Scalable Webcam Eye Tracking by Learning from User Interactions.

Eye tracking systems are commonly used in a variety of research domains, but cost thousands of dollars. In my thesis I investigate a new approach to enable eye tracking for common webcams. The aim is to provide a natural experience to everyday users that are not restricted to laboratories and highly controlled studies. The accuracy of eye tracking webcams will be improved by user interactions which continuously calibrate the eye tracker during regular usage. Eye tracking can become a reality for many potential applications such as large-scale naturalistic user studies, online gaming, or enabling people to perform hands-free navigation of websites.