| Author: | Vera Bakic |
| Advisor: | Dr. George Stockman |
| Email: | bakicve1@cps.msu.edu; http://www.cps.msu.edu/ bakicve1 |
A non-intrusive real-time program is developed which detects the eyes and nose of a moving workstation user at a rate of between 10 and 30 Hertz. Based on the head pose in 2D, we determine where on the workstation screen the subject is looking. The user can make a selection by making certain face expression (eg. opening the mouth). In the long run, we can provide a system for controlling a computer using head movements and gaze direction. The program creates a base facility for other capabilities such as detecting facial gestures, creating face models, and normalizing for face recognition. A skin color model is used along with geometric knowledge about the face and weak assumptions about the lighting. Good results are reported over various conditions, including facial hair, 3D motion, clothing color, and use of eyeglasses. Good performance has been demonstrated with dozens of subjects on a low end SGI workstation with an eye-camera to acquire images. Our work is directed toward a general capability to detect and track a human face as it moves in a 3D workspace. Having achieved this capability, it can then be used to enable others. For example, knowing the approximate 3D head pose allows normalization for face recognition or for reduction of database search in the eigenface approaches to recognition. Or, 3D pose can be used directly for Human-Computer Interface (HCI) or for evaluation of how humans explore computer displays or virtual environments.
Return to Workshop Listing