P2CA: How Much Face Information is Needed?

Multimodal 2D+3D face biometrics commonly report that performance improves relative to that of a single modality. Complete 2D and 3D data can be available during training because they are acquired in a controlled scenario. However, in the evaluation scenario, only partial 2D and 3D data can be acquired and hence available for recognition. In this paper we present experimental results that determine how partial data contribute to the task of recognition using partial principal component analysis (P²CA) algorithm in a multimodal scheme. From our results it seems that discrimination power on individuals is ascribed to different regions of the face if we consider 2D or 3D data.