Statistical models of appearance for eye tracking and eye-blink detection and measurement

Ioana Bacivarov; Mircea Ionita; Peter Corcoran

doi:10.1109/TCE.2008.4637622

Statistical models of appearance for eye tracking and eye-blink detection and measurement

Ioana Bacivarov, Mircea Ionita, Peter Corcoran

Electrical & Electronic Engineering

University of Galway

Research output: Contribution to a Journal (Peer & Non Peer) › Article › peer-review

103 Citations (Scopus)

Abstract

A statistical Active Appearance Model (AAM) developed to track and detect eye blinking. The model has been designed to be robust to variations of head pose or gaze. particular we analyze and determine the model parameters which encode the variations caused by blinking. This global model is further extended using a series of sub-models enable independent modeling and tracking of the two eye regions. Several methods to enable measurement and detection of eye-blink are proposed and evaluated. The results various tests on different image databases are presented validate each model.

Original language	English
Pages (from-to)	1312-1328
Number of pages	17
Journal	IEEE Transactions on Consumer Electronics
Volume	54
Issue number	3
DOIs	https://doi.org/10.1109/TCE.2008.4637622
Publication status	Published - 2008

Keywords

Active appearance model
Digital imaging
Eye blinking
Eye tracking

Access to Document

10.1109/TCE.2008.4637622

Cite this

@article{701c45aac2164b40a25c00dccbbaed27,

title = "Statistical models of appearance for eye tracking and eye-blink detection and measurement",

abstract = "A statistical Active Appearance Model (AAM) developed to track and detect eye blinking. The model has been designed to be robust to variations of head pose or gaze. particular we analyze and determine the model parameters which encode the variations caused by blinking. This global model is further extended using a series of sub-models enable independent modeling and tracking of the two eye regions. Several methods to enable measurement and detection of eye-blink are proposed and evaluated. The results various tests on different image databases are presented validate each model.",

keywords = "Active appearance model, Digital imaging, Eye blinking, Eye tracking",

author = "Ioana Bacivarov and Mircea Ionita and Peter Corcoran",

year = "2008",

doi = "10.1109/TCE.2008.4637622",

language = "English",

volume = "54",

pages = "1312--1328",

journal = "IEEE Transactions on Consumer Electronics",

issn = "0098-3063",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "3",

}

TY - JOUR

T1 - Statistical models of appearance for eye tracking and eye-blink detection and measurement

AU - Bacivarov, Ioana

AU - Ionita, Mircea

AU - Corcoran, Peter

PY - 2008

Y1 - 2008

N2 - A statistical Active Appearance Model (AAM) developed to track and detect eye blinking. The model has been designed to be robust to variations of head pose or gaze. particular we analyze and determine the model parameters which encode the variations caused by blinking. This global model is further extended using a series of sub-models enable independent modeling and tracking of the two eye regions. Several methods to enable measurement and detection of eye-blink are proposed and evaluated. The results various tests on different image databases are presented validate each model.

AB - A statistical Active Appearance Model (AAM) developed to track and detect eye blinking. The model has been designed to be robust to variations of head pose or gaze. particular we analyze and determine the model parameters which encode the variations caused by blinking. This global model is further extended using a series of sub-models enable independent modeling and tracking of the two eye regions. Several methods to enable measurement and detection of eye-blink are proposed and evaluated. The results various tests on different image databases are presented validate each model.

KW - Active appearance model

KW - Digital imaging

KW - Eye blinking

KW - Eye tracking

UR - https://www.scopus.com/pages/publications/54349113392

U2 - 10.1109/TCE.2008.4637622

DO - 10.1109/TCE.2008.4637622

M3 - Article

SN - 0098-3063

VL - 54

SP - 1312

EP - 1328

JO - IEEE Transactions on Consumer Electronics

JF - IEEE Transactions on Consumer Electronics

IS - 3

ER -

Statistical models of appearance for eye tracking and eye-blink detection and measurement

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this