A 3D face recognition system using curvature-based detection and holistic multimodal classification

We present here a fully automated system for face detection and recognition. In a scene acquired by a three-dimensional laser scanner the system can detect the presence of human faces; the faces detected are registered in a canonical position and then recognized. Both the 3D and 2D (i.e. pictorial) information provided by the scanner are exploited. The 3D representation is used to detect the presence of faces and normalize them. In the recognition step 3D and 2D information are independently analyzed, producing two different scores that are then combined to compute the output of the system.