Improving fusion with optimal weight selection in Face Recognition

Face recognition has a large number of applications, including security/counterterrorism, person identification, Internet communications, E-commerce, and computer entertainment. Although research in automatic face recognition has been conducted since the 1960s, there exist research challenges in its practical application in the terms of performance accuracy, which deteriorates significantly with changes in illumination, pose, expression and occlusions. However, these inherent limitations can be potentially alleviated by fusing biometric information based on multiple facial features. Following this vision, the work presented here offers three contributions. Firstly, we present a Face Recognition System, where diverse biometrics features such as total face, eyes, nose, mouth, etc are extracted from the face image. Secondly, we analyse a number of approaches for combining the aforementioned information at matching score level. Thirdly, we proposed a new approach, based on a recently proposed optimisation technique, the Bees Algorithm, to determine the optimal weight parameters to enhance the performance of the fusion system. Experiments on the CASIA and ORL face databases indicate that the proposed method achieves consistently high recognition rates, compared to traditional FR approaches, such as the Eigenfaces, Fisherfaces, and D-LDA methods.