Automatic diagnosis of skin diseases using convolution neural network

Skin diseases are becoming a most common health issues among all the countries worldwide. The method proposed in this work detects four types of skin diseases using computer vision. The proposed approach involves Convolutional Neural Networks with specific focus on skin disease. The Convolutional Neural Network (CNN) used in this paper has utilized around 11 layers viz., Convolution Layer, Activation Layer, Pooling Layer, Fully Connected Layer and Soft-Max Classifier. Images from the DermNet database are used for validating the architecture. The database comprises all types of skin diseases out of which we have considered four different types of skin diseases like Acne, Keratosis, Eczema herpeticum, Urticaria with each class containing around 30 to 60 different samples. The challenges in automating the process includes the variation of skin tones, location of the disease, specifications of the image acquisition system etc., The proposed CNN Classifier results in an accuracy of 98.6% to 99.04%. (C) 2020 Elsevier B.V. All rights reserved.