A Real-time Face Tracker
Abstract
We present a real-time face tracker in this paper. The system has achieved a rate of 30+ frames/second using an HP-9000 workstation with a framegrabber and a Canon VC-C1 cam era. It can track a person's face while the person moves freely (e.g., walks, jumps, sits down and stands up) in a room. Three types of models have been employed in developing the sys tem. First, we present a stochastic model to characterize skin-color distributions of human faces. The information provided by the model is sufficient for tracking a human face in various poses and views. This model is adaptable to differ ent people and different lighting conditions in real-time. Sec ond, a motion model is used to estimate image motion and to predict search window. Third, a camera model is used to pre dict and to compensate for camera motion. The system can be applied to tele-conferencing and many HCI applications including lip-reading and gaze tracking. The principle in de veloping this system can be extended to other tracking prob lems such as tracking the human hand.
BibTeX
@workshop{Yang-1996-16280,author = {Jie Yang and Alex Waibel},
title = {A Real-time Face Tracker},
booktitle = {Proceedings of 3rd IEEE Workshop on Applications of Computer Vision (WACV '96)},
year = {1996},
month = {December},
pages = {142 - 147},
}