Video-based face recognition using a probabilistic graphical model

Yi Chia Chan, Cheng Chieh Chiang, Kai Ming Wang, Greg C. Lee

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

Abstract

This paper presents a probabilistic graphical model to formulate and deal with video-based face recognition. Our formulation divides the problem into two parts: one for likelihood measure and the other for transition measure. The likelihood measure can be regarded as a traditional task of face recognition within a single image, i.e., to recognize who the current observing face image is. In our work, two-dimensional linear discriminant analysis (2DLDA) is employed to judge the likelihood measure. Moreover, the transition measure estimates the probability of the change from a false recognition at the previous stage to the correct person at the current stage. Our approach for transition measure does not only consider the visual difference among persons according to the training face images but also involve prior information of the pose change in video frames. We also provide several experiments to show the efficiency of our proposed approach in this paper.

Original languageEnglish
Title of host publicationProceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009
Pages106-109
Number of pages4
Publication statusPublished - 2009 Dec 1
Event11th IAPR Conference on Machine Vision Applications, MVA 2009 - Yokohama, Japan
Duration: 2009 May 202009 May 22

Publication series

NameProceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009

Other

Other11th IAPR Conference on Machine Vision Applications, MVA 2009
CountryJapan
CityYokohama
Period09/5/2009/5/22

Fingerprint

Face recognition
Discriminant analysis
Experiments

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Chan, Y. C., Chiang, C. C., Wang, K. M., & Lee, G. C. (2009). Video-based face recognition using a probabilistic graphical model. In Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009 (pp. 106-109). (Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009).

Video-based face recognition using a probabilistic graphical model. / Chan, Yi Chia; Chiang, Cheng Chieh; Wang, Kai Ming; Lee, Greg C.

Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009. 2009. p. 106-109 (Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009).

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

Chan, YC, Chiang, CC, Wang, KM & Lee, GC 2009, Video-based face recognition using a probabilistic graphical model. in Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009. Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009, pp. 106-109, 11th IAPR Conference on Machine Vision Applications, MVA 2009, Yokohama, Japan, 09/5/20.
Chan YC, Chiang CC, Wang KM, Lee GC. Video-based face recognition using a probabilistic graphical model. In Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009. 2009. p. 106-109. (Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009).
Chan, Yi Chia ; Chiang, Cheng Chieh ; Wang, Kai Ming ; Lee, Greg C. / Video-based face recognition using a probabilistic graphical model. Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009. 2009. pp. 106-109 (Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009).
@inproceedings{356c83f809ba47b38c620f621cf943e2,
title = "Video-based face recognition using a probabilistic graphical model",
abstract = "This paper presents a probabilistic graphical model to formulate and deal with video-based face recognition. Our formulation divides the problem into two parts: one for likelihood measure and the other for transition measure. The likelihood measure can be regarded as a traditional task of face recognition within a single image, i.e., to recognize who the current observing face image is. In our work, two-dimensional linear discriminant analysis (2DLDA) is employed to judge the likelihood measure. Moreover, the transition measure estimates the probability of the change from a false recognition at the previous stage to the correct person at the current stage. Our approach for transition measure does not only consider the visual difference among persons according to the training face images but also involve prior information of the pose change in video frames. We also provide several experiments to show the efficiency of our proposed approach in this paper.",
author = "Chan, {Yi Chia} and Chiang, {Cheng Chieh} and Wang, {Kai Ming} and Lee, {Greg C.}",
year = "2009",
month = "12",
day = "1",
language = "English",
isbn = "9784901122092",
series = "Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009",
pages = "106--109",
booktitle = "Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009",

}

TY - GEN

T1 - Video-based face recognition using a probabilistic graphical model

AU - Chan, Yi Chia

AU - Chiang, Cheng Chieh

AU - Wang, Kai Ming

AU - Lee, Greg C.

PY - 2009/12/1

Y1 - 2009/12/1

N2 - This paper presents a probabilistic graphical model to formulate and deal with video-based face recognition. Our formulation divides the problem into two parts: one for likelihood measure and the other for transition measure. The likelihood measure can be regarded as a traditional task of face recognition within a single image, i.e., to recognize who the current observing face image is. In our work, two-dimensional linear discriminant analysis (2DLDA) is employed to judge the likelihood measure. Moreover, the transition measure estimates the probability of the change from a false recognition at the previous stage to the correct person at the current stage. Our approach for transition measure does not only consider the visual difference among persons according to the training face images but also involve prior information of the pose change in video frames. We also provide several experiments to show the efficiency of our proposed approach in this paper.

AB - This paper presents a probabilistic graphical model to formulate and deal with video-based face recognition. Our formulation divides the problem into two parts: one for likelihood measure and the other for transition measure. The likelihood measure can be regarded as a traditional task of face recognition within a single image, i.e., to recognize who the current observing face image is. In our work, two-dimensional linear discriminant analysis (2DLDA) is employed to judge the likelihood measure. Moreover, the transition measure estimates the probability of the change from a false recognition at the previous stage to the correct person at the current stage. Our approach for transition measure does not only consider the visual difference among persons according to the training face images but also involve prior information of the pose change in video frames. We also provide several experiments to show the efficiency of our proposed approach in this paper.

UR - http://www.scopus.com/inward/record.url?scp=84872737636&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872737636&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84872737636

SN - 9784901122092

T3 - Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009

SP - 106

EP - 109

BT - Proceedings of the 11th IAPR Conference on Machine Vision Applications, MVA 2009

ER -