Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

An Unsupervised Image Enhancement Framework for Multiple Fault Detection of Insulators.

Sensors (Basel, Switzerland)·2025
Same author

Power Line Segmentation Algorithm Based on Lightweight Network and Residue-like Cross-Layer Feature Fusion.

Sensors (Basel, Switzerland)·2025
Same author

Association between genetic polymorphisms and gestational diabetes mellitus susceptibility in a Chinese population.

Frontiers in endocrinology·2024
Same author

T2 mapping for quantitative assessment of ankle cartilage of weightlifters.

Scientific reports·2023
Same author

Association of miR-196a2 and miR-27a polymorphisms with gestational diabetes mellitus susceptibility in a Chinese population.

Frontiers in endocrinology·2023
Same author

A Lightweight Algorithm for Insulator Target Detection and Defect Identification.

Sensors (Basel, Switzerland)·2023

Related Experiment Video

Updated: Jan 17, 2026

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

1.2K

sEMG-Based Gesture Recognition Using Sigimg-GADF-MTF and Multi-Stream Convolutional Neural Network.

Ming Zhang1,2, Leyi Qu1,2, Weibiao Wu1,2

  • 1School of Electronic & Electrical Engineering, Wuhan Textile University, Wuhan 430200, China.

Sensors (Basel, Switzerland)
|September 19, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a novel algorithm for surface electromyography (sEMG) based gesture recognition, achieving high accuracy by processing sEMG signals into images and using a multi-stream convolutional neural network.

Keywords:
Gramian angular difference field (GADF)Markov transition field (MTF)gesture recognitionmulti-stream convolutional neural network (MSCNN)sEMG signal

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.3K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K

Related Experiment Videos

Last Updated: Jan 17, 2026

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

1.2K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.3K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K

Area of Science:

  • Biomedical Engineering
  • Machine Learning
  • Signal Processing

Background:

  • Surface electromyography (sEMG) signals contain rich temporal, static, and dynamic information crucial for gesture recognition.
  • Existing methods often struggle to fully leverage these complex signal features, limiting recognition accuracy.
  • The temporal characteristics of sEMG, sensitive to action amplitude and muscle recruitment, necessitate advanced processing techniques.

Purpose of the Study:

  • To develop an innovative sEMG-based gesture recognition algorithm that comprehensively utilizes temporal, static, and dynamic signal features.
  • To introduce novel data processing methods (Sigimg, Gram Angular Difference Field (GADF), Markov Transition Field (MTF)) for sEMG signal transformation.
  • To combine these methods with a multi-stream convolutional neural network (MSCNN) and a multi-stream fusion strategy for enhanced recognition.

Main Methods:

  • Rearranging multi-channel sEMG signals into a 2D image (Sigimg) using a sliding window.
  • Transforming individual sEMG channels into 2D sub-images via GADF and MTF methods.
  • Stitching GADF and MTF sub-images horizontally, constructing a training dataset with Sigimg, GADF, and MTF images, and applying a MSCNN with fully connected layer fusion.

Main Results:

  • The proposed Sigimg-GADF-MTF-MSCNN algorithm achieved an average accuracy of 88.4% on the Ninapro DB1 dataset.
  • This accuracy surpasses most mainstream gesture recognition models.
  • Generalization testing on a self-developed sEMG acquisition platform yielded an average accuracy of 82.4%, validating the algorithm's effectiveness.

Conclusions:

  • The Sigimg-GADF-MTF-MSCNN algorithm effectively leverages multi-channel sEMG signal features for accurate gesture recognition.
  • The novel data processing and multi-stream fusion strategy significantly enhance performance compared to existing methods.
  • The algorithm demonstrates robust generalization capabilities, showing promise for real-world applications.