%0 Journal Article
%T Edge Extraction of Face Images for Expression Analysis<br>一种适合于表情分析的人脸二值边缘图像的提取
%A SONG Jia-tao~
%A LIU Ji-lin~
%A CHI Zhe-ru~
%A WANG Wei~ ~ ~
%A <br>宋加涛
%A 刘济林
%A 池哲儒
%A 王蔚
%J 中国图象图形学报
%D 2004
%I 
%X Edge map is an important representation of human face image. It is of significance for automatic face image analysis. This paper presents a new method for the extraction of face image edges and a scheme for facial expression analysis based on the resulting binary edge images (BEI). Making use of the multi-resolution property of wavelet transform, the edge detection method includes two binarization steps and a noise removing step. Our method provides a robust solution to face image edge extraction, in particular, if changes of lighting conditions are encountered. Experimental results show that different components in a BEI are well separated and pixels of the same face component are connected well. Preliminary experimental results on facial expression analysis on the subsets of AR and Yale face databases show that recognition rates of above 93% can be achieved when our facial analysis scheme is used for recognizing four action units.
%K face image
%K edge extraction
%K binarization
%K noise removing
%K facial expression analysis
%K wavelet transform<br>边缘图像
%K 人脸图像
%K 图像边缘
%K 二值化
%K 识别率
%K 鲁棒性
%K 部件
%K 高频
%K 去噪
%K 小波变换
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=D06194629680C940ACE75262F54B9D85&aid=4B526F7C9796AD72&yid=D0E58B75BFD8E51C&vid=9CF7A0430CBB2DFD&iid=F3090AE9B60B7ED1&sid=7CCBDF94263DBB99&eid=53A4507B400B4E65&journal_id=1006-8961&journal_name=中国图象图形学报&referenced_num=1&reference_num=15