A Gesture Recognition Method Based on Optimal Projective Symmetry Approximate Sparse Classification

A technology of gesture recognition and sparse classification, which is applied in the field of OP-SYSRC robust gesture recognition algorithm based on big data, can solve the problems of low recognition rate and poor real-time performance of gesture recognition, and achieve improved classification effect, fast and accurate gesture recognition, stability, Effects that improve recognition and contrast performance

Active Publication Date: 2022-03-15
NORTHWESTERN POLYTECHNICAL UNIV
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Poor real-time performance and low recognition rate of gesture recognition for big data

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 Optimal Projective Symmetry Approximate Sparse Classification
  • A Gesture Recognition Method Based on Optimal Projective Symmetry Approximate Sparse Classification
  • A Gesture Recognition Method Based on Optimal Projective Symmetry Approximate Sparse Classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention proposes an OP-SYSRC robust gesture recognition algorithm based on big data, which mainly consists of three parts: technical features of gesture recognition, construction of OP-SYSRC algorithm, and model training / testing.

[0042] The method specifically includes steps as follows:

[0043] 1. Feature extraction for gesture recognition:

[0044] After collecting a lot of gesture image data, first of all, the gesture image needs to be normalized and corrected, which is an important part of gesture recognition. Its purpose is mainly to remove distracting information such as complex backgrounds in gesture images. The result of normalization correction directly affects the effect of subsequent feature extraction and classification recognition. This allows each image to contain only the characteristic regions of the gesture.

[0045] After the normalized gesture image is obtained, the POEM features of the image are extracted, and feature size reductio...

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 for approximating sparse classification by optimizing projection symmetry. First, the gesture images are normalized and corrected, gesture features are extracted, an OP-SYSRC algorithm is constructed, and then the Faster R-CNN algorithm for target recognition is adopted. Transfer learning is used to build a gesture recognition model. After the model performs the region selection and feature extraction procedures, the constructed OP‑SYSRC algorithm is added to train and test the model. In the big data gesture recognition environment, the recognition and contrast performance of gesture images under large database capacity are greatly improved, and the data scalability of the system is ensured.

Description

technical field [0001] The invention belongs to the field of image processing and computer vision, and in particular relates to a big data-based OP-SYSRC (Optimized Projective Symmetry Approximate Sparse Representation Classification) robust gesture recognition algorithm. Background technique [0002] The development and application of big data technology has promoted the rapid development of information technology in various fields, and a large amount of data is constantly updated to support various databases. If these data are put to good use, they will deliver a huge return in value. Gesture recognition has been widely used in personal authentication, video surveillance and human-computer interaction and other fields. At present, gesture recognition has been gradually applied to the work of commanding sign language in the military. The commander makes command gestures of the troops to the computer equipment, and the computer detects and understands the command gestures ...

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): G06V40/20G06V10/77G06V10/764G06K9/62
CPCG06V40/28G06F18/21345G06F18/241
Inventor 黄攀峰李沅澔董刚奇马志强陈路
Owner NORTHWESTERN POLYTECHNICAL 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