Facial expression recognition for learning status analysis
HCII'11 Proceedings of the 14th international conference on Human-computer interaction: users and applications - Volume Part IV
| Hi-index | 0.00 |
Facial expression recognition can be divided into three steps: face detection, expression feature extraction and expression categorization. Facial expression feature extraction and categorization are the most key issue. To address this issue, we propose a method to combine local binary pattern (LBP) and embedded hidden markov model (EHMM), which is the key contribution of this paper. This paper first gives an introduction about facial expression recognition and then describes EHMM and LBP. Finally, we give out the LBP-EHMM method in facial expression recognition, and perform an experiment to obtain a comparison between LBP feature and discrete cosine transform (DCT) feature.