Two-step approach for real-time eye tracking with a new filtering technique

Head and face detection and eye tracking in realtime are the first steps for head gesture recognition and/or face expression recognition for a human-computer interaction interface. We propose a two-step approach for eye tracking in video streams. First, we detect or track a point between the eyes. For this task, we apply a special filter we proposed before. Once we detect the point between the eyes, it is fairly easy to locate the eyes, which are the two small darkest parts on each side of this point. Because detecting the point between the eyes is easier and more stable than directly detecting the eyes, the system can robustly track the eyes. We implement the system on a SGI O2 workstation. The video image size is 320×240 pixels. The system processes images at seven frames per second in the detection mode, and 13 frames per second in the tracking mode without any special hardware.