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.
Highlights
We have determined that there are patterns inside the instantaneous HD-Surface electromyography (sEMG) that are reproducible across trials of the same gesture and discriminative among different gestures
Our method achieved an accuracy of 96.8% using simple majority voting over the entire segment of each trial, an 6.4% improvement over the latest work of gesture recognition base on HD-sEMG23
We performed a series of experiments to verify our assumptions on the patterns inside instantaneous sEMG images and demonstrate that the hand gestures of a specific subject will be effectively recognized directly on the instantaneous sEMG images with an image classifier trained on the samples of hand gestures from the same subject
Summary
We performed a series of experiments to verify our assumptions on the patterns inside instantaneous sEMG images and demonstrate that the hand gestures of a specific subject will be effectively recognized directly on the instantaneous sEMG images with an image classifier trained on the samples of hand gestures from the same subject. For 27 finger gestures from CSL-HDEMG, the recognition accuracy reached 55.8% on a single frame of HD-sEMG signals with a 2,048 Hz sampling rate, and it reached 96.8% using simple majority voting over the entire segment of each trial–an 6.3% improvement over the latest work[23]. For 52 hand gestures from NinaPro DB1, the recognition accuracy reached 65.1% on a single frame of sEMG signals with a 100 Hz sampling rate, and it reached 96.7% using simple majority voting over the entire segment of each trial. This research will open new avenues for studying muscle characteristics and interpreting the physiological mechanisms of patterns in dynamic transitional motions via sEMG, in addition to static gestures. We plan to investigate more sophisticated classification algorithms for sEMG-based gesture recognition
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
