Classification of malignant melanoma and Benign Skin Lesion by using back propagation neural network and ABCD rule

Abstract

Human Cancer is a standout amongest the most unsafe illnesses which is for the most part brought about by hereditary insecurity of various sub-atomic modifications. Among many types of human disease, skin tumour is the most widely recognized one. To recognize skin tumour at an early stage we will think about and break down them through different methods named as segmentation and feature extraction. Here, we center threatening melanoma skin disease, (because of the high grouping of Melanoma-Hier we offer our skin, in the dermis layer of the skin) location. In this, We utilized our ABCD govern dermoscopy innovation for harmful melanoma skin malignancy location. In this framework distinctive stride for melanoma skin injury portrayal i.e, to begin with, the Image Acquisition Technique, pre-processing, segmentation, characterize a component for skin Feature Selection decides sore portrayal, grouping strategies. In the Feature extraction by advanced picture preparing technique incorporates, Asymmetry recognition, Border Detection, Colour, and Diameter detection and furthermore we utilized LBP for extract the texture based features. Here we proposed the Back Propagation Neural Network to classify the benign or malignant stage.