CN113393444A - Dacron DTY network point detection method based on image processing technology - Google Patents
Dacron DTY network point detection method based on image processing technology Download PDFInfo
- Publication number
- CN113393444A CN113393444A CN202110683546.1A CN202110683546A CN113393444A CN 113393444 A CN113393444 A CN 113393444A CN 202110683546 A CN202110683546 A CN 202110683546A CN 113393444 A CN113393444 A CN 113393444A
- Authority
- CN
- China
- Prior art keywords
- image
- network
- dty
- pixel
- formula
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 34
- 239000005020 polyethylene terephthalate Substances 0.000 title claims abstract description 33
- 238000005516 engineering process Methods 0.000 title claims abstract description 26
- 238000001514 detection method Methods 0.000 title claims abstract description 25
- 229920004934 Dacron® Polymers 0.000 title claims description 8
- 229920000728 polyester Polymers 0.000 claims abstract description 40
- 229920004933 Terylene® Polymers 0.000 claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 20
- 230000000877 morphologic effect Effects 0.000 claims abstract description 12
- 238000004364 calculation method Methods 0.000 claims description 3
- 150000001875 compounds Chemical class 0.000 claims description 3
- 230000007717 exclusion Effects 0.000 abstract 1
- 239000000835 fiber Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000009941 weaving Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000009987 spinning Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000011800 void material Substances 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
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- 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)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Treatment Of Fiber Materials (AREA)
Abstract
The invention relates to a terylene DTY network point detection method based on an image processing technology, which comprises the following steps: (1) performing morphological image processing on a single image B (x, y) subjected to binarization operation to obtain an image Bp(x, y); the single image B (x, y) is an image of the polyester DTY filament yarn, and the polyester DTY filament yarn in the image is parallel to the horizontal direction of the image and is formed by splicing a plurality of continuous non-overlapped images; (2) calculating image Bp(x, y) taking the number of pixel points on the column where the ith pixel point of the terylene DTY filament in a certain line as the diameter d corresponding to the ith pixel pointi(ii) a (3) Positioning image BpA nexus area in (x, y); (4) IM by morphological open operation pairiCarrying out treatment; (5) exclusion of BpA pseudo mesh point region among the mesh point regions in (x, y); (6) systemMeter IMiAnd calculating the network degree according to the number of the areas with the continuous numerical values of 1. The method reduces the dependence on people, meets the detection requirement of the network points of the polyester DTY filaments, and has high application value.
Description
Technical Field
The invention belongs to the technical field of polyester filament yarn quality detection methods, and relates to a polyester DTY network point detection method based on an image processing technology.
Background
The polyester low-stretch yarn is called DTY for short, takes polyester slices as raw materials, adopts high-speed spinning polyester pre-oriented yarn, and is processed by drafting and false twisting, and has the characteristics of short process, high efficiency, good quality and the like. The existing polyester yarn, whether being fully drawn yarn or DTY, is compounded by a plurality of polyester monofilament fibers, and the multifilament of the existing polyester yarn is reinforced by a network processing technology, so that cohesion is generated between the monofilaments, and favorable conditions are provided for later-stage pulp-free weaving. The yarn processed by the network technology is called network yarn, the number of network points contained in each meter of network yarn is called network degree, the network yarn is an important quality index of the network yarn, the hand feeling style and the durability of the subsequently produced fabric are determined, and the production efficiency of subsequent weaving is influenced. At present, the network point detection still depends on a manual detection mode, the requirement of the existing filament high-degree automatic production is difficult to adapt, and a machine vision-based automatic network degree detection method is urgently needed to be developed. The patent (CN201910056400.7) provides a method for testing network degree of network filaments based on image processing technology, which is to regard network point detection as a classification problem and use a VGG16 deep network model for model training and detection, and has the disadvantages of requiring a large number of training samples, requiring retraining of filaments of different specifications, and having high time cost.
Disclosure of Invention
The invention provides a terylene DTY network point detection method based on an image processing technology, and aims to solve the problem that the efficiency of detecting the network degree of terylene DTY filaments by relying on artificial vision in the prior art is low.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a terylene DTY network point detection method based on image processing technology,
(1) for the document subjected to binarization operationThe image B (x, y) is subjected to morphological image processing for filling the void region and removing interference to obtain an image Bp(x,y);
The single image B (x, y) is an image of the polyester DTY filament yarn, and the polyester DTY filament yarn in the image is parallel to the horizontal direction of the image and is formed by splicing a plurality of continuous non-overlapped images; the continuous non-overlapping means that no frame is missed when the images of the polyester DTY filaments are shot, and two continuously shot images are not overlapped (the polyester DTY filaments in the two images are two completely different sections); the method can be realized by matching the motion speed with the shooting frame frequency; x is the pixel point position of the image in the horizontal direction, and y is the pixel point position of the image in the vertical direction;
(2) calculating image Bp(x, y) taking the number of pixel points on the column where the ith pixel point of the terylene DTY filament in a certain line as the diameter d corresponding to the ith pixel pointiThen image BpThe diameter set corresponding to all pixel points of the terylene DTY filament in the (x, y) line is the set { d }i}; the polyester DTY filament yarn in a certain row means that the certain row is positioned in a polyester DTY filament yarn area, but not in a non-polyester DTY filament yarn area;
(3) for the diameter of the polyester DTY filament, as the diameter of the network point area is obviously smaller than that of the non-network point area, the image B is positioned by applying the formula ApNetwork Point area in (x, y), denoted IMi;
Formula A is:
in the formula (I), the compound is shown in the specification,is a set { diMean value of }, IMiEqual to 1 denotes here (i.e. IM)iPoint where the median data is 1) is image BpLocation of network points in (x, y), IMiEqual to 0 means here image BpA non-network point location in (x, y); m is the image height;is to BpAll pixels of the image column in (x, y) are added (here)Or can be written directly as di);
(4) To eliminate the interference of abnormal diameter to the network point positioning result, IM is performed by adopting morphological open operationiProcessing (IM)iIs an array, which can be processed as an image with only one line), the size of the template used for the opening operation is 20 pixels × 1 pixel;
(5) for the diameter of the polyester DTY filament, the real network points have the appearance characteristics of small diameter at the network points and large diameters at the left side and the right side, so that the image B is excludedpThe pseudo nexus area in the nexus area (pseudo nexus is an area which is not a nexus and is mistaken for the nexus area because the diameter is small) in (x, y) comprises the following steps:
(5.1) adopting a formula B to position the boundary position P of the network point area and the non-network point areaj;
The formula B is:
if so, (IM)i1 and IMi+10 or (IM)i0 and IMi+11), the horizontal position of the pixel point i is taken as the horizontal position of the boundary position, and is marked as Pj(ii) a Wherein, IMi+1The IM value of the pixel point at the position i +1 is represented;
(5.2) calculating the average diameter of each non-network point area by adopting a formula C, wherein the average diameter of the jth non-network point area is marked as DNIMj;
The formula C is:
in the formula, PjIs the horizontal position of the jth boundary position, Pj+1Is the horizontal position of the j +1 th boundary position,Pj+1-PjThe number of pixel points i between the horizontal position of the j +1 th boundary position and the horizontal position of the j th boundary position,is PjAnd Pj+1The sum of the corresponding diameter values of each pixel point on the certain line of the terylene DTY filaments;
Pjand Pj+1The positions of the boundary points are recorded, and the average diameter of each non-network point area can be obtained by traversing all the adjacent boundary points.
(5.3) since the non-nexus areas on the left and right sides of the nexus area are large in diameter if DNIMjLess than average diameterThe network point area is a pseudo network point and needs to be removed; eliminating false network points by adopting a formula D;
the formula D is:
(6) Statistical IMiAnd obtaining the number of the network points by the number of the areas with the continuous numerical values of 1, and further calculating the network degree.
As a preferred technical scheme:
in the method for detecting the network point of the polyester DTY based on the image processing technology, the single image B (x, y) subjected to the binarization operation is a continuous and non-overlapping image set { I) of the polyester DTY filament yarniCarry out binarization operation to obtain an image set { B }i}; then will { BiThe images in the (1) are spliced in a left-right arrangement mode, x is the position of a pixel point of the image in the horizontal direction (for the image, the upper left corner is a coordinate origin, the abscissa is the horizontal direction), and y is the position of the pixel point of the image in the vertical direction (the ordinate is the vertical direction).
The terylene DTY network point detection method based on the image processing technology, the image set { I }iThe filament image in the pattern is an 8-bit gray image, and the pixel gray value range is an integer between 0 and 255.
The terylene DTY network point detection method based on the image processing technology, the image set { I }iObtained with an industrial camera in a dark box backlighting mode, with dimensions M pixels x N pixels.
In the method for detecting the dacron DTY network points based on the image processing technology, the binary calculation formula is as follows:
wherein, Bi(x, y) is Ii(x, y) binarized image,is Ii(x, y) the sum of the gray levels of the 1 st to M th pixel points in the vertical direction at the x positioni(x, y) can be regarded as a specific gray value of the pixel (specifically, the ith pixel, the horizontal position is x, and the vertical position is y), where x and y are subscripts, and M is the image height.
In the method for detecting the dacron DTY network points based on the image processing technology, the morphological image processing is to perform closed operation on a single image B (x, y), and the circular radius of the structural element is 10 pixels.
According to the terylene DTY network point detection method based on the image processing technology, the number of continuous and non-overlapped images is more than or equal to 1000, and the image acquisition resolution is less than 0.02 mm/pixel.
According to the method for detecting the network points of the polyester DTY based on the image processing technology, the specification of the polyester DTY is 30-300D.
The principle of the invention is as follows:
the method utilizes the appearance characteristic of large diameter difference of the polyester DTY network yarn, utilizes the image processing technology to extract the diameter, and on the basis, combines the change rule of the left diameter and the right diameter of the network point and the morphological method to eliminate the false network point, thereby improving the detection precision. In addition, the method of the invention removes the false network points, and overcomes the problem of poor precision when directly adopting the diameter.
Has the advantages that:
aiming at the defects of low detection accuracy and time and labor consumption of the terylene DTY network points depending on manual operation, the invention provides the terylene DTY network point detection method based on the image processing technology, reduces the dependence on the manual operation, meets the requirement of fast and accurate detection of the terylene DTY filament network points in practical application, and has good application value.
Drawings
FIG. 1 shows the image set { I } when the polyester DTY filament is DTY75D/72FiA schematic of one of the images in (1);
FIG. 2 is a binarized image of the image shown in FIG. 1;
FIG. 3 is a single image B (x, y) resulting from the stitching of the images shown in FIG. 2;
fig. 4 is a morphologically processed image of the image shown in fig. 3.
Detailed Description
The invention will be further illustrated with reference to specific embodiments. It should be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Further, it should be understood that various changes or modifications of the present invention may be made by those skilled in the art after reading the teaching of the present invention, and such equivalents may fall within the scope of the present invention as defined in the appended claims.
A terylene DTY network point detection method based on image processing technology comprises the following steps:
(1) the method adopts an industrial camera to realize the continuous non-overlapping of more than 1000 terylene DTY (draw textured yarn) filaments with no frame leakage and 30-300D continuous shooting specification by matching the motion speed and the shooting frame frequency under the backlight illumination mode of a dark boxImage, and the image acquisition resolution is less than 0.02 mm/pixel, and the image set is marked as { IiThe two polyester DTY filament sections in the two images are completely different; when the polyester DTY filament specification is DTY75D/72F, the image set is { IiOne image in (1); wherein the size is M pixels multiplied by N pixels; set of images { IiThe filament image in the pattern is an 8-bit gray image, and the pixel gray value range is an integer between 0 and 255;
(2) image set for polyester DTY filament { IiCarry out binarization operation to obtain an image set { B }iWill { B } againiSplicing each image in the images in a left-right arrangement mode to obtain a single image B (x, y); wherein, the splicing refers to arranging images according to the length direction of the polyester DTY filaments in each image; the calculation formula of binarization is as follows:
wherein, Bi(x, y) is Ii(x, y) binarized image,is Ii(x, y) the sum of the gray levels of the 1 st to M th pixel points in the vertical direction at the x positioni(x, y) can be regarded as a specific gray value of a pixel (specifically, the ith pixel, the horizontal position is x, and the vertical position is y), where x and y are subscripts, and M is the image height; x is the pixel point position of the image in the horizontal direction (for the image, the upper left corner is the origin of coordinates, the abscissa is the horizontal direction), and y is the pixel point position of the image in the vertical direction (the ordinate is the vertical direction);
when the specification of the polyester DTY filament is 75D/72F, the image after binarization is shown in figure 2, and a single image B (x, y) is shown in figure 3;
(3) performing morphological image processing (closed operation) on the single image B (x, y) obtained in the step (2) to obtain an image Bp(x, y); structural element in morphological image processingThe circle radius of the pixel is 10 pixels; image B when the polyester DTY filament yarn size is 75D/72Fp(x, y) is as shown in FIG. 4;
(4) calculating image BpIn (x, y), the number of pixel points on a column where the ith pixel point of the terylene DTY filament yarn in a certain line (one line in the horizontal direction) is positioned is taken as the diameter d corresponding to the ith pixel pointiThen image BpThe diameter set corresponding to all pixel points of the terylene DTY filament in the (x, y) line is the set { d }i};
(5) Positioning image B by applying formula ApNetwork Point area in (x, y), denoted IMi;
in the formula (I), the compound is shown in the specification,is a set { diMean value of }, IMiEqual to 1 denotes here (i.e. IM)iPoint where the median data is 1) is image BpLocation of network points in (x, y), IMiEqual to 0 means here image BpA non-network point location in (x, y); m is the image height;is to Bp(x, y) adding all pixels of the image column;
(6) IM by morphological open operation pairiProcessing, wherein the size of a template adopted by the opening operation is 20 pixels multiplied by 1 pixel;
(7) excluding image BpThe pseudo network point area in the network point area in (x, y) comprises the following specific steps:
(7.1) locating the boundary position P of the network point area and the non-network point area by adopting a formula Bj;
The formula B is:
if so, (IM)i1 and IMi+10 or (IM)i0 and IMi+11), the horizontal position of the pixel point i is taken as the horizontal position of the boundary position, and is marked as Pj;
(7.2) calculating the average diameter of each non-network point area by adopting a formula C, wherein the average diameter of the jth non-network point area is marked as DNIMj;
The formula C is:
in the formula, PjIs the horizontal position of the jth boundary position, Pj+1Is the horizontal position of the j +1 th boundary position, Pj+1-PjThe number of pixel points i between the horizontal position of the j +1 th boundary position and the horizontal position of the j th boundary position,is PjAnd Pj+1The sum of the corresponding diameter values of each pixel point on the certain line of the terylene DTY filaments;
(7.3) eliminating the false network points by adopting a formula D;
(8) Statistical IMiAnd obtaining the number of the network points by the number of the areas with the continuous numerical values of 1.
The method for detecting the polyester DTY network points based on the image processing technology is adopted to detect the polyester DTY network points with different specifications, and the detection results are listed in the following table:
as shown in the table above, the maximum relative error of the DTY detection for different sizes of polyester fibers is 6.4%, and the minimum relative error is 1%, which fully illustrates the effectiveness of the method provided by the present invention, and meanwhile, as the denier of the polyester DTY filament increases, the error is smaller, because the difference between the diameters of the network point and the non-network point is large when the denier is large, which is more beneficial for the distinction.
Claims (8)
1. A terylene DTY network point detection method based on image processing technology is characterized in that:
(1) performing morphological image processing on a single image B (x, y) subjected to binarization operation to obtain an image Bp(x,y);
The single image B (x, y) is an image of the polyester DTY filament yarn, and the polyester DTY filament yarn in the image is parallel to the horizontal direction of the image and is formed by splicing a plurality of continuous non-overlapped images; the continuous non-overlapping means that no frame is missed when the image of the polyester DTY filament is shot, and two continuously shot images are not overlapped; x is the pixel point position of the image in the horizontal direction, and y is the pixel point position of the image in the vertical direction;
(2) calculating image Bp(x, y) taking the number of pixel points on the column where the ith pixel point of the terylene DTY filament in a certain line as the diameter d corresponding to the ith pixel pointiThen image BpThe diameter set corresponding to all pixel points of the terylene DTY filament in the (x, gamma) line is the set { d }i};
(3) Positioning image B by applying formula ApNetwork Point area in (x, y), denoted IMi;
Formula A is:
in the formula (I), the compound is shown in the specification,is a set { diMean value of }, IMiEqual to 1 indicates here image BpLocation of network points in (x, y), IMiEqual to 0 means here image BpA non-network point location in (x, y); m is the image height;is to Bp(x, y) adding all pixels of the image column;
(4) IM by morphological open operation pairiProcessing, wherein the size of a template adopted by the opening operation is 20 pixels multiplied by 1 pixel;
(5) excluding image BpThe pseudo network point area in the network point area in (x, y) comprises the following specific steps:
(5.1) adopting a formula B to position the boundary position P of the network point area and the non-network point areaj;
The formula B is:
if so, (IM)i1 and IMi+10 or (IM)i0 and IMi+11), the horizontal position of the pixel point i is taken as the horizontal position of the boundary position, and is marked as Pj;
(5.2) calculating the average diameter of each non-network point area by adopting a formula C, wherein the average diameter of the jth non-network point area is marked as DNIMj;
The formula C is:
in the formula, PjIs the horizontal position of the jth boundary position, Pj+1Is the horizontal position of the j +1 th boundary position, Pj+1-PjThe number of pixel points i between the horizontal position of the j +7 th boundary position and the horizontal position of the j th boundary position,is PjAnd Pj+1The sum of the diameter values corresponding to each pixel point on the terylene DTY filament;
(5.3) eliminating the false network points by adopting a formula D;
the formula D is:
(6) statistical IMiAnd obtaining the number of the network points by the number of the areas with the continuous numerical values of 1.
2. The method as claimed in claim 1, wherein the single image B (X, y) is a continuous and non-overlapping image set { I } of the polyester DTY filamentiCarry out binarization operation to obtain an image set { B }i}; then will { BiAnd splicing the images, wherein x is the position of a pixel point of the image in the horizontal direction, and y is the position of the pixel point of the image in the vertical direction.
3. The method for detecting the network points of the dacron DTY based on the image processing technology as claimed in claim 2, wherein the image set { I } isiThe filament image in the pattern is an 8-bit gray image, and the pixel gray value range is an integer between 0 and 255.
4. The method for detecting the network points of the dacron DTY based on the image processing technology as claimed in claim 3, wherein the image set { I } isiObtained with an industrial camera in a dark box backlighting mode, with dimensions M pixels x N pixels.
5. The method for detecting the dacron DTY network points based on the image processing technology as claimed in claim 2, wherein the calculation formula of binarization is as follows:
6. The method as claimed in claim 1, wherein the morphological image processing is performed by performing a closed operation on a single image B (x, y), and the structural element is a circle with a radius of 10 pixels.
7. The method for detecting the dacron DTY network points based on the image processing technology as claimed in claim 1, wherein the number of continuous and non-overlapped images is greater than or equal to 1000, and the image acquisition resolution is less than 0.02 mm/pixel.
8. The image processing technology-based terylene DTY network point detection method according to claim 1, wherein the specification of terylene DTY is 30D-300D.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110683546.1A CN113393444B (en) | 2021-06-21 | 2021-06-21 | Polyester DTY network point detection method based on image processing technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110683546.1A CN113393444B (en) | 2021-06-21 | 2021-06-21 | Polyester DTY network point detection method based on image processing technology |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113393444A true CN113393444A (en) | 2021-09-14 |
CN113393444B CN113393444B (en) | 2023-06-02 |
Family
ID=77623069
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110683546.1A Active CN113393444B (en) | 2021-06-21 | 2021-06-21 | Polyester DTY network point detection method based on image processing technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113393444B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0563971A (en) * | 1991-09-05 | 1993-03-12 | Minolta Camera Co Ltd | Picture processor |
US20150178946A1 (en) * | 2013-12-19 | 2015-06-25 | Google Inc. | Image adjustment using texture mask |
CN109903267A (en) * | 2019-01-22 | 2019-06-18 | 江苏恒力化纤股份有限公司 | A method of based on image processing techniques test network wire network degree |
CN111415349A (en) * | 2020-03-27 | 2020-07-14 | 江苏恒力化纤股份有限公司 | Method for detecting polyester filament yarn based on image processing technology |
CN112365452A (en) * | 2020-10-26 | 2021-02-12 | 江苏恒力化纤股份有限公司 | Network wire network point detection method based on bilateral images |
-
2021
- 2021-06-21 CN CN202110683546.1A patent/CN113393444B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0563971A (en) * | 1991-09-05 | 1993-03-12 | Minolta Camera Co Ltd | Picture processor |
US20150178946A1 (en) * | 2013-12-19 | 2015-06-25 | Google Inc. | Image adjustment using texture mask |
CN109903267A (en) * | 2019-01-22 | 2019-06-18 | 江苏恒力化纤股份有限公司 | A method of based on image processing techniques test network wire network degree |
CN111415349A (en) * | 2020-03-27 | 2020-07-14 | 江苏恒力化纤股份有限公司 | Method for detecting polyester filament yarn based on image processing technology |
CN112365452A (en) * | 2020-10-26 | 2021-02-12 | 江苏恒力化纤股份有限公司 | Network wire network point detection method based on bilateral images |
Also Published As
Publication number | Publication date |
---|---|
CN113393444B (en) | 2023-06-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110163853B (en) | Edge defect detection method | |
CN113643289B (en) | Fabric surface defect detection method and system based on image processing | |
CN108364291A (en) | Grey cloth rapid detection method based on computer vision technique | |
CN111223093A (en) | AOI defect detection method | |
CN116977358B (en) | Visual auxiliary detection method for corrugated paper production quality | |
CN114842007B (en) | Textile wear defect detection method based on image processing | |
CN114897894B (en) | Method for detecting defects of cheese chrysanthemum core | |
CN112330598B (en) | Method, device and storage medium for detecting stiff yarn defects on chemical fiber surface | |
CN111415349B (en) | Polyester filament yarn detection method based on image processing technology | |
CN115131348B (en) | Method and system for detecting textile surface defects | |
CN106780464A (en) | A kind of fabric defect detection method based on improvement Threshold segmentation | |
CN113177924A (en) | Industrial production line product flaw detection method | |
CN114998321B (en) | Textile material surface hairiness degree identification method based on optical means | |
CN115063424B (en) | Textile bobbin yarn detection method based on computer vision | |
CN110458809B (en) | Yarn evenness detection method based on sub-pixel edge detection | |
CN112435235A (en) | Seed cotton impurity content detection method based on image analysis | |
CN116563276B (en) | Chemical fiber filament online defect detection method and detection system | |
CN109387524A (en) | Thread defect detection method and device based on linearly polarized photon | |
CN115330769B (en) | Defect detection method for aluminum pipe surface scratching and indentation | |
CN113393444A (en) | Dacron DTY network point detection method based on image processing technology | |
CN111402225A (en) | Cloth folding false detection defect discrimination method | |
CN115294119B (en) | Machine vision-based method for detecting stains in inner grooves of heads of plum-blossom-shaped threads | |
CN115311264B (en) | Fabric flaw line defect identification method for textile production | |
CN115294097A (en) | Textile surface defect detection method based on machine vision | |
CN109211937B (en) | Detection system and detection method for bending defect of elastic braid of underwear |
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 |