Gesture action recognition method for Chinese Puyue sign language coding

A technology of gestures and gestures, which is applied in sign language recognition systems and human-computer interaction, in the field of gestures and actions recognition of China Pule Sign Language Coding, which can solve the problems of inability to achieve recognition effects, high HOG feature dimensions, and inability to meet real-time efficiency and other problems

Active Publication Date: 2019-07-23
HEFEI UNIV OF TECH
View PDF10 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When using the above-mentioned gesture recognition method to recognize Chinese Pule sign language, it cannot achieve a good recognition effect, because the direction correction method described is no longer suitable when using a conventional camera or wearing long sleeves, and the commonly used HOG feature has a relatively small dimension. High, unable to meet the real-time and efficient needs, so it is not suitable for Chinese Pule sign language coded gesture recognition

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 action recognition method for Chinese Puyue sign language coding
  • Gesture action recognition method for Chinese Puyue sign language coding
  • Gesture action recognition method for Chinese Puyue sign language coding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] In this embodiment, a gesture recognition method of Chinese Pule sign language encoding includes: 1. First capture the gesture action video of Chinese Pule sign language encoding with a camera to obtain a frame-by-frame RGB image sequence; 2. Perform color space conversion on each frame of image And determine the gesture area; 3 determine the fitting circle according to the minimum value of the extracted hand-shaped edge contour point sequence, and replace the palm area, and then detect the fingertip and finger root; 4 take the center of the circle and the vertically downward unit vector as the standard, Extract the angle and distance features of each contour point; 5 use the dynamic time warping algorithm to map and transform the features to obtain the similar distance features of a certain gesture; 6 use a variety of classifiers to recognize sign language actions.

[0052] In this embodiment, in order to verify the effect of the present invention on recognizing Chinese...

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 action recognition method for Chinese Puyue sign language coding, which comprises the following steps of: 1, capturing a Chinese Puyue sign language coding gesture action video by using a camera to obtain a framed RGB image sequence; 2, performing color space conversion on each frame of image and determining a gesture area; 3, determining a fitting circle according to the extracted minimum value of the hand-shaped edge contour point sequence, replacing a palm center area, and then detecting a fingertip and a finger root; 4, extracting the angle and distance characteristics of each contour point by taking the circle center and the vertically downward unit vector as standards; 5, performing mapping transformation on the features by adopting a dynamic time warping algorithm to obtain similar distance features of a certain gesture; and 6, identifying the sign language actions by adopting a plurality of classifiers. The method can effectively identify the Chinese Puyue sign language coding gesture actions, provides a solution for a continuous and large-scale vocabulary Chinese sign language identification system, and is of great significance for popularizing normative Chinese sign languages.

Description

technical field [0001] The invention belongs to the technical field of gesture recognition of Chinese sign language, and in particular relates to a gesture recognition method of Chinese Pule sign language coding, which is mainly used in sign language recognition systems, human-computer interaction and other related fields. Background technique [0002] Gesture action is an important input method of human-computer interaction, and it is applied to various information communication processes with its rich and varied meanings and flexible execution methods. Gesture recognition refers to the use of computers to detect, analyze and explain the gestures performed by people, such as the movement mode and force of arms, wrists, fingers, etc., so as to judge the intention of the movement and provide corresponding services. Gesture recognition technology is widely used in Sign language recognition, rehabilitation training, human-computer interaction, home appliance control, smart cars...

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): G06K9/00G06K9/46G06K9/62
CPCG06V40/28G06V20/42G06V10/443G06V10/752G06F18/243
Inventor 成娟魏馥琳刘羽陈勋李畅宋仁成
Owner HEFEI 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