Person Recognition using Facial Micro-Expressions with Deep Learning

TL;DR

This paper explores using facial micro-expressions with deep learning to improve person recognition accuracy, demonstrating significant gains over existing methods across multiple databases.

Contribution

It introduces a deep learning approach that captures fine-grained micro-expressions for enhanced person recognition, expanding biometric identification techniques.

Findings

Increased recognition accuracy on three micro-expression datasets.

Deep learning effectively captures subtle facial motions.

Micro-expressions improve identification robustness.

Abstract

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.