There are thousands of skin cancer patients are registered globally every year. Skin cancer is one of the types of cancer that kills millions of people each year. Early detection and treatment of new dangerous skin cancer cases are critical to ensuring a low death rate as well as a high survival rate. The vast majority of relevant research focuses on machine learning-based algorithms. Another powerful deep learning approach for extracting many properties from an image is a convolutional neural network (CNN). There are two types of images: benign (non-cancerous) and malignant (cancerous) (cancerous). ISIC dataset contains the total number of 2637 images in trained and 660 in the testing dataset used for melanoma detection and classification with the optimum accuracy of 96%.
Index Terms- CNN, testing, training, benign, malignant, skin cancer, melanoma, cancerous, non-cancerous.