Pupil Center Detection Approaches: A comparative analysis

TL;DR

This paper compares four traditional pupil center detection methods using a large dataset, highlighting their accuracy, robustness, and speed to guide future eye-tracking technology improvements.

Contribution

It provides the first comprehensive comparison of four widely used pupil detection techniques on the same dataset and metrics.

Findings

Radial symmetry transform achieved over 94% accuracy and robustness.

Ellipse fitting was the fastest method at 0.06 seconds per image.

The study offers insights into the trade-offs between accuracy and computational efficiency.

Abstract

In the last decade, the development of technologies and tools for eye tracking has been a constantly growing area. Detecting the center of the pupil, using image processing techniques, has been an essential step in this process. A large number of techniques have been proposed for pupil center detection using both traditional image processing and machine learning-based methods. Despite the large number of methods proposed, no comparative work on their performance was found, using the same images and performance metrics. In this work, we aim at comparing four of the most frequently cited traditional methods for pupil center detection in terms of accuracy, robustness, and computational cost. These methods are based on the circular Hough transform, ellipse fitting, Daugman's integro-differential operator and radial symmetry transform. The comparative analysis was performed with 800 infrared images from the CASIA-IrisV3 and CASIA-IrisV4 databases containing various types of disturbances. The best performance was obtained by the method based on the radial symmetry transform with an accuracy and average robustness higher than 94%. The shortest processing time, obtained with the ellipse fitting method, was 0.06 s.