Terahertz Deep Learning Super Resolution Imaging Training on Sinogram

Zhao-Hong Tu; Yi-Chun Hung; Shang-Hua Yang

doi:10.1109/IRMMW-THz46771.2020.9370682

Back

Conference paper

Terahertz Deep Learning Super Resolution Imaging Training on Sinogram

Zhao-Hong Tu, Yi-Chun Hung and Shang-Hua Yang

International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz, Vol.2020-November, pp.524-525

11/2020

DOI: https://doi.org/10.1109/IRMMW-THz46771.2020.9370682

Abstract

Energy Engineering and Power Technology

Electrical and Electronic Engineering

We presented a supervised deep learning method to decrease six-fold data acquisition time and to suppress terahertz image artifact levels based on sinogram from terahertz time-domain spectroscopy (THz- TDS). Our method delivered superior image quality than conventional bicubic interpolation method with 0.9612 and 0.0155 in mean square error (MSE) and structural similarity index (SSIM), respectively.

Metrics

1 Record Views

Details

Title: Terahertz Deep Learning Super Resolution Imaging Training on Sinogram
Translated title: Terahertz Deep Learning Super Resolution Imaging Training on Sinogram
Creators - without role: Zhao-Hong Tu - National Tsing Hua University
Yi-Chun Hung - National Tsing Hua University
Shang-Hua Yang - National Tsing Hua University
Identifiers: 9781728166209; 9957772125706774
Academic Unit: Institute of Electronics Engineering, College of Electrical Engineering and Computer Science, National Tsing Hua University
Language: English
Resource Type: Conference paper
Publication Details: International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz, Vol.2020-November, pp.524-525

Terahertz Deep Learning Super Resolution Imaging Training on Sinogram

Abstract

Related links

Metrics

Details

National Tsing Hua University Social media