Fourier Active Appearance Models

Abstract

Gaining invariance to camera and illumination variations has been a well investigated topic in Active Appearance Model (AAM) fitting literature. The major problem lies in the inability of the appearance parameters of the AAM to generalize to unseen conditions. An attractive approach for gaining invariance is to fit an AAM to a multiple filter response (e.g. Gabor) representation of the input image. Naively applying this concept with a traditional AAM is computationally prohibitive, especially as the number of filter responses increase. In this paper, we present a computationally efficient AAM fitting algorithm based on the Lucas-Kanade (LK) algorithm posed in the Fourier domain that affords invariance to both expression and illumination. We refer to this as a Fourier AAM (FAAM), and show that this method gives substantial improvement in person specific AAM fitting performance over traditional AAM fitting methods.

Cite

Text

Navarathna et al. "Fourier Active Appearance Models." IEEE/CVF International Conference on Computer Vision, 2011. doi:10.1109/ICCV.2011.6126461

Markdown

[Navarathna et al. "Fourier Active Appearance Models." IEEE/CVF International Conference on Computer Vision, 2011.](https://mlanthology.org/iccv/2011/navarathna2011iccv-fourier/) doi:10.1109/ICCV.2011.6126461

BibTeX

@inproceedings{navarathna2011iccv-fourier,
  title     = {{Fourier Active Appearance Models}},
  author    = {Navarathna, Rajitha and Sridharan, Sridha and Lucey, Simon},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2011},
  pages     = {1919-1926},
  doi       = {10.1109/ICCV.2011.6126461},
  url       = {https://mlanthology.org/iccv/2011/navarathna2011iccv-fourier/}
}