Abstract: Skin cancer is the most dangerous in medical science. Dermatoscope is a device which is used to capture the melanocytic skin lesion images. Dermoscopy images have great potential in the early diagnostic of malignant melanoma. Automatic skin lesion segmentation is an important part of computer-based image. Melanoma is the deadliest form of skin cancer if left untreated. There is a need for an automated system to assess a patient's risk of melanoma using photographs of their skin lesions. Proposed work is used for improving the segmentation accuracy and classification. Segmentation of skin lesion image is done on the basis of a k-means clustering. Classification as melanoma or others based on a kernel sparse based representation classifier.

Keywords: Skin cancer, Image segmentation, Dermatoscope, Kernel sparse classifier.