Stick figure recognition method based on convolutional neural fuzzy network

A fuzzy network and convolutional neural technology, which is applied in the field of deep learning and image recognition, can solve the problem of low recognition accuracy of stick figures, and achieve the effect of improving recognition accuracy, enhancing processing capacity, and improving recognition efficiency.

Pending Publication Date: 2020-06-23
GUANGDONG UNIV OF TECH
View PDF1 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to solve the problem of low accuracy of stick figure recognition in the prior art, the present invention proposes a stick figure recognition method based on convolutional neuro-fuzzy network

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
  • Stick figure recognition method based on convolutional neural fuzzy network
  • Stick figure recognition method based on convolutional neural fuzzy network
  • Stick figure recognition method based on convolutional neural fuzzy network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be further described below in conjunction with the accompanying drawings.

[0023] Such as figure 1 , a described method for recognizing stick figures based on a convolutional neuro-fuzzy network, wherein the convolutional neuro-fuzzy network is constructed based on a traditional convolutional neural network, consisting of some fuzzy convolutional layers and a fully connected layer, Each fuzzy convolution layer usually includes three steps of fuzzy convolution, nonlinear processing and pooling. The convolutional neural network can be mainly divided into three stages:

[0024] 1). Process the input data in the fuzzy layer to obtain fuzzy logic representation

[0025] Assuming X is an input matrix, each element in X is assigned a number of labels associated with the membership function. The fuzzy membership function calculates the membership of each input node to a specific fuzzy set. fuzzy set It is calculated by the fuzzy relationship ob...

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

In order to solve the problem that in the prior art, the stick figure recognition accuracy is low, the invention provides a stick figure recognition method based on a convolutional neural fuzzy network, and the method comprises the steps: carrying out the fuzzy processing of input data in a fuzzy convolution layer, calculating the membership degree of each input node to a specific fuzzy set through a fuzzy membership degree function, and obtaining a feature containing fuzzy logic; and inputting the features containing the fuzzy logic into a full-connection layer structure for classification, and finally identifying the stick figure corresponding to the input data. The recognition method based on the convolutional neural fuzzy network can well solve the problem that an existing recognitionmethod is low in recognition accuracy, and the recognition efficiency is effectively improved.

Description

technical field [0001] The invention relates to the technical field of deep learning and image recognition, in particular to a method for recognizing stick figures based on a convolutional neuro-fuzzy network. Background technique [0002] With the rapid development of Internet information technology and multimedia applications, massive picture information and data have emerged, and image recognition technology has gradually penetrated into various fields of daily life, such as target tracking, vehicle navigation, biomedicine, military and e-commerce etc., bring great convenience to our daily life and work. The stick figure is a relatively concise form of painting, which is simple and intuitive, and is also one of the main forms of human-computer interaction and network communication. [0003] Early recognition of stick figures mainly followed the traditional image classification model, that is, extracting corresponding manual features such as histogram of orientation gradi...

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): G06K9/62G06K9/46G06N3/04
CPCG06V10/40G06N3/045G06F18/24
Inventor 唐瑜祺孙为军邱耀儒
Owner GUANGDONG 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

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