Multi-modal Biometircs System Using Face and Signature

Abstract

In this paper, we propose a multi-modal biometrics system based on the face and signature recognition. For this, we suggest biometric algorithms for the face and signature recognition. First, we describe a fuzzy linear discriminant analysis (LDA) method for the face recognition. It is an expanded version of the Fisherface method using the fuzzy logic which assigns fuzzy membership to the LDA feature values. On the other hand, the signature recognition has the problem that its performance is often deteriorated by signature variation from various factors. Therefore, we propose a robust online signature recognition method using LDA and so-called Partition Peak Points (PPP) matching technique. Finally, we propose a fusion method for multi-modal biometrics based on the support vector machine. From the various experiments, we find that the proposed method renders higher recognition rates comparing with the single biometric cases under various situations.