Evaluating Open‐Source Solutions for Computerized Inference of Infant Facial Affect
Developmental Science · 2026-03 · 29 (2)
DOI: 10.1111/desc.70156 ↗Kurz gefasst
Fachartikel in der Zeitschrift Developmental Science, online erschienen am 24.02.2026. Verfasst von Martin Lund Trinhammer und 6 weiteren Autor:innen. Beteiligte Einrichtung: Audio-Visual Computing, Section of Data Science, IT University of Copenhagen, Copenhagen S, Denmark. Hauptthemen laut MEDLINE: Facial Expression, Affect. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: DNRF, Danmarks Grundforskningsfond.
Abstract (Originalsprache)
Infant affect is often expressed through facial expressions, making this modality a key source of insight into the child's well‐being and social functioning. Computational inference of infant affect could critically assist both researchers and clinicians working with infant development and mitigate the need for manual coding. While many studies have explored open‐source solutions in the adult domain, only the commercial Baby FaceReader 9 exists for the infant domain. To address this gap, we utilize the recently proposed, open‐source infant‐native action unit (AU) detection library PyAFAR (Python‐based Automated Facial Action Recognition) on a sample of 71 four‐month‐old infants, whose facial expressions were manually annotated frame‐by‐frame for three minutes according to the Infant Facial Affect (IFA) coding scheme. Using these AUs as features, we classify facial affect into negative, neutral, and positive using XGBoost and Bayesian filtering, both in a multiclass and a binary setup. Our results show that AUs estimates from PyAFAR, combined with an XGBoost classification model, can distinguish positive from neutral and positive from negative affect with AUC scores of 0.78 and 0.76, respectively. This performance is essentially on par with that reported in evaluation studies of the Baby FaceReader 9, when accounting for differences in study setup. Our work indicates that the area of infant facial affect is particularly well‐suited to supervised learning, given the availability of two distinct, commensurable measurement schemes that underpin the same phenomenon. Finally, we discuss how future iterations of PyAFAR may benefit from including AUs that capture more variability around infant forehead and mouth opening.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Audio-Visual Computing, Section of Data Science, IT University of Copenhagen, Copenhagen S, Denmark.
- Pioneer Centre for Artificial Intelligence, Copenhagen K, Denmark.
- Centre of Excellence in Early Intervention and Family Studies (CIF), Department of Psychology, University of Copenhagen, Copenhagen K, Denmark.
- National Institute of Public Health, University of Southern Denmark, Copenhagen K, Denmark.
ORCID-Profile: Martin Lund Trinhammer, Marianne Thode Krogh, Anne Christine Stuart, Sami Sebastian Brandt
Förderung
- DNRF
- Danmarks Grundforskningsfond
Zitieren
APA
Trinhammer, M. L., Egmose, I., Krogh, M. T., Stuart, A. C., Væver, M. S., Brandt, S. S., & Graßhof, S. (2026). Evaluating Open‐Source Solutions for Computerized Inference of Infant Facial Affect. Developmental Science, 29(2). https://doi.org/10.1111/desc.70156
Vancouver
Trinhammer ML, Egmose I, Krogh MT, Stuart AC, Væver MS, Brandt SS, et al. Evaluating Open‐Source Solutions for Computerized Inference of Infant Facial Affect. Developmental Science. 2026;29(2). doi:10.1111/desc.70156
BibTeX
@article{Trinhammer2026,
author = {Trinhammer, Martin Lund and Egmose, Ida and Krogh, Marianne Thode and Stuart, Anne Christine and Væver, Mette Skovgaard and Brandt, Sami Sebastian and Graßhof, Stella},
title = {Evaluating Open‐Source Solutions for Computerized Inference of Infant Facial Affect},
journal = {Developmental Science},
year = {2026},
volume = {29},
number = {2},
doi = {10.1111/desc.70156}
}
EUVIMED