基于遗传算法实现签名曲线的匹配  

Implementation of the Signature Curve Matching Based on Genetic Algorithm

作　　者：张巍[1] 郑建彬[1] 

机构地区：[1]武汉理工大学信息工程学院,湖北武汉430070

出　　处：《武汉理工大学学报（信息与管理工程版）》2008年第1期39-43,共5页Journal of Wuhan University of Technology：Information & Management Engineering

基　　金：国家自然科学基金资助项目(69672014)

摘　　要：将遗传算法的思想应用于曲线比较,解决了签名曲线匹配的问题。先通过对一般的曲线相似性比较,建立起数学模型,然后结合数学模型,分离出待讨论的关键参数,对参数进行选择、交叉和变异等遗传操作,寻找最优的个体,从而寻找最短的距离。最后结合在线签名认证实例,对签名曲线进行匹配比较,同时对算法进行分析。实验结果较好地证明了该方法的有效性。The concept of genetic algorithm was used to the curve comparison to solve the signature curve matching problems. A mathematical model to the general curve similarity comparison process was established. On this basis, the essential parameters to be discussed were separated. After making some choices, crossover and mutation operation to the parameters, the optimum individual can be found to seek for the shortest distance. With the online signature authentication examples, the matching comparison to the signature curves was conducted and some analysis of the algorithm was made. The experiment result proves the validity of the algorithm.

关 键 词：遗传算法 选择 交叉 变异 签名认证 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]