Unlock instant, AI-driven research and patent intelligence for your innovation.

Paper tube defect detection method and device, electronic equipment and storage medium

A defect detection and defect technology, applied in the field of image processing, can solve problems such as poor accuracy, achieve the effect of improving accuracy, reducing complexity, and avoiding blurred classification

Pending Publication Date: 2021-02-05
ゼジャンハーレイテクノロジーカンパニーリミテッド
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present invention provides a paper tube defect detection method, device, electronic equipment and storage medium to solve the problem of poor accuracy in determining the type of paper tube defects in the prior art

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
  • Paper tube defect detection method and device, electronic equipment and storage medium
  • Paper tube defect detection method and device, electronic equipment and storage medium
  • Paper tube defect detection method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] figure 1 The schematic diagram of the paper tube defect detection process provided by the embodiment of the present invention includes the following process:

[0050] S101: Acquiring a side image and a top image of the paper tube.

[0051]S102: Input the side image into the pre-trained first detection model, perform defect detection on the side image based on the first detection model, and output the first defect area and the first defect category in the side image .

[0052] S103: Input the top image into the pre-trained second detection model, perform defect detection on the top image based on the second detection model, and output the second defect area and the second defect area in the top image. defect category.

[0053] The paper tube defect detection method provided by the embodiment of the present invention is applied to an electronic device, and the electronic device may be a PC, a tablet computer, or the like.

[0054] The side image and the top image of t...

Embodiment 2

[0058] Because paper tube defects intersect in space, in the above embodiment, after the first defect area is determined based on the first detection model, and the second defect area is determined based on the second detection model, the same type of defect area will appear In the case of multiple detection frames, the detection result is very unattractive. In order to make the detection result more intuitive and clear, in the embodiment of the present invention, the method further includes:

[0059] A preset algorithm is used to perform fusion processing on the first defect regions with intersections of the same category and the second defect regions with intersections of the same category respectively.

[0060] In the embodiment of the present invention, defect detection is performed on the side image based on the first detection model, and after outputting the first defect area and the first defect category in the side image, the first defect area is divided according to di...

Embodiment 3

[0063] On the basis of the above-mentioned embodiments, in the embodiment of the present invention, the detection model sequentially includes a residual network structure, a positioning layer and a classification layer;

[0064] Defect detection is performed on the image based on the detection model, and the defect areas and defect categories in the output image include:

[0065] Based on the residual network structure, the image is convolved to obtain a feature image; based on the positioning layer, the position information of the defect area in the feature image is determined; based on the classification layer, it is determined that the defect area corresponds to category of defects.

[0066] The first detection model and the second detection model in the embodiment of the present invention have the same structure, including a residual network structure, a positioning layer and a classification layer. The difference between the first detection model and the second detection ...

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 paper tube defect detection method and device, electronic equipment and a storage medium, and the method comprises the steps: training two models in advance during paper tubedefect detection, i.e., a first detection model for detecting the side defects of a paper tube and a second detection model for detecting the top defects of the paper tube, in this way, during modeltraining, training the first detection model based on the side sample images, and training the second detection model based on the top surface sample images. The complexity of the first detection model and the second detection model is reduced. Besides, the first detection model only detects the defects and the corresponding categories of the side images, and the second detection model only detects the defects and the corresponding categories of the top images, so that the problem of fuzzy classification of the defect categories is avoided, and the accuracy of determining the defect categoriesis improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a paper tube defect detection method, device, electronic equipment and storage medium. Background technique [0002] After the manufacturer produces the paper tube product, or when the user uses the paper tube product, it is generally necessary to perform defect detection on the paper tube. In the existing technology, products with trip wires are generally detected by manual observation. On the one hand, manual inspection has low detection efficiency and consumes a lot of human resources. lower. [0003] With the rapid development of machine vision, a solution for detecting paper tube defects based on machine vision has appeared in the prior art. The top image and side image of the paper tube are collected, and for each image, the exhaustive method is used to traverse the image to obtain each candidate area, and then each candidate area is compared with the pre-saved n...

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): G06T7/00
CPCG06T7/0004G06T2207/10004G06T2207/20081G06T2207/20084
Inventor 朱辉李晶周璐
Owner ゼジャンハーレイテクノロジーカンパニーリミテッド
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com