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

Recycling bottle classification method based on deep learning model

A deep learning and classification method technology, applied in the field of computer vision, can solve the problems of poor recycling environment, high false detection rate, and low efficiency, and achieve the effect of accurate model recognition, good model accuracy, and reduced workload

Pending Publication Date: 2020-12-01
FOSHAN NANHAI GUANGDONG TECH UNIV CNC EQUIP COOP INNOVATION INST +1
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, due to the huge amount of garbage, and the small number of people in the garbage recycling industry, most of them are not young and middle-aged, the recycling environment is poor, manual sorting and processing, the efficiency is low, and the false detection rate is high

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
  • Recycling bottle classification method based on deep learning model
  • Recycling bottle classification method based on deep learning model
  • Recycling bottle classification method based on deep learning model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] Below, in conjunction with accompanying drawing and specific embodiment, the present invention is described further:

[0035] as attached figure 1 As shown, a kind of recycling bottle classification method based on deep learning model provided by the present invention comprises the following steps:

[0036] S01: Acquire recycled bottle images, label and define categories for each recycled bottle image, and form a training image dataset, a verification image dataset, and a test image dataset. The recycled bottles in the present invention can be, but not limited to, various types of recyclable plastic bottles. Specifically, the following steps may be included:

[0037] S011: Use industrial cameras to take videos of recycled bottles on the conveyor belt;

[0038] S012: Use opencv (image processing library) to extract the image of the same frame interval in the video to obtain the recycled bottle image. The image at this time is the original image data. On this basis, th...

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 discloses a recycling bottle classification method based on a deep learning model, and the method comprises the following steps: S01, obtaining recycling bottle images, carrying out themarking and category definition of each recycling bottle image, and forming a training image data set, a verification image data set and a test image data set; S02, establishing a deep learning model,and training the deep learning model by adopting the training image data set; S03, verifying and testing the trained deep learning model by adopting the verification image data set and the test imagedata set, and returning to the step S02 to continue deep learning model training if a verification or test result does not reach a set value; if the verification or test result reaches a set value, obtaining a prediction model; and S04, loading the prediction model in a recovery device, and enabling the output result of the prediction model to control the manipulator to classify the recovered bottles. The invention provides a recovery bottle classification method based on a deep learning model, which is used for improving the identification and recovery efficiency of recovery bottles.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a recycling bottle classification method based on a deep learning model. Background technique [0002] As my country's emphasis on ecological protection and environmental sanitation continues to increase, the recycling of garbage is becoming more and more standardized and industrialized. In the process of garbage recycling, it is hoped that the efficiency of garbage recycling will be improved. Therefore, the intelligent garbage disposal and recycling industry is rapidly developing. develop. Use automated equipment to share part of the work of manual sorting of garbage, so as to improve recycling efficiency and quality. [0003] Among them, automation equipment involves the fields of deep learning, computer vision and image processing. At present, due to the huge amount of garbage and the small number of people in the garbage recycling industry, most of them are not young and middl...

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): G06K9/00G06K9/62G06N3/04B07C5/12B07C5/342
CPCB07C5/122B07C5/3422G06V20/40G06N3/045G06F18/214
Inventor 杨海东李俊宇黄坤山彭文瑜林玉山
Owner FOSHAN NANHAI GUANGDONG TECH UNIV CNC EQUIP COOP INNOVATION INST
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