Discrimination Algorithms of the New and the Used Bills Using Neural Network

Abstract

In this paper, we propose a classification method of the new and used bills from observed data using neural networks and 2-stage adaptive digital filters(ADFs). 2-stage ADFs is used in order to detect the desired signal from noisy input data. And neural network (NN) is used in order to discriminate the new and the used bill money. The technique used here is based on an extension of the usual ADF by Widrow and the back-error-propagation(BP) method.