CFP last date
20 January 2025
Reseach Article

Gaussian Noise Reduction using Adaptive Window Median Filter

Published on September 2014 by Sandip Mehta, Jayashri Vajpai, Sanjay B.c. Gaur
National Conference on Advances in Technology and Applied Sciences
Foundation of Computer Science USA
NCATAS - Number 2
September 2014
Authors: Sandip Mehta, Jayashri Vajpai, Sanjay B.c. Gaur
59f072bf-f812-4c51-901b-30b0d6573709

Sandip Mehta, Jayashri Vajpai, Sanjay B.c. Gaur . Gaussian Noise Reduction using Adaptive Window Median Filter. National Conference on Advances in Technology and Applied Sciences. NCATAS, 2 (September 2014), 25-27.

@article{
author = { Sandip Mehta, Jayashri Vajpai, Sanjay B.c. Gaur },
title = { Gaussian Noise Reduction using Adaptive Window Median Filter },
journal = { National Conference on Advances in Technology and Applied Sciences },
issue_date = { September 2014 },
volume = { NCATAS },
number = { 2 },
month = { September },
year = { 2014 },
issn = 0975-8887,
pages = { 25-27 },
numpages = 3,
url = { /proceedings/ncatas/number2/17954-1615/ },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Proceeding Article
%1 National Conference on Advances in Technology and Applied Sciences
%A Sandip Mehta
%A Jayashri Vajpai
%A Sanjay B.c. Gaur
%T Gaussian Noise Reduction using Adaptive Window Median Filter
%J National Conference on Advances in Technology and Applied Sciences
%@ 0975-8887
%V NCATAS
%N 2
%P 25-27
%D 2014
%I International Journal of Computer Applications
Abstract

This paper proposes an adaptive window median filter (AWMDF) for Gaussian noise reduction. This is a spatial method where an n x n filtering window is applied around each noisy pixel. However, to make this possible for the boundary pixels, the image has to be padded on all sides by some padding method. The symmetrical padding method has been adopted here. Odd sized window is preferred as it provides better results for median estimation. Depending upon the noise levels, the method chooses desired window sizes. For low noise levels, the 3x3 filtering window is preferred, for medium noise levels, the 5x5 filtering window is preferred while for high noise levels, the 7x7 filtering window is preferred. Higher sized windows viz. 9x9, 11x11, etc. do not provide any advantage at any noise levels. The advantage of this filter is its simplicity and ease of application and provides reasonable qualitative and quantitative results.

References
  1. Rafael C. Gonzalez, and Richard E. Woods, "Digital Image Processing", 2nd edition, Prentice Hall, 2002.
  2. Bovik, Handbook of Image and Video Processing. New York: Academic, 2000.
  3. C. Bovik, T. Huang, and D. C. Munson, "A generalization of median filtering using linear combinations of order statistics," IEEE Trans. Acoust. , Speech, Signal Processing, vol. ASSP-31, pp. 1342–1350, June 1983.
  4. T. A. Nodes and N. C. Gallagher, Jr. , "The output distribution of median type filters," IEEE Trans. Commun. , vol. COM-32, pp. 532–541, May 1984.
  5. T. Sun and Y. Neuvo, "Detail-preserving median based filters in image processing," Pattern Recognit. Lett. , vol. 15, pp. 341–347, Apr. 1994.
  6. Florencio and T. Schafer, "Decision-Based Median Filter Using Local Signal Statistics", Proc. SPIE Int. Symp. Visual Communications Image Processing, 1994.
  7. Pitas and A. N. Venetsanopoulos, "Order Statistics in Digital Image Processsing ", Proceedings of the IEEE, vol. 80, No. 12, December 1992.
  8. D. L. Donoho and I. M. Johnstone, "Ideal Spatial Adaptation via Wavelet Shrinkage", Biometrika, Vol. 81, No. 3, pp. 425–455, 1994.
  9. D. L. Donoho and I. M. Johnstone, "Adapting to Unknown Smoothness via Wavelet Shrinkage," J. Amer. Stat. Assoc. , Vol. 90, No. 432, pp. 1200–1224, 1995.
Index Terms

Computer Science
Information Sciences

Keywords

Gaussian Noise Median Filter Spatial Method