International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 47 - Number 4 |
Year of Publication: 2012 |
Authors: Rashmi Kumari, S.k.aggarwal |
10.5120/7176-9824 |
Rashmi Kumari, S.k.aggarwal . Modeling of Uncertainties using Fuzzy Interval for Enhancement of Images Corrupted by Impulse Noise. International Journal of Computer Applications. 47, 4 ( June 2012), 22-24. DOI=10.5120/7176-9824
Noise filtering is the fundamental pre-processing step for digital images. In this paper we present a novel method in which the uncertainties of fuzzy membership function is modeled to reduce and the concept of this reduced uncertainties is used to detect the impulse corrupted pixels of digital images. Taking an interval instead of using a crisp value of membership function deals better with the uncertainties arises due to noisy data, uncertain meaning of word etc. Impulse noise is detected by using Laplacian operator and blurred S-shaped fuzzy membership function is used for removal of impulse noise where for the restoration the half of sum of mean and median of the kernel is used . The performance is compared with other existing filters on the basis of PSNR values calculated for original and restored images.