Discriminative kernel-based metric learning for face verification

Siew Chin Chong, Thian Song Ong, Beng Jin Teoh

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This paper outlines a simplistic formulation for doublet constrained discriminative metric learning framework for face verification. The Mahalanobis distance metric of the framework is formulated by leveraging the within-class scatter matrix of the doublet and a quadratic kernel function. Unlike existing metric learning methods, the proposed framework admits efficient solution attributed to the convexity nature of the kernel machines. We demonstrate three realizations of the proposed framework based on the well-known kernel machine instances, namely Support Vector Machine, Kernel Ridge Regression and Least Squares Support Vector Machine. Due to wide availability of off-the-shelf kernel learner solvers, the proposed method can be easily trained and deployed. We evaluate the proposed discriminative kernel-based metric learning with two types of face verification setup: standard and unconstrained face verification through three benchmark datasets. The promising experimental results corroborate the feasibility and robustness of the proposed framework.

Original languageEnglish
Pages (from-to)207-219
Number of pages13
JournalJournal of Visual Communication and Image Representation
Volume56
DOIs
Publication statusPublished - 2018 Oct 1

Fingerprint

Support vector machines
Availability

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Media Technology
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

@article{2e623a0c4b0147cb954c8f80b787121b,
title = "Discriminative kernel-based metric learning for face verification",
abstract = "This paper outlines a simplistic formulation for doublet constrained discriminative metric learning framework for face verification. The Mahalanobis distance metric of the framework is formulated by leveraging the within-class scatter matrix of the doublet and a quadratic kernel function. Unlike existing metric learning methods, the proposed framework admits efficient solution attributed to the convexity nature of the kernel machines. We demonstrate three realizations of the proposed framework based on the well-known kernel machine instances, namely Support Vector Machine, Kernel Ridge Regression and Least Squares Support Vector Machine. Due to wide availability of off-the-shelf kernel learner solvers, the proposed method can be easily trained and deployed. We evaluate the proposed discriminative kernel-based metric learning with two types of face verification setup: standard and unconstrained face verification through three benchmark datasets. The promising experimental results corroborate the feasibility and robustness of the proposed framework.",
author = "Chong, {Siew Chin} and Ong, {Thian Song} and Teoh, {Beng Jin}",
year = "2018",
month = "10",
day = "1",
doi = "10.1016/j.jvcir.2018.09.017",
language = "English",
volume = "56",
pages = "207--219",
journal = "Journal of Visual Communication and Image Representation",
issn = "1047-3203",
publisher = "Academic Press Inc.",

}

Discriminative kernel-based metric learning for face verification. / Chong, Siew Chin; Ong, Thian Song; Teoh, Beng Jin.

In: Journal of Visual Communication and Image Representation, Vol. 56, 01.10.2018, p. 207-219.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Discriminative kernel-based metric learning for face verification

AU - Chong, Siew Chin

AU - Ong, Thian Song

AU - Teoh, Beng Jin

PY - 2018/10/1

Y1 - 2018/10/1

N2 - This paper outlines a simplistic formulation for doublet constrained discriminative metric learning framework for face verification. The Mahalanobis distance metric of the framework is formulated by leveraging the within-class scatter matrix of the doublet and a quadratic kernel function. Unlike existing metric learning methods, the proposed framework admits efficient solution attributed to the convexity nature of the kernel machines. We demonstrate three realizations of the proposed framework based on the well-known kernel machine instances, namely Support Vector Machine, Kernel Ridge Regression and Least Squares Support Vector Machine. Due to wide availability of off-the-shelf kernel learner solvers, the proposed method can be easily trained and deployed. We evaluate the proposed discriminative kernel-based metric learning with two types of face verification setup: standard and unconstrained face verification through three benchmark datasets. The promising experimental results corroborate the feasibility and robustness of the proposed framework.

AB - This paper outlines a simplistic formulation for doublet constrained discriminative metric learning framework for face verification. The Mahalanobis distance metric of the framework is formulated by leveraging the within-class scatter matrix of the doublet and a quadratic kernel function. Unlike existing metric learning methods, the proposed framework admits efficient solution attributed to the convexity nature of the kernel machines. We demonstrate three realizations of the proposed framework based on the well-known kernel machine instances, namely Support Vector Machine, Kernel Ridge Regression and Least Squares Support Vector Machine. Due to wide availability of off-the-shelf kernel learner solvers, the proposed method can be easily trained and deployed. We evaluate the proposed discriminative kernel-based metric learning with two types of face verification setup: standard and unconstrained face verification through three benchmark datasets. The promising experimental results corroborate the feasibility and robustness of the proposed framework.

UR - http://www.scopus.com/inward/record.url?scp=85054196882&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054196882&partnerID=8YFLogxK

U2 - 10.1016/j.jvcir.2018.09.017

DO - 10.1016/j.jvcir.2018.09.017

M3 - Article

AN - SCOPUS:85054196882

VL - 56

SP - 207

EP - 219

JO - Journal of Visual Communication and Image Representation

JF - Journal of Visual Communication and Image Representation

SN - 1047-3203

ER -