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

Viscoelastic characterization of the human osteosarcoma cancer cell line MG-63 using a fractional-order zener model through automated algorithm design and configuration.

Scientific reports·2025
Same author

Lightweight U-Net for Blood Vessels Segmentation in X-Ray Coronary Angiography.

Journal of imaging·2025
Same author

REGEEG: A Regression-Based EEG Signal Processing in Emotion Recognition.

IEEE journal of biomedical and health informatics·2025
Same author

Optimal hybrid resonant current controller for microgrids connected to an unbalanced IEEE test distribution network.

Heliyon·2024
Same author

Multiclass Classification of Visual Electroencephalogram Based on Channel Selection, Minimum Norm Estimation Algorithm, and Deep Network Architectures.

Sensors (Basel, Switzerland)·2024
Same author

Motor Imagery Multi-Tasks Classification for BCIs Using the NVIDIA Jetson TX2 Board and the EEGNet Network.

Sensors (Basel, Switzerland)·2023

Related Experiment Video

Updated: Dec 3, 2025

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

1.0K

Multi-Stroke handwriting character recognition based on sEMG using convolutional-recurrent neural networks.

Jose Guadalupe Beltran-Hernandez1, Jose Ruiz-Pinales1, Pedro Lopez-Rodriguez1

  • 1Digital Signal Processing and Telematics Groups, Engineering Division of the Campus Irapuato-Salamanca (DICIS), Universidad de Guanajuato, Palo Blanco, Salamanca, Guanajuato, Mexico.

Mathematical Biosciences and Engineering : MBE
|October 30, 2020
PubMed
Summary

This study introduces a new method using electromyographic signals and deep learning to recognize handwriting characters with 94.85% accuracy. This technology could enhance communication and aid individuals with disabilities.

Keywords:
convolutional neural networksgated recurrent unitlong short-term memorysurface EMG

More Related Videos

Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment
05:58

Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment

Published on: March 11, 2021

4.9K
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

4.9K

Related Experiment Videos

Last Updated: Dec 3, 2025

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

1.0K
Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment
05:58

Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment

Published on: March 11, 2021

4.9K
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

4.9K

Area of Science:

  • Biomedical Engineering
  • Artificial Intelligence
  • Human-Computer Interaction

Background:

  • Handwriting remains a vital communication method and crucial for child development.
  • Existing handwriting recognition technologies often struggle with free-style, multi-stroke inputs.
  • Electromyographic (EMG) signals offer a novel data source for capturing fine motor movements.

Purpose of the Study:

  • To develop and evaluate a novel methodology for recognizing multi-user, free-style, multi-stroke handwriting characters.
  • To leverage advanced Deep Learning (DL) architectures for robust feature extraction and sequence recognition.
  • To explore the potential applications of this technology in AI and assistive devices.

Main Methods:

  • Utilized electromyographic (EMG) signals captured during handwriting tasks.
  • Employed Deep Learning (DL) models, specifically Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs).
  • Developed a framework for feature extraction and sequence recognition from EMG data for handwriting character identification.

Main Results:

  • Achieved a high accuracy rate of 94.85% in recognizing handwriting characters.
  • Demonstrated the effectiveness of DL architectures (CNNs and RNNs) in processing complex EMG signal patterns.
  • Validated the methodology across multiple users and diverse handwriting styles.

Conclusions:

  • The proposed EMG-based DL methodology offers a highly accurate approach to handwriting character recognition.
  • This technology has significant potential for developing advanced AI applications that enhance communication.
  • The system can be applied to create assistive technologies for individuals with disabilities, improving their interaction capabilities.