A neural network-based model for paper currency recognition and verification

IEEE Transactions on Neural NetworksPublished 1 November 1996

Andrea Frosini, Marco Gori, P. Priami

Citations125

TL;DR

The neural-based recognition and verification techniques used in a banknote machine, recently implemented for accepting paper currency of different countries, are described and the experimental results are very interesting, particularly when considering that the recognition and verify steps are based on low-cost sensors.

Abstract

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 implementation on a standard microcontroller-based 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.

Keywords

ChemistryComputer ScienceEngineering

The MIT Press eBooksParallel Distributed Processing

15,227 Citations1986David E. Rumelhart, James L. McClelland +1 more

IEEE Transactions on Pattern Analysis and Machine IntelligenceOn the problem of local minima in backpropagation

656 Citations1992Marco Gori, A. Tesi

A theoretical framework for backpropagation (BP) is proposed and it is proven in particular that the convergence holds if the classes are linearly separable and that multilayered neural networks (MLNs) exceed perceptrons in generalization to new examples.

IEEE Signal Processing MagazineText-independent speaker identification

352 Citations1994H. Gish, M. Schmidt

A robust speaker-identification system is presented that was able to deal with various forms of anomalies that are localized in time, such as spurious noise events and crosstalk.

IEEE Transactions on Neural NetworksHigh speed paper currency recognition by neural networks

107 Citations1995Fumiaki Takeda, Sigeru Omatu

A new technique is proposed to improve the recognition ability and the transaction speed to classify the Japanese and US paper currency and to reduce the input scale of the neural network without preventing the growth of recognition.

IEEE Transactions on Neural NetworksThe effects of quantization on multilayer neural networks

98 Citations1995Günhan Dündar, Kenneth Rose

The effect of weight quantization in multilayer neural networks is discussed and a method is derived by which one can predict the performance degradation at the output given the properties of the network and number of bit quantization.

IEEE Transactions on Neural NetworksLearning in multilayered networks used as autoassociators

56 Citations1995Monica Bianchini, Paolo Frasconi +1 more

This paper focuses attention on multilayered networks used as autoassociators and derives a condition which is met at the end of the learning process and shows that this condition has a very intriguing geometrical meaning in the pattern space.

A paper currency recognition method by a small size neural network with optimized masks by GA

21 Citations2002Fumiaki Takeda, Saizo Onami +3 more

It is shown that the proposed method by neuro-recognition with masks can be applied effectively to paper currency recognition machine using the genetic algorithm (GA) to optimize the masks.

Speech CommunicationWhat's in a number? Moving beyond the equal error rate

21 Citations1995J. Oglesby

A performance profile is suggested that encompasses the important aspects of a system under test, namely the actual verification performance, model storage requirements, confusability of the speakers in the test set, quality of the speech data used and the duration of speech data available for enrolment and testing.