Towards Natural Image Denoising by Sparse Code Shrinkage: Improvements and Applications

DOI

10.2991/iske.2007.207How to use a DOI?

Keywords

Sparse code shrinkage, Feature extraction, Independent component analysis, Image denoising.

Abstract

Sparse code shrinkage (SCS) has been proved to be a very promising method for natural image denoising, but it still has some drawbacks such as considerable complexity of computation and inevitable loss of image details. In this paper, we propose a new compensation operation and an improved shrinkage function to effectively combat the loss of image details in SCS. We also propose a new strategy of sliding window and non-square ICA filters to relieve the computational complexity of SCS in real-time system. Compared with ordinary SCS, our method can remain better performance while achieving higher efficiency in natural image denoising.

Copyright

© 2007, 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  - Ying Yu
AU  - Jian Yang
AU  - Dan Xu
PY  - 2007/10
DA  - 2007/10
TI  - Towards Natural Image Denoising by Sparse Code Shrinkage: Improvements and Applications
BT  - Proceedings of the 2007 International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2007)
PB  - Atlantis Press
SP  - 1214
EP  - 1221
SN  - 1951-6851
UR  - https://doi.org/10.2991/iske.2007.207
DO  - 10.2991/iske.2007.207
ID  - Yu2007/10
ER  -