Detection of back acupoints based on improved OpenPose
Yarong Zhang, Biqing Zeng, Yaoqi Xian, Rui Yang · 2024
It is better to use physiotherapy to solve sub-health problems than to medicine. Identifying acupoints is an important part of the physiotherapy. Currently, identifying acupoints is highly dependent on doctors, which is time-consuming and labor-intensive. In recent years, with the development of artificial intelligence, deep learning has been gradually employed to realize automatic acupoint recognition, but most of the methods are still based on manual designed features. In this paper, we propose a back acupoints detection method based on improved OpenPose. Moreover, we build an acupoint detection dataset, and a total of three acupuncture points on the back were annotated. Experiments are performed and promising result is achieved.