Expression recognition from 3D dynamic faces using robust spatio-temporal shape features

Vuong Le; Hao Tang; Thomas S. Huang

doi:10.1109/FG.2011.5771435

Expression recognition from 3D dynamic faces using robust spatio-temporal shape features

Vuong Le, Hao Tang, Thomas S. Huang

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

Abstract

This paper proposes a new method for comparing 3D facial shapes using facial level curves. The pair- and segment-wise distances between the level curves comprise the spatio-temporal features for expression recognition from 3D dynamic faces. The paper further introduces universal background modeling and maximum a posteriori adaptation for hidden Markov models, leading to a decision boundary focus classification algorithm. Both techniques, when combined, yield a high overall recognition accuracy of 92.22% on the BU-4DFE database in our preliminary experiments. Noticeably, our feature extraction method is very efficient, requiring simple preprocessing, and robust to variations of the input data quality.

Original language	English (US)
Title of host publication	2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011
Pages	414-421
Number of pages	8
DOIs	https://doi.org/10.1109/FG.2011.5771435
State	Published - 2011
Externally published	Yes
Event	2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011 - Santa Barbara, CA, United States Duration: Mar 21 2011 → Mar 25 2011

Publication series

Name	2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011

Other

Other	2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011
Country/Territory	United States
City	Santa Barbara, CA
Period	3/21/11 → 3/25/11

ASJC Scopus subject areas

Artificial Intelligence
Computer Vision and Pattern Recognition

Online availability

10.1109/FG.2011.5771435

Library availability

Discover UIUC Full Text

Cite this

Le, V., Tang, H., & Huang, T. S. (2011). Expression recognition from 3D dynamic faces using robust spatio-temporal shape features. In 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011 (pp. 414-421). Article 5771435 (2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011). https://doi.org/10.1109/FG.2011.5771435

Expression recognition from 3D dynamic faces using robust spatio-temporal shape features. / Le, Vuong; Tang, Hao; Huang, Thomas S.
2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011. 2011. p. 414-421 5771435 (2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011).

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

Le, V, Tang, H & Huang, TS 2011, Expression recognition from 3D dynamic faces using robust spatio-temporal shape features. in 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011., 5771435, 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011, pp. 414-421, 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011, Santa Barbara, CA, United States, 3/21/11. https://doi.org/10.1109/FG.2011.5771435

Le V, Tang H, Huang TS. Expression recognition from 3D dynamic faces using robust spatio-temporal shape features. In 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011. 2011. p. 414-421. 5771435. (2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011). doi: 10.1109/FG.2011.5771435

@inproceedings{6aca076d7144401980ebe0d3f57f59e7,

title = "Expression recognition from 3D dynamic faces using robust spatio-temporal shape features",

abstract = "This paper proposes a new method for comparing 3D facial shapes using facial level curves. The pair- and segment-wise distances between the level curves comprise the spatio-temporal features for expression recognition from 3D dynamic faces. The paper further introduces universal background modeling and maximum a posteriori adaptation for hidden Markov models, leading to a decision boundary focus classification algorithm. Both techniques, when combined, yield a high overall recognition accuracy of 92.22% on the BU-4DFE database in our preliminary experiments. Noticeably, our feature extraction method is very efficient, requiring simple preprocessing, and robust to variations of the input data quality.",

author = "Vuong Le and Hao Tang and Huang, {Thomas S.}",

year = "2011",

doi = "10.1109/FG.2011.5771435",

language = "English (US)",

isbn = "9781424491407",

series = "2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011",

pages = "414--421",

booktitle = "2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011",

note = "2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011 ; Conference date: 21-03-2011 Through 25-03-2011",

}

TY - GEN

T1 - Expression recognition from 3D dynamic faces using robust spatio-temporal shape features

AU - Le, Vuong

AU - Tang, Hao

AU - Huang, Thomas S.

PY - 2011

Y1 - 2011

N2 - This paper proposes a new method for comparing 3D facial shapes using facial level curves. The pair- and segment-wise distances between the level curves comprise the spatio-temporal features for expression recognition from 3D dynamic faces. The paper further introduces universal background modeling and maximum a posteriori adaptation for hidden Markov models, leading to a decision boundary focus classification algorithm. Both techniques, when combined, yield a high overall recognition accuracy of 92.22% on the BU-4DFE database in our preliminary experiments. Noticeably, our feature extraction method is very efficient, requiring simple preprocessing, and robust to variations of the input data quality.

AB - This paper proposes a new method for comparing 3D facial shapes using facial level curves. The pair- and segment-wise distances between the level curves comprise the spatio-temporal features for expression recognition from 3D dynamic faces. The paper further introduces universal background modeling and maximum a posteriori adaptation for hidden Markov models, leading to a decision boundary focus classification algorithm. Both techniques, when combined, yield a high overall recognition accuracy of 92.22% on the BU-4DFE database in our preliminary experiments. Noticeably, our feature extraction method is very efficient, requiring simple preprocessing, and robust to variations of the input data quality.

UR - http://www.scopus.com/inward/record.url?scp=79958719389&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79958719389&partnerID=8YFLogxK

U2 - 10.1109/FG.2011.5771435

DO - 10.1109/FG.2011.5771435

M3 - Conference contribution

AN - SCOPUS:79958719389

SN - 9781424491407

T3 - 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011

SP - 414

EP - 421

BT - 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011

T2 - 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011

Y2 - 21 March 2011 through 25 March 2011

ER -

Expression recognition from 3D dynamic faces using robust spatio-temporal shape features

Abstract

Publication series

Other

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this