LAMP-HQ: A Large-Scale Multi-pose High-Quality Database and Benchmark for NIR-VIS Face Recognition

• Published in: International journal of computer vision Vol. 129; no. 5; pp. 1467 - 1483
• Main Authors: Yu, Aijing, Wu, Haoxue, Huang, Huaibo, Lei, Zhen, He, Ran
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.05.2021; Springer; Springer Nature B.V
• Subjects: Artificial Intelligence; Benchmarks; Biometry; Computer Imaging; Computer Science; Computer vision; Face recognition; Image Processing and Computer Vision; Machine learning; Machine vision; Near infrared radiation; Object recognition; Pattern Recognition; Pattern Recognition and Graphics; Performance enhancement; Special Issue on Computer Vision for All Seasons: Adverse Weather and Lighting Conditions; Training; Vision; Spectral conditional attention; Database; Heterogeneous face recognition; Near infrared-visible matching; Variational spectral attention
• ISSN: 0920-5691; 1573-1405
• DOI: 10.1007/s11263-021-01432-4

Near-infrared-visible (NIR-VIS) heterogeneous face recognition matches NIR to corresponding VIS face images. However, due to the sensing gap, NIR images often lose some identity information so that the NIR-VIS recognition issue is more difficult than conventional VIS face recognition. Recently, NIR-VIS heterogeneous face recognition has attracted considerable attention in the computer vision community because of its convenience and adaptability in practical applications. Various deep learning-based methods have been proposed and substantially increased the recognition performance, but the lack of NIR-VIS training samples leads to the difficulty of the model training process. In this paper, we propose a new L a rge-Scale M ulti- P ose H igh- Q uality NIR-VIS database ‘ LAMP - H Q ’ containing 56,788 NIR and 16,828 VIS images of 573 subjects with large diversities in pose, illumination, attribute, scene and accessory. We furnish a benchmark along with the protocol for NIR-VIS face recognition via generation on LAMP-HQ, including Pixel2-Pixel, CycleGAN, ADFL, PCFH, and PACH. Furthermore, we propose a novel exemplar-based variational spectral attention network to produce high-fidelity VIS images from NIR data. A spectral conditional attention module is introduced to reduce the domain gap between NIR and VIS data and then improve the performance of NIR-VIS heterogeneous face recognition on various databases including the LAMP-HQ.