Magnifying Subtle Facial Motions for Effective 4D Expression Recognition
This work addresses emotion classification from 4D facial data, offering a novel method that enhances performance for applications like human-computer interaction, but it is incremental as it builds on existing ideas in geometry and filtering.
The paper tackles 4D facial expression recognition by combining Riemannian geometry for spatial deformations with temporal filtering to magnify subtle facial motions, achieving a state-of-the-art 94.18% average accuracy on the BU-4DFE dataset with over 10% improvement after magnification.
In this paper, an effective pipeline to automatic 4D Facial Expression Recognition (4D FER) is proposed. It combines two growing but disparate ideas in Computer Vision -- computing the spatial facial deformations using tools from Riemannian geometry and magnifying them using temporal filtering. The flow of 3D faces is first analyzed to capture the spatial deformations based on the recently-developed Riemannian approach, where registration and comparison of neighboring 3D faces are led jointly. Then, the obtained temporal evolution of these deformations are fed into a magnification method in order to amplify the facial activities over the time. The latter, main contribution of this paper, allows revealing subtle (hidden) deformations which enhance the emotion classification performance. We evaluated our approach on BU-4DFE dataset, the state-of-art 94.18% average performance and an improvement that exceeds 10% in classification accuracy, after magnifying extracted geometric features (deformations), are achieved.