Eye-state analysis using an interdependence and adaptive scale mean shift (IASMS) algorithm

Masrullizam Mat Ibrahim, John Soraghan, Lykourgos Petropoulakis

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Eye state analysis in real-time is a main input source for Fatigue Detection Systems and Human Computer Interaction applications. This paper presents a novel eye state analysis design aimed for human fatigue evaluation systems. The design is based on an interdependence and adaptive scale mean shift (IASMS) algorithm. IASMS uses moment features to track and estimate the iris area in order to quantify the state of the eye. The proposed system is shown to substantially improve non-rigid eye tracking performance, robustness and reliability. For evaluating the design performance an established eye blink database for blink frequency analysis was used. The design performance was further assessed using the newly formed Strathclyde Facial Fatigue (SFF) video footage database1 of controlled sleep-deprived volunteers.
Original languageEnglish
Pages (from-to)53-62
Number of pages10
JournalBiomedical Signal Processing and Control
Volume11
Early online date19 Mar 2014
DOIs
Publication statusPublished - May 2014

Fingerprint

Fatigue of materials
Fatigue
Human computer interaction
Computer Systems
Iris
Volunteers
Sleep
Databases

Keywords

  • mean shift algorithm
  • eye state analysis
  • fatigue assessment
  • eye tracking
  • adaptive scale
  • IASMS
  • algorithm
  • mean shift

Cite this

@article{9858cdf0f010475591395305227a6450,
title = "Eye-state analysis using an interdependence and adaptive scale mean shift (IASMS) algorithm",
abstract = "Eye state analysis in real-time is a main input source for Fatigue Detection Systems and Human Computer Interaction applications. This paper presents a novel eye state analysis design aimed for human fatigue evaluation systems. The design is based on an interdependence and adaptive scale mean shift (IASMS) algorithm. IASMS uses moment features to track and estimate the iris area in order to quantify the state of the eye. The proposed system is shown to substantially improve non-rigid eye tracking performance, robustness and reliability. For evaluating the design performance an established eye blink database for blink frequency analysis was used. The design performance was further assessed using the newly formed Strathclyde Facial Fatigue (SFF) video footage database1 of controlled sleep-deprived volunteers.",
keywords = "mean shift algorithm, eye state analysis , fatigue assessment, eye tracking, adaptive scale, IASMS , algorithm, mean shift",
author = "{Mat Ibrahim}, Masrullizam and John Soraghan and Lykourgos Petropoulakis",
year = "2014",
month = "5",
doi = "10.1016/j.bspc.2014.02.007",
language = "English",
volume = "11",
pages = "53--62",
journal = "Biomedical Signal Processing and Control",
issn = "1746-8094",

}

TY - JOUR

T1 - Eye-state analysis using an interdependence and adaptive scale mean shift (IASMS) algorithm

AU - Mat Ibrahim, Masrullizam

AU - Soraghan, John

AU - Petropoulakis, Lykourgos

PY - 2014/5

Y1 - 2014/5

N2 - Eye state analysis in real-time is a main input source for Fatigue Detection Systems and Human Computer Interaction applications. This paper presents a novel eye state analysis design aimed for human fatigue evaluation systems. The design is based on an interdependence and adaptive scale mean shift (IASMS) algorithm. IASMS uses moment features to track and estimate the iris area in order to quantify the state of the eye. The proposed system is shown to substantially improve non-rigid eye tracking performance, robustness and reliability. For evaluating the design performance an established eye blink database for blink frequency analysis was used. The design performance was further assessed using the newly formed Strathclyde Facial Fatigue (SFF) video footage database1 of controlled sleep-deprived volunteers.

AB - Eye state analysis in real-time is a main input source for Fatigue Detection Systems and Human Computer Interaction applications. This paper presents a novel eye state analysis design aimed for human fatigue evaluation systems. The design is based on an interdependence and adaptive scale mean shift (IASMS) algorithm. IASMS uses moment features to track and estimate the iris area in order to quantify the state of the eye. The proposed system is shown to substantially improve non-rigid eye tracking performance, robustness and reliability. For evaluating the design performance an established eye blink database for blink frequency analysis was used. The design performance was further assessed using the newly formed Strathclyde Facial Fatigue (SFF) video footage database1 of controlled sleep-deprived volunteers.

KW - mean shift algorithm

KW - eye state analysis

KW - fatigue assessment

KW - eye tracking

KW - adaptive scale

KW - IASMS

KW - algorithm

KW - mean shift

UR - http://www.sciencedirect.com/science/article/pii/S1746809414000202

UR - http://dx.doi.org/10.1016/j.bspc.2014.02.007

U2 - 10.1016/j.bspc.2014.02.007

DO - 10.1016/j.bspc.2014.02.007

M3 - Article

VL - 11

SP - 53

EP - 62

JO - Biomedical Signal Processing and Control

JF - Biomedical Signal Processing and Control

SN - 1746-8094

ER -