Circle-based Eye Center Localization (CECL)

TL;DR

The paper introduces CECL, a simple and robust eye center localization method based on the Hough transform, which achieves accuracy comparable to complex state-of-the-art techniques by utilizing color and shape cues.

Contribution

The paper presents a novel, efficient eye center localization method that outperforms many existing approaches in accuracy and simplicity using the Hough transform.

Findings

Achieved 80.8% to 99.4% accuracy across five error thresholds.

Ranked first for 2 out of 5 error thresholds in comparison.

Demonstrated robustness and simplicity of the CECL method.

Abstract

We propose an improved eye center localization method based on the Hough transform, called Circle-based Eye Center Localization (CECL) that is simple, robust, and achieves accuracy on a par with typically more complex state-of-the-art methods. The CECL method relies on color and shape cues that distinguish the iris from other facial structures. The accuracy of the CECL method is demonstrated through a comparison with 15 state-of-the-art eye center localization methods against five error thresholds, as reported in the literature. The CECL method achieved an accuracy of 80.8% to 99.4% and ranked first for 2 of the 5 thresholds. It is concluded that the CECL method offers an attractive alternative to existing methods for automatic eye center localization.