Fingerprint matching based on the genetic algorithm

被引：0

作者：

Hong, B. ^{[1
]}

Rong, G. ^{[1
]}

Huang, T. ^{[1
]}

机构：

[1] Dept. of Automat., Tsinghua Univ., Beijing 100084, China

来源：

Qinghua Daxue Xuebao/Journal of Tsinghua University | 2001年 / 41卷 / 03期

关键词：

Convergence of numerical methods - Feature extraction - Functions - Genetic algorithms;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

Fingerprint plays an important role in identity verification. A matching method based on genetic algorithm is proposed. Taking consideration of the characteristics of fingerprint matching, specific objective function and genetic operators are introduced to search the possible geometric relation between two fingerprints. Point pair relations are then determined according to these parameters. Thus similarity between the two fingerprints can be decided. Experiment results show that this method can find the correct feature point pairs under transformation and local distortion. This parameter based method convergence speed is 5 times faster than that of genetic algorithm based method.

引用

页码：93 / 96