Konferans bildirisi Açık Erişim

3D Face Recognition Benchmarks on the Bosphorus Database with Focus on Facial Expressions

2008    Alyuz, Nese; Gokberk, Berk; Dibeklioglu, Hamdi; Savran, Arman; Salah, Albert Ali; Akarun, Lale; Sankur, Buelent

This paper presents all evaluation of several 3D face recognizers oil the Bosphorus database which was gathered for studies oil expression and pose invariant face analysis. We provide identification results of three 3D face recognition algorithms, namely generic face template based ICP approach, one-to-all ICP approach, and depth image-based Principal Component Analysis (PCA) method. All of these techniques treat faces globally and are usually accepted as baseline approaches. In addition, 2D texture classifiers are also incorporated in a fusion setting. Experimental results reveal that even though global shape classifiers achieve almost perfect identification in neutral-to-neutral comparisons, they are sub-optimal under extreme expression variations. We show that it is possible to boost the identification accuracy by focusing oil the rigid facial regions and by fusing complementary information coming from shape and texture modalities.