Three-dimensional face analysis via new geometrical descriptors

3D face was recently investigated for various applications, including biometrics and diagnosis. Describing facial surface, i.e. how it bends and which kinds of patches is composed by, is the aim of studies in Face Analysis, whose ultimate goal is to identify which features could be extracted from three-dimensional faces depending on the application. In this study, we propose 54 novel geometrical descriptors for Face Analysis. They are generated by composing primary geometrical descriptors such as mean, Gaussian, principal curvatures, shape index, curvedness, and the coefficients of the fundamental forms. The new descriptors were mapped on 217 facial depth maps and analysed in terms of descriptiveness of facial shape and exploitability for localizing landmark points. Automatic landmark extraction stands as the final aim of this analysis. Results showed that the newly generated descriptors are suitable to 3D face description and to support landmark localization procedures.