Multi-Fold Gabor, PCA, and ICA Filter Convolution Descriptor for Face Recognition

Cheng Yaw Low, Beng Jin Teoh, Cong Jie Ng

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

This paper devises a new means of filter diversification, dubbed multi-fold filter convolution (FFC), for face recognition. On the assumption that FFC receives single-scale Gabor filters of varying orientations as input, these filters are self-cross convolved by fold to instantiate a filter offspring set. The FFC flexibility also permits cross convolution amongst Gabor filters and other filter banks of profoundly dissimilar traits, e.g., principal component analysis (PCA) filters and independent component analysis (ICA) filters. The 2-FFC of Gabor, PCA, and ICA filters thus yields three offspring sets: 1) Gabor filters solely; 2) Gabor-PCA filters; and 3) Gabor-ICA filters, to render the learning-free and the learning-based 2-FFC descriptors. To facilitate a sensible Gabor filter selection for FFC, the 40 multi-scale, multi-orientation Gabor filters are condensed into eight elementary filters. Aside from that, an average histogram pooling operator is employed to leverage the 2-FFC histogram features, prior to the final whitening PCA compression. The empirical results substantiate that the 2-FFC descriptors prevail over, or on par with, other face descriptors on both identification and verification tasks.

Original languageEnglish
Article number8063938
Pages (from-to)115-129
Number of pages15
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume29
Issue number1
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Independent component analysis
Face recognition
Convolution
Principal component analysis
Gabor filters
Filter banks
Mathematical operators

All Science Journal Classification (ASJC) codes

  • Media Technology
  • Electrical and Electronic Engineering

Cite this

@article{cce33612649b4bf580f2b8b8daa0d7e5,
title = "Multi-Fold Gabor, PCA, and ICA Filter Convolution Descriptor for Face Recognition",
abstract = "This paper devises a new means of filter diversification, dubbed multi-fold filter convolution (FFC), for face recognition. On the assumption that FFC receives single-scale Gabor filters of varying orientations as input, these filters are self-cross convolved by fold to instantiate a filter offspring set. The FFC flexibility also permits cross convolution amongst Gabor filters and other filter banks of profoundly dissimilar traits, e.g., principal component analysis (PCA) filters and independent component analysis (ICA) filters. The 2-FFC of Gabor, PCA, and ICA filters thus yields three offspring sets: 1) Gabor filters solely; 2) Gabor-PCA filters; and 3) Gabor-ICA filters, to render the learning-free and the learning-based 2-FFC descriptors. To facilitate a sensible Gabor filter selection for FFC, the 40 multi-scale, multi-orientation Gabor filters are condensed into eight elementary filters. Aside from that, an average histogram pooling operator is employed to leverage the 2-FFC histogram features, prior to the final whitening PCA compression. The empirical results substantiate that the 2-FFC descriptors prevail over, or on par with, other face descriptors on both identification and verification tasks.",
author = "Low, {Cheng Yaw} and Teoh, {Beng Jin} and Ng, {Cong Jie}",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/TCSVT.2017.2761829",
language = "English",
volume = "29",
pages = "115--129",
journal = "IEEE Transactions on Circuits and Systems for Video Technology",
issn = "1051-8215",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

Multi-Fold Gabor, PCA, and ICA Filter Convolution Descriptor for Face Recognition. / Low, Cheng Yaw; Teoh, Beng Jin; Ng, Cong Jie.

In: IEEE Transactions on Circuits and Systems for Video Technology, Vol. 29, No. 1, 8063938, 01.01.2019, p. 115-129.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Multi-Fold Gabor, PCA, and ICA Filter Convolution Descriptor for Face Recognition

AU - Low, Cheng Yaw

AU - Teoh, Beng Jin

AU - Ng, Cong Jie

PY - 2019/1/1

Y1 - 2019/1/1

N2 - This paper devises a new means of filter diversification, dubbed multi-fold filter convolution (FFC), for face recognition. On the assumption that FFC receives single-scale Gabor filters of varying orientations as input, these filters are self-cross convolved by fold to instantiate a filter offspring set. The FFC flexibility also permits cross convolution amongst Gabor filters and other filter banks of profoundly dissimilar traits, e.g., principal component analysis (PCA) filters and independent component analysis (ICA) filters. The 2-FFC of Gabor, PCA, and ICA filters thus yields three offspring sets: 1) Gabor filters solely; 2) Gabor-PCA filters; and 3) Gabor-ICA filters, to render the learning-free and the learning-based 2-FFC descriptors. To facilitate a sensible Gabor filter selection for FFC, the 40 multi-scale, multi-orientation Gabor filters are condensed into eight elementary filters. Aside from that, an average histogram pooling operator is employed to leverage the 2-FFC histogram features, prior to the final whitening PCA compression. The empirical results substantiate that the 2-FFC descriptors prevail over, or on par with, other face descriptors on both identification and verification tasks.

AB - This paper devises a new means of filter diversification, dubbed multi-fold filter convolution (FFC), for face recognition. On the assumption that FFC receives single-scale Gabor filters of varying orientations as input, these filters are self-cross convolved by fold to instantiate a filter offspring set. The FFC flexibility also permits cross convolution amongst Gabor filters and other filter banks of profoundly dissimilar traits, e.g., principal component analysis (PCA) filters and independent component analysis (ICA) filters. The 2-FFC of Gabor, PCA, and ICA filters thus yields three offspring sets: 1) Gabor filters solely; 2) Gabor-PCA filters; and 3) Gabor-ICA filters, to render the learning-free and the learning-based 2-FFC descriptors. To facilitate a sensible Gabor filter selection for FFC, the 40 multi-scale, multi-orientation Gabor filters are condensed into eight elementary filters. Aside from that, an average histogram pooling operator is employed to leverage the 2-FFC histogram features, prior to the final whitening PCA compression. The empirical results substantiate that the 2-FFC descriptors prevail over, or on par with, other face descriptors on both identification and verification tasks.

UR - http://www.scopus.com/inward/record.url?scp=85031898687&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85031898687&partnerID=8YFLogxK

U2 - 10.1109/TCSVT.2017.2761829

DO - 10.1109/TCSVT.2017.2761829

M3 - Article

VL - 29

SP - 115

EP - 129

JO - IEEE Transactions on Circuits and Systems for Video Technology

JF - IEEE Transactions on Circuits and Systems for Video Technology

SN - 1051-8215

IS - 1

M1 - 8063938

ER -