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

Sensing In Exergames for Efficacy and Motion Quality: Scoping Review of Recent Publications.

JMIR serious games·2024
Same author

Assessing the Accuracy of Smartwatch-Based Estimation of Maximum Oxygen Uptake Using the Apple Watch Series 7: Validation Study.

JMIR biomedical engineering·2024
Same author

IMU-Based Fitness Activity Recognition Using CNNs for Time Series Classification.

Sensors (Basel, Switzerland)·2024
Same author

Recognizing Full-Body Exercise Execution Errors Using the Teslasuit.

Sensors (Basel, Switzerland)·2021
Same author

Quality Criteria for Serious Games: Serious Part, Game Part, and Balance.

JMIR serious games·2020

Related Experiment Video

Updated: Jul 7, 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

500

Give Me a Sign: Using Data Gloves for Static Hand-Shape Recognition.

Philipp Achenbach1, Sebastian Laux1, Dennis Purdack1

  • 1Serious Games Group, Technical University of Darmstadt, 64289 Darmstadt, Germany.

Sensors (Basel, Switzerland)
|December 23, 2023
PubMed
Summary

This study introduces a hand-shape recognition system using data gloves for virtual reality (VR) communication. The system achieves high accuracy in distinguishing various hand gestures, enhancing immersive VR experiences.

Keywords:
classificationdata augmentationfeature selectionhand-shape recognitionlogistic regressionmachine learningoutlier detectionrandom forest classifiersign languagesupport vector machinesvirtual realityvoting meta-classifier

More Related Videos

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

1.6K
Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing
06:25

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

615

Related Experiment Videos

Last Updated: Jul 7, 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

500
Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

1.6K
Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing
06:25

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

615

Area of Science:

  • Computer Science
  • Human-Computer Interaction
  • Virtual Reality

Background:

  • Traditional computer communication methods like keyboards and microphones limit immersion in virtual reality (VR).
  • Microphones are not always suitable for VR due to silent command needs or user limitations like hearing loss.
  • Data gloves offer a natural interaction method, capturing hand shapes for non-verbal cues and sign language within VR.

Purpose of the Study:

  • To develop and evaluate a hand-shape recognition system using Manus Prime X data gloves for non-verbal communication in VR.
  • To investigate the impact of outlier detection and feature selection on classification accuracy and time.
  • To assess the effectiveness of data augmentation for creating a more generalized recognition approach.

Main Methods:

  • Data acquisition and preprocessing using Manus Prime X data gloves.
  • Implementation of outlier detection and feature selection techniques.
  • Application of data augmentation to expand the training dataset.
  • Classification of 56 distinct hand shapes using various machine learning models, including voting meta-classifier (VL2) and random forest (RF).

Main Results:

  • The system achieved up to 93.28% accuracy for 56 hand shapes and 95.55% for 27 hand shapes.
  • Outlier detection improved classification time significantly.
  • Data augmentation enhanced the generalizability of the recognition system.
  • The voting meta-classifier (VL2) offered the highest accuracy, while random forest provided a good balance of speed and accuracy.

Conclusions:

  • The developed hand-shape recognition system using data gloves is effective for enabling non-verbal communication in VR.
  • The preprocessing techniques, including outlier detection and feature selection, are crucial for optimizing performance.
  • Data augmentation contributes to a more robust and generalizable hand-shape recognition model for VR applications.