Fusion of visual and infrared face verification systems

Byounggyu Choi, Youngsung Kim, Kar Ann Toh

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper presents a two-stage procedure to combine multiple face traits for identity authentication. At the first stage, a high dimensional random projection is applied to the raw visual and infrared face images to extract useful information relevant to each identity. This is followed by a dimension reduction using eigenfeature regularization and extraction (ERE). At the second stage, the scores from two verification systems based on each face modality are fused by an error minimization algorithm. This error minimization algorithm directly optimizes the verification accuracy by adjusting the parameters of a polynomial classifier. Two data sets consisting of visual and infrared face images have been used for experimentation. Our empirical observation shows encouraging results regarding the effectiveness of the proposed method.

Original languageEnglish
Pages (from-to)500-514
Number of pages15
JournalSecurity and Communication Networks
Volume4
Issue number5
DOIs
Publication statusPublished - 2011 May

Fingerprint

Fusion reactions
Infrared radiation
Authentication
Classifiers
Polynomials

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Computer Networks and Communications

Cite this

Choi, Byounggyu ; Kim, Youngsung ; Toh, Kar Ann. / Fusion of visual and infrared face verification systems. In: Security and Communication Networks. 2011 ; Vol. 4, No. 5. pp. 500-514.
@article{3a77d964bc4447c8a07550ffdb21d2b6,
title = "Fusion of visual and infrared face verification systems",
abstract = "This paper presents a two-stage procedure to combine multiple face traits for identity authentication. At the first stage, a high dimensional random projection is applied to the raw visual and infrared face images to extract useful information relevant to each identity. This is followed by a dimension reduction using eigenfeature regularization and extraction (ERE). At the second stage, the scores from two verification systems based on each face modality are fused by an error minimization algorithm. This error minimization algorithm directly optimizes the verification accuracy by adjusting the parameters of a polynomial classifier. Two data sets consisting of visual and infrared face images have been used for experimentation. Our empirical observation shows encouraging results regarding the effectiveness of the proposed method.",
author = "Byounggyu Choi and Youngsung Kim and Toh, {Kar Ann}",
year = "2011",
month = "5",
doi = "10.1002/sec.251",
language = "English",
volume = "4",
pages = "500--514",
journal = "Security and Communication Networks",
issn = "1939-0114",
publisher = "John Wiley and Sons Inc.",
number = "5",

}

Fusion of visual and infrared face verification systems. / Choi, Byounggyu; Kim, Youngsung; Toh, Kar Ann.

In: Security and Communication Networks, Vol. 4, No. 5, 05.2011, p. 500-514.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Fusion of visual and infrared face verification systems

AU - Choi, Byounggyu

AU - Kim, Youngsung

AU - Toh, Kar Ann

PY - 2011/5

Y1 - 2011/5

N2 - This paper presents a two-stage procedure to combine multiple face traits for identity authentication. At the first stage, a high dimensional random projection is applied to the raw visual and infrared face images to extract useful information relevant to each identity. This is followed by a dimension reduction using eigenfeature regularization and extraction (ERE). At the second stage, the scores from two verification systems based on each face modality are fused by an error minimization algorithm. This error minimization algorithm directly optimizes the verification accuracy by adjusting the parameters of a polynomial classifier. Two data sets consisting of visual and infrared face images have been used for experimentation. Our empirical observation shows encouraging results regarding the effectiveness of the proposed method.

AB - This paper presents a two-stage procedure to combine multiple face traits for identity authentication. At the first stage, a high dimensional random projection is applied to the raw visual and infrared face images to extract useful information relevant to each identity. This is followed by a dimension reduction using eigenfeature regularization and extraction (ERE). At the second stage, the scores from two verification systems based on each face modality are fused by an error minimization algorithm. This error minimization algorithm directly optimizes the verification accuracy by adjusting the parameters of a polynomial classifier. Two data sets consisting of visual and infrared face images have been used for experimentation. Our empirical observation shows encouraging results regarding the effectiveness of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=79954993376&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79954993376&partnerID=8YFLogxK

U2 - 10.1002/sec.251

DO - 10.1002/sec.251

M3 - Article

AN - SCOPUS:79954993376

VL - 4

SP - 500

EP - 514

JO - Security and Communication Networks

JF - Security and Communication Networks

SN - 1939-0114

IS - 5

ER -