Adaptive edge discriminated median filter to remove impulse noise

In this article, a new approach for removal of impulse noise has been proposed. Here main emphasize is given to distinguish between an edge pixel and a noisy pixel. The proposed method is, basically, a three step method, where in the first step; the suspected pixels are detected based on their differences from neighboring pixels. In the next step, suspected pixels are categorized by edge pixels or noisy pixels. Then the noisy pixels are only replaced by median of uncorrupted pixels of the considering window. To demonstrate the effectiveness of the proposed method, results are compared with other state-of-the-art methods qualitatively and quantitatively. Results of the proposed method are found to be encouraging.