Utilization of Facial Image Analysis Technology for Blink Detection

A Validation Study

Momoko Kitazawa, Michitaka Yoshimura, Kuo Ching Liang, Satoshi Wada, Masaru Mimura, Kazuo Tsubota, Taishiro Kishimoto

Research output: Contribution to journalArticle

Abstract

PURPOSE: The assessment of anterior eye diseases and the understanding of psychological functions of blinking can benefit greatly from a validated blinking detection technology. In this work, we proposed an algorithm based on facial recognition built on current video processing technologies to automatically filter and analyze blinking movements. We compared electrooculography (EOG), the gold standard of blinking measurement, with manual video tape recording counting (mVTRc) and our proposed automated video tape recording analysis (aVTRa) in both static and dynamic conditions to validate our aVTRa method.

METHODS: We measured blinking in both static condition, where the subject was sitting still with chin fixed on the table, and dynamic condition, where the subject's face was not fixed and natural communication was taking place between the subject and interviewer. We defined concordance of blinks between measurement methods as having less than 50 ms difference between eyes opening and closing.

RESULTS: The subjects consisted of seven healthy Japanese volunteers (3 male, four female) without significant eye disease with average age of 31.4±7.2. The concordance of EOG vs. aVTRa, EOG vs. mVTRc, and aVTRa vs. mVTRc (average±SD) were found to be 92.2±10.8%, 85.0±16.5%, and 99.6±1.0% in static conditions and 32.6±31.0%, 28.0±24.2%, and 98.5±2.7% in dynamic conditions, respectively.

CONCLUSIONS: In static conditions, we have found a high blink concordance rate between the proposed aVTRa versus EOG, and confirmed the validity of aVTRa in both static and dynamic conditions.

Original languageEnglish
Pages (from-to)S297-S301
JournalEye & contact lens
Volume44
DOIs
Publication statusPublished - 2018 Nov 1

Fingerprint

Videotape Recording
Validation Studies
Blinking
Technology
Electrooculography
Eye Diseases
Chin
Healthy Volunteers
Communication
Interviews
Psychology

ASJC Scopus subject areas

  • Ophthalmology

Cite this

Utilization of Facial Image Analysis Technology for Blink Detection : A Validation Study. / Kitazawa, Momoko; Yoshimura, Michitaka; Liang, Kuo Ching; Wada, Satoshi; Mimura, Masaru; Tsubota, Kazuo; Kishimoto, Taishiro.

In: Eye & contact lens, Vol. 44, 01.11.2018, p. S297-S301.

Research output: Contribution to journalArticle

Kitazawa, Momoko ; Yoshimura, Michitaka ; Liang, Kuo Ching ; Wada, Satoshi ; Mimura, Masaru ; Tsubota, Kazuo ; Kishimoto, Taishiro. / Utilization of Facial Image Analysis Technology for Blink Detection : A Validation Study. In: Eye & contact lens. 2018 ; Vol. 44. pp. S297-S301.
@article{7919c71af0104940bda5306b8616f947,
title = "Utilization of Facial Image Analysis Technology for Blink Detection: A Validation Study",
abstract = "PURPOSE: The assessment of anterior eye diseases and the understanding of psychological functions of blinking can benefit greatly from a validated blinking detection technology. In this work, we proposed an algorithm based on facial recognition built on current video processing technologies to automatically filter and analyze blinking movements. We compared electrooculography (EOG), the gold standard of blinking measurement, with manual video tape recording counting (mVTRc) and our proposed automated video tape recording analysis (aVTRa) in both static and dynamic conditions to validate our aVTRa method.METHODS: We measured blinking in both static condition, where the subject was sitting still with chin fixed on the table, and dynamic condition, where the subject's face was not fixed and natural communication was taking place between the subject and interviewer. We defined concordance of blinks between measurement methods as having less than 50 ms difference between eyes opening and closing.RESULTS: The subjects consisted of seven healthy Japanese volunteers (3 male, four female) without significant eye disease with average age of 31.4±7.2. The concordance of EOG vs. aVTRa, EOG vs. mVTRc, and aVTRa vs. mVTRc (average±SD) were found to be 92.2±10.8{\%}, 85.0±16.5{\%}, and 99.6±1.0{\%} in static conditions and 32.6±31.0{\%}, 28.0±24.2{\%}, and 98.5±2.7{\%} in dynamic conditions, respectively.CONCLUSIONS: In static conditions, we have found a high blink concordance rate between the proposed aVTRa versus EOG, and confirmed the validity of aVTRa in both static and dynamic conditions.",
author = "Momoko Kitazawa and Michitaka Yoshimura and Liang, {Kuo Ching} and Satoshi Wada and Masaru Mimura and Kazuo Tsubota and Taishiro Kishimoto",
year = "2018",
month = "11",
day = "1",
doi = "10.1097/ICL.0000000000000513",
language = "English",
volume = "44",
pages = "S297--S301",
journal = "Eye and Contact Lense",
issn = "1542-2321",
publisher = "Lippincott Williams and Wilkins",

}

TY - JOUR

T1 - Utilization of Facial Image Analysis Technology for Blink Detection

T2 - A Validation Study

AU - Kitazawa, Momoko

AU - Yoshimura, Michitaka

AU - Liang, Kuo Ching

AU - Wada, Satoshi

AU - Mimura, Masaru

AU - Tsubota, Kazuo

AU - Kishimoto, Taishiro

PY - 2018/11/1

Y1 - 2018/11/1

N2 - PURPOSE: The assessment of anterior eye diseases and the understanding of psychological functions of blinking can benefit greatly from a validated blinking detection technology. In this work, we proposed an algorithm based on facial recognition built on current video processing technologies to automatically filter and analyze blinking movements. We compared electrooculography (EOG), the gold standard of blinking measurement, with manual video tape recording counting (mVTRc) and our proposed automated video tape recording analysis (aVTRa) in both static and dynamic conditions to validate our aVTRa method.METHODS: We measured blinking in both static condition, where the subject was sitting still with chin fixed on the table, and dynamic condition, where the subject's face was not fixed and natural communication was taking place between the subject and interviewer. We defined concordance of blinks between measurement methods as having less than 50 ms difference between eyes opening and closing.RESULTS: The subjects consisted of seven healthy Japanese volunteers (3 male, four female) without significant eye disease with average age of 31.4±7.2. The concordance of EOG vs. aVTRa, EOG vs. mVTRc, and aVTRa vs. mVTRc (average±SD) were found to be 92.2±10.8%, 85.0±16.5%, and 99.6±1.0% in static conditions and 32.6±31.0%, 28.0±24.2%, and 98.5±2.7% in dynamic conditions, respectively.CONCLUSIONS: In static conditions, we have found a high blink concordance rate between the proposed aVTRa versus EOG, and confirmed the validity of aVTRa in both static and dynamic conditions.

AB - PURPOSE: The assessment of anterior eye diseases and the understanding of psychological functions of blinking can benefit greatly from a validated blinking detection technology. In this work, we proposed an algorithm based on facial recognition built on current video processing technologies to automatically filter and analyze blinking movements. We compared electrooculography (EOG), the gold standard of blinking measurement, with manual video tape recording counting (mVTRc) and our proposed automated video tape recording analysis (aVTRa) in both static and dynamic conditions to validate our aVTRa method.METHODS: We measured blinking in both static condition, where the subject was sitting still with chin fixed on the table, and dynamic condition, where the subject's face was not fixed and natural communication was taking place between the subject and interviewer. We defined concordance of blinks between measurement methods as having less than 50 ms difference between eyes opening and closing.RESULTS: The subjects consisted of seven healthy Japanese volunteers (3 male, four female) without significant eye disease with average age of 31.4±7.2. The concordance of EOG vs. aVTRa, EOG vs. mVTRc, and aVTRa vs. mVTRc (average±SD) were found to be 92.2±10.8%, 85.0±16.5%, and 99.6±1.0% in static conditions and 32.6±31.0%, 28.0±24.2%, and 98.5±2.7% in dynamic conditions, respectively.CONCLUSIONS: In static conditions, we have found a high blink concordance rate between the proposed aVTRa versus EOG, and confirmed the validity of aVTRa in both static and dynamic conditions.

UR - http://www.scopus.com/inward/record.url?scp=85055831831&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055831831&partnerID=8YFLogxK

U2 - 10.1097/ICL.0000000000000513

DO - 10.1097/ICL.0000000000000513

M3 - Article

VL - 44

SP - S297-S301

JO - Eye and Contact Lense

JF - Eye and Contact Lense

SN - 1542-2321

ER -