基于小波变换的纸币真伪识别算法研究  

Algorithm research on banknote authenticity identification based on wavelet transform

作　　者：徐莹[1] 陈普春[2] 曹俊 张莹 

机构地区：[1]西南石油大学电子信息工程学院,四川成都610500 [2]西南石油大学理学院,四川成都610500

出　　处：《现代电子技术》2012年第4期22-24,共3页Modern Electronics Technique

摘　　要：针对真钞和伪钞在投射图像纹理上的差异,对纸币的真假识别进行了研究,提出了一种新的纸币真伪识别算法,即对真伪纸币进行小波变换,以提取纸币的纹理特征,利用得到的各尺度小波变换域的平局能量构造特征矢量,实现了纸币的真伪判别。仿真结果表明,该方法速度快,精度高,适合于纸币实时鉴伪。The discrimination of real and counterfeit currency is studied according to the differences of the projected textures of them.A new algorithm is put forward for recognizing the authenticity of banknotes.It performs wavelet transform on the true and false banknotes respectively to extract texture features of banknotes.Then the feature vector is formed by the obtained mean energy on wavelet transform domain to realize the recognition of authentic and counterfeit currency.The simulation results show that the method has high speed,high precision and good real-time property which is suitable for identification of the authenticity of banknotes.

关 键 词：纹理提取 小波变换 特征矢量 纸币 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]