Gesture recognition by instantaneous surface EMG images

TLDR

Gesture recognition in non‑intrusive muscle‑computer interfaces typically relies on windowed sEMG features due to rapid amplitude fluctuations, but high‑density electrodes could enable instantaneous control of prostheses and exoskeletons. This study demonstrates that patterns in instantaneous high‑density sEMG values can be used for gesture recognition, and validates this concept computationally. The authors construct spatial sEMG images from high‑density recordings and classify them with a deep convolutional neural network. Using a single sEMG image frame, the method achieved 89.3 % accuracy on an 8‑gesture within‑subject test and 99.0 % with majority voting over 40 frames, outperforming state‑of‑the‑art approaches on the NinaPro and CSL‑HDEMG databases and enabling low‑latency, fluid muscle‑computer interfaces.

Abstract

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.