One factor cancellable fingerprint scheme based on novel minimum hash signature and secure extended feature vector

To solve the problems of privacy preserving and biometric template protection, the one-factor fingerprint biometric authentication scheme based on Novel Minimum Hash Signature (NMHS) and Secure Extended Feature Vector (SEFV) is proposed to generate Pseudo Identifiers. The NMHS algorithm is designed to generate hash codes using the symbols ‘1’ and ‘0’ of the binary fingerprint template and the XOR operation in the hashing process is used to improve the stable of the performance. Then, XOR operation is carried out between the hash codes and the random binary string to get the encryption string to form the fuzzy vault. Furtherly, to improves the security of fingerprint template, the SEFV hash is used to get the Pseudo Identifier. During authentication stage, the Pseudo Identifier is generated with genuine queries using the auxiliary data providing by the system and then is employed to classify using the hamming distance. To improve the performance during the authentication stage, the matching score of ‘1’ and ‘0’ are fused by a novel fusion rule. Experimental results demonstrate that the proposed scheme is also shown satisfy irreversibility, unlinkability and revocability template protection criteria while preserving the favorable authentication performance on benchmark FVC2002 and FVC2004 fingerprint databases. The security and privacy attacks such as the Brute-force attack, False accept attack and Birthday attack are also analyzed in theory in the experiments.