제목 Appearance Model Fitting Method for Face Expression Recognition
저자명

Luning Li, Jung-hu Kim, Youngjoon, Han

초   록

  Active Appearance Model is an efficient method for the localization of facial feature points. It 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 propose an efficient facial fitting algorithm which is Inverse Compositional Image Alignment (ICIA) to reduce a considerable amount of computationaltime resulted from traditional gradient descent fitting algorithm. After training a set of images, we can get the fitting result of the ICIA algorithm which is used as raw data of face expression recognition.
원문 수록처 HCI KOREA 2013 / 워크샵 '다중 디바이스 환경에서 HCI 정보의 표현 및 처리'
자료유형 학술대회 자료