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.
This work presents an algorithm for efficient shape coding using cubic B-splines. In the framework of object-based layered coding of image sequences, shape information is essential for content-based access to video objects, and its efficient encoding needs to be investigated. We present a rate and distortion controlled algorithm for vide object shape approximation by variable number of cubic B-spline segments and motion compensated inter-frame coding of B-spline control points. Rate-distortion efficiency of the proposed algorithm is compared to MPEG-4 context arithmetic encoding and two stage motion compensated chain coding.