Banknote Discrimination Based on Information Fusion of Multispectral Images
XUE Liming
WU Jie
WANG Junmin
Abstract：In order to enhance the discriminative power of the banknote discriminating devices,a systematical banknote dis?crimination approach is proposed where the discriminative features of multispectral images are used. First,the principal component analysis algorithm is used to calculate the slant angle,and then tilt correction is implemented by rotating the image. Second,the col?or histogram of the visible image is extracted and used for denomination recognition. Finally,the improved local binary pattern algo?rithm is used to extract the discriminative features of the infrared image,and the thresholding method is used to extract the discrimi?native features of the ultraviolet image,and then these features are combined to discriminate the banknote. The experimental results show that the proposed method has a strong discriminative power for banknote discrimination.
Keywords：banknote discriminationmultispectral imagefeature extraction
Publication Date：2019-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 1364-1367,1376 )