Image denoising with Weighted
ORientation-Matched filters (WORM)
Abstract
Real world signals commonly exhibit slow variations or oscillations, punctuated
with rapid transients. For example, images typically have smooth regions
interrupted by edges or abrupt changes in contrast. These abrupt changes are
often the most interesting parts of the data perceptually, as well as in terms
of the information that they provide. Some of the high frequency content
represents the important abrupt changes in image intensity that are associated
with real edges of objects in the image. However, some of the high-frequency
content also comprises the noise that is present in the image. We wish to retain
this edge information, while removing the noise. In this Paper, we present a
dynamic filtering process where the dynamic mask is oriented to match the local
gradients and its weights are proportional to the magnitude of the local
gradients.
BibTex
@INPROCEEDINGS{karmaker2018denoising,
author={D. {Karmaker} and I. {Schiffner} and M. {Wilson} and M. V.
{Srinivasan}},
booktitle={2018 IEEE International Conference on Robotics and Biomimetics
(ROBIO)},
title={Image Denoising with Weighted Orientation-Matched Filters(WORM)},
doi={10.1109/ROBIO.2018.8665336},
year={2018}
}
This project was conducted during my PhD candidature at The University of
Queensland
(UQ).
