A comparative analysis of feature extraction methods for face recognition system

A. J. Nor'aini; P. Raveendran; N. Selvanathan

doi:10.1109/ASENSE.2005.1564534

A comparative analysis of feature extraction methods for face recognition system

A. J. Nor'aini, P. Raveendran, N. Selvanathan

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

3 Citations (Scopus)

Abstract

Recognizing face images due to changes in illumination condition, pose, facial expression and others are challenging task. Solving these problems requires a feature extraction method that can generate distinct features for each class of image. Hence, this paper describes the comparative analysis of feature extraction methods namely Geometric moments, Zernike moments, Krawtchouk moments and Principle component analysis (PCA) in terms of their capability to recognize face images. The classification technique employed in the recognition stage is Back propagation neural network (BPNN). The experiments utilized database face images from Olivetti research laboratory (ORL) consisting of 40 subjects of 10 samples each where none of them are identical [1]. They vary in position, rotation, scale and expression. From the comparative study, the most suitable feature extraction method is considered for face recognition system.

Original language	English
Title of host publication	2005 Asian Conference on Sensors and the International Conference on New Techniques in Pharmaceutical and Biomedical Research - Proceedings
Pages	176-181
Number of pages	6
DOIs	https://doi.org/10.1109/ASENSE.2005.1564534
Publication status	Published - 2005
Externally published	Yes
Event	Asian Conference on Sensors and the International Conference on new Techniques in Pharmaceutical and Biomedical Research 2005 - Kuala Lumpur, Malaysia Duration: 5 Sept 2005 → 7 Sept 2005 https://ieeexplore.ieee.org/xpl/conhome/10462/proceeding (Proceedings)

Publication series

Name	2005 Asian Conference on Sensors and the International Conference on New Techniques in Pharmaceutical and Biomedical Research - Proceedings
Volume	2005

Conference

Conference	Asian Conference on Sensors and the International Conference on new Techniques in Pharmaceutical and Biomedical Research 2005
Country/Territory	Malaysia
City	Kuala Lumpur
Period	5/09/05 → 7/09/05
Internet address	https://ieeexplore.ieee.org/xpl/conhome/10462/proceeding (Proceedings)

Keywords

BPNN
Geometric moments
Krawtchouk
Moments
PCA
Zernike moments

Access to Document

10.1109/ASENSE.2005.1564534

Cite this

Nor'aini, A. J., Raveendran, P., & Selvanathan, N. (2005). A comparative analysis of feature extraction methods for face recognition system. In 2005 Asian Conference on Sensors and the International Conference on New Techniques in Pharmaceutical and Biomedical Research - Proceedings (pp. 176-181). (2005 Asian Conference on Sensors and the International Conference on New Techniques in Pharmaceutical and Biomedical Research - Proceedings; Vol. 2005). https://doi.org/10.1109/ASENSE.2005.1564534

Nor'aini, A. J. ; Raveendran, P. ; Selvanathan, N. / A comparative analysis of feature extraction methods for face recognition system. 2005 Asian Conference on Sensors and the International Conference on New Techniques in Pharmaceutical and Biomedical Research - Proceedings. 2005. pp. 176-181 (2005 Asian Conference on Sensors and the International Conference on New Techniques in Pharmaceutical and Biomedical Research - Proceedings).

@inproceedings{35d73828626e48f6817210efabeaa9e9,

title = "A comparative analysis of feature extraction methods for face recognition system",

abstract = "Recognizing face images due to changes in illumination condition, pose, facial expression and others are challenging task. Solving these problems requires a feature extraction method that can generate distinct features for each class of image. Hence, this paper describes the comparative analysis of feature extraction methods namely Geometric moments, Zernike moments, Krawtchouk moments and Principle component analysis (PCA) in terms of their capability to recognize face images. The classification technique employed in the recognition stage is Back propagation neural network (BPNN). The experiments utilized database face images from Olivetti research laboratory (ORL) consisting of 40 subjects of 10 samples each where none of them are identical [1]. They vary in position, rotation, scale and expression. From the comparative study, the most suitable feature extraction method is considered for face recognition system.",

keywords = "BPNN, Geometric moments, Krawtchouk, Moments, PCA, Zernike moments",

author = "Nor'aini, {A. J.} and P. Raveendran and N. Selvanathan",

year = "2005",

doi = "10.1109/ASENSE.2005.1564534",

language = "English",

isbn = "0780393708",

series = "2005 Asian Conference on Sensors and the International Conference on New Techniques in Pharmaceutical and Biomedical Research - Proceedings",

pages = "176--181",

booktitle = "2005 Asian Conference on Sensors and the International Conference on New Techniques in Pharmaceutical and Biomedical Research - Proceedings",

note = "Asian Conference on Sensors and the International Conference on new Techniques in Pharmaceutical and Biomedical Research 2005 ; Conference date: 05-09-2005 Through 07-09-2005",

url = "https://ieeexplore.ieee.org/xpl/conhome/10462/proceeding",

}

Nor'aini, AJ, Raveendran, P & Selvanathan, N 2005, A comparative analysis of feature extraction methods for face recognition system. in 2005 Asian Conference on Sensors and the International Conference on New Techniques in Pharmaceutical and Biomedical Research - Proceedings. 2005 Asian Conference on Sensors and the International Conference on New Techniques in Pharmaceutical and Biomedical Research - Proceedings, vol. 2005, pp. 176-181, Asian Conference on Sensors and the International Conference on new Techniques in Pharmaceutical and Biomedical Research 2005, Kuala Lumpur, Malaysia, 5/09/05. https://doi.org/10.1109/ASENSE.2005.1564534

A comparative analysis of feature extraction methods for face recognition system. / Nor'aini, A. J.; Raveendran, P.; Selvanathan, N.
2005 Asian Conference on Sensors and the International Conference on New Techniques in Pharmaceutical and Biomedical Research - Proceedings. 2005. p. 176-181 (2005 Asian Conference on Sensors and the International Conference on New Techniques in Pharmaceutical and Biomedical Research - Proceedings; Vol. 2005).

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

TY - GEN

T1 - A comparative analysis of feature extraction methods for face recognition system

AU - Nor'aini, A. J.

AU - Raveendran, P.

AU - Selvanathan, N.

PY - 2005

Y1 - 2005

N2 - Recognizing face images due to changes in illumination condition, pose, facial expression and others are challenging task. Solving these problems requires a feature extraction method that can generate distinct features for each class of image. Hence, this paper describes the comparative analysis of feature extraction methods namely Geometric moments, Zernike moments, Krawtchouk moments and Principle component analysis (PCA) in terms of their capability to recognize face images. The classification technique employed in the recognition stage is Back propagation neural network (BPNN). The experiments utilized database face images from Olivetti research laboratory (ORL) consisting of 40 subjects of 10 samples each where none of them are identical [1]. They vary in position, rotation, scale and expression. From the comparative study, the most suitable feature extraction method is considered for face recognition system.

AB - Recognizing face images due to changes in illumination condition, pose, facial expression and others are challenging task. Solving these problems requires a feature extraction method that can generate distinct features for each class of image. Hence, this paper describes the comparative analysis of feature extraction methods namely Geometric moments, Zernike moments, Krawtchouk moments and Principle component analysis (PCA) in terms of their capability to recognize face images. The classification technique employed in the recognition stage is Back propagation neural network (BPNN). The experiments utilized database face images from Olivetti research laboratory (ORL) consisting of 40 subjects of 10 samples each where none of them are identical [1]. They vary in position, rotation, scale and expression. From the comparative study, the most suitable feature extraction method is considered for face recognition system.

KW - BPNN

KW - Geometric moments

KW - Krawtchouk

KW - Moments

KW - PCA

KW - Zernike moments

UR - http://www.scopus.com/inward/record.url?scp=33846281929&partnerID=8YFLogxK

U2 - 10.1109/ASENSE.2005.1564534

DO - 10.1109/ASENSE.2005.1564534

M3 - Conference Paper

AN - SCOPUS:33846281929

SN - 0780393708

SN - 9780780393707

T3 - 2005 Asian Conference on Sensors and the International Conference on New Techniques in Pharmaceutical and Biomedical Research - Proceedings

SP - 176

EP - 181

BT - 2005 Asian Conference on Sensors and the International Conference on New Techniques in Pharmaceutical and Biomedical Research - Proceedings

T2 - Asian Conference on Sensors and the International Conference on new Techniques in Pharmaceutical and Biomedical Research 2005

Y2 - 5 September 2005 through 7 September 2005

ER -

Nor'aini AJ, Raveendran P, Selvanathan N. A comparative analysis of feature extraction methods for face recognition system. In 2005 Asian Conference on Sensors and the International Conference on New Techniques in Pharmaceutical and Biomedical Research - Proceedings. 2005. p. 176-181. (2005 Asian Conference on Sensors and the International Conference on New Techniques in Pharmaceutical and Biomedical Research - Proceedings). doi: 10.1109/ASENSE.2005.1564534

A comparative analysis of feature extraction methods for face recognition system

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this