Enhancing Skin Disease Diagnosis Through Convolutional Neural Networks and YOLO v8 Object Detection

Skin disease detection and diagnosis has been overviewed as one of the most predominant challenges in this lousy and contaminated environment. Appropriate skin checking and disease detection can be a revolutionary outbreak in the medical science field. This leads to early discovery of any destructive skin diseases. Laser and photonic based medical technologies can help in the diagnosis, yet the scope of those tests is quite limited. Machine learning techniques contribute to enhancing robust frameworks capable of categorizing different classes of skin diseases. Within this context, Computer vision plays a crucial role employing various techniques for the effective detection of skin diseases in. This work contributes to the research of early detection of skin diseases. An image processing-based method is proposed in this work. The method takes digital images of the affected area and use image analysis to identify the type of disease. Our approach is fast, accurate, easily available, simple, and cost-effective. After proper analysis, the results are shown to the user including type of disease and severity. The system successfully detects 8 distinct types of skin diseases with an average accuracy of 80-90%.