A Score-Level Fusion Method for Protecting Fingerprint and Palmprint Templates

Today computers are in virtually everything we touch. With this increased use of computers, there is a need for secure authentication of the users using their biometric characteristics. If a biometric template is lost/stolen, it is lost permanently and can’t be reissued like traditional authentication systems using a password or token. Taking two of the well-known traits, i.e., fingerprint and palmprint into consideration, a multi-biometric system is built. Binary vectors for each of the biometric traits are constructed, calculated the match score of both of them individually then we applied score-level fusion using T-operators. As compared to the previous multi-biometric schemes, the analysis of the results of the experiments provides us with good accuracy, i.e., an EER of 6.58% was reported which shows the validity of the proposed method.