TY - GEN
T1 - Three factor scheme for biometric-based cryptographic key regeneration using iris
AU - Kanade, Sanjay
AU - Camara, Danielle
AU - Krichen, Emine
AU - Petrovska-Delacrétaz, Dijana
AU - Dorizzi, Bernadette
PY - 2008/12/1
Y1 - 2008/12/1
N2 - In this paper we propose a three factor (smart card, iris code and password) scheme for cryptographic key regeneration based on fuzzy sketches idea which handles biometric variability with error correcting codes. Because errors in iris codes have mixed nature (random and burst errors), concatenated Hadamard and Reed-Solomon codes are used in this work. Hadamard codes can correct up to 25% errors but experiments showed that it is necessary to increase this capacity. In order to correct this higher amount of errors, a zero padding scheme is introduced. In addition, a user specific iris code shuffling key is used which increases the separation between genuine and impostor Hamming distance distributions, providing better separability between genuine users and impostors. We succeeded in regenerating a 198-bit key with estimated entropy of 83 bits on the NIST-ICE database at 0.055% False Acceptance Rate (FAR) and 1.04% False Rejection Rate (FRR).
AB - In this paper we propose a three factor (smart card, iris code and password) scheme for cryptographic key regeneration based on fuzzy sketches idea which handles biometric variability with error correcting codes. Because errors in iris codes have mixed nature (random and burst errors), concatenated Hadamard and Reed-Solomon codes are used in this work. Hadamard codes can correct up to 25% errors but experiments showed that it is necessary to increase this capacity. In order to correct this higher amount of errors, a zero padding scheme is introduced. In addition, a user specific iris code shuffling key is used which increases the separation between genuine and impostor Hamming distance distributions, providing better separability between genuine users and impostors. We succeeded in regenerating a 198-bit key with estimated entropy of 83 bits on the NIST-ICE database at 0.055% False Acceptance Rate (FAR) and 1.04% False Rejection Rate (FRR).
UR - https://www.scopus.com/pages/publications/56749164763
U2 - 10.1109/BSYM.2008.4655523
DO - 10.1109/BSYM.2008.4655523
M3 - Conference contribution
AN - SCOPUS:56749164763
SN - 9781424425679
T3 - 2008 Biometrics Symposium, BSYM
SP - 59
EP - 64
BT - 2008 Biometrics Symposium, BSYM
T2 - 2008 Biometrics Symposium, BSYM
Y2 - 23 September 2008 through 25 September 2008
ER -