원문정보
초록
영어
A novel fuzzy logic based filtering technique is proposed to restore images corrupted by impulse noise. The proposed scheme is in two phases namely the detection of noisy pixels at all locations in the image using fuzzy knowledge based and application of recursive median filter on the corrupted pixels to remove the impulse noise. The performance of the proposed technique is tested on various test images corrupted at various noise densities and also compared with some of the existing filters. Experimental results show that the proposed technique exhibits superior performance than their counterparts and is efficiently capable of removing fixed-valued impulse noise densities, ranging from 5% to 40% in the image while at the same time effectively preserving the useful information in the image.
목차
1. Introduction
2. Impulse Noise Model
3. Proposed Technique
A. Impulse Noise Detection and Fuzzy Rules
B. Defuzzification
C. Recursive Median Filtering Algorithm
4. Simulation Results
5. Conclusion
References