摘要：To a certain extent,whether a banknote can continue to circulate depends on how dirty it is. Therefor，a multi-layer support vecior machines (MLSVMs)recognition method based on regional image texture features and threshold selection was proposed. Firstly, the contact image sensor (CIS) is used to collect the double-sided reflection gray-scale images of banknotes under blue light, green light, red light, infrared light and ultraviolet light,and the gray-scale images under green light transmission and infrared light transmission. Secondly,according to the pattern disstribution of banknote images,the collected banknote image is divided into 8 areas with different sizes，and 22 texture feature parameters such as entropy,dissimilarityand correlation of the banknote image，are extracted based on the gray-level co-occurrence matrix (GLCM) to describe the visual features of banknotes dirty degree. Then the 22 texture features by using GLCM under different light sources in different regions are selected through thresholds.Finally，MLSVMs are used to recognition the dirty degree of banknotes, and the simulation results show the effectiveness of the proposed method.
