%0 Journal Article
%T An Automatic Facial Expression Recognition Approach Based on Confusion-crossed Support Vector Machine Tree<br>基于混淆交叉支撑向量机树的自动面部表情分类方法
%A XU Qin-zhen
%A ZHANG Pin-zheng
%A PEI Wen-jiang
%A HE Zhen-ya
%A <br>徐琴珍
%A 章品正
%A 裴文江
%A 杨绿溪
%A 何振亚
%J 中国图象图形学报
%D 2008
%I 
%X Automatic facial expression recognition is the kernel part of emotional information processing.This study is dedicated to develop an automatic facial expression recognition approach based on confusion-crossed support vector machine tree(CSVMT)to improve recognition accuracy and robustness.Pseudo-Zernike moment features were extracted to train a CSVMT for automatic recognition.The structure of CSVMT enables the model to divide the facial recognition problem into sub-problems according to the teacher signals,so that it can solve the sub-problems in decreased complexity in different tree levels.In the training phase,those sub-samples assigned to two internal sibling nodes perform decreasing confusion cross,thus,the generalization ability of CSVMT for recognition of facial expression is enhanced.The experiments are conducted on Cohn-Kanade facial expression database.Competitive recognition accuracy 96.31% is achieved.The compared results on Cohn-Kanade facial expression database also show that the proposed approach appeared higher recognition accuracy and robustness than other approaches.
%K automatic facial recognition
%K confusion cross
%K support vector machine tree
%K Pseudo-Zernike moment<br>面部表情自动识别
%K 混淆交叉
%K 支撑向量机树
%K 伪Zernike矩
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=D06194629680C940ACE75262F54B9D85&aid=619DA0C9105B6F6E6E404E10CD237C3A&yid=67289AFF6305E306&vid=FC0714F8D2EB605D&iid=DF92D298D3FF1E6E&sid=1EB017852C08068A&eid=9F83C44826B8A7D6&journal_id=1006-8961&journal_name=中国图象图形学报&referenced_num=1&reference_num=15