Melanoma is the dangerous form of skin cancer. Rate of melanoma incidence have been increasing nowadays. It is found to be common among non-Hispanic white males and females, but survival rates are high if detected early. Due to the costs for dermatologists to examine every patient, there arises a need for an automated system to assess a patient's risk of melanoma using images of their skin lesions captured using a standard digital camera. One challenge in implementing such a system is locating the skin lesion in the digital image. In the proposed method the image is processed, segmented and spatially gray level dependency matrix (SGLD) features are extracted. Then the features are compared with the given database and classification is done using back propagated artificial neural network (BP-ANN). The proposed framework has higher accuracy compared to other tested algorithms.