Smart Osteology: An AI-Powered Two-Stage System for Multi-Species Long Bone Detection and Classification Using YOLOv5 and CNN Architectures for Veterinary Anatomy Education and Forensic Applications

In this study, bone detection was performed using the YOLO algorithm on a dataset comprising photographs of the scapula, humerus, and femur from cattle, horses, and dogs. Subsequently, convolutional neural networks (CNNs) were employed to classify both the bone type and the species. Trained on a total of 26,148 images, the model achieved an accuracy rate of up to 97.6%. The system was designed to operate not only on mobile devices but also in an offline, "closed model" version, thereby enhancing its applicability in forensic medicine settings where data security is critical. Additionally, the application was structured as a virtual assistant capable of responding to users in both written and spoken formats and of generating output in PDF format. In this regard, this study presents a significant example of digital transformation in fields such as veterinary anatomy education, forensic medicine, archaeology, and crime scene investigation, providing a solid foundation for future applications.