Facial Expression Recognition Using Gabor Motion Energy Filters

Abstract

Spatial Gabor energy filters (GE) are one of the most successful approaches to represent facial expressions in computer vision applications, including face recognition and expression analysis. It is well known that these filters approximate the response of complex cells in primary visual cortex. However these neurons are modulated by the temporal, not just spatial, properties of the visual signal. This suggests that spatio-temporal Gabor filters may provide useful representations for applications that involve video sequences. In this paper we explore Gabor motion energy filters (GME) as a biologically inspired representation for dynamic facial expressions. Experiments on the Cohn-Kanade expression dataset show that GME outperforms GE, particularly on difficult low intensity expression discrimination.

Cite

Text

Wu et al. "Facial Expression Recognition Using Gabor Motion Energy Filters." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2010. doi:10.1109/CVPRW.2010.5543267

Markdown

[Wu et al. "Facial Expression Recognition Using Gabor Motion Energy Filters." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2010.](https://mlanthology.org/cvprw/2010/wu2010cvprw-facial/) doi:10.1109/CVPRW.2010.5543267

BibTeX

@inproceedings{wu2010cvprw-facial,
  title     = {{Facial Expression Recognition Using Gabor Motion Energy Filters}},
  author    = {Wu, Tingfan and Bartlett, Marian Stewart and Movellan, Javier R.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2010},
  pages     = {42-47},
  doi       = {10.1109/CVPRW.2010.5543267},
  url       = {https://mlanthology.org/cvprw/2010/wu2010cvprw-facial/}
}