CapRe: a gaze tracking system in man-machine interaction

We present a real-time camera-based system designed for gaze tracking focused on human-computer communication. We aim to equip computer systems with a tool which can provide visual information about the user. This tool must satisfy interaction constraints and not intrusive. Therefore, we use a CCD camera placed between the keyboard and the screen. The system detects the user presence, locates his position and then tracks his face, nose and both eyes. The detection is performed by combining image processing techniques and pattern recognition methods.