Breast cancer is the most commonly observed cancer in women both in the developing and the developed countries of the world . Cancer refers to the uncontrolled multiplication of a group of cells in a particular location of the body. A group of rapidly growing or dividing cells may form lump or mass of extra tissue. These masses are referred to as tumors. Cancer cells are termed as malignant tumors. Any form of malignant tumor developed from breast cells is nothing but breast cancer. Breast cancer detection is the standard diagnosis and prognosis. Digital Mammogram has considered as the most popular screening technique for early detection of Breast Cancer and other abnormalities. Digital mammograms are medical images that are difficult to interpret, Develop Computer Aided Diagnosis (CAD) systems that will improve detection of abnormalities in mammogram images. In this paper we present detection of abnormal masses by preprocessing of Breast Images, Region of Interest (ROI). The filters proposed are fully able to isolate and abnormal regions in the breast tissue, If any abnormalities are present it gets accurately highlighted by this filtering and mammogram image preprocessing.