Masked projection for 3D face recognition under occlusion

Nese Alyüz, Berk Gökberk, Lale Akarun

Abstract: With advances in sensor technology, three dimensional (3D) face has become an emerging biometric modality, preferred especially in high security applications. However, dealing with facial occlusions is a great challenge, which should be handled to enable applicability to fully automatic security systems. In this paper, we propose a technique to deal with occlusions at the classification stage: A masking strategy, which we call masked projection, is proposed to enable the use of subspace analysis techniques with incomplete data. Furthermore, a regional scheme suitable for occlusion handling is incorporated in classification to improve the overall results. Experimental results on two databases with realistic facial occlusions, namely, the Bosphorus and the UMB-DB, confirm that the masked subspace analysis offer an occlusion robust face recognition system.