A neuro-paper currency recognition method using optimized masks by genetic algorithm
Fumiaki Takeda, Sigeru Omatu · 2002
Many applications to neural networks (NNs) of genetic algorithms (GA) have been reported. In this paper, the authors adopt the GA to a neuro-paper currency recognition method using the masks which they have proposed. Namely, the authors regard the position of the masked part as a gene. The authors sample the parental masks and operate "crossover", "selection", and "mutation" to some genes. By repeating a series of the GA operations, the authors can optimize the masks for the paper currency recognition in a short period. The authors compare the ability of the NN using the masks optimized by the GA with the NN using the masks determined by random numbers. Then the authors show that the GA is effective for systematizing the neuro-paper currency recognition with masks. Furthermore, the authors refer to a high-speed neuro recognition board which they have developed to realize neuro-paper currency recognition in commercial products and show its capacity.