An Isotropic 3D Gesture Recognition Method Based on Feature Selection

An isotropic, three-dimensional gesture technology, applied in the field of gesture recognition, can solve problems such as the influence of gesture direction on gesture recognition, achieve the effects of reducing data collection, improving gesture recognition rate, and reducing requirements

Active Publication Date: 2020-08-11
杭州淘艺数据技术有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method mainly solves the three-dimensional gesture recognition of direction-independent and redundant feature elimination, and is suitable for people with different hand sizes, and solves the problem that image-based gesture recognition is greatly affected by the direction of the gesture.

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
  • An Isotropic 3D Gesture Recognition Method Based on Feature Selection
  • An Isotropic 3D Gesture Recognition Method Based on Feature Selection
  • An Isotropic 3D Gesture Recognition Method Based on Feature Selection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention will be further described below in conjunction with accompanying drawing.

[0027] like figure 1 As shown, an isotropic 3D gesture recognition method based on feature selection, including data acquisition, feature extraction and feature selection, is as follows:

[0028] Step 1. Use the API of the somatosensory controller (Leap Motion) to collect the three-dimensional coordinate data of 10 gestures in Chinese sign language, and put them into the training set and the test set; wherein, the three-dimensional coordinate data of each gesture includes the fingertips of each finger, each finger 3D coordinates of joints, palms and wrists. In the training set, only the gestures of one person are collected, and each gesture is only collected with the palm facing down, and each gesture is collected 50 times with the palm facing down to obtain 50 sets of 3D coordinate data; the gestures of multiple people are collected in the test set, For each gesture of e...

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 isotropic three-dimensional gesture recognition method based on feature selection. The existing 3D gesture recognition algorithm does not consider the contribution of the extracted gesture-related features to the classification, and the redundant features affect the recognition rate. The present invention extracts 24 features from the collected three-dimensional coordinate data of gestures and inputs them into the random forest model, arranges the importance scores of each feature obtained by the training model from large to small, and selects among the 24 features arranged in k groups of each gesture The first n features of each group are combined into a combination feature. Based on the ten-fold cross-validation method and the Gaussian Naive Bayesian recognition model, the recognition rate of the Gaussian Naive Bayesian recognition model under 24 groups of combined features is obtained; The recognition rate of the naive Bayesian recognition model determines the selection of the combined features composed of the first few features for the final recognition model. The invention not only reduces the amount of feature-related data collection, simplifies the model calculation, but also improves the recognition rate.

Description

technical field [0001] The invention belongs to the field of gesture recognition, in particular to an isotropic three-dimensional gesture recognition method based on feature selection. Background technique [0002] There are many deaf people in the world, and sign language is their main medium of communication. However, there are certain obstacles in the communication between the deaf-mute and normal people, so the realization of sign language recognition is of great significance for improving the communication status between the two. Sign language gestures include elements such as hand shape, position, and movement. Among them, the most intuitive one is hand shape, which expresses the shape of the hand when making a gesture. Different hand shapes have different meanings of gestures. Therefore, handshake recognition has become the key to gesture recognition. [0003] In recent years, with the development of depth sensors, 3D gesture recognition has become possible. Featur...

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 Patents(China)
IPC IPC(8): G06F3/01G06K9/00
CPCG06F3/017G06V40/107
Inventor 章田张钰
Owner 杭州淘艺数据技术有限公司
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