Synthesis of High-Quality Visible Faces from Polarimetric Thermal Faces using Generative Adversarial Networks

The large domain discrepancy between faces captured in polarimetric (or conventional) thermal and visible domains makes cross-domain face verification a highly challenging problem for human examiners as well as computer vision algorithms. Previous approaches utilize either a two-step procedure (visi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of computer vision Jg. 127; H. 6-7; S. 845 - 862
Hauptverfasser: Zhang, He, Riggan, Benjamin S., Hu, Shuowen, Short, Nathaniel J., Patel, Vishal M.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York Springer US 01.06.2019
Springer
Springer Nature B.V
Schlagworte:
Algorithms
Artificial Intelligence
Computer Imaging
Computer Science
Computer vision
Domains
Face recognition
Generative adversarial networks
Image Processing and Computer Vision
Image quality
Image reconstruction
Pattern Recognition
Pattern Recognition and Graphics
Polarimetry
Program verification (computers)
Protocol (computers)
Signatures
Synthesis
Vision
Deep learning
Polarimetric data
Generative adversarial networks
Face synthesis
Heterogeneous face recognition
Thermal face recognition
ISSN:0920-5691, 1573-1405
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The large domain discrepancy between faces captured in polarimetric (or conventional) thermal and visible domains makes cross-domain face verification a highly challenging problem for human examiners as well as computer vision algorithms. Previous approaches utilize either a two-step procedure (visible feature estimation and visible image reconstruction) or an input-level fusion technique, where different Stokes images are concatenated and used as a multi-channel input to synthesize the visible image given the corresponding polarimetric signatures. Although these methods have yielded improvements, we argue that input-level fusion alone may not be sufficient to realize the full potential of the available Stokes images. We propose a generative adversarial networks based multi-stream feature-level fusion technique to synthesize high-quality visible images from polarimetric thermal images. The proposed network consists of a generator sub-network, constructed using an encoder–decoder network based on dense residual blocks, and a multi-scale discriminator sub-network. The generator network is trained by optimizing an adversarial loss in addition to a perceptual loss and an identity preserving loss to enable photo realistic generation of visible images while preserving discriminative characteristics. An extended dataset consisting of polarimetric thermal facial signatures of 111 subjects is also introduced. Multiple experiments evaluated on different experimental protocols demonstrate that the proposed method achieves state-of-the-art performance. Code will be made available at https://github.com/hezhangsprinter .
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-019-01175-3