ML Anthology

Norm2-Based Face Recognition

Daniel B. Graham, Nigel M. Allinson
CVPR 1999 pp. 1586-1591
doi:10.1109/CVPR.1999.786998 /cvpr/1999/graham1999cvpr-norm/

Abstract

Increasingly the problems of recognising faces under
\na variety of viewing conditions, including depth
\nrotations, is being considered in the field. The concept
\nof norm-based coding an face recognition is not
\nnew but has been little investigated in machine models.
\nHere we describe a norm-based face recognition system
\nwhich is capable of generalising from a single training
\nview to recognise novel views of target faces. The system
\nis based upon the characteristic nature of faces as
\nthey move through a pose-varying eigenspace of facial
\nimages and deviations from the norm of a gallery of
\nface images. We illustrate the use of the technique for
\na large range of pose variation.

CVPR Semantic Scholar

Cite

Text

Graham and Allinson. "Norm2-Based Face Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999. doi:10.1109/CVPR.1999.786998

Markdown

[Graham and Allinson. "Norm2-Based Face Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999.](https://mlanthology.org/cvpr/1999/graham1999cvpr-norm/) doi:10.1109/CVPR.1999.786998

BibTeX

@inproceedings{graham1999cvpr-norm,
  title     = {{Norm2-Based Face Recognition}},
  author    = {Graham, Daniel B. and Allinson, Nigel M.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1999},
  pages     = {1586-1591},
  doi       = {10.1109/CVPR.1999.786998},
  url       = {https://mlanthology.org/cvpr/1999/graham1999cvpr-norm/}
}