# putEMG -- a surface electromyography hand gesture recognition dataset

## TL;DR

The putEMG dataset provides comprehensive sEMG and hand motion data for gesture recognition, enabling benchmarking and development of robust classification methods with high accuracy.

## Contribution

This paper introduces the putEMG dataset, a new publicly available resource for evaluating hand gesture recognition methods based on surface electromyography signals.

## Key findings

- Achieved 90% accuracy with SVM and RMS features.
- LDA/Du performs better on full hand gestures.
- SVM/RMS outperforms on pinch gestures.

## Abstract

In this paper, we present a putEMG dataset intended for evaluation of hand gesture recognition methods based on sEMG signal. The dataset was acquired for 44 able-bodied subjects and include 8 gestures (3 full hand gestures, 4 pinches, and idle). It consists of uninterrupted recordings of 24 sEMG channels from the subject's forearm, RGB video stream and depth camera images used for hand motion tracking. Moreover, exemplary processing scripts are also published. putEMG dataset is available under Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license at: https://www.biolab.put.poznan.pl/putemg-dataset/. The dataset was validated regarding sEMG amplitudes and gesture recognition performance. The classification was performed using state-of-the-art classifiers and feature sets. Accuracy of 90% was achieved for SVM classifier utilising RMS feature and for LDA classifier using Hudgin's and Du's feature sets. Analysis of performance for particular gestures showed that LDA/Du combination has significantly higher accuracy for full hand gestures, while SVM/RMS performs better for pinch gestures. Presented dataset can be used as a benchmark for various classification methods, evaluation of electrode localisation concepts, or development of classification methods invariant to user-specific features or electrode displacement.