Performance observation of mammograms using an improved dynamic window based adaptive median filter

Breast cancer is one of the vital causes of an increase in the rate of mortality of women in developing countries. Detection of masses in the breast tissue by the radiologists is a significant step in the process of identification of cancer in the breast. Pre-processing in mammogram has played a major role in identifying such masses in the breast. Mammography has emerged as the popular screening approach for early identification of masses in the breast. In this manuscript, we have introduced an improved Dynamic Window based Adaptive Median Filter (DWAMF) for removal of impulse noise. DWAMF algorithm is implemented for removal of noise based on its size in the direction to enhance the image standard. The experimental results of DWAMF has been compared with Standard Median Filter (MF), and its observed that the DWAMF gives better result and higher value along with the introduction of threshold value with the increased percentage of noise. To compare the performance of the studies on filter methods, the Mean square Error (ME), Peak signal to Noise Ratio (PNR) and Structural Content (SC) measures are used to evaluate and compare the performance of the studied models.