Stacking PCANet +: An Overly Simplified ConvNets Baseline for Face Recognition

Cheng Yaw Low, Beng Jin Teoh, Kar Ann Toh

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

The principal component analysis network (PCANet) is asserted as a parsimonious stacking-based convolutional neural networks (CNNs) instance for generic object recognition including face. However, to be regarded a CNN resemblance, PCANet lacks a nonlinearity in between two successive convolutional layers. The multilayer PCANet (by neglecting the nonlinearity pre-requisite) is also deemed far-fetched for the network depth beyond two, due to feature dimensionality explosion. We thus devise a PCANet alternative, dubbed PCANet+ in this letter, to untangle these constraints. To be more precise, conforming to the CNN essentials, PCANet+ conveys a mean-pooling unit manipulating each feature map. On top of that, we streamline the PCANet topology to permit a deep construction with an expanded PCA filter ensemble. We scrutinize the PCANet+ performance using face recognition technology and other two faces in the wild datasets, namely, labeled faces in the wild and YouTube faces. The experimental results reveal that the PCANet+ descriptor prevails over its predecessor and other stacking-based descriptors in face identification and verification, serving a baseline for ConvNets.

Original languageEnglish
Article number8027103
Pages (from-to)1581-1585
Number of pages5
JournalIEEE Signal Processing Letters
Volume24
Issue number11
DOIs
Publication statusPublished - 2017 Nov 1

Fingerprint

Stacking
Face recognition
Face Recognition
Principal component analysis
Principal Component Analysis
Baseline
Face
Neural Networks
Neural networks
Descriptors
Nonlinearity
Pooling
Object recognition
Object Recognition
Network Performance
Streamlines
Network performance
Network Topology
Explosion
Explosions

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering
  • Applied Mathematics

Cite this

@article{c23ff668612f4bbeaef9980a47960c2b,
title = "Stacking PCANet +: An Overly Simplified ConvNets Baseline for Face Recognition",
abstract = "The principal component analysis network (PCANet) is asserted as a parsimonious stacking-based convolutional neural networks (CNNs) instance for generic object recognition including face. However, to be regarded a CNN resemblance, PCANet lacks a nonlinearity in between two successive convolutional layers. The multilayer PCANet (by neglecting the nonlinearity pre-requisite) is also deemed far-fetched for the network depth beyond two, due to feature dimensionality explosion. We thus devise a PCANet alternative, dubbed PCANet+ in this letter, to untangle these constraints. To be more precise, conforming to the CNN essentials, PCANet+ conveys a mean-pooling unit manipulating each feature map. On top of that, we streamline the PCANet topology to permit a deep construction with an expanded PCA filter ensemble. We scrutinize the PCANet+ performance using face recognition technology and other two faces in the wild datasets, namely, labeled faces in the wild and YouTube faces. The experimental results reveal that the PCANet+ descriptor prevails over its predecessor and other stacking-based descriptors in face identification and verification, serving a baseline for ConvNets.",
author = "Low, {Cheng Yaw} and Teoh, {Beng Jin} and Toh, {Kar Ann}",
year = "2017",
month = "11",
day = "1",
doi = "10.1109/LSP.2017.2749763",
language = "English",
volume = "24",
pages = "1581--1585",
journal = "IEEE Signal Processing Letters",
issn = "1070-9908",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "11",

}

Stacking PCANet + : An Overly Simplified ConvNets Baseline for Face Recognition. / Low, Cheng Yaw; Teoh, Beng Jin; Toh, Kar Ann.

In: IEEE Signal Processing Letters, Vol. 24, No. 11, 8027103, 01.11.2017, p. 1581-1585.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Stacking PCANet +

T2 - An Overly Simplified ConvNets Baseline for Face Recognition

AU - Low, Cheng Yaw

AU - Teoh, Beng Jin

AU - Toh, Kar Ann

PY - 2017/11/1

Y1 - 2017/11/1

N2 - The principal component analysis network (PCANet) is asserted as a parsimonious stacking-based convolutional neural networks (CNNs) instance for generic object recognition including face. However, to be regarded a CNN resemblance, PCANet lacks a nonlinearity in between two successive convolutional layers. The multilayer PCANet (by neglecting the nonlinearity pre-requisite) is also deemed far-fetched for the network depth beyond two, due to feature dimensionality explosion. We thus devise a PCANet alternative, dubbed PCANet+ in this letter, to untangle these constraints. To be more precise, conforming to the CNN essentials, PCANet+ conveys a mean-pooling unit manipulating each feature map. On top of that, we streamline the PCANet topology to permit a deep construction with an expanded PCA filter ensemble. We scrutinize the PCANet+ performance using face recognition technology and other two faces in the wild datasets, namely, labeled faces in the wild and YouTube faces. The experimental results reveal that the PCANet+ descriptor prevails over its predecessor and other stacking-based descriptors in face identification and verification, serving a baseline for ConvNets.

AB - The principal component analysis network (PCANet) is asserted as a parsimonious stacking-based convolutional neural networks (CNNs) instance for generic object recognition including face. However, to be regarded a CNN resemblance, PCANet lacks a nonlinearity in between two successive convolutional layers. The multilayer PCANet (by neglecting the nonlinearity pre-requisite) is also deemed far-fetched for the network depth beyond two, due to feature dimensionality explosion. We thus devise a PCANet alternative, dubbed PCANet+ in this letter, to untangle these constraints. To be more precise, conforming to the CNN essentials, PCANet+ conveys a mean-pooling unit manipulating each feature map. On top of that, we streamline the PCANet topology to permit a deep construction with an expanded PCA filter ensemble. We scrutinize the PCANet+ performance using face recognition technology and other two faces in the wild datasets, namely, labeled faces in the wild and YouTube faces. The experimental results reveal that the PCANet+ descriptor prevails over its predecessor and other stacking-based descriptors in face identification and verification, serving a baseline for ConvNets.

UR - http://www.scopus.com/inward/record.url?scp=85029160419&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029160419&partnerID=8YFLogxK

U2 - 10.1109/LSP.2017.2749763

DO - 10.1109/LSP.2017.2749763

M3 - Article

AN - SCOPUS:85029160419

VL - 24

SP - 1581

EP - 1585

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

SN - 1070-9908

IS - 11

M1 - 8027103

ER -