Circle-based Eye Center Localization (CECL)

Soelistio, Yustinus Eko and Postma, Eric and Maes, Alfons (2015) Circle-based Eye Center Localization (CECL). In: IAPR International Conference on Machine Vision Applications.

Text 3. Yustinus Eko - Circle-based Eye Center Localization (CECL).pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (787kB)

Abstract

The ability to automatically detect eye center locations in video images allows for estimating gaze direction. This, in turn, facilitates the study of human-computer interaction and behavioral analyses of social interactions. 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 at 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 circle enclosing the iris is localized by means of the Hough transform and the center of the iris is determined using the intensity level within the detected circle. 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.

Item Type:	Conference or Workshop Item (Paper)
Keywords:	Iris , Accuracy , Face , Hair , Histograms , Visualization , Glass
Subjects:	600 Technology (Applied Sciences) > 610 Medicine and Health > 610 Medicine and Health
Divisions:	Faculty of Engineering & Informatics > Information System
Depositing User:	Administrator UMN Library
Date Deposited:	27 Feb 2020 03:28
Last Modified:	21 Jun 2023 01:53
URI:	https://kc.umn.ac.id/id/eprint/12434

Actions (login required)

View Item