EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Non-Invasive Approach for Facial Action Unit Extraction and Its Application in Pain Detection

Mondher Bouazizi iD, Kevin Feghoul, Shengze Wang iD, Yue Yin iD, Tomoaki Ohtsuki iD

Bioengineering · 17.02.2025 · 12 (2) · 195

DOI: 10.3390/bioengineering12020195 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 17.02.2025. Verfasst von Mondher Bouazizi und 4 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Science and Technology, Keio University, Yokohama 223-8522, Japan. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Grants-in-Aid for Scientific Research (KAKENHI), Japan Science and Technology Agency (JST) ASPIRE.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A significant challenge that hinders advancements in medical research is the sensitive and confidential nature of patient data in available datasets. In particular, sharing patients’ facial images poses considerable privacy risks, especially with the rise of generative artificial intelligence (AI), which could misuse such data if accessed by unauthorized parties. However, facial expressions are a valuable source of information for doctors and researchers, which creates a need for methods to derive them without compromising patient privacy or safety by exposing identifiable facial images. To address this, we present a quick, computationally efficient method for detecting action units (AUs) and their intensities—key indicators of health and emotion—using only 3D facial landmarks. Our proposed framework extracts 3D face landmarks from video recordings and employs a lightweight neural network (NN) to identify AUs and estimate AU intensities based on these landmarks. Our proposed method reaches a 79.25% F1-score in AU detection for the main AUs, and 0.66 in AU intensity estimation Root Mean Square Error (RMSE). This performance shows that it is possible for researchers to share 3D landmarks, which are far less intrusive, instead of facial images while maintaining high accuracy in AU detection. Moreover, to showcase the usefulness of our AU detection model, using the detected AUs and estimated intensities, we trained state-of-the-art Deep Learning (DL) models to detect pain. Our method reaches 91.16% accuracy in pain detection, which is not far behind the 93.14% accuracy obtained when employing a convolutional neural network (CNN) with residual blocks trained on actual images and the 92.11% accuracy obtained when employing all the ground-truth AUs.

Schlagwörter

Stichwörter der Autor:innen

3D facial landmarksaction unitspain detectiontransformer

Autor:innen und Institutionen

  • Faculty of Science and Technology, Keio University, Yokohama 223-8522, Japan.
  • Graduate School of Science and Technology, Keio University, Yokohama 223-8522, Japan.

ORCID-Profile: Mondher Bouazizi, Shengze Wang, Yue Yin, Tomoaki Ohtsuki

Förderung

  • Grants-in-Aid for Scientific Research (KAKENHI)
  • Japan Science and Technology Agency (JST) ASPIRE

Zitieren

APA

Bouazizi, M., Feghoul, K., Wang, S., Yin, Y., & Ohtsuki, T. (2025). A Non-Invasive Approach for Facial Action Unit Extraction and Its Application in Pain Detection. Bioengineering, 12(2), 195. https://doi.org/10.3390/bioengineering12020195

Vancouver

Bouazizi M, Feghoul K, Wang S, Yin Y, Ohtsuki T. A Non-Invasive Approach for Facial Action Unit Extraction and Its Application in Pain Detection. Bioengineering. 2025;12(2):195. doi:10.3390/bioengineering12020195

BibTeX
@article{Bouazizi2025,
  author = {Bouazizi, Mondher and Feghoul, Kevin and Wang, Shengze and Yin, Yue and Ohtsuki, Tomoaki},
  title = {A Non-Invasive Approach for Facial Action Unit Extraction and Its Application in Pain Detection},
  journal = {Bioengineering},
  year = {2025},
  volume = {12},
  number = {2},
  pages = {195},
  doi = {10.3390/bioengineering12020195}
}
Kostenlos starten →