Deep Perceptual Mapping for Thermal to Visible Face Recognition
This addresses a critical need for security applications by significantly improving thermal-to-visible face recognition, though it is incremental as it builds on existing deep learning methods.
The paper tackles the challenging problem of cross-modal face matching between thermal and visible spectra for night-time surveillance by learning a non-linear mapping using a deep neural network, resulting in a more than 10% improvement in Rank-1 identification and bridging the modality gap by over 40%.
Cross modal face matching between the thermal and visible spectrum is a much de- sired 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 be- tween 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 in- formation. We show substantive performance improvement on a difficult thermal-visible face dataset. The presented approach improves the state-of-the-art by more than 10% in terms of Rank-1 identification and bridge the drop in performance due to the modality gap by more than 40%.