Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Comparative Study of EMG- and IMU-based Gesture Recognition at the Wrist and Forearm

Soroush Baghernezhad, Elaheh Mohammadreza, Vinicius Prado da Fonseca, Ting Zou, Xianta Jiang

TL;DR

The paper compares EMG and IMU modalities for static hand gesture recognition at the wrist and forearm, showing IMU-only input can achieve strong performance and even surpass EMG in static tasks. It provides a detailed methodology including sensor placement (W1–W4 and F1–F4), data collection from 12 participants across 17 gestures, and a robust feature-classification pipeline using LDA and SVM. A key finding is that tendon-induced micro-movements captured by IMUs contribute significantly to gesture discernment, with nine-axis IMU data and broad anatomical coverage delivering the highest accuracy (around 89%). The work demonstrates the viability of IMU-based, non-invasive gesture recognition for prosthetic control and other HCI applications, and outlines future directions toward dynamic gestures and real-time wearable devices.

Abstract

Gestures are an integral part of our daily interactions with the environment. Hand gesture recognition (HGR) is the process of interpreting human intent through various input modalities, such as visual data (images and videos) and bio-signals. Bio-signals are widely used in HGR due to their ability to be captured non-invasively via sensors placed on the arm. Among these, surface electromyography (sEMG), which measures the electrical activity of muscles, is the most extensively studied modality. However, less-explored alternatives such as inertial measurement units (IMUs) can provide complementary information on subtle muscle movements, which makes them valuable for gesture recognition. In this study, we investigate the potential of using IMU signals from different muscle groups to capture user intent. Our results demonstrate that IMU signals contain sufficient information to serve as the sole input sensor for static gesture recognition. Moreover, we compare different muscle groups and check the quality of pattern recognition on individual muscle groups. We further found that tendon-induced micro-movement captured by IMUs is a major contributor to static gesture recognition. We believe that leveraging muscle micro-movement information can enhance the usability of prosthetic arms for amputees. This approach also offers new possibilities for hand gesture recognition in fields such as robotics, teleoperation, sign language interpretation, and beyond.

A Comparative Study of EMG- and IMU-based Gesture Recognition at the Wrist and Forearm

TL;DR

The paper compares EMG and IMU modalities for static hand gesture recognition at the wrist and forearm, showing IMU-only input can achieve strong performance and even surpass EMG in static tasks. It provides a detailed methodology including sensor placement (W1–W4 and F1–F4), data collection from 12 participants across 17 gestures, and a robust feature-classification pipeline using LDA and SVM. A key finding is that tendon-induced micro-movements captured by IMUs contribute significantly to gesture discernment, with nine-axis IMU data and broad anatomical coverage delivering the highest accuracy (around 89%). The work demonstrates the viability of IMU-based, non-invasive gesture recognition for prosthetic control and other HCI applications, and outlines future directions toward dynamic gestures and real-time wearable devices.

Abstract

Gestures are an integral part of our daily interactions with the environment. Hand gesture recognition (HGR) is the process of interpreting human intent through various input modalities, such as visual data (images and videos) and bio-signals. Bio-signals are widely used in HGR due to their ability to be captured non-invasively via sensors placed on the arm. Among these, surface electromyography (sEMG), which measures the electrical activity of muscles, is the most extensively studied modality. However, less-explored alternatives such as inertial measurement units (IMUs) can provide complementary information on subtle muscle movements, which makes them valuable for gesture recognition. In this study, we investigate the potential of using IMU signals from different muscle groups to capture user intent. Our results demonstrate that IMU signals contain sufficient information to serve as the sole input sensor for static gesture recognition. Moreover, we compare different muscle groups and check the quality of pattern recognition on individual muscle groups. We further found that tendon-induced micro-movement captured by IMUs is a major contributor to static gesture recognition. We believe that leveraging muscle micro-movement information can enhance the usability of prosthetic arms for amputees. This approach also offers new possibilities for hand gesture recognition in fields such as robotics, teleoperation, sign language interpretation, and beyond.

Paper Structure

This paper contains 15 sections, 3 equations, 9 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Methodology
  4. Sensor Placement
  5. Data Collection
  6. Signal Quality Evaluation
  7. Preprocessing
  8. Classification
  9. Statistical analysis
  10. Results
  11. Signal Evaluation results
  12. Classification results
  13. Optimal Placement
  14. Conclusion
  15. Future Work

Figures (9)

  • Figure 1: Overview of our work. (a) Sensor Placement (b) Gestures (c) Feature Extraction (d) Model Training
  • Figure 2: Placement of sensors on (a) Anterior and (b) Posterior side of the arm.
  • Figure 3: (a) Participant postures during phase two and (b) phase one of the experiment.
  • Figure 4: Gestures used in this experiment. From top left: Rest, Thumb Extension (TE), Index Extension (IE), Middle Extension (ME), Ring Extension (RE), Pinky Extension (PE), Thumbs Up (TU), Pointing (PO), Peace (PC), OK, Horn (HN), Hang Loose (HL), Power Grasp (PG), Hand Open (HO), Ulnar Deviation (UD), Radial Deviation (RD), Wrist Extension (WE), and Wrist Flexion (WF).
  • Figure 5: Overview of the general pipeline used in this study. (a) Data collection (b) Filtering and preprocessing (c) Windowing (d) Feature extraction (e) Classification and Prediction
  • ...and 4 more figures