Facial Expression Recognition with Controlled Privacy Preservation and Feature Compensation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Feng, Ahmedt-Aristizabal, David, Petersson, Lars, Wang, Dadong, Li, Xun
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913595692941312
author Xu, Feng
Ahmedt-Aristizabal, David
Petersson, Lars
Wang, Dadong
Li, Xun
author_facet Xu, Feng
Ahmedt-Aristizabal, David
Petersson, Lars
Wang, Dadong
Li, Xun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_00277
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Facial Expression Recognition with Controlled Privacy Preservation and Feature Compensation
Xu, Feng
Ahmedt-Aristizabal, David
Petersson, Lars
Wang, Dadong
Li, Xun
Computer Vision and Pattern Recognition
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.
title Facial Expression Recognition with Controlled Privacy Preservation and Feature Compensation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.00277