Performance evaluation of face recognition algorithms on Asian face database

Bon W. Hwang, Myung Cheol Roh, Seong Whan Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

13 Citations (Scopus)

Abstract

Human face is one of the most common and useful keys to a person's identity. Although, a number of face recognition algorithms have been proposed, many researchers believe that the technology should be improved further in oder to overcome the instability due to variable illuminations, expressions, poses and accessories. In general, face databases for European and American such as CMU PIE(USA), FERET(USA), AR Face DB(USA) and XM2VTS(UK) have been used for training face recognition algorithms and testing the performance of those. However, many of the images in databases are not adequately annotated with the exact pose angle, illumination angle and illuminant color. Also, the faces on these databases have definitely different characteristics from those of Asian. Thus, we constructed the well-designed Korean Face Database(KFDB) which includes not only images but also ground truth information for facial feature points and description files for subjects and exact capture environments. In this paper, we report the experimental results of face recognition performed using CM(Correlation Matching), PCA(Principal Component Analysis) and LFA(Local Feature Analysis) algorithms under various conditions on the KFDB.

Original languageEnglish
Title of host publicationProceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition
Pages278-283
Number of pages6
Publication statusPublished - 2004 Sep 24
EventProceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004 - Seoul, Korea, Republic of
Duration: 2004 May 172004 May 19

Other

OtherProceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004
CountryKorea, Republic of
CitySeoul
Period04/5/1704/5/19

Fingerprint

Face recognition
Lighting
Accessories
Principal component analysis
Color
Testing

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Hwang, B. W., Roh, M. C., & Lee, S. W. (2004). Performance evaluation of face recognition algorithms on Asian face database. In Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition (pp. 278-283)

Performance evaluation of face recognition algorithms on Asian face database. / Hwang, Bon W.; Roh, Myung Cheol; Lee, Seong Whan.

Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition. 2004. p. 278-283.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hwang, BW, Roh, MC & Lee, SW 2004, Performance evaluation of face recognition algorithms on Asian face database. in Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition. pp. 278-283, Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004, Seoul, Korea, Republic of, 04/5/17.
Hwang BW, Roh MC, Lee SW. Performance evaluation of face recognition algorithms on Asian face database. In Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition. 2004. p. 278-283
Hwang, Bon W. ; Roh, Myung Cheol ; Lee, Seong Whan. / Performance evaluation of face recognition algorithms on Asian face database. Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition. 2004. pp. 278-283
@inproceedings{fd31c245aa7640fcb2b70602443a9a0d,
title = "Performance evaluation of face recognition algorithms on Asian face database",
abstract = "Human face is one of the most common and useful keys to a person's identity. Although, a number of face recognition algorithms have been proposed, many researchers believe that the technology should be improved further in oder to overcome the instability due to variable illuminations, expressions, poses and accessories. In general, face databases for European and American such as CMU PIE(USA), FERET(USA), AR Face DB(USA) and XM2VTS(UK) have been used for training face recognition algorithms and testing the performance of those. However, many of the images in databases are not adequately annotated with the exact pose angle, illumination angle and illuminant color. Also, the faces on these databases have definitely different characteristics from those of Asian. Thus, we constructed the well-designed Korean Face Database(KFDB) which includes not only images but also ground truth information for facial feature points and description files for subjects and exact capture environments. In this paper, we report the experimental results of face recognition performed using CM(Correlation Matching), PCA(Principal Component Analysis) and LFA(Local Feature Analysis) algorithms under various conditions on the KFDB.",
author = "Hwang, {Bon W.} and Roh, {Myung Cheol} and Lee, {Seong Whan}",
year = "2004",
month = "9",
day = "24",
language = "English",
isbn = "0769521223",
pages = "278--283",
booktitle = "Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition",

}

TY - GEN

T1 - Performance evaluation of face recognition algorithms on Asian face database

AU - Hwang, Bon W.

AU - Roh, Myung Cheol

AU - Lee, Seong Whan

PY - 2004/9/24

Y1 - 2004/9/24

N2 - Human face is one of the most common and useful keys to a person's identity. Although, a number of face recognition algorithms have been proposed, many researchers believe that the technology should be improved further in oder to overcome the instability due to variable illuminations, expressions, poses and accessories. In general, face databases for European and American such as CMU PIE(USA), FERET(USA), AR Face DB(USA) and XM2VTS(UK) have been used for training face recognition algorithms and testing the performance of those. However, many of the images in databases are not adequately annotated with the exact pose angle, illumination angle and illuminant color. Also, the faces on these databases have definitely different characteristics from those of Asian. Thus, we constructed the well-designed Korean Face Database(KFDB) which includes not only images but also ground truth information for facial feature points and description files for subjects and exact capture environments. In this paper, we report the experimental results of face recognition performed using CM(Correlation Matching), PCA(Principal Component Analysis) and LFA(Local Feature Analysis) algorithms under various conditions on the KFDB.

AB - Human face is one of the most common and useful keys to a person's identity. Although, a number of face recognition algorithms have been proposed, many researchers believe that the technology should be improved further in oder to overcome the instability due to variable illuminations, expressions, poses and accessories. In general, face databases for European and American such as CMU PIE(USA), FERET(USA), AR Face DB(USA) and XM2VTS(UK) have been used for training face recognition algorithms and testing the performance of those. However, many of the images in databases are not adequately annotated with the exact pose angle, illumination angle and illuminant color. Also, the faces on these databases have definitely different characteristics from those of Asian. Thus, we constructed the well-designed Korean Face Database(KFDB) which includes not only images but also ground truth information for facial feature points and description files for subjects and exact capture environments. In this paper, we report the experimental results of face recognition performed using CM(Correlation Matching), PCA(Principal Component Analysis) and LFA(Local Feature Analysis) algorithms under various conditions on the KFDB.

UR - http://www.scopus.com/inward/record.url?scp=4544357359&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4544357359&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:4544357359

SN - 0769521223

SP - 278

EP - 283

BT - Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition

ER -