Hand Gesture Recognition Based on Deep Learning Method
Authors:
- 1 June 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 542-546
Abstract
The classical classification method usually consists preprocessing, windowing, feature extraction and classification. Despite the promising performance have been shown in recent researcher, the greatest disadvantage of those classical methods is that some useful information may be discarded when extracting feature. In this paper, a novel model based on deep learning is proposed to improve the accuracy of EMG-based hand gesture recognition. A parallel architecture with five convolution layers is adopted. The results show a slight improvement when using convolution neural network. Meanwhile, the effect of preprocessing on CNN-based method has also been evaluated.Keywords
This publication has 25 references indexed in Scilit:
- The Influencing Factors, Regional Difference and Temporal Variation of Industrial Technology Innovation: Evidence with the FOA-GRNN ModelSustainability, 2018
- Gesture recognition by instantaneous surface EMG imagesScientific Reports, 2016
- EMG Feature Set Selection Through Linear Relationship for Grasp RecognitionJournal of Medical and Biological Engineering, 2016
- Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic HandsFrontiers in Neurorobotics, 2016
- Transradial Amputee Gesture Classification Using an Optimal Number of sEMG Sensors: An Approach Using ICA ClusteringIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2015
- A Novel Method for Disease Prediction: Hybrid of Random Forest and Multivariate Adaptive Regression SplinesJournal of Computers, 2013
- Learning human reach-to-grasp strategies: Towards EMG-based control of robotic arm-hand systems2012
- Actuation of prosthetic drive using EMG signal2009
- A Novel Video Summarization Based on Mining the Story-Structure and Semantic Relations Among Concept EntitiesIEEE Transactions on Multimedia, 2009
- Multi-channel surface EMG classification using support vector machines and signal-based wavelet optimizationBiomedical Signal Processing and Control, 2008