A Comparative analysis of various segmentation techniques for breast thermal images

Breast cancer is one of the deadliest diseases among women ranging from young to old and second common disease that leads to death for women after lung cancer. In this paper investigates the effectiveness of thresholding, edge detection, region-based, and watershed-based segmentation techniques on breast thermal images captured from five distinct perspectives: front view, left at 45°, left at 90°, right at 45° and right at 90° views. The main objective of this research is to identify an appropriate segmentation technique that can improve the accuracy of breast cancer detection in noninvasively through thermal imaging. Each segmentation technique is applied on Region of Interest (ROI) breast thermal images to accurately delineate the breast abnormalities. Results suggest a suitable segmentation that is suitable to analyze breast thermal images with particular angle.