Identifying Masses in Mammograms Using Template Matching

This paper introduces a novel segmentation scheme based on the template-matching method is used for identifying cancerous part in the mammogram image. These templates are defined according to the shape, and brightness of the masses or micro calcifications. Earlier to template matching, median filtering enhances the mammogram images, Edge detection operators such as Sobel, Prewitts, Laplacian and Laplacian of Guassian masks are enhances and detect the edges and then edge detection is used to detect the shape of the cancerous part. In the template matching, the threshold is set for the calculated values of the crosscorrelation. Then the percentile method is used to set an overall threshold for each mammogram image. The segmentation accuracy is increased as the proposed scheme is more robust to noise and hence, it prevents over segmentation in final segmented images. It is exposed that, this method of template matching for identifying early stage cancerous parts gives considerably better detection results.