Real Time Face-to-Screen Distance Estimation on Smartphones Using Iris Diameter and the Pinhole Camera Model

Authors

  • Daniel Al-Burgan Warsaw University of Technology
  • Jerzy Weremczuk Warsaw University of Technology

Abstract

This paper presents a proof-of-concept architecture that investigates if a standard smartphone front camera can estimate face-to-screen distance in real time by using the average human iris diameter as a biological scale reference within a pinhole camera model. The proposed Android implementation uses automatic eye region localization, camera intrinsic calibration, grayscale preprocessing, and random sample consensus circle fitting to measure iris diameter in pixels. To support natural device use, a gaze rectification step compensates for perspective distortion when the user looks at the screen instead of directly into the camera. The method was evaluated in a pilot study with 48 recordings from one participant across eight distances from 200 to 550 millimeters, captured under both screen-directed and camera-directed gaze conditions. The system remained stable over the 250 to 500 millimeter range and produced comparable performance for screen and camera gaze. While accuracy degraded markedly at 550 millimeters. The main limitation was a systematic underestimation of roughly 20 to 35 millimeters, affected by the ground truth measurement setup and the static biological assumption of  iris diameter. The findings of this paper show that an on-device, real-time pipeline for iris based monocular distance estimation is computationally feasible for mobile applications.

Additional Files

Published

2026-07-17

Issue

Section

Metrology, Measurement Science