Multimodal Biometric System:- Fusion Of Face And Fingerprint Biometrics At Match Score Fusion Level

Abstract

Biometrics has developed to be one of the most relevant technologies used in Information Technology (IT) security. Unimodal biometric systems have a variety of problems which decreases the performance and accuracy of these system. One way to overcome the limitations of the unimodal biometric systems is through fusion to form a multimodal biometric system. Generally, biometric fusion is defined as the use of multiple types of biometric data or ways of processing the data to improve the performance of biometric systems. This paper proposes to develop a model for fusion of the face and fingerprint biometric at the match score fusion level. The face and fingerprint unimodal in the proposed model are built using scale invariant feature transform (SIFT) algorithm and the hamming distance to measure the distance between key points. To evaluate the performance of the multimodal system the FAR and FRR of the multimodal are compared along those of the individual unimodal systems. It has been established that the multimodal has a higher accuracy of 92.5% compared to the face unimodal system at 90% while the fingerprint unimodal system is at 82.5%.