Deep Perceptual Mapping for Cross-Modal Face Recognition

TL;DR

This paper introduces a deep neural network approach to significantly improve cross-modal face recognition between thermal and visible spectra, addressing the large modality gap for security applications.

Contribution

It presents a novel deep learning method that learns a non-linear mapping to bridge the thermal-visible modality gap, outperforming previous state-of-the-art techniques.

Findings

Over 10% improvement on UND-X1 dataset

Over 15-30% improvement on NVESD dataset

Reduces modality gap impact by more than 40%

Abstract

Cross modal face matching between the thermal and visible spectrum is a much desired capability for night-time surveillance and security applications. Due to a very large modality gap, thermal-to-visible face recognition is one of the most challenging face matching problem. In this paper, we present an approach to bridge this modality gap by a significant margin. Our approach captures the highly non-linear relationship between the two modalities by using a deep neural network. Our model attempts to learn a non-linear mapping from visible to thermal spectrum while preserving the identity information. We show substantive performance improvement on three difficult thermal-visible face datasets. The presented approach improves the state-of-the-art by more than 10\% on UND-X1 dataset and by more than 15-30\% on NVESD dataset in terms of Rank-1 identification. Our method bridges the drop in performance due to the modality gap by more than 40\%.