北京交通大学学报2011，Vol.35Issue(2)：8-13,6.
基于多特征描述的指横纹识别
Knuckleprint authentication using multiple representations
摘要
Abstract
A novel knuckleprint authentication method is proposed by using multiple representations.Principle component analysis (PCA) features, 2D Gabor phase features and magnitude features are extracted for knuckleprint authentication. Fisher criterion based linear discrimination analysis (LDA) is used for match-score fusion, which can further improve the system performance. Experiments based on the database that contains 1 971 image samples from 98 individuals demonstrate that the high recognition accuracy and efficient performance can be achieved with the proposed algorithm. The recognition rate is 99.39％, and the half total error rate (HTER) is no more than 0.56％ and one match time consumption reaches 0.67 ms.关键词
指横纹/主成分分析/2D Gabor滤波/匹配分数融合Key words
knuckleprint/ principle component analysis/ 2D Gabor filter/ score-level fusion分类
信息技术与安全科学引用本文复制引用
张延强,孙冬梅,裘正定..基于多特征描述的指横纹识别[J].北京交通大学学报,2011,35(2):8-13,6.基金项目
国家自然科学基金资助项目(60773015) （60773015）
北京市自然科学基金资助项目(4102051) （4102051）
中央高校基本科研业务费专项资金资助(2009JBZ006) （2009JBZ006）
