PERFORMANCE ANALYSIS OF MEDIAN FILTERING APPROACHES FOR IMAGE DENOISING IN THE PRESENCE OF IMPULSIVE NOISE

Abstract

Impulsive noise is also known as salt and pepper noise. Impulsive noise is found in situations where quick transients such as faulty switching take place during image acquisition. Standard median filter has been established as reliable method to remove this noise without harming the edge and image overall contrast. However, the major problem of standard Median Filter (MF) is that the filter is effective only at low noise densities. In our proposed method, adaptive median filter and modified median filtering approaches are implemented and these are compared with different methods to find median for the given data called median of ungrouped data (MUD) also known as standard median filter approach, median of grouped discrete frequency data distribution (MGDFD) and median of grouped continuous frequency data distribution (MGCFD). Our proposed methods performs better in removing low to high density impulsive noise with detail preservation and gives better visual quality and better peak signal to noise ratio(PSNR).