Title :
Facial expression recognition based on two-dimensional structure of emotion
Author :
Shin, Youngsuk ; Lee, Sooyong ; Chung, Chansup ; Yillbyung Lee
Author_Institution :
Graduate Program in Cognitive Sci., Yonsei Univ., Seoul, South Korea
Abstract :
We present a new system for facial expression recognition based on the two-dimensional structure of emotion, which is an extension to facial expression recognition based on basic emotions. The two-dimensional structure model of emotion consists of pleasure/displeasure and arousal dimension. Feature vectors for facial expressions are extracted from a hybrid approach. Facial expression recognition is implemented by a neural network in the two-dimensional structure of emotion. The dimension structure of emotion shows that it is possible to recognize not only facial expressions related to basic emotions but also expressions of various emotions
Keywords :
face recognition; feature extraction; image coding; neural nets; transform coding; transforms; 2D structure model; Gabor transformation; arousal dimension; emotion two-dimensional structure; facial expression recognition; feature vectors extraction; hybrid approach; neural network; pleasure/displeasure; sparse coding; Cognitive science; Emotion recognition; Face detection; Face recognition; Feature extraction; Histograms; Humans; Joining processes; Kernel; Neural networks;
Conference_Titel :
Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-5747-7
DOI :
10.1109/ICOSP.2000.891800
