Joint features classifier with genetic set for undersampled face recognition

Abstract

Face recognition with limited training samples is a very difficult task. Especially in face recognition featuring one training image per individual, it even seems to be impossible to enable a superb accuracy. In this paper, we present a novel joint features classification approach with an external generic set for face recognition. The presented scheme leverages two representations based on Gabor feature and local Gabor binary patterns (LGBP) feature. Firstly, Gabor feature-based representation with an external generic set and LGBP feature-based representation with an external generic set are obtained independently. Then a weighted score level fusion scheme is adopted to automatically combine Gabor feature and LGBP feature, and to output the final decision. Three metrics, i.e., recognition rate, stability and execution time, are investigated in our evaluation of the performance of the presented method. The comprehensive experimental results on three large face databases (i.e., AR, FERET and WLF) demonstrated that the presented approach can always achieve very satisfactory accuracy and stability and that it is computationally tractable.