A common framework for real-time emotion recognition and facial action unit detection

Tobias Gehrig; Hazim Kemal Ekenel

doi:10.1109/CVPRW.2011.5981817

A common framework for real-time emotion recognition and facial action unit detection

Tobias Gehrig^*, Hazim Kemal Ekenel

^*Corresponding author for this work

Karlsruhe Institute of Technology

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

23 Citations (Scopus)

Abstract

In this paper, we present a common framework for realtime action unit detection and emotion recognition that we have developed for the emotion recognition and action unit detection sub-challenges of the FG 2011 Facial Expression Recognition and Analysis Challenge. For these tasks we employed a local appearance-based face representation approach using discrete cosine transform, which has been shown to be very effective and robust for face recognition. Using these features, we trained multiple one-versus-all support vector machine classifiers corresponding to the individual classes of the specific task. With this framework we achieve 24.2% and 7.6% absolute improvement over the overall baseline results on the emotion recognition and action unit detection sub-challenge, respectively.

Original language	English
Title of host publication	2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011
DOIs	https://doi.org/10.1109/CVPRW.2011.5981817
Publication status	Published - 2011
Externally published	Yes
Event	2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011 - Colorado Springs, CO, United States Duration: 20 Jun 2011 → 25 Jun 2011

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Conference

Conference	2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011
Country/Territory	United States
City	Colorado Springs, CO
Period	20/06/11 → 25/06/11

Access to Document

10.1109/CVPRW.2011.5981817

Cite this

Gehrig, T., & Ekenel, H. K. (2011). A common framework for real-time emotion recognition and facial action unit detection. In 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011 Article 5981817 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). https://doi.org/10.1109/CVPRW.2011.5981817

@inproceedings{dfee57c3d7d544d59791b4e9003e8be0,

title = "A common framework for real-time emotion recognition and facial action unit detection",

abstract = "In this paper, we present a common framework for realtime action unit detection and emotion recognition that we have developed for the emotion recognition and action unit detection sub-challenges of the FG 2011 Facial Expression Recognition and Analysis Challenge. For these tasks we employed a local appearance-based face representation approach using discrete cosine transform, which has been shown to be very effective and robust for face recognition. Using these features, we trained multiple one-versus-all support vector machine classifiers corresponding to the individual classes of the specific task. With this framework we achieve 24.2% and 7.6% absolute improvement over the overall baseline results on the emotion recognition and action unit detection sub-challenge, respectively.",

author = "Tobias Gehrig and Ekenel, {Hazim Kemal}",

year = "2011",

doi = "10.1109/CVPRW.2011.5981817",

language = "English",

isbn = "9781457705298",

series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

booktitle = "2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011",

note = "2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011 ; Conference date: 20-06-2011 Through 25-06-2011",

}

Gehrig, T & Ekenel, HK 2011, A common framework for real-time emotion recognition and facial action unit detection. in 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011., 5981817, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011, Colorado Springs, CO, United States, 20/06/11. https://doi.org/10.1109/CVPRW.2011.5981817

A common framework for real-time emotion recognition and facial action unit detection. / Gehrig, Tobias; Ekenel, Hazim Kemal.
2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011. 2011. 5981817 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).

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

TY - GEN

T1 - A common framework for real-time emotion recognition and facial action unit detection

AU - Gehrig, Tobias

AU - Ekenel, Hazim Kemal

PY - 2011

Y1 - 2011

N2 - In this paper, we present a common framework for realtime action unit detection and emotion recognition that we have developed for the emotion recognition and action unit detection sub-challenges of the FG 2011 Facial Expression Recognition and Analysis Challenge. For these tasks we employed a local appearance-based face representation approach using discrete cosine transform, which has been shown to be very effective and robust for face recognition. Using these features, we trained multiple one-versus-all support vector machine classifiers corresponding to the individual classes of the specific task. With this framework we achieve 24.2% and 7.6% absolute improvement over the overall baseline results on the emotion recognition and action unit detection sub-challenge, respectively.

AB - In this paper, we present a common framework for realtime action unit detection and emotion recognition that we have developed for the emotion recognition and action unit detection sub-challenges of the FG 2011 Facial Expression Recognition and Analysis Challenge. For these tasks we employed a local appearance-based face representation approach using discrete cosine transform, which has been shown to be very effective and robust for face recognition. Using these features, we trained multiple one-versus-all support vector machine classifiers corresponding to the individual classes of the specific task. With this framework we achieve 24.2% and 7.6% absolute improvement over the overall baseline results on the emotion recognition and action unit detection sub-challenge, respectively.

UR - http://www.scopus.com/inward/record.url?scp=80054939986&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2011.5981817

DO - 10.1109/CVPRW.2011.5981817

M3 - Conference contribution

AN - SCOPUS:80054939986

SN - 9781457705298

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

BT - 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011

T2 - 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011

Y2 - 20 June 2011 through 25 June 2011

ER -

A common framework for real-time emotion recognition and facial action unit detection

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this