Litcius/Paper detail

YOLOv8-ACU: improved YOLOv8-pose for facial acupoint detection

Zijian Yuan, Pengwei Shao, Jinran Li, Yinuo Wang, Zixuan Zhu, Weijie Qiu, B. Chen, Yan Tang, Aiqing Han

2024Frontiers in Neurorobotics40 citationsDOIOpen Access PDF

Abstract

Introduction: Acupoint localization is integral to Traditional Chinese Medicine (TCM) acupuncture diagnosis and treatment. Employing intelligent detection models for recognizing facial acupoints can substantially enhance localization accuracy. Methods: This study introduces an advancement in the YOLOv8-pose keypoint detection algorithm, tailored for facial acupoints, and named YOLOv8-ACU. This model enhances acupoint feature extraction by integrating ECA attention, replaces the original neck module with a lighter Slim-neck module, and improves the loss function for GIoU. Results: The YOLOv8-ACU model achieves impressive accuracy, with an [email protected] of 97.5% and an [email protected] of 76.9% on our self-constructed datasets. It also marks a reduction in model parameters by 0.44M, model size by 0.82 MB, and GFLOPs by 9.3%. Discussion: With its enhanced recognition accuracy and efficiency, along with good generalization ability, YOLOv8-ACU provides significant reference value for facial acupoint localization and detection. This is particularly beneficial for Chinese medicine practitioners engaged in facial acupoint research and intelligent detection.

Topics & Concepts

Computer scienceArtificial intelligencePattern recognition (psychology)GeneralizationFeature extractionFeature (linguistics)Computer visionMathematicsPhilosophyMathematical analysisLinguisticsTraditional Chinese Medicine StudiesAcupuncture Treatment Research StudiesFace recognition and analysis