ML Anthology

Recognising Faces in Unseen Modes: A Tensor Based Approach

Santu Rana, Wanquan Liu, Mihai M. Lazarescu, Svetha Venkatesh
CVPR 2008
doi:10.1109/CVPR.2008.4587813 /cvpr/2008/rana2008cvpr-recognising/

Abstract

This paper addresses the limitation of current multilinear techniques (multilinear PCA, multilinear ICA) when applied to face recognition for handling faces in unseen illumination and viewpoints. We propose a new recognition method, exploiting the interaction of all the subspaces resulting from multilinear decomposition (for both multilinear PCA and ICA), to produce a new basis called multilinear-eigenmodes. This basis offers the flexibility to handle face images at unseen illumination or viewpoints. Experiments on benchmarked datasets yield superior performance in terms of both accuracy and computational cost.

PDF CVPR Semantic Scholar

Cite

Text

Rana et al. "Recognising Faces in Unseen Modes: A Tensor Based Approach." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008. doi:10.1109/CVPR.2008.4587813

Markdown

[Rana et al. "Recognising Faces in Unseen Modes: A Tensor Based Approach." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008.](https://mlanthology.org/cvpr/2008/rana2008cvpr-recognising/) doi:10.1109/CVPR.2008.4587813

BibTeX

@inproceedings{rana2008cvpr-recognising,
  title     = {{Recognising Faces in Unseen Modes: A Tensor Based Approach}},
  author    = {Rana, Santu and Liu, Wanquan and Lazarescu, Mihai M. and Venkatesh, Svetha},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2008},
  doi       = {10.1109/CVPR.2008.4587813},
  url       = {https://mlanthology.org/cvpr/2008/rana2008cvpr-recognising/}
}