Action unit reconstruction of occluded facial expression

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

研究成果: Conference contribution

2 引文 斯高帕斯(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

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Engineering(all)

指紋 深入研究「Action unit reconstruction of occluded facial expression」主題。共同形成了獨特的指紋。

引用此