Robust Expression-Invariant Face Recognition from Partially Missing Data

Abstract

Recent studies on three-dimensional face recognition proposed to model facial expressions as isometries of the facial surface. Based on this model, expression-invariant signatures of the face were constructed by means of approximate isometric embedding into flat spaces. Here, we apply a new method for measuring isometry-invariant similarity between faces by embedding one facial surface into another. We demonstrate that our approach has several significant advantages, one of which is the ability to handle partially missing data. Promising face recognition results are obtained in numerical experiments even when the facial surfaces are severely occluded.

Cite

Text

Bronstein et al. "Robust Expression-Invariant Face Recognition from Partially Missing Data." European Conference on Computer Vision, 2006. doi:10.1007/11744078_31

Markdown

[Bronstein et al. "Robust Expression-Invariant Face Recognition from Partially Missing Data." European Conference on Computer Vision, 2006.](https://mlanthology.org/eccv/2006/bronstein2006eccv-robust/) doi:10.1007/11744078_31

BibTeX

@inproceedings{bronstein2006eccv-robust,
  title     = {{Robust Expression-Invariant Face Recognition from Partially Missing Data}},
  author    = {Bronstein, Alexander M. and Bronstein, Michael M. and Kimmel, Ron},
  booktitle = {European Conference on Computer Vision},
  year      = {2006},
  pages     = {396-408},
  doi       = {10.1007/11744078_31},
  url       = {https://mlanthology.org/eccv/2006/bronstein2006eccv-robust/}
}