제목 Efficient Model Building in Active Appearance Model for the Rotated Face
저자명

jaehyun So, Sanghun Han, Yongtak Kim, Hwanik Chung, Youngjoon Han
 

초   록

  this paper proposes the efficient model building in active apperance model (AAM) for the rotated face. Finding

an exact region of the face is generally difficult due to different shaps and viewpoints, Unlike many paper about the

fitting method of AAM, this paper treats how images are chosen for fitting of the rotated face in modelling process.To solove this problem , databases of facial rotation and experession are selected and models are built using Procrusters method and principal component analysis(PCA). these models are appiled in fitting methods like basic AAM fitting, inverse compositional alignment(ICV),project-out ICA, normalization ICA,robust normalization inverse compositional algorithm(RNIC) and efficient robust normalization algorithm(ERN). RNIC and ERN can fit the rotated face in image efficiently. The efficiency of model building is checked using sequence image mad by ourselves



원문 수록처 Journal of Measurement Science and Instrumentation Vol.4 No.4, Dec 2013 Sum No.16
자료유형 International Journal