File(s) under permanent embargo
Recognising faces in unseen modes: a tensor based approach
conference contribution
posted on 2008-01-01, 00:00 authored by Santu RanaSantu Rana, W Liu, M Lazarescu, Svetha VenkateshSvetha VenkateshThis 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.
History
Event
Computer Vision and Pattern Recognition. Conference (26th : 2008 : Anchorage, Alaska)Series
Computer Vision and Pattern Recognition ConferencePagination
1 - 8Publisher
Institute of Electrical and Electronics EngineersLocation
Anchorage, AlaskaPlace of publication
Piscataway, N.J.Publisher DOI
Start date
2008-06-23End date
2008-06-28ISBN-13
9781424422432Language
engPublication classification
E1.1 Full written paper - refereedCopyright notice
2008, IEEEEditor/Contributor(s)
[Unknown]Title of proceedings
CVPR 2008 : Proceedings of the 26th IEEE Conference on Computer Vision and Pattern RecognitionUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC