ML Anthology

Automatic Face Recognition: What Representation?

Nicholas Costen, Ian Craw, Graham Robertson, Shigeru Akamatsu
ECCV 1996 pp. 504-513
doi:10.1007/BFB0015561 /eccv/1996/costen1996eccv-automatic/

Abstract

A testbed for automatic face recognition shows an eigenface coding of shape-free texture, with manually coded landmarks, was more effective than correctly shaped faces, being dependent upon high-quality representation of the facial variation by a shape-free ensemble. Configuration also allowed recognition, these measures combine to improve performance and allowed automatic measurement of the face-shape. Caricaturing further increased performance. Correlation of contours of shapefree images also increased recognition, suggesting extra information was available. A natural model considers faces as in a manifold, linearly approximated by the two factors, with a separate system for local features.

PDF ECCV Semantic Scholar

Cite

Text

Costen et al. "Automatic Face Recognition: What Representation?." European Conference on Computer Vision, 1996. doi:10.1007/BFB0015561

Markdown

[Costen et al. "Automatic Face Recognition: What Representation?." European Conference on Computer Vision, 1996.](https://mlanthology.org/eccv/1996/costen1996eccv-automatic/) doi:10.1007/BFB0015561

BibTeX

@inproceedings{costen1996eccv-automatic,
  title     = {{Automatic Face Recognition: What Representation?}},
  author    = {Costen, Nicholas and Craw, Ian and Robertson, Graham and Akamatsu, Shigeru},
  booktitle = {European Conference on Computer Vision},
  year      = {1996},
  pages     = {504-513},
  doi       = {10.1007/BFB0015561},
  url       = {https://mlanthology.org/eccv/1996/costen1996eccv-automatic/}
}