Appearance based user-independent gaze estimation

Abstract

An ideal gaze user interface should be able to accurately estimates the user's gaze direction in a non-intrusive setting. Most studies on gaze estimation focus on the accuracy of the estimation results, imposing important constraints on the user such as no head movement, intrusive head mount setting and repetitive calibration process. Due to these limitations, most graphic user interfaces (GUIs) are reluctant to include gaze as an input modality. We envision user-independent gaze detectors for user computer interaction that do not impose any constraints on the users. We believe the appearance of the eye pairs, which implicitly reveals head pose, provides conclusive information on the gaze direction. More importantly, the relative appearance changes in the eye pairs due to the different gaze direction should be consistent among different human subjects. We collected a multimodal corpus (MSP-GAZE) to study and evaluate user independent, appearance based gaze estimation approaches. This corpus considers important factors that affect the appearance based gaze estimation: the individual difference, the head movement, and the distance between the user and the interface's screen. Using this database, our initial study focused on the eye pair appearance eigenspace approach, where the projections into the eye appearance eigenspace basis are used to build regression models to estimate the gaze position. We compare the results between user dependent (training and testing on the same subject) and user independent (testing subject is not included in the training data) models. As expected, due to the individual differences between subjects, the performance decreases when the models are trained without data from the target user. The study aims to reduce the gap between user dependent and user independent conditions.