Previous work by the authors has proposed a banknote recognition system usi
ng a neural network (NN) to develop new types of banknote recognition machi
nes. This system is constructed by means of some core techniques. One is a
small-scale neural recognition technique using masks. The second is a mask-
optimization technique using a genetic algorithm (GA), The last is a neural
hardware technique using a digital signal processor (DSP). This paper focu
ses on and discusses the mask optimization by the GA, which is the second c
ore technique in the neural recognition system. This technique enables the
selection of good masks, that can effectively generate the characteristic v
alues of the input image. Further, the effectiveness of this technique is s
hown not only by the generalization of the NN, but also by a statistical an
alysis, using the Italian banknotes. Finally, the feasibility and effective
ness of the neural recognition system is shown by using worldwide banknotes
. (C) 1999 Elsevier Science Ltd. All rights reserved.