Robust Real-Time Face Tracking and Gesture Recognition
Robust Real-Time Face Tracking and Gesture Recognition
复制标题
强大的实时面部跟踪和手势识别
DOI：
--
复制
发表时间：
1997
期刊：
影响因子：
--
通讯作者：
A. Zelinsky
中科院分区：
文献类型：
--
作者：
J. Heizmann;A. Zelinsky
人们自然而然地通过面部手势来表达自己。我们已经实现了一个界面，可以在实时(30赫兹)下稳健地跟踪人的面部特征，并且不需要艺术人工制品，如特殊的I L光照或面部化妆。即使特征被遮挡，在特征重新出现在图像中之后，系统也能够在几帧内恢复跟踪。在此容错人脸跟踪器的基础上，我们实现了真正的手势识别，能够区分从“是”、“否”、“可能是”到眨眼、眨眼和“睡着”等12种不同的手势。
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".