Robust Real-Time Face Tracking and Gesture Recognition
Abstract
People natural ly express themselves through facial gestures. We have implemented an interface that tracks a person's facial features robustly in real t ime (30Hz) and does not require art i f icial artifacts such as special i l lumination or facial makeup. Even if features become occluded the system is capable of recovering tracking in a couple of frames after the features reappear in the image. Based on this fault tolerant face tracker we have implemented realt ime gesture recognition capable of distinguish 12 different gestures ranging from yes, no and may be to winks, blinks and asleep.
Cite
Text
Heizmann and Zelinsky. "Robust Real-Time Face Tracking and Gesture Recognition." International Joint Conference on Artificial Intelligence, 1997.Markdown
[Heizmann and Zelinsky. "Robust Real-Time Face Tracking and Gesture Recognition." International Joint Conference on Artificial Intelligence, 1997.](https://mlanthology.org/ijcai/1997/heizmann1997ijcai-robust/)BibTeX
@inproceedings{heizmann1997ijcai-robust,
title = {{Robust Real-Time Face Tracking and Gesture Recognition}},
author = {Heizmann, J. and Zelinsky, Alexander},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {1997},
pages = {1525-1530},
url = {https://mlanthology.org/ijcai/1997/heizmann1997ijcai-robust/}
}