Facial Expression Recognition with Controlled Privacy Preservation and Feature Compensation

TL;DR

This paper introduces a two-stream FER framework that enhances privacy by removing identity information while maintaining high expression recognition accuracy, using frequency-based feature separation and a privacy-utility trade-off.

Contribution

It proposes a novel frequency-based two-stream framework with privacy enhancement and feature compensation, along with a quantifiable privacy-utility trade-off for FER.

Findings

Achieves 78.84% recognition accuracy on CREMA-D

Maintains only 2.01% facial identity leakage

Demonstrates effective privacy preservation in FER

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.