IEICE TRANSACTIONS on Information
Facial Expression Recognition Based on Facial Region Segmentation and Modal Value Approach
Summary :
This paper presents a facial expression recognition algorithm based on segmentation of a face image into four facial regions (eyes-eyebrows, 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.
- Publication
- IEICE TRANSACTIONS on Information Vol.E97-D No.4 pp.928-935
- Publication Date
- 2014/04/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E97.D.928
- Type of Manuscript
- PAPER
- Category
- Image Recognition, Computer Vision
Authors
Gibran BENITEZ-GARCIA
The University of Electro-Communications,National Polytechnic Institute
Gabriel SANCHEZ-PEREZ
National Polytechnic Institute
Hector PEREZ-MEANA
National Polytechnic Institute
Keita TAKAHASHI
The University of Electro-Communications
Masahide KANEKO
The University of Electro-Communications
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Gibran BENITEZ-GARCIA, Gabriel SANCHEZ-PEREZ, Hector PEREZ-MEANA, Keita TAKAHASHI, Masahide KANEKO, "Facial Expression Recognition Based on Facial Region Segmentation and Modal Value Approach" in IEICE TRANSACTIONS on Information,
vol. E97-D, no. 4, pp. 928-935, April 2014, doi: 10.1587/transinf.E97.D.928.
Abstract: This paper presents a facial expression recognition algorithm based on segmentation of a face image into four facial regions (eyes-eyebrows, 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.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E97.D.928/_p
Copy
@ARTICLE{e97-d_4_928,
author={Gibran BENITEZ-GARCIA, Gabriel SANCHEZ-PEREZ, Hector PEREZ-MEANA, Keita TAKAHASHI, Masahide KANEKO, },
journal={IEICE TRANSACTIONS on Information},
title={Facial Expression Recognition Based on Facial Region Segmentation and Modal Value Approach},
year={2014},
volume={E97-D},
number={4},
pages={928-935},
abstract={This paper presents a facial expression recognition algorithm based on segmentation of a face image into four facial regions (eyes-eyebrows, 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.},
keywords={},
doi={10.1587/transinf.E97.D.928},
ISSN={1745-1361},
month={April},}
Copy
TY - JOUR
TI - Facial Expression Recognition Based on Facial Region Segmentation and Modal Value Approach
T2 - IEICE TRANSACTIONS on Information
SP - 928
EP - 935
AU - Gibran BENITEZ-GARCIA
AU - Gabriel SANCHEZ-PEREZ
AU - Hector PEREZ-MEANA
AU - Keita TAKAHASHI
AU - Masahide KANEKO
PY - 2014
DO - 10.1587/transinf.E97.D.928
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2014
AB - This paper presents a facial expression recognition algorithm based on segmentation of a face image into four facial regions (eyes-eyebrows, 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.
ER -
English
