No abstract

In order to detect any possible anomaly in the region of breast, the use of thermal images has experienced a considerable workload of research in the recent years, this due to the promising results of this technique. One of the principal tasks in this process is the segmentation of the Region of Interest (ROI), but this task is difficult, most of the proposed techniques perform a manual or semi-automatic process to extract it. In this paper, we propose an alternative technique to detect the ROI in thermal breast images. In the proposed technique, we focus on the higher temperature areas in the image. We apply local contrast enhancement, group higher temperature regions, spline cubic interpolation and statistical operations as a part of the method. The achieved results are competitive with the state of the art showing a new alternative to accomplish the automatic segmentation of thermal breast images.