Recognition using robust bit extraction

We present a novel technique for extracting bits from the perceptually significant components of an image transformation, thus making the recognition of objects under nonideal conditions robust. Specifically, we describe five popular face recognition transform methods [ including principal component...

Full description

Bibliographic Details
Main Authors: Ngo, David C. L., Goh, Alwyn, Teoh, Andrew B. J.
Format: Article
Published: 2005
Subjects:
Online Access:http://shdl.mmu.edu.my/2183/
_version_ 1848789986779856896
author Ngo, David C. L.
Goh, Alwyn
Teoh, Andrew B. J.
author_facet Ngo, David C. L.
Goh, Alwyn
Teoh, Andrew B. J.
author_sort Ngo, David C. L.
building MMU Institutional Repository
collection Online Access
description We present a novel technique for extracting bits from the perceptually significant components of an image transformation, thus making the recognition of objects under nonideal conditions robust. Specifically, we describe five popular face recognition transform methods [ including principal component analysis ( PCA), linear discriminant analysis ( LDA), wavelet transform, wavelet transform with PCA, and wavelet transform with Fourier-Mellin transform] with robust bit extraction enhancement for various numbers of bits extracted. The robustness guarantees that all similar face images will produce almost the same bits. This property is useful for generating cryptographic keys. The theoretical results are evaluated on the Olivetti Research Laboratory ( ORL) face database, showing that the extended methods significantly outperform the corresponding standard methods when the number of extracted bits reaches 100. (c) 2005 SPIE and IS&T.
first_indexed 2025-11-14T18:05:26Z
format Article
id mmu-2183
institution Multimedia University
institution_category Local University
last_indexed 2025-11-14T18:05:26Z
publishDate 2005
recordtype eprints
repository_type Digital Repository
spelling mmu-21832011-09-12T05:50:31Z http://shdl.mmu.edu.my/2183/ Recognition using robust bit extraction Ngo, David C. L. Goh, Alwyn Teoh, Andrew B. J. TA Engineering (General). Civil engineering (General) We present a novel technique for extracting bits from the perceptually significant components of an image transformation, thus making the recognition of objects under nonideal conditions robust. Specifically, we describe five popular face recognition transform methods [ including principal component analysis ( PCA), linear discriminant analysis ( LDA), wavelet transform, wavelet transform with PCA, and wavelet transform with Fourier-Mellin transform] with robust bit extraction enhancement for various numbers of bits extracted. The robustness guarantees that all similar face images will produce almost the same bits. This property is useful for generating cryptographic keys. The theoretical results are evaluated on the Olivetti Research Laboratory ( ORL) face database, showing that the extended methods significantly outperform the corresponding standard methods when the number of extracted bits reaches 100. (c) 2005 SPIE and IS&T. 2005-10 Article NonPeerReviewed Ngo, David C. L. and Goh, Alwyn and Teoh, Andrew B. J. (2005) Recognition using robust bit extraction. Journal of Electronic Imaging, 14 (4). 043016. ISSN 10179909 http://dx.doi.org/10.1117/1.2135321 doi:10.1117/1.2135321 doi:10.1117/1.2135321
spellingShingle TA Engineering (General). Civil engineering (General)
Ngo, David C. L.
Goh, Alwyn
Teoh, Andrew B. J.
Recognition using robust bit extraction
title Recognition using robust bit extraction
title_full Recognition using robust bit extraction
title_fullStr Recognition using robust bit extraction
title_full_unstemmed Recognition using robust bit extraction
title_short Recognition using robust bit extraction
title_sort recognition using robust bit extraction
topic TA Engineering (General). Civil engineering (General)
url http://shdl.mmu.edu.my/2183/
http://shdl.mmu.edu.my/2183/
http://shdl.mmu.edu.my/2183/