US tab


We propose, as an alternative to current face recognition paradigms, an algorithm using reweighted l₂ minimization, whose recognition rates are not only comparable to the random projection using l₁ minimization compressive sensing method of Yang et al [5], but also robust to occlusion. Through numerical experiments, reweighted l₂mirrors the l₁solution [1] even with occlusion. Moreover, we present a theoretical analysis on the convergence of the proposed l₂approach.

KEY WORDS: reweighted, minimization, face recognition, implementation

Introduction >>