Facial Expression Recognition with Controlled Privacy Preservation and Feature Compensation

Feng Xu, David Ahmedt-Aristizabal, Lars Petersson, Dadong Wang, Xun Li; Proceedings of the Winter Conference on Applications of Computer Vision (WACV), 2025, pp. 2611-2621

Abstract


Facial expression recognition (FER) systems raise significant privacy concerns due to the potential exposure of sensitive identity information. This paper presents a study on removing identity information while preserving FER capabilities. Drawing on the observation that low-frequency components predominantly contain identity information and high-frequency components capture expression we propose a novel two-stream framework that applies privacy enhancement to each component separately. We introduce a controlled privacy enhancement mechanism to optimize performance and a feature compensator to enhance task-relevant features without compromising privacy. Furthermore we propose a novel privacy-utility trade-off providing a quantifiable measure of privacy preservation efficacy in closed-set FER tasks. Extensive experiments on the benchmark CREMA-D dataset demonstrate that our framework achieves 78.84% recognition accuracy with a privacy (facial identity) leakage ratio of only 2.01% highlighting its potential for secure and reliable video-based FER applications.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Xu_2025_WACV, author = {Xu, Feng and Ahmedt-Aristizabal, David and Petersson, Lars and Wang, Dadong and Li, Xun}, title = {Facial Expression Recognition with Controlled Privacy Preservation and Feature Compensation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {2611-2621} }