A Rapid Webcam-based Eye Tracking Method for Human Computer Interaction

This study proposes a rapid eye tracking method, to respond to a situation that require a high processing speed but less accuracy. Unlike other studies, this study uses a webcam with a low resolution of 640 x 480, which decreased the cost of devices considerably. We also developed the corresponding algorithm to suit the low-quality image. We use an efficient algorithm to detect the pupils which is based on color intensity change to decrease the calculation load. The processing speed exceeds the requirement of eye tracking for saccade eyeball movement. The result of experiment shows that the proposed method is a fast and low-cost method for eye tracking.