Literature DB >> 34190449

[Development and application of computer vision-based acupuncture manipulation classification system].

Tao Tu1, Ye-Hao Su1, Chong Su1, Lei Wang2, Ya-Nan Zhao2, Jie Chen3.   

Abstract

OBJECTIVE: To improve the accuracy of acupuncture manipulation modeling and inheritance, this article explores the feasibility of automatically classifying "twirling" and "lifting and thrusting", two basic acupuncture manipulations in science of acupuncture and moxibustion, with the computer vision technology.
METHODS: A hybrid deep learning network model was designed based on 3D convolutional neural network and long-short term memory neural network to extract the spatial-temporal features of video frame sequences, which were then input into the classifier for classification.
RESULTS: The model discriminated between "twirling" and "lifting and thrusting" manipulations in 200 videos, with the training and verification accuracy reaching up to 95.4% and 95.3%, respectively.
CONCLUSION: This computer vision-based acupuncture manipulation classification system provides an effective way for the data extraction and inheritance of acupuncture manipulations.

Keywords:  3D convolutional neural network; Acupuncture manipulations; Computer vision; Deep learning; Long-short term memory network

Mesh:

Year:  2021        PMID: 34190449     DOI: 10.13702/j.1000-0607.20210154

Source DB:  PubMed          Journal:  Zhen Ci Yan Jiu        ISSN: 1000-0607


  1 in total

Review 1.  Artificial intelligence-directed acupuncture: a review.

Authors:  Yulin Wang; Xiuming Shi; Thomas Efferth; Dong Shang
Journal:  Chin Med       Date:  2022-06-28       Impact factor: 4.546

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.