The rapid advancement of real-time medical technologies necessitates a focus on patient health, safety, and privacy. Reducing human intervention is essential due to age-related factors and the need for secure handling of sensitive information. This study explores the application of a Capsule Neural Network (Caps-Net) for real-time medical image recognition and analysis, a task traditionally enhanced by Convolutional Neural Networks (CNNs). Caps-Net is employed to identify and analyse injuries such as hand cuts, head and nose bleeding, and leg injuries from accidents. Utilizing a dataset of 12,000 images processed in Google Colab, the proposed model achieved a remarkable accuracy of 97%. These results highlight CapsNet's efficacy in medical imaging, offering significant benefits to healthcare professionals by improving diagnostic accuracy and expediting patient care. This research highlights the potential of advanced AI technologies in transforming medical image processing and enhancing clinical outcomes. © 2024 Elsevier B.V., All rights reserved.