TY - JOUR
T1 - Facial expression recognition based on facial region segmentation and modal value approach
AU - Benitez-Garcia, Gibran
AU - Sanchez-Perez, Gabriel
AU - Perez-Meana, Hector
AU - Takahashi, Keita
AU - Kaneko, Masahide
PY - 2014
Y1 - 2014
N2 - SUMMARY This paper presents a facial expression recognition algorithm based on segmentation of a face image into four facial regions (eyeseyebrows, forehead, mouth and nose). In order to unify the different results obtained from facial region combinations, a modal value approach that employs the most frequent decision of the classifiers is proposed. The robustness of the algorithm is also evaluated under partial occlusion, using four different types of occlusion (half left/right, eyes and mouth occlusion). The proposed method employs sub-block eigenphases algorithm that uses the phase spectrum and principal component analysis (PCA) for feature vector estimation which is fed to a support vector machine (SVM) for classification. Experimental results show that using modal value approach improves the average recognition rate achieving more than 90% and the performance can be kept high even in the case of partial occlusion by excluding occluded parts in the feature extraction process.
AB - SUMMARY This paper presents a facial expression recognition algorithm based on segmentation of a face image into four facial regions (eyeseyebrows, forehead, mouth and nose). In order to unify the different results obtained from facial region combinations, a modal value approach that employs the most frequent decision of the classifiers is proposed. The robustness of the algorithm is also evaluated under partial occlusion, using four different types of occlusion (half left/right, eyes and mouth occlusion). The proposed method employs sub-block eigenphases algorithm that uses the phase spectrum and principal component analysis (PCA) for feature vector estimation which is fed to a support vector machine (SVM) for classification. Experimental results show that using modal value approach improves the average recognition rate achieving more than 90% and the performance can be kept high even in the case of partial occlusion by excluding occluded parts in the feature extraction process.
KW - Facial expression recognition
KW - Facial segmentation
KW - Modal value
KW - Partial occlusion
UR - http://www.scopus.com/inward/record.url?scp=84897399064&partnerID=8YFLogxK
U2 - 10.1587/transinf.E97.D.928
DO - 10.1587/transinf.E97.D.928
M3 - Artículo
SN - 0916-8532
VL - E97-D
SP - 928
EP - 935
JO - IEICE Transactions on Information and Systems
JF - IEICE Transactions on Information and Systems
IS - 4
ER -