This study investigates the efficacy of facial micro-expressions as a soft biometric for enhancing person recognition, aiming to broaden the understanding of the subject and its potential applications. We propose a deep learning approach designed to capture spatial semantics and motion at a fine temporal resolution. Experiments on three widely-used micro-expression databases demonstrate a notable increase in identification accuracy compared to existing benchmarks, highlighting the potential of integrating facial micro-expressions for improved person recognition across various fields.
@article{arxiv.2306.13907,
title = {Person Recognition using Facial Micro-Expressions with Deep Learning},
author = {Tuval Kay and Yuval Ringel and Khen Cohen and Mor-Avi Azulay and David Mendlovic},
journal= {arXiv preprint arXiv:2306.13907},
year = {2023}
}