Robust methods for head orientation estimation and user identification based on HOG and codebook

We propose a robust method of estimating head orientation based on HOG. The proposed method is able to estimate head orientation with a camera even though when a user is not facing the camera. With this method, a head orientation can be estimated precisely in all three axes: roll, yaw, pitch. Furthermore, a simple and robust user identification method is composed by using the results of the Approximate Nearest Neighbor Search. Finally, we combine these head orientation estimation and user identification methods to apply them into real applications to provide useful services to users in any intelligent environment.