Raspberry Pi-based mobile system of the pupil size evaluation

Abstract

The article considers development of a human pupil measuring system on the Raspberry platform. The system is aimed at evaluating the variations of the human pupil diameter or area in the process of watching test images or video recordings. To reduce the interference from the eye surface the camera uses a band-stop color glass filter PS 13. In order to increase the pupil image contrast, IR LED backlighting of the eye is implemented. To provide the mobility of the system, battery power of the single-board computer was used while the registered image and the measurement results were transmitted via a Wi-Fi channel. The video camera and the single-board computer Raspberry Pi 4 with the battery bay are attached to the head-mounted flexible belt. The article gives the operation duration evaluation of the battery-supplied system. During the first stage of image processing, binarization by the threshold was performed. The threshold is determined by the image brightness histogram. Since the study is focused on relative variations of the pupil size, the pupil diameter or area values in pixels were chosen as informative parameters. The image recording and processing frequency in the system equalled 25 Hz that provides accurate recording of the pupil variations.