Finger Multi-biometric Cryptosystem using Feature-Level Fusion
Li Lu, Jialiang Peng · International Journal of Signal Processing Image Processing and Pattern Recognition · 2014
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 featurelevel fusion for finger multi-biometric cryptosystem with respect to their impact on security and recognition accuracy.The comparative experimental results ascertain that finger multibiometric cryptosystem outperforms the uni-biometric counterparts in terms of verification performance and template security.