Article
AI-Driven Monkeypox Recognition Using Enhanced VGG16 and Custom Convolutional Networks
Monkeypox is a contagious viral disease that primarily affects the skin and can spread rapidly if not identified at an early stage. Accurate and timely diagnosis is therefore essential to support effective treatment and prevent further transmission. This study proposes an AI-Driven Monkeypox Recognition Using Enhanced VGG16 and Custom Convolutional Networks for automatic classification of skin lesion images. The proposed system utilizes image preprocessing techniques such as resizing, normalization, and dataset partitioning to improve data quality before model training. An enhanced VGG16 model based on transfer learning is employed to extract high-level visual features, while a custom convolutional neural network is developed to learn disease-specific image patterns. The performance of both models is evaluated using standard metrics, including accuracy, precision, recall, F1-score, and confusion matrix analysis. Experimental results indicate that the custom CNN model achieves superior classification performance compared with the enhanced VGG16 model, providing reliable detection of Monkeypox and normal skin conditions. The developed prediction system enables users to upload skin lesion images and receive rapid diagnostic results, making it a practical decision-support tool for healthcare professionals. Overall, the proposed framework demonstrates the effectiveness of deep learning in improving automated Monkeypox recognition and supporting intelligent medical image analysis.
Full Text Attachment
