A Wavelet Domain Implementation of Sparse Representation Method for Face Recognition

Recently, a new discriminative sparse representation method for robust face recognition via l
₂
regularization (NDSRFR) was published. In this paper, a Wavelet domain (WDNDSRFR) is presented. In particular, the Two-Dimensional Discrete Wavelet Transform implementation is given and shown to considerably reduce the computational complexity and the storage requirements while maintaining the recognition accuracy of the NDSRFR. Extensive simulations were performed on five face databases, namely, ORL, YALE, FERET, Cropped AR, and Georgia Tech and the enhanced properties of the WDNDSRFR are confirmed as shown in the given sample results.