EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Two-Stage Cascaded Regression Framework for Automatic Facial Acupoint Localization in Infrared Thermal Images

Jiahao Li iD, Xingcheng Ming, Ying Zeng, Ruifeng Yang, Jin Tian, Fu Niu

Sensors · 15.07.2026 · 26 (14) · 4498

DOI: 10.3390/s26144498 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 15.07.2026. Verfasst von Jiahao Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: Systems Engineering Institute, Academy of Military Sciences, PLA, Beijing 100091, China. Hauptthemen laut MEDLINE: Acupuncture Points, Face, Image Processing, Computer-Assisted, Thermography. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Infrared thermal imaging offers objective physiological insights for Traditional Chinese Medicine (TCM), yet automated acupoint localization struggles with low texture and extreme pose variations. To address this, we constructed a multi-pose thermal facial dataset using digitized bone-proportional measurements and TCM anatomical rules. We propose T2FAL, a two-stage cascaded regression framework explicitly decoupling macroscopic face detection from fine-grained acupoint localization. Stage 1 utilizes an improved YOLOv12m-based Thermal-Aware Face Detector—integrating ICAN_C2f, MixNeck, and TAF-IoU—to mitigate domain shifts and thermal noise. Stage 2 deploys pose-specific regressors incorporating Gated Feature-Conditioned Cascade Refinement (FCCR) and a Selective GeoDeriv module, mathematically translating anatomical rules into geometric constraints. Under the stated experimental protocol, Stage 1 processed images at 87.3 frames per second on an NVIDIA RTX 4090. For Stage 2, the final frontal- and profile-view configurations achieved mAP@50–95 values of 73.19% and 86.92%, with mean pixel errors of 1.986 and 3.109 pixels, respectively. These results support the feasibility of automated reference-coordinate localization on the datasets used. However, given the partial reliance of the annotations on image registration and geometric rules, the use of the cross-domain set for model selection, and the lack of clinical or diagnostic evaluation, further validation using independently generated expert annotations, a strictly held-out external test set, and clinically labeled data is required before clinical or diagnostic use.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Acupuncture PointsFaceImage Processing, Computer-AssistedThermographyInfrared RaysHumansMedicine, Chinese TraditionalAlgorithms

Stichwörter der Autor:innen

Traditional Chinese Medicineacupoint localizationgeometric constraintsinfrared thermal imagekeypoints detectionobject detection

Autor:innen und Institutionen

  • Systems Engineering Institute, Academy of Military Sciences, PLA, Beijing 100091, China.

ORCID-Profile: Jiahao Li

Zitieren

APA

Li, J., Ming, X., Zeng, Y., Yang, R., Tian, J., & Niu, F. (2026). A Two-Stage Cascaded Regression Framework for Automatic Facial Acupoint Localization in Infrared Thermal Images. Sensors, 26(14), 4498. https://doi.org/10.3390/s26144498

Vancouver

Li J, Ming X, Zeng Y, Yang R, Tian J, Niu F. A Two-Stage Cascaded Regression Framework for Automatic Facial Acupoint Localization in Infrared Thermal Images. Sensors. 2026;26(14):4498. doi:10.3390/s26144498

BibTeX
@article{Li2026,
  author = {Li, Jiahao and Ming, Xingcheng and Zeng, Ying and Yang, Ruifeng and Tian, Jin and Niu, Fu},
  title = {A Two-Stage Cascaded Regression Framework for Automatic Facial Acupoint Localization in Infrared Thermal Images},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {14},
  pages = {4498},
  doi = {10.3390/s26144498}
}
Kostenlos starten →