Enhanced Interpupillary Distance Identification for Children Using YOLOv5 and YOLOX Object Detection Models

Interpupillary distance (IPD), which is the distance between the centers of the pupils of the eyes, is a key measurement in many applications, including optics, virtual reality, and medicine. Measuring IPD in adults is generally easier than measuring it in children due to adults' more stable eye positions and greater cooperation during the measurement process. Additionally, adults have a longer attention span, which aids in maintaining focus. Historically, technological options for accurately measuring IPD in children have been limited compared to those available for adults.In this work, we present a novel approach to accurately measure the IPD of children aged 5 to 15 years using an object detection model. Data were personally collected from students in this age group and subsequently pre-processed and annotated using labelImg software. The YoloV5 and YoloX models were employed for object detection, with YoloV5 demonstrating superior performance on the dataset. This model was utilized to locate the centers of the pupils and calculate the IPD using the Euclidean distance method between the centers of the bounding boxes for the detected pupils. The model accurately detected IPD while accounting for even the slightest variations in different eye movements and gazes, providing precise results. Additionally, a chin rest and a brief flash were incorporated as a gaze correction methodology to further enhance measurement accuracy. The precise measurement of IPD enables the customization of spectacles for children, ensuring better fit and comfort.