Non-contact Eye Gaze Estimation System using Robust Feature Extraction and Mapping of Corneal Reflections

The population with disabilities has risen remarkably during the past century. Especially, the disabled with two arms disability cannot manipulate devices by themselves. They suffer from operating computer using conventional interface devices such as joysticks or keyboards. In this paper, an eye gaze estimation system is proposed. The eye gaze estimation system is a system to estimate the eye-gaze direction of an user.The proposed system consisted of five IR LEDs and a CCD camera. The direction of the user’s eye gaze can be computed without computing the geometrical relation among the eye, the camera, and the monitor in 3D space. Our method is comparatively simple and fast. The disabled can manipulate a computer using this system. We will introduce our method and show experimental results. The experimental results will verify the feasibility of the proposed system as an interface for the disabled.