Fuzzy Based Filter for Additive Noise Removal

The paper proposes a new fuzzy-based two-step filter for restoring images corrupted with additive noise. The process is implemented as two stages. In the first stage, the difference between the central pixel and its neighbourhood in a selected window is computed and a fuzzy membership degree for each difference value using a Gaussian membership function is calculated. This fuzzy membership values are appropriately utilized as weights for each pixel and then computes the weighted average representing the modified value for the current central pixel. The goal of second stage is to improve the result obtained in the first stage by reducing the noise in the color component differences without destroying the fine details of the image. Finally, the image edges are padded with corresponding pixels to restore the image more accurately. The proposed method gives better results compared to existing advanced filters for additive noise reduction.