Segmentation Algorithms for Thermal Images

• DOI: 10.1016/j.protcy.2014.10.178
• Publication Date: 2014-11-11T12:44:40Z
• Authors: A. Duarte; L. Carrão; M. Espanha; T. Viana; D. Freitas; P. Bártolo; P. Faria; H.A. Almeida
• Keywords: Ellipse; Region of interest; Thermography; Identification

Biomedical techniques and applications are being developed placed at the service of clinicians. An example is medical thermography, which used more often in detection certain diseases also pain distribution. Current thermography processing software has some limitations mainly because it for general does not allow identification a Region Of Interest (ROI) with specific anatomic shape. commercial usually uses regular prismatic shapes definition these regions, such as, rectangles, squares, circles and/or ellipse that poorly define complex geometric regions. These present when they do fit shape area to be characterized, either by exclusion or inclusion irrelevant data evaluation thermal images. This particular limitation observed no matter how accurate ROI is. In order improve characterization images, computational application was developed. The existing overcome designing an allows choosing any ROI, independently its optimize further processing. research work presents several segmentation algorithms comparison untreated optimized ROI's.