Eye-controlled mouse based on eye-gaze tracking using one camera

An eye-gaze tracking method, which can make this system be adaptive to external lighting changes and to the user's head movements, was put forward to alleviate the restriction on the user's head movements. In this paper, our interest is concentrated mainly on the development of the algorithms: the thresholds for extraction of the pupil and corneal reflection were automated. On the basis of the brightness, gradient of the edge points of the pupil and the smoothness of the pupil boundary, the edge points could be obtained by a ID line search. A solution to cope with eyelashes, eyelids and glints in the pupil area was also discussed. A new randomized method of ellipse fitting was proposed. The gaze direction was determined by the relationship between the position of the pupil center and the corneal reflections. The gaze point on the computer screen was derived and the mouse position could be determined through the eye. The accuracy of the position of the cursor on the screen is within 40 pixels.