Fuzzy filters for noisy image filtering

In this paper, seven fuzzy filters for noise reduction in images are introduced. Each of these fuzzy filters applies a weighted membership function to an image within a window to determine the center pixel, and is easy and fast to implement. Simulation results on the filtering performance of these seven fuzzy filters, the standard median filter (MED), and the standard moving average filter (MAV) on images contaminated with low, medium and high impulse and random noise are presented. Results indicate that these seven fuzzy filters achieve varying success in noise reduction in images as compared to the MED and MAV filters.

[1]  Hon Keung Kwan,et al.  Median filtering using fuzzy concept , 1993, Proceedings of 36th Midwest Symposium on Circuits and Systems.

[2]  Moncef Gabbouj,et al.  Nonlinear Digital Filters in Signal Processing , 1991 .

[3]  Sanjit K. Mitra,et al.  Nonlinear image processing , 2000 .

[4]  Fabrizio Russo.  Recent advances in fuzzy techniques for image enhancement , 1998, IEEE Trans. Instrum. Meas..

[5]  Dimitri Van De Ville,et al.  An overview of fuzzy filters for noise reduction , 2001, 10th IEEE International Conference on Fuzzy Systems. (Cat. No.01CH37297).

[6]  D. Van De Ville,et al.  An overview of classical and fuzzy-classical filters for noise reduction , 2001, 10th IEEE International Conference on Fuzzy Systems. (Cat. No.01CH37297).

[7]  Dimitri Van De Ville,et al.  A comparative study of classical and fuzzy filters for noise reduction , 2001, 10th IEEE International Conference on Fuzzy Systems. (Cat. No.01CH37297).

[8]  J. Astola,et al.  Binary polynomial transforms and nonlinear digital filters , 1995 .