基于样例学习的面部特征自动标定算法-JDL联合试验室.PDFVIP

1000-9825/2005/16(05)0718 ©2005 Journal of Software 软 件 学 报 Vol.16, No.5 ∗ 基于样例学习的面部特征自动标定算法 1+ 1 1,2 1,2 柴秀娟 , 山世光 , 高 文 , 陈熙霖 1(哈尔滨工业大学 计算机学院,黑龙江 哈尔滨 150001) 2( 中国科学院 计算技术研究所 ICT-ISVISION 面像识别联合实验室,北京 100080) Example-Based Learning for Automatic Face Alignment 1+ 1 1,2 1,2 CHAI Xiu-Juan , SHAN Shi-Guang , GAO Wen , CHEN Xi-Lin 1(Department of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China) 2(ICT-ISVISION Joint RD Laboratory for Face Recognition, Institute of Computing Technology, The Chinese Academy of Sciences, Beijing 100080, China) + Corresponding author: Phn: +86-10ext 314, E-mail: xjchai@j , / Received 2004-04-09; Accepted 2004-06-11 Chai XJ, Shan SG, Gao W, Chen XL. Example-Based learning for automatic face alignment. Journal of Software, 2005,16(5):718−726. DOI: 10.1360/jos160718 Abstract: In this paper, a novel example-based automatic face alignment strategy has been proposed for facial features alignment, i.e. facial shape extracting. The method is motivated by an intuitive and experimental observation that there exists an approximate linearity relationship between the image intensity difference and the shape difference, that is, similar face image intensity distribution implies similar face shape. Therefore, given a learning set of face images with their corresponding face landmarks labeled, the shape of any other face image can be learned by estimating its similarities to the training images in the le