TY - GEN
T1 - Automatic facial expression recognition system using neural networks
AU - Tai, S. C.
AU - Chung, K. C.
PY - 2007
Y1 - 2007
N2 - In this paper, an automatic facial expression recognition system is presented. When a face image is input, two inner canthi are detected as the reference points for searching the expression features extracted from the contour and displacement of eyebrows, eyes, and mouth. Our feature extraction method can reduce the partial influence of shadows and noises. Finally, the expression features are used as the input to an Elman Neural Network of classifiers. The results on the JAFFE facial database show an average recognition accuracy of 84.7% in seven expressions by automatic canthi detection and 92.2% by manual canthi detection.
AB - In this paper, an automatic facial expression recognition system is presented. When a face image is input, two inner canthi are detected as the reference points for searching the expression features extracted from the contour and displacement of eyebrows, eyes, and mouth. Our feature extraction method can reduce the partial influence of shadows and noises. Finally, the expression features are used as the input to an Elman Neural Network of classifiers. The results on the JAFFE facial database show an average recognition accuracy of 84.7% in seven expressions by automatic canthi detection and 92.2% by manual canthi detection.
UR - http://www.scopus.com/inward/record.url?scp=48649086561&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=48649086561&partnerID=8YFLogxK
U2 - 10.1109/TENCON.2007.4429124
DO - 10.1109/TENCON.2007.4429124
M3 - Conference contribution
AN - SCOPUS:48649086561
SN - 1424412722
SN - 9781424412723
T3 - IEEE Region 10 Annual International Conference, Proceedings/TENCON
BT - TENCON 2007 - 2007 IEEE Region 10 Conference
T2 - IEEE Region 10 Conference, TENCON 2007
Y2 - 30 October 2007 through 2 November 2007
ER -