Image Processing-Based Application for Determining Wound Types in Forensic Medical Cases

Abstract

Wounds result from physical violence that damages the continuity of body tissues and are frequently observed in forensic medicine and medicolegal science. In forensic medicine and medicolegal science, wounds play a significant role in creating a medicolegal examination and report (VeR) for deceased individuals and living victims. However, research findings indicate that the quality of clinical forensic descriptive results in VeR needs to improve in several hospitals in Indonesia. Meanwhile, high-quality VeR results are crucial in determining penalties for perpetrators in court, and poor VeR results can hinder the legal process. The application of information technology in medicine has yielded numerous tools that can assist experts in carrying out their duties. Likewise, clinical forensics, a generally conservative forensic pathology practice, can be enhanced through image-processing techniques and machine learning. Digital technology support for forensic cases has been available previously, such as in forensic photography; however, its application still needs improvement, and further development is required. This study applied a Yolo V4-based machine learning and image processing algorithm to classify and detect types of wounds. This algorithm was chosen for its high speed and accuracy in classification and detection tasks. The research results showed that the learning model's performance, measured in accuracy, precision, recall, and average F1 score, reached 92%. Usability testing showed that the system performed well and could be helpful with minor improvements.