Development of Efficient Classification Systems for the Diagnosis of Melanoma

Skin cancer is usually classified as melanoma and non-melanoma. Melanoma now represents 75% of humans passing away worldwide one the most brutal types cancer. Previously, studies were not mainly focused on feature extraction Melanoma, which caused classification accuracy. However, in this work, Histograms orientation gradients local binary patterns procedures are used to extract important features such asymmetry, symmetry, boundary irregularity, color, diameter, etc., removed from both non-melanoma images. This proposed Efficient Classification Systems for Diagnosis (ECSDM) framework consists different schemes preprocessing, segmentation, extraction, classification. We Machine Learning (ML) Deep (DL) classifiers framework. The ML classifier Naïve Bayes (NB) Support Vector Machines (SVM). And also, DL Convolution Neural Network (CNN) classify benign results show that (NNET) classifier’ achieves 97.17% accuracy when contrasting with classifiers.