Video-based discomfort detection for infants

Research output: Contribution to journalArticleAcademicpeer-review

2 Citations (Scopus)
7 Downloads (Pure)

Abstract

Infants are particularly vulnerable to the effects of pain and discomfort, which can lead to abnormal brain development, yielding long-term adverse neurodevelopmental outcomes. In this study, we propose a video-based method for automated detection of their discomfort. The infant face is first detected and normalized. A two-phase classification workflow is then employed, where Phase 1 is subject-independent, and Phase 2 is subject-dependent. Phase 1 derives geometric and appearance features, while Phase 2 incorporates facial landmark-based template matching. An SVM classifier is finally applied to video frames to recognize facial expressions of comfort or discomfort. The method is evaluated using videos from 22 infants. Experimental results show an AUC of 0.87 for the subject-independent phase and 0.97 for the subject-dependent phase, which is promising for clinical use.

Original languageEnglish
Pages (from-to)933-944
JournalMachine Vision and Applications
Volume30
Issue number5
DOIs
Publication statusPublished - 1 Jul 2018

Fingerprint

Template matching
Brain
Classifiers

Keywords

  • Discomfort/stress detection
  • Face detection
  • Facial expression recognition
  • Infant discomfort

Cite this

@article{bf9e6406d82c4fc2ad888d496767e551,
title = "Video-based discomfort detection for infants",
abstract = "Infants are particularly vulnerable to the effects of pain and discomfort, which can lead to abnormal brain development, yielding long-term adverse neurodevelopmental outcomes. In this study, we propose a video-based method for automated detection of their discomfort. The infant face is first detected and normalized. A two-phase classification workflow is then employed, where Phase 1 is subject-independent, and Phase 2 is subject-dependent. Phase 1 derives geometric and appearance features, while Phase 2 incorporates facial landmark-based template matching. An SVM classifier is finally applied to video frames to recognize facial expressions of comfort or discomfort. The method is evaluated using videos from 22 infants. Experimental results show an AUC of 0.87 for the subject-independent phase and 0.97 for the subject-dependent phase, which is promising for clinical use.",
keywords = "Discomfort/stress detection, Face detection, Facial expression recognition, Infant discomfort",
author = "Yue Sun and Caifeng Shan and Tao Tan and Xi Long and Arash Pourtaherian and Svitlana Zinger and {de With}, {Peter H.N.}",
year = "2018",
month = "7",
day = "1",
doi = "10.1007/s00138-018-0968-1",
language = "English",
volume = "30",
pages = "933--944",
journal = "Machine Vision and Applications",
issn = "0932-8092",
publisher = "Springer",
number = "5",

}

TY - JOUR

T1 - Video-based discomfort detection for infants

AU - Sun, Yue

AU - Shan, Caifeng

AU - Tan, Tao

AU - Long, Xi

AU - Pourtaherian, Arash

AU - Zinger, Svitlana

AU - de With, Peter H.N.

PY - 2018/7/1

Y1 - 2018/7/1

N2 - Infants are particularly vulnerable to the effects of pain and discomfort, which can lead to abnormal brain development, yielding long-term adverse neurodevelopmental outcomes. In this study, we propose a video-based method for automated detection of their discomfort. The infant face is first detected and normalized. A two-phase classification workflow is then employed, where Phase 1 is subject-independent, and Phase 2 is subject-dependent. Phase 1 derives geometric and appearance features, while Phase 2 incorporates facial landmark-based template matching. An SVM classifier is finally applied to video frames to recognize facial expressions of comfort or discomfort. The method is evaluated using videos from 22 infants. Experimental results show an AUC of 0.87 for the subject-independent phase and 0.97 for the subject-dependent phase, which is promising for clinical use.

AB - Infants are particularly vulnerable to the effects of pain and discomfort, which can lead to abnormal brain development, yielding long-term adverse neurodevelopmental outcomes. In this study, we propose a video-based method for automated detection of their discomfort. The infant face is first detected and normalized. A two-phase classification workflow is then employed, where Phase 1 is subject-independent, and Phase 2 is subject-dependent. Phase 1 derives geometric and appearance features, while Phase 2 incorporates facial landmark-based template matching. An SVM classifier is finally applied to video frames to recognize facial expressions of comfort or discomfort. The method is evaluated using videos from 22 infants. Experimental results show an AUC of 0.87 for the subject-independent phase and 0.97 for the subject-dependent phase, which is promising for clinical use.

KW - Discomfort/stress detection

KW - Face detection

KW - Facial expression recognition

KW - Infant discomfort

UR - http://www.scopus.com/inward/record.url?scp=85051659784&partnerID=8YFLogxK

U2 - 10.1007/s00138-018-0968-1

DO - 10.1007/s00138-018-0968-1

M3 - Article

AN - SCOPUS:85051659784

VL - 30

SP - 933

EP - 944

JO - Machine Vision and Applications

JF - Machine Vision and Applications

SN - 0932-8092

IS - 5

ER -