Title :
A facial expression recognition model based on HMM
Author_Institution :
Sch. of Electron. & Inf. Eng, Shenzhen Polytech., Shenzhen, China
Abstract :
The most expressive way humans display emotions is through facial expressions, and the facial expression recognition has been widely used. Although so many researches are done, it is hard to find a practical application in the real world. The motion of the face is modeled by HMM as follows, first, according to the function of HMM in processing continuous dynamic signal and model recognition, and for the sample´s overlap and similarity in the sample space, Code-HMM was made up respectively; then, inducted KNN and some discrimination rules by analyzing the output result. A method based on code HMM+KNN is proposed to recognize the facial expression. The experimental results show that this method is better than traditional HMM.
Keywords :
emotion recognition; face recognition; hidden Markov models; learning (artificial intelligence); pattern classification; code HMM+KNN; code-HMM; continuous dynamic model recognition; continuous dynamic signal recognition; discrimination rules; facial expression recognition model; hidden Markov model; inducted KNN; k-nearest neighbor; Classification algorithms; Encoding; Face recognition; Hidden Markov models; Markov processes; Speech recognition; Training; HMM; code-hidden markov model(C-HMM); facial expression recognition; k-nearest Neighbor;
Conference_Titel :
Electronic and Mechanical Engineering and Information Technology (EMEIT), 2011 International Conference on
Conference_Location :
Harbin, Heilongjiang, China
Print_ISBN :
978-1-61284-087-1
DOI :
10.1109/EMEIT.2011.6023733
