DocumentCode :
3391271
Title :
Development of a Facial Emotion Recognition Method Based on Combining AAM with DBN
Author :
Ko, Kwang-Eun ; Sim, Kwee-Bo
Author_Institution :
Sch. of Electr. & Electron. Eng., Chung-Ang Univ., Seoul, South Korea
fYear :
2010
fDate :
20-22 Oct. 2010
Firstpage :
87
Lastpage :
91
Abstract :
In this paper, novel methods for facial emotion recognition in facial image sequences are presented. Our facial emotional feature detection and extracting based on Active Appearance Models (AAM) with Ekman´s Facial Action Coding System (FACS). Our approach to facial emotion recognition lies in the dynamic and probabilistic framework based on Dynamic Bayesian Network (DBN) with Kalman Filter for modeling and understanding the temporal phases of facial expressions in image sequences. By combining AAM and DBN, the proposed method can achieve a higher recognition performance level compare with other facial expression recognition methods. The result on the BioID dataset show a recognition accuracy of more than 90% for facial emotion reasoning using the proposed method.
Keywords :
Kalman filters; belief networks; emotion recognition; face recognition; feature extraction; BioID dataset; Ekman facial action coding system; Kalman filter; active appearance models; dynamic Bayesian network; facial emotion recognition; facial emotional feature detection; facial emotional feature extraction; facial image sequences; Active appearance model; Emotion recognition; Face recognition; Facial features; Feature extraction; Image sequences; Shape; Active Appearance Model; Dynamic Bayesian Network; Facial Action Coding System; Facial Emotion Recognition Facial Feature Extraction;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Cyberworlds (CW), 2010 International Conference on
Conference_Location :
Singapore
Print_ISBN :
978-1-4244-8301-3
Electronic_ISBN :
978-0-7695-4215-7
Type :
conf
DOI :
10.1109/CW.2010.65
Filename :
5655092
Link To Document :
بازگشت