Improved sorted switching median filter for removal of impulse noise

Digital image processing plays important role in our daily life. Digital Image Processing involves the modification of digital data for improving the image qualities with the aid of computer. The processing helps in maximize the clarity, sharpness of image and details of features of interest. The digital image is given as input into a computer and computer is programmed to change data with the help of various computations and then store the values of the computation for each pixel.Noise is defined as unwanted signals. The noise is removed with the help of image denoising algorithm. In this paper a filtering algorithm, improved sorted switching median filter (ISSMF) is introduced. In this algorithm two phases are included. In the first phase, the processing pixel is checked whether it is corrupted or uncorrupted. If processing pixel is uncorrupted then it remains unchanged and if processing pixel is corrupted then it is passed to second phase. In the second phase the filtering process is applied to corrupted pixel and value of corrupted pixel is replaced with the calculated median value using ISSMF.In order to preserve the edges detail, the gradient smoothing is applied. Several extensive simulation results conducted on both grayscale and color images with various density levels and ISSMF performs better than the existing median-based filters. Keywords—Digital image, Processing pixel, Impulse noise, Denoising, ISSMF, Edge detection, Gradient, PSNR, MSE, RMSE, BER.