Circle-based Eye Center Localization (CECL)

by   Yustinus Eko Soelistio, et al.

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 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.



There are no comments yet.


page 3


Hybrid eye center localization using cascaded regression and hand-crafted model fitting

We propose a new cascaded regressor for eye center detection. Previous m...

Center of circle after perspective transformation

Video-based glint-free eye tracking commonly estimates gaze direction ba...

Pupil Center Detection Approaches: A comparative analysis

In the last decade, the development of technologies and tools for eye tr...

EllSeg: An Ellipse Segmentation Framework for Robust Gaze Tracking

Ellipse fitting, an essential component in pupil or iris tracking based ...

No way to crop: On robust image crop localization

Previous image forensics schemes for crop detection are only limited on ...

Automated Steel Bar Counting and Center Localization with Convolutional Neural Networks

Automated steel bar counting and center localization plays an important ...

Robust Eye Centers Localization with Zero--Crossing Encoded Image Projections

This paper proposes a new framework for the eye centers localization by ...

Code Repositories


Eye center localization method based on Hough transformation. The method is free to use for scientific purposes. All publications and references to the method should be directed to ...

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.