Published Paper Details:

Skin diseases are a significant public health issue, affecting millions of people globally. Early and accurate diagnosis of these diseases is crucial for effective treatment and prevention of their spread. In recent years, convolutional neural networks (CNNs) have demonstrated outstanding performance in image classification and recognition tasks. Support vector machines (SVMs) are also widely used for classification tasks. In this study, we propose a skin disease diagnosis system that combines the strengths of CNNs and SVMs. Our approach involves training a CNN to extract features from skin lesion images, which are then used as input to the SVM classifier for classification. The CNN model is trained on a large dataset of skin lesion images, and the SVM model is trained on the extracted features from the CNN. The experimental results showed that our proposed method achieved higher accuracy, sensitivity, and specificity compared to other methods, demonstrating its effectiveness in skin disease diagnosis. In conclusion, our proposed skin disease diagnosis system based on CNN and SVM techniques provides a reliable and accurate tool for early and effective skin disease diagnosis, which could have significant implications for the management and treatment of these conditions.