An Adaptive Weighted Mean Filtering Algorithm

DOI

10.2991/iiicec-15.2015.388How to use a DOI?

Keywords

Salt and pepper noise; Gauss noise; Weight; Mean filter; Adaptive.

Abstract

In order to remove the salt and pepper noise and Gauss noise in an image, an improved mean filtering algorithm was presented. The algorithm statistics the non-extreme pixels in a 3x3 filtering window, if the number is smaller than five, then expends the size of filtering window to 5x5, finds out the median of these pixels, and gets the absolute values of difference between these pixels and their median, uses these absolute values and their median to calculate every non-extreme pixel corresponding weight according to normalizing method, then uses these weights and corresponding pixels to weight, the result is used as the center pixel filtering out. Simulation experiments demonstrate the proposed algorithm has strong denoising ability and good detail preserving performance for images polluted by salt and pepper noise and Gauss noise, the filtering effects are better than traditional mean filtering algorithm and other two improved filtering algorithms.

Copyright

© 2015, 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  - Dehai Shen
AU  - Jian Hou
AU  - Xu E
AU  - Longchang Zhang
PY  - 2015/03
DA  - 2015/03
TI  - An Adaptive Weighted Mean Filtering Algorithm
BT  - Proceedings of the 2015 International Industrial Informatics and Computer Engineering Conference
PB  - Atlantis Press
SP  - 1783
EP  - 1786
SN  - 2352-538X
UR  - https://doi.org/10.2991/iiicec-15.2015.388
DO  - 10.2991/iiicec-15.2015.388
ID  - Shen2015/03
ER  -