Abstract: Facial expression recognition is an essential issue in the field of human and computer interaction. The objective of this paper is to deal with the problem of failure for the feature points on face based on actives appearance model (AAM) in fitting with different users, A high quality AAM alignment results rely on appropriate selections of initial positions, In our method, we apply partial AAM fitting on mouth and eyes, To obtain stable partial AAM, we use multi-level optical flow to determine initial position of facial feature models. Then we use the Eigen-faces dynamic face recognition system to recognize different users and select the trained fitting model in recognition with Eigen-face dynamic face recognition. In this paper, we have demonstrated our approach which can accurately recognize different users facial expressions and emotional variation.
|
DOI:
10.17148/IJARCCE.2022.116106
