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

Waste mobile phone color identification method based on deep convolutional neural network

A technology of deep convolution and color recognition, applied in biological neural network models, neural architecture, character and pattern recognition, etc., to achieve the effect of accelerating the circulation process, improving efficiency, and reducing the difficulty of classification learning

Pending Publication Date: 2021-12-10
BEIJING UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention designs a mobile phone color recognition method based on a deep convolutional neural network, which mainly corrects the polarized light color in the machine inspection photos through the retinal color correction algorithm, and uses the deep convolutional neural network to realize fast and accurate recognition of the color of the used mobile phone; Solve the problem of color recognition in the recycling process of waste mobile phones, and improve the recycling efficiency of mobile phones

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
  • Waste mobile phone color identification method based on deep convolutional neural network
  • Waste mobile phone color identification method based on deep convolutional neural network
  • Waste mobile phone color identification method based on deep convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] A method for identifying the color of waste mobile phones based on a deep convolutional neural network, which realizes accurate identification of the color of mobile phones by designing a deep convolutional network structure, is characterized in that it includes the following steps:

[0042] (1) The input variables of the selection and mobile phone color recognition model are: the abscissa x of the pixel of the input image sample; the y coordinate of the pixel of the input image sample; the pixel (x, y) of the red channel pixel matrix of the input image sample pixel value i r (x, y); the pixel value i of the pixel point (x, y) in the green channel pixel matrix of the input image sample g (x, y); the pixel value i of the pixel point (x, y) in the blue channel pixel matrix of the input image sample b (x,y);

[0043] (2) Establish a hexagonal pyramid high-dimensional space color conversion model

[0044]

[0045]

[0046]

[0047] In the formula: α t+1 (x, y) ...

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 waste mobile phone color identification method based on a deep convolutional neural network. The problem that colors are difficult to accurately identify in the waste mobile phone recycling process is solved. According to the invention, a retina color correction algorithm is utilized to correct the polarized light color in the mobile phone inspection photo, and a deep convolutional neural network is constructed to realize rapid and accurate identification of the color of the waste mobile phone. The mobile phone color identification in different scenes can keep good rapidity and accuracy, and the waste mobile phone recycling efficiency and the economic benefits of recycling enterprises can be improved.

Description

technical field [0001] The present invention utilizes a color recognition method for waste mobile phones based on a deep convolutional neural network to realize accurate recognition of the color of mobile phones in the recycling process of waste mobile phones. In the process of recycling waste mobile phones, it is one of the important steps to classify mobile phones by color. There are many colors of mobile phone brands with high similarity, and the surface color of mobile phones is easily affected by factors such as polarization and occlusion, which has caused certain problems to the task of mobile phone color recognition. difficulty. Applying the color recognition method of used mobile phones based on convolutional neural network to the recycling process of used mobile phones can save labor costs and improve the accuracy and speed of recycling used mobile phones. It is an important branch in the field of image recognition and belongs to the treatment of solid waste. field. ...

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): G06K9/46G06K9/62G06N3/04G06T7/13G06T7/90G06F17/16
CPCG06T7/13G06T7/90G06F17/16G06N3/045G06F18/214Y02W30/82
Inventor 韩红桂甄晓玲杜永萍杨宏艳
Owner BEIJING UNIV OF TECH
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