An Approach to Minimize Very High Density Salt and Pepper Noise through Trimmed Global Mean

In this paper, we are proposing an approach to minimize very high density salt and pepper noise through trimmed global mean. The Modified decision based unsymmetrical trimmed median filter tries to remove high density salt and pepper noise by taking the mean value of the elements within the processing window. This algorithm fails if all the elements within the processing window is either ‘0’ or ‘255’. In our approach, if all the elements within the window are ‘0’ or ‘255’ then the noisy pixel is replaced by the trimmed global mean. The proposed algorithm exhibits better image quality than the median filter, adaptive median filter, decision based median filter and modified decision based unsymmetrical trimmed median filter. The proposed algorithm is tested for different grayscale and color images and it gives better peak signal to noise ratio and image enhancement factor.