Palmprint Verification Based on Genetic Algorithm

摘要：

This paper proposes a novel idea based featureselection in the verification system of palmprint,which can realize the specific feature selection fordifferent user using genetic algorithm(GA).In thestage of enrollment,discrete wavelet transforms (DWT)and statistical methods are first used for featureextraction.Then GA is employed for feature selection,which means that each user has a specific featureindex and verification modality.In the stage ofverification,according to the feature index,theselected features are input to the related supportvector machine(SVM)for classification.We test theproposed method on Hong Kong PolytechnicUniversity Palmprint Database. Through thecomparison,the experimental results show that ourproposed method is effective and can reach highperformance.

作者: Yan Jin Miao Qi Yinghua Lu Yao Fu Jun Kong

作者单位: Changchun Medical College,Jilin Province,China Computer School,Northeast Normal University,jilin Province,China Key Laboratory for Applied Statisti Computer School,Northeast Normal University,jilin Province,China

会议类型: 国际会议

会议名称: 2008 3rd International Conference on Intelligent System and Knowledge Engineering(第三届智能系统与知识工程国际会议)(ISKE 2008)

会议地点: 厦门

会议语种:英文

页码: 471-475

在线出版日期: 2008-11-17（万方平台首次上网日期，不代表论文的发表时间）