A study on illumination normalization for 2D face verification

Qian Tao; Raymond Veldhuis

doi:10.5220/0001082900420049

A study on illumination normalization for 2D face verification

Qian Tao^*, Raymond Veldhuis

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

2 Citations (Scopus)

1 Downloads (Pure)

Abstract

Illumination normalization is very important for 2D face verification. This study examines the state-of-art illumination normalization methods, and proposes two solutions, namely horizontal Gaussian derivative filters and local binary patterns. Experiments show that our methods significantly improve the generalization capability, while maintaining good discrimination capability of a face verification system. The proposed illumination normalization methods have low requirements on image acquisition, and low computation complexities, and are very suitable for low-end 2D face verification systems.

Original language	English
Title of host publication	Proceedings of the Third International Conference on Computer Vision Theory and Applications
Publisher	SCITEPRESS
Pages	42-49
Number of pages	8
ISBN (Print)	9789898111210
DOIs	https://doi.org/10.5220/0001082900420049
Publication status	Published - 15 Dec 2008
Event	3rd International Conference on Computer Vision Theory and Applications, VISAPP 2008 - Funchal, Madeira, Portugal Duration: 22 Jan 2008 → 25 Jan 2008 http://www.visapp.visigrapp.org/VISAPP2008/

Conference

Conference	3rd International Conference on Computer Vision Theory and Applications, VISAPP 2008
Abbreviated title	VISAPP 2008
Country/Territory	Portugal
City	Funchal, Madeira
Period	22/01/08 → 25/01/08
Internet address	http://www.visapp.visigrapp.org/VISAPP2008/

Keywords

Face recognition
Gaussian derivative filters
Illumination normalization
Local binary patterns

Access to Document

10.5220/0001082900420049

Cite this

@inproceedings{282f9de63127480f96a06583df72cc95,

title = "A study on illumination normalization for 2D face verification",

abstract = "Illumination normalization is very important for 2D face verification. This study examines the state-of-art illumination normalization methods, and proposes two solutions, namely horizontal Gaussian derivative filters and local binary patterns. Experiments show that our methods significantly improve the generalization capability, while maintaining good discrimination capability of a face verification system. The proposed illumination normalization methods have low requirements on image acquisition, and low computation complexities, and are very suitable for low-end 2D face verification systems.",

keywords = "Face recognition, Gaussian derivative filters, Illumination normalization, Local binary patterns",

author = "Qian Tao and Raymond Veldhuis",

year = "2008",

month = dec,

day = "15",

doi = "10.5220/0001082900420049",

language = "English",

isbn = "9789898111210",

pages = "42--49",

booktitle = "Proceedings of the Third International Conference on Computer Vision Theory and Applications",

publisher = "SCITEPRESS",

note = "3rd International Conference on Computer Vision Theory and Applications, VISAPP 2008, VISAPP 2008 ; Conference date: 22-01-2008 Through 25-01-2008",

url = "http://www.visapp.visigrapp.org/VISAPP2008/",

}

Tao, Q & Veldhuis, R 2008, A study on illumination normalization for 2D face verification. in Proceedings of the Third International Conference on Computer Vision Theory and Applications. SCITEPRESS, pp. 42-49, 3rd International Conference on Computer Vision Theory and Applications, VISAPP 2008, Funchal, Madeira, Portugal, 22/01/08. https://doi.org/10.5220/0001082900420049

TY - GEN

T1 - A study on illumination normalization for 2D face verification

AU - Tao, Qian

AU - Veldhuis, Raymond

PY - 2008/12/15

Y1 - 2008/12/15

N2 - Illumination normalization is very important for 2D face verification. This study examines the state-of-art illumination normalization methods, and proposes two solutions, namely horizontal Gaussian derivative filters and local binary patterns. Experiments show that our methods significantly improve the generalization capability, while maintaining good discrimination capability of a face verification system. The proposed illumination normalization methods have low requirements on image acquisition, and low computation complexities, and are very suitable for low-end 2D face verification systems.

AB - Illumination normalization is very important for 2D face verification. This study examines the state-of-art illumination normalization methods, and proposes two solutions, namely horizontal Gaussian derivative filters and local binary patterns. Experiments show that our methods significantly improve the generalization capability, while maintaining good discrimination capability of a face verification system. The proposed illumination normalization methods have low requirements on image acquisition, and low computation complexities, and are very suitable for low-end 2D face verification systems.

KW - Face recognition

KW - Gaussian derivative filters

KW - Illumination normalization

KW - Local binary patterns

UR - http://www.scopus.com/inward/record.url?scp=57349189413&partnerID=8YFLogxK

U2 - 10.5220/0001082900420049

DO - 10.5220/0001082900420049

M3 - Conference contribution

AN - SCOPUS:57349189413

SN - 9789898111210

SP - 42

EP - 49

BT - Proceedings of the Third International Conference on Computer Vision Theory and Applications

PB - SCITEPRESS

T2 - 3rd International Conference on Computer Vision Theory and Applications, VISAPP 2008

Y2 - 22 January 2008 through 25 January 2008

ER -

A study on illumination normalization for 2D face verification

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this