Abstract
Given an image filter y=f(x), where x and y are input and output images, respectively, reverse image filtering consists of rendering an approximation to x from y using the filter f(⋅) itself as a black box, without knowing the internal structure of the filter. In this paper, we propose to use modified Landweber iterations for reverse image filtering, evaluate the performance of our approach, and present applications to image deblurring and super-resolution. An important advantage of our approach over the existing reverse image filtering methods is high robustness to noise.
Original language | English |
---|---|
Pages (from-to) | 333-341 |
Number of pages | 9 |
Journal | Signal, Image and Video Processing |
Volume | 17 |
Issue number | 2 |
Early online date | 1 Jul 2022 |
DOIs | |
Publication status | Published - Mar 2023 |
Keywords
- Deblurring
- Image super-resolution
- Landweber iterations
- Phase correction
- Reverse filtering
ASJC Scopus subject areas
- Signal Processing
- Electrical and Electronic Engineering