Volume 4, Issue 1 (Journal of Control, V.4, N.1 Spring 2010)                   JoC 2010, 4(1): 22-32 | Back to browse issues page

XML Persian Abstract Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Shakoori Ganjavi H, Arabi M. Introduction to a Novel Fuzzy Filter for Smoothing 2-Dimensional Signals. JoC 2010; 4 (1) :22-32
URL: http://joc.kntu.ac.ir/article-1-145-en.html
Abstract:   (17000 Views)
: Infection of the correct data by various kinds of noise in transmission or reception of communication signals is an undeniable fact. Data errors may also exist in statistical socio-economic measurements. Annihilation or reduction of noise is a field that attracts many researchers. On the other hand, fuzzy theory has appeared as a powerful tool in this field. Fuzzy filters are often strong in smoothing of corrupted signals, whereas these filters have simple structure. This paper presents a novel fuzzy logic based smoothing filter that has shown both accuracy and simplicity in recovering noisy images by sharpness reduction. Indeed, the proposed procedure is generalization of a previously introduced Fuzzy Smoothing Filter (FSF) for one-dimensional signals. In this method, the sharpness of each point is first determined assigning an index term. Then the procedure looks for “very sharp” points and then smoothes by sharing the values of the eight (or more) neighboring points to correct their values. The lower is the average sharpness of the signal the lower is the signal noise level. This way, the method smoothes out the sharpness and hence reduces the noise of the mix data. To obtain experimental results of the proposed procedure, it is applied to enhance color images corrupted by various levels of noise. The results are compared with some other known methods like AWFM, PWLFIRE and DSFIRE. This comparison exhibits superiority of the proposed method in numerical measures and visual inspection. The method has been designed for annihilation of all kinds of impulse noise in any two-dimensional signals, especially socio-economic statistical data.
Full-Text [PDF 458 kb]   (2391 Downloads)    
Type of Article: Research paper | Subject: Special
Received: 2014/08/22 | Accepted: 2014/08/22 | Published: 2014/08/22

Add your comments about this article : Your username or Email:
CAPTCHA

Send email to the article author


Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

© 2024 CC BY-NC 4.0 | Journal of Control

Designed & Developed by : Yektaweb