A Detail Preserving Filter for Impulse Noise Detection and Removal

It is imperative to remove impulse noise corrupted pixels in images, in order to facilitate the subsequent processing such as image analysis, segmentation, pattern recognition etc. Many linear and non linear filtering techniques have been proposed earlier to remove impulse noise, however the removal of impulse noise is often accomplished at the expense of blurred and distorted features of edges; therefore it is necessary to preserve the edges and fine details during filtering. In this paper a no reference blur metric based iterative edge preserving filtering technique has been proposed, that is selective on noisy and edge pixels. Experimental results show that the proposed filter is superior over the state of art filters in maintaining higher peak signal to noise ratio (PSNR), near ideal structural similarity index measurement (SSIM) and lower blur.