Defect detection algorithm for paper currency sorting system

This paper advances a homogeneity based algorithm for the detection of scratches and cracks appearing on paper currency. The homogeneity feature of the sensed paper currency image is first constructed to locate the possibly polluted pixels. The image registration algorithm is subsequently used to overlay the sensed and reference paper currency images. At last, each possibly polluted pixel on the sensed image is compared with its corresponding pixel on the reference image to estimate the contamination level.