Multi-Metric Evaluation of Thermal-to-Visual Face Recognition

TL;DR

This paper investigates cross-spectral face recognition by synthesizing visual images from infrared using GANs and evaluates recognition performance with various similarity measures.

Contribution

It introduces a multi-metric evaluation framework for thermal-to-visual face recognition using GAN-based synthesis and CNN feature extraction.

Findings

GANs effectively synthesize visual face images from infrared.

CNN features improve face recognition accuracy.

Performance varies with different similarity measures.

Abstract

In this paper, we aim to address the problem of heterogeneous or cross-spectral face recognition using machine learning to synthesize visual spectrum face from infrared images. The synthesis of visual-band face images allows for more optimal extraction of facial features to be used for face identification and/or verification. We explore the ability to use Generative Adversarial Networks (GANs) for face image synthesis, and examine the performance of these images using pre-trained Convolutional Neural Networks (CNNs). The features extracted using CNNs are applied in face identification and verification. We explore the performance in terms of acceptance rate when using various similarity measures for face verification.