Abstract: In this paper, a various noise reduction techniques to remove high density Salt and Pepper noise is presented and the importance of impulse noise removal has been studied and implemented. The effective removal of impulse noise from gray-scale image is performed by median filter and analyzed various noise reduction techniques such as Switching Median filter, Adaptive median filter, Dynamic median filter and Trimmed median filter which removes noise effectively even at high noise level and preserves the fine details and edges effectively with reduced streaking at higher noise densities and gives better performance when compared to Median filter. The above techniques works by detecting the corrupted pixels and replaced them with median value. It will remove only 0 and 255, they will be most likely replaced close approximations of their original values (i.e. 0 with 1 or 2 and 255 with 254 or 253). Different filtering techniques are applied in removing low to medium density impulse noise with detail preservation up to a noise density of 70% compared to standard median filter (MF), Switching median filter (SMF), Adaptive median filter (AMF), Dynamic Adaptive Median Filter (DAMF), Unsymmetric Median Filter (USMF), Trimmed median filter (TMF).The ITMF performs well compared to other filters and it gives better results with high PSNR.

Keywords: MATLAB; Switching median filter, Dynamic Adaptive median filter, Unsymmetric median filter, Trimmed median filter, salt & pepper noise, PSNR.