Sparse Bayesian regression for head pose estimation

This paper presents a high performance head pose estimation system based on the newly-proposed sparse Bayesian regression technique (Relevance Vector Machine, RVM) and sparse representation of facial patterns. In our system, after localizing 20 key facial points, sparse features of these points are extracted to represent facial property, and then RVM is utilized to learn the relation between the sparse representation and yaw and pitch angle. Because RVM requires only a very few kernel functions, it can guarantee better generalization, faster speed and less memory in a practical implementation. To thoroughly evaluate the performance of our system, we compare it with conventional methods such as CCA, Kernel CCA, SVR on a large database; In experiments, we also investigate the influence of the facial points localization error on pose estimation by using manually labelled results and automatically localized results separately, and the influence of different features on pose estimation such as geometrical features and texture features. These experimental results demonstrate that our system can estimate face pose more accurately, robustly and fast than those based on conventional methods.