Personal Authentication Using Relevance Vector Machine (RVM) for Biometric Match Score Fusion

In this paper, the authors propose a personal authentication system using a combination of both face and fingerprint features. In the proposed system, face and fingerprint features are extracted by Zernike Moment (ZM), the extracted features are classified by Relevance Vector Machine (RVM), the generated matching scores are fused using sum rule. Experimental results on the FVC2004 DB4 and ORL databases show that RVM provides better accuracy compared to unit face or fingerprint recognition and existing fusion algorithms. With respect to SVM fusion, it is observed that, the accuracy of RVM and SVM are comparable, however, the time for RVM fusion is significantly reduced.