Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Gesture image segmentation and recognition method and device based on deep learning

An image segmentation and deep learning technology, applied in the fields of computer vision and human-computer interaction, can solve the problem of low recognition rate of gesture images and achieve good overall performance, good gesture recognition effect, and accurate gesture segmentation results

Active Publication Date: 2021-12-10
HEBEI UNIVERSITY
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a gesture image segmentation and recognition method and device based on deep learning to solve the problem of low recognition rate of gesture images in complex backgrounds in existing methods

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 image segmentation and recognition method and device based on deep learning
  • Gesture image segmentation and recognition method and device based on deep learning
  • Gesture image segmentation and recognition method and device based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The gesture image segmentation and recognition method based on deep learning provided by the present invention generally includes the following three steps:

[0053] Step 1: Perform a resize (resize operation) on all gesture images under complex backgrounds to make their image sizes fixed.

[0054] Step 2: Input the resized gesture image under the complex background into the dense segmentation network to train the dense segmentation network, and output the trained dense segmentation network model. Finally, the trained dense segmentation network model is used to output binarized gesture images.

[0055] Step 3: Input the gesture image segmented in step 2 into the gesture recognition network, use gesture images of different gesture shapes to train the gesture recognition network, and output the trained gesture recognition network model. Use this network model to classify each different gesture and realize gesture image recognition.

[0056] Due to the variability of ges...

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 provides a gesture image segmentation and recognition method and device based on deep learning. According to the method, firstly, a gesture image is preprocessed, so that the size of the image is fixed; secondly, in a complex background, a dense segmentation network is used for densely connecting hole convolution with different hole rates to obtain gesture multi-scale information on different visual fields, so that the accuracy of feature expression is improved; besides, in order to fuse details and spatial position information on different levels and improve the segmentation performance of the whole network, the dense segmentation network adopts an encoder-decoder structure, redundant background information is removed, and accurate segmentation of the gesture image is realized; and finally, the mask image which only retains the gesture image is inputted into a gesture recognition network, and recognition is conducted by adopting an improved algorithm. The segmentation performance of the gesture image can be improved, so that the recognition rate of the gesture image is improved.

Description

technical field [0001] The present invention relates to the fields of human-computer interaction and computer vision, in particular to a deep learning-based gesture image segmentation and recognition method and device. Background technique [0002] Gesture interaction based on gesture recognition is one of the basic interaction methods in the field of human-computer interaction, and it is one of the key research directions in the fields of machine vision and computer applications. Gesture recognition has a wide range of applications in fields such as drone gimbals, AR (Augmented Reality), VR (Virtual Reality), and has strong advantages in various environments, such as non-contact environments, noisy or quiet environments etc., so how to increase the robustness and performance of gesture recognition is very important. [0003] At present, gesture interaction methods are mainly divided into two types: sensor-based and vision-based. For gesture recognition based on sensing de...

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): G06K9/00G06K9/34G06K9/38G06K9/62G06N3/04G06N3/08G06T7/11G06F3/01
CPCG06T7/11G06N3/084G06F3/017G06T2207/20081G06T2207/20084G06T2207/20132G06T2207/30196G06N3/045G06F18/241G06F18/214Y02T10/40
Inventor 崔振超雷玉齐静杨文柱
Owner HEBEI UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com