3D Facial expression recognition based on automatically selected features

Hao Tang, Thomas S Huang

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

Abstract

In this paper, the problem of person-independent facial expression recognition from 3D facial shapes is investigated. We propose a novel automatic feature selection method based on maximizing the average relative entropy of marginalized class-conditional feature distributions and apply it to a complete pool of candidate features composed of normalized Euclidean distances between 83 facial feature points in the 3D space. Using a regularized multi-class AdaBoost classification algorithm, we achieve a 95.1% average recognition rate for six universal facial expressions on the publicly available 3D facial expression database BU-3DFE [1], with a highest average recognition rate of 99.2% for the recognition of surprise. We compare these results with the results based on a set of manually devised features and demonstrate that the auto features yield better results than the manual features. Our results outperform the results presented in the previous work [2] and [3], namely average recognition rates of 83.6% and 91.3% on the same database, respectively.

Original languageEnglish (US)
Title of host publication2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops
DOIs
StatePublished - Sep 22 2008
Event2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops - Anchorage, AK, United States
Duration: Jun 23 2008Jun 28 2008

Publication series

Name2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops

Other

Other2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops
CountryUnited States
CityAnchorage, AK
Period6/23/086/28/08

Fingerprint

Adaptive boosting
Feature extraction
Entropy

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Tang, H., & Huang, T. S. (2008). 3D Facial expression recognition based on automatically selected features. In 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops [4563052] (2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops). https://doi.org/10.1109/CVPRW.2008.4563052

3D Facial expression recognition based on automatically selected features. / Tang, Hao; Huang, Thomas S.

2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops. 2008. 4563052 (2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops).

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

Tang, H & Huang, TS 2008, 3D Facial expression recognition based on automatically selected features. in 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops., 4563052, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops, Anchorage, AK, United States, 6/23/08. https://doi.org/10.1109/CVPRW.2008.4563052
Tang H, Huang TS. 3D Facial expression recognition based on automatically selected features. In 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops. 2008. 4563052. (2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops). https://doi.org/10.1109/CVPRW.2008.4563052
Tang, Hao ; Huang, Thomas S. / 3D Facial expression recognition based on automatically selected features. 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops. 2008. (2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops).
@inproceedings{ff61019e09ec4e19b94323f75adbae5c,
title = "3D Facial expression recognition based on automatically selected features",
abstract = "In this paper, the problem of person-independent facial expression recognition from 3D facial shapes is investigated. We propose a novel automatic feature selection method based on maximizing the average relative entropy of marginalized class-conditional feature distributions and apply it to a complete pool of candidate features composed of normalized Euclidean distances between 83 facial feature points in the 3D space. Using a regularized multi-class AdaBoost classification algorithm, we achieve a 95.1{\%} average recognition rate for six universal facial expressions on the publicly available 3D facial expression database BU-3DFE [1], with a highest average recognition rate of 99.2{\%} for the recognition of surprise. We compare these results with the results based on a set of manually devised features and demonstrate that the auto features yield better results than the manual features. Our results outperform the results presented in the previous work [2] and [3], namely average recognition rates of 83.6{\%} and 91.3{\%} on the same database, respectively.",
author = "Hao Tang and Huang, {Thomas S}",
year = "2008",
month = "9",
day = "22",
doi = "10.1109/CVPRW.2008.4563052",
language = "English (US)",
isbn = "9781424423408",
series = "2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops",
booktitle = "2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops",

}

TY - GEN

T1 - 3D Facial expression recognition based on automatically selected features

AU - Tang, Hao

AU - Huang, Thomas S

PY - 2008/9/22

Y1 - 2008/9/22

N2 - In this paper, the problem of person-independent facial expression recognition from 3D facial shapes is investigated. We propose a novel automatic feature selection method based on maximizing the average relative entropy of marginalized class-conditional feature distributions and apply it to a complete pool of candidate features composed of normalized Euclidean distances between 83 facial feature points in the 3D space. Using a regularized multi-class AdaBoost classification algorithm, we achieve a 95.1% average recognition rate for six universal facial expressions on the publicly available 3D facial expression database BU-3DFE [1], with a highest average recognition rate of 99.2% for the recognition of surprise. We compare these results with the results based on a set of manually devised features and demonstrate that the auto features yield better results than the manual features. Our results outperform the results presented in the previous work [2] and [3], namely average recognition rates of 83.6% and 91.3% on the same database, respectively.

AB - In this paper, the problem of person-independent facial expression recognition from 3D facial shapes is investigated. We propose a novel automatic feature selection method based on maximizing the average relative entropy of marginalized class-conditional feature distributions and apply it to a complete pool of candidate features composed of normalized Euclidean distances between 83 facial feature points in the 3D space. Using a regularized multi-class AdaBoost classification algorithm, we achieve a 95.1% average recognition rate for six universal facial expressions on the publicly available 3D facial expression database BU-3DFE [1], with a highest average recognition rate of 99.2% for the recognition of surprise. We compare these results with the results based on a set of manually devised features and demonstrate that the auto features yield better results than the manual features. Our results outperform the results presented in the previous work [2] and [3], namely average recognition rates of 83.6% and 91.3% on the same database, respectively.

UR - http://www.scopus.com/inward/record.url?scp=51849110283&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51849110283&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2008.4563052

DO - 10.1109/CVPRW.2008.4563052

M3 - Conference contribution

AN - SCOPUS:51849110283

SN - 9781424423408

T3 - 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops

BT - 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops

ER -