Skip to main navigation Skip to search Skip to main content

Modified Generative Adversarial Network for Super-Resolution of Terahertz Image

  • Xi'an Jiaotong University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Scopus citations

Abstract

Terahertz (THz) images have low spatial resolution, blurring contour features and high background noise owing to the limitation of terahertz (THz) wavelengths and the THz imaging systems. We have proposed a modified Generative Adversarial Network (GAN) for super-resolution (SR) purpose. To fit the THz images, we design a kind of image degradation model to generate low-resolution images with Gaussian blur and white Gaussian noise. We establish a dataset of damage images in the field of non-destructive testing (NDT) for training and testing. The experimental results on THz images demonstrate that the improved GAN model can improve the quality of THz images effectively. Our method can be beneficial to improve the accuracy of THz NDT with low resolution.

Original languageEnglish
Title of host publicationInternational Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages602-605
Number of pages4
ISBN (Electronic)9781728192772
DOIs
StatePublished - 15 Oct 2020
Event1st International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2020 - Xi'an, China
Duration: 15 Oct 202017 Oct 2020

Publication series

NameInternational Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2020 - Proceedings

Conference

Conference1st International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2020
Country/TerritoryChina
CityXi'an
Period15/10/2017/10/20

Keywords

  • THz image
  • deep learning
  • degradation model
  • super-resolution

Fingerprint

Dive into the research topics of 'Modified Generative Adversarial Network for Super-Resolution of Terahertz Image'. Together they form a unique fingerprint.

Cite this