Euro Banknote Recognition System Using a Three - layered Perceptron and RBF Networks

We propose an Euro banknote recognition system using two types of neural networks; a three-layered perceptron and a Radial Basis Function (RBF) network. A three-layered perceptron is well known method for pattern recognition and is also a very effective tool for classifing banknotes. An RBF network has a potential to reject invalid data because it estimates the probability distribution of the sample data. We use a three-layered perceptron for classification and several RBF networks for validation. The proposed system has two advantages over the system using only one RBF network. The feature extraction area can be simply defined, and the calculation cost does not increase when the number of classes increases. We also propose to use infra-red (IR) and visible images as input data to the system since Euro banknotes have quite significant features in IR images. We have tested our system in terms of acceptance rates for valid banknotes and rejection rates for invalid data.

[1]  Friedhelm Schwenker,et al.  Three learning phases for radial-basis-function networks , 2001, Neural Networks.

[2]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[3]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[4]  Masahiro Tanaka,et al.  A Rejecting Method of Non-objective Currencies using Multi-Dimensional Gaussian Probability Density Function for Neuro-Multi National Currency Recognition , 1998 .

[5]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[6]  Sigeru Omatu,et al.  High Speed Conveyed Bill Money Recognition with Neural Network , 1992, Robotics, Mechatronics and Manufacturing Systems.

[7]  Mohammad S. Obaidat,et al.  Performance comparison of neural networks and pattern recognition techniques for classifying ultrasonic transducers , 1992, SAC '92.

[8]  David S. Broomhead,et al.  Multivariable Functional Interpolation and Adaptive Networks , 1988, Complex Syst..

[9]  Sigeru Omatu,et al.  A Neuro-Money Recognition Using Optimised Masks by GA , 1994, IEEE/Nagoya-University World Wisepersons Workshop.

[10]  R. Palmer,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[11]  Paul D. Gader,et al.  Outlier rejection with MLPs and variants of RBF networks , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[12]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[13]  T. Kosaka,et al.  Classification of the Italian Liras using the LVQ method , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).