Supercharge Your Innovation With Domain-Expert AI Agents!

A Gesture Recognition Method Based on Multi-core Learning Heterogeneous Feature Fusion

A heterogeneous feature fusion and multi-core learning technology, applied in character and pattern recognition, instruments, computer components, etc., can solve the problem of low recognition rate of gesture recognition, achieve the effect of improving recognition rate and generalization ability

Inactive Publication Date: 2017-10-31
LIAONING UNIVERSITY OF PETROLEUM AND CHEMICAL TECHNOLOGY
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In order to overcome the deficiencies in the above-mentioned prior art, the present invention designs a gesture recognition method based on image feature fusion and multi-core support vector machine; solves the problem of low recognition rate of gesture recognition in the prior art

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
  • A Gesture Recognition Method Based on Multi-core Learning Heterogeneous Feature Fusion
  • A Gesture Recognition Method Based on Multi-core Learning Heterogeneous Feature Fusion
  • A Gesture Recognition Method Based on Multi-core Learning Heterogeneous Feature Fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Below in conjunction with example the present invention is described in further detail.

[0024] The invention mainly includes four parts: gesture segmentation, feature extraction of gesture image, construction and fusion of basic kernel, training and recognition of multi-core support vector machine. figure 1 Be the system flowchart of algorithm of the present invention, concrete steps are as follows:

[0025] 1. Gesture Segmentation

[0026] 1. Take gesture images through the camera, collect several images of different gestures of different people for training image sets, and pre-set the meanings of various gestures in the training set.

[0027] 2. Gesture segmentation: Segment all captured gesture images. First, light compensation processing is performed on the image. Then, the gesture area is segmented by setting the threshold of HSV color space. The segmented gesture image has a black background and a colored part of the human hand. Finally, grayscale the image...

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 relates to a gesture recognition method based on multi-core learning fusion of heterogeneous features, comprising the following steps: performing gesture segmentation on a gesture image, extracting three different types of features of the gesture image after segmentation, generating a feature descriptor, and using a support vector machine The kernel function of the kernel function generates the basic kernel of three characteristics, according to the relevant theory of the kernel function, the three basic kernels are weighted and fused into a fusion kernel, and the multi-kernel learning algorithm is used to calculate the best fusion weight of the basic kernel and the classification model of the support vector machine. Through the obtained fusion kernel, the trained support vector machine model is used to distinguish the category of the unknown category of gestures to realize gesture recognition. The invention combines the kernel function theory with a multi-core learning algorithm, realizes the fusion of image heterogeneous features, increases the generalization ability of the support vector machine for gesture recognition, and improves the recognition rate of recognizing multiple types of gestures.

Description

technical field [0001] The invention belongs to the field of image processing and pattern recognition, in particular to a gesture recognition method based on multi-core learning heterogeneous feature fusion. Background technique [0002] The human-computer interaction mode with the theme of harmony and nature has become the development trend of human-computer interaction technology in the future. Such technology has become a hot research issue in the world today. Gesture recognition is a new type of human-computer interaction technology. The static gesture recognition system based on computer vision has the advantages of being natural, intuitive, and easy to learn. Static gesture recognition mainly has the following applications: ① interaction in virtual environment; ② sign language recognition; ③ grasping of robot manipulators. Therefore, designing a simple, efficient, and easy-to-implement gesture recognition system has become a research hotspot for researchers in the fi...

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): G06K9/00
CPCG06V40/28G06F18/2411
Inventor 曹江涛余思泉李平
Owner LIAONING UNIVERSITY OF PETROLEUM AND CHEMICAL TECHNOLOGY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com