Denoising High Density Impulse Noise using Duo-Median Filter for Mammogram Images

Abstract

Mammogram plays a vital role on cancer detection in the breast. Computerized processing enhances readability of digital mammogram. Impulse noise is one of the major noise which affects mammogram. Duo-median filter is anticipated to removes high density impulse noise. The projected filter checks for impulse noise and replace the pixel value by median of 2x2 neighboring pixel value. Results of proposed algorithm are compared with median filter, adaptive median filter and super mean filter using various parameters such as peak signal to noise ratio and structural similarities for general image and mammogram. The proposed Duo-median shows significantly better result with AMF and SUMF for higher noise percentage.