Deep Perceptual Mapping for Thermal to Visible Face Recogntion

M. Saquib Sarfraz and Rainer Stiefelhagen

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-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 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%.

Session

Deep Learning

Files

Extended Abstract (PDF, 149K)
Paper (PDF, 524K)

DOI

10.5244/C.29.9
https://dx.doi.org/10.5244/C.29.9

Citation

Bibtex

@inproceedings{BMVC2015_9,
	title={Deep Perceptual Mapping for Thermal to Visible Face Recogntion},
	author={M. Saquib Sarfraz and Rainer Stiefelhagen},
	year={2015},
	month={September},
	pages={9.1-9.11},
	articleno={9},
	numpages={11},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.9},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.9}
}