CN112150423A - Longitude and latitude sparse mesh defect identification method - Google Patents
Longitude and latitude sparse mesh defect identification method Download PDFInfo
- Publication number
- CN112150423A CN112150423A CN202010971538.2A CN202010971538A CN112150423A CN 112150423 A CN112150423 A CN 112150423A CN 202010971538 A CN202010971538 A CN 202010971538A CN 112150423 A CN112150423 A CN 112150423A
- Authority
- CN
- China
- Prior art keywords
- image
- defect
- longitude
- latitude
- sparse
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 108
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000012545 processing Methods 0.000 claims abstract description 27
- 230000011218 segmentation Effects 0.000 claims abstract description 25
- 239000004744 fabric Substances 0.000 claims abstract description 18
- 230000000877 morphologic effect Effects 0.000 claims description 13
- 239000003550 marker Substances 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 150000001875 compounds Chemical class 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 230000008961 swelling Effects 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 5
- 239000000463 material Substances 0.000 abstract description 5
- 238000002474 experimental method Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 9
- 238000001514 detection method Methods 0.000 description 8
- 230000006872 improvement Effects 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 229920000742 Cotton Polymers 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000011152 fibreglass Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 241000238631 Hexapoda Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 239000003365 glass fiber Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000004753 textile Substances 0.000 description 1
- 238000012418 validation experiment Methods 0.000 description 1
- 238000009941 weaving 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
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Treatment Of Fiber Materials (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a longitude and latitude sparse mesh defect identification method, and belongs to the technical field of image processing. The method comprises the following steps: denoising the longitude and latitude sparse mesh defect image; carrying out convolution operation on the Sobel operator and the defect image to respectively obtain the gradient components of the defect image in the horizontal direction and the vertical direction to obtain a marked image, and carrying out threshold processing on the marked image by adopting an Otsu method to obtain a binary image; obtaining a defect segmentation image; the defect identification of the warp and weft sparse fabric is realized through the difference of three defects of hole breaking, warp missing and weft breaking of the warp and weft sparse fabric in the geometric dimension. Experiments prove that the defect identification method can be used for identifying three defects of holes, warp defects and weft breakage of longitude and latitude sparse meshes with different materials and densities. Compared with the prior art, the method has the advantages that the recognition precision is increased, the repeatability is good, and the economic benefit of an enterprise is improved.
Description
Technical Field
The invention relates to the field of image processing, in particular to a longitude and latitude sparse mesh defect identification method.
Background
Along with the improvement of the life quality of people, the application of the longitude and latitude sparse meshes is more and more extensive, and the market demand is gradually increased, for example, the shoe uppers of the net shoes in life, the insect-proof nets in agriculture, the medical gauzes in the medical field and the like. Because no manufacturing process can ensure 100% of defects are not existed, the quality of good defect detection is in a good condition, and the improvement of the economic benefit of enterprises is greatly influenced.
In textile processing manufacturing field, surface defect detection technique plays decisive action to the height of product quality, has very big influence to product appearance and grade division, and damage like the fly net can influence crops protection against insects effect, and the broken yarn of hail prevention net can influence crops defense etc.. Compared with the common fabric, the warp and weft sparse fabric has the defects of holes, warp lack, weft breakage and the like more easily in weaving and transportation due to the special material. However, most of the defects of longitude and latitude sparse meshes in China are detected on a manual level, the problems of low efficiency, easy fatigue, large influence on subjective factors, large component and the like exist in manual defect detection, the production efficiency is seriously reduced, the product quality fluctuation is large, and further the adverse influence on enterprise operation is caused.
The image processing technology has good stability and repeatability, can save a large amount of manpower, material resources and financial resources, and achieves the purposes of saving cost and improving economic benefits, so that the method is widely applied to the field of product defect detection. In addition, most of the existing methods carry out feature extraction through a Gabor filter bank or carry out defect segmentation through semantic segmentation, and the calculated amount is too large, so that the algorithm efficiency is low, and the requirements of real-time monitoring of a production line cannot be met.
Disclosure of Invention
[ problem ] to
Most of the existing detection methods are directed at common fabrics, and the applicability and detection effect of the existing detection methods to warp and weft sparse fabrics cannot be guaranteed. In addition, most of the existing methods carry out feature extraction through a Gabor filter bank or carry out defect segmentation through semantic segmentation, and the calculated amount is too large, so that the algorithm efficiency is low, and the requirements of real-time monitoring of a production line cannot be met.
[ solution ]
The invention provides a longitude and latitude sparse mesh defect identification method, which comprises the following steps:
(1) denoising the longitude and latitude sparse mesh defect image to obtain a denoised image;
(2) performing threshold segmentation on the longitude and latitude sparse mesh defect image, comprising the following steps of: performing convolution operation on the Sobel operator and the defect image to respectively obtain gradient components in the horizontal direction and the vertical direction of the defect image, obtaining a gradient image through the gradient components in the horizontal direction and the vertical direction, performing point multiplication on the gradient image and the denoised image to obtain a marked image, performing threshold processing on the marked image by adopting an Otsu method to obtain a binary image, and performing negation operation;
(3) selecting the standard size of meshes of the longitude and latitude sparse fabric as a structural element, performing morphological opening operation processing on the inverted binary image, and enabling the area which meets the standard size to disappear through the morphological opening operation processing, so that a defect part which does not meet the standard size is segmented, and a defect segmented image is obtained;
(4) and carrying out connected domain marking on the defect segmentation image, extracting shape characteristic parameters of the defect region, and realizing the defect identification of the warp and weft sparse fabric through the difference of three defects of hole breaking, warp missing and weft breaking of the warp and weft sparse fabric in the geometric dimension.
In one embodiment of the present invention, in the (1), the defect image is subjected to denoising processing by using a median filter.
In one embodiment of the present invention, the performing a morphological open operation on the binary image after the inversion operation includes: removing a pixel area with a smaller size than the structural element through a morphological opening operation fob; the expression is as follows:
in the formula (I), the compound is shown in the specification,
in order to etch the symbol(s),
for the symbol of swelling, DbThe definition fields for the structural elements, (x + x '), (y + y'), (x-x '), (y-y') are all in the definition field of image f.
In one embodiment of the present invention, the horizontal and vertical gradient components of the defect image are respectively:
wherein I' represents the input denoised defect image, Gsx、GsyRepresenting the gradient components in the horizontal and vertical directions, respectively.
In one embodiment of the present invention, the magnitude of the image gradient is:
in one embodiment of the present invention, the marker image is:
Z(x,y)＝I′(x,y)*Gs(x,y)
wherein Z (x, y) is a marker image, Gs(x, y) is a gradient image.
In an embodiment of the present invention, the obtaining a binary image by thresholding the marker image using the Otsu method includes:
the image is I', T is the segmentation threshold of the foreground and the background, and the ratio w of the foreground pixel in the image0Average gray of foreground is u0(ii) a The background pixel accounts for w in the image1Average gray of background is u1Then the average gray scale of the image is:
uT＝w0u0+w1u1
variance between classes
Comprises the following steps:
the optimal threshold is then:
and finally obtaining a binary image after threshold processing, and directly carrying out negation operation on the image subjected to threshold segmentation.
In one embodiment of the invention, the defect segmented images are connected domain labeled by a bwleabel function built into MATLAB.
In one embodiment of the present invention, the expression of the bwleabel function is as follows:
[L,num]＝bwlabel(BW,n)
in the formula, BW is a binary image to be marked; n is a connected domain type; num is the total number of connected regions in BW; l is a matrix for holding the connected component labels.
In one embodiment of the invention, the image region attribute measurement is carried out on each connected domain of the mark by utilizing the regionprops function, the properties parameter in the regionprops function is set as a 'boundingBox' operator, the structure array STATS can return the length and the width of each connected domain, and as the three defects of hole breaking, warp breaking and weft breaking have obvious difference in geometric dimension, different aspect ratio limit ranges are set for the three defects, and finally the defect identification of the longitude and latitude sparse meshes is realized.
In one embodiment of the invention, the sample material was exchanged from cotton with sparse warp and weft to fiberglass silk with dense fiber glass, and a validation experiment was performed. Experimental results show that the algorithm of the invention also has defect detection capability on mesh fabrics made of other materials.
[ advantageous effects ]
According to the method, optimal global threshold processing based on an Otsu method of gradient improvement is carried out on a defect image, and properties parameters are set as 'BoundingBox' operators, so that the structure array STATS can return the length and the width of each connected domain, and as three defects of hole breaking, warp missing and weft breaking are obviously different in geometric size, different length-width ratio limit ranges are set for the three defects, and finally defect identification of longitude and latitude sparse meshes is realized. Compared with the prior art, the time consumption for processing a single image is only 1.2s, the identification speed is high, good repeatability is achieved, and the economic benefit of an enterprise is improved.
Drawings
Fig. 1 is a diagram of denoising effect.
Fig. 2 is a diagram of threshold processing and negation effects.
FIG. 3 is a diagram illustrating the effect of dividing defects by an on operation.
FIG. 4 is a flowchart of a defect identification algorithm.
Fig. 5 shows the defect recognition result.
Fig. 6 shows the results of the verification experiment.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
Example 1
The embodiment provides a longitude and latitude sparse mesh defect identification method, which comprises the following steps: denoising processing, image threshold segmentation, defect segmentation and defect identification.
As shown in fig. 4, includes:
firstly, denoising a longitude and latitude sparse mesh defect image; the defect image is subjected to denoising processing by using a median filter.
Secondly, performing threshold segmentation on the longitude and latitude sparse mesh defect image; and (4) obtaining a binary image by carrying out Otsu method processing based on gradient improvement on the defect image.
Thirdly, performing defect segmentation on the defect image; and performing morphological opening operation processing on the binary image to obtain a defect segmentation image.
Fourthly, identifying the defects of the defect images; firstly, performing connected domain marking on a defect segmentation image through a bwleabel function built in an MATLAB platform, and then extracting shape characteristic parameters of a defect region; the method comprises the steps of returning the geometrical size of a defect area including the length and the width of the defect area through a BoundingBox operator, and setting different length-width ratio limiting ranges for three defects of hole breaking, warp missing and weft breaking to finally realize defect identification of the warp and weft sparse fabric.
The denoising process, specifically, the denoising process is performed on the defect image by using a median filter, and the processing effect is as shown in fig. 1.
The image threshold segmentation specifically comprises the following steps: through carrying out optimal global threshold processing based on an Otsu method of gradient improvement on a defect image, firstly carrying out convolution operation on a Sobel operator and the image, and obtaining brightness difference approximate values in horizontal and vertical directions respectively. The formula is shown as formula (1):
in the formula, I' represents the defect of input after denoisingImage, Gsx、GsyRepresenting the gradient components in the horizontal and vertical directions, respectively. The magnitude of the image gradient is then:
then, a gradient image is obtained through a Sobel operator I' (x, y), and the gradient image is multiplied by the denoised image point to obtain a marked image. The formula is as follows:
Z(x,y)＝I′(x,y)*Gs(x,y) (3)
wherein Z (x, y) is a marker image, Gs(x, y) is a gradient image.
Background pixels and internal pixels of some defects in the marked image are zero, while edge pixels of the defects are not zero, so that the influence of internal highlight pixels is reduced, and the effective segmentation of darker edge pixels is facilitated.
Finally, the Otsu method (madzu algorithm) is used to calculate the pixel histogram in Z (x, y), and the threshold is used to segment the defect image I' (x, y) globally. An image is set as I', T is a segmentation threshold value of a foreground and a background, and the ratio w of foreground pixels in the image0Average gray of foreground is u0(ii) a The background pixel accounts for w in the image1Average gray of background is u1Then the average gray scale of the image is:
uT＝w0u0+w1u1 (4)
variance between classes
Comprises the following steps:
the optimal threshold is then:
the binary image is finally obtained after the threshold processing, and due to the requirement of subsequent morphological operation, the image after the threshold segmentation is directly subjected to negation operation, and the processing effect is as shown in fig. 2.
The defect segmentation specifically comprises the following steps: by performing the morphological open operation processing on the binary image, the morphological open operation fob can remove a pixel region having a smaller size than the structural element. The expression is as follows:
in the formula (I), the compound is shown in the specification,
in order to etch the symbol(s),
for the symbol of swelling, DbThe definition fields for the structural elements, (x + x '), (y + y'), (x-x '), (y-y') are all in the definition field of image f.
The structural elements are set to be in the standard size of meshes of the warp and weft sparse fabric, and white areas which accord with the standard size disappear through morphological open operation, so that defect parts which do not accord with the standard size are segmented. The effect of this treatment is shown in FIG. 3.
The defect identification specifically comprises the following steps: the difference of three defects of hole breaking, warp missing and weft breaking of the warp and weft sparse fabric in the geometric dimension is used for judging and identifying, and the algorithm flow is shown in figure 4. Firstly, a connected domain mark is carried out on a binary image after defect segmentation through a bwleabel function built in MATLAB, and the expression of the bwleabel function is shown as a formula (10).
[ L, num ] ═ bwebabel (BW, n) (10) formula, BW is the binary image to be marked; n is a connected domain type, the value is 4 or 8, and the default is 8; num is the total number of connected regions in BW; l is a matrix for holding the connected component labels.
After the bwleabel function reads the input binary image BW, an L matrix with the same size as the BW is returned, where the L matrix includes category labels marking each connected region in the BW, and the values of these labels are 1, 2, and … … num (total number of connected regions). In the invention, the default value of the connected domain type is 8, namely, the region is searched according to the 8-connected standard.
And then, performing image region attribute measurement on each marked connected domain by using a regionprops function, wherein the expression of the regionprops function is shown as the formula (11).
STATS＝regionprops(L,properties) (11)
In the formula, L is a matrix for storing the label of the connected domain obtained by a bwleabel function; properties is a designated effective attribute character string; STATS is an array of structures of length max (L (:)), the corresponding field of the array of structures defining the metric under the corresponding attribute of each region.
In this embodiment, the properties parameter is set as a 'bounding box' operator, the structure array STATS can return the length and the width of each connected domain, and the three defects of hole breaking, warp missing and weft breaking are obviously different in geometric size, so that different length-width ratio limitation ranges are set for the three defects, and finally, the defect identification of the longitude and latitude sparse meshes is realized, and the identification result is shown in fig. 5.
In the embodiment, the sample material is replaced by the encrypted glass fiber silk fabric from cotton fabric with sparse warp and weft, and a verification experiment is carried out. The experimental result is shown in fig. 6, which proves that the defect identification method provided by the invention can be used for identifying three defects of hole breaking, warp missing and weft breaking of longitude and latitude sparse meshes with different materials and densities.
The scope of the present invention is not limited to the above embodiments, and any modifications, equivalent substitutions, improvements, etc. that can be made by those skilled in the art within the spirit and principle of the inventive concept should be included in the scope of the present invention.
Claims (10)
1. A longitude and latitude sparse mesh defect identification method is characterized by comprising the following steps:
(1) denoising the longitude and latitude sparse mesh defect image to obtain a denoised image;
(2) performing threshold segmentation on the longitude and latitude sparse mesh defect image, comprising the following steps of: performing convolution operation on the Sobel operator and the defect image to respectively obtain gradient components in the horizontal direction and the vertical direction of the defect image, obtaining a gradient image through the gradient components in the horizontal direction and the vertical direction, performing point multiplication on the gradient image and the denoised image to obtain a marked image, performing threshold processing on the marked image by adopting an Otsu method to obtain a binary image, and performing negation operation;
(3) selecting the standard size of meshes of the longitude and latitude sparse fabric as a structural element, performing morphological opening operation processing on the inverted binary image, and enabling the area which meets the standard size to disappear through the morphological opening operation processing, so that a defect part which does not meet the standard size is segmented, and a defect segmented image is obtained;
(4) and marking a connected domain of the defect segmentation image, extracting shape characteristic parameters of the defect region, and identifying the defects of the warp and weft sparse fabric according to the difference of the three defects of hole breaking, warp missing and weft breaking of the warp and weft sparse fabric in the geometric dimension.
2. The method for identifying a defect in a graticule sparse mesh as claimed in claim 1, wherein in the step (1), the defect image is denoised by using a median filter.
3. The longitude and latitude sparse mesh defect identification method of claim 1, wherein the morphological opening operation processing of the inverted binary image comprises: removing a pixel area with a smaller size than the structural element through a morphological opening operation fob; the expression is as follows:
in the formula (I), the compound is shown in the specification,
in order to etch the symbol(s),
for the symbol of swelling, DbThe definition fields for the structural elements, (x + x '), (y + y'), (x-x '), (y-y') are all in the definition field of image f.
4. The method for recognizing the defect of the longitude and latitude sparse mesh of claim 1, wherein the gradient components of the horizontal direction and the vertical direction of the defect image are respectively as follows:
wherein I' represents the input denoised defect image, Gsx、GsyRepresenting the gradient components in the horizontal and vertical directions, respectively.
5. The method for recognizing the longitude and latitude sparse mesh defect of claim 1, wherein the amplitude of the image gradient is as follows:
6. the method for recognizing the defect of the longitude and latitude sparse mesh of claim 1, wherein the marked image is as follows:
Z(x,y)＝I′(x,y)*Gs(x,y)；
wherein Z (x, y) is a marker image, Gs(x, y) is a gradient image.
7. The longitude and latitude sparse mesh defect identification method of claim 1, wherein the thresholding the marker image to obtain a binary image by using Otsu method comprises:
the image is I', T is the segmentation threshold of the foreground and the background, and the ratio w of the foreground pixel in the image0Average gray of foreground is u0(ii) a The background pixel accounts for w in the image1Average gray of background is u1Then the average gray scale of the image is:
uT＝w0u0+w1u1；
variance between classes
Comprises the following steps:
the optimal threshold is then:
and finally obtaining a binary image after threshold processing, and directly carrying out negation operation on the image subjected to threshold segmentation.
8. The method for recognizing the defect of the longitude and latitude sparse mesh of claim 1, wherein the defect segmented image is marked by a connected domain through a bwleabel function built in MATLAB.
9. The method for identifying the defect in the sparse mesh of longitude and latitude of claim 8, wherein the expression of the bwleabel function is as follows:
[L,num]＝bwlabel(BW,n)；
in the formula, BW is a binary image to be marked; n is a connected domain type; num is the total number of connected regions in BW; l is a matrix for holding the connected component labels.
10. The longitude and latitude sparse mesh defect identification method according to claim 9, wherein image region attribute measurement is performed on each connected domain of the mark by using a regionprops function, and the properties parameter in the regionprops function is set as a 'BoundingBox' operator, so that the structure array STATS can return the length and width of each connected domain, and different aspect ratio limit ranges are set for three defects, namely hole breaking, warp missing and weft breaking, so that the defect identification of the longitude and latitude sparse mesh is finally realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010971538.2A CN112150423B (en) | 2020-09-16 | 2020-09-16 | Method for identifying defects of warp and weft sparse meshes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010971538.2A CN112150423B (en) | 2020-09-16 | 2020-09-16 | Method for identifying defects of warp and weft sparse meshes |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112150423A true CN112150423A (en) | 2020-12-29 |
| CN112150423B CN112150423B (en) | 2024-04-30 |
Family
ID=73892862
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010971538.2A Active CN112150423B (en) | 2020-09-16 | 2020-09-16 | Method for identifying defects of warp and weft sparse meshes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112150423B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113658131A (en) * | 2021-08-16 | 2021-11-16 | 东华大学 | Tour type ring spinning broken yarn detection method based on machine vision |
| CN114913178A (en) * | 2022-07-19 | 2022-08-16 | 山东天宸塑业有限公司 | Melt-blown fabric defect detection method and system |
| CN115082710A (en) * | 2022-08-18 | 2022-09-20 | 南通保利金纺织科技有限公司 | Intelligent fabric mesh classifying and identifying method and system |
| CN115311265A (en) * | 2022-10-10 | 2022-11-08 | 南通惠罗家用纺织品有限公司 | Loom intelligence control system based on weaving quality |
| CN116385353A (en) * | 2023-02-10 | 2023-07-04 | 南通大学 | Camera module abnormality detection method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009157701A (en) * | 2007-12-27 | 2009-07-16 | Shimadzu Corp | Method and unit for image processing |
| CN101526484A (en) * | 2009-04-13 | 2009-09-09 | 江南大学 | Bearing defect detecting technique based on embedded-type machine vision |
| CN106778734A (en) * | 2016-11-10 | 2017-05-31 | 华北电力大学（保定） | A kind of insulator based on rarefaction representation falls to go here and there defect inspection method |
| CN109615612A (en) * | 2018-11-20 | 2019-04-12 | 华南理工大学 | A kind of defect inspection method of solar panel |
| CN109816652A (en) * | 2019-01-25 | 2019-05-28 | 湖州云通科技有限公司 | A kind of intricate casting defect identification method based on gray scale conspicuousness |
-
2020
- 2020-09-16 CN CN202010971538.2A patent/CN112150423B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009157701A (en) * | 2007-12-27 | 2009-07-16 | Shimadzu Corp | Method and unit for image processing |
| CN101526484A (en) * | 2009-04-13 | 2009-09-09 | 江南大学 | Bearing defect detecting technique based on embedded-type machine vision |
| CN106778734A (en) * | 2016-11-10 | 2017-05-31 | 华北电力大学（保定） | A kind of insulator based on rarefaction representation falls to go here and there defect inspection method |
| CN109615612A (en) * | 2018-11-20 | 2019-04-12 | 华南理工大学 | A kind of defect inspection method of solar panel |
| CN109816652A (en) * | 2019-01-25 | 2019-05-28 | 湖州云通科技有限公司 | A kind of intricate casting defect identification method based on gray scale conspicuousness |
Non-Patent Citations (3)
| Title |
|---|
| 刘茁梅;李鹏飞;景军锋;: "基于稀疏表示的印花织物疵点检测", 西安工程大学学报, no. 02, 25 April 2018 (2018-04-25) * |
| 王侦倪;高炜欣;汤楠;: "一种基于稀疏描述的X射线焊缝检测方法", 西安石油大学学报(自然科学版), no. 05, 25 September 2018 (2018-09-25) * |
| 黄娟;杨建玺;: "图像处理在医用纱布表面缺陷检测中的应用", 机械设计与制造, no. 10, 8 October 2013 (2013-10-08) * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113658131A (en) * | 2021-08-16 | 2021-11-16 | 东华大学 | Tour type ring spinning broken yarn detection method based on machine vision |
| CN114913178A (en) * | 2022-07-19 | 2022-08-16 | 山东天宸塑业有限公司 | Melt-blown fabric defect detection method and system |
| CN114913178B (en) * | 2022-07-19 | 2022-09-23 | 山东天宸塑业有限公司 | Melt-blown fabric defect detection method and system |
| CN115082710A (en) * | 2022-08-18 | 2022-09-20 | 南通保利金纺织科技有限公司 | Intelligent fabric mesh classifying and identifying method and system |
| CN115311265A (en) * | 2022-10-10 | 2022-11-08 | 南通惠罗家用纺织品有限公司 | Loom intelligence control system based on weaving quality |
| CN116385353A (en) * | 2023-02-10 | 2023-07-04 | 南通大学 | Camera module abnormality detection method |
| CN116385353B (en) * | 2023-02-10 | 2024-01-30 | 南通大学 | Camera module abnormality detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112150423B (en) | 2024-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112150423A (en) | Longitude and latitude sparse mesh defect identification method | |
| CN107230202B (en) | Automatic identification method and system for road surface disease image | |
| CN111179225B (en) | Test paper surface texture defect detection method based on gray gradient clustering | |
| Navon et al. | Color image segmentation based on adaptive local thresholds | |
| US9971929B2 (en) | Fingerprint classification system and method using regular expression machines | |
| Thenmozhi et al. | Image processing techniques for insect shape detection in field crops | |
| WO2018233205A1 (en) | Method for detecting pedestrians in image by using gaussian penalty | |
| CN111583227A (en) | Method, device, equipment and medium for automatically counting fluorescent cells | |
| EP2556491A2 (en) | Methods for segmenting objects in images | |
| CN104123731A (en) | Method for dividing low-contrast-ratio ginned cotton mulching film image | |
| CN108109133A (en) | A kind of silkworm seed automatic counting method based on digital image processing techniques | |
| Anantrasirichai et al. | Automatic leaf extraction from outdoor images | |
| CN110110667A (en) | A kind of processing method, system and the associated component of diatom image | |
| Wang et al. | A fast image segmentation algorithm for detection of pseudo-foreign fibers in lint cotton | |
| CN109472779A (en) | A kind of yarn appearance characteristic parameter extraction and analysis method based on morphosis | |
| Xu et al. | Detection method for the buds on winter vines based on computer vision | |
| CN111868783B (en) | Region merging image segmentation algorithm based on boundary extraction | |
| CN103226709B (en) | A kind of network curtain image recognition method of fall webworm larvae | |
| CN107578414A (en) | A kind of processing method of pavement crack image | |
| CN109716355A (en) | Grain boundaries identification | |
| KR102392252B1 (en) | Mushroom Object Growth Monitoring Method Using Image Processing Technology | |
| CN108205678A (en) | A kind of nameplate Text region processing method containing speck interference | |
| Wei et al. | Method for vortex shape retrieval and area calculation based on convex hull algorithm | |
| CN115620196A (en) | Key frame extraction method, article identification method and device | |
| Xin et al. | A fast feature extraction algorithm for detection of foreign fiber in lint cotton within a complex background |
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 |