Keywords : organizing neural network
Impulse Noise Removal From Highly Corrupted Astronomical Images using Modified Progressive Switching Median Filter Guided by Neural Networks
Journal of Al-Qadisiyah for Computer Science and Mathematics,
2011, Volume 3, Issue 2, Pages 1-14
In this paper, a novel and effective method for impulse noise removal in corrupted color images is discussed. The new method consists of three phases. The first phase is a noise detection phase where a modified self-organizing neural network is used to detect impulse noise pixels. The second is a noise filtering phase process is performed in recursive manner. Third phase is Histogram Equalizer the processed (output) image is obtained by mapping each pixel with level rk in the input image into a corresponding pixel with levels sk in the output image is presented. we propose a technique based on impulse noise detection by means of a self-organizing neural network and a class of the Modified Progressive Switching Median Filter(MPSM) that can remove impulse noise effectively while preserving details. Also, we add a histogram equalizer filter at the output of our proposed system in order to enhance the final output images. Experimental results demonstrate that the performance of the proposed technique is superior to that of the traditional median filter family for impulse noise removal in image applications.