ML Anthology

Simultaneous Extraction of Functional Face Subspaces

Nicholas Costen, Timothy F. Cootes, Gareth J. Edwards, Christopher J. Taylor
CVPR 1999 pp. 1492-
doi:10.1109/CVPR.1999.786983 /cvpr/1999/costen1999cvpr-simultaneous/

Abstract

Facial variation divides into a number of functional subspaces. An improved method of measuring these was designed within the space defined by an Appearance Model. Initial estimates of the subspaces (lighting, pose, identity, expression) were obtained by Principal Components Analysis on appropriate groups of faces. An iterative algorithm was applied to image codings to maximise the probability of coding across these non-orthogonal subspaces before obtaining the projection on each sub-space and recalculating the spaces. This procedure enhances identity recognition, reduces overall sub-space variance and produces Principal Components with greater span and less contamination.

PDF CVPR Semantic Scholar

Cite

Text

Costen et al. "Simultaneous Extraction of Functional Face Subspaces." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999. doi:10.1109/CVPR.1999.786983

Markdown

[Costen et al. "Simultaneous Extraction of Functional Face Subspaces." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999.](https://mlanthology.org/cvpr/1999/costen1999cvpr-simultaneous/) doi:10.1109/CVPR.1999.786983

BibTeX

@inproceedings{costen1999cvpr-simultaneous,
  title     = {{Simultaneous Extraction of Functional Face Subspaces}},
  author    = {Costen, Nicholas and Cootes, Timothy F. and Edwards, Gareth J. and Taylor, Christopher J.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1999},
  pages     = {1492-},
  doi       = {10.1109/CVPR.1999.786983},
  url       = {https://mlanthology.org/cvpr/1999/costen1999cvpr-simultaneous/}
}