Person Recognition using Facial Micro-Expressions with Deep Learning
This work addresses person recognition for applications in security and identification, but it is incremental as it builds on existing deep learning methods for micro-expressions.
The study tackled person recognition by using facial micro-expressions as a soft biometric, achieving a notable increase in identification accuracy on three widely-used databases compared to existing benchmarks.
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.