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 language | English |
---|---|
Pages (from-to) | 933-944 |
Journal | Machine Vision and Applications |
Volume | 30 |
Issue number | 5 |
DOIs | |
Publication status | Published - 1 Jul 2018 |
Fingerprint
Keywords
- Discomfort/stress detection
- Face detection
- Facial expression recognition
- Infant discomfort
Cite this
}
Video-based discomfort detection for infants. / Sun, Yue; Shan, Caifeng (Corresponding author); Tan, Tao; Long, Xi; Pourtaherian, Arash; Zinger, Svitlana; de With, Peter H.N.
In: Machine Vision and Applications, Vol. 30, No. 5, 01.07.2018, p. 933-944.Research output: Contribution to journal › Article › Academic › peer-review
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 -