The Recognition of New and Old Banknotes Based on SVM

On basis of reviewing the existed research results, and with digital image processing technology, this paper brings forward a rapid algorithm of detecting new and old banknotes, in which the Support Vector Machines (SVM) and Dynamic Time Warp (DTW) are combined. First, the banknotes gray histogram is aligned by DTW. Second, the aligned Gray Histogram is embedded in radial basis function (RBF) of SVM. Then, a mixed structure RBF/DTW is built. The simulation results show that the proposed structure is efficient to recognize the banknote levels of new and old.