Novel multi-step region growing algorithm for the segmentation of burn images

Abstract

In this paper, a novel region growing algorithm for segmenting burn wounds in digital photographs of the skin is presented. This segmentation step has been developed as part of a CAD tool for burn diagnosis. During the region growing the inclusion condition relies on a tolerance parameter, which is adaptively determined. It initially has a low value and this is recursively increased until a stop condition is reached. This condition is based on the analysis of the statistical distribution of the pixels within the grown region. The great advantage of the method is that it does not rely on fine-tune parameters. The algorithm has been tested with 44 images of burn wounds obtaining very good results. Its performance has been measured quantitatively by comparing it with a ground truth obtained from the manual segmentation of five experts.