Document Type
Article
Publication Date
10-29-2021
Publication Source
Optical Engineering
Abstract
Super-resolution (SR) aims to increase the resolution of imagery. Applications include security, medical imaging, and object recognition. We propose a deep learning-based SR system that takes a hexagonally sampled low-resolution image as an input and generates a rectangularly sampled SR image as an output. For training and testing, we use a realistic observation model that includes optical degradation from diffraction and sensor degradation from detector integration. Our SR approach first uses non-uniform interpolation to partially upsample the observed hexagonal imagery and convert it to a rectangular grid. We then leverage a state-of-the-art convolutional neural network (CNN) architecture designed for SR known as Residual Channel Attention Network (RCAN). In particular, we use RCAN to further upsample and restore the imagery to produce the final SR image estimate. We demonstrate that this system is superior to applying RCAN directly to rectangularly sampled LR imagery with equivalent sample density. The theoretical advantages of hexagonal sampling are well known. However, to the best of our knowledge, the practical benefit of hexagonal sampling in light of modern processing techniques such as RCAN SR is heretofore untested. Our SR system demonstrates a notable advantage of hexagonally sampled imagery when employing a modified RCAN for hexagonal SR.
ISBN/ISSN
Print: 0091-3286; Electronic: 1560-2303
Document Version
Published Version
Copyright
Copyright © 2021 Society of Photo-Optical Instrumentation Engineers (SPIE). One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this publication for a fee or for commercial purposes, and modification of the contents of the publication are prohibited.
Publisher
Society of Photo-Optical Instrumentation Engineers (SPIE)
Volume
60
Peer Reviewed
yes
Issue
10
Keywords
hexagonal sampling, single-image super-resolution, convolutional neural network, image restoration, University of Dayton Electro-optics and Photonics
eCommons Citation
Flaute, Dylan; Hardie, Russell C.; and Elwarfalli, Hamed, "Resampling and Super-Resolution of Hexagonally Sampled Images Using Deep Learning" (2021). Electrical and Computer Engineering Faculty Publications. 438.
https://ecommons.udayton.edu/ece_fac_pub/438
Included in
Computer Engineering Commons, Electrical and Electronics Commons, Electromagnetics and Photonics Commons, Optics Commons, Other Electrical and Computer Engineering Commons, Systems and Communications Commons
Comments
The document is made available in compliance with the publisher's policy on self-archiving. Permission documentation is on file. To view the paper on the publisher's website, use the DOI: https://doi.org/10.1117/1.OE.60.10.103105