Advancing Eye Analysis and Eye-Tracking with Ultralytics YOLO11 and EMME: Applications in Archaeology, Ophthalmology, Biometric Security, and Human-Computer Interaction

Eye-tracking and eye analysis technologies have emerged as transformative tools across diverse disciplines, including archaeology, healthcare, security, and human-computer interaction (HCI). This study presents an integrated approach combining Eye Movement Modelling Examples (EMME) and Ultralytics YOLO11 to enhance the understanding and practical application of visual attention. Conducted at Assist University, Seoul, EMME leverages recordings of expert gaze patterns to improve students’ comprehension of archaeological artefact analysis, demonstrating significant educational benefits. Simultaneously, YOLO11, a state-of-the-art deep learning model, achieves high-precision segmentation of iris and pupil features, enabling applications in automated eye disease detection, biometric identity verification, and gaze-based accessibility enhancements in HCI. By proposing a unified framework that synergizes these technologies, we aim to bridge educational advancements with practical innovations. Our findings indicate potential to enhance archaeological education at Assist University, improve diagnostic efficiency in ophthalmology, strengthen biometric security measures, and advance HCI systems, while acknowledging limitations that guide future research directions. This work underscores the value of AI-driven vision systems in addressing contemporary challenges across these fields.