Non-Intrusive Gaze Tracking Using Artificial Neural Networks

Abstract

We have developed an artificial neural network based gaze tracking, system which can be customized to individual users. A three layer feed forward network, trained with standard error back propagation, is used to determine the position of a user's gaze from the appearance of the user's eye. Unlike other gaze trackers. Which normally require the user to wear cumbersome headgear, or to use a chin rest to ensure head mobility our system is entirely non-intrusive. Currently, the best intrusive gaze tracking systems are accurate to approximately O.75 degrees. In our experiments, we have been able to achieve an accuracy of 1.5 degrees, while allowing head mobility. In its current implementation, our system at 15 hz. In this paper we present an empirical analysis of the performance of a large number of artificial neural network architectures for this task. Suggestions for further explorations for neurally based gaze trackers are presented, and are related to other similar artificial neural network applications such as autonomous road following.