This paper presents a new method to find personal characteristics of signatures using a genetic algorithm. The new method uses a new coding method, a new crossover method, and a genetic algorithm with a local improvement mechanism. The new coding method is devised for finding personal characteristics from signatures. The new crossover method determines the number of characteristics used for the signature verification. The genetic algorithm is very efficient in improving the local portions of chromosomes.
Experiments are done to show that the personal characteristics are efficiently found by the proposed method.
J-STAGEがリニューアルされました! https://www.jstage.jst.go.jp/browse/-char/ja/
