%0 Journal Article
%T 3D Face Deformable Model Based on Feature Points<br>基于特征点的三维人脸形变模型
%A GONG Xun
%A WANG Guo-Yin
%A <br>龚勋
%A 王国胤
%J 软件学报
%D 2009
%I 
%X The traditional 3D deformable model is inefficient in face reconstruction. To address this problem, a linear deformable model is proposed based on facial landmarks. First, a 2D template-based alignment algorithm isdeveloped to process the correspondence between faces automatically, and a facial linear model is built. Then, adynamic component-based deforming model is proposed to select the most correlative components as the basicspace. Finally, the facial shape is reconstructed by a double deformation framework, a combination of the globaldeformation and local modification. Experimental results show that this method outperforms the conventionalmethods in modeling precision, and the 3D faces generated from real-world photos are rather realistic based on afew landmarks.
%K dense correspondence
%K 3D face reconstruction
%K linear regression
%K deformable model
%K radial based function<br>稠密对应
%K 三维人脸重建
%K 线性回归
%K 形变模型
%K 径向基函数
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=7735F413D429542E610B3D6AC0D5EC59&aid=297342B7F259D998461720ED5AEA3E87&yid=DE12191FBD62783C&vid=A04140E723CB732E&iid=38B194292C032A66&sid=94655B9881133A28&eid=EED44B83FAB71309&journal_id=1000-9825&journal_name=软件学报&referenced_num=4&reference_num=33