No abstract

No abstract

No abstract

Up to now, Authors' research have been focussed on applications for banknotes recognition on neural networks (NNs). Especially, we have clarified its effectiveness of neuro-recognition system on industrial use by implementing the neuro-recognition system to various banking machines in spite of unfocussed sensing data and various noised data. Recently, another demand on banknotes recognition will be appeared. Namely, it is needed the more number of banknotes to be recognized at the same time on the banking machines according to appearance of Euro banknotes. In order to solve this problem, we propose a neuro-templates matching method whose templates are constructed by plural NNs. We show its effectiveness by experiments for various foreign banknotes and Euro dummy. Furthermore, we also refer extension of the proposed method to human security using bio-parametric information such as palm prints, finger prints, face image and so on. 196T.

We have proposed neural network (NN) to develop new types of the paper currency recognition machines.We have showed various effectiveness of NN recognition method by experimental results. However, there are two themes on the paper currency recognition problem. One is the correct recognition of the objective currency.Another is the rejection of non-objective currencies. Conventionally, we use the template matching method as a post processor to reject the non-objective currencies. However, even objective currency is sometimes rejected by this conventional method owing to its terrible damage. In this paper, to solve this problem, we propose a rejecting method of the non-objective currencies by multi-dimensional Gaussian Probability Density Function (PDF). First, we estimate the PDF of currency vector as the multi-dimensional Gaussian PDF. Second, we get the function value and judge the evaluated currency as the objective one or not by this value. Here, we show the effectiveness of the proposed method using multiple national currencies.Furthermore, we implement the proposed method to the experimental system and discuss the effectiveness on a real time system.