Melanoma Detection Using Support Vector Machine

Abstract

Skin cancer is a major disease caused by exposure of ultraviolet light. Among the four types of skin cancer as Basal cell carcinoma, squamous cell carcinoma and melanoma, melanoma is most capricious being a fatal disease if not cured in its early stages, such dermatological disease is most difficult to diagnose due to its complexity and subjectivity to manual interpretation. The skin cancer detection technology is broadly divided into four basic components, viz., image pre-processing which includes, de-noise, sharpening, resize of the given skin image, segmentation which is used for segmenting out the region of interest from the given image. In this paper, authors have used k-means segmentation. The classification algorithm used here is Support Vector Machine (SVM) and Convolutional Neural Network (CNN); the latter being used for comparison purpose.