Real-time Facial Features Tracker Based on Topologic Information and Similarity Analysis  

作　　者：LIANG Ronghua FANG Jinglong MAO Jianfei ZHOU Delong 

机构地区：[1]College of Information Engineering, Zhejiang University of Technology, Hangzhou 310014, China [2]State Key Laboratory of Audiovisual Information Processing, Peking University, Beijing 100871, China [3]Institute of Graphics and Image, Hangzhou Dianzi Universtity, Hangzhou 310018, China

出　　处：《Chinese Journal of Electronics》2008年第2期205-209,共5页电子学报（英文版）

基　　金：This work is partly supported by the National Natural Science Foundation of China （No.60703002 and No.60572077）, and Zhejiang Provincial Natural Science Foundation of China （No.Y105206）.

摘　　要：Real-time facial features tracking of video can be widely used in face recognition, video surveillance, face animation and Human-Computer Interaction. We present a fast tracking approach, and our method only requires simple device---a digital camera and a PC, and our approach needs limited user interactions. We first use eigenface and topologic information to detect the position and the size of face from the first frame, and facial features of the first frame are acquired automatically. The successor of the first frame can be tracked by using similarity analysis and motion estimation, the automatic tracker of first frame is also used to resolve the features occlusion problem when the tracked features disappear which is a difficult issue for tracking. Experimental results show that our approach is easily implemented, and the analysis also shows the high robustness of our method.

关 键 词：Topologic information Similarity analysis Motion estimation Eigenface. 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]