A novel face representation toward pose invariant face recognition

Liang Yu; Sei Ichiro Kamata; Yong Fang

doi:10.1109/TENCON.2010.5685977

A novel face representation toward pose invariant face recognition

Liang Yu^*, Sei Ichiro Kamata, Yong Fang

^*Corresponding author for this work

Graduate School of Information, Production and Systems

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

Abstract

Though elastic bunch graph matching (EBGM) has a good performance on face recognition in the distortion of facial expression, it is still not robust enough to in-depth rotation. To solve this problem, a novel face representation approach based on the space-filling tree is proposed in this paper. This kind of representation shows a better performance than Elastic bunch graph matching (EBGM) in in-depth rotation of pose especially when there are only frontal images in the training set. With the proposed face representation approach, the face recognition system is built. Experimental results on the FERET standard database show that the proposed face representation approach is more effective and robust to the in-depth rotation of pose when there are only frontal images in the training set.

Original language	English
Title of host publication	TENCON 2010 - 2010 IEEE Region 10 Conference
Pages	179-183
Number of pages	5
DOIs	https://doi.org/10.1109/TENCON.2010.5685977
Publication status	Published - 2010 Dec 1
Event	2010 IEEE Region 10 Conference, TENCON 2010 - Fukuoka, Japan Duration: 2010 Nov 21 → 2010 Nov 24

Publication series

Name	IEEE Region 10 Annual International Conference, Proceedings/TENCON

Other

Other	2010 IEEE Region 10 Conference, TENCON 2010
Country/Territory	Japan
City	Fukuoka
Period	10/11/21 → 10/11/24

Keywords

Elastic bunch graph matching
Face recognition
Pose invariant
Space-filling tree

ASJC Scopus subject areas

Computer Science Applications
Electrical and Electronic Engineering

Access to Document

10.1109/TENCON.2010.5685977

Cite this

@inproceedings{60577e6efb144379b03ee0a6fbcf0021,

title = "A novel face representation toward pose invariant face recognition",

abstract = "Though elastic bunch graph matching (EBGM) has a good performance on face recognition in the distortion of facial expression, it is still not robust enough to in-depth rotation. To solve this problem, a novel face representation approach based on the space-filling tree is proposed in this paper. This kind of representation shows a better performance than Elastic bunch graph matching (EBGM) in in-depth rotation of pose especially when there are only frontal images in the training set. With the proposed face representation approach, the face recognition system is built. Experimental results on the FERET standard database show that the proposed face representation approach is more effective and robust to the in-depth rotation of pose when there are only frontal images in the training set.",

keywords = "Elastic bunch graph matching, Face recognition, Pose invariant, Space-filling tree",

author = "Liang Yu and Kamata, {Sei Ichiro} and Yong Fang",

year = "2010",

month = dec,

day = "1",

doi = "10.1109/TENCON.2010.5685977",

language = "English",

isbn = "9781424468904",

series = "IEEE Region 10 Annual International Conference, Proceedings/TENCON",

pages = "179--183",

booktitle = "TENCON 2010 - 2010 IEEE Region 10 Conference",

note = "2010 IEEE Region 10 Conference, TENCON 2010 ; Conference date: 21-11-2010 Through 24-11-2010",

}

TY - GEN

T1 - A novel face representation toward pose invariant face recognition

AU - Yu, Liang

AU - Kamata, Sei Ichiro

AU - Fang, Yong

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Though elastic bunch graph matching (EBGM) has a good performance on face recognition in the distortion of facial expression, it is still not robust enough to in-depth rotation. To solve this problem, a novel face representation approach based on the space-filling tree is proposed in this paper. This kind of representation shows a better performance than Elastic bunch graph matching (EBGM) in in-depth rotation of pose especially when there are only frontal images in the training set. With the proposed face representation approach, the face recognition system is built. Experimental results on the FERET standard database show that the proposed face representation approach is more effective and robust to the in-depth rotation of pose when there are only frontal images in the training set.

AB - Though elastic bunch graph matching (EBGM) has a good performance on face recognition in the distortion of facial expression, it is still not robust enough to in-depth rotation. To solve this problem, a novel face representation approach based on the space-filling tree is proposed in this paper. This kind of representation shows a better performance than Elastic bunch graph matching (EBGM) in in-depth rotation of pose especially when there are only frontal images in the training set. With the proposed face representation approach, the face recognition system is built. Experimental results on the FERET standard database show that the proposed face representation approach is more effective and robust to the in-depth rotation of pose when there are only frontal images in the training set.

KW - Elastic bunch graph matching

KW - Face recognition

KW - Pose invariant

KW - Space-filling tree

UR - http://www.scopus.com/inward/record.url?scp=79951667900&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79951667900&partnerID=8YFLogxK

U2 - 10.1109/TENCON.2010.5685977

DO - 10.1109/TENCON.2010.5685977

M3 - Conference contribution

AN - SCOPUS:79951667900

SN - 9781424468904

T3 - IEEE Region 10 Annual International Conference, Proceedings/TENCON

SP - 179

EP - 183

BT - TENCON 2010 - 2010 IEEE Region 10 Conference

T2 - 2010 IEEE Region 10 Conference, TENCON 2010

Y2 - 21 November 2010 through 24 November 2010

ER -

A novel face representation toward pose invariant face recognition

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this