Unrolling of Graph Total Variation for Image Denoising

Simple item page
dc.contributor.advisorCheung, Gene
dc.contributor.authorVu Huy, Duc
dc.date.accessioned2021-07-06T12:54:36Z
dc.date.available2021-07-06T12:54:36Z
dc.date.copyright2021-04
dc.date.issued2021-07-06
dc.date.updated2021-07-06T12:54:35Z
dc.degree.disciplineElectrical and Computer Engineering
dc.degree.levelMaster's
dc.degree.nameMASc - Master of Applied Science
dc.description.abstractWhile deep learning have enabled effective solutions in image denoising, in general their implementations overly rely on training data and require tuning of a large parameter set. In this thesis, a hybrid design that combines graph signal filtering with feature learning is proposed. It utilizes interpretable analytical low-pass graph filters and employs 80\% fewer parameters than a state-of-the-art DL denoising scheme called DnCNN. Specifically, to construct a graph for graph spectral filtering, a CNN is used to learn features per pixel, then feature distances are computed to establish edge weights. Given a constructed graph, a convex optimization problem for denoising using a graph total variation prior is formulated. Its solution is interpreted in an iterative procedure as a graph low-pass filter with an analytical frequency response. For fast implementation, this response is realized by Lanczos approximation. This method outperformed DnCNN by up to 3dB in PSNR in statistical mistmatch case.
dc.identifier.urihttp://hdl.handle.net/10315/38500
dc.languageen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subjectComputer engineering
dc.subject.keywordsdeep learning
dc.subject.keywordsimage processing
dc.subject.keywordsgraph signal processing
dc.subject.keywordssignal processing
dc.subject.keywordsimage denoising
dc.subject.keywordsimage restoration
dc.subject.keywordsconvolutional neural network
dc.subject.keywordsgraph neural network
dc.titleUnrolling of Graph Total Variation for Image Denoising
dc.typeElectronic Thesis or Dissertation

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Vu_Huy_2021_Masters.pdf
Size:
2.65 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
license.txt
Size:
1.87 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
YorkU_ETDlicense.txt
Size:
3.39 KB
Format:
Plain Text
Description:
Download

Collections

Electrical and Computer Engineering

All items in the YorkSpace institutional repository are protected by copyright, with all rights reserved except where explicitly noted.