Mammograms Image Quality Enhancement Using Center Adaptive Median Filter (CEAMF) for Noise and Artifact Removal

Noise and artifact removal is a crucial phase of image preprocessing. Digital mammogram images contain many noises (i.e., salt and pepper, speckles) and artifacts (i.e., opacity, markers, chest wall, date, and background). Artifacts, illumination, and fewer pixel resolutions lead to poor-quality images, reducing segmentation and classification accuracy. This work proposes a center adaptive median filter (CEAMF) for noise and artifact removal to improve image quality. The proposed CEAMF filter performs pixel-wise traversal to remove the noise and artifacts. The proposed method is evaluated on collected and DDSM datasets using the peak signal-to-noise ratio (PSNR) and mean square error (MSE) as parameters and compared with median, mean and Gaussian filters. It is found that the MSE value for the mammogram images is reduced using the proposed method compared to other filters. This reduction in MSE leads to an increase in PSNR and improves the image quality of mammograms.