Curse of mis-alignment in face recognition: problem and a novel mis-alignment learning solution

In this paper, we present the rarely concerned curse of mis-alignment problem in face recognition, and propose a novel mis-alignment learning solution. Mis-alignment problem is firstly empirically investigated through systematically evaluating Fisherface's sensitivity to mis-alignment on the FERET face database by perturbing the eye coordinates, which reveals that the imprecise localization of the facial landmarks abruptly degenerates the Fisherface system. We explicitly define this problem as curse of mis-alignment to highlight its graveness. We then analyze the sources of curse of mis-alignment and group the possible solutions into three categories: invariant features, mis-alignment modeling, and alignment retuning. And then we propose a set of measurement combining the recognition rate with the alignment error distribution to evaluate the overall performance of specific face recognition approach with its robustness against the mis-alignment considered. Finally, a novel mis-alignment learning method, named E-Fisherface, is proposed to reinforce the recognizer to model the mis-alignment variations. Experimental results have impressively indicated the effectiveness of the proposed E-Fisherface in tackling the curse of mis-alignment problem.