Non Local Means Denoising for 3D MR Images

DOI

10.2991/iccsee.2013.197How to use a DOI?

Keywords

NL-means, denoising, 3D, MRI, parallelize, GPU

Abstract

Denoising is a crucial step to increase image conspicuity and to improve the performances of all the processing needed for quantitative image analysis. In this paper, the main method we proposed is Non Local Means. We carried out our experiments based on 3D MR images from Brain Web. We compared The NL-means with some classical methods, such as Anisotropic Diffusion Filter and Bilateral Filter. The results show that the Filtering performance of NL-means is better than other methods. Moreover, we present an optimized version of original NL-means and parallelize the computation on GPU device.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Hao Song
AU  - Jing Jin
PY  - 2013/03
DA  - 2013/03
TI  - Non Local Means Denoising for 3D MR Images
BT  - Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering (ICCSEE 2013)
PB  - Atlantis Press
SP  - 780
EP  - 783
SN  - 1951-6851
UR  - https://doi.org/10.2991/iccsee.2013.197
DO  - 10.2991/iccsee.2013.197
ID  - Song2013/03
ER  -