Eye-gaze determination of user intent at the computer interface

Abstract

Abstract Determination of user intent at the computer interface through eye-gaze monitoring can significantly aid applications for the disabled, as well as telerobotics and process control interfaces. Whereas current eye-gaze control applications are limited to object selection and x/y gazepoint tracking, a methodology was developed here to discriminate a more Abstract interface operation: zooming-in or out. This methodology first collects samples of eye-gaze location looking at controlled stimuli, at 30 Hz, just prior to a user’s decision to zoom. The sample is broken into data frames, or temporal snapshots. Within a data frame, all spatial samples are connected into a minimum spanning tree, then clustered, according to user defined parameters. Each cluster is mapped to one in the prior data frame, and statistics are computed from each cluster. These characteristics include cluster size, position, and pupil size. A multiple discriminant analysis uses these statistics both within and between data frames to formulate optimal rules for assigning the observations into zoom-in, zoom- out, or no zoom conditions. The statistical procedure effectively generates heuristics for future assignments, based upon these variables. Future work will enhance the accuracy and precision of the modeling technique, and will empirically test users in controlled experiments.