Reference : Automatic Analysis of Facial Expressions Based on Deep Covariance Trajectories
Scientific journals : Article
Engineering, computing & technology : Computer science
Computational Sciences
http://hdl.handle.net/10993/41230
Automatic Analysis of Facial Expressions Based on Deep Covariance Trajectories
English
Otberdout, Naima []
Kacem, Anis mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
Daoudi, Mohamed []
Ballihi, Lahoucine []
Berreti, Stefano []
3-Oct-2019
IEEE Transactions on Neural Networks and Learning Systems
IEEE Computational Intelligence Society
Yes
International
2162-237X
United States
[en] Convolutional neural networks ; covariance matrix ; deep trajectory ; facial expression recognition
[en] In this article, we propose a new approach for facial expression recognition (FER) using deep covariance descriptors. The solution is based on the idea of encoding local and global deep convolutional neural network (DCNN) features extracted from still images, in compact local and global covariance descriptors. The space geometry of the covariance matrices is that of symmetric positive definite (SPD) matrices. By conducting the classification of static facial expressions using a support vector machine (SVM) with a valid Gaussian kernel on the SPD manifold, we show that deep covariance descriptors are more effective than the standard classification with fully connected layers and softmax. Besides, we propose a completely new and original solution to model the temporal dynamic of facial expressions as deep trajectories on the SPD manifold. As an extension of the classification pipeline of covariance descriptors, we apply SVM with valid positive definite kernels derived from global alignment for deep covariance trajectories classification. By performing extensive experiments on the Oulu-CASIA, CK+, static facial expression in the wild (SFEW), and acted facial expressions in the wild (AFEW) data sets, we show that both the proposed static and dynamic approaches achieve the state-of-the-art performance for FER outperforming many recent approaches.
Researchers ; Professionals ; Students
http://hdl.handle.net/10993/41230
https://ieeexplore.ieee.org/document/8901420

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
TNNLS.pdfAuthor preprint9.33 MBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.