<?xml version="1.0" encoding="UTF-8"?> <article key="pdf/14248" mdate="2008-05-23 00:00:00"> <author>Sunho Ki and Daehwan Kim and Seongwon Cho and Sun-Tae Chung and Jaemin Kim and Yun-Kwang Hong and Chang Joon Park and Dongmin Kwon and Minhee Kang and Yusung Kim and Younghan Yoon</author> <title>Reliable Face Alignment Using TwoStage AAM</title> <pages>1682 - 1686</pages> <year>2008</year> <volume>2</volume> <number>5</number> <journal>International Journal of Computer and Information Engineering</journal> <ee>https://publications.waset.org/pdf/14248</ee> <url>https://publications.waset.org/vol/17</url> <publisher>World Academy of Science, Engineering and Technology</publisher> <abstract>AAM (active appearance model) has been successfully applied to face and facial feature localization. However, its performance is sensitive to initial parameter values. In this paper, we propose a twostage AAM for robust face alignment, which first fits an inner faceAAM model to the inner facial feature points of the face and then localizes the whole face and facial features by optimizing the whole faceAAM model parameters. Experiments show that the proposed face alignment method using twostage AAM is more reliable to the background and the head pose than the standard AAMbased face alignment method.</abstract> <index>Open Science Index 17, 2008</index> </article>