期刊名称：International Journal of Signal Processing, Image Processing and Pattern Recognition
印刷版ISSN：2005-4254
出版年度：2014
卷号：7
期号：3
页码：223-236
DOI：10.14257/ijsip.2014.7.3.18
出版社：SERSC
摘要：In this paper, we propose a new finger multi-biometric cryptosystem using feature-level fusion to simultaneously protect multiple templates of fingerprint, finger vein, finger knuckle print and finger shape traits as a single secure sketch. We theoretically analyze the feature- level fusion for finger multi-biometric cryptosystem with respect to their impact on security and recognition accuracy. The comparative experimental results ascertain that finger multi- biometric cryptosystem outperforms the uni-biometric counterparts in terms of verification performance and template security.
