sEMG gesture recognition method based on wavelet width learning system

A learning system, gesture recognition technology, applied in character and pattern recognition, input/output process of data processing, input/output of user/computer interaction, etc. The effect of recognition rate

Pending Publication Date: 2019-10-29
GUANGDONG UNIV OF TECH
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these classic network models consu

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • sEMG gesture recognition method based on wavelet width learning system
  • sEMG gesture recognition method based on wavelet width learning system
  • sEMG gesture recognition method based on wavelet width learning system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The present invention will be further described in detail below in conjunction with the embodiments and the accompanying drawings, but the embodiments of the present invention are not limited thereto.

[0044] Such as Figure 1~3 Shown, a kind of sEMG gesture recognition method based on wavelet width learning system comprises the following steps:

[0045] Step 1: Define the number d of gesture types according to the corresponding recognition scene, and assign a sequence number to each gesture.

[0046] Step 2, use such as image 3 The shown electromyographic signal acquisition device acquires sEMG signal s.

[0047] Step 3: According to the frequency characteristics of the sEMG signal, filter the original sEMG signal for noise reduction, and use the Butterworth filter to remove the noise outside the 10Hz-500Hz frequency band:

[0048]

[0049] where N is the order of the filter, ω c filter for the cutoff frequency.

[0050] Step 4, using the moving window method...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an sEMG gesture recognition method based on a wavelet width learning system. The sEMG gesture recognition method comprises: 1, defining the number d of gesture action types according to a corresponding recognition scene; 2, acquiring an sEMG signal s by using electromyographic signal acquisition equipment; 3, filtering and denoising the sEMG original signal according to thefrequency characteristic of the sEMG signal, and removing noise outside the frequency band of 10Hz-500Hz by using a Butterworth filter; 4, detecting an active section in the sEMG signal by adopting amoving window method; step 5, carrying out feature extraction on the detected movable section. Compared with an algorithm based on a traditional deep learning network, the method has the advantages that model training and parameter determination can be completed more quickly, so that the working efficiency is improved; nodes can be dynamically expanded, so that the recognition rate of the systemis improved, and a model does not need to be completely rebuilt and trained.

Description

technical field [0001] The invention relates to the technical field of machine learning and signal classification, in particular to a sEMG gesture recognition method based on a wavelet width learning system. Background technique [0002] Gestures in body language play an important role in daily communication, such as referee actions on the football field and so on. Therefore, scholars have focused on how to enable computers and machines to efficiently and accurately recognize human gestures and execute corresponding programs. This will change the form of communication between humans and machines. [0003] At present, the recognition algorithms for gesture actions are mainly divided into the following categories: classification algorithms based on visual image recognition and gesture recognition algorithms based on surface electromyography (sEMG); Relatively high and the price of the device will be relatively expensive, so it is difficult to popularize, but the recognition ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F3/01G06K9/00G06K9/62
CPCG06F3/015G06F3/017G06V40/28G06F18/23213G06F18/24
Inventor 林佳泰刘治章云
Owner GUANGDONG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap