Robust glint detection through homography normalization

Dan Witzner Hansen; Lars  Roholm; Iván  	 García Ferreiros

doi:10.1145/2578153.2578165

Robust glint detection through homography normalization

Dan Witzner Hansen, Lars Roholm, Iván García Ferreiros

Computer Science

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

Abstract

A novel normalization principle for robust glint detection is presented. The method is based on geometric properties of corneal reflections and allows for simple and effective detection of glints even in the presence of several spurious and identically appearing reflections. The method is tested on both simulated and data obtained from web cameras. The proposed method is a possible direction towards making eye trackers more robust to challenging scenarios.

Original language	English
Title of host publication	ETRA '14 Proceedings of the Symposium on Eye Tracking Research and Applications
Number of pages	4
Publisher	Association for Computing Machinery
Publication date	1 May 2014
Pages	91-94
ISBN (Print)	978-1-4503-2751-0
DOIs	https://doi.org/10.1145/2578153.2578165
Publication status	Published - 1 May 2014

Keywords

Normalization principle
Robust glint detection
Corneal reflections
Eye tracking
Web camera data

Access to Document

10.1145/2578153.2578165

etra2014GlintNormalisationAccepted author manuscript, 639 KB

http://eye.itu.dk

Cite this

@inproceedings{976dc2b6b7a14b6ea2720ddd5f6fcf1a,

title = "Robust glint detection through homography normalization",

abstract = "A novel normalization principle for robust glint detection is presented. The method is based on geometric properties of corneal reflections and allows for simple and effective detection of glints even in the presence of several spurious and identically appearing reflections. The method is tested on both simulated and data obtained from web cameras. The proposed method is a possible direction towards making eye trackers more robust to challenging scenarios.",

keywords = "Normalization principle, Robust glint detection, Corneal reflections, Eye tracking, Web camera data",

author = "Hansen, {Dan Witzner} and Lars Roholm and {Garc{\'i}a Ferreiros}, Iv{\'a}n",

year = "2014",

month = may,

day = "1",

doi = "10.1145/2578153.2578165",

language = "English",

isbn = "978-1-4503-2751-0 ",

pages = "91--94",

booktitle = "ETRA '14 Proceedings of the Symposium on Eye Tracking Research and Applications",

publisher = "Association for Computing Machinery",

address = "United States",

}

Robust glint detection through homography normalization. / Hansen, Dan Witzner; Roholm, Lars ; García Ferreiros, Iván .
ETRA '14 Proceedings of the Symposium on Eye Tracking Research and Applications . Association for Computing Machinery, 2014. p. 91-94.

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

TY - GEN

T1 - Robust glint detection through homography normalization

AU - Hansen, Dan Witzner

AU - Roholm, Lars

AU - García Ferreiros, Iván

PY - 2014/5/1

Y1 - 2014/5/1

N2 - A novel normalization principle for robust glint detection is presented. The method is based on geometric properties of corneal reflections and allows for simple and effective detection of glints even in the presence of several spurious and identically appearing reflections. The method is tested on both simulated and data obtained from web cameras. The proposed method is a possible direction towards making eye trackers more robust to challenging scenarios.

AB - A novel normalization principle for robust glint detection is presented. The method is based on geometric properties of corneal reflections and allows for simple and effective detection of glints even in the presence of several spurious and identically appearing reflections. The method is tested on both simulated and data obtained from web cameras. The proposed method is a possible direction towards making eye trackers more robust to challenging scenarios.

KW - Normalization principle

KW - Robust glint detection

KW - Corneal reflections

KW - Eye tracking

KW - Web camera data

U2 - 10.1145/2578153.2578165

DO - 10.1145/2578153.2578165

M3 - Article in proceedings

SN - 978-1-4503-2751-0

SP - 91

EP - 94

BT - ETRA '14 Proceedings of the Symposium on Eye Tracking Research and Applications

PB - Association for Computing Machinery

ER -