Skin cancer is the most common type of cancer in the United States. Melanoma is the most life-threatening form of skin cancer. Each year, more than 68,000 Americans are diagnosed with melanoma, and another 48,000 are diagnosed with an early form of the disease that involves only the top layer of skin. Although advanced melanoma is often considered as incurable, if detected and excised early, the prognosis is promising. Today, clinician use Computer Vision in an increasing number of applications to aid early detection of melanoma through dermatological image analysis. Different methods are used now a day for the analysis of melanoma at the earlier stages. Analysis is mainly based on the various feature sets. Such as Asymmetry, Border, Color, Diameter, Evolution, Texture, Shape etc…But for the detection of melanoma, combining all these features make the method more complex and also more time consuming. To avoid such problem here, these feature sets are compared based on their accuracy and finally find more accurate and time consuming method.

Keywords : Skin Cancer , Melanoma , Computer vision , Feature sets.