Robust Representation of 3d Faces for Recognition

Automatic face recognition is becoming increasingly important due to the security applications derived from it. Although the face recognition problem has focused on 2D images, recently, due to the proliferation of 3D scanning hardware, 3D face recognition has become a feasible application. This 3D approach do not use the colour of the faces, so, when it is compared to the more traditional 2D approach, has the main advantages of being robust under lighting variations and also of providing more relevant information. In this paper we present a new 3D face model based on curvature properties of the face surface. As will be presented, our system is able to detect the subset of characteristics of the face with higher discrimination power among a large set of them. The robustness of the model is tested by comparing recognition rates using both controlled and non-controlled environments regarding facial expressions and face rotations. The difference between the recognition rate of the two environments of only 5% proves that the model has a high degree of robustness against pose and facial expressions and that is robust enough to implement facial recognition applications, which can achieve up to 91% correct recognition rate.