Skin melanoma segmentation by morphological approach

A new approach to extract the lesion region of melanoma is presented. This approach is based on color morphological operators which are defined from a lexicographic order on the HSI color space. The morphological filtering allows highlighting the region of melanoma that is then segmented by binarization. No a priori knowledge about the process of image acquisition and the type of melanoma is employed and a few heuristics are used. Tests were performed for two sets of benign and malignant melanoma images and compared with the ground-truth lesion segmentation by applying twelve metrics. The results prove the efficiency of this approach with regard to the automatic segmentation of both benign and malignant melanoma.