A study of pupil detection and tracking by image processing techniques for a human eye-computer interaction system

Abstract

The pupil detection and tracking is an important step for developing a human-computer interaction system. To develop a human eye-computer interaction system, we examine pupil detection and tracking by image processing techniques. In the image processing techniques, the illumination directly influences the image quality in general. If influences of illumination is little, we can obtain an image of good image quality. The subsequent image processing techniques are expected almost to succeed. In this paper, in order to avoid the influences of illumination, we have tried to combine the hardware constitution of an infrared light-emitting diode (LED) light, a sensitive infrared camera, and an infrared (IR) filter. In the experiment with this hardware constitution, we investigate the effects of the pupil detection and tracking by image processing techniques for a human eye-computer interaction system.