APCA-Net: Adaptive Patch-Correlation Attention Network for Vision-Based Human Hand Acupoint Detection in Acupuncture
- 19 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Human-Machine Systems
- Vol. 56 (3) , 542-551
Abstract
Acupuncture plays an important role in the treatment of diseases, prevention, and health care. However, it is difficult to detect acupoints from the hand surface due to the complicated tasks: first, the acupoint regions are similar to the surrounding areas on the hand surface; second, the skin tone on the hand varies in depth. To address these challenges, an adaptive patch-correlation attention network (APCA-Net) is proposed for vision-based human hand acupoint detection in acupuncture, where the adaptive patch aware attention module is designed to distinguish acupoint from the surrounding skin tissue by capturing fine-grained features from small patches, while the adaptive correlation channel attention module is devised to detect acupoints of different skin tones by modeling channel correlation. Experiments on benchmarks show that the proposed APCA-Net can achieve the acupoint detection rate of 76.11% and 88.32% on the 11 K Hands Subset and Depth Hand datasets, respectively, outperforming other state-of-the-art approaches.Keywords
Funding Information
- National Key R&D Program of China (2022YFB4703100)
- National Natural Science Foundation of China (62403145)
- National Natural Science Foundation of China (62273105)
- National Natural Science Foundation of China (U1911401)
- National Natural Science Foundation of China (62203121)
- Guangdong Province Foundation (2019B1515120036)
- Guangdong Province Foundation (501200069)
This publication has 61 references indexed in Scilit:
- Exploration of electrosensitization of Sifeng (EX-UE10) in children with constipation (syndrome of excessive heat in intestine) based on meridian detectionJournal of Acupuncture and Tuina Science, 2025
- FM-OSD: Foundation Model-Enabled One-Shot Detection of Anatomical Landmarks2024
- AIR-Net: Acupoint image registration network for automatic acupoint recognition and localizationDisplays, 2024
- A review of traditional Chinese medicine diagnosis using machine learning: Inspection, auscultation-olfaction, inquiry, and palpationComputers in Biology and Medicine, 2024
- Perforating cutaneous vessels: A key feature of acupoints – Anatomical evidence from five‐Shu acupoints in the upper limbsClinical Anatomy, 2023
- 3D Localization of Hand Acupoints Using Hand Geometry and Landmark Points Based on RGB-D CNN FusionAnnals of Biomedical Engineering, 2022
- Microscopy of structures surrounding typical acupoints used in clinical practice and electron microscopic evaluation of acupuncture needlesClinical Anatomy, 2022
- EfficientHRNetJournal of Real-Time Image Processing, 2021
- Accuracy and Precision in Acupuncture Point Location: A Critical Systematic ReviewJournal of Acupuncture and Meridian Studies, 2019
- 11K Hands: Gender recognition and biometric identification using a large dataset of hand imagesMultimedia Tools and Applications, 2019