Efficient tensor based face recognition

This paper addresses the limitation of current multilinear PCA based techniques, in terms of prohibitive computational cost of testing and poor generalisation in some scenarios, when applied to large training databases. We define person-specific eigenmodes to obtain a set of projection bases, wherei...

Full description

Bibliographic Details
Main Authors: Rana, Santu, Liu, Wan-Quan, Lazarescu, Mihai, Venkatesh, Svetha
Other Authors: Not known
Format: Conference Paper
Published: IEEE 2008
Online Access:http://hdl.handle.net/20.500.11937/31640
_version_ 1848753438119165952
author Rana, Santu
Liu, Wan-Quan
Lazarescu, Mihai
Venkatesh, Svetha
author2 Not known
author_facet Not known
Rana, Santu
Liu, Wan-Quan
Lazarescu, Mihai
Venkatesh, Svetha
author_sort Rana, Santu
building Curtin Institutional Repository
collection Online Access
description This paper addresses the limitation of current multilinear PCA based techniques, in terms of prohibitive computational cost of testing and poor generalisation in some scenarios, when applied to large training databases. We define person-specific eigenmodes to obtain a set of projection bases, wherein a particular basis captures variation across lightings and viewpoints for a particular person. A new recognition approach is developed utilizing these bases. The proposed approach performs on a par with the existing multilinear approaches, whilst significantly reducing the complexity order of the testing algorithm.
first_indexed 2025-11-14T08:24:31Z
format Conference Paper
id curtin-20.500.11937-31640
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T08:24:31Z
publishDate 2008
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-316402018-03-29T09:08:51Z Efficient tensor based face recognition Rana, Santu Liu, Wan-Quan Lazarescu, Mihai Venkatesh, Svetha Not known This paper addresses the limitation of current multilinear PCA based techniques, in terms of prohibitive computational cost of testing and poor generalisation in some scenarios, when applied to large training databases. We define person-specific eigenmodes to obtain a set of projection bases, wherein a particular basis captures variation across lightings and viewpoints for a particular person. A new recognition approach is developed utilizing these bases. The proposed approach performs on a par with the existing multilinear approaches, whilst significantly reducing the complexity order of the testing algorithm. 2008 Conference Paper http://hdl.handle.net/20.500.11937/31640 10.1109/ICPR.2008.4761706 IEEE restricted
spellingShingle Rana, Santu
Liu, Wan-Quan
Lazarescu, Mihai
Venkatesh, Svetha
Efficient tensor based face recognition
title Efficient tensor based face recognition
title_full Efficient tensor based face recognition
title_fullStr Efficient tensor based face recognition
title_full_unstemmed Efficient tensor based face recognition
title_short Efficient tensor based face recognition
title_sort efficient tensor based face recognition
url http://hdl.handle.net/20.500.11937/31640