Sign language recognition method based on surface myoelectric sensor and nine-axis sensor

A nine-axis sensor and recognition method technology, applied in the field of sign language recognition based on surface electromyography sensors and nine-axis sensors, can solve the problems of inconvenient wearing of data glove recognition technology

Pending Publication Date: 2019-07-05
GUANGDONG POLYTECHNIC NORMAL UNIV
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the above-mentioned defects of the prior art, especially to solve the problem of inconvenient wearing of the recognition technology based on data gloves, the present invention provides a sign language recognit

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
  • Sign language recognition method based on surface myoelectric sensor and nine-axis sensor
  • Sign language recognition method based on surface myoelectric sensor and nine-axis sensor
  • Sign language recognition method based on surface myoelectric sensor and nine-axis sensor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0159] according to Figure 1-2 A kind of sign language recognition method based on surface electromyography sensor and nine-axis sensor shown, comprises the arm band 1 that is worn on the arm, and described arm band 1 is provided with a nine-axis sensor 2, eight myoelectric sensors 3 and A bluetooth receiver 4, the nine-axis sensor 2 is used to detect the movement trajectory and orientation of the arm, the surface myoelectric sensor 3 is used to detect the myoelectric signals of different gestures, the armband 1 is connected through the bluetooth receiver 4 Terminal equipment, sign language recognition methods are as follows:

[0160] Step 1. First, wear the armband 1 on the arm, collect all the raw sign language data through the training of the myoelectric sensor 3 and the nine-axis sensor 2, and send it to the terminal device through the Bluetooth receiver 4;

[0161] Step 2. Obtain effective motion data of the gesture to be recognized by detecting the signal starting poin...

Embodiment 2

[0167] according to figure 1 Shown is a sign language recognition method based on a surface electromyography sensor and a nine-axis sensor, eight of the myoelectric sensors 3 are evenly embedded in the inner wall of the armband 1, and the nine-axis sensor 2 and the Bluetooth receiver 4 are arranged on the Inside the armband 1, the myoelectric sensor 3 and the nine-axis sensor 2 are connected to the bluetooth receiver 4 through the A / D sensor, and the bluetooth receiver 4 is communicatively connected to a terminal device, and the terminal device includes a mobile phone or a computer;

[0168] The action potential waveform of the muscle motor unit (by muscle fiber cells) is detected by the myoelectric sensor 3, and the nine-axis sensor 2 includes a three-axis accelerometer, a three-axis gyroscope and a three-axis magnetometer, and the three-axis accelerometer and the three-axis gyroscope respectively judge The acceleration direction and speed of the arm and the current rotation ...

Embodiment 3

[0170] according to figure 2 A sign language recognition method based on a surface electromyography sensor and a nine-axis sensor is shown, and the implementation of the specific recognition method is as follows:

[0171] Step 1, collecting all raw data through the myoelectric sensor 3 and the nine-axis sensor 2;

[0172] In the process of wearing the armband 1, the terminal device will read the real-time data of the eight myoelectric sensors 3 and the nine-axis sensor 2 through the low-power Bluetooth 4.0 receiver, and display them on the terminal device for processing;

[0173] Step 2, collect effective motion data of the gesture to be recognized by detecting the signal starting point based on sample entropy;

[0174] Sample Entropy (Sample Entropy, SampEn), measures the probability of generating new patterns in signals by measuring the complexity of time series; SampEn overcomes data deviation, has stronger anti-noise ability and excellent consistency, and uses less data ...

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 a sign language recognition method based on a surface myoelectric sensor and a nine-axis sensor, and particularly relates to the field of sign language recognition. The methodcomprises the following steps of 1, acquiring all original data through the myoelectric sensor and the nine-axis sensor; 2, obtaining effective action data of the to-be-identified gesture through signal starting point detection based on sample entropy; 3, performing noise preprocessing on the effective action data of the to-be-identified gesture through Kalman filtering, and outputting the filtered to-be-identified gesture data; and 4, performing time-frequency domain feature extraction and normalization on the to-be-identified gesture data output in the step 3. According to the present invention, the gesture data of the user is collected by adopting a mode of fusing the surface electromyogram signal sensor and the nine-axis sensor, and modeling is performed through the integrated learningmodel, so that the data volume and the accuracy of recognizable sign language are improved, and meanwhile, the stability and the fault tolerance of sign language recognition are also enhanced.

Description

technical field [0001] The present invention relates to the technical field of sign language recognition, and more specifically, the present invention relates to a sign language recognition method based on a surface electromyography sensor and a nine-axis sensor. Background technique [0002] Sign language is currently the language used by the deaf. Sign language is to use gestures to compare actions, and to simulate images or syllables to form certain meanings or words according to the changes in gestures. It is a language for deaf-mute people to communicate and exchange ideas with each other. However, sign language is a very large and complex language system, and it is obviously unrealistic for most able-bodied people to learn sign language to communicate. Therefore, in order to help the deaf-mute maintain rapid and effective normal communication with healthy people, improve their independent living ability and social well-being, and reduce the burden on the family and so...

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): G06F3/01G06F3/0346G06K9/62G06N3/04G06N3/08
CPCG06F3/015G06F3/017G06F3/0346G06N3/084G06N3/044G06N3/045G06F18/2148G06F18/2411
Inventor 郭海森施金鸿李钊华曾善玲李嘉豪何焯正刁宇桦李鸿纬范鸿鑫
Owner GUANGDONG POLYTECHNIC NORMAL UNIV
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