A Neural Network-Based Model for
Paper Currency Recognition and Verification
A. Frosini?, M. Gori??, and P. Priami?
? Dipartimento di Sistemi e Informatica, Universit?a di Firenze
Via S. Marta, 3 - 50138 Firenze (Italy)
Tel. +39 (55) 479.6361 E-mail: [email protected]
This paper describes the neural-based recognition and verification techniques
used in a banknote machine, recently implemented for accepting paper currency
of different countries.
The perception mechanism is based on low cost optoelectronic devices which produce a signal associated with the light refracted by the banknotes.
The classification and verification steps are carried out by a society of multilayer
perceptrons whose operation is properly scheduled by an external controlling
algorithm, which guarantees real-time implementationon a standard microcontrollerbased
platform. The verification relies mainly on the property of autoassociators
to generate closed separation surfaces in the pattern space.
The experimental results are very interesting, particularly when considering that the recognition and verification steps are based on low cost sensors.
Automatic machines capable of recognizing banknotes are massively used in automatic dispensers of a number of different products, ranging from cigarettes to bus tickets, as well as in many automatic banking operations.
The wide range of applications of these machines places severe constraints on their cost, performance and, consequently, architectural solutions. For instance, most machines operating in automatic dispensers are not very effective in terms of performance but, on the other hand, they are available at very low cost. Whereas machines used in banking operations usually have to pass very severe tests, but are available at a higher cost.
Recently, the problem of paper currency recognition has been dealt with very effectively by using neural networks at Glory LTD jointly with University of Tokushima