Active shape models—their training and application
Computer Vision and Image Understanding
Automatic facial expression recognition using facial animation parameters and multistream HMMs
IEEE Transactions on Information Forensics and Security
Facial expression recognition based on combined HMM
International Journal of Computer Applications in Technology
Hi-index | 0.00 |
Most of facial expression recognition methods generally use single feature extraction method currently. These methods can not extract effective features for each feature area. A method of facial expression recognition based on hybrid features and fusing discrete HMMs is presented in this paper. In this method, texture feature for the eye area is extracted by using Gabor wavelet transformation, and shape variety feature for the mouth area is extracted by using AAM. In the process of recognition, discrete HMM is adopted for expression recognition in each expression area respectively. The recognition results are fused by means of integrating the probability of each expression in each area with its weight obtained by contribution analysis algorithm, and the final expression is determined as which with the maximal probability. Experiments show that our method can get high recognition rate.