Defect detection algorithm for paper currency using chromatic homogeneity

This paper advances a chromatic homogeneity based algorithm for banknote defect detection, in which the homogeneity feature matrix of the chromatic image is constructed to locate the pixels probably polluted, the image registration algorithm is subsequently used to overlay the sensed and reference paper currency image. Finally, each probably polluted pixel on the sensed image is compared with its corresponding pixel on the reference image to estimate the contamination level. The proposed algorithm is sensitive to the odd edge-information and is robust to the color shift or edge intensity change, which leads to a high capacity for low quality banknote processing.