Automatic Analysis of Facial Expressions Based on Deep Covariance Trajectories - Archive ouverte HAL Access content directly
Journal Articles IEEE Transactions on Neural Networks and Learning Systems Year : 2020

Automatic Analysis of Facial Expressions Based on Deep Covariance Trajectories

Abstract

In this paper, we propose a new approach for facial expression recognition 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 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+, SFEW and AFEW datasets, we show that both the proposed static and dynamic approaches achieve state-of-the-art performance for facial expression recognition outperforming many recent approaches.
Fichier principal
Vignette du fichier
TNNLS_2019.pdf (8.97 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02369410 , version 1 (18-11-2019)
hal-02369410 , version 2 (02-12-2019)

Identifiers

Cite

Naima Otberdout, Anis Kacem, Mohamed Daoudi, Lahoucine Ballihi, Stefano Berretti. Automatic Analysis of Facial Expressions Based on Deep Covariance Trajectories. IEEE Transactions on Neural Networks and Learning Systems, 2020, 31 (10), pp.3892-3905. ⟨10.1109/TNNLS.2019.2947244⟩. ⟨hal-02369410v2⟩
50 View
56 Download

Altmetric

Share

Gmail Facebook X LinkedIn More