基于屋脊滤波的指横纹认证
首发时间:2010-01-19
摘要:提出了基于屋脊边缘滤波的指横纹定位与提取算法,采用基于归一化互相关方法对特征点进行匹配。在98个人1971幅图像的测试数据上表明,指横纹作为生物特征的普遍性和有效性。单模最优系统为无名指指横纹,EER为0.8778%;最差系统为小拇指指横纹,EER为2.0403%。采用fisher判别法融合四类指横纹,系统EER为0.2078%,达到了较高的安全级别。
For information in English, please click here
Inner Knuckleprint Verification based on Roof Edge Detect
Abstract:A novel biometric defined as “inner knuckleprint” is presented in this paper. Roof edge detecter is used for locating and extracting the inner knuckleprint. Normalized cross-correlation based feature matching and decision fusion scheme are integrated to implement a real-time verification system. The system is evaluated based on the database contains 1,853 image samples from 98 individuals. For single model , the equal error rate (EER) is 2.04% to the worst system ,while 0.8778% to the best one. Which indicates that the inner knuckleprints are reliable and universal as a biometric, and demonstrates the effectiveness of the proposed method.
Keywords: Inner knuckleprint Roof edge detect Normalized cross-correlation Score level decision fusion
论文图表:
引用
No.3921051281012638****
同行评议
共计0人参与
勘误表
基于屋脊滤波的指横纹认证
评论
全部评论0/1000