Recognition using robust bit extraction

David C.L. Ngo, Alwyn Goh, Andrew B.J. Teoh

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

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.

Original languageEnglish
Article number043016
JournalJournal of Electronic Imaging
Volume14
Issue number4
DOIs
Publication statusPublished - 2005 Oct 1

Fingerprint

wavelet analysis
Wavelet transforms
principal components analysis
Principal component analysis
Mellin transforms
Discriminant analysis
Research laboratories
Face recognition
Fourier transforms
augmentation

All Science Journal Classification (ASJC) codes

  • Atomic and Molecular Physics, and Optics
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Ngo, David C.L. ; Goh, Alwyn ; Teoh, Andrew B.J. / Recognition using robust bit extraction. In: Journal of Electronic Imaging. 2005 ; Vol. 14, No. 4.
@article{59cee0f254084a00be3e1caa9dd495dc,
title = "Recognition using robust bit extraction",
abstract = "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.",
author = "Ngo, {David C.L.} and Alwyn Goh and Teoh, {Andrew B.J.}",
year = "2005",
month = "10",
day = "1",
doi = "10.1117/1.2135321",
language = "English",
volume = "14",
journal = "Journal of Electronic Imaging",
issn = "1017-9909",
publisher = "SPIE",
number = "4",

}

Recognition using robust bit extraction. / Ngo, David C.L.; Goh, Alwyn; Teoh, Andrew B.J.

In: Journal of Electronic Imaging, Vol. 14, No. 4, 043016, 01.10.2005.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Recognition using robust bit extraction

AU - Ngo, David C.L.

AU - Goh, Alwyn

AU - Teoh, Andrew B.J.

PY - 2005/10/1

Y1 - 2005/10/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=33644662906&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33644662906&partnerID=8YFLogxK

U2 - 10.1117/1.2135321

DO - 10.1117/1.2135321

M3 - Article

AN - SCOPUS:33644662906

VL - 14

JO - Journal of Electronic Imaging

JF - Journal of Electronic Imaging

SN - 1017-9909

IS - 4

M1 - 043016

ER -