A new approach for face recognition under makeup changes

In this paper, we target a recent challenging problem raised in image processing area: face verification in the presence of facial makeup. To the best of our knowledge, very few works have been proposed to solve this problem. In this paper, we propose a novel face verification scheme. Random subspace is applied to get multiple correlation spaces. Similarity measures among face images are calculated based on correlation subspaces. In addition, performance on different facial parts is evaluated. Experiments on an unconstrained dataset demonstrate the effectiveness of the proposed approach.