Gesture recognition method for large vocabulary

A technology of gesture recognition and large vocabulary, applied in the field of gesture recognition for large vocabulary, can solve the problems that the machine cannot correctly recognize the intention of the sign language person, it is difficult to meet the time requirements, and the gesture data dimension is high, so as to reduce the impact and improve the accuracy rate , the effect of reducing redundant data

Active Publication Date: 2018-04-13
SOUTH CHINA UNIV OF TECH +1
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The system needs to process a large amount of gesture data, and the gesture data has a high dimension, so there will inevitably be a long time delay, which is difficult to meet the actual time requirements
It is easy to cause time redundancy and cannot be recognized in real time. Due to the influence of many gestures with similar movements, the same gesture inevitably has time-space differences due to different execution speeds and movement ranges, resulting in a low gesture recognition rate, and the machine cannot recognize it correctly. Signer Intentions Affect the Communication Process

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
  • Gesture recognition method for large vocabulary
  • Gesture recognition method for large vocabulary
  • Gesture recognition method for large vocabulary

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] like figure 1 As shown, a gesture recognition method for large vocabulary, including training Hidden Markov Model (HMM) and gesture shunt recognition;

[0034] S1. Training Hidden Markov Model

[0035] S11. According to the Chinese Sign Language Handbook, 800 gestures commonly used by the deaf-mute are predefined. Obtain the hand posture data of 800 predefined gestures through the data glove. Obtain n data at each moment, which is the n-dimensional feature of the gesture at this moment, and the feature includes the curvature of the finger and the direction of the palm. Each gesture takes M training sample data, 800 gestures, that is 800M training sample data. Each training sample selects t moments, and each moment obtains n data for the n-dimensional features of gestures at this moment, and each training sample data is defined as X={x 1,1 ,x 1,2 ,...,x 1,t ; x 2,1 ,x 2,2 ,...,x 2,t ;...;x n,1 ,x n,2 ,...,x n,t}, where x i,j Represents the data of the i-th d...

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 gesture recognition method for large vocabulary, which comprises a training hidden Markov model and the gesture recognition of a shunt recognition frame. The method can effectively reduce the dimension of the gesture data and reduce the dimensionality of the data processed by the algorithm. In this way, the running time of the algorithm is reduced, the real-time performance of the gesture recognition is further improved, the habit of normal gesture communication is met, and the gesture communication is more natural and smooth. The method combines the gesture shunt recognition frame to effectively pre-classify the gesture data, shortens the time of the recognition process, and improves the recognition rate of the overall gesture recognition, thereby further improving the accuracy and efficiency of gesture recognition, and can effectively solve the problem of training and recognizing a large number of continuous gestures in a real-time scene.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence and human-computer interaction, in particular to a gesture recognition method for large vocabulary. Background technique [0002] Gesture is one of the important ways of human communication. With the development of science and technology, the importance of human-computer interaction and gesture recognition has gradually become prominent, and it has become a hot spot in the field of artificial intelligence. People are increasingly pursuing gesture recognition effects with high fluency and good communication experience, especially for some specific application fields, such as for deaf-mute people in special groups, correct, effective and real-time gesture recognition communication is even more indispensable The way. [0003] For deaf-mute communication, the gesture recognition technology involved mainly involves Chinese sign language translation. Chinese sign language has the chara...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06F3/01
CPCG06F3/017G06V40/113G06V40/28G06F18/295
Inventor 周智恒代雨锟陈曦杨溢
Owner SOUTH CHINA 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