This paper compares efficient filters for the restoration of images that are corrupted by a high density of Salt and Pepper noise. There are several non linear filters for the restoration of the images. Among these, median filters are the most popular and powerful technique for the removal of salt and pepper noise. Different variations of median filters are now available. These variations outperform the standard median filter. These filtering techniques include two stages, such as noise detection stage and noise filtering stage. The noise detection stage will identify the noisy pixel within the image and noise filtering stage will filter the image. The performance qualities of different filters are measured using Peak-Signal to Noise Ratio (PSNR) and Image Enhancement Factor (IEF) value.