Vision-based plate surface detecting method

A surface inspection and plate technology, which is applied in the field of vision-based plate surface inspection, can solve problems such as a large number of waste products, complex production processes, and visual fatigue of employees, so as to reduce the production cost of enterprises, improve production efficiency, and reduce the effect of personnel misjudgment.

Active Publication Date: 2018-11-16
SHANDONG IND TECH RES INST OF ZHEJIANG UNIV
View PDF20 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] At present, manual inspection is used in enterprises, and the surface condition of manual inspection depends on the subjective judgment of workers. Long-term observation may easily cause visual fatigue of employees, and problems cannot be found in time.
If the employees are not experienced enough, it is easy to cause misjudgment. Due to the complex production process, there is currently no perfect production theory system. It takes a long time to adjust the parameters and will generate a lot of waste products, which seriously affects the profit of the enterprise. Therefore, There is an urgent need for a better and more objective method for judging the extrusion status of the sheet surface

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
  • Vision-based plate surface detecting method
  • Vision-based plate surface detecting method
  • Vision-based plate surface detecting method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] Such as Figure 1 to Figure 6 As shown, a vision-based plate surface detection method includes the following steps:

[0051] 101) The step of obtaining the extrusion molding image: obtaining the original grayscale image of the foam sheet to be tested. That is, the camera is placed on the upper part of the foam board to be tested through an external mechanical frame, 1.5 meters away from the formed foam board, for image generation and acquisition.

[0052] 102) Image preprocessing step: perform bilateral filtering processing of non-linear filtering on the image obtained in step 101), so as to not only preserve the edge information of the image, but also achieve the effect of denoising. Bilateral filtering is a compromise process that combines the spatial proximity of the image and the similarity of pixel values. At the same time, it considers the spatial information and gray similarity, which can not only preserve the edge information of the image, but also achieve the ...

Embodiment 2

[0064] Such as figure 1 As shown, a vision-based plate surface detection method includes the following steps:

[0065] 101) The step of obtaining the extrusion molding image: the camera is placed on the upper part of the foam sheet to be tested through an external mechanical frame, 1 meter to 2 meters away from the formed foam sheet, and the image is generated to obtain the original grayscale image. Among them, the best distance from the foam board is 1.5 meters, because the detection at this position can not only cover the whole picture of the board, but also can see the surface information of the board to the greatest extent.

[0066] Its camera selection:

[0067] 1) Resolution calculation: The detection accuracy is set at 1mm. Since XPS boards are produced continuously, it is only necessary to set the width resolution. The width of the XPS board is 680mm, so the field of view of the camera is set to 750mm, so the resolution in the width direction is 750. In practical app...

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 vision-based plate surface detecting method comprising an extrusion forming image acquisition step, an image preprocessing step, a Canny edge detecting step, an expansion processing step, and a connected domain area qualified product determining step. The vision-based plate surface detecting method reduces enterprise production cost, improves production efficiency, and reduces misjudgment.

Description

technical field [0001] The invention relates to the field of surface detection, more specifically, it relates to a visual-based board surface detection method. Background technique [0002] Extruded polystyrene foam board, referred to as extruded board, also known as XPS board, has good heat insulation performance, no water absorption, good heat preservation, compression resistance, flame retardancy, light weight, etc., and is widely used in wall insulation Moisture-proof and thermal insulation in fields such as highways, airport runways, etc. [0003] The XPS board is made of polystyrene resin plus other auxiliary materials and polymers, heated and mixed while injecting a catalyst, and then extruded and pressed. The chemical reaction process is particularly sensitive to changes in temperature and pressure. Once a large change occurs It will cause uneven foaming of the XPS board, and the surface condition and three-dimensional size will have a large change. [0004] In man...

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): G01B11/24
CPCG01B11/24
Inventor 曹衍龙陈洪凯杨将新曹彦鹏
Owner SHANDONG IND TECH RES INST OF ZHEJIANG UNIV
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