Cross-Spectral Face Hallucination via Disentangling Independent Factors

Duan, Boyan; Fu, Chaoyou; Li, Yi; Song, Xianfeng; He, Ran

doi:10.1109/cvpr42600.2020.00795

Cited by 48 publications

(35 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For quantitative evaluation, we perform cross-spectral face recognition based on original and synthesized face images. We also provide five HFR benchmarks on LAMP-HQ, including Pixel2Pixel (Isola et al 2017), CycleGAN (Zhu et al 2017), ADFL (Song et al 2018), PCFH (Yu et al 2019), and PACH (Duan et al 2020). Both LightCNN-9 and LightCNN-29 (Wu et al 2018) are employed as face classifiers in the experiment.…”

Section: Methodsmentioning

confidence: 99%

“…We will release the new database in the near future. In addition, we provide an effective benchmark on a few state-of-the-art methods, including Pixel2Pixel (Isola et al 2017), CycleGAN (Zhu et al 2017), ADFL (Song et al 2018), PCFH (Yu et al 2019), and PACH (Duan et al 2020).…”

Section: Introductionmentioning

confidence: 99%

“…2. We provide a comprehensive qualitative and quantitative efficient benchmark of several state-of-the-art methods for NIR-VIS heterogeneous face recognition (HFR), including Pixel2Pixel (Isola et al 2017), CycleGAN (Zhu et al 2017), and ADFL (Song et al 2018), PCFH (Yu et al 2019), and PACH (Duan et al 2020). The performance on the LAMP-HQ reflects its challenges and difficulties.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Huang

et al. 2021

Int J Comput Vis

Self Cite

View full text Add to dashboard Cite

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 Large-Scale Multi-Pose High-Quality NIR-VIS database 'LAMP-HQ' 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.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Huang

et al. 2021

Int J Comput Vis

Self Cite

View full text Add to dashboard Cite

show abstract

“…Other research directions, such as maximum margin classifier (Siena et al, 2013) and transductive learning (Zhu et al, 2014), are also explored. Further, deep learning-based approaches are also proposed for heterogeneous matching to learn shared representation (Yi et al, 2015), to leverage large homogeneous data (Reale et al, 2016), to learn using limited data (Hu et al, 2018), to facilitate transfer learning (Liu et al, 2016), performing face hallucination via disentangling (Duan et al, 2020), and learning deep models using Wasserstein distance (He et al, 2019). Deng Z. et al (2019) extend MCA to utilize convolutional neural networks for heterogeneous matching.…”

Section: Literature Reviewmentioning

confidence: 99%

Kernelized Heterogeneity-Aware Cross-View Face Recognition

Dhamecha¹,

Ghosh²,

Vatsa³

et al. 2021

Front. Artif. Intell.

View full text Add to dashboard Cite

Cross-view or heterogeneous face matching involves comparing two different views of the face modality such as two different spectrums or resolutions. In this research, we present two heterogeneity-aware subspace techniques, heterogeneous discriminant analysis (HDA) and its kernel version (KHDA) that encode heterogeneity in the objective function and yield a suitable projection space for improved performance. They can be applied on any feature to make it heterogeneity invariant. We next propose a face recognition framework that uses existing facial features along with HDA/KHDA for matching. The effectiveness of HDA and KHDA is demonstrated using both handcrafted and learned representations on three challenging heterogeneous cross-view face recognition scenarios: (i) visible to near-infrared matching, (ii) cross-resolution matching, and (iii) digital photo to composite sketch matching. It is observed that, consistently in all the case studies, HDA and KHDA help to reduce the heterogeneity variance, clearly evidenced in the improved results. Comparison with recent heterogeneous matching algorithms shows that HDA- and KHDA-based matching yields state-of-the-art or comparable results on all three case studies. The proposed algorithms yield the best rank-1 accuracy of 99.4% on the CASIA NIR-VIS 2.0 database, up to 100% on the CMU Multi-PIE for different resolutions, and 95.2% rank-10 accuracies on the e-PRIP database for digital to composite sketch matching.

show abstract

“…In recent years, facial images used for the identification purpose are captured at different electromagnetic spectra and wavelengths, namely, Near-Infrared (NIR), Visible Light (VIS), Short Wavelength Spectrum (SWIR), and Long Wavelength Infrared (LWIR) [ 14 ]. A face recognition system using different spectra, such as VIS and NIR, referred to as cross-spectral (CS) face recognition, is becoming more attractive because of the benefits it potentially brings in the security area and surveillance applications, such as helping to identify a criminal [ 18 , 19 , 20 , 21 , 22 ]. In the surveillance context, CS face recognition schemes can be useful in extreme situations or harsh environments, where the identification and verification process are done in less controlled environments.…”

Section: Introductionmentioning

confidence: 99%

Homomorphic Filtering and Phase-Based Matching for Cross-Spectral Cross-Distance Face Recognition

Arnia

Oktiana

Saddami

et al. 2021

Sensors

View full text Add to dashboard Cite

Facial recognition has a significant application for security, especially in surveillance technologies. In surveillance systems, recognizing faces captured far away from the camera under various lighting conditions, such as in the daytime and nighttime, is a challenging task. A system capable of recognizing face images in both daytime and nighttime and at various distances is called Cross-Spectral Cross Distance (CSCD) face recognition. In this paper, we proposed a phase-based CSCD face recognition approach. We employed Homomorphic filtering as photometric normalization and Band Limited Phase Only Correlation (BLPOC) for image matching. Different from the state-of-the-art methods, we directly utilized the phase component from an image, without the need for a feature extraction process. The experiment was conducted using the Long-Distance Heterogeneous Face Database (LDHF-DB). The proposed method was evaluated in three scenarios: (i) cross-spectral face verification at 1m, (ii) cross-spectral face verification at 60m, and (iii) cross-spectral face verification where the probe images (near-infrared (NIR) face images) were captured at 1m and the gallery data (face images) was captured at 60 m. The proposed CSCD method resulted in the best recognition performance among the CSCD baseline approaches, with an Equal Error Rate (EER) of 5.34% and a Genuine Acceptance Rate (GAR) of 93%.

show abstract

Cross-Spectral Face Hallucination via Disentangling Independent Factors

Cited by 48 publications

References 21 publications

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

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

Kernelized Heterogeneity-Aware Cross-View Face Recognition

Homomorphic Filtering and Phase-Based Matching for Cross-Spectral Cross-Distance Face Recognition

Contact Info

Product

Resources

About