DeepSkin: A Deep Learning Approach for Skin Cancer Classification

Skin cancer is one of the most rapidly spreading illnesses in world and because limited resources available. Early detection skin crucial accurate diagnosis identification for preventive approach general. Detecting at an early stage challenging dermatologists, as well recent years, both supervised unsupervised learning tasks have made extensive use deep learning. One these models, Convolutional Neural Networks (CNN), has surpassed all others object classification tests. The dataset screened from MNIST: HAM10000 which consists seven different types lesions with sample size 10015 used experimentation. data pre-processing techniques like sampling, dull razor segmentation using autoencoder decoder employed. Transfer DenseNet169 Resnet 50 were to train model obtain results.