Spectral Face Recognition Using Orthogonal Subspace Bases

Title:
Spectral Face Recognition Using Orthogonal Subspace Bases
Authors:
Wimberly, Andrew; Robila, Stefan A.; Peplau, Tansy
Abstract:
We present an efficient method for facial recognition using hyperspectral imaging and orthogonal subspaces. Projecting the data into orthogonal subspaces has the advantage of compactness and reduction of redundancy. We focus on two approaches: Principal Component Analysis and Orthogonal Subspace Projection. Our work is separated in three stages. First, we designed an experimental setup that allowed us to create a hyperspectral image database of 17 subjects under different facial expressions and viewing angles. Second, we investigated approaches to employ spectral information for the generation of fused grayscale images. Third, we designed and tested a recognition system based on the methods described above. The experimental results show that spectral fusion leads to improvement of recognition accuracy when compared to regular imaging. The work expands on previous band extraction research and has the distinct advantage of being one of the first that combines spatial information (i.e. face characteristics) with spectral information. In addition, the techniques are general enough to accommodate differences in skin spectra.
Citation:
Wimberly, Andrew, Stefan A. Robila, and Tansy Peplau. 2010. "Spectral Face Recognition Using Orthogonal Subspace Bases." Proceedings of SPIE - International Society for Optical Engineering. Conference title: Algorithms And Technologies For Multispectral, Hyperspectral, And Ultraspectral Imagery Xvi 7695: 76952-76952E.
Publisher:
SPIE-International Society for Optical Engineering
DATE ISSUED:
2010
Department:
Computer Science
Type:
article
PUBLISHED VERSION:
10.1117/12.849892
PERMANENT LINK:
http://hdl.handle.net/11282/309958

Full metadata record

DC FieldValue Language
dc.contributor.authorWimberly, Andrewen_US
dc.contributor.authorRobila, Stefan A.en_US
dc.contributor.authorPeplau, Tansyen_US
dc.date.accessioned2013-12-23T16:22:02Zen
dc.date.available2013-12-23T16:22:02Zen
dc.date.issued2010en
dc.identifier.citationWimberly, Andrew, Stefan A. Robila, and Tansy Peplau. 2010. "Spectral Face Recognition Using Orthogonal Subspace Bases." Proceedings of SPIE - International Society for Optical Engineering. Conference title: Algorithms And Technologies For Multispectral, Hyperspectral, And Ultraspectral Imagery Xvi 7695: 76952-76952E.en_US
dc.identifier.issn0277-786Xen_US
dc.identifier.urihttp://hdl.handle.net/11282/309958en
dc.description.abstractWe present an efficient method for facial recognition using hyperspectral imaging and orthogonal subspaces. Projecting the data into orthogonal subspaces has the advantage of compactness and reduction of redundancy. We focus on two approaches: Principal Component Analysis and Orthogonal Subspace Projection. Our work is separated in three stages. First, we designed an experimental setup that allowed us to create a hyperspectral image database of 17 subjects under different facial expressions and viewing angles. Second, we investigated approaches to employ spectral information for the generation of fused grayscale images. Third, we designed and tested a recognition system based on the methods described above. The experimental results show that spectral fusion leads to improvement of recognition accuracy when compared to regular imaging. The work expands on previous band extraction research and has the distinct advantage of being one of the first that combines spatial information (i.e. face characteristics) with spectral information. In addition, the techniques are general enough to accommodate differences in skin spectra.en_US
dc.language.isoen_USen_US
dc.publisherSPIE-International Society for Optical Engineeringen_US
dc.identifier.doi10.1117/12.849892en
dc.subject.departmentComputer Scienceen_US
dc.titleSpectral Face Recognition Using Orthogonal Subspace Basesen_US
dc.typearticleen_US
dc.identifier.journalProceedings of SPIE - International Society for Optical Engineeringen_US
dc.subject.keywordFace recognitionen_US
dc.subject.keywordHyperspectral dataen_US
dc.subject.keywordPrincipal component analysisen_US
dc.subject.keywordOrthogonal subspacesen_US
dc.subject.keywordImage classificationen_US
dc.subject.keywordProjection approachen_US
dc.subject.keywordEigenfacesen_US
dc.subject.keywordOpticsen_US
dc.identifier.volume7695en_US
dc.identifier.startpage76952en_US
All Items in The Five Colleges of Ohio Digital Repository are protected by copyright, with all rights reserved, unless otherwise indicated.