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

Fiberboard quality classification method based on machine vision

A quality classification and machine vision technology, applied in the direction of instruments, image analysis, computer parts, etc., can solve the problems of threshold segmentation to obtain the fiberboard surface, no defect direction, and morphological feature analysis, so as to improve the timeliness of repair, The effect of reducing labor intensity and accurate test results

Inactive Publication Date: 2022-05-06
泗阳富艺木业股份有限公司
View PDF0 Cites 39 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The invention provides a fiberboard quality classification method based on machine vision to solve the problem that the direction and morphological features of defects are not analyzed when judging or classifying defects, which makes it difficult to directly pass The problem of obtaining the defects on the surface of fiberboard by threshold segmentation

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
  • Fiberboard quality classification method based on machine vision
  • Fiberboard quality classification method based on machine vision
  • Fiberboard quality classification method based on machine vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053]A kind of embodiment of the fiberboard quality classification method based on machine vision of the present invention, as figure 1 shown, including:

[0054] S101. Obtaining a grayscale image of the surface of the fiberboard

[0055] Use machine vision to collect the surface image of the fiberboard, perform semantic segmentation on the collected image to remove background interference, and then multiply the image after semantic segmentation with the collected image and perform grayscale processing to facilitate subsequent operations on the features in the image extraction and analysis.

[0056] S102. Obtain the sliding window area corresponding to each pixel

[0057] Taking each pixel in the grayscale image of the fiberboard surface as the center, the sliding window processing is performed to obtain the sliding window area corresponding to each pixel. The gray value difference of the pixel points of the same fiber in the defective fiberboard is small, so the pixel Poi...

Embodiment 2

[0073] A kind of embodiment of the fiberboard quality classification method based on machine vision of the present invention, as figure 2 shown, including:

[0074] S201. Obtain a grayscale image of the fiberboard surface

[0075] Use machine vision to collect the surface image of the fiberboard, perform semantic segmentation on the collected image to remove background interference, and then multiply the image after semantic segmentation with the collected image and perform grayscale processing to facilitate subsequent operations on the features in the image extraction and analysis.

[0076] Arrange the camera, collect the image of the fiberboard, and use DNN semantic segmentation to identify and segment the target area in the image. The specific process is as follows:

[0077] 1) The data set used is a product image data set collected from a top view, and the styles of fiberboards are various.

[0078] 2) The pixels that need to be segmented are divided into two categorie...

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 relates to the field of artificial intelligence, in particular to a fiberboard quality classification method based on machine vision. The method includes: acquiring a fiberboard surface grayscale image; performing sliding window processing on the grey-scale map on the surface of the fiberboard to obtain a plurality of sliding window areas; calculating the smoothness of a central pixel point of the sliding window; taking the pixel point corresponding to the minimum smoothness as a target pixel point, and obtaining a plurality of target connected domains; obtaining gradient amplitudes of pixel points in each target connected domain to construct a corresponding gradient histogram, calculating the probability that each target connected domain is a defect area, and determining all defect areas; calculating the probability of each gray value as a standard gray value, and determining the standard gray value; and calculating the quality coefficient of the fiberboard according to the gray average value of each defect area, and classifying the quality of the fiberboard. By analyzing the glossiness of the surface image of the fiberboard, the defect that the spatial domain feature is not obvious can be detected, so that the detection result is more accurate, and the product classification accuracy and the repair timeliness are improved; and the production efficiency is effectively improved.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a method for classifying fiberboard quality based on machine vision. Background technique [0002] When producing fiberboard, it needs to be sliced, cooked, separated from the fibers, dried, and then applied with urea-formaldehyde resin or other suitable adhesives, and then made by hot pressing. [0003] In the production process, the raw materials are not good, the cooking time is too short, the feeding amount is too large or the feeding amount is uneven, etc., which will cause the board surface to be rough and affect the subsequent processing. [0004] In the traditional detection of fiberboard surface defects, the detection and screening are usually carried out by manual observation. This method is inefficient and costly, and the detection effect is easily affected by the state of the staff. In order to improve the detection efficiency, the method of machine vision will ...

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): G06T7/00G06T7/187G06K9/62G06T5/40G06V10/764
CPCG06T7/0004G06T7/187G06T5/40G06F18/24
Inventor 谢正富
Owner 泗阳富艺木业股份有限公司
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