Patch-based locality-enhanced collaborative representation for face recognition

In the field of face recognition, the small sample size (SSS) problem and non-ideal situations of facial images are recognised as two of the most challenging issues. Recently, Zhu et al. proposed a patch-based collaborative representation (PCRC) method which showed good performance for the SSS and the single sample per person problems; and Peng et al. proposed a locality-constrained collaborative representation (LCCR) method which achieved high robustness for face recognition in non-ideal situations. Inspired by the methods proposed in PCRC and LCCR, this study proposes a patch-based locality-enhanced collaborative representation (PLECR) method to combine and enhance the advantages of both PCRC and LCCR. The PLECR and several related methods are implemented on AR, face recognition technology and extended Yale B databases; and the extensive numerical results show that PLECR is more efficient among these methods for the SSS problem in non-ideal situations, especially for the SSS problem with occlusions.