Abstract

Sparse representation techniques for robust face recognition have been widely studied in the past several years. Recently face recogni- tion with simultaneous misalignment, occlusion and other variations has achieved interesting results via robust alignment by sparse representa- tion (RASR). In RASR, the best alignment of a testing sample is sought sub ject by sub ject in the database. However, such an exhaustive search strategy can make the time complexity of RASR prohibitive in large-scale face databases. In this paper, we propose a novel scheme, namely mis- alignment robust representation (MRR), by representing the misaligned testing sample in the transformed face space spanned by all sub jects. The MRR seeks the best alignment via a two-step optimization with a coarse-to-fine search strategy, which needs only two deformation-recovery operations. Extensive experiments on representative face databases show that MRR has almost the same accuracy as RASR in various face recog- nition and verification tasks but it runs tens to hundreds of times faster than RASR. The running time of MRR is less than 1 second in the large-scale Multi-PIE face database, demonstrating its great potential for real-time face recognition.