Face recognition using histogram-based features in spatial and frequency domains

Qiu Chen; Koji Kotani; Feifei Lee; Tadahiro Ohmi

Face recognition using histogram-based features in spatial and frequency domains

Qiu Chen, Koji Kotani, Feifei Lee, Tadahiro Ohmi

ENG - Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Previously, we proposed an efficient algorithm using vector quantization (VQ) histogram for facial image recognition in low-frequency DCT domains. In this paper, we newly utilize Local Binary Pattern (LBP) histogram in spatial domain. These two histograms, which contain both spatial and frequency domain information of a facial image, are utilized as a very effective personal feature. Publicly available AT&T database is used for the evaluation of our proposed algorithm, which is consisted of 40 subjects with 10 images per subject containing variations in lighting, posing, and expressions. It is demonstrated that face recognition using combined histogrambased features can achieve much higher recognition rate.

Original language	English
Title of host publication	6th International Conferences on Advances in Multimedia, MMEDIA 2014
Editors	Pascal Lorenz
Publisher	International Academy, Research and Industry Association, IARIA
Pages	53-57
Number of pages	5
ISBN (Electronic)	9781612083209
Publication status	Published - 2014 Jan 1
Event	6th International Conferences on Advances in Multimedia, MMEDIA 2014 - Nice, France Duration: 2014 Feb 23 → 2014 Feb 27

Publication series

Name	MMEDIA - International Conferences on Advances in Multimedia
ISSN (Print)	2308-4448

Other

Other	6th International Conferences on Advances in Multimedia, MMEDIA 2014
Country	France
City	Nice
Period	14/2/23 → 14/2/27

Keywords

DCT coefficients
Face recognition
Local Binary Patterns (LBP)
Vector quantizaiton (VQ)

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Face recognition using histogram-based features in spatial and frequency domains'. Together they form a unique fingerprint.

Cite this

Face recognition using histogram-based features in spatial and frequency domains. / Chen, Qiu; Kotani, Koji; Lee, Feifei; Ohmi, Tadahiro.

6th International Conferences on Advances in Multimedia, MMEDIA 2014. ed. / Pascal Lorenz. International Academy, Research and Industry Association, IARIA, 2014. p. 53-57 (MMEDIA - International Conferences on Advances in Multimedia).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Chen, Q, Kotani, K, Lee, F & Ohmi, T 2014, Face recognition using histogram-based features in spatial and frequency domains. in P Lorenz (ed.), 6th International Conferences on Advances in Multimedia, MMEDIA 2014. MMEDIA - International Conferences on Advances in Multimedia, International Academy, Research and Industry Association, IARIA, pp. 53-57, 6th International Conferences on Advances in Multimedia, MMEDIA 2014, Nice, France, 14/2/23.

Chen, Qiu ; Kotani, Koji ; Lee, Feifei ; Ohmi, Tadahiro. / Face recognition using histogram-based features in spatial and frequency domains. 6th International Conferences on Advances in Multimedia, MMEDIA 2014. editor / Pascal Lorenz. International Academy, Research and Industry Association, IARIA, 2014. pp. 53-57 (MMEDIA - International Conferences on Advances in Multimedia).

@inproceedings{33f704d802c84a698090262ada54bef5,

title = "Face recognition using histogram-based features in spatial and frequency domains",

abstract = "Previously, we proposed an efficient algorithm using vector quantization (VQ) histogram for facial image recognition in low-frequency DCT domains. In this paper, we newly utilize Local Binary Pattern (LBP) histogram in spatial domain. These two histograms, which contain both spatial and frequency domain information of a facial image, are utilized as a very effective personal feature. Publicly available AT&T database is used for the evaluation of our proposed algorithm, which is consisted of 40 subjects with 10 images per subject containing variations in lighting, posing, and expressions. It is demonstrated that face recognition using combined histogrambased features can achieve much higher recognition rate.",

keywords = "DCT coefficients, Face recognition, Local Binary Patterns (LBP), Vector quantizaiton (VQ)",

author = "Qiu Chen and Koji Kotani and Feifei Lee and Tadahiro Ohmi",

year = "2014",

month = jan,

day = "1",

language = "English",

series = "MMEDIA - International Conferences on Advances in Multimedia",

publisher = "International Academy, Research and Industry Association, IARIA",

pages = "53--57",

editor = "Pascal Lorenz",

booktitle = "6th International Conferences on Advances in Multimedia, MMEDIA 2014",

note = "6th International Conferences on Advances in Multimedia, MMEDIA 2014 ; Conference date: 23-02-2014 Through 27-02-2014",

}

TY - GEN

T1 - Face recognition using histogram-based features in spatial and frequency domains

AU - Chen, Qiu

AU - Kotani, Koji

AU - Lee, Feifei

AU - Ohmi, Tadahiro

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Previously, we proposed an efficient algorithm using vector quantization (VQ) histogram for facial image recognition in low-frequency DCT domains. In this paper, we newly utilize Local Binary Pattern (LBP) histogram in spatial domain. These two histograms, which contain both spatial and frequency domain information of a facial image, are utilized as a very effective personal feature. Publicly available AT&T database is used for the evaluation of our proposed algorithm, which is consisted of 40 subjects with 10 images per subject containing variations in lighting, posing, and expressions. It is demonstrated that face recognition using combined histogrambased features can achieve much higher recognition rate.

AB - Previously, we proposed an efficient algorithm using vector quantization (VQ) histogram for facial image recognition in low-frequency DCT domains. In this paper, we newly utilize Local Binary Pattern (LBP) histogram in spatial domain. These two histograms, which contain both spatial and frequency domain information of a facial image, are utilized as a very effective personal feature. Publicly available AT&T database is used for the evaluation of our proposed algorithm, which is consisted of 40 subjects with 10 images per subject containing variations in lighting, posing, and expressions. It is demonstrated that face recognition using combined histogrambased features can achieve much higher recognition rate.

KW - DCT coefficients

KW - Face recognition

KW - Local Binary Patterns (LBP)

KW - Vector quantizaiton (VQ)

UR - http://www.scopus.com/inward/record.url?scp=84907905490&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907905490&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84907905490

T3 - MMEDIA - International Conferences on Advances in Multimedia

SP - 53

EP - 57

BT - 6th International Conferences on Advances in Multimedia, MMEDIA 2014

A2 - Lorenz, Pascal

PB - International Academy, Research and Industry Association, IARIA

T2 - 6th International Conferences on Advances in Multimedia, MMEDIA 2014

Y2 - 23 February 2014 through 27 February 2014

ER -