1997 Volume 63 Issue 615 Pages 3933-3940
We propose three core methods for paper currency recognition using the neural network. The first method is to create a small size neuro-recognition technology for paper currency using masks. The second method is to adapt the genetic algorithm to the mask determination. The last method is to develop a high speed neuro-recognition board using a DSP to realize the commercial products. In this paper, we unify three methods for paper currency recognition and realize the neuro-system technology. We show development and effectiveness in an experimental system using current banking machines.