Simple shape space for 3D face registration
Andrej Košir, Igor Perkon, Drago Bračun, Jurij Franc Tasič, Janez Možina · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2009
Three dimensional (3D) face recognition is a topic getting increasing interest in biometric applications. In our research framework we developed a laser scanner that provides 3D cloud information and texture data. In a user scenario with cooperative subjects with indoor light conditions, we address three problems of 3D face biometrics: the face registration, the formulation of a shape space together with a special designed gradient algorithm and the impact of initial approximation to the convergence of a registration algorithm. By defining the face registration as a problem of aligning a 3D data cloud with a predefined reference template, we solve the registration problem with a second order gradient algorithm working on a shape space designed for reducing the computational complexity of the method.