Robustifying eye interaction

Dan Witzner Hansen; John Paulin Hansen

doi:10.1109/CVPRW.2006.181

Robustifying eye interaction

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

Abstract

This paper presents a gaze typing system based on consumer hardware. Eye tracking based on consumer hardware is subject to several unknown factors. We propose methods using robust statistical principles to accommodate uncertainties in image data as well as in gaze estimates to improve accuracy. We have succeeded to track the gaze of people with a standard consumer camera, obtaining accuracies about 160 pixels on screen. Proper design of the typing interface, however, reduces the need for high accuracy. We have observed typing speeds in the range of 3 - 5 words per minute for untrained subjects using large on-screen buttons and a new noise tolerant dwell-time principle

Translated title of the contribution	Robustifying eye interaction
Original language	English
Title of host publication	Robustifying eye interaction
Publication date	2006
ISBN (Print)	0769526462
DOIs	https://doi.org/10.1109/CVPRW.2006.181
Publication status	Published - 2006

Keywords

appearence
gaze tracking
particle
Folder - Computer
cascade
boost classifier
iris detection
particle filtering
eyes tracking

Access to Document

10.1109/CVPRW.2006.181

Cite this

@inbook{073bcd3357f4423792d7cd5d241d3d93,

title = "Robustifying eye interaction",

abstract = " This paper presents a gaze typing system based on consumer hardware. Eye tracking based on consumer hardware is subject to several unknown factors. We propose methods using robust statistical principles to accommodate uncertainties in image data as well as in gaze estimates to improve accuracy. We have succeeded to track the gaze of people with a standard consumer camera, obtaining accuracies about 160 pixels on screen. Proper design of the typing interface, however, reduces the need for high accuracy. We have observed typing speeds in the range of 3 - 5 words per minute for untrained subjects using large on-screen buttons and a new noise tolerant dwell-time principle",

keywords = "appearence, gaze tracking, particle, Folder - Computer, cascade, boost classifier, iris detection, particle filtering, eyes tracking, appearence, gaze tracking, particle, Folder - Computer, cascade, boost classifier, iris detection, particle filtering, eyes tracking",

author = "Hansen, {Dan Witzner} and Hansen, {John Paulin}",

year = "2006",

doi = "10.1109/CVPRW.2006.181",

language = "English",

isbn = "0769526462",

booktitle = "Robustifying eye interaction",

}

TY - CHAP

T1 - Robustifying eye interaction

AU - Hansen, Dan Witzner

AU - Hansen, John Paulin

PY - 2006

Y1 - 2006

N2 - This paper presents a gaze typing system based on consumer hardware. Eye tracking based on consumer hardware is subject to several unknown factors. We propose methods using robust statistical principles to accommodate uncertainties in image data as well as in gaze estimates to improve accuracy. We have succeeded to track the gaze of people with a standard consumer camera, obtaining accuracies about 160 pixels on screen. Proper design of the typing interface, however, reduces the need for high accuracy. We have observed typing speeds in the range of 3 - 5 words per minute for untrained subjects using large on-screen buttons and a new noise tolerant dwell-time principle

AB - This paper presents a gaze typing system based on consumer hardware. Eye tracking based on consumer hardware is subject to several unknown factors. We propose methods using robust statistical principles to accommodate uncertainties in image data as well as in gaze estimates to improve accuracy. We have succeeded to track the gaze of people with a standard consumer camera, obtaining accuracies about 160 pixels on screen. Proper design of the typing interface, however, reduces the need for high accuracy. We have observed typing speeds in the range of 3 - 5 words per minute for untrained subjects using large on-screen buttons and a new noise tolerant dwell-time principle

KW - appearence

KW - gaze tracking

KW - particle

KW - Folder - Computer

KW - cascade

KW - boost classifier

KW - iris detection

KW - particle filtering

KW - eyes tracking

KW - appearence

KW - gaze tracking

KW - particle

KW - Folder - Computer

KW - cascade

KW - boost classifier

KW - iris detection

KW - particle filtering

KW - eyes tracking

U2 - 10.1109/CVPRW.2006.181

DO - 10.1109/CVPRW.2006.181

M3 - Book chapter

SN - 0769526462

BT - Robustifying eye interaction

ER -