FERT: Real-Time Facial Expression Recognition with Short-Range FMCW Radar

TL;DR

This paper introduces a real-time facial expression recognition system using short-range FMCW radar with multi-modal data processing, achieving high accuracy and demonstrating potential for low-cost, non-contact emotion detection.

Contribution

The study presents a novel multi-modal radar-based architecture for real-time facial expression recognition, achieving near 99% accuracy and operating independently of individual subjects.

Findings

Achieved 98.91% classification accuracy.

Operates in real-time and person-independent.

Utilizes low-cost FMCW radar for effective recognition.

Abstract

This study proposes a novel approach for real-time facial expression recognition utilizing short-range Frequency-Modulated Continuous-Wave (FMCW) radar equipped with one transmit (Tx), and three receive (Rx) antennas. The system leverages four distinct modalities simultaneously: Range-Doppler images (RDIs), micro range-Doppler Images (micro-RDIs), range azimuth images (RAIs), and range elevation images (REIs). Our innovative architecture integrates feature extractor blocks, intermediate feature extractor blocks, and a ResNet block to accurately classify facial expressions into smile, anger, neutral, and no-face classes. Our model achieves an average classification accuracy of 98.91% on the dataset collected using a 60 GHz short-range FMCW radar. The proposed solution operates in real-time in a person-independent manner, which shows the potential use of low-cost FMCW radars for effective facial expression recognition in various applications.