Hand acupuncture point localization method based on a dual-attention mechanism and cascade network model.

Abstract

Deep learning techniques have, to a certain extent, solved the problem of overreliance on clinical experience for traditional acupoint localization, but the accuracy and repetition rate of its localization still need to be improved. This paper proposes a hand acupoint localization method based on the dual-attention mechanism and cascade network model. First, by superimposing the dual-attention mechanism SE and CA in the YOLOv5 model and calculating the prior box size using K-means++ to optimize the hand location, we cascade the heatmap regression algorithm with HRNet as the backbone network to detect 21 predefined key points on the hand. Finally, "MF-cun" is combined to complete the acupoint localization. The FPS value is 35 and the average offset error value is 0.0269, which is much lower than the error threshold through dataset validation and real scene testing. The results show that this method can reduce the offset error value by more than 40% while ensuring real-time performance and can combat complex scenes such as unequal lighting, occlusion, and skin color interference.