%0 Journal Article
%T Robust Non-Frontal Face Alignment with Edge Based Texture
%A Hua Li
%A Shui-Cheng Yan
%A Li-Zhong Peng
%A <br>Hua Li
%A Shui-Cheng Yan
%A and Li-Zhong Peng
%J 计算机科学技术学报
%D 2005
%I 
%X This paper proposes a new algorithm, called Edge-based Texture Driven Shape Model (E-TDSM), for non-frontal face alignment task. First, the texture is defined as the un-warped edge image contained in the shape rectangle; then, a Bayesian network is constructed to describe the relationship between the shape and texture models; finally, Expectation-Maximization (EM) approach is utilized to infer the optimal texture and position parameters from the observed shape and texture information. Compared with the traditional shape localization algorithms, E-TDSM has the following advantages: 1) the un-warped edge-based texture can better predict the shape and is more robust to the illumination and expression variation than the conventional warped gray-level based texture; 2) the presented Bayesian network indicates the logic structure of the face alignment task; and 3) the mutually enhanced shape and texture observations are integrated to infer the optimal parameters of the proposed Bayesian network using EM approach. The extensive experiments on non-frontal face alignment task demonstrate the effectiveness and robustness of the proposed E-TDSM algorithm.
%K computer vision
%K face and gesture recognition
%K feature evaluation and selection
%K Bayesian network<br>计算机图象
%K 形状模型
%K 图象识别
%K 特征评估
%K Bayesian网络
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=F57FEF5FAEE544283F43708D560ABF1B&aid=52F4F395473CE558CA25C894002616A2&yid=2DD7160C83D0ACED&vid=A04140E723CB732E&iid=B31275AF3241DB2D&sid=8AD9BBE1FAF6BB78&eid=8D95DD1211171525&journal_id=1000-9000&journal_name=计算机科学技术学报&referenced_num=0&reference_num=13