Related Experiment Video
Updated: Feb 18, 2026
08:15
Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
Published on: March 28, 2025
1.3K
An Individual Finger Gesture Recognition System Based on Motion-Intent Analysis Using Mechanomyogram Signal
Huijun Ding1, Qing He1, Yongjin Zhou1
1Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Guangdong, China.
Frontiers in Neurology
|November 24, 2017
Summary
This study introduces a novel motion-intent-based finger gesture recognition system capable of identifying individual finger taps. Achieving up to 94% accuracy, this technology enhances human-computer interaction and assistive device control.
Area of Science:
- Biomedical Engineering
- Human-Computer Interaction
- Signal Processing
Background:
- Motion-intent-based finger gesture recognition is vital for applications like prosthesis control and sign language recognition.
- Existing systems often lack the precision to differentiate individual finger taps.
Purpose of the Study:
- To design and evaluate a novel system for accurate, motion-intent-based recognition of individual finger taps.
- To introduce and assess auto-event annotation algorithms for finger tap detection.
Main Methods:
- Two auto-event annotation algorithms were used to detect finger tapping frames.
- Wavelet Packet Transform (WPT) coefficients were computed and compressed for feature extraction.
- Feature selection optimized the feature set, and Naive Bayes, KNN, and SVM classifiers were evaluated.
Main Results:
- The system successfully identified individual finger taps with high accuracy.
- Recognition accuracy reached up to 94% using optimized feature sets and evaluated classifiers.
- The proposed auto-event annotation algorithms effectively detected finger tapping events.
Conclusions:
- The developed motion-intent-based finger gesture recognition system demonstrates significant potential for advanced human-computer interaction.
- The integration of WPT and feature selection provides an effective method for robust finger gesture recognition.
- This system offers a promising advancement for applications requiring precise finger movement interpretation.
