A Switching Weighted Adaptive Median Filter for Impulse Noise Removal

Images are often corrupted by impulse noise due to a noisy sensor or channel transmission errors. The goal of impulse noise removal is to suppress the noise by preserving the integrity of edges and detail information. In this paper, a new filter called Switching Weighted Adaptive Median (SWAM) filter is proposed for effective suppression of impulse noise which is used to incorporate the Recursive Weighted Median (RWM) filter and the Switching Adaptive Median (SAM) filter. The adaptive window size is selected using RWM and the output image produced by this filter with least mean square error is considered as input image to SAM filter where impulse detection mechanism is adopted. In this mechanism, the noise is attenuated by estimating the values of noisy pixels with a switch based median filter applied exclusively to those neighborhood pixels not labeled as noisy. Simulation results show consistent and stable performance across a wide range of noise density ranging from 10% to 90%. Unlike the filters like SMF, AMF, WMF and RWM, in the proposed SWAM filter, the window size is selected first based on the presence of the noise density which helps to preserve 2D edge structures of image and delivers a better performance with less computational complexity even at high density impulse noise.