An Analytic Gabor Feedforward Network for Single-Sample and Pose-Invariant Face Recognition

Beom Seok Oh, Kar Ann Toh, Beng Jin Teoh, Zhiping Lin

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Gabor magnitude is known to be among the most discriminative representations for face images due to its space- frequency co-localization property. However, such property causes adverse effects even when the images are acquired under moderate head pose variations. To address this pose sensitivity issue and other moderate imaging variations, we propose an analytic Gabor feedforward network which can absorb such moderate changes. Essentially, the network works directly on the raw face images and produces directionally projected Gabor magnitude features at the hidden layer. Subsequently, several sets of magnitude features obtained from various orientations and scales are fused at the output layer for final classification decision. The network model is analytically trained using a single sample per identity. The obtained solution is globally optimal with respect to the classification total error rate. Our empirical experiments conducted on five face data sets (six subsets) from the public domain show encouraging results in terms of identification accuracy and computational efficiency.

Original languageEnglish
Pages (from-to)2791-2805
Number of pages15
JournalIEEE Transactions on Image Processing
Volume27
Issue number6
DOIs
Publication statusPublished - 2018 Jun 1

Fingerprint

Face recognition
Computational efficiency
Imaging techniques
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Graphics and Computer-Aided Design

Cite this

@article{d4855a331a35401589df10aa417d4f68,
title = "An Analytic Gabor Feedforward Network for Single-Sample and Pose-Invariant Face Recognition",
abstract = "Gabor magnitude is known to be among the most discriminative representations for face images due to its space- frequency co-localization property. However, such property causes adverse effects even when the images are acquired under moderate head pose variations. To address this pose sensitivity issue and other moderate imaging variations, we propose an analytic Gabor feedforward network which can absorb such moderate changes. Essentially, the network works directly on the raw face images and produces directionally projected Gabor magnitude features at the hidden layer. Subsequently, several sets of magnitude features obtained from various orientations and scales are fused at the output layer for final classification decision. The network model is analytically trained using a single sample per identity. The obtained solution is globally optimal with respect to the classification total error rate. Our empirical experiments conducted on five face data sets (six subsets) from the public domain show encouraging results in terms of identification accuracy and computational efficiency.",
author = "Oh, {Beom Seok} and Toh, {Kar Ann} and Teoh, {Beng Jin} and Zhiping Lin",
year = "2018",
month = "6",
day = "1",
doi = "10.1109/TIP.2018.2809040",
language = "English",
volume = "27",
pages = "2791--2805",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

An Analytic Gabor Feedforward Network for Single-Sample and Pose-Invariant Face Recognition. / Oh, Beom Seok; Toh, Kar Ann; Teoh, Beng Jin; Lin, Zhiping.

In: IEEE Transactions on Image Processing, Vol. 27, No. 6, 01.06.2018, p. 2791-2805.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An Analytic Gabor Feedforward Network for Single-Sample and Pose-Invariant Face Recognition

AU - Oh, Beom Seok

AU - Toh, Kar Ann

AU - Teoh, Beng Jin

AU - Lin, Zhiping

PY - 2018/6/1

Y1 - 2018/6/1

N2 - Gabor magnitude is known to be among the most discriminative representations for face images due to its space- frequency co-localization property. However, such property causes adverse effects even when the images are acquired under moderate head pose variations. To address this pose sensitivity issue and other moderate imaging variations, we propose an analytic Gabor feedforward network which can absorb such moderate changes. Essentially, the network works directly on the raw face images and produces directionally projected Gabor magnitude features at the hidden layer. Subsequently, several sets of magnitude features obtained from various orientations and scales are fused at the output layer for final classification decision. The network model is analytically trained using a single sample per identity. The obtained solution is globally optimal with respect to the classification total error rate. Our empirical experiments conducted on five face data sets (six subsets) from the public domain show encouraging results in terms of identification accuracy and computational efficiency.

AB - Gabor magnitude is known to be among the most discriminative representations for face images due to its space- frequency co-localization property. However, such property causes adverse effects even when the images are acquired under moderate head pose variations. To address this pose sensitivity issue and other moderate imaging variations, we propose an analytic Gabor feedforward network which can absorb such moderate changes. Essentially, the network works directly on the raw face images and produces directionally projected Gabor magnitude features at the hidden layer. Subsequently, several sets of magnitude features obtained from various orientations and scales are fused at the output layer for final classification decision. The network model is analytically trained using a single sample per identity. The obtained solution is globally optimal with respect to the classification total error rate. Our empirical experiments conducted on five face data sets (six subsets) from the public domain show encouraging results in terms of identification accuracy and computational efficiency.

UR - http://www.scopus.com/inward/record.url?scp=85042720499&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042720499&partnerID=8YFLogxK

U2 - 10.1109/TIP.2018.2809040

DO - 10.1109/TIP.2018.2809040

M3 - Article

C2 - 29570082

AN - SCOPUS:85042720499

VL - 27

SP - 2791

EP - 2805

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 6

ER -