Gaze estimation using morphable models

The paper presents preliminary work on a novel technique for gaze estimation from a single image. The goal is to provide rough estimates of where a person is looking at a monitor. Many applications for human-computer interaction are possible for such a technique. The approach uses the morphable model framework of Jones and Poggio (1998) to model a region around the eyes of a person. After matching this model to an input image of a person's eye region, the resulting model parameters are sent to a neural network which approximates the screen coordinates being viewed. The system is user independent and can handle changes in both head orientation and iris location. Currently the system is not real-time. Future work will focus on improving the speed of the system.