Iris Segmentation Based on Ellipse Detection for Gaze Tracking System

DOI

10.2991/msmee-17.2017.181How to use a DOI?

Keywords

Face Alignment, Iris Detection, Morphological Processing, Ellipse Detection.

Abstract

This paper propose a novel algorithm to detect the center and boundary of iris in face images of low resolution for gaze tracking system. The algorithm localizes the eye accurately by face alignments and uses convolution to detect the approximate pixel of the iris center which can determines the iris region. After thresholding and a series of morphological processing, the boundary and precise center of iris is detected via ellipse detection. The experiment shows good result on different kinds of people looking into different directions on Columbia Gaze Data Set.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yumeng Zhang
AU  - Cai Meng
PY  - 2017/05
DA  - 2017/05
TI  - Iris Segmentation Based on Ellipse Detection for Gaze Tracking System
BT  - Proceedings of the 2017 2nd International Conference on Materials Science, Machinery and Energy Engineering (MSMEE 2017)
PB  - Atlantis Press
SP  - 937
EP  - 941
SN  - 2352-5401
UR  - https://doi.org/10.2991/msmee-17.2017.181
DO  - 10.2991/msmee-17.2017.181
ID  - Zhang2017/05
ER  -