Image Processing-Based Human Monkeypox Detection using Deep Learning Models

Cihan P

Published on: 2023-11-02

Abstract

Due to its rapid transmission across numerous nations, monkeypox has emerged as a notable public health issue. Although human monkeypox disease shares symptoms similar to measles and chickenpox, such as rash and fever, there are differences in details such as distinct types of skin lesions. Timely identification and diagnosis of monkeypox play a critical role in ensuring effective treatment and control of the disease. In this study, Convolutional Neural Network (CNN) based deep learning models, including VGG16, ResNet50, EfficientNetB3, Xception, and InceptionResNetV2, were used for the image-based classification of human monkeypox disease. The classification performance of the models was compared using metrics such as accuracy, precision, recall, and F1-score. The results showed that the InceptionResNetV2 model achieved 92% accuracy, demonstrating its success in classifying human monkeypox disease better than other models. This finding indicates the promising potential of the InceptionResNetV2 model in the accurate diagnosis of human monkeypox disease.