Segmentation of Skin Lesion towards Melanoma Skin Cancer Classification

Melanoma is one form of skin cancer which is one of the most hazardous types of cancer happened in people. Incidence of skin cancer has been increasing over decades due to excess exposure of radiations from sun causing erosion to skin melanin. The automatic detection of melanoma in dermatological images is a challenging task because of the diverse contrast of skin lesions, the magnitude of melanoma within the class, and the utmost optical similarity to melanoma and lesions other than melanoma and the beingness of many artifacts in the lesion pictures. In this work, the skin lesion analysis system to aid for the melanoma detection is proposed. Firstly, the skin lesion from dermoscopy images is automatically segmented with the use of texture filters. Then, the features according to the underlying ABCD dermatology rules are then extracted from the segmented skin lesion. Finally, the system is classified by random subspace ensemble classifier in order to determine the images as benign or malignant melanoma The performance of the study was experimented with their precision and it achieves with compromising results