3-D face recognition system based on feature analysis and support vector machine

Jiann Der Lee; Chen Hui Kuo; Chen Min Hsu

3-D face recognition system based on feature analysis and support vector machine

Jiann Der Lee^*, Chen Hui Kuo, Chen Min Hsu

^*Corresponding author for this work

Department of Electrical Engineering

Chang Gung University

Research output: Contribution to conference › Conference Paper › peer-review

1 Scopus citations

Abstract

In this paper, a novel 3-D face recognition system based on feature analysis and support vector machine (SVM) is proposed The first stage of this approach is to normalize the altitude and angle of 3-D facial data to remove the distortion resulted from the head pose under arbitrary rotation. Next, the chain code method is employed for feature extraction in several selected facial regions. With the aids of the factor analysis techniques, the number of features is effectively reduced from 26 to 10, which decreased massive computation cost and make the whole system more efficiently. From the experimental results, it is observed that the correction rate using the recognition scheme based on SVM achieves up to 98%, which proves the superior performance of this system.

Original language	English
Pages	B144-B147
State	Published - 2004
Event	IEEE TENCON 2004 - 2004 IEEE Region 10 Conference: Analog and Digital Techniques in Electrical Engineering - Chiang Mai, Thailand Duration: 21 11 2004 → 24 11 2004

Conference

Conference	IEEE TENCON 2004 - 2004 IEEE Region 10 Conference: Analog and Digital Techniques in Electrical Engineering
Country/Territory	Thailand
City	Chiang Mai
Period	21/11/04 → 24/11/04

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Cite this

@conference{a67e979c36f447a9911db618bbf665fd,

title = "3-D face recognition system based on feature analysis and support vector machine",

abstract = "In this paper, a novel 3-D face recognition system based on feature analysis and support vector machine (SVM) is proposed The first stage of this approach is to normalize the altitude and angle of 3-D facial data to remove the distortion resulted from the head pose under arbitrary rotation. Next, the chain code method is employed for feature extraction in several selected facial regions. With the aids of the factor analysis techniques, the number of features is effectively reduced from 26 to 10, which decreased massive computation cost and make the whole system more efficiently. From the experimental results, it is observed that the correction rate using the recognition scheme based on SVM achieves up to 98%, which proves the superior performance of this system.",

author = "Lee, {Jiann Der} and Kuo, {Chen Hui} and Hsu, {Chen Min}",

year = "2004",

language = "英语",

pages = "B144--B147",

note = "IEEE TENCON 2004 - 2004 IEEE Region 10 Conference: Analog and Digital Techniques in Electrical Engineering ; Conference date: 21-11-2004 Through 24-11-2004",

}

3-D face recognition system based on feature analysis and support vector machine. / Lee, Jiann Der; Kuo, Chen Hui; Hsu, Chen Min.
2004. B144-B147 Paper presented at IEEE TENCON 2004 - 2004 IEEE Region 10 Conference: Analog and Digital Techniques in Electrical Engineering, Chiang Mai, Thailand.

Research output: Contribution to conference › Conference Paper › peer-review

TY - CONF

T1 - 3-D face recognition system based on feature analysis and support vector machine

AU - Lee, Jiann Der

AU - Kuo, Chen Hui

AU - Hsu, Chen Min

PY - 2004

Y1 - 2004

N2 - In this paper, a novel 3-D face recognition system based on feature analysis and support vector machine (SVM) is proposed The first stage of this approach is to normalize the altitude and angle of 3-D facial data to remove the distortion resulted from the head pose under arbitrary rotation. Next, the chain code method is employed for feature extraction in several selected facial regions. With the aids of the factor analysis techniques, the number of features is effectively reduced from 26 to 10, which decreased massive computation cost and make the whole system more efficiently. From the experimental results, it is observed that the correction rate using the recognition scheme based on SVM achieves up to 98%, which proves the superior performance of this system.

AB - In this paper, a novel 3-D face recognition system based on feature analysis and support vector machine (SVM) is proposed The first stage of this approach is to normalize the altitude and angle of 3-D facial data to remove the distortion resulted from the head pose under arbitrary rotation. Next, the chain code method is employed for feature extraction in several selected facial regions. With the aids of the factor analysis techniques, the number of features is effectively reduced from 26 to 10, which decreased massive computation cost and make the whole system more efficiently. From the experimental results, it is observed that the correction rate using the recognition scheme based on SVM achieves up to 98%, which proves the superior performance of this system.

UR - http://www.scopus.com/inward/record.url?scp=27944503462&partnerID=8YFLogxK

M3 - 论文

AN - SCOPUS:27944503462

SP - B144-B147

T2 - IEEE TENCON 2004 - 2004 IEEE Region 10 Conference: Analog and Digital Techniques in Electrical Engineering

Y2 - 21 November 2004 through 24 November 2004

ER -

3-D face recognition system based on feature analysis and support vector machine

Abstract

Conference

UN SDGs

Other files and links

Fingerprint

Cite this