A reference-based framework for pose invariant face recognition

While face recognition technology has made significant progress in recent years, practical pose invariant face recognition remains a challenge. This paper describes a reference-based framework for solving this problem. The similarity between a face image and a set of reference individuals defines the reference-based descriptor for a face image. Recognition is performed using the reference-based descriptors of probe and gallery images. The dimensionality of the face descriptor generated by the accompanying face recognition algorithm is reduced to the number of individuals in the reference set. The proposed framework is a generalization of previous recognition methods that use indirect similarity and reference-based descriptors. Results are shown on a combination of seven publicly available face databases (LFW, FEI, RaFD, FERET, FacePix, CMU-PIE, and Multi-PIE). The proposed approach achieves good accuracy as compared to popular state-of-the-art algorithms, and it is computationally efficient.