Skip to main content

Not afraid of the dark: NIR-VIS face recognition via cross-spectral hallucination and low-rank embedding

Publication ,  Journal Article
Lezama, J; Qiu, Q; Sapiro, G
Published in: Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
November 6, 2017

Surveillance cameras today often capture NIR (near infrared) images in low-light environments. However, most face datasets accessible for training and verification are only collected in the VIS (visible light) spectrum. It remains a challenging problem to match NIR to VIS face images due to the different light spectrum. Recently, breakthroughs have been made for VIS face recognition by applying deep learning on a huge amount of labeled VIS face samples. The same deep learning approach cannot be simply applied to NIR face recognition for two main reasons: First, much limited NIR face images are available for training compared to the VIS spectrum. Second, face galleries to be matched are mostly available only in the VIS spectrum. In this paper, we propose an approach to extend the deep learning breakthrough for VIS face recognition to the NIR spectrum, without retraining the underlying deep models that see only VIS faces. Our approach consists of two core components, cross-spectral hallucination and low-rank embedding, to optimize respectively input and output of a VIS deep model for cross-spectral face recognition. Cross-spectral hallucination produces VIS faces from NIR images through a deep learning approach. Low-rank embedding restores a low-rank structure for faces deep features across both NIR and VIS spectrum. We observe that it is often equally effective to perform hallucination to input NIR images or low-rank embedding to output deep features for a VIS deep model for cross-spectral recognition. When hallucination and low-rank embedding are deployed together, we observe significant further improvement; we obtain state-of-the-art accuracy on the CASIA NIR-VIS v2.0 benchmark, without the need at all to re-train the recognition system.

Duke Scholars

Published In

Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

DOI

Publication Date

November 6, 2017

Volume

2017-January

Start / End Page

6807 / 6816
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Lezama, J., Qiu, Q., & Sapiro, G. (2017). Not afraid of the dark: NIR-VIS face recognition via cross-spectral hallucination and low-rank embedding. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, 2017-January, 6807–6816. https://doi.org/10.1109/CVPR.2017.720
Lezama, J., Q. Qiu, and G. Sapiro. “Not afraid of the dark: NIR-VIS face recognition via cross-spectral hallucination and low-rank embedding.” Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 2017-January (November 6, 2017): 6807–16. https://doi.org/10.1109/CVPR.2017.720.
Lezama J, Qiu Q, Sapiro G. Not afraid of the dark: NIR-VIS face recognition via cross-spectral hallucination and low-rank embedding. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. 2017 Nov 6;2017-January:6807–16.
Lezama, J., et al. “Not afraid of the dark: NIR-VIS face recognition via cross-spectral hallucination and low-rank embedding.” Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, vol. 2017-January, Nov. 2017, pp. 6807–16. Scopus, doi:10.1109/CVPR.2017.720.
Lezama J, Qiu Q, Sapiro G. Not afraid of the dark: NIR-VIS face recognition via cross-spectral hallucination and low-rank embedding. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. 2017 Nov 6;2017-January:6807–6816.

Published In

Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

DOI

Publication Date

November 6, 2017

Volume

2017-January

Start / End Page

6807 / 6816