Skin disease identification is a major topic of research in the fields of medical imaging and computer vision, which have grown tremendously in recent years. A computer vision system was created in this work to determine if a skin lesion is indicative of monkeypox or not. A skin illness dataset, which was divided into training and validation sets, was used to train the system. It contained pictures of skin lesions. The need for a dependable and effective approach to identify skin conditions, particularly monkeypox, to enhance patient benefits and public health is the issue this study attempts to solve. Convolutional neural networks (CNNs) and SVM were offered a job in this study's analysis and research techniques for picture classification. The model was implemented using the TensorFlow and Keras libraries in Python. According to the study's findings, the model was capable of categorizing skin lesions as either indicative of monkeypox or not with an accuracy rate of more than 80%. This indicates the viability of applying deep learning and computer vision methods to the detection of skin conditions and underlines the promise of additional study in this area. The contribution of these results is that they establish automated skin disease detection systems, which have the potential to significantly increase the precision and efficiency of medical diagnoses, particularly in resource-constrained areas with restricted access to healthcare. Additionally, these results point to the possibility of further system performance enhancement and the creation of models for identifying other skin conditions in future research.

Python, CNN, VGG16, SVM, Skin disease detection, Machine Learning