Menna Massoud, September 2018--August 2020, "Framework for Kernel-based BM3D Algorithm", Computer Science Department, Faculty of Science, University of Western Ontario, Canada
M.Sc. Thesis Abstract
Patch-based approaches as Block Matching and 3D collaborative fltering (BM3D) algorithm represent the current state of the art in image denoising. However, BM3D still suffers from degradation in performance in smooth areas as well as the loss of image details, specifcally at the presence of high noise levels. Integrating shape adaptive methods with BM3D improves the denoising performance and the visual quality of the denoised image. It also maintains image details. In this study, we proposed a framework that produces multiple images using various shapes. These images will then be aggregated at the pixel or patch levels for both stages in BM3D. These images, when appropriately aggregated, resulting in better denoising performance than BM3D by 1.15 dB, on average.