Quality assessment of Median filtering techniques for impulse noise removal from digital images

Abstract

Impulse noise still poses challenges in front of researchers today. The removal of impulse noise brings blurring which leads to edges being distorted and image thus being of poor quality. Hence the need is to preserve edges and fine details during filtering. The proposed method consists of noise detection and then removal of detected noise by Improved Adaptive Median Filter using pixels that are not noise themselves in gray level as well as colour images. The pixels are split in two groups, which are noise-free pixels and noisy pixels. In removing out Impulse noise, only noisy pixels are processed. The noiseless pixels are then sent directly to the output image. The proposed method adaptively changes the masking matrix size of the median filter based on the count of the noisy pixels. Computer simulation and analysis have been carried out eventually to analyse the performance of the proposed method with that of Simple Median Filter (SMF), Simple Adaptive Median Filter (SAMF) and Adaptive Switched Median Filter (ASMF). The proposed filter proves to be more efficient in terms of both objective and subjective parameters.