제목

Facial Model Fitting Algorithm Based on Active appearance Model

저자명 Li, Luning, Hahn Hernsoo, Han Youngjoon

초 록

Active Appearance Model is an efficient method for the localization of facial feature points, which is also useful for the subsequent work such as face detection and facial expression recognition. In this paper, we mainly consider the Active Appearance Models based on Principal
Component Analysis (PCA). We also proposed an efficient facial fitting algorithm, which is named Inverse Compositional Image Alignment (ICIA), to eliminate a considerable of computation resulted from traditional gradient descent fitting algorithm. Finally, 3D facial curvature is used to initialize the location of facial feature, which helps select the parameters of initial state for improved AAM.

Keyword Active appearance model; ICIA; facial fitting; facial curvature
원문 수록처The Fourth International Conference on Smart IT Applications(SITA 2012), Technical Session 815
자료유형 학술대회자료