A secure multimodal authentication system based on chaos cryptography and fuzzy fusion of iris and face

The rising attention of terrorism violations approve that applicable and accurate systems is more needed. The saved or transmitted templates increase the chance of compromise the privacy or identity breach. Due to the high accuracy level of iris identifier and the convenience and passive recognition properties of face modality, the proposed fuzzy logic fusion strategy could allow an efficient and accurate identification procedure for high-security critical applications. Towards a secure transmission and saving, a secure sketch of biometric data will be rescinded and reissued at diverse attacks points. Dissimilar to the classical systems, the introduced chaotic biometric protection system based on Henon and 2D Logistic maps could offer an imperious and speedy ciphering procedure against typical algorithms. Moreover, it could present good key sensitive properties with large key space and more robust to statistical and differential attacks. Also, being not invasive to the identification procedure, the fuzzy logic decision which taken at the matching score and the decision levels after normalization of both iris and face scores using the min-max rule introduced false accept rate of 0.0345%, and false reject rate 0.001% respectively for matching the decrypted templates.