CN115588010A - Surface defect detection method for non-woven fabric - Google Patents
Surface defect detection method for non-woven fabric Download PDFInfo
- Publication number
- CN115588010A CN115588010A CN202211575610.5A CN202211575610A CN115588010A CN 115588010 A CN115588010 A CN 115588010A CN 202211575610 A CN202211575610 A CN 202211575610A CN 115588010 A CN115588010 A CN 115588010A
- Authority
- CN
- China
- Prior art keywords
- detected
- gray
- region
- area
- obtaining
- 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.)
- Granted
Links
- 239000004745 nonwoven fabric Substances 0.000 title claims abstract description 37
- 230000007547 defect Effects 0.000 title claims abstract description 18
- 238000001514 detection method Methods 0.000 title abstract description 8
- 238000000034 method Methods 0.000 claims abstract description 30
- 230000008859 change Effects 0.000 claims abstract description 26
- 239000011159 matrix material Substances 0.000 claims abstract description 20
- 238000003708 edge detection Methods 0.000 claims abstract description 12
- 239000013598 vector Substances 0.000 claims description 8
- 239000000126 substance Substances 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 2
- 238000009826 distribution Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000005098 hot rolling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 229920000642 polymer Polymers 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013519 translation Methods 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration by the use of histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention relates to the technical field of image data processing, in particular to a surface defect detection method for non-woven fabrics. The method comprises the following steps: acquiring a target gray image of the surface of the non-woven fabric; performing edge detection on the target gray level image to obtain each to-be-detected area corresponding to the target gray level image; obtaining gray diversity degree, perimeter and Hu moment of the edge to be detected according to each region to be detected; obtaining a gray scale change index corresponding to each region to be detected according to the adjacent gray scale difference matrix; obtaining fractal characteristic indexes of the areas to be detected by using a fractal dimension box; and judging whether each area to be detected is a stain area or not according to the perimeter, the Hu moment, the gray diversity degree, the gray variation index and the fractal characteristic index of each area to be detected. The invention can quickly and accurately identify the stain area on the surface of the non-woven fabric.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to a surface defect detection method for non-woven fabrics.
Background
The non-woven fabric is a non-woven fabric which is formed by directly utilizing high polymer slices, short fibers or filaments to form a net through air flow or machinery, then carrying out spunlace, needling or hot rolling reinforcement, and finally carrying out after-treatment. Due to various factors, when the printing is small and frequent, stains close to the printing patterns appear on the surface, the stains can be difficult to identify, but when the stains exist on the surface of the non-woven fabric, the subsequent use of the non-woven fabric is influenced, and therefore the stain detection of the non-woven fabric is very important.
At present, the method for identifying and detecting stains on the non-woven fabric is generally realized by machine vision, and because the outlines of printed patterns are changeable, the method mostly utilizes various printed templates to be matched with an area to be detected, and judges whether the printed patterns are the stains area or not based on a matching result.
Disclosure of Invention
The invention provides a method for detecting surface defects of non-woven fabrics, which is used for solving the problem that the defect detection efficiency of the non-woven fabrics by the existing method is lower, and the adopted technical scheme is as follows:
the embodiment of the invention provides a surface defect detection method for non-woven fabrics, which comprises the following steps:
acquiring a target gray image of the surface of the non-woven fabric;
performing edge detection on the target gray level image to obtain each to-be-detected area corresponding to the target gray level image; obtaining gray diversity degree, perimeter and Hu moment of the edge to be detected according to each region to be detected;
obtaining a gray scale change index corresponding to each region to be detected according to the adjacent gray scale difference matrix;
obtaining fractal characteristic indexes of the areas to be detected by using a fractal dimension box;
and judging whether each area to be detected is a stain area or not according to the perimeter, the Hu moment, the gray scale diversity degree, the gray scale change index and the fractal characteristic index of each area to be detected.
Preferably, the method for performing edge detection on the target gray-scale image to obtain each to-be-detected region corresponding to the target gray-scale image includes:
performing edge extraction on the target gray level image by using Canny edge detection to obtain edge pixel points on the target gray level image;
and analyzing the connected domains of the edge pixel points to obtain each connected domain, and recording as a to-be-detected region.
Preferably, obtaining the gray-scale diversity degree of the edge to be detected according to each region to be detected includes:
acquiring a gray level histogram corresponding to each to-be-detected area;
counting the number of gray values with frequency not being 0 on each gray histogram;
for any region to be detected, calculating the gray diversity degree of each region to be detected according to the following formula:
in the formula, S is the number of gray values with the frequency number of not 0 on the gray histogram corresponding to the region to be detected.
Preferably, the method for obtaining the gray scale change index corresponding to each region to be detected according to the adjacent gray scale difference matrix includes:
traversing each region to be detected by using an adjacent gray level difference matrix to obtain the gray level difference absolute value of each pixel point and the adjacent pixel point in each region to be detected;
for any region to be detected, calculating the gray scale change index of the region to be detected according to the following formula:
wherein the content of the first and second substances,
is the gray scale change index of the area to be detected,
the total number of types of gray values in the region to be detected,
is the area to be detectedThe number of pixels with a medium gray scale value of u,
and summing the gray difference absolute values of all the pixel points with the gray value u and the adjacent pixel points in the region to be detected.
Preferably, the sum of the absolute value of the gray difference between all the pixel points with the gray value u and the adjacent pixel points in the area to be detected is calculated according to the following formula:
wherein, the first and the second end of the pipe are connected with each other,
i and j are respectively an abscissa value and an ordinate value of the mth pixel point, x and y are constants,
is a horizontal coordinate value of
The ordinate value is
The gray value of the pixel point.
Preferably, the method for obtaining the fractal characteristic index of each region to be detected by using the fractal dimension box comprises the following steps:
acquiring a three-dimensional gray curved surface of a target surface gray image;
covering the gray curved surface by using a fractal dimension box;
for any region to be detected, calculating the fractal characteristic index of the region to be detected according to the following formula:
wherein the content of the first and second substances,
is the fractal characteristic index of the region to be detected,
for the side length of the box of fractal dimension,
and covering the acquired three-dimensional gray curved surface for the fractal dimension box to obtain the number of boxes.
Preferably, the method for judging whether each area to be detected is a stain area according to the perimeter, the Hu moment, the gray diversity degree, the gray variation index and the fractal characteristic index of each area to be detected comprises the following steps:
constructing and obtaining a feature vector corresponding to each region to be detected according to the perimeter, the Hu moment, the gray diversity degree, the gray variation index and the fractal feature index of each region to be detected;
and inputting the feature vectors corresponding to the areas to be detected into a trained support vector machine, and judging the areas to be detected with the output results of the stain areas as the areas where the stains are located.
Has the advantages that: firstly, acquiring a target gray level image of the surface of a non-woven fabric; performing edge detection on the target gray level image to obtain each to-be-detected area corresponding to the target gray level image; obtaining the gray-scale diversity degree and the perimeter of the edge to be detected according to each region to be detected; secondly, obtaining gray scale change indexes corresponding to the to-be-detected areas according to the adjacent gray scale difference matrix; then, a fractal dimension box is utilized to obtain fractal characteristic indexes of each to-be-detected area; and finally, judging whether each area to be detected is a stain area or not according to the perimeter, the Hu moment, the gray scale diversity degree, the gray scale change index and the fractal characteristic index of each area to be detected. The method and the device only distinguish the stain area from the printing area based on the trained vector machine according to the characteristics of the area to be detected, so as to achieve the purpose of identifying the stain area.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for detecting surface defects of a non-woven fabric according to the present invention.
Detailed Description
In the following, the technical solutions in the embodiments of the present invention will be clearly and completely described with reference to the drawings in 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, rather than all of the embodiments, and all other embodiments obtained by a person skilled in the art based on the embodiments of the present invention belong to the protection scope of the embodiments of the present invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The present embodiment provides a method for detecting surface defects of a nonwoven fabric, which is described in detail as follows:
as shown in fig. 1, the method for detecting surface defects of non-woven fabric comprises the following steps:
and S001, acquiring a target gray image of the surface of the non-woven fabric.
In the production of the non-woven fabric, when the printing is small and numerous, and stains close to the printing patterns appear on the surface, the stains are difficult to identify, so that the defects in the non-woven fabric production need to be detected by combining a computer vision technology, and the embodiment mainly detects the detected area to be detected by utilizing the gray distribution characteristic and the fractal characteristic, and can quickly and accurately identify whether the area to be detected is a stain area.
In this embodiment, an industrial camera is used to obtain an image of a surface of a non-woven fabric, perform a graying process and an image preprocessing operation, where the image preprocessing operation includes noise reduction, enhancement, and the like, and finally obtain a preprocessed grayscale image, that is, a high-quality grayscale image, and mark the preprocessed grayscale image as a target grayscale image.
Step S002, carrying out edge detection on the target gray level image to obtain each to-be-detected area corresponding to the target gray level image; and obtaining the gray diversity degree, the perimeter and the Hu moment of the edge to be detected according to each region to be detected.
Generally, when stains appear on the surface of the non-woven fabric, the gray value distribution change of the stains in a gray image is single, and the shape of the stains is regular and is generally a round dot or a strip; when the surface of the non-woven fabric is printed, the distribution change of gray values and the fractal condition of the whole appearance may occur in a gray image due to the design of the printing; therefore, according to the difference of the stains and the printing in the image, the stains and the printing appearing in the gray-scale image of the non-woven fabric are analyzed in terms of gray-scale change and appearance shape to obtain characteristics capable of distinguishing the stains and the printing, and the subsequent judgment and classification of the types of the stains are facilitated by calculating the characteristics; the specific process is as follows:
because edges are formed in both a stain area and a printing area, the gray level of a normal area is uniform, and almost no edge information exists, edge extraction is performed on a target gray level image by using Canny edge detection to obtain edge pixel points on the target gray level image; then, performing connected domain analysis on the edge pixel points to obtain a plurality of connected domains, and recording the connected domains as to-be-detected regions; the area to be detected may be a dirty area or a printed area, and therefore the resulting connected domains need to be further analyzed one by one.
Then obtaining the perimeter and the Hu moment of each region to be detected; the calculated amount of the Hu moment is small, and the contour characteristics of the target to be detected in the image can be described; the Hu moment is:
wherein, the first and the second end of the pipe are connected with each other,
、
、
、
、
、
、
…
the parameters of the form are the normalized central moments,
and
are all an integer, and are all the same,
、
、
、
、
、
and
is the Hu moment value, and has seven total; the central moment is normalized to solve the problem of translation invariance, so that the central moment is adopted to describe the image, and the central moment is normalized to eliminate the influence caused by proportion change.
Combining the gray scale of the dirt and the printing and the edge image obtained by the contour change, wherein the inner area of the edge line is the area of the part to be detected, storing and recording the coordinates of the pixel points of the edge line, and counting the inner area of the edge line in the gray scale image, namely the gray scale distribution of the area to be detected; then analyzing the gray distribution of the area to be detected; the method specifically comprises the following steps:
acquiring a gray level histogram corresponding to each to-be-detected area; counting the number of gray values with frequency not being 0 on each gray histogram; obtaining the gray diversity degree of each to-be-detected area according to the number of gray values with the frequency not being 0 on the gray histogram corresponding to each to-be-detected area; for any region to be detected, calculating the gray diversity degree of each region to be detected according to the following formula:
in the formula, S is the number of gray values whose upper frequency of the gray histogram corresponding to the region to be detected is not 0, and 256 represents the number of types of total gray values in the gray image. The formula reflects the proportion of the gray value with the frequency not being 0 in the area to be detected, the larger the S is, the more the gray value with the frequency not being 0 is, the larger the H value is, and the more various the gray composition of the area is; conversely, the smaller the H value, the less the gray scale component.
And S003, obtaining the gray scale change index corresponding to each to-be-detected area according to the adjacent gray scale difference matrix.
Then, an adjacent gray level difference matrix is constructed to analyze the target gray level image, and the adjacent gray level difference matrix is recorded as
(ii) a Whereinu1Is the gray value of the current pixel point,
the number of pixels corresponding to the gray value is,
for the frequency of occurrence of the gray-scale value,
for the sum of all pixels of each gray value and the absolute value of the gray difference of the neighboring pixels,
is the number of levels of the adjacent gray matrix. The adaptive adjacent gray difference matrix
Is a pixel point
Is distributed in the form of a matrix of,ifor the rows in the matrix, it is,jare columns in a matrix. The positions of pixel points on each edge line are recorded during edge detection, and the pixel points in the flaws are analyzed by utilizing the self-adaptive adjacent gray difference matrix along the edge lines in the gray image of the non-woven fabric to be detected: traversing the region to be detected by using a 3-order self-adaptive adjacent gray difference matrix; and calculating and analyzing the gray level change condition in the area to be detected by using the following formula when the matrix is slid.
For any region to be detected, calculating the gray scale change index of the region to be detected according to the following formula:
wherein the content of the first and second substances,
is the gray scale change index of the area to be detected,
the total number of types of gray values in the region to be detected,
the number of pixels with the gray scale value u in the region to be detected,
summing the gray difference absolute values of all pixel points with the gray value u and the adjacent pixel points in the region to be detected; the gray scale change index obtained by the formula
The larger the value of (A), the more complicated the gray level change in the area, and the higher the roughness, i.e. the more uneven the gray level distribution; on the contrary, the method can be used for carrying out the following steps,
the smaller the value of (d), the more uniform the gradation distribution.
In addition, in the above formula
Is calculated as follows:
wherein the content of the first and second substances,
i and j are respectively an abscissa value and an ordinate value of the mth pixel point, x and y are constants,
is given an abscissa value of
The ordinate value is
The gray value of the pixel point;
to calculate the sum of the neighboring pixel gray values of the mth pixel point,
expressing the absolute value of the gray difference between all the pixel points with the gray value u and the adjacent pixel points in the area to be detected; then the
The sum of the absolute values of the gray differences of all pixels and the adjacent pixels of each gray scale is obtained.
And step S004, obtaining fractal characteristic indexes of the regions to be detected by using the fractal dimension box.
As fractal is a morphological characteristic of filling space in a non-integer dimensional form, when stains or printing appear on the surface of the non-woven fabric, the fractal dimension of the printing is higher than that of the stains, the fractal dimension can be used for describing the fractal characteristics of the to-be-detected area in the image by performing fractal analysis on the gray level image of the to-be-detected area; the method specifically comprises the following steps:
acquiring a three-dimensional gray curved surface of a target surface gray image, namely acquiring pixel point horizontal and vertical coordinate information and gray information, and covering the gray curved surface by using a fractal dimension box; for any region to be detected, calculating the fractal characteristic index of the region to be detected according to the following formula:
wherein the content of the first and second substances,
is the fractal characteristic index of the region to be detected,
for the side length of the box of fractal dimension,
the number of boxes obtained by covering the acquired three-dimensional gray curved surface for the fractal dimension box; in which is provided with
The fractal in the image is more complex and the characteristics are more obvious.
And S005, judging whether each area to be detected is a stain area or not according to the perimeter, the Hu moment, the gray diversity degree, the gray variation index and the fractal characteristic index of each area to be detected.
Constructing and obtaining a feature vector corresponding to each region to be detected according to the perimeter, the Hu moment, the gray diversity degree, the gray variation index and the fractal feature index of each region to be detected; inputting the feature vectors corresponding to the areas to be detected into a trained Support Vector Machine (SVM), and judging the areas to be detected with output results of stain areas as areas where stains are located as defect areas; judging the area to be detected with the output result of the printing area as a printing area, and judging the area to be detected as a normal area; i.e. completing the judgment and classification of the stains and the prints.
In the embodiment, a target gray image of the surface of a non-woven fabric is obtained firstly; performing edge detection on the target gray level image to obtain each to-be-detected area corresponding to the target gray level image; obtaining the gray diversity degree and the perimeter of the edge to be detected according to each area to be detected; secondly, obtaining a gray scale change index corresponding to each to-be-detected area according to the adjacent gray scale difference matrix; then, obtaining fractal characteristic indexes of the regions to be detected by using a fractal dimension box; and finally, judging whether each area to be detected is a stain area or not according to the perimeter, the Hu moment, the gray diversity degree, the gray variation index and the fractal characteristic index of each area to be detected. According to the method, the stain area and the printing area are distinguished only according to the characteristics of the area to be detected and based on the trained vector machine, so that the purpose of identifying the stain area is achieved, the printing template does not need to be matched with the area to be detected, various printing templates are used for matching with the area to be detected, the calculated amount can be reduced, and the detection efficiency is high.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications or substitutions do not cause the essential features of the corresponding technical solutions to depart from the scope of the technical solutions of the embodiments of the present application, and are intended to be included within the scope of the present application.
Claims (7)
1. A method for detecting surface defects of a non-woven fabric, comprising the steps of:
acquiring a target gray image of the surface of the non-woven fabric;
performing edge detection on the target gray level image to obtain each to-be-detected area corresponding to the target gray level image; obtaining the gray diversity degree, the perimeter and the Hu moment of the edge to be detected according to each area to be detected;
obtaining a gray scale change index corresponding to each region to be detected according to the adjacent gray scale difference matrix;
obtaining fractal characteristic indexes of the areas to be detected by using a fractal dimension box;
and judging whether each area to be detected is a stain area or not according to the perimeter, the Hu moment, the gray scale diversity degree, the gray scale change index and the fractal characteristic index of each area to be detected.
2. The method for detecting the surface defects of the non-woven fabric according to claim 1, wherein the method for performing edge detection on the target gray image to obtain each region to be detected corresponding to the target gray image comprises the following steps:
performing edge extraction on the target gray level image by using Canny edge detection to obtain edge pixel points on the target gray level image;
and analyzing the connected domains of the edge pixel points to obtain each connected domain, and recording as the to-be-detected region.
3. The method for detecting surface defects of non-woven fabric according to claim 1, wherein obtaining the gray-scale diversity of the edge to be detected according to each region to be detected comprises:
acquiring a gray level histogram corresponding to each to-be-detected area;
counting the number of gray values with frequency not being 0 on each gray histogram;
for any region to be detected, calculating the gray diversity degree of each region to be detected according to the following formula:
in the formula, S is the number of gray values with the frequency number of not 0 on the gray histogram corresponding to the region to be detected.
4. The method for detecting the surface defects of the non-woven fabric according to claim 1, wherein the method for obtaining the gray scale change index corresponding to each region to be detected according to the adjacent gray scale difference matrix comprises the following steps:
traversing each region to be detected by using an adjacent gray level difference matrix to obtain the gray level difference absolute value of each pixel point and the adjacent pixel point in each region to be detected;
for any region to be detected, calculating the gray scale change index of the region to be detected according to the following formula:
wherein, the first and the second end of the pipe are connected with each other,
is the gray scale change index of the area to be detected,
the total number of types of gray values in the region to be detected,
in the region to be detectedThe number of pixels having a gray value of u,
and summing the gray difference absolute values of all the pixel points with the gray value u and the adjacent pixel points in the region to be detected.
5. The method according to claim 4, wherein the sum of the absolute gray differences between all pixels with a gray value u and the adjacent pixels in the region to be detected is calculated according to the following formula:
wherein the content of the first and second substances,
i and j are respectively an abscissa value and an ordinate value of the mth pixel point, x and y are constants,
is given an abscissa value of
Ordinate value of
The gray value of the pixel point.
6. The method for detecting surface defects of non-woven fabrics according to claim 1, wherein the method for obtaining fractal characteristic indexes of each to-be-detected region by using a fractal dimension box comprises the following steps:
acquiring a three-dimensional gray curved surface of a gray image of the surface of a target;
covering the gray curved surface by using a fractal dimension box;
for any region to be detected, calculating the fractal characteristic index of the region to be detected according to the following formula:
wherein, the first and the second end of the pipe are connected with each other,
is the fractal characteristic index of the region to be detected,
for the side length of the box of fractal dimension,
and covering the obtained three-dimensional gray curved surface for the fractal dimension box to obtain the number of boxes.
7. The method for detecting surface defects of non-woven fabrics according to claim 1, wherein the method for judging whether each area to be detected is a stain area or not according to the perimeter, the Hu moment, the gray scale diversity degree, the gray scale change index and the fractal characteristic index of each area to be detected comprises the following steps:
constructing and obtaining a feature vector corresponding to each region to be detected according to the perimeter, the Hu moment, the gray diversity degree, the gray variation index and the fractal feature index of each region to be detected;
and inputting the feature vectors corresponding to the areas to be detected into a trained support vector machine, and judging the areas to be detected with the output results of stain areas as the areas where stains are located.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211575610.5A CN115588010B (en) | 2022-12-09 | 2022-12-09 | Surface defect detection method for non-woven fabric |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211575610.5A CN115588010B (en) | 2022-12-09 | 2022-12-09 | Surface defect detection method for non-woven fabric |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115588010A true CN115588010A (en) | 2023-01-10 |
| CN115588010B CN115588010B (en) | 2023-06-02 |
Family
ID=84783345
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211575610.5A Active CN115588010B (en) | 2022-12-09 | 2022-12-09 | Surface defect detection method for non-woven fabric |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115588010B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102221559A (en) * | 2011-03-05 | 2011-10-19 | 河海大学常州校区 | Online automatic detection method of fabric defects based on machine vision and device thereof |
| CN102621154A (en) * | 2012-04-10 | 2012-08-01 | 河海大学常州校区 | Method and device for automatically detecting cloth defects on line based on improved differential box multi-fractal algorithm |
| WO2017114473A1 (en) * | 2015-12-31 | 2017-07-06 | Shanghai United Imaging Healthcare Co., Ltd. | Methods and systems for image processing |
| CN108896561A (en) * | 2018-07-09 | 2018-11-27 | 苏州新乐隆自动化科技有限公司 | A kind of textile cloth detection method based on multithreading machine vision |
| CN114419004A (en) * | 2022-01-21 | 2022-04-29 | 佛山技研智联科技有限公司 | Fabric flaw detection method and device, computer equipment and readable storage medium |
| CN114757916A (en) * | 2022-04-15 | 2022-07-15 | 西安交通大学 | Industrial CT image defect classification method based on feature extraction and BP network |
| CN115272334A (en) * | 2022-09-29 | 2022-11-01 | 江苏美克美斯自动化科技有限责任公司 | Method for detecting micro defects on surface of steel rail under complex background |
| CN115311298A (en) * | 2022-10-12 | 2022-11-08 | 南通舒芯居纺织品有限公司 | Textile quality detection method |
| CN115311289A (en) * | 2022-10-12 | 2022-11-08 | 南通甜享纺织品有限公司 | Method for detecting oil stain defects of plain-color cloth |
-
2022
- 2022-12-09 CN CN202211575610.5A patent/CN115588010B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102221559A (en) * | 2011-03-05 | 2011-10-19 | 河海大学常州校区 | Online automatic detection method of fabric defects based on machine vision and device thereof |
| CN102621154A (en) * | 2012-04-10 | 2012-08-01 | 河海大学常州校区 | Method and device for automatically detecting cloth defects on line based on improved differential box multi-fractal algorithm |
| WO2017114473A1 (en) * | 2015-12-31 | 2017-07-06 | Shanghai United Imaging Healthcare Co., Ltd. | Methods and systems for image processing |
| CN108896561A (en) * | 2018-07-09 | 2018-11-27 | 苏州新乐隆自动化科技有限公司 | A kind of textile cloth detection method based on multithreading machine vision |
| CN114419004A (en) * | 2022-01-21 | 2022-04-29 | 佛山技研智联科技有限公司 | Fabric flaw detection method and device, computer equipment and readable storage medium |
| CN114757916A (en) * | 2022-04-15 | 2022-07-15 | 西安交通大学 | Industrial CT image defect classification method based on feature extraction and BP network |
| CN115272334A (en) * | 2022-09-29 | 2022-11-01 | 江苏美克美斯自动化科技有限责任公司 | Method for detecting micro defects on surface of steel rail under complex background |
| CN115311298A (en) * | 2022-10-12 | 2022-11-08 | 南通舒芯居纺织品有限公司 | Textile quality detection method |
| CN115311289A (en) * | 2022-10-12 | 2022-11-08 | 南通甜享纺织品有限公司 | Method for detecting oil stain defects of plain-color cloth |
Non-Patent Citations (2)
| Title |
|---|
| KAZIM H.等: "Fabric defect detection methods for circular knitting machines" * |
| 王孟涛 等: "基于灰度梯度共生矩阵和SVDD的织物疵点检测", 《丝绸》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115588010B (en) | 2023-06-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110349126B (en) | Convolutional neural network-based marked steel plate surface defect detection method | |
| CN109410230B (en) | Improved Canny image edge detection method capable of resisting noise | |
| CN116843688B (en) | Visual detection method for quality of textile | |
| CN108918536B (en) | Tire mold surface character defect detection method, device, equipment and storage medium | |
| CN113592845A (en) | Defect detection method and device for battery coating and storage medium | |
| CN115082419A (en) | Blow-molded luggage production defect detection method | |
| CN107862677A (en) | The Tunnel Lining Cracks recognition methods of thresholding algorithm and system between a kind of class based on gradient | |
| CN110555467B (en) | Industrial data classification method based on model migration | |
| Schachter et al. | Some experiments in image segmentation by clustering of local feature values | |
| CN107330979A (en) | Vector diagram generation method and device for building house type and terminal | |
| CN110348451A (en) | Case number (CN) automatic collection and recognition methods in railway container cargo handling process | |
| CN109685766A (en) | A kind of Fabric Defect detection method based on region fusion feature | |
| CN102156996A (en) | Image edge detection method | |
| CN115100221A (en) | Glass defect segmentation method | |
| CN114219794B (en) | Method and system for evaluating surface quality of shaving board based on machine vision | |
| Zhang et al. | A fast segmentation method for high-resolution color images of foreign fibers in cotton | |
| CN101106716A (en) | A shed image division processing method | |
| CN116664559A (en) | Machine vision-based memory bank damage rapid detection method | |
| CN113506246B (en) | Concrete 3D printing component fine detection method based on machine vision | |
| CN113221881B (en) | Multi-level smart phone screen defect detection method | |
| CN114549441A (en) | Sucker defect detection method based on image processing | |
| CN106022379A (en) | Method and device for detecting depreciation degree of screen | |
| CN116008289A (en) | Nonwoven product surface defect detection method and system | |
| CN117541588B (en) | Printing defect detection method for paper product | |
| CN110059573A (en) | Wild ginseng based on image recognition is classified calibration method |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A surface defect detection method for non-woven fabrics Effective date of registration: 20231129 Granted publication date: 20230602 Pledgee: Industrial Commercial Bank of China Ltd. Huimin branch Pledgor: Binzhou huaran chemical fiber rope net Co.,Ltd. Registration number: Y2023980068215 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |