On-line detecting method of machine vision system for printed calico flaw

A technology of machine vision system and detection method, which is applied to the inspection of textile materials, instruments, measuring devices, etc., can solve the problems of low product pass rate, inability to guarantee the quality of inspection, and high labor intensity, so as to improve accuracy and pass The effect of reducing the detection labor intensity and ensuring the accuracy

Inactive Publication Date: 2008-04-09
WUXI DONGWANG TECH
View PDF0 Cites 42 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Aiming at the problems that the online manual detection of calico defects in the prior art is labor-intensive and prone to visual fatigue, the inspection quality cannot be guaranteed and the product delivery rate is low, the present invention provides an online detection method for calico defects by a machine vision system , which greatly reduces the inspection labor intensity of workers, and the accuracy of defect detection is high, which can effectively guarantee the pass rate of ex-factory products

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
  • On-line detecting method of machine vision system for printed calico flaw
  • On-line detecting method of machine vision system for printed calico flaw

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] Example 1, detection of "misalignment" defects in calico images:

[0030] A. Adopt white cotton cloth, the image is as shown in Figure 1, as the detection example cloth.

[0031] B. Arrange 4 Xi'an Fangcheng 1300UM industrial cameras evenly along the horizontal direction of the calico, and fix them at a height of 1.5m. The cameras use 8mm COMPUTAR lenses, the aperture is adjusted to the maximum value, the exposure time is adjusted to 0.58ms, and the gain value (It determines the contrast effect of the image) Adjust to 0; use 2.65MHZ white light source, directly above the light, so that it is relatively insensitive to the color and pattern of the fabric, but sensitive to the light of the defect; the power supply of the display light source is a constant voltage Constant current is a stable light source without frequency variation or high frequency variation, so that clear and flawed images can be captured more stably and displayed on the computer screen.

[0032] C. The...

Embodiment 2

[0043] Example 2: Detection of "missing" defects in calico patterns:

[0044] The detection example cloth, photographing equipment and operation steps are the same as those in Example 1. Four Xi'an Fangcheng 1300UM cameras were evenly arranged horizontally along the calico and fixed at a height of 1.5m. The camera used an 8mm COMPUTAR lens, with the aperture set to 2 / 3, the exposure time set to 0.8ms, and the gain value set to 100 .

[0045] During the real-time shooting process, the dynamic automatic compensation of the light intensity of the standard image template and the correction of the pixel shift of the real-time captured image are also the same as those in Embodiment 1. The "missing" defect image of the calico pattern exceeding the precision requirements shown in Figure 3 was captured. The part within the dotted line area in Figure 3 is the missing area, and the computer screen shows that the area value of the "missing" defect in the image in Figure 3 is 20 square mi...

Embodiment 3

[0047] Example 3: Detection of "smudge" defects in calico patterns:

[0048] The detection example cloth, photographing equipment and operation steps are the same as those in Example 1. Four Xi'an Fangcheng 1300UM cameras were evenly arranged horizontally along the calico and fixed at a height of 1.5m. The camera used an 8mm COMPUTAR lens, the aperture was adjusted to 1 / 3 position, the exposure time was adjusted to 1ms, and the gain value was 50.

[0049] During the real-time shooting process, the dynamic automatic compensation of the light intensity of the standard image template and the correction of the pixel shift of the real-time captured image are also the same as those in Embodiment 1. The "smudge" defect image of the calico pattern exceeding the accuracy requirements shown in Figure 4 was obtained. The shaded part in Figure 4 is the stained area, the gray value of the image is 5, and the difference between the gray value of the image is 70, " The defect area of ​​"smu...

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 an online detecting method of a machine vision system for detecting blemishes of a printed cloth. The invention aims at solving the problem that the labor intensity of manual online detecting blemishes of the printed cloth is high, and the detecting quality is bad. Clear and thorough, and spotless graphs are shot on the running printed cloth through industrial camera. The clear and thorough, and spotless graphs are stored in the calculating machine as a standard graph molding board. The blemish area and graphic gray value are taken as the detecting parameter of the blemish. The precision scope of the detecting parameter is arranged according to the requirement of the consumer. The graphs of the running printed cloth are shot in real-time, and are conveyed to the calculating machine. The real-timely shot graphs are compared with the standard graph molding board and are dealt with. If a blemish appears, the operating personnel are indicated to deal with the blemish of the printed cloth through an alarm. The alarm is started through the calculating machine. The invention can carry out light intensity self-compensating of the standard graph molding board, and dynamically correcting the shift of the pixel of the real-timely shot printed cloth graphs. The invention has the advantages of high precision and fast speed of detecting blemishes of the printed cloth, and greatly reduced labor intensity of manual detecting.

Description

technical field [0001] The invention relates to the technical field of on-line detection by using a machine vision system, in particular to a method for on-line detection of defects of the calico by using a machine vision system at a printed cloth production site. Background technique [0002] In the production workshop of printing and dyeing calico in assembly line operation, the defects of calico need to be detected online. In the prior art, the on-line detection of calico defects relies on manual detection, and 2-4 people are arranged on both sides of the printing machine to visually inspect and process the defects of calico, and 1 person is arranged at the drying place to carry out inspection. Product quality tracking and testing. Its disadvantages include: high temperature and humidity on site, harsh working environment for workers, and high labor intensity; workers who work for a long time are prone to visual fatigue, and cannot guarantee the quality of inspection, so...

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): G01N21/898D06H3/00
Inventor 董仲伟庞彦清
Owner WUXI DONGWANG TECH
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