CN111784691A - Textile flaw detection method - Google Patents
Textile flaw detection method Download PDFInfo
- Publication number
- CN111784691A CN111784691A CN202010727983.4A CN202010727983A CN111784691A CN 111784691 A CN111784691 A CN 111784691A CN 202010727983 A CN202010727983 A CN 202010727983A CN 111784691 A CN111784691 A CN 111784691A
- Authority
- CN
- China
- Prior art keywords
- feature data
- texture feature
- textile
- image
- product
- 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.)
- Pending
Links
- 239000004753 textile Substances 0.000 title claims abstract description 74
- 238000001514 detection method Methods 0.000 title claims abstract description 69
- 230000002950 deficient Effects 0.000 claims abstract description 38
- 238000000034 method Methods 0.000 claims abstract description 31
- 239000004744 fabric Substances 0.000 claims abstract description 16
- 238000004519 manufacturing process Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims description 14
- 230000007547 defect Effects 0.000 claims description 7
- 230000000737 periodic effect Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000000903 blocking effect Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000004075 alteration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/143—Segmentation; Edge detection involving probabilistic approaches, e.g. Markov random field [MRF] modelling
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30124—Fabrics; Textile; Paper
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a method for detecting textile flaws, which is characterized in that a textile to be detected is installed on a production machine, so that the textile is unfolded, two detection cameras are respectively arranged above the advancing direction of the textile detection, the spacing distance between the two detection cameras is set according to the advancing speed of cloth and the shooting time difference of the two detection cameras, so as to ensure that the two detection cameras can shoot the same area of the woven textile, the two detection cameras are respectively arranged above the advancing direction of the textile detection, the spacing distance between the two detection cameras can detect the produced textile twice according to the advancing speed of the cloth and the shooting time difference of the two detection cameras, and the quality of the textile is judged by comparing the threshold values of the defective area and the non-defective area which are measured before, so as to further improve the detection efficiency, and meanwhile, the error rate is reduced.
Description
Technical Field
The invention relates to the technical field of textile processing, in particular to a method for detecting textile flaws.
Background
The economic benefit of the textile is determined by the quality of the textile, the textile with excellent quality brings income, the defective goods with defects bring economic loss, and the traditional manual detection mode is to evaluate the quality of the textile according to the experience of detection personnel, the grade and evaluation of the textile and other standards. This approach has a low detection speed and a high miss rate, and therefore, it is necessary to develop a fast, accurate and unsupervised method for detecting textile defects. The types of fabrics for which textile defect detection is currently aimed can be divided into two categories: the first type is a textile which has a simple structure, does not contain complex patterns and is mostly pure color; the second type has more complex pattern information and the pattern has periodicity.
The existing flaw detection method cannot well detect the quality of produced textiles, the existing technology needs to train parameters of samples, the required time and the cost are extremely high, and the detection result is general, so that the method for detecting the flaws of the textiles is provided.
Disclosure of Invention
The present invention is directed to a method for detecting defects of textiles, so as to solve the problems mentioned in the background art.
In order to achieve the purpose, the invention provides the following technical scheme: a textile flaw detection method specifically comprises the following steps:
s1: the method comprises the following steps of installing a textile to be detected on a production machine, unfolding the textile, arranging two detection cameras above the advancing direction of textile detection, and setting the interval distance of the two detection cameras according to the advancing speed of the fabric and the shooting time difference of the two detection cameras to ensure that the two detection cameras can shoot the same area of the woven textile;
s2: the method comprises the steps that 100 groups of textile surface images with flaws in the moving process are captured through a detection camera, a computer processes textile images input with patterns to be detected, the size of a periodic template of the patterns is determined, the images are partitioned according to the size of the template to obtain image blocks to be corrected, the images obtain parameters through a Markov random field model, and the obtained parameters are normalized to obtain texture feature data of fabrics in the images;
s3: shooting a 100-grid combined textile surface image through a detection camera, processing the input qualified textile surface image by a computer, determining the size of a periodic template of a pattern, blocking the image according to the size of the template to obtain an image block to be corrected with the size of mxn, obtaining parameters of the image through a Markov random field model, and performing normalization processing on the obtained parameters to obtain texture feature data of a fabric in the image;
s4: respectively marking the texture characteristic data of the defective textile surface image and the qualified textile surface image in the motion process shot by the detection camera as a defective area and an imperfect area, and extracting the texture characteristic data of the defective area;
s5: the method comprises the steps that a clustering center of image texture feature data generated by shooting 100 groups of textile surface images with flaws in the moving process through a detection camera is used as intermediate data of corresponding flaw product texture feature data, the maximum value of the distance from the texture feature data of all the types of flaw product images to the intermediate data of the corresponding flaw product texture feature data is a corresponding flaw threshold value, 100 combined grid textile surface images are shot through the detection camera, extracted texture feature data is used as the clustering center of all qualified product image texture feature data and is qualified product texture feature data intermediate data, and the maximum value of the distance from the texture feature data of all the qualified product images to the intermediate data of the qualified product texture feature data is a qualified product threshold value;
s6: the method comprises the following steps that a first detection camera shoots the surface of a produced textile in the production process, because the distance between two detection cameras is according to the cloth advancing speed and the shooting time difference of the two detection cameras, an image shot by the first camera is processed by a computer and then is compared with texture feature data of a qualified product image for analysis, the product is judged to be qualified when the threshold value of the texture feature data of the shot image is not larger than the threshold value of the image processing feature data of the qualified product, if the threshold value of the texture feature data of the shot image is larger than the threshold value of the image processing feature data of the qualified product, the computer compares the threshold value of the texture feature data of the product with the threshold value of the texture feature data of a defective product, and if the comparison is not larger than the threshold value of the texture feature data of the defective product, the;
s7: and a subsequent computer starts a second detection camera to shoot the surface of the produced textile again, secondary judgment is carried out, the image shot by the second camera compares the texture feature data threshold of the product with the texture feature data threshold of the defective product again through the computer, if the comparison is not greater than the texture feature data threshold of the defective product, the defective product is judged, an alarm is used for alarming to remind a user of paying attention to the situation, if the image shot by the second camera compares the texture feature data threshold of the product with the texture feature data threshold of the defective product again through the computer, if the comparison is greater than the texture feature data threshold of the defective product, the defective product is judged, a new defect or a major problem occurs on the surface, the computer is directly stopped to alarm, and greater loss is avoided.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention detects the clustering center of image texture characteristic data generated by shooting 100 groups of textile surface images with flaws in the moving process by a camera, the clustering center is the middle data of the texture characteristic data of corresponding flaw products, the maximum value of the distance from the texture characteristic data of all the types of flaw product images to the middle data of the texture characteristic data of corresponding flaw products is the corresponding flaw threshold value, the maximum value of the distance from the texture characteristic data of all the qualified product images to the middle data of the texture characteristic data of the qualified products is the qualified product threshold value by shooting 100 groups of textile surface images by the detection camera, the extracted texture characteristic data is the clustering center of the texture characteristic data of all the qualified product images, the middle data of the texture characteristic data of the qualified products is the qualified product threshold value, the reference data can be provided for the subsequent textile processing conveniently, and problems can be found in advance, avoiding causing larger loss;
2. according to the invention, two detection cameras are respectively arranged above the advancing direction of textile detection, the interval distance between the two detection cameras can detect the produced textile twice according to the advancing speed of the cloth and the shooting time difference of the two detection cameras, and the quality of the textile is judged by comparing the threshold values of the defective area and the non-defective area which are measured before, so that the detection efficiency is further improved, and the error rate is reduced.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious 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 technical scheme that: a textile flaw detection method specifically comprises the following steps:
s1: the method comprises the following steps of installing a textile to be detected on a production machine, unfolding the textile, arranging two detection cameras above the advancing direction of textile detection, and setting the interval distance of the two detection cameras according to the advancing speed of the fabric and the shooting time difference of the two detection cameras to ensure that the two detection cameras can shoot the same area of the woven textile;
s2: the method comprises the steps that 100 groups of textile surface images with flaws in the moving process are captured through a detection camera, a computer processes textile images input with patterns to be detected, the size of a periodic template of the patterns is determined, the images are partitioned according to the size of the template to obtain image blocks to be corrected, the images obtain parameters through a Markov random field model, and the obtained parameters are normalized to obtain texture feature data of fabrics in the images;
s3: shooting a 100-grid combined textile surface image through a detection camera, processing the input qualified textile surface image by a computer, determining the size of a periodic template of a pattern, blocking the image according to the size of the template to obtain an image block to be corrected with the size of mxn, obtaining parameters of the image through a Markov random field model, and performing normalization processing on the obtained parameters to obtain texture feature data of a fabric in the image;
s4: respectively marking the texture characteristic data of the defective textile surface image and the qualified textile surface image in the motion process shot by the detection camera as a defective area and an imperfect area, and extracting the texture characteristic data of the defective area;
s5: the method comprises the steps that a clustering center of image texture feature data generated by shooting 100 groups of textile surface images with flaws in the moving process through a detection camera is used as intermediate data of corresponding flaw product texture feature data, the maximum value of the distance from the texture feature data of all the types of flaw product images to the intermediate data of the corresponding flaw product texture feature data is a corresponding flaw threshold value, 100 combined grid textile surface images are shot through the detection camera, extracted texture feature data is used as the clustering center of all qualified product image texture feature data and is qualified product texture feature data intermediate data, and the maximum value of the distance from the texture feature data of all the qualified product images to the intermediate data of the qualified product texture feature data is a qualified product threshold value;
s6: the method comprises the following steps that a first detection camera shoots the surface of a produced textile in the production process, because the distance between two detection cameras is according to the cloth advancing speed and the shooting time difference of the two detection cameras, an image shot by the first camera is processed by a computer and then is compared with texture feature data of a qualified product image for analysis, the product is judged to be qualified when the threshold value of the texture feature data of the shot image is not larger than the threshold value of the image processing feature data of the qualified product, if the threshold value of the texture feature data of the shot image is larger than the threshold value of the image processing feature data of the qualified product, the computer compares the threshold value of the texture feature data of the product with the threshold value of the texture feature data of a defective product, and if the comparison is not larger than the threshold value of the texture feature data of the defective product, the;
s7: and a subsequent computer starts a second detection camera to shoot the surface of the produced textile again, secondary judgment is carried out, the image shot by the second camera compares the texture feature data threshold of the product with the texture feature data threshold of the defective product again through the computer, if the comparison is not greater than the texture feature data threshold of the defective product, the defective product is judged, an alarm is used for alarming to remind a user of paying attention to the situation, if the image shot by the second camera compares the texture feature data threshold of the product with the texture feature data threshold of the defective product again through the computer, if the comparison is greater than the texture feature data threshold of the defective product, the defective product is judged, a new defect or a major problem occurs on the surface, the computer is directly stopped to alarm, and greater loss is avoided.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (1)
1. A textile flaw detection method is characterized by comprising the following steps: the method specifically comprises the following steps:
s1: the method comprises the following steps of installing a textile to be detected on a production machine, unfolding the textile, arranging two detection cameras above the advancing direction of textile detection, and setting the interval distance of the two detection cameras according to the advancing speed of the fabric and the shooting time difference of the two detection cameras to ensure that the two detection cameras can shoot the same area of the woven textile;
s2: the method comprises the steps that 100 groups of textile surface images with flaws in the moving process are captured through a detection camera, a computer processes textile images input with patterns to be detected, the size of a periodic template of the patterns is determined, the images are partitioned according to the size of the template to obtain image blocks to be corrected, the images obtain parameters through a Markov random field model, and the obtained parameters are normalized to obtain texture feature data of fabrics in the images;
s3: shooting a 100-grid combined textile surface image through a detection camera, processing the input qualified textile surface image by a computer, determining the size of a periodic template of a pattern, blocking the image according to the size of the template to obtain an image block to be corrected with the size of mxn, obtaining parameters of the image through a Markov random field model, and performing normalization processing on the obtained parameters to obtain texture feature data of a fabric in the image;
s4: respectively marking the texture characteristic data of the defective textile surface image and the qualified textile surface image in the motion process shot by the detection camera as a defective area and an imperfect area, and extracting the texture characteristic data of the defective area;
s5: the method comprises the steps that a clustering center of image texture feature data generated by shooting 100 groups of textile surface images with flaws in the moving process through a detection camera is used as intermediate data of corresponding flaw product texture feature data, the maximum value of the distance from the texture feature data of all the types of flaw product images to the intermediate data of the corresponding flaw product texture feature data is a corresponding flaw threshold value, 100 combined grid textile surface images are shot through the detection camera, extracted texture feature data is used as the clustering center of all qualified product image texture feature data and is qualified product texture feature data intermediate data, and the maximum value of the distance from the texture feature data of all the qualified product images to the intermediate data of the qualified product texture feature data is a qualified product threshold value;
s6: the method comprises the following steps that a first detection camera shoots the surface of a produced textile in the production process, because the distance between two detection cameras is according to the cloth advancing speed and the shooting time difference of the two detection cameras, an image shot by the first camera is processed by a computer and then is compared with texture feature data of a qualified product image for analysis, the product is judged to be qualified when the threshold value of the texture feature data of the shot image is not larger than the threshold value of the image processing feature data of the qualified product, if the threshold value of the texture feature data of the shot image is larger than the threshold value of the image processing feature data of the qualified product, the computer compares the threshold value of the texture feature data of the product with the threshold value of the texture feature data of a defective product, and if the comparison is not larger than the threshold value of the texture feature data of the defective product, the;
s7: and a subsequent computer starts a second detection camera to shoot the surface of the produced textile again, secondary judgment is carried out, the image shot by the second camera compares the texture feature data threshold of the product with the texture feature data threshold of the defective product again through the computer, if the comparison is not greater than the texture feature data threshold of the defective product, the defective product is judged, an alarm is used for alarming to remind a user of paying attention to the situation, if the image shot by the second camera compares the texture feature data threshold of the product with the texture feature data threshold of the defective product again through the computer, if the comparison is greater than the texture feature data threshold of the defective product, the defective product is judged, a new defect or a major problem occurs on the surface, the computer is directly stopped to alarm, and greater loss is avoided.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010727983.4A CN111784691A (en) | 2020-07-27 | 2020-07-27 | Textile flaw detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010727983.4A CN111784691A (en) | 2020-07-27 | 2020-07-27 | Textile flaw detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111784691A true CN111784691A (en) | 2020-10-16 |
Family
ID=72763556
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010727983.4A Pending CN111784691A (en) | 2020-07-27 | 2020-07-27 | Textile flaw detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111784691A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114324354A (en) * | 2021-12-29 | 2022-04-12 | 杭州信畅信息科技有限公司 | Textile flaw detection method based on machine vision template |
CN115201211A (en) * | 2022-09-15 | 2022-10-18 | 江苏牛掌柜科技有限公司 | Quality control method and system for intelligent visual textile product |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103529051A (en) * | 2013-11-01 | 2014-01-22 | 南通大学 | Method for automatic on-line detection of detects of woven textile |
CN107895363A (en) * | 2017-10-31 | 2018-04-10 | 常州大学 | Textile flaw detection method based on template characteristic |
CN107966444A (en) * | 2017-10-12 | 2018-04-27 | 常州信息职业技术学院 | Textile flaw detection method based on template |
-
2020
- 2020-07-27 CN CN202010727983.4A patent/CN111784691A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103529051A (en) * | 2013-11-01 | 2014-01-22 | 南通大学 | Method for automatic on-line detection of detects of woven textile |
CN104949990A (en) * | 2013-11-01 | 2015-09-30 | 南通大学 | Online detecting method suitable for defects of woven textiles |
CN107966444A (en) * | 2017-10-12 | 2018-04-27 | 常州信息职业技术学院 | Textile flaw detection method based on template |
CN107895363A (en) * | 2017-10-31 | 2018-04-10 | 常州大学 | Textile flaw detection method based on template characteristic |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114324354A (en) * | 2021-12-29 | 2022-04-12 | 杭州信畅信息科技有限公司 | Textile flaw detection method based on machine vision template |
CN115201211A (en) * | 2022-09-15 | 2022-10-18 | 江苏牛掌柜科技有限公司 | Quality control method and system for intelligent visual textile product |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhu et al. | Yarn-dyed fabric defect detection based on autocorrelation function and GLCM | |
CN103529051B (en) | A kind of Woven textiles flaw automatic on-line detection method | |
CN105894036B (en) | A kind of characteristics of image template matching method applied to mobile phone screen defects detection | |
CN111784691A (en) | Textile flaw detection method | |
CN108364291A (en) | Grey cloth rapid detection method based on computer vision technique | |
CN107966444B (en) | Textile flaw detection method based on template | |
CN111861996A (en) | Printed fabric defect detection method | |
CN102331425A (en) | Textile defect detection method based on defect enhancement | |
WO2022021774A1 (en) | Online detection method for circular weft knitting horizontal stripe defects based on grayscale gradient method | |
CN115100206A (en) | Printing defect identification method for textile with periodic pattern | |
CN104568956A (en) | Machine vision based detection method for strip steel surface defects | |
CN104240252A (en) | Detecting Algorithm for cracks of surface of high-temperature billet of machine vision bar | |
CN110458809B (en) | Yarn evenness detection method based on sub-pixel edge detection | |
Divyadevi et al. | Survey of automated fabric inspection in textile industries | |
CN114693652B (en) | Fabric Defect Detection Method Based on Gaussian Mixture Model | |
CN111402225B (en) | Cloth folding false-detection defect discriminating method | |
CN110940676B (en) | Flaw detection method and system based on cylindrical loom | |
CN115311264B (en) | Fabric flaw line defect identification method for textile production | |
CN115082460B (en) | Weaving production line quality monitoring method and system | |
CN115294100A (en) | Loom parking control method and system based on data processing | |
CN116482125A (en) | Cloth defect processing method based on machine vision | |
CN110672635A (en) | Cloth defect detection device and real-time detection method | |
CN115839958A (en) | Garment flaw detection method | |
CN113516628A (en) | Sizing yarn reed collision detection method based on machine vision | |
CN113920112A (en) | Fabric flaw detection method based on independent classification type feature extraction |
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 |