The paper discusses the removal of salt and pepper noise by using various median filters for various test images. It gives a better idea and analysis of different median filter algorithms for the restoration of various gray scale images that are corrupted by salt and pepper noise. The performance of different median filters, such as Standard Median Filter (MF), Adaptive Median Filter (AMF), Adaptive Weighted Algorithm (AWA), Switching Median Filter (SMF), Decision-Based Algorithm (DBA) and Modified Decision-Based Unsymmetric Trimmed Median Filter (MDBUTMF), is compared by using Mean Square Error (MSE) and Peak Signal-to-Noise Ratio (PSNR) obtained from the simulation results for different images.

Filtering is the most crucial part in signal processing system, which is used to estimate the signal degradation, most probably because of impulse noise. Several filtering techniques are proposed to remove this noise and to improve the image details to make them appealing to human visual perception (Gonzales and Woods, 2002). Several filtering techniques are proposed and used for various applications. Nonlinear filtering techniques are popularly used in image processing because of the nonlinearities of the image information. The filters that are having good image quality and preserve edge details are highly desirable. The most commonly used filters to remove impulse noise are the variants in median filters. When median filters are applied over the noisy image, they tend to modify both noisy as well as noise-free pixels of the image, resulting in blurred and distorted image (Arce and McLoughlin, 1987).

In signal processing, noise reduction is desirable on an image or signal. The most basic and popular nonlinear digital filtering technique is median filter, which is used to remove noise. Such noise reduction is a typical preprocessing step to improve the results of later processing. Median filtering is very widely used in digital image processing because under certain conditions, it preserves edges while removing noise.

Telecommunications Journal, Image, Noise, Median filter, Standard Median Filter (MF), Adaptive Median Filter (AMF), Adaptive Weighted Algorithm (AWA), Switching Median Filter (SMF), Decision-Based Algorithm (DBA).