Segmentation and classification of burn images by color and texture information

摘要

In this paper, a burn color image segmentation and classificationsystem is proposed. The aim of the system is to separate burnwounds from healthy skin, and to distinguish among the differenttypes of burns (burn depths). Digital color photographs are used asinputs to the system. The system is based on color and texture information,since these are the characteristics observed by physicians inorder to form a diagnosis. A perceptually uniform color space(L *u*v *) was used, since Euclidean distances calculated in thisspace correspond to perceptual color differences. After the burn issegmented, a set of color and texture features is calculated that servesas the input to a Fuzzy-ARTMAP neural network. The neural networkclassifies burns into three types of burn depths: superficial dermal,deep dermal, and full thickness. Clinical effectiveness of the methodwas demonstrated on 62 clinical burn wound images, yielding anaverage classification success rate of 82%