An Adaptive Algorithm for Eye-Gaze-Tracking-Device Calibration

Abstract

Eye-gaze tracking has been an important and interesting area of research for quite some time now. In laboratory experiments for psychological research, eye-gaze tracking constitutes a helpful tool to probe the perceptual or the cognitive processes of the subjects. In day-to-day applications, eye-gaze tracking can be used as a computer interface for both industrial and nonindustrial applications, which require hands-free installations. It can also be used to help disabled people to use computers for communication and for environmental control. This paper aims to develop a computer system to facilitate the study of visual scanning and eye fixation during image exploration. The system uses an infrared device to detect horizontal and vertical eye movements. This paper mainly focuses its attention on the calibration procedure that can be effectively utilized for correction of the nonlinearities in the oculomotor for the eyes of each individual subject. An adaptive calibration algorithm has been developed by employing a polynomial model. Several experiments have been carried out to demonstrate that the proposed approach is a rapid one and is accurate for the study of visual perception and recognition processes.