Face verification using sparse representation techniques

We present a novel method of face verification which is based on the concept of sparse representation of signals. The sparse representation techniques are used in both feature extraction and classification steps. The proposed method is relatively invariant to changes in imaging conditions such as illumination variations. This is due to the characteristics of the sparse sampling method. Our experimental studies on the XM2VTS and XM2VTS-DARK datasets demonstrate that the proposed method improves the performance of the verification system.