Action unit reconstruction of occluded facial expression

Chung-Hsien Wu, Jen Chun Lin, Wen Li Wei

研究成果: Conference contribution

1 引文 (Scopus)

摘要

Facial occlusion is a critical issue that may dramatically degrade the performance on facial expression-based emotion recognition. In this study, the Error Weighted Cross-Correlation Model (EWCCM) is employed to predict the facial Action Unit (AU) under partial facial occlusion from non-occluded facial regions for facial geometric feature reconstruction. In EWCCM, a Gaussian Mixture Model (GMM)-based Cross-Correlation Model (CCM) is first adopted to construct the statistical dependency among features from paired facial components such as eyebrows-cheeks of the non-occluded regions for AU prediction of the occluded region. A Bayesian classifier weighting scheme is then used to enhance the AU prediction accuracy considering the contributions of the GMM-based CCMs. Based on the predicted AU, a regression fusion scheme is proposed to reconstruct the occluded facial geometric features. Experimental results show that the proposed approach yielded satisfactory results on the NCKU-FEPO database for facial AU reconstruction.

原文English
主出版物標題IEEE International Conference on Orange Technologies, ICOT 2014
發行者Institute of Electrical and Electronics Engineers Inc.
頁面177-180
頁數4
ISBN(電子)9781479962846
DOIs
出版狀態Published - 2014 十一月 12
事件2014 IEEE International Conference on Orange Technologies, ICOT 2014 - Xi'an, China
持續時間: 2014 九月 202014 九月 23

出版系列

名字IEEE International Conference on Orange Technologies, ICOT 2014

Other

Other2014 IEEE International Conference on Orange Technologies, ICOT 2014
國家China
城市Xi'an
期間14-09-2014-09-23

指紋

Classifiers
Fusion reactions

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Engineering(all)

引用此文

Wu, C-H., Lin, J. C., & Wei, W. L. (2014). Action unit reconstruction of occluded facial expression. 於 IEEE International Conference on Orange Technologies, ICOT 2014 (頁 177-180). [6956628] (IEEE International Conference on Orange Technologies, ICOT 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICOT.2014.6956628
Wu, Chung-Hsien ; Lin, Jen Chun ; Wei, Wen Li. / Action unit reconstruction of occluded facial expression. IEEE International Conference on Orange Technologies, ICOT 2014. Institute of Electrical and Electronics Engineers Inc., 2014. 頁 177-180 (IEEE International Conference on Orange Technologies, ICOT 2014).
@inproceedings{3ab426626b7e45fe913a078228f539ed,
title = "Action unit reconstruction of occluded facial expression",
abstract = "Facial occlusion is a critical issue that may dramatically degrade the performance on facial expression-based emotion recognition. In this study, the Error Weighted Cross-Correlation Model (EWCCM) is employed to predict the facial Action Unit (AU) under partial facial occlusion from non-occluded facial regions for facial geometric feature reconstruction. In EWCCM, a Gaussian Mixture Model (GMM)-based Cross-Correlation Model (CCM) is first adopted to construct the statistical dependency among features from paired facial components such as eyebrows-cheeks of the non-occluded regions for AU prediction of the occluded region. A Bayesian classifier weighting scheme is then used to enhance the AU prediction accuracy considering the contributions of the GMM-based CCMs. Based on the predicted AU, a regression fusion scheme is proposed to reconstruct the occluded facial geometric features. Experimental results show that the proposed approach yielded satisfactory results on the NCKU-FEPO database for facial AU reconstruction.",
author = "Chung-Hsien Wu and Lin, {Jen Chun} and Wei, {Wen Li}",
year = "2014",
month = "11",
day = "12",
doi = "10.1109/ICOT.2014.6956628",
language = "English",
series = "IEEE International Conference on Orange Technologies, ICOT 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "177--180",
booktitle = "IEEE International Conference on Orange Technologies, ICOT 2014",
address = "United States",

}

Wu, C-H, Lin, JC & Wei, WL 2014, Action unit reconstruction of occluded facial expression. 於 IEEE International Conference on Orange Technologies, ICOT 2014., 6956628, IEEE International Conference on Orange Technologies, ICOT 2014, Institute of Electrical and Electronics Engineers Inc., 頁 177-180, 2014 IEEE International Conference on Orange Technologies, ICOT 2014, Xi'an, China, 14-09-20. https://doi.org/10.1109/ICOT.2014.6956628

Action unit reconstruction of occluded facial expression. / Wu, Chung-Hsien; Lin, Jen Chun; Wei, Wen Li.

IEEE International Conference on Orange Technologies, ICOT 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 177-180 6956628 (IEEE International Conference on Orange Technologies, ICOT 2014).

研究成果: Conference contribution

TY - GEN

T1 - Action unit reconstruction of occluded facial expression

AU - Wu, Chung-Hsien

AU - Lin, Jen Chun

AU - Wei, Wen Li

PY - 2014/11/12

Y1 - 2014/11/12

N2 - Facial occlusion is a critical issue that may dramatically degrade the performance on facial expression-based emotion recognition. In this study, the Error Weighted Cross-Correlation Model (EWCCM) is employed to predict the facial Action Unit (AU) under partial facial occlusion from non-occluded facial regions for facial geometric feature reconstruction. In EWCCM, a Gaussian Mixture Model (GMM)-based Cross-Correlation Model (CCM) is first adopted to construct the statistical dependency among features from paired facial components such as eyebrows-cheeks of the non-occluded regions for AU prediction of the occluded region. A Bayesian classifier weighting scheme is then used to enhance the AU prediction accuracy considering the contributions of the GMM-based CCMs. Based on the predicted AU, a regression fusion scheme is proposed to reconstruct the occluded facial geometric features. Experimental results show that the proposed approach yielded satisfactory results on the NCKU-FEPO database for facial AU reconstruction.

AB - Facial occlusion is a critical issue that may dramatically degrade the performance on facial expression-based emotion recognition. In this study, the Error Weighted Cross-Correlation Model (EWCCM) is employed to predict the facial Action Unit (AU) under partial facial occlusion from non-occluded facial regions for facial geometric feature reconstruction. In EWCCM, a Gaussian Mixture Model (GMM)-based Cross-Correlation Model (CCM) is first adopted to construct the statistical dependency among features from paired facial components such as eyebrows-cheeks of the non-occluded regions for AU prediction of the occluded region. A Bayesian classifier weighting scheme is then used to enhance the AU prediction accuracy considering the contributions of the GMM-based CCMs. Based on the predicted AU, a regression fusion scheme is proposed to reconstruct the occluded facial geometric features. Experimental results show that the proposed approach yielded satisfactory results on the NCKU-FEPO database for facial AU reconstruction.

UR - http://www.scopus.com/inward/record.url?scp=84916243284&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84916243284&partnerID=8YFLogxK

U2 - 10.1109/ICOT.2014.6956628

DO - 10.1109/ICOT.2014.6956628

M3 - Conference contribution

AN - SCOPUS:84916243284

T3 - IEEE International Conference on Orange Technologies, ICOT 2014

SP - 177

EP - 180

BT - IEEE International Conference on Orange Technologies, ICOT 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Wu C-H, Lin JC, Wei WL. Action unit reconstruction of occluded facial expression. 於 IEEE International Conference on Orange Technologies, ICOT 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 177-180. 6956628. (IEEE International Conference on Orange Technologies, ICOT 2014). https://doi.org/10.1109/ICOT.2014.6956628