Action unit reconstruction of occluded facial expression

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

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.

Original languageEnglish
Title of host publicationIEEE International Conference on Orange Technologies, ICOT 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages177-180
Number of pages4
ISBN (Electronic)9781479962846
DOIs
Publication statusPublished - 2014 Nov 12
Event2014 IEEE International Conference on Orange Technologies, ICOT 2014 - Xi'an, China
Duration: 2014 Sep 202014 Sep 23

Publication series

NameIEEE International Conference on Orange Technologies, ICOT 2014

Other

Other2014 IEEE International Conference on Orange Technologies, ICOT 2014
CountryChina
CityXi'an
Period14-09-2014-09-23

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Engineering(all)

Fingerprint Dive into the research topics of 'Action unit reconstruction of occluded facial expression'. Together they form a unique fingerprint.

  • Cite this

    Wu, C-H., Lin, J. C., & Wei, W. L. (2014). Action unit reconstruction of occluded facial expression. In IEEE International Conference on Orange Technologies, ICOT 2014 (pp. 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