Gesture Recognition by Instantaneous Surface EMG Images

Abstract

Gesture recognition in non-intrusive muscle-computer interfaces is usually based on windowed descriptive and discriminatory surface electromyography (sEMG) features because the recorded amplitude of a myoelectric signal may rapidly fluctuate between voltages above and below zero. Here, we present that the patterns inside the instantaneous values of high-density sEMG enables gesture recognition to be performed merely with sEMG signals at a specific instant. We introduce the concept of an sEMG image spatially composed from high-density sEMG and verify our findings from a computational perspective with experiments on gesture recognition based on sEMG images with a classification scheme of a deep convolutional network. Without any windowed features, the resultant recognition accuracy of an 8-gesture within-subject test reached 89.3% on a single frame of sEMG image and reached 99.0% using simple majority voting over 40 frames with a 1,000 Hz sampling rate. Experiments on the recognition of 52 gestures of NinaPro database and 27 gestures of csl-hdemg database also validated that our approach outperforms state-of-the-arts methods. Our findings are a starting point for the development of more fluid and natural muscle-computer interfaces with very little observational latency. For example, active prostheses and exoskeletons based on high-density electrodes could be controlled with instantaneous responses.

Muscle-Computer Interface (MCI) System

The MCI system: (1) electrode array; (2) reference electrode; (3) acquisition modules; (4) data transmission module; (5) lithium battery; (6) instantaneous sEMG image; (7) recognized gesture.

Dataset

Our CapgMyo database includes HD-sEMG data for 128 channels acquired from 23 intact subjects by using our newly developed acquisition device. The acquisition device has a matrix-type (8×16) differential electrode array with silver wet electrodes. The CapgMyo database consists of 3 sub-databases (DB-a, DB-b and DB-c); 8 isometric and isotonic hand gestures were obtained from 18 of the 23 subjects in DB-a and from 10 of the 23 subjects in DB-b, and 12 basic movements of the fingers were obtained from 10 of the 23 subjects in DB-c. Please see the data descriptor for details.

BibTex

@article{geng2016gesture,
    title={Gesture recognition by instantaneous surface EMG images},
    author={Geng, Weidong and Du, Yu and Jin, Wenguang and Wei, Wentao and Hu, Yu and Li, Jiajun},
    journal={Scientific reports},
    volume={6},
    pages={36571},
    year={2016},
    publisher={Nature Publishing Group}
}

Related Work

• CapgMyo: A High Density Surface Electromyography Database for Gesture Recognition
• Surface EMG-Based Inter-Session Gesture Recognition Enhanced by Deep Domain Adaptation
• Semi-Supervised Learning for Surface EMG-based Gesture Recognition

Acknowledgements

This work was supported by a grant from the National Natural Science Foundation of China (No. 61379067) and the National Key Research and Development Program of China (No. 2016YFB1001300).