In this paper, we propose a novel learned visual codebook (LVC) for 3D face recognition. In our method, we first extract intrinsic discriminative information embedded in 3D faces...
—When reconstructing a specific type or class of object using stereo, we can leverage prior knowledge of the shape of that type of object. A popular class of object to reconstru...
Conventional subspace learning-based face recognition aims to attain low recognition errors and assumes same loss from all misclassifications. In many real-world face recognition...