Feature Level Fusion Approach in Multimodal Biometric System Design: A Comparative Analysis of Feature Fusion Techniques in Multimodal Biometric Systems

Abstract

This paper discusses the fusion at feature extraction level for face and fingerprint biometrics. The proposed approach is based on the fusion of the two traits by extracting independent feature point sets from the two modalities, and making the two point sets compatible for concatenation. Moreover, to handle the ‘problem of curse of dimensionality’, the feature point sets are properly reduced in dimension. Different feature reduction techniques are implemented, prior and after the feature point sets fusion, and the results are duly recorded. Principal Component Analysis is used to reduce the dimensionality of facial images.