Human facial expression recognition based on learning subspace method

Xilin Chen; Sam Kwong; Yan Lu

doi:10.1109/ICME.2000.869625

Human facial expression recognition based on learning subspace method

Xilin Chen
, Sam Kwong
, Yan Lu

Department of Computer Science

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

1 Citation (Scopus)

Abstract

Learning subspace method (LSM) is one of the most important methods for pattern recognition and it has been successfully used in many practical applications. In this paper, we propose to use the LSM for human facial expression recognition. Seven expression subspaces are built for expression models. The idea of recognizing facial expression through a single static image is realized and the recognition rate as high as 89.5% is achieved. In order to make these expression subspaces more adaptive we can gradually learn them by using the averaged learning subspace method (ALSM). Experimental results also indicate that the recognition rate is over 90%. The dynamic characteristics of the projection vector sequence on these facial expression subspaces are also discussed in this paper. © 2000 IEEE

Original language	English
Title of host publication	2000 IEEE International Conference on Multimedia and Expo
Subtitle of host publication	ICME2000, Proceedings
Publisher	IEEE
Pages	403-406
Volume	1
ISBN (Print)	0-7803-6536-4
DOIs	https://doi.org/10.1109/ICME.2000.869625
Publication status	Published - Aug 2000
Event	2000 IEEE Internatinal Conference on Multimedia and Expo (ICME 2000) - New York, NY, United States Duration: 30 Jul 2000 → 2 Aug 2000

Conference

Conference	2000 IEEE Internatinal Conference on Multimedia and Expo (ICME 2000)
Place	United States
City	New York, NY
Period	30/07/00 → 2/08/00

Access Output

10.1109/ICME.2000.869625

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{40f83619394345a0b81e8ff502525547,

title = "Human facial expression recognition based on learning subspace method",

abstract = "Learning subspace method (LSM) is one of the most important methods for pattern recognition and it has been successfully used in many practical applications. In this paper, we propose to use the LSM for human facial expression recognition. Seven expression subspaces are built for expression models. The idea of recognizing facial expression through a single static image is realized and the recognition rate as high as 89.5\% is achieved. In order to make these expression subspaces more adaptive we can gradually learn them by using the averaged learning subspace method (ALSM). Experimental results also indicate that the recognition rate is over 90\%. The dynamic characteristics of the projection vector sequence on these facial expression subspaces are also discussed in this paper. {\textcopyright} 2000 IEEE",

author = "Xilin Chen and Sam Kwong and Yan Lu",

year = "2000",

month = aug,

doi = "10.1109/ICME.2000.869625",

language = "English",

isbn = "0-7803-6536-4",

volume = "1",

pages = "403--406",

booktitle = "2000 IEEE International Conference on Multimedia and Expo",

publisher = "IEEE",

address = "United States",

note = "2000 IEEE Internatinal Conference on Multimedia and Expo (ICME 2000) ; Conference date: 30-07-2000 Through 02-08-2000",

}

Human facial expression recognition based on learning subspace method. / Chen, Xilin; Kwong, Sam; Lu, Yan.
2000 IEEE International Conference on Multimedia and Expo: ICME2000, Proceedings. Vol. 1 IEEE, 2000. p. 403-406.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Human facial expression recognition based on learning subspace method

AU - Chen, Xilin

AU - Kwong, Sam

AU - Lu, Yan

PY - 2000/8

Y1 - 2000/8

N2 - Learning subspace method (LSM) is one of the most important methods for pattern recognition and it has been successfully used in many practical applications. In this paper, we propose to use the LSM for human facial expression recognition. Seven expression subspaces are built for expression models. The idea of recognizing facial expression through a single static image is realized and the recognition rate as high as 89.5% is achieved. In order to make these expression subspaces more adaptive we can gradually learn them by using the averaged learning subspace method (ALSM). Experimental results also indicate that the recognition rate is over 90%. The dynamic characteristics of the projection vector sequence on these facial expression subspaces are also discussed in this paper. © 2000 IEEE

AB - Learning subspace method (LSM) is one of the most important methods for pattern recognition and it has been successfully used in many practical applications. In this paper, we propose to use the LSM for human facial expression recognition. Seven expression subspaces are built for expression models. The idea of recognizing facial expression through a single static image is realized and the recognition rate as high as 89.5% is achieved. In order to make these expression subspaces more adaptive we can gradually learn them by using the averaged learning subspace method (ALSM). Experimental results also indicate that the recognition rate is over 90%. The dynamic characteristics of the projection vector sequence on these facial expression subspaces are also discussed in this paper. © 2000 IEEE

UR - https://www.scopus.com/pages/publications/0034509754

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0034509754&origin=recordpage

U2 - 10.1109/ICME.2000.869625

DO - 10.1109/ICME.2000.869625

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 0-7803-6536-4

VL - 1

SP - 403

EP - 406

BT - 2000 IEEE International Conference on Multimedia and Expo

PB - IEEE

T2 - 2000 IEEE Internatinal Conference on Multimedia and Expo (ICME 2000)

Y2 - 30 July 2000 through 2 August 2000

ER -

Human facial expression recognition based on learning subspace method

Abstract

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this