becomes extremely urgent. On the basis of references about recognition of banknote denomination at abroad and home, contraposing to RMB self-characteristics, this thesis designs denomination recognition method based on image processing and neural network technology.
     On the basis of RMB banknote images obtained in advance, this method is composed of image noise filtering, declining image adjusting, image locating and segmentation, feature extraction, denomination recognition and several other components.①Declining image adjusting is a more crucial tache. In the course of adjusting declining image, this thesis puts forward a method of calculating the slope of the upper frame line with line fit, consequently, the declining angle is obtained, and then we can rotate the image based on the above angle.②In the process of image locating and segmentation, a gray projection method is adopted. According to the obvious differences between image background and objectives, we can accurately locate the border of target image to separate target image from background image, and then normalize the target image.③In the process of feature extraction, the characteristics are extracted with similar axis-symmetry masks according to the specialty of the RMB image.④In the process of denomination recognition, we adequately use the abilities of parallel processing and high fault tolerance for NN, apply BP algorithm to denomination identifying of banknote. This recognition method not only recognizes new and slightly polluted banknotes, but also for defected and old but still circulating banknote is strongly robust, too. Through experiments for a certain number of RMB images acquired by the scanner, on the condition of a small amount of rejection, this method can achieve 100 percent correct recognition rate. It can fully meet the current domestic automatic recognition requirements for RMB denomination and will have good prospects for the practical application.
引文
[1] F. Takeda, S. Omatu, T. Inoue. An expert system for determining the discriminative functions for bill money recognition. Trans. Info. Process. Soc. Japan, 1992, 33(7):980-990.
    [2] F. Takeda, S. Omatu. High-speed Paper Currency Recognition by Neural Networks. IEEE Traps. Neural Networks, 1995, 6(1):73-77.
    [3] F. Takeda, S. Omatu, T. Inoue. Bill Money Recognition by a Small Size Neural Network. Tech. Rep. Bull. Faculty Eng, Japan, 1993, (38):62-66.
    [4] F. Takeda, S. Omatu, T. Inoue etc.. High-speed Conveyed Bill Money Recognition with Neural Networks. in Proc. IMACS/SCINE Int. Symp. Robot., Mechatron. Manufacture. System. Kobe, Japan, 1992:16-20.
    [5] F. Takeda, T. Nishikage, Y. Matsumoto. Characteristics Extraction of Paper Currency using Symmetrical Masks Optimized by GA and Neuro-Recognition of Mufti-National Paper Currency. Proceedings of IEEE World Congress on Computational Intelligence, Alaska, USA, 1998, 1:634-639.
    [6] Angelo Frosimi, Marco Gori. A Neural Network-based Model for Paper Currency Recognition and Verification. IEEE Transaction on Neural Networks, 1996, 7(6):1482-1490.
    [7] Jae-Kang Lee, Seong-Goo icon, Ⅱ-Hwan Kim. Distinctive Point Extraction and Recognition Mgorithm for Various Kinds of Euro Banknotes. International Journal of Control, Automation and Systems, 2004, 2(2):201-206.
    [8] F. Takeda, T. Nishikage. A Proposal of Structure Method for Multi-Currency Simultaneous Recognition using Neural Networks. T. IEE Japan, 2000, 120-C: 1602-1608.
    [9] F. Takeda, S.Omatu, Y. Matsumoto. Development of High Speed Neuro-Recogniton Board and Application for Paper Currency. The International Workshop on Signal Processing Application and Technology, 1998, 49-56.
    [10] F. Takeda, S. Omatu, T. Inoue etc.. Bill Money Recognition using Neural Network with FFT as Pre-processor. Trans. Inst. Syst., Control and Info. Eng., Japan, 1992, 5(7):265-273
    [11] 王勇.纸币清分机图像处理算法及控制策略的研究:(硕士学位论文).杭州:浙江大学,2004.
    [12] 刘斌昌.基于DSP的快速纸币图像识别技术研究:(硕士学位论文).武汉:华中科学大学,2003.
    [13] 赵楠楠.人民币图像识别系统: (硕士学位论文).鞍山:鞍山科技大学,2003.
    [14] 曹丹华,刘斌昊,吴裕斌.投影特征匹配的快速纸币面值识别算法.光电工程,2004.1,第31卷第1期.
    [15] 张国华.人民币纸币面额识别方法的研究: (硕士学位论文).沈阳:沈阳工业大学,2005.
    [16] 程海玉.人民币智能分捡器软件系统设计: (硕士学位论文).武汉:武汉理工大学,2006.
    [17] 罗皓斐.纸币清分机图像处理系统的研究: (硕士学位论文).杭州:浙江大学,2005.
    [18] 曾红玉.基于神经网络BP算法的改进: (硕士学位论文).乌鲁木齐:新疆大学,2003.
    [19] 李继飞.神经网络模式识别技术在自动售货机中的应用研究:(硕士学位论文).长沙:湖南大学,2004.
    [20] 陈传波,金先级.数字图像处理.北京:机械工业出版社,2004.
    [21] 何东建.数字图像处理.西安:西安电子科技大学出版社,2003.
    [22] 龚声蓉,刘纯平,王强等.数字图像处理与分析.北京:清华大学出版社,2006.
    [23] Linda G.Shapiro,George C.Stockman计算机视觉.赵清杰,钱芳,蔡利栋.译北京:机械工业出版社,2005.
    [24] 容观澳.计算机图像处理.北京:清华大学出版社,2000.
    [25] 夏良正.数字图像处理.南京:东南大学出版社,1999.
    [26] 张兆礼,赵春晖,梅晓丹.现代图像处理技术及Matlab实现.北京:人民邮电出版社,2001.
    [27] 何斌,马天予,王运坚等.vc++数字图像处理.第2版.北京:人民邮电出版社.2003.
    [28] 宋铭利,关于去除图像噪音的中值滤波算法.洛阳师范学院学报,2002(5):67-69.
    [29] 程杰.一种基于直方图的分割方法.华中理工大学学报,1999,27(1):20-23.
    [30] 高湘玲.PCB数字图像检测与识别研究:(硕士学位论文).成都:西南交通大学,2002.
    [31] 阮秋琦.数字图像处理学.北京:电子工业出版社,2001.
    [32] 权炜,郑南宁,贾新春.复杂背景下车辆牌照字符提取方法研究.信息与控制,2002,31(1):25-29.
    [33] Widrow, B. Winter, R.G., Baxter, R.A.. Layered Neural Nets for Pattern Recognition. IEEE Transaction Acoustic, 1998, 36(7):308-314.
    [34] 沈清,汤霖.模式识别导论.北京:国防科技大学出版社,1991.
    [35] (美)J.P.Marques de S6著.模式识别—原理、方法与应用.吴逸飞译.北京:清华大学出版社.2003.
    [36] 边肇棋,张学工等.模式识别.第2版.北京:清华大学出版社,1998.
    [37] 李介谷,蔡国廉.计算机模式识别技术.上海:上海交通大学出版社,1986.
    [38] 张承福.神经网络系统.力学进展,1988,(2):145-160.
    [39] 许东,吴铮.基于Matlab6.x的系统分析与设计——神经网络.西安:西安电子科技大学出版社,2002.
    [40] 焦李成 编著,神经网络计算.西安:西安电子科技大学出版社.1995.
    [41] 王永骥,涂健.神经元网络控制.北京:机械工业出版社.1998.
    [42] 楼顺天,施阳.基于MATLAB的系统分析与设计—神经网络.北京:西安电子科技大学出版社,1995.
    [43] 闻新,周露,王丹力等.MATLAB神经网络应用设计.北京:科学出版社2000.
    [44] 蒋德明.神经网络模式识别方法在云分类中的应用研究:(硕士学位论文).南京:南京气象学院,2001.
    [45] 张立明.人工神经网络的模型及其应用.上海:复旦大学出版社,1992.
    [46] 施阳,李俊等.MATLAB语言工具箱-TOOLBOX实用指南.西安:西北工业大学出版社,1999.
    [47] (美)D.Hanselman,B.Littlefield著.精通MATLAB6.张航,黄攀译.北京:清华大学出版社.2002.
    [48] 王晓丹,吴崇明.基于MATLAB的系统分析与设计—图像处理.西安:西安电子科技大学出版社,2000.
    [49] 许东,吴铮.基于MATLAB的系统分析与设计—神经网络.西安:西安电子科技大学出版社,2002.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700