TY - GEN
T1 - Shape analysis using generalized procrustes analysis on Active Appearance Model for facial expression recognition
AU - Komalasari, Desy
AU - Widyanto, Muhammad Rahmat
AU - Basaruddin, T.
AU - Liliana, Dewi Yanti
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017
Y1 - 2017
N2 - Facial expression recognition is an active research area in the field of signal social processing. The goal is to distinguish human emotion. The problem is similar emotion, variation of emotion, and independent object through face image. The existing research using various method for modeling human facial to entirely describe facial expression through face image. We consider to variation analysis of the face image using Generalized Procrustes Analysis (GPA) method. GPA is implied for modeling variation of facial expression. We fit our GPA model exact the position of facial skeleton using Active Appearance Model (AAM). AAM is needed for extract shape feature of face image. Also, we use Gabor to get texture information of face image. The facial expression recognition method is based on Support Vector Machine (SVM). We tested our model with CK+ and Jaffe dataset on six basic emotion: Anger, disgust, fear, happy, sad, and surprise. Our method gained accuracy 93.58% for CK+ dataset and 94.7% for Jaffe dataset.
AB - Facial expression recognition is an active research area in the field of signal social processing. The goal is to distinguish human emotion. The problem is similar emotion, variation of emotion, and independent object through face image. The existing research using various method for modeling human facial to entirely describe facial expression through face image. We consider to variation analysis of the face image using Generalized Procrustes Analysis (GPA) method. GPA is implied for modeling variation of facial expression. We fit our GPA model exact the position of facial skeleton using Active Appearance Model (AAM). AAM is needed for extract shape feature of face image. Also, we use Gabor to get texture information of face image. The facial expression recognition method is based on Support Vector Machine (SVM). We tested our model with CK+ and Jaffe dataset on six basic emotion: Anger, disgust, fear, happy, sad, and surprise. Our method gained accuracy 93.58% for CK+ dataset and 94.7% for Jaffe dataset.
KW - active appearance model
KW - facial expression recognition
KW - generalized procrustes analysis
KW - support vector machine
UR - http://www.scopus.com/inward/record.url?scp=85041637527&partnerID=8YFLogxK
U2 - 10.1109/ICECOS.2017.8167123
DO - 10.1109/ICECOS.2017.8167123
M3 - Conference contribution
AN - SCOPUS:85041637527
T3 - ICECOS 2017 - Proceeding of 2017 International Conference on Electrical Engineering and Computer Science: Sustaining the Cultural Heritage Toward the Smart Environment for Better Future
SP - 154
EP - 159
BT - ICECOS 2017 - Proceeding of 2017 International Conference on Electrical Engineering and Computer Science
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 International Conference on Electrical Engineering and Computer Science, ICECOS 2017
Y2 - 22 August 2017 through 23 August 2017
ER -