Characterization of skin lesions

Malignant melanoma is the deadliest form among all skin cancers. Fortunately, if detected early, even malignant melanoma may be treated successfully. In this paper, a new intelligent method of classifying benign and malignant melanoma lesions is used. As the first step of the image analysis, preprocessing techniques are used to remove noise and undesired structures from the images using filter such as median filtering. Segmentation is one of the important steps in cancer automatic detection, because it can greatly affect on the results of detection. In the second step, a simple thresholding method is used to segment and localize the lesion, a boundary tracing algorithm is also implemented to validate the segmentation. In the third step, the different features are extracted from a segmented image and classified by using Stolz algorithm.