Image Fusion Techniques for Face Recognition

Abstract

The traditional matrix-based feature extraction methods that have been widely used in face recognition. The efficient management and combination of uncertain and conflicting sources of information are of great importance for the development of reliable information fusion systems. Biometric fusion consolidates the output of multiple biometric classifiers to make a decision about the identity of an individual. In this paper, a dynamic selection algorithm is designed to optimize both verification accuracy and computational cost. The proposed algorithm unifies the constituent classifiers and fusion schemes. In this method, a novel score-level fusion strategy based on quality measures for multimodal bio-metric authentication is presented and the fusion function is adapted every time.