Abstract
This study proposes a super-resolution (SR) method for terahertz time-domain spectroscopy (THz-TDS) images, combining a convolutional neural network (CNN) and a mathematical degradation model. The mathematical degradation model considers three possible factors affecting the quality of THz images: the blur kernel, noise, and down-sampler. Specifically, the blur kernel characterizes the continual change of image blur extent with the imaging distance. The designed CNN learns from the degradation model and then copes with the distance dependent image restoration problem based on the learned mapping between the low and high-resolution image pairs. The designed two-stage comparative experiment shows that the proposed method significantly improved the quality of the THz images. To be specific, our proposed method enhanced the resolution by a factor of 1.95 to 0.61 mm with respect to the diffraction limit. In addition, our method achieved the greatest improvement in terms of image quality, with an increase of 4.35 in PSNR and 0.10 in SSIM. We believe that our method could offer a satisfactory solution for THz-TDs image SR applications.
Highlights
Terahertz (THz) imaging has recently emerged as a promising tool for non-destructive detection [1,2,3,4,5], biomedical imaging [6,7,8,9,10], and security scanning [11,12,13]
The designed convolutional neural network (CNN) learns from the degradation model and copes with the distance dependent image restoration problem
THZ IMAGE ACQUISITION The terahertz time-domain spectroscopy (THz-timedomain spectroscopy (TDS)) system used in this study was the T-Ray 5000 manufactured by Advanced Phonotix, Inc
Summary
Terahertz (THz) imaging has recently emerged as a promising tool for non-destructive detection [1,2,3,4,5], biomedical imaging [6,7,8,9,10], and security scanning [11,12,13]. The unique characteristics of THz waves, such as their ability to penetrate through most nonmetallic materials, low energy, and non-ionizing properties, have made THz imaging popular. Due to the intrinsic long wavelength of THz wave, THz images often encounter severe blurring, low signal-to-noise ratio, and lowresolution problems, which is a significant obstacle to the practical application of the THz imaging technique. It is significant to enhance the resolution of the THz images. There are roughly two ways to enhance the resolution of THz images. The first approach is system enhancements, for example, near-field imaging, which could achieve a nanometer-scale lateral resolution [14, 15]. In near-field imaging systems, the object should be placed at a subwavelength distance from the lens.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
