ANALYSIS OF SPOOFING ROBUSTNESS IN A MULTIMODAL BIOMETRIC SYSTEM

Abstract

As modern means of communication upgrade in their potential and receptiveness, they instigate additional demands in terms of security. Biometric recognition is a new technology that has become the essence of an extensive array of highly secure identification and personal verification solutions. Unimodal biometric system suffers from inherent limitations of noise in sensor data, non universality of biometric trait, intra-class variations and unaccepted error rates. Multimodal biometric system overcome all these limitations by presenting multiple evidences of single biometric trait due to which spoofing of these simultaneously become more difficult for an imposter. In this paper, face and fingerprint are the two biometrics used to build multibiometric system. Here, fusion of two modalities is done at matching score level. An experimental result shows that the Multimodal biometric system is efficient compared to unimodal biometric system.