Abstract: In automatic face recognition(AFR) applications,input images typically present multiple types of variations on expression,resolution and pose.Existing approaches attempt to seek a common feature space shared by these variations through linear or local linear mappings.We used deep networks stacked by restricted Boltzmann machines to discover intrinsic non-linear representations of these variations.Deep learning can provide insight into how high-dimensional data are organized in a lower dimensional feature space and it also improves the performance of classification and recognition.In the meantime,we realized a supervised regression layer on the top of the network so that both feature extraction and recognition can be achieved in a unified deep framework.For the pre-training phrase,the whole network is initialized by training set including different poses with various expressions under high resolution(HR) and low resolution(LR).For the fine-tuning phrase,the parameter space is adjusted by the errors between the output of network and the labels via standard back propagation.For the test phrase,a profile face image from Probe is chosen randomly,then the feature vector in the subspace is gained.Compared with all of the vectors in the Gallery set,we determined the identity of images by the nearest neighborhood.We performed the extensive experiments on CMU-PIE facial database that presents rich expressions and wide range pose variations.The experiments show the superior recognition rate of our approach over the state-of-the-art linear(or locally linear) methods.

Key words: Face recognition,Deep networks,Low resolution,Pose,Expression