CN108896561B - Textile fabric detection method based on multi-thread machine vision - Google Patents
Textile fabric detection method based on multi-thread machine vision Download PDFInfo
- Publication number
- CN108896561B CN108896561B CN201810746728.7A CN201810746728A CN108896561B CN 108896561 B CN108896561 B CN 108896561B CN 201810746728 A CN201810746728 A CN 201810746728A CN 108896561 B CN108896561 B CN 108896561B
- Authority
- CN
- China
- Prior art keywords
- distance
- value
- standard
- area
- reference value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Abstract
The invention relates to a detection method of a textile sewing cloth, which comprises the following steps: setting a standard value of the distance between two standard adjacent sewing hole positions and setting a standard value of the area of the standard sewing hole positions; acquiring an image by using a CCD camera, and converting the acquired image into pixel data; gray value processing is carried out on the obtained pixel data, hole positions on the textile fabric are displayed as bright spots, and the coordinate value of each bright spot is recorded; measuring the distance between two adjacent bright color spots, comparing the distance with a distance reference value, and judging that the printing is missed if the distance is greater than the distance reference value; comparing the area of the bright color spots with an area reference value, and if the area is smaller than the area reference value, judging the hole site jumper; and fourthly, transmitting the processed result to a computer, and controlling a sorting mechanism by the computer to push the jumper wire products and the neglected beating products into the area to be detected. The invention solves the problem of detecting cloth skip line or miss line by manual naked eyes, and has high working efficiency and high accuracy.
Description
Technical Field
The invention relates to the technical field of machine vision, in particular to a detection method of textile fabric.
Background
Whether the detection method of the detection of the jumper wire in the cloth weaving sewing process is manual detection, the cloth has the risk of the jumper wire due to external reasons after being sewn, the service life of the product is shortened due to the reasons in the using process, and the effect is poor. After the production of the products is finished, special detection personnel can detect the batch of products by naked eyes, the detection times in one day are about tens of thousands of times, the detection efficiency is very low, the misjudgment rate is high, and the production benefits and public praise of enterprises are badly influenced. Therefore, it is desirable to provide an automatic jumper detection device to solve such a problem.
Disclosure of Invention
Whether the detection method that whether cloth weaving in-process was jumped or missed and beaten detects the detection method that uses at present is artifical the detection, and the cloth has the risk of jumper or missed and beaten because of external reason after the sewing, can lead to product life to reduce because of this reason in the use, and the effect worsens. In order to solve the problems, the invention provides a textile fabric detection method with high detection efficiency and good detection effect, and in order to achieve the purpose, the invention adopts the following technical scheme: a textile fabric detection method based on multi-thread machine vision comprises the following steps:
the method comprises the following steps: setting a standard value of the distance between two standard adjacent sewing hole positions, and setting a standard value of the area of a standard sewing hole position;
step two: collecting images by using a CCD camera, and converting the collected images into pixel data by using a computer;
step three: gray value processing is carried out on the pixel data obtained in the step two, hole positions on the textile fabric are displayed as bright spots, and the coordinate value of each bright spot is recorded;
step four: sequentially sorting the bright color spots in the third step from left to right in the X-axis direction, measuring the distance between two adjacent bright color spots, comparing the distance with a distance reference value, and judging that the bright color spots are missed to be printed if the distance is greater than the distance reference value; comparing the area of the bright color spots in the step three with an area reference value, and if the area is smaller than the area reference value, judging the hole site jumper;
step five: and fourthly, transmitting the processed result to a computer, and controlling a sorting mechanism by the computer to push the jumper wire products and the neglected beating products into the area to be detected.
Preferably, the method further comprises saving the jumper/skip printing pictures after the step five.
Preferably, the gray value processing includes the steps of:
(1) selecting a standard value of the bright spots of the standard sewing hole and setting a threshold value;
(2) carrying out difference calculation on the gray value of the pixel data and the reference value of the bright color spots of the standard sewing hole positions, selecting pixel points with absolute values smaller than the threshold value from the obtained difference calculation result, and displaying the pixel points as the bright color spots;
(3) and (3) setting a gain value for the image obtained by the processing in the step (2) to improve the contrast.
Preferably, the gray reference value is a gray value within a range, and the gain value is 2 times.
Preferably, the threshold value is 10 to 30.
Preferably, the exposure of the lens of the CCD camera is adjusted to the maximum when the CCD camera collects an image.
Preferably, the method further comprises the steps of setting a standard position point on the machine tool, setting a standard distance between the CCD camera and the standard position point, setting a camera to detect the distance between the CCD camera and the standard position point, and automatically correcting by the computer control execution element when the distance is inconsistent with the standard distance.
The technical scheme adopted by the invention solves the problem of detecting cloth skip line or miss line by manual naked eyes, and has high working efficiency and high accuracy.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to specific embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a textile fabric detection method with high detection efficiency and good detection effect, and in order to achieve the purpose, the invention adopts the following technical scheme: a textile fabric detection method based on multi-thread machine vision comprises the following steps:
the method comprises the following steps: setting a standard value of the distance between two standard adjacent sewing hole positions, and setting a standard value of the area of a standard sewing hole position;
step two: collecting images by using a CCD camera, and converting the collected images into pixel data by using a computer;
step three: gray value processing is carried out on the pixel data obtained in the step two, hole positions on the textile fabric are displayed as bright spots, and the coordinate value of each bright spot is recorded;
step four: sequentially sorting the bright color spots in the third step from left to right in the X-axis direction, measuring the distance between two adjacent bright color spots, comparing the distance with a distance reference value, and judging that the bright color spots are missed to be printed if the distance is greater than the distance reference value; comparing the area of the bright color spots in the step three with an area reference value, and if the area is smaller than the area reference value, judging the hole site jumper;
step five: and fourthly, transmitting the processed result to a computer, and controlling a sorting mechanism by the computer to push the jumper wire products and the neglected beating products into the area to be detected.
Preferably, the method further comprises saving the jumper/skip printing pictures after the step five.
Preferably, the gray value processing includes the steps of:
(1) selecting a standard value of the bright spots of the standard sewing hole and setting a threshold value;
(2) carrying out difference calculation on the gray value of the pixel data and the reference value of the bright color spots of the standard sewing hole positions, selecting pixel points with absolute values smaller than the threshold value from the obtained difference calculation result, and displaying the pixel points as the bright color spots;
(3) and (3) setting a gain value for the image obtained by the processing in the step (2) to improve the contrast.
Preferably, the gray reference value is a gray value within a range, and the gain value is 2 times.
Preferably, the threshold value is 10 to 30.
Preferably, the exposure of the lens of the CCD camera is adjusted to the maximum when the CCD camera collects an image.
Preferably, the method further comprises the steps of setting a standard position point on the machine tool, setting a standard distance between the CCD camera and the standard position point, setting a camera to detect the distance between the CCD camera and the standard position point, and automatically correcting by the computer control execution element when the distance is inconsistent with the standard distance.
The technical scheme adopted by the invention solves the problem of detecting cloth skip line or miss line by manual naked eyes, and has high working efficiency and high accuracy.
Claims (7)
1. A textile cloth detection method based on multi-thread machine vision is characterized by comprising the following steps:
the method comprises the following steps: setting a standard value of the distance between two standard adjacent sewing hole positions, and setting a standard value of the area of a standard sewing hole position;
step two: collecting images by using a CCD camera, and converting the collected images into pixel data by using a computer;
step three: gray value processing is carried out on the pixel data obtained in the step two, hole positions on the textile fabric are displayed as bright spots, and the coordinate value of each bright spot is recorded;
step four: sequentially sorting the bright color spots in the third step from left to right in the X-axis direction, measuring the distance between two adjacent bright color spots, comparing the distance with a distance reference value, and judging that the bright color spots are missed to be printed if the distance is greater than the distance reference value; comparing the area of the bright color spots in the step three with an area reference value, and if the area is smaller than the area reference value, judging the hole site jumper;
step five: and fourthly, transmitting the processed result to a computer, and controlling a sorting mechanism by the computer to push the jumper wire products and the neglected beating products into the area to be detected.
2. The method for detecting textile fabric based on multi-thread machine vision according to claim 1, characterized by further comprising saving jumper/skip printing pictures after the fifth step.
3. A method of detecting textile cloth based on multi-thread machine vision as claimed in claim 1, characterized in that said grey value processing comprises the following steps: selecting a gray level reference value of the bright color spots of a standard sewing hole, and setting a threshold value; carrying out difference calculation on the gray value of the pixel data and the gray reference value of the bright color spots of the standard sewing hole positions, selecting pixel points with absolute values smaller than the threshold value from the obtained difference calculation result, and displaying the pixel points as the bright color spots; and setting a gain value for the image obtained by the processing in the step two, and improving the contrast.
4. A method as claimed in claim 3, wherein the grey scale reference value is a grey scale value in the range of 0-255, and the gain value is 2 times.
5. A method of detecting textile fabric based on multi-thread machine vision as claimed in claim 3, wherein said threshold value is 10-30.
6. The method as claimed in claim 1, wherein the exposure of the lens of the CCD camera is adjusted to the maximum when the CCD camera collects the image.
7. The method of claim 1, further comprising setting a standard position point on the machine tool, setting a standard distance between the CCD camera and the standard position point, setting a camera to detect the distance between the CCD camera and the standard position point, wherein the distance is not consistent with the standard distance and is automatically corrected by the computer control executing element.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810746728.7A CN108896561B (en) | 2018-07-09 | 2018-07-09 | Textile fabric detection method based on multi-thread machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810746728.7A CN108896561B (en) | 2018-07-09 | 2018-07-09 | Textile fabric detection method based on multi-thread machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108896561A CN108896561A (en) | 2018-11-27 |
| CN108896561B true CN108896561B (en) | 2021-04-06 |
Family
ID=64348785
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810746728.7A Active CN108896561B (en) | 2018-07-09 | 2018-07-09 | Textile fabric detection method based on multi-thread machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108896561B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110067089B (en) * | 2019-04-28 | 2020-12-22 | 季华实验室 | Detection unit for detecting sewing quality of fabric |
| CN115588010B (en) * | 2022-12-09 | 2023-06-02 | 滨州华然化纤绳网有限公司 | Surface defect detection method for non-woven fabric |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002088641A (en) * | 2000-09-13 | 2002-03-27 | Toyota Central Res & Dev Lab Inc | Woven fabric inspector |
| JP2008020321A (en) * | 2006-07-13 | 2008-01-31 | Purex:Kk | Flaw cloth piece detector with flaw marking device |
| CN101387493B (en) * | 2008-07-10 | 2010-09-08 | 长春理工大学 | Shape and position dimension non-contact photoelectric detection method for pylon component hole |
| CN107016664B (en) * | 2017-01-18 | 2019-08-30 | 华侨大学 | A kind of bad needle flaw detection method of large circle machine |
| CN107328775B (en) * | 2017-06-23 | 2020-12-01 | 广东小天才科技有限公司 | Abnormity detection method and device for screw installation of automatic screw machine |
| CN107328793B (en) * | 2017-06-30 | 2019-12-03 | 航天新长征大道科技有限公司 | A kind of jewelry surface word print flaw detection method and device based on machine vision |
-
2018
- 2018-07-09 CN CN201810746728.7A patent/CN108896561B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN108896561A (en) | 2018-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109239076B (en) | Sewing stitch defect detection method based on machine vision | |
| CN108896561B (en) | Textile fabric detection method based on multi-thread machine vision | |
| US9076037B2 (en) | Image processing apparatus and method | |
| CN102930266B (en) | Method for locating Mark points on PCB (printed circuit board) by utilizing outline gravity center method | |
| CN109872309B (en) | Detection system, method, device and computer readable storage medium | |
| CN103134809A (en) | Welded line defect detection method | |
| JPH04240261A (en) | Image-recognition apparatus and pattern-machining and cutting appapratus | |
| CN108890692A (en) | A kind of material color identification method for industrial robot vision's sorting | |
| CN109324056B (en) | Sewing thread trace measuring method based on machine vision | |
| CN111524101A (en) | Electronic screen defect detection method based on machine vision technology | |
| CN108871185B (en) | Method, device and equipment for detecting parts and computer readable storage medium | |
| CN108315852B (en) | Spinning machine threading method and device | |
| CN110413122B (en) | AR (augmented reality) glasses application method and system with working scene recognition function | |
| CN111337509A (en) | Textile fabric surface flaw detection device, detection system and detection method thereof | |
| CN108972556B (en) | Wire grabbing system and method in complex illumination environment on micro special motor production line | |
| CN112080829B (en) | Binding yarn detection image system | |
| CN115471504B (en) | Automatic thread end identification method based on textile fabric | |
| CN108986093B (en) | Method for detecting screen blocking defects of rotary screen or flat screen printing machine based on machine vision | |
| CN110672209A (en) | Online detection method for warp knitting cloth color difference | |
| CN107413679A (en) | A kind of intelligent ore dressing device and method based on machine vision technique | |
| CN212459435U (en) | Textile fabric surface flaw detection device | |
| CN113450405B (en) | Method for positioning cylindrical part and hooking grapple of yard crane | |
| CN108664588A (en) | Automatic method for online detection and control of cloth skewing | |
| JP2013246149A (en) | Work position detection device and work position detection method | |
| RU2672966C1 (en) | Method of visual observation and control of mechanical processing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |