TY - GEN
T1 - Obtaining cryptographic keys using feature level fusion of iris and face biometrics for secure user authentication
AU - Kanade, Sanjay
AU - Petrovska-Delacrétaz, Dijana
AU - Dorizzi, Bernadette
PY - 2010/9/17
Y1 - 2010/9/17
N2 - Biometric traits are permanently associated with a user. Though this is an advantage from identity verification point of view, if such biometric data is compromised, it cannot be replaced by a new one and becomes unusable in the system. This limitation can be overcome by combining biometrics with cryptographic techniques to induce revocability in biometric systems. In this paper, a multi-biometrics based cryptographic key regeneration scheme is proposed which combines information from iris and face to obtain a long cryptographic key having high entropy. The biometric information fusion is carried in feature domain using weighted feature level fusion technique. With the proposed system, we obtain 210-bit keys with 183-bit entropy (which is significantly higher than the 83-bit entropy obtained for iris), at a False Acceptance Rate of 0% and a False Rejection Rate of 0.91%.
AB - Biometric traits are permanently associated with a user. Though this is an advantage from identity verification point of view, if such biometric data is compromised, it cannot be replaced by a new one and becomes unusable in the system. This limitation can be overcome by combining biometrics with cryptographic techniques to induce revocability in biometric systems. In this paper, a multi-biometrics based cryptographic key regeneration scheme is proposed which combines information from iris and face to obtain a long cryptographic key having high entropy. The biometric information fusion is carried in feature domain using weighted feature level fusion technique. With the proposed system, we obtain 210-bit keys with 183-bit entropy (which is significantly higher than the 83-bit entropy obtained for iris), at a False Acceptance Rate of 0% and a False Rejection Rate of 0.91%.
U2 - 10.1109/CVPRW.2010.5544618
DO - 10.1109/CVPRW.2010.5544618
M3 - Conference contribution
AN - SCOPUS:77956519688
SN - 9781424470297
T3 - 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops, CVPRW 2010
SP - 138
EP - 145
BT - 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops, CVPRW 2010
T2 - 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops, CVPRW 2010
Y2 - 13 June 2010 through 18 June 2010
ER -