Related Experiment Video
Updated: Jun 26, 2026
08:15
Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
Published on: March 28, 2025
Sign language recognition using intrinsic-mode sample entropy on sEMG and accelerometer data
Vasiliki E Kosmidou1, Leontios J Hadjileontiadis
1Department of Electrical and Computer Engineering, Aristotle University of Thessaloniki, Thessaloniki GR 54124, Greece. vkosm@auth.gr
IEEE Transactions on Bio-Medical Engineering
|January 29, 2009
Summary
Automated recognition of Greek Sign Language (GSL) gestures is possible using intrinsic-mode entropy (IMEn) analysis of electromyogram and accelerometer data. This method achieved over 93% accuracy, enhancing communication for the deaf community.
Area of Science:
- Computer Science
- Biomedical Engineering
- Linguistics
Background:
- Sign languages are crucial for deaf communication.
- Automated gesture recognition can bridge communication gaps between deaf and hearing individuals.
- Greek Sign Language (GSL) recognition is an area with potential for technological advancement.
Purpose of the Study:
- To develop an automated system for recognizing isolated Greek Sign Language (GSL) signs.
- To evaluate the effectiveness of intrinsic-mode entropy (IMEn) for GSL gesture recognition.
- To identify optimal parameters for IMEn calculation in the context of GSL.
Main Methods:
- Collected five-channel surface electromyogram and 3-D accelerometer data from signers' dominant hands.
- Applied intrinsic-mode entropy (IMEn) analysis to the collected sensor data.
- Utilized discriminant analysis to determine effective IMEn scales and window lengths for classification.
Main Results:
- Intrinsic-mode entropy (IMEn) analysis was applied to a 60-word GSL lexicon.
- Three native signers repeated each sign ten times.
- Achieved a mean classification accuracy exceeding 93% using IMEn as the sole feature set.
Conclusions:
- Intrinsic-mode entropy (IMEn) is a highly effective feature for automated Greek Sign Language (GSL) recognition.
- The developed method shows significant promise for advancing automated GSL gesture recognition systems.
- This research contributes to improved communication tools for the deaf community.
