CN112288734A - Printed fabric surface defect detection method based on image processing - Google Patents
Printed fabric surface defect detection method based on image processing Download PDFInfo
- Publication number
- CN112288734A CN112288734A CN202011232463.2A CN202011232463A CN112288734A CN 112288734 A CN112288734 A CN 112288734A CN 202011232463 A CN202011232463 A CN 202011232463A CN 112288734 A CN112288734 A CN 112288734A
- Authority
- CN
- China
- Prior art keywords
- image
- detected
- cloth
- point
- pixel
- 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
- 239000004744 fabric Substances 0.000 title claims abstract description 54
- 230000007547 defect Effects 0.000 title claims abstract description 26
- 238000001514 detection method Methods 0.000 title claims abstract description 18
- 230000009466 transformation Effects 0.000 claims abstract description 11
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims abstract description 8
- 230000011218 segmentation Effects 0.000 claims abstract description 6
- 230000002457 bidirectional effect Effects 0.000 claims abstract description 3
- 239000011159 matrix material Substances 0.000 claims description 18
- 238000000034 method Methods 0.000 claims description 17
- 238000001914 filtration Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000002699 waste material Substances 0.000 description 2
- 235000002566 Capsicum Nutrition 0.000 description 1
- 239000006002 Pepper Substances 0.000 description 1
- 235000016761 Piper aduncum Nutrition 0.000 description 1
- 235000017804 Piper guineense Nutrition 0.000 description 1
- 244000203593 Piper nigrum Species 0.000 description 1
- 235000008184 Piper nigrum Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 230000037303 wrinkles Effects 0.000 description 1
Images
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
-
- G06T3/147—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
- G06T7/337—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving reference images or patches
-
- 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
Abstract
The invention discloses a printed fabric surface defect detection method based on image processing, which comprises the steps of collecting a template image and a cloth image to be detected, carrying out the same pretreatment on the images, calculating SURF characteristics of the images, and determining characteristic points; performing bidirectional feature point matching by taking the cloth image to be detected as a template image and taking the template image as a reference image to obtain feature point information after registration, and performing affine transformation, image registration and image difference, and extracting a difference region in the image to obtain a difference image; and carrying out threshold segmentation, opening operation and connected domain marking operation on the difference image to obtain an image marked with defects. The detection method solves the problems of non-uniform detection standard and low accuracy in the existing defect detection method.
Description
Technical Field
The invention belongs to the technical field of digital printing, and particularly relates to a printed fabric surface defect detection method based on image processing.
Background
The defects of dot and strip patterns of printed patterns can be caused by faults of nozzle blockage, nozzle ink leakage, cloth wrinkles, motor stepping deviation and the like in the production process of the printed cloth. In the batch printing process, if faults are not discovered and eliminated in time, a large amount of defective products are produced, and unnecessary resource waste is caused. At present, although each machine is provided with corresponding detection personnel, the labor cost is high, the detection standards are not unified, human eyes can be tired due to long-time work, and the actual detection effect is poor. Due to the limitation of human physiological factors, the accuracy of the register cannot be accurately and objectively detected. Machine vision is a technology for measuring and judging by replacing human eyes with a machine, can replace manual monitoring and detection, and has the advantages of high speed, long working time, high measuring precision and the like.
Disclosure of Invention
The invention aims to provide a printed fabric surface defect detection method based on image processing, and solves the problems of non-uniform detection standard and low accuracy in the existing defect detection method.
The technical scheme adopted by the invention is that the printed fabric surface defect detection method based on image processing is implemented according to the following steps:
step 1, acquiring a template image and acquiring a cloth image to be detected;
step 2, carrying out the same pretreatment on the template image and the cloth image to be detected;
step 3, calculating SURF characteristics of the template image preprocessed in the step 2 and the cloth image to be detected, and determining characteristic points;
step 4, according to the characteristic points determined in the step 3, respectively taking the cloth image to be detected processed in the step 2 as a template image and the template image processed in the step 2 as a reference image, performing bidirectional matching on the characteristic points, and acquiring the registered characteristic point information;
step 5, carrying out affine transformation according to the registered feature point information obtained in the step 4, and registering the image;
step 6, carrying out image difference according to the registration image in the step 5, and extracting a difference region in the image to obtain a difference image;
and 7, performing threshold segmentation, opening operation and connected domain marking operation on the difference image obtained in the step 6 to obtain an image with marked defects.
The present invention is also characterized in that,
the preprocessing in the step 2 comprises graying, brightness adjustment and image blurring to realize de-texturing.
The graying specifically comprises the following steps:
(1) calculating the RGB components of each pixel point of the template image and the cloth image to be detected through an OpenCV function;
(2) calculating a weighted gray value: 0.3 XB +0.59 XG +0.11 XR;
(3) assigning the weighted gray value calculated in the step (2) to each corresponding pixel point in the step (1);
the expression for adjusting the brightness is:
g(i,j)＝αf(i,j)+β (1)
in the formula (1), g (i, j) is a pixel after adjustment, f (i, j) is a pixel before adjustment, alpha is greater than 0, beta is a gain variable, and i and j are coordinates of a certain pixel point in the acquired template image and the cloth image to be detected;
image blurring is performed by adopting a Laplacian operator to realize de-texturing, and the expression is as follows:
sharpened_pixel＝5×current-left-right-up-down (2)。
the specific process of the step 3 is as follows:
step 3.1, performing gaussian filtering operation on the template image preprocessed in the step 2 and the cloth image to be detected to obtain a filtered image g (σ), constructing a hessian matrix of each pixel point in the template image preprocessed in the step 2 and the cloth image to be detected according to the filtered image g (σ), and when the scale is σ, setting a blackson matrix of the pixel point X ═ X, y as follows:
wherein L isxxThe second derivative of the filtered image g (sigma) in the x direction; l isxyThe second derivative of the filtered image g (sigma) in the x and y directions; l isyyFor the filtered image g (sigma) in the y-directionThe second derivative of (a);
step 3.2, det (H) according to the discriminantapprox)＝LxxLyy-(0.9Lxy)2Calculating the value of the Hessian matrix, judging whether the pixel point is a characteristic point according to the positive and negative values of the Hessian matrix, and if the value of the Hessian matrix is positive, taking the pixel point as the characteristic point;
step 3.3, constructing an image pyramid according to the scale;
and 3.4, comparing the size of the feature point determined in the step 3.2 with 26 points of the three-dimensional field in which the feature point is located in the fields of different scale spaces according to the image pyramid constructed in the step 3.3, and if the interest point is the point with the maximum feature value in the neighborhood, determining the interest point as the feature point in the neighborhood.
The affine expression in step 5 is:
in the formulas (4) and (5), (m, n) are coordinates of pixel points before transformation of the preprocessed cloth image to be detected, (m ', n') are coordinates of pixel points after transformation of the preprocessed cloth image to be detected, and dm、dnThe translation amount is a, b are rotation parameters, and c, d are stretching parameters.
In step 7, the threshold value selected for threshold value segmentation is 42, and the open operation uses a structural matrix with a unit structure of 6 × 6.
The invention has the beneficial effects that: the printed fabric surface defect detection method based on image processing can effectively and timely detect the defects of the cloth, improves the production efficiency, reduces the waste of the cloth, reduces the probability of secondary processing, improves the automation degree of a production line, and can take proper improvement measures according to the defect types.
Drawings
FIG. 1 is a flow chart of a method for detecting surface defects of a printed fabric according to the present invention;
FIG. 2 is a schematic view of affine transformation in the method for detecting surface defects of printed fabrics.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
The invention relates to a printed fabric surface defect detection method based on image processing, which is implemented according to the following steps:
step 1, acquiring a template image and acquiring a cloth image to be detected;
step 2, carrying out the same pretreatment on the template image and the cloth image to be detected, specifically comprising graying, brightness adjustment and image blurring to realize de-texturing;
the graying specifically comprises the following steps:
(1) calculating the RGB components of each pixel point of the template image and the cloth image to be detected through an OpenCV function;
(2) calculating a weighted gray value: 0.3 XB +0.59 XG +0.11 XR;
(3) assigning the weighted gray value calculated in the step (2) to each corresponding pixel point in the step (1);
the expression for adjusting the brightness is as follows:
g(i,j)＝αf(i,j)+β (1)
in the formula (1), g (i, j) is a pixel after adjustment, f (i, j) is a pixel before adjustment, alpha is greater than 0, beta is a gain variable, and i and j are coordinates of a certain pixel point in the acquired template image and the cloth image to be detected;
the image blurring is carried out by adopting a Laplacian operator to realize de-texturing, and the expression is as follows:
sharpened_pixel＝5×current-left-right-up-down (2)；
the method comprises the steps of image cutting and image denoising, wherein a proper filtering method needs to be selected according to the type of image noise, and because salt and pepper noise or particle noise generated in a factory environment is common noise, median filtering and mean filtering are commonly selected;
step 3, calculating SURF characteristics of the template image preprocessed in the step 2 and the cloth image to be detected, and determining characteristic points, wherein the specific process is as follows:
step 3.1, performing gaussian filtering operation on the template image preprocessed in the step 2 and the cloth image to be detected to obtain a filtered image g (σ), constructing a hessian matrix of each pixel point in the template image preprocessed in the step 2 and the cloth image to be detected according to the filtered image g (σ), and when the scale is σ, setting a blackson matrix of the pixel point X ═ X, y as follows:
wherein L isxxThe second derivative of the filtered image g (sigma) in the x direction; l isxyThe second derivative of the filtered image g (sigma) in the x and y directions; l isyyThe second derivative of the filtered image g (sigma) in the y direction;
step 3.2, det (H) according to the discriminantapprox)＝LxxLyy-(0.9Lxy)2Calculating the value of the Hessian matrix, judging whether the pixel point is a characteristic point according to the positive and negative values of the Hessian matrix, and if the value of the Hessian matrix is positive, taking the pixel point as the characteristic point;
3.3, constructing an image pyramid according to the scale, wherein the total number of points in the three-dimensional field is 27;
step 3.4, determining the characteristic points by a three-dimensional linear interpolation method, specifically: and (3) comparing the size of the feature point determined in the step (3.2) with the size of 26 points in the three-dimensional field in which the feature point is located in the field of the space with different scales according to the image pyramid constructed in the step (3.3), and if the interest point is the point with the maximum feature value in the neighborhood, determining the interest point as the feature point in the region.
Step 4, according to a two-way uniqueness criterion, respectively taking the cloth image to be detected processed in the step 2 as a template image and the template image processed in the step 2 as a reference image, performing two-way matching on feature points, and acquiring feature point information after registration;
step 5, acquiring the registered feature point information according to the step 4, and performing affine transformation by using a least square method to register an image;
wherein, the expression of affine is:
in the formulas (4) and (5), (m, n) are coordinates of pixel points before transformation of the preprocessed cloth image to be detected, (m ', n') are coordinates of pixel points after transformation of the preprocessed cloth image to be detected, and dm、dnThe translation amount is a, b is a rotation parameter, and c and d are stretching parameters;
step 6, carrying out image difference by adopting a difference method according to the registration image in the step 5, and extracting a difference region in the image to obtain a difference image;
the difference image method is that the difference information between two images is extracted by means of difference of image gray values, the image information of the printed matter is extracted by image segmentation after the template image is registered with the cloth image to be detected, then the template image is differenced with the cloth image to be detected, and the differenced difference is the shape defect;
step 7, performing threshold segmentation, opening operation and connected domain marking operation on the difference image obtained in the step 6 to obtain an image with marked defects;
wherein, the threshold value for the threshold value division is 42, and the open operation uses the structure matrix with the unit structure of 6 multiplied by 6.
Claims (6)
1. A printed fabric surface defect detection method based on image processing is characterized by comprising the following steps:
step 1, acquiring a template image and acquiring a cloth image to be detected;
step 2, carrying out the same pretreatment on the template image and the cloth image to be detected;
step 3, calculating SURF characteristics of the template image preprocessed in the step 2 and the cloth image to be detected, and determining characteristic points;
step 4, according to the characteristic points determined in the step 3, respectively taking the cloth image to be detected processed in the step 2 as a template image and the template image processed in the step 2 as a reference image, performing bidirectional matching on the characteristic points, and acquiring the registered characteristic point information;
step 5, carrying out affine transformation according to the registered feature point information obtained in the step 4, and registering the image;
step 6, carrying out image difference according to the registration image in the step 5, and extracting a difference region in the image to obtain a difference image;
and 7, performing threshold segmentation, opening operation and connected domain marking operation on the difference image obtained in the step 6 to obtain an image with marked defects.
2. The method for detecting the surface defects of the printed fabric based on the image processing as claimed in claim 1, wherein the preprocessing in the step 2 comprises graying, brightness adjustment, image blurring and de-texturing.
3. The method for detecting the surface defects of the printed fabric based on the image processing as claimed in claim 2, wherein the graying is specifically as follows:
(1) calculating the RGB components of each pixel point of the template image and the cloth image to be detected through an OpenCV function;
(2) calculating a weighted gray value: 0.3 XB +0.59 XG +0.11 XR;
(3) assigning the weighted gray value calculated in the step (2) to each corresponding pixel point in the step (1);
the expression for adjusting the brightness is as follows:
g(i,j)＝αf(i,j)+β (1)
in the formula (1), g (i, j) is a pixel after adjustment, f (i, j) is a pixel before adjustment, alpha is greater than 0, beta is a gain variable, and i and j are coordinates of a certain pixel point in the acquired template image and the cloth image to be detected;
the image blurring is carried out by adopting a Laplacian operator to realize de-texturing, and the expression is as follows:
sharpened_pixel＝5×current-left-right-up-down (2)。
4. the method for detecting the surface defects of the printed fabric based on the image processing as claimed in claim 1, wherein the specific process of the step 3 is as follows:
step 3.1, performing gaussian filtering operation on the template image preprocessed in the step 2 and the cloth image to be detected to obtain a filtered image g (σ), constructing a hessian matrix of each pixel point in the template image preprocessed in the step 2 and the cloth image to be detected according to the filtered image g (σ), and when the scale is σ, setting a blackson matrix of the pixel point X ═ X, y as follows:
wherein L isxxThe second derivative of the filtered image g (sigma) in the x direction; l isxyThe second derivative of the filtered image g (sigma) in the x and y directions; l isyyThe second derivative of the filtered image g (sigma) in the y direction;
step 3.2, det (H) according to the discriminantapprox)＝LxxLyy-(0.9Lxy)2Calculating the value of the Hessian matrix, judging whether the pixel point is a characteristic point according to the positive and negative values of the Hessian matrix, and if the value of the Hessian matrix is positive, taking the pixel point as the characteristic point;
step 3.3, constructing an image pyramid according to the scale;
and 3.4, comparing the size of the feature point determined in the step 3.2 with 26 points of the three-dimensional field in which the feature point is located in the fields of different scale spaces according to the image pyramid constructed in the step 3.3, and if the interest point is the point with the maximum feature value in the neighborhood, determining the interest point as the feature point in the neighborhood.
5. The method for detecting the surface defects of the printed fabric based on the image processing as claimed in claim 1, wherein the affine expression in the step 5 is as follows:
in the formulas (4) and (5), (m, n) are coordinates of pixel points before transformation of the preprocessed cloth image to be detected, (m ', n') are coordinates of pixel points after transformation of the preprocessed cloth image to be detected, and dm、dnThe translation amount is a, b are rotation parameters, and c, d are stretching parameters.
6. The method for detecting the surface defects of the printed fabric based on the image processing as claimed in claim 1, wherein the threshold value selected for the threshold value segmentation in the step 7 is 42, and the open operation uses a structure matrix with a unit structure of 6 x 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011232463.2A CN112288734A (en) | 2020-11-06 | 2020-11-06 | Printed fabric surface defect detection method based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011232463.2A CN112288734A (en) | 2020-11-06 | 2020-11-06 | Printed fabric surface defect detection method based on image processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112288734A true CN112288734A (en) | 2021-01-29 |
Family
ID=74352112
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011232463.2A Pending CN112288734A (en) | 2020-11-06 | 2020-11-06 | Printed fabric surface defect detection method based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112288734A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113470788A (en) * | 2021-07-08 | 2021-10-01 | 山东志盈医学科技有限公司 | Synchronous browsing method and device for multiple digital slices |
| CN113592831A (en) * | 2021-08-05 | 2021-11-02 | 北京方正印捷数码技术有限公司 | Method and device for detecting printing error and storage medium |
| CN113658176A (en) * | 2021-09-07 | 2021-11-16 | 重庆科技学院 | Ceramic tile surface defect detection method based on interactive attention and convolutional neural network |
| CN114565607A (en) * | 2022-04-01 | 2022-05-31 | 南通沐沐兴晨纺织品有限公司 | Fabric defect image segmentation method based on neural network |
| CN116109839A (en) * | 2023-02-15 | 2023-05-12 | 北京拙河科技有限公司 | Picture difference comparison method and device |
| CN116309573A (en) * | 2023-05-19 | 2023-06-23 | 成都工业学院 | Defect detection method for printed characters of milk packaging box |
| CN117670872A (en) * | 2024-01-29 | 2024-03-08 | 江苏恒力化纤股份有限公司 | Quick identification method for patterns of bobbin paper tube |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0742431A1 (en) * | 1995-05-10 | 1996-11-13 | Mahlo GmbH & Co. KG | Method and apparatus for detecting flaws in moving fabrics or the like |
| CN105160654A (en) * | 2015-07-09 | 2015-12-16 | 浙江工商大学 | Towel label defect detecting method based on feature point extraction |
| CN106600600A (en) * | 2016-12-26 | 2017-04-26 | 华南理工大学 | Wafer defect detection method based on characteristic matching |
| CN109934802A (en) * | 2019-02-02 | 2019-06-25 | 浙江工业大学 | A kind of Fabric Defects Inspection detection method based on Fourier transformation and morphological image |
| WO2019134327A1 (en) * | 2018-01-03 | 2019-07-11 | 东北大学 | Facial expression recognition feature extraction method employing edge detection and sift |
| CN110503633A (en) * | 2019-07-29 | 2019-11-26 | 西安理工大学 | A kind of applique ceramic disk detection method of surface flaw based on image difference |
| CN111028213A (en) * | 2019-12-04 | 2020-04-17 | 北大方正集团有限公司 | Image defect detection method and device, electronic equipment and storage medium |
| CN111861996A (en) * | 2020-06-23 | 2020-10-30 | 西安工程大学 | Printed fabric defect detection method |
-
2020
- 2020-11-06 CN CN202011232463.2A patent/CN112288734A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0742431A1 (en) * | 1995-05-10 | 1996-11-13 | Mahlo GmbH & Co. KG | Method and apparatus for detecting flaws in moving fabrics or the like |
| CN105160654A (en) * | 2015-07-09 | 2015-12-16 | 浙江工商大学 | Towel label defect detecting method based on feature point extraction |
| CN106600600A (en) * | 2016-12-26 | 2017-04-26 | 华南理工大学 | Wafer defect detection method based on characteristic matching |
| WO2019134327A1 (en) * | 2018-01-03 | 2019-07-11 | 东北大学 | Facial expression recognition feature extraction method employing edge detection and sift |
| CN109934802A (en) * | 2019-02-02 | 2019-06-25 | 浙江工业大学 | A kind of Fabric Defects Inspection detection method based on Fourier transformation and morphological image |
| CN110503633A (en) * | 2019-07-29 | 2019-11-26 | 西安理工大学 | A kind of applique ceramic disk detection method of surface flaw based on image difference |
| CN111028213A (en) * | 2019-12-04 | 2020-04-17 | 北大方正集团有限公司 | Image defect detection method and device, electronic equipment and storage medium |
| CN111861996A (en) * | 2020-06-23 | 2020-10-30 | 西安工程大学 | Printed fabric defect detection method |
Non-Patent Citations (3)
| Title |
|---|
| 张培 等: "一种仿射变换的印刷品缺陷检测方法", 《东华大学学报（自然科学版）》 * |
| 徐足骋 等: "基于视觉的印刷品缺陷检测技术", 《重庆理工大学学报(自然科学)》 * |
| 黄春凤 等: "改进的SURF算法在图像匹配中的应用", 《现代电子技术》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113470788A (en) * | 2021-07-08 | 2021-10-01 | 山东志盈医学科技有限公司 | Synchronous browsing method and device for multiple digital slices |
| CN113470788B (en) * | 2021-07-08 | 2023-11-24 | 山东志盈医学科技有限公司 | Synchronous browsing method and device for multiple digital slices |
| CN113592831A (en) * | 2021-08-05 | 2021-11-02 | 北京方正印捷数码技术有限公司 | Method and device for detecting printing error and storage medium |
| CN113592831B (en) * | 2021-08-05 | 2024-03-19 | 北京方正印捷数码技术有限公司 | Printing error detection method, device and storage medium |
| CN113658176A (en) * | 2021-09-07 | 2021-11-16 | 重庆科技学院 | Ceramic tile surface defect detection method based on interactive attention and convolutional neural network |
| CN113658176B (en) * | 2021-09-07 | 2023-11-07 | 重庆科技学院 | Ceramic tile surface defect detection method based on interaction attention and convolutional neural network |
| CN114565607A (en) * | 2022-04-01 | 2022-05-31 | 南通沐沐兴晨纺织品有限公司 | Fabric defect image segmentation method based on neural network |
| CN116109839A (en) * | 2023-02-15 | 2023-05-12 | 北京拙河科技有限公司 | Picture difference comparison method and device |
| CN116309573A (en) * | 2023-05-19 | 2023-06-23 | 成都工业学院 | Defect detection method for printed characters of milk packaging box |
| CN116309573B (en) * | 2023-05-19 | 2023-07-25 | 成都工业学院 | Defect detection method for printed characters of milk packaging box |
| CN117670872A (en) * | 2024-01-29 | 2024-03-08 | 江苏恒力化纤股份有限公司 | Quick identification method for patterns of bobbin paper tube |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112288734A (en) | Printed fabric surface defect detection method based on image processing | |
| CN105067638B (en) | Tire fetal membrane face character defect inspection method based on machine vision | |
| CN101799434B (en) | Printing image defect detection method | |
| CN111539935B (en) | Online cable surface defect detection method based on machine vision | |
| CN106204610A (en) | Peg-in-hole assembly automatic centering system based on image procossing | |
| CN111126391B (en) | Printed character defect positioning method | |
| CN107749057B (en) | Method for detecting appearance slurry leakage defect of solar cell | |
| CN109685766A (en) | A kind of Fabric Defect detection method based on region fusion feature | |
| CN102496161A (en) | Method for extracting contour of image of printed circuit board (PCB) | |
| CN110348461A (en) | A kind of Surface Flaw feature extracting method | |
| CN112489042A (en) | Metal product printing defect and surface damage detection method based on super-resolution reconstruction | |
| CN115131353B (en) | Flat screen printing textile production abnormity identification and positioning method and system | |
| CN114279357A (en) | Die casting burr size measurement method and system based on machine vision | |
| CN105300302A (en) | Diameter measurement method for Brinell hardness indent circle | |
| CN111882549A (en) | Automatic detection and identification method and system for grayish green small foreign fibers | |
| CN107516309B (en) | Visual inspection method for defects of printing panel | |
| CN116880353A (en) | Machine tool setting method based on two-point gap | |
| Jiang | Defect features recognition in 3D industrial CT images | |
| CN110033469A (en) | A kind of sub-pixel edge detection method and system | |
| CN109886912A (en) | A kind of thrust bearing retainer detection method of surface flaw | |
| Chong et al. | Fabric Defect Detection Method Based on Projection Location and Superpixel Segmentation | |
| Zhang et al. | Edge detection of printed matter based on improved Canny operator | |
| CN112785574A (en) | Scarf pattern defect detection method based on improved YOLOv3 | |
| CN111798429B (en) | Visual inspection method for defects of printed matter | |
| Zou et al. | A visual detection method of tile surface defects based on spatial-frequency domain image enhancement and region growing |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210129 |