DocumentCode :
3179514
Title :
A Quadratic Deformation Model for Facial Expression Recognition
Author :
Obaid, M. ; Mukundan, R. ; Goecke, R. ; Billinghurst, M. ; Seichter, H.
Author_Institution :
HITLab New Zealand, Univ. of Canterbury, Christchurch, New Zealand
fYear :
2009
fDate :
1-3 Dec. 2009
Firstpage :
264
Lastpage :
270
Abstract :
In this paper, we propose a novel approach for recognizing facial expressions based on using an active appearance model facial feature tracking system with the quadratic deformation model representations of facial expressions. Thirty seven facial feature points are tracked based on the MPEG-4 facial animation parameters layout. The proposed approach relies on the Euclidean distance measures between the tracked feature points and the reference deformed facial feature points of the six main expressions (smile, sad, fear, disgust, surprise, and anger). An evaluation of 30 model subjects, selected randomly from the Cohn-Kanade database, was carried out. Results show that the main six facial expressions can successfully be recognized with an overall recognition accuracy of 89%. The proposed approach yields to promising recognition rates and can be used in real time applications.
Keywords :
computer animation; face recognition; visual databases; Cohn-Kanade database; Euclidean distance; MPEG-4 facial animation parameters layout; active appearance model facial feature tracking system; anger expression; disgust expression; facial expression recognition; fear expression; quadratic deformation model; sad expression; smile expression; surprise expression; Active appearance model; Application software; Computer science; Computer vision; Deformable models; Face recognition; Facial animation; Facial features; Image recognition; MPEG 4 Standard; Active Appearance Models; Facial Expression Recognition; Facial Feature Tracking; Quadratic Deformation Models;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Digital Image Computing: Techniques and Applications, 2009. DICTA '09.
Conference_Location :
Melbourne, VIC
Print_ISBN :
978-1-4244-5297-2
Electronic_ISBN :
978-0-7695-3866-2
Type :
conf
DOI :
10.1109/DICTA.2009.51
Filename :
5384965
Link To Document :
بازگشت