Handy Skin Diseases using Deep Learning to detect Skin Infections While on the Go

Skin diseases can significantly impact a person’s quality of life. Accurate and timely diagnosis is crucial for effective treatment. This research explores the application of Convolutional Neural Networks (CNNs) to improve dermatological diagnosis. The study utilizes the ISIC 2017 dataset, a large collection of dermatoscopic images, to train and evaluate various CNN architectures, including VGG-16, AlexNet, DermNet, GoogleNet, and MobileNetV2. Preprocessing techniques are employed to enhance image quality and facilitate accurate classification. The proposed hybrid model, combining DermNet and MobileNet with Softmax and ReLU activation functions, achieves an impressive accuracy of $100 \%$ in classifying skin diseases. This result demonstrates the potential of deep learning techniques to revolutionize dermatological diagnosis, enabling early detection and appropriate treatment.