Paper Contents
Abstract
The skin, a vital protective barrier for internal organs, is prone to infections caused by viruses, fungi, or dust, leading to conditions like eczema and acne that affect millions globally. Early detection and diagnosis of skin diseases are crucial to prevent severe complications and ensure effective treatment. This study focuses on developing a neural network-based website to detect 23 skin diseases, offering related videos, articles, and suggestions for nearby dermatologists. A convolutional neural network (CNN) using the DenseNet architecture was employed for model training on the DERMNET dataset. The system achieved a 90.5% accuracy rate at 48 epochs, implemented using Python. With further enhancements and a larger dataset, the solution holds significant potential for improving skin disease management and awareness.
Copyright
Copyright © 2025 Ankitha R. This is an open access article distributed under the Creative Commons Attribution License.
