Combining LGBP Histograms with AAM coefficients in the Multi-Kernel SVM framework to detect Facial Action Units

Thibaud Sénéchal (1) , Vincent Rapp (1) , Hanan Salam , Renaud Seguier (2) , Kevin Bailly (1) , Lionel Prevost (1)

1 ISIR - Institut des Systèmes Intelligents et de Robotique
2 IETR - Institut d'Électronique et des Technologies du numéRique

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.

Thibaud Sénéchal, Vincent Rapp, Hanan Salam, Renaud Seguier, Kevin Bailly, et al.. Combining LGBP Histograms with AAM coefficients in the Multi-Kernel SVM framework to detect Facial Action Units. FG 2011, Mar 2011, Santa Barbara, United States. pp.860 - 865, ⟨10.1109/FG.2011.5771363⟩. ⟨hal-00657734⟩