An Analytic Gabor Feedforward Network for Single-sample and Pose-invariant Face Recognition

Gabor magnitude is known to be among the most discriminative representations for face images due to its spacefrequency co-localization property. However, such property causes adverse effects even when the images are acquired under moderate head pose variations. To address this pose sensitivity issue as well as other moderate imaging variations, we propose an analytic Gabor feedforward network which can absorb such moderate changes. Essentially, the network works directly on the raw face images and produces directionally projected Gabor magnitude features at the hidden layer. Subsequently, several sets of magnitude features obtained from various orientations and scales are fused at the output layer for final classification decision. The network model is analytically trained using a single sample per identity. The obtained solution is globally optimal with respect to the classification total error rate. Our empirical experiments conducted on five face datasets (six subsets) from the public domain show encouraging results in terms of identification accuracy and computational efficiency.