An Incremental Learning Method for Unconstrained Gaze Estimation

This paper presents an online learning algorithm for appearancebased gaze estimation that allows free head movement in a casual desktop environment. Our method avoids the lengthy calibration stage using an incremental learning approach. Our system keeps running as a background process on the desktop PC and continuously updates the estimation parameters by taking user’s operations on the PC monitor as input. To handle free head movement of a user, we propose a pose-based clustering approach that efficiently extends an appearance manifold model to handle the large variations of the head pose. The effectiveness of the proposed method is validated by quantitative performance evaluation with three users.