CN113538489A - Method for measuring fiber diameter of non-woven fabric - Google Patents
Method for measuring fiber diameter of non-woven fabric Download PDFInfo
- Publication number
- CN113538489A CN113538489A CN202110813367.5A CN202110813367A CN113538489A CN 113538489 A CN113538489 A CN 113538489A CN 202110813367 A CN202110813367 A CN 202110813367A CN 113538489 A CN113538489 A CN 113538489A
- Authority
- CN
- China
- Prior art keywords
- image
- diameter
- fiber
- woven fabric
- pixel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
Abstract
The invention discloses a method for measuring the fiber diameter of a non-woven fabric, and belongs to the field of textile detection. The method comprises the steps of collecting a non-woven fabric fiber net image, preprocessing the non-woven fabric fiber net image, extracting contour curves of upper and lower edges of fibers in the preprocessed image, scanning the contour curve image one by pixel points in the column direction of the non-woven fabric fiber image from top to bottom, obtaining a pixel point set, fitting the pixel point set to a neural network function, solving the fiber diameter by using a fitting equation of the neural network function, and obtaining the most credible diameter distribution interval by adopting a K-means clustering algorithm. The invention realizes the automatic measurement of the fiber diameter of the non-woven fabric by utilizing the image processing technology, the measurement method has convenient sampling and simple operation, saves time and labor compared with the traditional manual measurement, is not influenced by the subjective factors of human beings, greatly reduces the workload in the measurement process and has wide application prospect.
Description
Technical Field
The invention relates to the field of textile detection, in particular to a method for measuring the fiber diameter of a non-woven fabric.
Background
The non-woven fabric takes short fibers or filaments as raw materials, and the raw materials are directionally or randomly arranged to be spun into a non-woven fabric sample without interweaving warp and weft. The raw material fibers used have a direct influence on the properties of the nonwoven. The fiber diameter affects the bulk density, frictional properties, strength, and hand of the nonwoven fabric.
Due to the disorder and randomness of the fiber raw material arrangement, the diameter measurement of single fibers is not slightly hindered, and the more traditional measurement methods which are widely used at present comprise an intuitive method and an optical microscope projection method. The direct viewing method mainly adopts a non-woven fabric sample electron microscope photo, then directly measures the fiber diameter on an image by using a measuring ruler with accurate scales, and the conversion is carried out according to the proportion. The method is used for industrial detection of the diameters of the melt-blown superfine fiber and the flash spun fiber.
The optical microscope projection method requires that the non-woven fabric fiber is made into a slice and placed on an object stage, the slice is projected on a screen after being amplified by a microscope, the fiber image on the projection must be guaranteed to be complete, a graduated scale or a wedge-shaped scale is selected during measurement, and the average value is removed repeatedly.
The two methods are both manual measurement essentially, and have the defects of long time consumption, low measurement efficiency, easy influence by subjective factors to generate errors and great limitation.
Therefore, how to provide a measuring method for automatically detecting the fiber diameter of the nonwoven fabric by using an image processing technology is a problem to be solved by those skilled in the art.
Disclosure of Invention
In view of the above, the present invention provides a method for measuring the fiber diameter of a nonwoven fabric. The measuring method provided by the invention is convenient to sample and simple to operate, saves time and labor compared with the traditional manual measurement, is not influenced by artificial subjective factors, greatly reduces the workload in the measuring process and has wide application prospect.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for measuring the fiber diameter of a non-woven fabric comprises the following steps:
s1, image acquisition: collecting a nonwoven web image of a nonwoven sample;
s2, image preprocessing: preprocessing the acquired nonwoven fabric web image;
s3, contour extraction: extracting contour curves of the upper edge and the lower edge of the fiber in the preprocessed image;
s4, edge tracing: scanning contour curve images one by pixel points from top to bottom in the column direction of the non-woven fabric fiber image to obtain a pixel point set curve;
s5, neural network curve fitting: fitting a curve of the pixel point set into a neural network function;
s6, calculating the diameter: solving the fiber diameter by utilizing a fitting equation of a neural network function;
s7, true diameter calculation: and obtaining the most reliable diameter distribution interval by adopting a K-means clustering algorithm.
Further, the image acquisition comprises the steps of placing a 2cm multiplied by 2cm non-woven fabric sample on an objective table of a video microscope, adjusting a light source, adjusting the magnification of an eyepiece and an objective lens, and transmitting the acquired fiber web to a computer screen through an acquisition card of a video camera to obtain a non-woven fabric fiber web image.
Further, the image preprocessing comprises a graying processing and a binarization processing.
Further, the graying processing comprises solving a gray map by adopting a weighted average method on the basis of the perception characteristics of the red, green and blue color components.
Further, the binarization processing includes scanning each pixel point of the image, setting the pixel point with a value less than 127 as 0, setting the color as black, setting the pixel point with a value greater than or equal to 127 as 255, and setting the color as white.
Further, the contour extraction comprises the steps of extracting pixel points of the contour of the upper edge and the lower edge of the fiber in the binary image by adopting a Laplacian operator, and obtaining two clear curves after extraction.
Further, the edge tracing includes scanning the contour curve image from top to bottom one by one from the row direction of the non-woven fabric fiber image, determining the top edge when the first white pixel is encountered, then scanning eight neighborhood pixels by taking the first white pixel as the center, tracing the position of the white pixel with the value of 255, continuing scanning eight neighborhood tracing by taking the two white pixels as the center, respectively tracing 20 pixels in the left and right directions, and setting the pixel as a pixel set.
Further, the neural network curve fitting comprises fitting a pixel point set by adopting a neural network function, adding k repeated central points in a network training set, controlling an error within a range of 0.01, wherein the error is an absolute value of a difference between a coordinate obtained by substituting a central point coordinate into a fitting equation and an original coordinate, keeping other parameters in the fitting equation unchanged, changing a constant value to enable a neural network curve to truly pass through the central point, increasing the weight of the central point by utilizing the algorithm, and increasing the weight of the central point in the network training set to enable the fitted curve to pass through an edge central point.
Further, the diameter calculation includes calculating a slope of a center point after obtaining a fitting equation, further calculating a normal direction equation of the center point, tracking the number of pixels along the normal direction, and converting actual lengths to calculate a fiber diameter, collecting n columns in the column direction of the sample image, and collecting n rows in the row direction to obtain m diameter lengths.
Further, the real diameter calculation comprises the step of obtaining an interval with the most compact diameter distribution by adopting a K-means clustering algorithm, so as to obtain the most reliable diameter distribution interval.
The method has the advantages that the automation of the detection of the fiber diameter of the non-woven fabric is realized by utilizing the image processing technology, the method is convenient to sample and simple to operate, time and labor are saved compared with the traditional manual measurement, the method is not influenced by the subjective factors of workers, the measurement result is accurate, the method has extremely high reference value, the workload in the measurement process is greatly reduced, and the method has wide market prospect.
Drawings
FIG. 1 is a flow chart of a diameter measuring method according to the present invention.
FIG. 2 is a drawing of a grayed nonwoven fiber sample of the present invention.
FIG. 3 is a drawing of a sample of a binarized nonwoven fabric fiber according to the present invention.
FIG. 4 is a schematic representation of the contour extraction effect of a fiber sample of a nonwoven fabric of the present invention.
FIG. 5 is a schematic diagram of an edge-tracking fitting curve according to the present invention.
FIG. 6 is a schematic diagram showing the calculation results of K-means.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
Example 1
As shown in fig. 1, the present invention provides a method for measuring the fiber diameter of a nonwoven fabric, comprising the steps of:
s1, image acquisition: collecting a nonwoven web image of a nonwoven sample;
s2, image preprocessing: preprocessing the acquired nonwoven fabric web image, graying the nonwoven fabric web image, and acquiring samples of 4 different areas, as shown in fig. 2; then, performing binarization processing on the 4 grayed samples, as shown in fig. 3;
s3, contour extraction: extracting contour curves of upper and lower edges of fibers in the preprocessed image, and extracting contours of the upper and lower edges of the fibers by using a Laplacian operator to obtain two clear curves, as shown in FIG. 4;
s4, edge tracing: scanning the contour curve image one by one pixel point from top to bottom in the column direction of the non-woven fabric fiber image to obtain a pixel point set curve, as shown in fig. 5;
s5, neural network curve fitting: fitting a curve of the pixel point set into a neural network function;
s6, calculating the diameter: solving the fiber diameter by utilizing a fitting equation of a neural network function;
s7, true diameter calculation: the most reliable diameter distribution interval is obtained by adopting a K-means clustering algorithm, as shown in FIG. 6, wherein the ordinate is the value of Gap Statistc, and the abscissa is the value of K.
The image acquisition comprises the steps of placing a 2cm multiplied by 2cm non-woven fabric sample on an objective table of a video microscope, adjusting a light source to proper intensity, adjusting the magnification of an ocular lens and an objective lens, and transmitting the acquired fiber web to a computer screen through an acquisition card of a video camera to obtain a non-woven fabric fiber web image.
The image preprocessing comprises gray level processing and binarization processing, the gray level processing comprises that a weighted average method is adopted to solve a gray level image on the basis of fully considering the perception characteristics of red, green and blue color components, the gray level processing mainly has the effects of reducing the dimension of an image matrix and improving the operation speed of the image processing, the binarization processing comprises scanning each pixel point of the image, setting the pixel point with the value less than 127 as 0, setting the color as black, setting the pixel point with the value more than or equal to 127 as 255 and setting the color as white, the image binarization has the advantages that the outline can be more clearly identified, the target fiber position is only related to the position of the point with the pixel point of 0 or 255 and is unrelated to the multi-level value of the pixel, so that the subsequent processing becomes simple, the data processing amount is small, the operation speed can be improved, and the unimportant characteristics caused in diameter detection can be further removed, is beneficial to the effective implementation of the next step of edge extraction.
The method is characterized in that the diameter of the non-woven fabric is measured, the upper edge contour and the lower edge contour of the fiber need to be extracted, two curves are obtained after extraction, and the contour extraction provides possibility for calculating the diameter by using a geometric method subsequently, so that the key point of the non-woven fabric fiber diameter measurement is the extraction of the edge contour of a target single fiber. The contour extraction identification object is a pixel point in a binary image, the gray value difference between a target pixel point and a background pixel point is large, and two clear curves are obtained after the upper edge contour and the lower edge contour of the fiber are extracted by adopting a Laplacian operator.
The edge tracking comprises the steps of scanning contour curve images one by one from top to bottom in the row direction of the non-woven fabric fiber image, judging the upper edge when the first white pixel point is encountered, then scanning eight neighborhood pixel points by taking the point as the center, tracking the position of the white pixel point with the value of 255, and then continuously scanning eight neighborhood tracking by taking the two points as the center. Tracking 20 pixels in the left and right directions respectively, and setting the pixels as a pixel set.
The neural network curve fitting comprises fitting a pixel point set by a neural network function, wherein the formed curve is a linear equation of two or a quadratic equation of two, k repeated central points are added in a network training set, and the error is controlled within the range of 0.01, wherein the error is the equation y which is obtained by substituting the coordinate of the central point x into the fitting equation y which is k2x2+k1The absolute value of the difference between the y coordinate obtained in x + b or y-kx + b and the original y coordinate is kept constant, and the values of other parameters in the fitting equation are changed to ensure that the curve actually passes through the center point, for example, k is kept2x2+k1K in x + b1，k2And changing the value b to ensure that the curve actually passes through the central point. The weight of the central point is increased by using the algorithm, and the weight of the central point in the network training set is increased to enable the fitted curve to pass through the edge central point.
And the diameter calculation comprises the steps of calculating the slope of the central point after the function equation of the edge fitting line is obtained, and further calculating the normal direction equation of the central point. The number of pixel points is tracked along the normal direction, the actual length is converted, so that the fiber diameter is obtained, n rows are collected in the row direction of the sample image according to the method, and n rows are adopted in the row direction, so that m diameter lengths are obtained.
Obtaining the diameter length with errors in the m diameters by adopting a K-means clustering algorithm to obtain the interval with the most compact diameter distribution so as to obtain the most credible diameter distribution interval, obtaining the real diameter d, and obtaining the K value category:
Gap(K)＝E(logDk)-logDk
wherein DkAs a loss function, here E (logD)k) Is referred to as logDkThe expectation is that the value is usually generated by Monte Carlo simulation, and we randomly generate as many random samples as the original samples in the area where the samples are located according to uniform distribution, and perform K-Means on the random samples to obtain Dk. Repeating the above steps for a plurality of times, usually 20 times, obtaining 20 logDsk. Averaging these 20 values yields E (logD)k) Can finally calculate the Gap Statisitc. In this embodiment, when K is 3, Gap (K) has the largest value, so that the optimal cluster number is K3.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the technical scope of the present invention, so that any minor modifications, equivalent changes and modifications made to the above embodiment according to the technical spirit of the present invention are within the technical scope of the present invention.
Claims (10)
1. A method for measuring the fiber diameter of a non-woven fabric is characterized by comprising the following steps: the method comprises the following steps:
s1, image acquisition: collecting a nonwoven web image of a nonwoven sample;
s2, image preprocessing: preprocessing the acquired nonwoven fabric web image;
s3, contour extraction: extracting contour curves of the upper edge and the lower edge of the fiber in the preprocessed image;
s4, edge tracing: scanning contour curve images one by pixel points from top to bottom in the column direction of the non-woven fabric fiber image to obtain a pixel point set;
s5, neural network curve fitting: fitting the pixel point set to a neural network function;
s6, calculating the diameter: solving the fiber diameter by utilizing a fitting equation of a neural network function;
s7, true diameter calculation: and obtaining the most reliable diameter distribution interval by adopting a K-means clustering algorithm.
2. The method of claim 1, wherein the image acquisition comprises placing a 2cm x 2cm sample of the nonwoven fabric on a stage of a stereomicroscope, adjusting the light source, adjusting the magnification of the eyepiece and the objective lens, and transmitting the acquired web to a computer screen via a video camera acquisition card to obtain an image of the nonwoven web.
3. The method of claim 1, wherein the image preprocessing includes a graying process and a binarization process.
4. The method of claim 3, wherein the graying comprises applying a weighted average method to obtain a gray scale map based on the three color component perception characteristics of red, green and blue.
5. A method of measuring a fiber diameter of a nonwoven fabric according to claim 3, wherein said binarization process includes scanning each pixel point of the image, the pixel point having a value less than 127 is set to 0, the color is set to black, the pixel point having a value equal to or greater than 127 is set to 255, and the color is set to white.
6. The method for measuring the fiber diameter of the non-woven fabric according to claim 5, wherein the contour extraction comprises the steps of extracting pixel points of contours of the upper edge and the lower edge of the fiber in a binary image by adopting a Laplacian operator, and obtaining two clear curves after extraction.
7. The method of claim 6, wherein the edge tracing includes scanning contour curve images from top to bottom in a row direction of the nonwoven fiber images, determining an upper edge when a first white pixel is encountered, scanning eight neighborhood pixels with the first white pixel as a center, tracing the position of the white pixel with a value of 255, continuing scanning eight neighborhood tracing with the two white pixels as a center, and tracing 20 pixels in left and right directions to set as a pixel set curve.
8. The method of claim 7, wherein the neural network curve fitting comprises fitting a pixel point set by using a neural network function, adding k repeated central points in a network training set, controlling an error within a range of 0.01, wherein the error is an absolute value of a difference between a coordinate obtained by substituting a central point coordinate into a fitting equation and an original coordinate, keeping other parameters in the fitting equation unchanged, changing a constant value to allow a neural network curve to truly pass through the central point, increasing the weight of the central point by using the algorithm, and increasing the weight of the central point in the network training set to allow the fitted curve to pass through an edge central point.
9. The method of claim 8, wherein the diameter calculation includes calculating a slope of a center point after obtaining a fitting equation, calculating a normal direction equation at the center point, tracking the number of pixels along the normal direction, and converting between actual lengths to calculate a fiber diameter, collecting n columns of the sample image in the column direction, and taking n rows of the sample image in the row direction to obtain m diameter lengths.
10. A method as claimed in claim 1, wherein said calculating of true diameter includes using K-means clustering algorithm to find the most closely distributed diameter interval, and thus the most reliable diameter distribution interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110813367.5A CN113538489B (en) | 2021-07-19 | 2021-07-19 | Method for measuring fiber diameter of non-woven fabric |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110813367.5A CN113538489B (en) | 2021-07-19 | 2021-07-19 | Method for measuring fiber diameter of non-woven fabric |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113538489A true CN113538489A (en) | 2021-10-22 |
| CN113538489B CN113538489B (en) | 2022-09-09 |
Family
ID=78100169
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110813367.5A Active CN113538489B (en) | 2021-07-19 | 2021-07-19 | Method for measuring fiber diameter of non-woven fabric |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113538489B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1359006A (en) * | 2002-01-14 | 2002-07-17 | 清华大学 | Method and system for measuring wool fiber fineness measurement |
| US20040197015A1 (en) * | 2003-04-02 | 2004-10-07 | Siemens Medical Solutions Usa, Inc. | Border detection for medical imaging |
| CN108305287A (en) * | 2018-02-02 | 2018-07-20 | 天津工业大学 | A kind of textile material fibre diameter measurement method based on phase information |
| CN109584291A (en) * | 2018-10-31 | 2019-04-05 | 东华大学 | It is a kind of based on the animal origin fineness calculation method for automatically extracting central axes |
| CN110986778A (en) * | 2019-12-25 | 2020-04-10 | 电子科技大学 | System and method for detecting size of rivet hole of carbon fiber composite material |
| WO2020089910A1 (en) * | 2018-11-02 | 2020-05-07 | Applied Materials Israel Ltd. | Method, system and computer program product for 3d-nand cdsem metrology |
| CN112330673A (en) * | 2020-12-11 | 2021-02-05 | 武汉纺织大学 | Woven fabric density detection method based on image processing |
| CN112577967A (en) * | 2021-01-06 | 2021-03-30 | 河南理工大学 | Method for detecting appearance quality of head of medicine ampoule bottle |
| CN112595265A (en) * | 2020-12-07 | 2021-04-02 | 新拓三维技术(深圳)有限公司 | Method and equipment for measuring bending radius of cable |
| CN112881042A (en) * | 2021-01-12 | 2021-06-01 | 北京铁科时代科技有限公司 | Wheel set detection system, method and medium based on laser profile |
| CN113129434A (en) * | 2021-04-28 | 2021-07-16 | 西安工程大学 | Non-woven fabric three-dimensional modeling method based on microscopic two-dimensional image sequence |
-
2021
- 2021-07-19 CN CN202110813367.5A patent/CN113538489B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1359006A (en) * | 2002-01-14 | 2002-07-17 | 清华大学 | Method and system for measuring wool fiber fineness measurement |
| US20040197015A1 (en) * | 2003-04-02 | 2004-10-07 | Siemens Medical Solutions Usa, Inc. | Border detection for medical imaging |
| CN108305287A (en) * | 2018-02-02 | 2018-07-20 | 天津工业大学 | A kind of textile material fibre diameter measurement method based on phase information |
| CN109584291A (en) * | 2018-10-31 | 2019-04-05 | 东华大学 | It is a kind of based on the animal origin fineness calculation method for automatically extracting central axes |
| WO2020089910A1 (en) * | 2018-11-02 | 2020-05-07 | Applied Materials Israel Ltd. | Method, system and computer program product for 3d-nand cdsem metrology |
| CN110986778A (en) * | 2019-12-25 | 2020-04-10 | 电子科技大学 | System and method for detecting size of rivet hole of carbon fiber composite material |
| CN112595265A (en) * | 2020-12-07 | 2021-04-02 | 新拓三维技术(深圳)有限公司 | Method and equipment for measuring bending radius of cable |
| CN112330673A (en) * | 2020-12-11 | 2021-02-05 | 武汉纺织大学 | Woven fabric density detection method based on image processing |
| CN112577967A (en) * | 2021-01-06 | 2021-03-30 | 河南理工大学 | Method for detecting appearance quality of head of medicine ampoule bottle |
| CN112881042A (en) * | 2021-01-12 | 2021-06-01 | 北京铁科时代科技有限公司 | Wheel set detection system, method and medium based on laser profile |
| CN113129434A (en) * | 2021-04-28 | 2021-07-16 | 西安工程大学 | Non-woven fabric three-dimensional modeling method based on microscopic two-dimensional image sequence |
Non-Patent Citations (3)
| Title |
|---|
| M.BIRVALSKI 等: "PIV measurements of waves and turbulence in stratified horizontal two-phase pipe flow", 《INTERNATIONAL JOURNAL OF MULTIPHASE FLOW》 * |
| 张杰 等: "基于MATLAB的摆线轮齿廓修形参数检测与反求", 《机械设计与制造》 * |
| 徐巧林 等: "基于图像处理的针织物表面纹理参数分析", 《针织工业》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113538489B (en) | 2022-09-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100561186C (en) | The method of testing and the device that are used for the textile color stability and color aberration grading | |
| CN103759662B (en) | A kind of textile yarn diameter dynamic rapid measurement device and method | |
| CN101806583B (en) | Microscopic image-based fiber fineness measurement method | |
| CN103499303B (en) | A kind of wool fineness method for automatic measurement | |
| Cybulska | Assessing yarn structure with image analysis methods1 | |
| CN102523366B (en) | Automatic fabric weaving style analyzing system and method | |
| CN113592867B (en) | Detection method based on residual binding yarns on carbon fiber cloth cover | |
| WO2023102952A1 (en) | Coiled material detection device, system and method capable of achieving real-time detection | |
| CN108921819A (en) | A kind of cloth examination device and method based on machine vision | |
| CN108444413A (en) | Ceramic wall and floor bricks flatness detecting device and method | |
| Wang et al. | Single vision based identification of yarn hairiness using adaptive threshold and image enhancement method | |
| CN111415349A (en) | Method for detecting polyester filament yarn based on image processing technology | |
| CN110458809B (en) | Yarn evenness detection method based on sub-pixel edge detection | |
| CN115100206A (en) | Printing defect identification method for textile with periodic pattern | |
| CN111724354B (en) | Image processing-based method for measuring wheat ear length and wheat ear number of multiple wheat plants | |
| Zhang et al. | Automatic inspection of yarn-dyed fabric density by mathematical statistics of sub-images | |
| CN112767384A (en) | Compensation method and device of elastic cloth gram weight online detection system | |
| Robson et al. | Cuticular scale measurements using image analysis techniques | |
| AU644164B2 (en) | Method for determining and controlling fiber luster properties | |
| CN113838081A (en) | Method and device for distinguishing color uniformity of flue-cured tobacco leaves based on machine vision | |
| CN113538489B (en) | Method for measuring fiber diameter of non-woven fabric | |
| CN113570652A (en) | Quantitative analysis method for sandstone reservoir mineral intercrystalline pores based on SEM image | |
| CN112730407A (en) | Detection device and detection method for detecting yarn hairiness index by using linear array digital camera | |
| CN111830036B (en) | Fabric density analysis method and system | |
| CN110261388A (en) | A kind of multi-angle yarn appearance digital test device and test method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |