Hand acupuncture point automatic positioning method based on fuzzy inference system

Through the automatic positioning method of hand acupuncture points based on fuzzy inference system, the problems of high annotation costs and high computing resource requirements in the existing technology are solved, efficient and accurate acupuncture points are achieved, and category scalability and confidence output are provided. Adapt to the fuzzy characteristics of Chinese medicine acupoints.

CN119007239AActive Publication Date: 2024-11-22泉州医学高等专科学校

Patent Information

Application Number
CN202410973154.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-19
Publication Date
2024-11-22
Estimated Expiration
2044-07-19

AI Technical Summary

Technical Problem

The prior art has problems in the positioning of hand acupuncture points with high labeling costs, high computing resource requirements, no consideration of the fuzzy characteristics and empirical nature of traditional Chinese medicine acupuncture points, and the empirical formula method cannot output confidence.

Method used

Using the automatic positioning method of hand acupuncture points based on the fuzzy inference system, the hand punctuation points are extracted through Mediapipe and MobileSAM networks, a local coordinate system is established, and the potential acupuncture points are generated using deep learning algorithms, and the membership function and the Fuzzy reasoning table, calculate the confidence of acupuncture points for positioning.

Benefits of technology

It reduces the labeling cost, improves the accuracy and efficiency of acupuncture points positioning, has category scalability, can output the predicted value and confidence of acupuncture points, and adapts to the fuzzy characteristics of Chinese medicine acupuncture points.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119007239A_ABST
    Figure CN119007239A_ABST
Patent Text Reader

Abstract

The invention discloses an automatic hand acupuncture point positioning method based on a fuzzy inference system, which comprises the following specific steps: acquiring image data of a hand, acquiring 21 hand navigation mark points from a sample picture through a Medipe hand key point extraction network, and then acquiring a mask of a hand area; creating a local coordinate system for each hand navigation mark point; generating a special area of each hand navigation mark point by using a deep learning algorithm, and generating potential acupuncture point sampling points; the potential acupuncture points are converted into scale coordinates to serve as input of follow-up processing; and calculating the confidence coefficient of the potential acupuncture point sampling points belonging to a certain type of acupuncture points, and determining the final acupuncture point by selecting the highest confidence coefficient, thereby completing the automatic positioning of the hand vacancy. The method not only improves the accuracy and efficiency of hand acupuncture point positioning, but also has the advantages of high category expandability, confidence output and the like.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Hand acupuncture point automatic positioning method

    CN113486758A

  • Accurate acupoint positioning method based on cascaded deep neural network

    CN116434277A

  • Hand acupuncture point recognition method based on lightweight deep learning network

    CN115634147A

  • Acupuncture point identification method based on ultrasonic imaging

    CN118248293A

Cited By

  • Traditional Chinese medicine acupoint auxiliary diagnosis and treatment system integrating deep learning and applet

    CN119601175A