Circle-based Eye Center Localization (CECL)
This provides a simpler, robust alternative for automatic eye center localization in computer vision applications, though it appears incremental.
The paper tackles eye center localization by proposing Circle-based Eye Center Localization (CECL), an improved Hough transform method that uses color and shape cues, achieving accuracy from 80.8% to 99.4% and ranking first for 2 out of 5 error thresholds compared to 15 state-of-the-art methods.
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.