Face recognition is among the most challenging areas of research in Computer Vision and Pattern Recognition. The early approaches, based on iconic representations and image filtering techniques, have been recently surpassed by new algorithms based on the extraction of distinctive features, and the adoption of powerful descriptors capturing essential information of the face. In this paper several issues related to the adoption of a space variant descriptor are discussed. In particular, it is shown that, combining the extraction of salient points and space-variant descriptors, a novel and efficient method for face recognition and authentication can be implemented. Preliminary experimental results obtained from both the FERET and the BANCA databases are reported, demonstrating the large-scale applicability of the devised technique.