一种实时纸币识别方法的研究

An Algorithm of Real-Time Paper Currency Recongnition

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 。

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