CASIA OpenIR  > 模式识别实验室
Adversarial Cross-Spectral Face Completion for NIR-VIS Face Recognition
He, Ran1,2; Cao, Jie1,2; Song, Lingxiao1,2; Sun, Zhenan1,2; Tan, Tieniu1,2
Source PublicationIEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
2020
Volume42Issue:5Pages:1024 - 1037
Abstract

Near infrared-visible (NIR-VIS) heterogeneous face recognition refers to the process of matching NIR to VIS face images. Current heterogeneous methods try to extend VIS face recognition methods to the NIR spectrum by synthesizing VIS images from NIR images. However, due to the self-occlusion and sensing gap, NIR face images lose some visible lighting contents so that they are always incomplete compared to VIS face images. This paper models high-resolution heterogeneous face synthesis as a complementary combination of two components: a texture inpainting component and a pose correction component. The inpainting component synthesizes and inpaints VIS image textures from NIR image textures. The correction component maps any pose in NIR images to a frontal pose in VIS images, resulting in paired NIR and VIS textures. A warping procedure is developed to integrate the two components into an end-to-end deep network. A fine-grained discriminator and a wavelet-based discriminator are designed to improve visual quality. A novel 3D-based pose correction loss, two adversarial losses, and a pixel loss are imposed to ensure synthesis results. We demonstrate that by attaching the correction component, we can simplify heterogeneous face synthesis from one-to-many unpaired image translation to one-to-one paired image translation, and minimize the spectral and pose discrepancy during heterogeneous recognition. Extensive experimental results show that our network not only generates high-resolution VIS face images but also facilitates the accuracy improvement of heterogeneous face recognition.

Keywordheterogeneous face recognition near infrared-visible matching face completion face inpainting
Indexed BySCI
Language英语
Sub direction classification生物特征识别
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/44729
Collection模式识别实验室
Affiliation1.中国科学院自动化研究所
2.中国科学院大学
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
He, Ran,Cao, Jie,Song, Lingxiao,et al. Adversarial Cross-Spectral Face Completion for NIR-VIS Face Recognition[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2020,42(5):1024 - 1037.
APA He, Ran,Cao, Jie,Song, Lingxiao,Sun, Zhenan,&Tan, Tieniu.(2020).Adversarial Cross-Spectral Face Completion for NIR-VIS Face Recognition.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,42(5),1024 - 1037.
MLA He, Ran,et al."Adversarial Cross-Spectral Face Completion for NIR-VIS Face Recognition".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 42.5(2020):1024 - 1037.
Files in This Item: Download All
File Name/Size DocType Version Access License
He 等。 - 2019 - Adver(4148KB)期刊论文作者接受稿开放获取CC BY-NC-SAView
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[He, Ran]'s Articles
[Cao, Jie]'s Articles
[Song, Lingxiao]'s Articles
Baidu academic
Similar articles in Baidu academic
[He, Ran]'s Articles
[Cao, Jie]'s Articles
[Song, Lingxiao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[He, Ran]'s Articles
[Cao, Jie]'s Articles
[Song, Lingxiao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: He 等。 - 2019 - Adversarial cross-spectral face completion for NIR.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.