中文摘要：

提出一种基于改进梯度方向直方图和支持向量机分类器的人民币识别方法。利用人民币红外图像中斑马线特征进行真伪识别，通过Fisher准则进行特征块选择实现梯度方向直方图特征的降维。针对斑马线防伪图案进行实验。结果表明，该方法能克服红外图像中的背景干扰和噪声，得到较好鉴伪结果。

英文摘要：

This paper presents a method to improve the histograms of oriented gradient descriptors and support vector machine classifier for Chinese RMB currency recognition. The zebra-stripe pattern of the infrared images of RMB pa-per currency was used for real and counterfeit classification. The dimension of histograms of oriented gradient fea-tures is decreased by feature block selection based on the Fisher criterion. Several experiments on zebra-stripe pat-tern recognition were conducted, and the proposed method shows its robustness against background interference and noise.