Tensor Based Robust Color Face Recognition

In this paper we address the robust face recognition problem for color faces with large variations in pose, illumination and facial expression. A novel algorithm is proposed, namely the Multilinear Color Tensor Discriminant (MCTD) model. This approach utilizes tensor representation to preserve image...

Full description

Bibliographic Details
Main Authors: Li, Billy, Liu, Wan-Quan, An, Senjian, Krishna, Aneesh
Other Authors: Eklundh, J-O.
Format: Conference Paper
Published: Institute of Electrical and Electronics Engineers (IEEE) 2012
Online Access:http://f4k.dieei.unict.it/proceedings/ICPR2012/media/files/0681.pdf
http://hdl.handle.net/20.500.11937/31374
_version_ 1848753362215895040
author Li, Billy
Liu, Wan-Quan
An, Senjian
Krishna, Aneesh
author2 Eklundh, J-O.
author_facet Eklundh, J-O.
Li, Billy
Liu, Wan-Quan
An, Senjian
Krishna, Aneesh
author_sort Li, Billy
building Curtin Institutional Repository
collection Online Access
description In this paper we address the robust face recognition problem for color faces with large variations in pose, illumination and facial expression. A novel algorithm is proposed, namely the Multilinear Color Tensor Discriminant (MCTD) model. This approach utilizes tensor representation to preserve image structure, as well as enhance discriminate capability via color space transformation. On the other hand, it uses the multilinear analysis technique to handle variations in pose, illumination and expressions and improve the performance via minimizing the least square of reconstruction error in the tensor framework. Extensive experiments conducted on the CMU-PIE and CurtinFaces databases demonstrate the effectiveness of the proposed approach.
first_indexed 2025-11-14T08:23:18Z
format Conference Paper
id curtin-20.500.11937-31374
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T08:23:18Z
publishDate 2012
publisher Institute of Electrical and Electronics Engineers (IEEE)
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-313742023-02-07T08:01:19Z Tensor Based Robust Color Face Recognition Li, Billy Liu, Wan-Quan An, Senjian Krishna, Aneesh Eklundh, J-O. Ohta, Y. Tanimoto, S. In this paper we address the robust face recognition problem for color faces with large variations in pose, illumination and facial expression. A novel algorithm is proposed, namely the Multilinear Color Tensor Discriminant (MCTD) model. This approach utilizes tensor representation to preserve image structure, as well as enhance discriminate capability via color space transformation. On the other hand, it uses the multilinear analysis technique to handle variations in pose, illumination and expressions and improve the performance via minimizing the least square of reconstruction error in the tensor framework. Extensive experiments conducted on the CMU-PIE and CurtinFaces databases demonstrate the effectiveness of the proposed approach. 2012 Conference Paper http://hdl.handle.net/20.500.11937/31374 http://f4k.dieei.unict.it/proceedings/ICPR2012/media/files/0681.pdf Institute of Electrical and Electronics Engineers (IEEE) restricted
spellingShingle Li, Billy
Liu, Wan-Quan
An, Senjian
Krishna, Aneesh
Tensor Based Robust Color Face Recognition
title Tensor Based Robust Color Face Recognition
title_full Tensor Based Robust Color Face Recognition
title_fullStr Tensor Based Robust Color Face Recognition
title_full_unstemmed Tensor Based Robust Color Face Recognition
title_short Tensor Based Robust Color Face Recognition
title_sort tensor based robust color face recognition
url http://f4k.dieei.unict.it/proceedings/ICPR2012/media/files/0681.pdf
http://hdl.handle.net/20.500.11937/31374