Face recognition using various scales of discriminant color space transform

Research on color face recognition in the existing literature is aimed to establish a color space that can have the most of the discriminative information from the original data. This mainly includes optimal combination of different color components from the original color space. Recently proposed d...

Full description

Bibliographic Details
Main Authors: Li, Billy, Liu, Wan-Quan, An, Senjian, Krishna, Aneesh, Xu, T.
Format: Journal Article
Published: Elsevier Science B.V. 2012
Online Access:http://hdl.handle.net/20.500.11937/41340
_version_ 1848756118252158976
author Li, Billy
Liu, Wan-Quan
An, Senjian
Krishna, Aneesh
Xu, T.
author_facet Li, Billy
Liu, Wan-Quan
An, Senjian
Krishna, Aneesh
Xu, T.
author_sort Li, Billy
building Curtin Institutional Repository
collection Online Access
description Research on color face recognition in the existing literature is aimed to establish a color space that can have the most of the discriminative information from the original data. This mainly includes optimal combination of different color components from the original color space. Recently proposed discriminate color space (DCS) is theoretically optimal for classification, in which one seeks a set of optimal coefficients in terms of linear combinations of the R, G and B components (based on a discriminate criterion). This work proposes an innovative block-wise DCS (BWDCS) method, which allows each block of the image to be in a distinct DCS. This is an interesting alternative to the methods relying on converting whole image to DCS. This idea is evaluated with four appearance-based subspace state-of-the-art methods on five different publicly available databases including the well-known FERET and FRGC databases. Experimental results show that the performance of these four gray-scale based methods can be improved by 17% on average when they are used with the proposed color space.
first_indexed 2025-11-14T09:07:07Z
format Journal Article
id curtin-20.500.11937-41340
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:07:07Z
publishDate 2012
publisher Elsevier Science B.V.
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-413402017-09-13T14:10:12Z Face recognition using various scales of discriminant color space transform Li, Billy Liu, Wan-Quan An, Senjian Krishna, Aneesh Xu, T. Research on color face recognition in the existing literature is aimed to establish a color space that can have the most of the discriminative information from the original data. This mainly includes optimal combination of different color components from the original color space. Recently proposed discriminate color space (DCS) is theoretically optimal for classification, in which one seeks a set of optimal coefficients in terms of linear combinations of the R, G and B components (based on a discriminate criterion). This work proposes an innovative block-wise DCS (BWDCS) method, which allows each block of the image to be in a distinct DCS. This is an interesting alternative to the methods relying on converting whole image to DCS. This idea is evaluated with four appearance-based subspace state-of-the-art methods on five different publicly available databases including the well-known FERET and FRGC databases. Experimental results show that the performance of these four gray-scale based methods can be improved by 17% on average when they are used with the proposed color space. 2012 Journal Article http://hdl.handle.net/20.500.11937/41340 10.1016/j.neucom.2012.04.005 Elsevier Science B.V. restricted
spellingShingle Li, Billy
Liu, Wan-Quan
An, Senjian
Krishna, Aneesh
Xu, T.
Face recognition using various scales of discriminant color space transform
title Face recognition using various scales of discriminant color space transform
title_full Face recognition using various scales of discriminant color space transform
title_fullStr Face recognition using various scales of discriminant color space transform
title_full_unstemmed Face recognition using various scales of discriminant color space transform
title_short Face recognition using various scales of discriminant color space transform
title_sort face recognition using various scales of discriminant color space transform
url http://hdl.handle.net/20.500.11937/41340