Recognising faces in unseen modes: a tensor based approach
dc.contributor.author | Rana, Santu | |
dc.contributor.author | Liu, Wan-Quan | |
dc.contributor.author | Lazarescu, Mihai | |
dc.contributor.author | Venkatesh, Svetha | |
dc.contributor.editor | NA | |
dc.date.accessioned | 2017-01-30T10:52:52Z | |
dc.date.available | 2017-01-30T10:52:52Z | |
dc.date.created | 2014-10-28T02:23:21Z | |
dc.date.issued | 2008 | |
dc.identifier.citation | Rana, S. and Liu, W. and Lazarescu, M. and Venkatesh, S. 2008. Recognising faces in unseen modes: a tensor based approach, in IEEE Conference on Computer Vision and Pattern recognition, Jun 23-28 2008. Anchorage, Alaska: IEEE. | |
dc.identifier.uri | http://hdl.handle.net/20.500.11937/6414 | |
dc.identifier.doi | 10.1109/CVPR.2008.4587813 | |
dc.description.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. | |
dc.publisher | IEEE | |
dc.title | Recognising faces in unseen modes: a tensor based approach | |
dc.type | Conference Paper | |
dcterms.source.title | IEEE Computer Society conference on computer vision and pattern recognition | |
dcterms.source.series | IEEE Computer Society conference on computer vision and pattern recognition | |
dcterms.source.isbn | 9781424422432 | |
dcterms.source.conference | 26th IEEE conference on computer vision and pattern recognition | |
dcterms.source.conference-start-date | Jun 24 2008 | |
dcterms.source.conferencelocation | Anchorage, Alaska | |
dcterms.source.place | USA | |
curtin.department | Department of Computing | |
curtin.accessStatus | Fulltext not available |