CN111507943B - Method for detecting broken filaments of polyester filaments - Google Patents
Method for detecting broken filaments of polyester filaments Download PDFInfo
- Publication number
- CN111507943B CN111507943B CN202010229519.2A CN202010229519A CN111507943B CN 111507943 B CN111507943 B CN 111507943B CN 202010229519 A CN202010229519 A CN 202010229519A CN 111507943 B CN111507943 B CN 111507943B
- Authority
- CN
- China
- Prior art keywords
- sample
- equal
- images
- diameter
- polyester
- 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.)
- Active
Links
- 229920000728 polyester Polymers 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000001514 detection method Methods 0.000 claims abstract description 20
- 238000001914 filtration Methods 0.000 claims abstract description 10
- 238000009826 distribution Methods 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims abstract description 9
- 238000004891 communication Methods 0.000 claims description 10
- 239000000835 fiber Substances 0.000 claims description 7
- 229910052731 fluorine Inorganic materials 0.000 claims description 2
- 125000001153 fluoro group Chemical group F* 0.000 claims description 2
- 238000012545 processing Methods 0.000 description 6
- 229920000297 Rayon Polymers 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000009987 spinning Methods 0.000 description 2
- 206010020112 Hirsutism Diseases 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004043 dyeing Methods 0.000 description 1
- 230000037308 hair color Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000000126 substance Substances 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
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/08—Measuring arrangements characterised by the use of optical techniques for measuring diameters
-
- 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
- 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
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/952—Inspecting the exterior surface of cylindrical bodies or wires
-
- 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 by the use of local operators
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8874—Taking dimensions of defect into account
-
- 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
- G01N2021/8883—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 involving the calculation of gauges, generating models
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30124—Fabrics; Textile; Paper
Abstract
The invention relates to a method for detecting broken filaments of polyester filaments, which comprises the following training stage: acquiring 1-line image x of hairless sample by linear array camera 1 (ii) a Using filter pair x 1 Filtering to obtain y 1 (ii) a To y 1 Carrying out binarization to obtain A 1 (ii) a Statistics A 1 The number of pixels included in the maximum connected region in (2) is set as the diameter d 1 (ii) a Repeating the above steps for N lines of images of the hairless sample to obtain the diameter of the hairless sample { d } n }; using Gaussian distribution pairs { d n Model mu and sigma 2 (ii) a (2) Using mu and sigma 2 And (3) detection: collecting K-line images { x) of to-be-detected sample through linear array camera k }; filtering with a filter to obtain y k (ii) a To y k Proceed binarization to obtain B k (ii) a Statistics B k Median diameter { d } k And the number of pixels equal to a' { p } k }; at { d k In (d) k μ + c σ orC is more than or equal to 3 and less than or equal to 5; broken filaments exist in the sample to be detected; whereas, no broken filaments are present.
Description
Technical Field
The invention belongs to the field of chemical fiber filament quality detection methods, and relates to a method for detecting broken filaments of polyester filaments.
Background
The broken filaments are the main appearance defects of the polyester filament yarns, and the quantity of the broken filaments directly influences the efficiency of downstream weaving and dyeing processes and the quality of finished products. Polyester filaments are generally produced by network processing of a plurality of very small diameter monofilaments, and fuzz is formed by stretching or breaking some of the monofilaments and protruding from the surface of the yarn body due to various external forces. In actual production, the polyester broken filaments are very fine and almost invisible to naked eyes, and can only be detected by visually observing the quantity of the broken filaments on the surface and the end face of the whole spinning cake, so that the detection of the broken filaments in the spinning cake cannot be realized. The existing patent application 201611036029.0 of the method for detecting broken filaments based on image processing is to collect viscose filament images through an industrial area-array camera and carry out a series of image processing operations on the viscose filament images to realize separation and detection of broken filaments, although the detection of the number and the length of the broken filaments can be accurately realized, the calculated amount is large, the detection speed is limited, and the method cannot be used for high-speed online detection.
Therefore, it is very important to develop a method for detecting a hair color with high detection accuracy, high efficiency, and stable detection results.
Disclosure of Invention
The invention provides a method for detecting broken filaments of polyester filaments, and aims to solve the problems in the prior art. The invention realizes the purpose of quickly and accurately detecting the position of broken filaments by acquiring the images of the polyester filaments through the linear array camera and quickly processing and analyzing each row of data.
In order to achieve the purpose, the invention adopts the following scheme:
a method for detecting polyester filament yarn broken filaments comprises the following steps:
(1) a training stage:
(1.1) acquiring 1 line of images of the hairless sample by using a line scan camera, and recording the images as x 1 ,x 1 ∈R m (R m Is a real space of m dimensions, representing x 1 Is a vector of dimension m, m being a positive integer);
(1.2) Using filters F vs. x 1 Performing a filtering operation to obtain y 1 (ii) a Filter F ═ 11111];y 1 ∈R m (R m Is a real space of m dimensions, representing y 1 Is a vector of m dimensions, m being a positive integer);
(1.4) binarization: by usingFor y 1 Proceed binarization by more thanThe assigned value of the pixel point is a and is less than or equal toThe pixel point is assigned as b to obtain a binary image A 1 ;
(1.5) obtaining diameter: statistics A 1 And A is a connected region of 1 The number of pixels contained in the maximum communication area in the polyester fiber is taken as the diameter of the polyester filament and is recorded as d 1 ;
(1.6) acquiring N-line images of the hairless sample through the line scan camera, and recording the N-line images as { x n N, N is a positive integer, 1,2,3, … …; x is the number of n ∈R m (R m Is a real space of m dimensions, x n Is a vector of dimension m, m being a positive integer); repeating the steps (1.1) - (1.5); the diameter of the polyester filament in the N-line image of the hairless sample is noted as { d n };
(1.7) modeling: using pairs of Gaussian distributions { d n Modeling is carried out to obtain the mean value mu and the variance sigma of the Gaussian distribution parameters 2 The calculation formula is as follows:
(2) using the parameters mu and sigma obtained during the training phase 2 The detection is carried out by the following steps:
(2.1) respectively acquiring K-line images of the sample to be detected through the linear array camera, and recording the K-line images as { x k Where K is 1,2,3, … …, K being a positive integer; x is a radical of a fluorine atom k ∈R m (R m Is a real space of m dimensions, x k Is a vector of m dimensions, m being a positive integer);
(2.2) Using filters F vs. x k Performing a filtering operation to obtain y k (ii) a Filter F ═ 11111];y k ∈R m (R m Is a real space of m dimensions, representing y k Is a vector of m dimensions, m being a positive integer);
(2.4) binarization: by usingFor y k Carry out binarization to be greater thanThe assigned value of the pixel point is a' and is less than or equal toThe pixel point is assigned as B' to obtain a binary image B k ;
(2.5) obtaining diameter: statistics B k And B is a region of communication in k The number of pixels contained in the maximum communication area in the polyester fiber is taken as the diameter of the polyester filament and is recorded as d k ;
The diameter of the polyester filament yarn in the K-line image of the sample to be detected is { d } k };
(2.6) statistics B k The number of the middle pixel points equal to a' is recorded as p k ;
Then systemEach binary image B obtained by counting K lines of images of a sample to be detected k The number of middle pixels equal to a' is marked as { p k };
(2.7) judging broken filaments: at { d k In (f), when d k Mu + c σ orC is more than or equal to 3 and less than or equal to 5; broken filaments exist in the K-line image of the sample to be detected; otherwise, no broken filament exists in the K-row image of the sample to be detected; wherein σ is σ 2 Solving by opening the square root; the smaller the value of c is, the stricter the judgment condition is, but the misjudgment rate is increased;
the hairless sample and the sample to be tested are filament products with the same specification, and products with different specifications need to be trained and tested again according to the method;
the linear array scanning direction of the linear array camera is perpendicular to the movement direction of polyester filaments in the sample.
According to the method for detecting the broken polyester filament yarns, a is 1, and b is 0.
According to the method for detecting the broken polyester filament yarns, a 'is 1, and b' is 0.
In the above method for detecting the polyester filament broken filaments, the value range of K is as follows: k is more than or equal to 1 and less than or equal to 10. When the K value is larger, the simultaneous judgment of multiple lines of images is indicated, and the detection precision is favorably improved.
The method for detecting the broken polyester filament yarn is characterized in that the value range of N is as follows: 5000 < N < 20000, the larger the N, the better, but the larger the N, the more time-consuming.
The conception of the invention is as follows:
the invention adopts a linear array camera to collect a single-line or multi-line image, and carries out rapid processing and analysis on the single-line or multi-line image, which comprises the following steps: firstly, carrying out single-line or multi-line image analysis on a hairless sample to obtain the diameter of a filament in the hairless sample, and modeling the filament to obtain a parameter value for judging whether a sample to be detected has hairiness; and further, analyzing the single-line or multi-line image of the sample to be detected, judging whether the single-line or multi-line image of the sample to be detected has broken filaments or not through comparison between the sample to be detected and the modeling data, and obtaining the position of the broken filaments in the sample to be detected through the position of the single-line or multi-line image in the sample to be detected. In the invention, Gaussian distribution is adopted to model the diameter of a hairless sample (filament) during modeling, the preparation expression of random variation of the diameter is realized, the false detection caused by noise interference is overcome, and the stability and the accuracy of hairless detection are improved; in addition, compared with the mode of acquiring images by an area-array camera, the detection efficiency of the invention is higher, and the requirement on acquisition conditions is lower, because the image acquisition speed of the area-array camera is limited by the sampling frame frequency, clear acquisition of high-speed moving filament images cannot be realized, and secondly, the requirement on uniformity of a light source is very high due to large image acquisition area of the area-array camera; and the linear array camera is adopted, so that the acquired images can be processed line by line, and the detection precision and stability are greatly improved.
Has the advantages that:
(1) the method for detecting the broken filaments of the polyester filaments adopts the linear array camera to acquire filament images, detects whether broken filaments exist in a sample to be detected or not through rapid processing and analysis of a single-line image, and can detect the positions and the quantity of the broken filaments;
(2) the method for detecting the broken filaments of the polyester filaments can overcome the defects of low manual detection speed and the like, and can meet the requirement of efficient and stable detection of the broken filaments in the polyester filaments in practical application.
Drawings
FIG. 1 is an image of a hairless sample collected in example 1;
FIG. 2 is an image of a fuzz collected in example 1.
FIG. 3 is an image of a hairless sample collected in example 2;
fig. 4 is an image of a haired yarn acquired in example 2, in which 1 is a row for judging whether a haired yarn is present.
Detailed Description
The present invention will be further described with reference to the following 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 can be made by those skilled in the art after reading the teaching of the present invention, and these equivalents also fall within the scope of the claims appended to the present application.
Example 1
A method for detecting polyester filament yarn broken filaments comprises the following steps:
(1) a training stage:
(1.1) acquiring 1 line of images of a hairless sample (polyester filament with the specification of 189dtex/96f) through a linear array camera, and recording the images as x 1 ,x 1 ∈R 1024 ;
(1.2) Using filters F vs. x 1 Performing a filtering operation to obtain y 1 (ii) a Filter F ═ 11111];y 1 ∈R 1024 ;
(1.4) binarization: by usingTo y 1 Carry out binarization to be greater thanIs assigned a value of 1, less than or equal toThe pixel point is assigned to be 0 to obtain a binary image A 1 ;
(1.5) obtaining diameter: statistics A 1 And A is a connected region of 1 The number of pixels contained in the maximum connected region in the middle is taken as the diameter of the polyester filament yarn and is respectively marked as d 1 =41;
(1.6) acquiring 5000 lines of images (wherein the images of continuous 300 lines are shown in figure 1) of the hairless sample by the line scan camera, and recording the images as x n Where n is 1,2,3, … … 5000, n is a positive integer, x n ∈R 1024 (ii) a Repeating the steps (1.1) - (1.5); the diameter of the polyester filament in the 5000 line image of the hairless sample is noted as { d } n };
(1.7) modeling: using pairs of Gaussian distributions { d n Modeling to obtain mu and sigma 2 :
(2) Using parameters mu and sigma obtained during the training phase 2 The detection is carried out by the following steps:
(2.1) respectively acquiring 10 lines of images of a sample to be detected (polyester filament yarn with the specification of 189dtex/96f) through a linear array camera, and recording the images as { x k Where k is 1,2,3, … …, 10; x is the number of k ∈R 1024 ;
(2.2) Using filters F vs. x k Performing a filtering operation to obtain y k (ii) a Filter F ═ 11111];y k ∈R 1024 ;
(2.4) binarization: by usingTo y k Carry out binarization to be greater thanIs assigned a value of 1, less than or equal toThe value of the pixel point is set to be 0, and a binary image B is obtained k ;
(2.5) Obtaining the diameter: statistics B k And B is a region of communication in k The number of pixels contained in the maximum communication area in the polyester fiber is taken as the diameter of the polyester filament and is recorded as d k ;
The diameter of the polyester filament yarn in the 10 lines of the acquired images of the sample to be detected is { d k }={32,31,33,35,31,36,35,37,35,33};
(2.6) statistics B k If the number of the middle pixel points is equal to 1, each binary image B obtained from 10 lines of images of the sample to be detected k The number of middle pixels equal to 1 is marked as { p k }={35,33,35,38,32,42,38,37,36,38}
(2.7) judging broken filaments: at { d k In due toThen there are broken filaments in the 10 rows of images of the sample to be tested, and the images of the broken filaments are shown in fig. 2 (in order to completely display the area of the broken filaments, fig. 2 includes 21 10 rows of images in which the broken filaments exist continuously).
Example 2
A method for detecting polyester filament yarn broken filaments comprises the following steps:
(1) a training stage:
(1.1) acquiring 1 line of images of a hairless sample (polyester filament, 167dtex/128f) by a linear array camera, and recording the images as x 1 ,x 1 ∈R 1024 ;
(1.2) Using filters F vs. x 1 Performing a filtering operation to obtain y 1 (ii) a Filter F ═ 11111];y 1 ∈R 1024 ;
(1.4) binarization: by usingFor y 1 Carry out binarization to be greater thanIs assigned a value of 1, less than or equal toThe value of the pixel point is 0 to obtain a binary image A 1 ;
(1.5) obtaining diameter: statistics A 1 And A is a connected region of 1 The number of pixels contained in the maximum connected region in the middle is taken as the diameter of the polyester filament yarn and is respectively marked as d 1 =32;
(1.6) acquiring 20000 rows of images (wherein the images of 300 continuous rows are shown in FIG. 3) of the hairless sample by the line scan camera, and recording as { x n Where n is 1,2,3, … … 20000, n is a positive integer, x n ∈R 1024 (ii) a Repeating the steps (1.1) - (1.5); the diameter of the polyester filament in 20000 rows of image of the sample without broken filament is marked as { d n };
(1.7) modeling: using pairs of Gaussian distributions { d n Modeling is carried out to obtain the mean value mu and the variance sigma of the parameters of Gaussian distribution 2 :
(2) Using the parameters mu and sigma obtained during the training phase 2 The detection is carried out by the following steps:
(2.1) respectively acquiring 1 line of images of a sample to be detected (polyester filament with the specification of 167dtex/128f) through a linear array camera, and marking as { x } 1 },x 1 ∈R 1024 ;
(2.2) Using filters F vs. x 1 Performing a filtering operation to obtain y 1 (ii) a Filter F ═ 11111];y 1 ∈R 1024 ;
(2.4) binarization: by usingFor y 1 Carry out binarization to be greater thanIs assigned a value of 1, less than or equal toThe value of the pixel point is set to be 0, and a binary image B is obtained 1 ;
(2.5) obtaining diameter: statistics B 1 And B is a region of communication in 1 The number of pixels contained in the maximum communication area in the polyester fiber is taken as the diameter of the polyester filament and is recorded as d 1 =89;
(2.6) statistics B 1 If the number of the middle pixel points is equal to 1, obtaining a binary image B from the 1-line image of the sample to be detected 1 The number of the middle pixel points equal to 1 is recorded as p k =89;
(2.7) judging broken filaments: at { d 1 In due to d 1 If the image is more than μ + c σ (i.e. 89 is more than 61.72, where c is 4), the image of the broken filament in 1 line of the sample to be tested is shown in fig. 4 (in order to completely display the area of the broken filament, fig. 4 shows the images of the adjacent lines in front and back).
Claims (3)
1. A method for detecting polyester filament yarn broken filaments is characterized by comprising the following steps:
(1) a training stage:
(1.1) acquiring 1 line of images of the hairless sample by using a line scan camera, and recording the images as x 1 ,x 1 ∈R m ,R m Is a real space of m dimensions, representing x 1 Is a vector of m dimensions, m being a positive integer;
(1.2) Using filters F vs. x 1 Performing a filtering operation to obtain y 1 (ii) a Filter F ═ 11111];y 1 ∈R m ;
(1.4) binarization: by usingFor y 1 Proceed binarization by more thanIs assigned a value of 1, less than or equal toThe value of the pixel point is 0 to obtain a binary image A 1 ;
(1.5) obtaining diameter: statistics A 1 And A is a connected region of 1 The number of pixels contained in the maximum communication area in the polyester fiber is taken as the diameter of the polyester filament and is recorded as d 1 ;
(1.6) acquiring N-line images of the hairless sample through the line scan camera, and recording the N-line images as { x n Wherein N is 1,2,3, … …, N; x is a radical of a fluorine atom n ∈R m (ii) a Repeating the steps (1.1) - (1.5); the diameter of the polyester filament in the N-line image of the hairless sample is noted as { d n };
(1.7) modeling: using pairs of Gaussian distributions { d n Modeling is carried out to obtain mean value mu and variance sigma of Gaussian distribution parameters 2 :
(2) Using parameters mu and sigma obtained during the training phase 2 The detection is carried out by the following steps:
(2.1) respectively collecting K lines of samples to be detected by a linear array cameraImage, noted as { x k Where K is 1,2,3, … …, K; x is the number of k ∈R m ;
(2.2) Using filters F vs. x k Performing a filtering operation to obtain y k (ii) a Filter F ═ 11111];y k ∈R m ;
(2.4) binarization: by usingFor y k Carry out binarization to be greater thanIs assigned a value of 1, less than or equal toThe assigned value of the pixel point is 0, and a binary image B is obtained k ;
(2.5) obtaining diameter: statistics B k And B is a region of communication in k The number of pixels contained in the maximum communication area in the polyester fiber is taken as the diameter of the polyester filament and is recorded as d k ;
The diameter of the polyester filament yarn in the K lines of images of the sample to be detected is { d k };
(2.6) statistics B k The number of the middle pixel points equal to 1 is recorded as p k ;
Then each binary image B obtained by counting K lines of images of the sample to be detected k The number of middle pixels equal to 1 is marked as { p k };
(2.7) judging broken filaments: at { d k In (f), when d k μ + c σ orC is more than or equal to 3 and less than or equal to 5; broken filaments exist in the K lines of images of the sample to be detected; otherwise, the sample to be testedNo broken filament exists in the K lines of images;
the hairless sample and the sample to be detected are filament products with the same specification;
the linear array scanning direction of the linear array camera is perpendicular to the movement direction of polyester filaments in the sample.
2. The method for detecting the broken polyester filament yarns according to claim 1, wherein the value range of K is as follows: k is more than or equal to 1 and less than or equal to 10.
3. The method for detecting the broken polyester filament yarns according to claim 1, wherein the value range of N is as follows: n is more than or equal to 5000 and less than or equal to 20000.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010229519.2A CN111507943B (en) | 2020-03-27 | 2020-03-27 | Method for detecting broken filaments of polyester filaments |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010229519.2A CN111507943B (en) | 2020-03-27 | 2020-03-27 | Method for detecting broken filaments of polyester filaments |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111507943A CN111507943A (en) | 2020-08-07 |
CN111507943B true CN111507943B (en) | 2022-08-19 |
Family
ID=71878185
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010229519.2A Active CN111507943B (en) | 2020-03-27 | 2020-03-27 | Method for detecting broken filaments of polyester filaments |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111507943B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103759662A (en) * | 2013-12-31 | 2014-04-30 | 东华大学 | Dynamic textile yarn diameter rapid-measuring device and method |
CN106709927A (en) * | 2016-12-27 | 2017-05-24 | 浙江大学 | Method for extracting target from acoustic image under complex background |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110189298A (en) * | 2019-04-18 | 2019-08-30 | 烟台南山学院 | A kind of image processing algorithm of quick detection yarn evenness |
-
2020
- 2020-03-27 CN CN202010229519.2A patent/CN111507943B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103759662A (en) * | 2013-12-31 | 2014-04-30 | 东华大学 | Dynamic textile yarn diameter rapid-measuring device and method |
CN106709927A (en) * | 2016-12-27 | 2017-05-24 | 浙江大学 | Method for extracting target from acoustic image under complex background |
Non-Patent Citations (1)
Title |
---|
图像处理技术在粘胶长丝毛丝自动检测系统中的应用;余恒炜等;《自动化技术与应用》;20171231;第36卷(第09期);第90-92页 * |
Also Published As
Publication number | Publication date |
---|---|
CN111507943A (en) | 2020-08-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107515220B (en) | Yarn blackboard hairiness amount detection and evaluation method based on image processing | |
CN114549522A (en) | Textile quality detection method based on target detection | |
CN114627125B (en) | Stainless steel tablet press surface quality evaluation method based on optical means | |
CN115330784B (en) | Cloth surface defect detection method | |
CN109507192A (en) | A kind of magnetic core detection method of surface flaw based on machine vision | |
CN115131348B (en) | Method and system for detecting textile surface defects | |
CN116630309B (en) | Cloth weft-break flaw detection method | |
CN100406849C (en) | Method for measuring non-woven fabric fiber diameter by polymer extruding method, and system | |
CN103471973A (en) | Method for determining porosity characteristics of fabric through image method | |
CN114723704A (en) | Textile quality evaluation method based on image processing | |
CN110781913B (en) | Zipper cloth belt defect detection method | |
Wang et al. | Single vision based identification of yarn hairiness using adaptive threshold and image enhancement method | |
CN106248680A (en) | A kind of engine commutator quality detecting system based on machine vision and detection method | |
CN111507942B (en) | Chemical fiber filament yarn detection device and method based on multi-view image analysis | |
CN113936001B (en) | Textile surface flaw detection method based on image processing technology | |
CN116342583A (en) | Anti-pilling performance detection method for spinning production and processing | |
CN113012105A (en) | Yarn hairiness detection and rating method based on image processing | |
CN114881960A (en) | Feature enhancement-based cloth linear defect detection method and system | |
CN112767384A (en) | Compensation method and device of elastic cloth gram weight online detection system | |
CN111507943B (en) | Method for detecting broken filaments of polyester filaments | |
Robson et al. | Cuticular scale measurements using image analysis techniques | |
CN110458809A (en) | A kind of yarn evenness detection method based on sub-pixel edge detection | |
CN112927180B (en) | Cashmere and wool optical microscope image identification method based on generation of confrontation network | |
Li et al. | A direct measurement method of yarn evenness based on machine vision | |
CN116805312A (en) | Knitted fabric quality detection method based on image processing |
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 |