Combining AAM coefficients with LGBP histograms in the multi-kernel SVM framework to detect facial action units

Thibaud Senechal; Vincent Rapp; Hanan Salam; Renaud Seguier; Kevin Bailly; Lionel Prevost

doi:10.1109/FG.2011.5771363

Combining AAM coefficients with LGBP histograms in the multi-kernel SVM framework to detect facial action units

Thibaud Senechal, Vincent Rapp, Hanan Salam, Renaud Seguier, Kevin Bailly, Lionel Prevost

Computer Science

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

Abstract

This study presents a combination of geometric and appearance features used to automatically detect Action Units in face images. We use one multi-kernel SVM for each Action Unit we want to detect. The first kernel matrix is computed using Local Gabor Binary Pattern (LGBP) histograms and a histogram intersection kernel. The second kernel matrix is computed from AAM coefficients and a RBF kernel. During the training step, we combine these two type s of features using the recent SimpleMKL algorithm. SVM outputs are then filtered to exploit dynamic relationships between Action Units.

Original language	English (US)
Title of host publication	2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011
Pages	860-865
Number of pages	6
DOIs	https://doi.org/10.1109/FG.2011.5771363
State	Published - 2011
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

Conference

Conference	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

Access to Document

10.1109/FG.2011.5771363

Cite this

Senechal, T., Rapp, V., Salam, H., Seguier, R., Bailly, K., & Prevost, L. (2011). Combining AAM coefficients with LGBP histograms in the multi-kernel SVM framework to detect facial action units. In 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011 (pp. 860-865). Article 5771363 (2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011). https://doi.org/10.1109/FG.2011.5771363

Combining AAM coefficients with LGBP histograms in the multi-kernel SVM framework to detect facial action units. / Senechal, Thibaud; Rapp, Vincent; Salam, Hanan et al.
2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011. 2011. p. 860-865 5771363 (2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011).

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

Senechal, T, Rapp, V, Salam, H, Seguier, R, Bailly, K & Prevost, L 2011, Combining AAM coefficients with LGBP histograms in the multi-kernel SVM framework to detect facial action units. in 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011., 5771363, 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011, pp. 860-865, 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.2011.5771363

Senechal T, Rapp V, Salam H, Seguier R, Bailly K, Prevost L. Combining AAM coefficients with LGBP histograms in the multi-kernel SVM framework to detect facial action units. In 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011. 2011. p. 860-865. 5771363. (2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011). doi: 10.1109/FG.2011.5771363

Senechal, Thibaud ; Rapp, Vincent ; Salam, Hanan et al. / Combining AAM coefficients with LGBP histograms in the multi-kernel SVM framework to detect facial action units. 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011. 2011. pp. 860-865 (2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011).

@inproceedings{15a72ed7580b4d0783d320aa71f4b2a9,

title = "Combining AAM coefficients with LGBP histograms in the multi-kernel SVM framework to detect facial action units",

abstract = "This study presents a combination of geometric and appearance features used to automatically detect Action Units in face images. We use one multi-kernel SVM for each Action Unit we want to detect. The first kernel matrix is computed using Local Gabor Binary Pattern (LGBP) histograms and a histogram intersection kernel. The second kernel matrix is computed from AAM coefficients and a RBF kernel. During the training step, we combine these two type s of features using the recent SimpleMKL algorithm. SVM outputs are then filtered to exploit dynamic relationships between Action Units.",

author = "Thibaud Senechal and Vincent Rapp and Hanan Salam and Renaud Seguier and Kevin Bailly and Lionel Prevost",

year = "2011",

doi = "10.1109/FG.2011.5771363",

language = "English (US)",

isbn = "9781424491407",

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

pages = "860--865",

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 - Combining AAM coefficients with LGBP histograms in the multi-kernel SVM framework to detect facial action units

AU - Senechal, Thibaud

AU - Rapp, Vincent

AU - Salam, Hanan

AU - Seguier, Renaud

AU - Bailly, Kevin

AU - Prevost, Lionel

PY - 2011

Y1 - 2011

N2 - This study presents a combination of geometric and appearance features used to automatically detect Action Units in face images. We use one multi-kernel SVM for each Action Unit we want to detect. The first kernel matrix is computed using Local Gabor Binary Pattern (LGBP) histograms and a histogram intersection kernel. The second kernel matrix is computed from AAM coefficients and a RBF kernel. During the training step, we combine these two type s of features using the recent SimpleMKL algorithm. SVM outputs are then filtered to exploit dynamic relationships between Action Units.

AB - This study presents a combination of geometric and appearance features used to automatically detect Action Units in face images. We use one multi-kernel SVM for each Action Unit we want to detect. The first kernel matrix is computed using Local Gabor Binary Pattern (LGBP) histograms and a histogram intersection kernel. The second kernel matrix is computed from AAM coefficients and a RBF kernel. During the training step, we combine these two type s of features using the recent SimpleMKL algorithm. SVM outputs are then filtered to exploit dynamic relationships between Action Units.

UR - http://www.scopus.com/inward/record.url?scp=79958762765&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79958762765&partnerID=8YFLogxK

U2 - 10.1109/FG.2011.5771363

DO - 10.1109/FG.2011.5771363

M3 - Conference contribution

AN - SCOPUS:79958762765

SN - 9781424491407

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

SP - 860

EP - 865

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 -

Combining AAM coefficients with LGBP histograms in the multi-kernel SVM framework to detect facial action units

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this