CN110246117A - A kind of digitizing solution of yarn diameter and yarn unevenness detection - Google Patents
A kind of digitizing solution of yarn diameter and yarn unevenness detection Download PDFInfo
- Publication number
- CN110246117A CN110246117A CN201910349859.6A CN201910349859A CN110246117A CN 110246117 A CN110246117 A CN 110246117A CN 201910349859 A CN201910349859 A CN 201910349859A CN 110246117 A CN110246117 A CN 110246117A
- Authority
- CN
- China
- Prior art keywords
- image
- yarn
- gray
- filter
- value
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 12
- 230000003044 adaptive effect Effects 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 12
- 230000000877 morphologic effect Effects 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims abstract description 10
- 238000012937 correction Methods 0.000 claims abstract description 8
- 230000011218 segmentation Effects 0.000 claims abstract description 8
- 238000010191 image analysis Methods 0.000 claims abstract description 3
- 238000007781 pre-processing Methods 0.000 claims abstract description 3
- 238000000034 method Methods 0.000 claims description 20
- 239000011159 matrix material Substances 0.000 claims description 16
- 238000009826 distribution Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 description 5
- 230000035945 sensitivity Effects 0.000 description 4
- 239000003086 colorant Substances 0.000 description 2
- 230000000052 comparative effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 230000001953 sensory effect Effects 0.000 description 2
- 239000004753 textile Substances 0.000 description 2
- 229920000742 Cotton Polymers 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000007378 ring spinning Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- 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
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30124—Fabrics; Textile; Paper
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention provides the digitizing solution of a kind of yarn diameter and yarn unevenness detection, it is acquired including the image to yarn, is split to image preprocessing, to the image after pretreatment, carrying out Morphological scale-space to the image after segmentation, to the image analysis calculation after Morphological scale-space, it is characterized by: described image pretreatment is completed under windows system, under MATLAB software environment, including three gray proces, gray-level correction, adaptive median filter steps;Wherein the gray proces are using the arithmetic weight algorithm routine function write, imhist function divides in the gray-level correction Calling MATLAB to calculate image grayscale, obtain corresponding histogram, and equalization processing is carried out to histogram, the adaptive median filter Denoising Algorithm handles yarn image, can accurately and efficiently calculate yarn diameter and measure the yarn unevenness of yarn.
Description
Technical field
The present invention relates to textile technology fields, more particularly to the digitlization of a kind of yarn diameter and yarn unevenness detection
Method.
Background technique
The diameter and yarn unevenness of yarn are the important parameters for influencing the style of yarn, appearance of fabrics quality and clothes,
Very important effect is played in the technological design and production process of textile.The apparent parameter of yarn mainly includes yarn hair
Plumage, fineness, diameter irregularity etc., it is every physical that these parameters not only directly affect yarn strength, draftability, wearability etc.
Can, have an effect on the apparent style of fabric.In common yarn diameter and yarn unevenness detection method, process complexity is cumbersome, holds
Subjective factor vulnerable to detection staff influences, and causes the difficulty to the assessment of yarn Quality Grade;In addition, condenser type yarn
Line evenness fault measurement method is also easy to be influenced by the test many factors such as environment and sample to be tested temperature and humidity, is equally difficult to
For truely and accurately assessing yarn qualities.
Summary of the invention
For the drawbacks described above for overcoming the prior art, the present invention provides the number of a kind of yarn diameter and yarn unevenness detection
Change method, is adopted the technical scheme that:
A kind of this digitizing solution of yarn diameter and yarn unevenness detection, be acquired including the image to yarn,
It is split to image preprocessing, to the image after pretreatment, carries out Morphological scale-space to the image after segmentation, to morphology
Image analysis calculation that treated, it is characterised in that: described image pretreatment is under windows system, MATLAB software loop
It is completed under border, including three gray proces, gray-level correction, adaptive median filter steps;Wherein
The gray proces are that the arithmetic weight algorithm routine function as shown in formula (1) is write in MATLAB software, will be adopted
Value of the RGB yarn image collected on tri- channels R, G, B substitutes into, and then maps to obtain gray value to obtain by weighted value
Gray level image:
H=0.2989R+0.5870G+0.1140B (1)
In formula: H represents the gray value of pixel in yarn image, R, G, and B respectively represents red, green, blue color in color image
Brightness value;;
The sensory system of the mankind is different to the sensitivity of different colours, the sensitivity most sensitive, blue to green
It is relatively low not as good as green.So can increase the ratio that the channel G accounts in mapping function, slightly reduction channel B is mapping
Ratio is accounted for obtain in function.
The gray-level correction is will to obtain gray level image to carry out image enhancement, and imhist function calculates in Calling MATLAB
Image grayscale point obtains corresponding histogram, and carries out equalization processing to histogram, becomes the grey level interval of gray level image
Must expand, close to normal distribution: the program function of equalization processing is: J=histeq (I, n): I is the original image of input, J
For the image obtained after histogram equalization, n is the number of greyscale levels after equalization;
The adaptive median filter processing is the processing carried out to the image after gray-level correction, and adaptive median filter is calculated
Method is to change filter radius automatically, while determining that current pixel is according to Rule of judgment according to pre-set condition
Noise if it is replaces current pixel with neighborhood intermediate value, is not, also uses current pixel;Key step is as follows:
(1) it determines the maximum radius of filter, and calculates in the pixel grey scale of the image under current maximal filter radius
Value Imed;
The pixel number L for counting yarn evenness section, the maximum radius r of filter is determined according to Lmax;It calculates currently most
The pixel grey scale intermediate value I of image under big filter radiusmed, calculation method is as follows: indicating pixel value a in the matrix formi,j, square
Battle array uses AiIt indicates, seeks the median I of all pixels value in matrixmed;
(2) radius of filter template is determined
Filter radius is successively reduced, and judges ImedWhether matrix A is included iniIn, if ImedIn matrix AiIn, then after
It is continuous to reduce filter radius r, until ImedNot in matrix AiIn, then stop reducing filter radius, filter radius at this time is
The radius of the filter template of selection;The specific method is as follows:
……
rn=rin,jn(in=jn,Imed∈Ai)
R at this timenFor the radius of determining filter template, and find out rnThe pixel grey scale of image under filter radius
Minimum value IminWith maximum value Imax;
(3) output pixel gray value
If currently processed pixel is in [Imin, Imax] between, export current pixel;Otherwise output pixel Imed;Expression formula
It is as follows:
G (x, y)=G [f (x, y)] (2)
Wherein, f (x, y) is input picture, and g (x, y) is output image, and G is the operator to image f, acts on point (x, y)
The value of definition;
S=G (r) (3)
Wherein, r indicates the gray scale in image f, and s indicates the gray scale in image g;The two is in identical coordinate in the picture
At (x, y);Above formula can be expressed simply are as follows:
Further, the segmentation is to carry out yarn and background to pretreated image with adaptive threshold fuzziness method
Segmentation.
Further, the Morphological scale-space includes carrying out burn into expansion, micronization processes to image.
Further, described image analytical calculation, which refers to, carries out analytical calculation to the result of morphological image process, obtains
Average diameter, deviation and the yarn evenness CV value of yarn.
The invention has the benefit that
(1) yarn image is handled by adaptive median filter Denoising Algorithm, it is straight can accurately and efficiently calculates yarn
Diameter and the yarn unevenness for measuring yarn.
(2) yarn irregularity can be effectively detected in a kind of extraction of yarn diameter parameter and analysis method, improve
The accuracy rate of digital measuring yarn diameter and yarn unevenness.
Detailed description of the invention
Fig. 1 is the collected original image of Epson V700 Photo type scanner.
Fig. 2 is the image that Fig. 1 passes through gradation conversion processing.
Fig. 3 (a) is the corresponding histogram of Fig. 2, is (b) histogram of (a) after histogram, is (c) figure (b)
The corresponding image after grey level enhancement.
Fig. 4 is image of the Fig. 3 (c) after common median filtering.
Fig. 5 is image of the Fig. 3 (c) after adaptive median filter of the present invention.
Fig. 6 is image of the Fig. 5 after adaptive threshold fuzziness method is split.
Fig. 7 is image of the Fig. 6 after Morphological scale-space.
Specific embodiment
Embodiment 1, to resultant yarn mode be RING SPINNING, comb yarn process is combing, the cotton yarn that thread density is 14.21tex, is led to
It crosses USB3.0 data line and connect Epson V700 Photo type scanner with computer, set resolution of scanner to
1200dpi obtains the monochrome image that image resolution ratio is 500pi × 500pi.As shown in Figure 1.
Gray proces: under windows system, under MATLAB software environment using inventor write as shown in formula (1)
Arithmetic weight algorithm RGB image is converted to gray level image.
The method of arithmetic weight average algorithm is to follow certain weighting according to value of the RGB image on tri- channels R, G, B
Specific gravity is weighted and averaged, and then maps to obtain gray value to obtain gray level image by weighted value.The sensory system pair of the mankind
The sensitivity of different colours is different, most sensitive to green, and blue sensitivity is relatively low not as good as green.So can
To increase the ratio that the channel G accounts in mapping function, slightly reduction channel B accounts for obtain ratio in mapping function.According to following public affairs
The mapping function of formula (1) can obtain more reasonable gray level image.
H=0.2989R+0.5870G+0.1140B (1)
In formula: H represents the gray value of pixel in yarn image, R, G, and B respectively represents red, green, blue color in color image
Brightness value.As shown in Figure 2.
Imhist function divides in Calling MATLAB to calculate image grayscale, corresponding histogram is obtained, as shown in Fig. 3 (a).
And equalization processing is carried out to histogram, make the grey level interval of gray level image become to expand, close to normal distribution;Equalization
The program function of processing is: J=histeq (I, n): I is the original image of input, and J is obtained image after histogram equalization, n
For the number of greyscale levels after equalization;As shown in Fig. 3 (b).Corresponding image such as Fig. 3 (c) institute after yarn image histogram equalization
Show.
Adaptive median filter is carried out to image shown in Fig. 3 (c), key step is as follows:
(1) it determines the maximum radius of filter, and calculates in the pixel grey scale of the image under current maximal filter radius
Value Imed;
The pixel number L for counting yarn evenness section, the maximum radius r of filter is determined according to Lmax;It calculates currently most
The pixel grey scale intermediate value I of image under big filter radiusmed, calculation method is as follows: indicating pixel value a in the matrix formi,j, square
Battle array uses AiIt indicates, seeks the median I of all pixels value in matrixmed;
(2) radius of filter template is determined
Filter radius is successively reduced, and judges ImedWhether matrix A is included iniIn, if ImedIn matrix AiIn, then after
It is continuous to reduce filter radius r, until ImedNot in matrix AiIn, then stop reducing filter radius, filter radius at this time is
The radius of the filter template of selection;The specific method is as follows:
……
rn=rin,jn(in=jn,Imed∈Ai)
R at this timenFor the radius of determining filter template, and find out rnThe pixel grey scale of image under filter radius
Minimum value IminWith maximum value Imax;
(3) output pixel gray value
If currently processed pixel is in [Imin, Imax] between, export current pixel;Otherwise output pixel Imed;Expression formula
It is as follows:
G (x, y)=G [f (x, y)] (2)
Wherein, f (x, y) is input picture, and g (x, y) is output image, and G is the operator to image f, acts on point (x, y)
The value of definition;
S=G (r) (3)
Wherein, r indicates the gray scale in image f, and s indicates the gray scale in image g;The two is in identical coordinate in the picture
At (x, y);Above formula can be expressed simply are as follows:
Retained preferably by the trunk of yarn in adaptive median filter treated yarn image, interference information and yarn
Main body separates more preferable.As shown in Figure 5.
Comparative example 1,
The step of before adaptive median filter, is same as Example 1.
Common median filter process is carried out to image shown in Fig. 3 (c), as shown in Figure 4.It can be seen that treated yarn
Soft edge, unintelligible, image is distorted with respect to original image.
The trunk that can be seen that adaptive median filter treated yarn in yarn image from the comparison of Fig. 4 and Fig. 5 is protected
It stays preferably, interference information separates more preferable with yarn main body.
Embodiment 2, to the image as shown in Figure 5 after median filter process, with adaptive threshold fuzziness method into
The segmentation of row yarn and background selects a position between two peak values, for example takes the position among two peak values.Usual feelings
Condition selects peak value more reliable than selection the lowest point, can reduce the interference of noise, obtained image segmentation is more preferable, yarn master
Dry image becomes apparent from.As shown in Figure 6.
Morphological scale-space, such as Fig. 7 are carried out to the image shown in fig. 6 after adaptive threshold fuzziness method is split
It is shown.
The above content is specific preferred embodiment and comparative example is combined, further detailed description of the invention, no
It can assert that a specific embodiment of the invention is only limitted to this, for those skilled in the art to which the present invention belongs, not
Under the premise of being detached from present inventive concept, several simple deduction or replace can also be made, all shall be regarded as belonging to institute of the present invention
Claims of submission determine scope of patent protection.
Claims (4)
1. the digitizing solution of a kind of yarn diameter and yarn unevenness detection, is acquired, including the image to yarn to figure
Morphological scale-space is carried out as pre-processing, being split to the image after pretreatment, to the image after segmentation, to Morphological scale-space
Image analysis calculation afterwards, it is characterised in that: described image pretreatment is complete under image capturing system MATLAB software environment
At, including three gray proces, gray-level correction, adaptive median filter steps;Wherein
The gray proces are that the arithmetic weight algorithm routine function as shown in formula (1) is write in MATLAB software, will be collected
Value of the RGB yarn image on tri- channels R, G, B substitute into, then map to obtain gray value to obtain gray scale by weighted value
Image:
H=0.2989R+0.5870G+0.1140B (1)
In formula: H represents the gray value of pixel in yarn image, R, G, and B respectively represents the bright of red, green, blue color in color image
Angle value;
The gray-level correction is will to obtain gray level image to carry out image enhancement, and imhist function calculates image in Calling MATLAB
Gray scale point obtains corresponding histogram, and carries out equalization processing to histogram, and the grey level interval of gray level image is made to become to expand
Greatly, close to normal distribution;The program function of equalization processing is: J=histeq (I, n): I is the original image of input, and J is straight
The image obtained after side's figure equalization, n are the number of greyscale levels after equalization;
The adaptive median filter processing is the processing carried out to the image after gray-level correction, and adaptive median filter algorithm is
According to pre-set condition, change filter radius automatically, while determining that current pixel is noise according to Rule of judgment,
If it is current pixel is replaced with neighborhood intermediate value, is not, also use current pixel;Key step is as follows:
(1) it determines the maximum radius of filter, and calculates the pixel grey scale intermediate value of the image under current maximal filter radius
Imed;
The pixel number L for counting yarn evenness section, the maximum radius r of filter is determined according to Lmax;Calculate current maximum filter
The pixel grey scale intermediate value I of image under wave device radiusmed, calculation method is as follows: indicating pixel value a in the matrix formi,j, matrix use
AiIt indicates, seeks the median I of all pixels value in matrixmed;
(2) radius of filter template is determined
Filter radius is successively reduced, and judges ImedWhether matrix A is included iniIn, if ImedIn matrix AiIn, then continue to subtract
Small filter radius r, until ImedNot in matrix AiIn, then stop reducing filter radius, filter radius at this time is to choose
Filter template radius;The specific method is as follows:
……
rn=rin,jn(in=jn,Imed∈Ai)
R at this timenFor the radius of determining filter template, and find out rnThe pixel grey scale of image under filter radius is minimum
Value IminWith maximum value Imax;
(3) output pixel gray value
If currently processed pixel is in [Imin, Imax] between, export current pixel;Otherwise output pixel Imed;Expression formula is such as
Under:
G (x, y)=G [f (x, y)] (2)
Wherein, f (x, y) is input picture, and g (x, y) is output image, and G is the operator to image f, acts on point (x, y) definition
Value;
S=G (r) (3)
Wherein, r indicates the gray scale in image f, and s indicates the gray scale in image g;The two be in the picture identical coordinate (x,
Y) place;Above formula can be expressed simply are as follows:
2. the digitizing solution of a kind of yarn diameter according to claim 1 and yarn unevenness detection, it is characterised in that:
The segmentation is to carry out the segmentation of yarn and background to pretreated image with adaptive threshold fuzziness method.
3. the digitizing solution of a kind of yarn diameter according to claim 1 and yarn unevenness detection, it is characterised in that:
The Morphological scale-space includes carrying out burn into expansion, micronization processes to image.
4. the digitizing solution of a kind of yarn diameter according to claim 1 and yarn unevenness detection, it is characterised in that:
Described image analytical calculation, which refers to, carries out analytical calculation to the result of morphological image process, obtains the average diameter, partially of yarn
Difference and yarn evenness CV value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910349859.6A CN110246117A (en) | 2019-04-28 | 2019-04-28 | A kind of digitizing solution of yarn diameter and yarn unevenness detection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910349859.6A CN110246117A (en) | 2019-04-28 | 2019-04-28 | A kind of digitizing solution of yarn diameter and yarn unevenness detection |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110246117A true CN110246117A (en) | 2019-09-17 |
Family
ID=67883503
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910349859.6A Pending CN110246117A (en) | 2019-04-28 | 2019-04-28 | A kind of digitizing solution of yarn diameter and yarn unevenness detection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110246117A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113160122A (en) * | 2021-02-08 | 2021-07-23 | 武汉纺织大学 | Yarn evenness detection method based on image processing |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104515778A (en) * | 2015-01-15 | 2015-04-15 | 无锡北斗星通信息科技有限公司 | Yarn quality monitoring and control system based on image identification |
CN105303561A (en) * | 2015-09-22 | 2016-02-03 | 成都融创智谷科技有限公司 | Image preprocessing grayscale space division method |
CN107392886A (en) * | 2017-06-14 | 2017-11-24 | 国网山东省电力公司菏泽供电公司 | A kind of power equipment image processing method |
-
2019
- 2019-04-28 CN CN201910349859.6A patent/CN110246117A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104515778A (en) * | 2015-01-15 | 2015-04-15 | 无锡北斗星通信息科技有限公司 | Yarn quality monitoring and control system based on image identification |
CN105303561A (en) * | 2015-09-22 | 2016-02-03 | 成都融创智谷科技有限公司 | Image preprocessing grayscale space division method |
CN107392886A (en) * | 2017-06-14 | 2017-11-24 | 国网山东省电力公司菏泽供电公司 | A kind of power equipment image processing method |
Non-Patent Citations (3)
Title |
---|
孙巧妍等: "基于毛羽补偿与自适应中值滤波的纱线主体图像识别算法", 《纺织学报》 * |
宓超等: "《装卸机器视觉及其应用》", 31 January 2016, 上海科学技术出版社 * |
章国红等: "基于图像分析技术的纱线黑板条干检测", 《棉纺织技术》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113160122A (en) * | 2021-02-08 | 2021-07-23 | 武汉纺织大学 | Yarn evenness detection method based on image processing |
CN113160122B (en) * | 2021-02-08 | 2024-04-19 | 武汉纺织大学 | Yarn evenness unevenness detection method based on image processing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106407917B (en) | The retinal vessel extracting method and system distributed based on Dynamic Multi-scale | |
CN114529550B (en) | Textile color fastness detection method and system based on image processing | |
CN109211918B (en) | Fabric bow weft detection method based on weft trend | |
CN105791709A (en) | Automatic exposure processing method and apparatus with back-light compensation | |
CN114693676B (en) | Optical detection method and device for bleaching defects of new material textiles | |
CN107515220A (en) | A kind of detection of yarn black filoplume amount and evaluation method based on image procossing | |
CN111861937A (en) | MSR (minimum shift register) improvement-based image enhancement method and system | |
CN105095907A (en) | Cotton foreign fiber identifying method based on RBF neural network | |
CN113777033A (en) | Raw sliver defect detection method and device based on machine vision | |
CN110246117A (en) | A kind of digitizing solution of yarn diameter and yarn unevenness detection | |
CN115266732A (en) | Carbon fiber tow defect detection method based on machine vision | |
CN114842013A (en) | Textile fiber strength detection method and system | |
CN112435235A (en) | Seed cotton impurity content detection method based on image analysis | |
CN113936001B (en) | Textile surface flaw detection method based on image processing technology | |
CN117808800B (en) | Intelligent assessment method and system for dyeing quality of textile | |
CN106203536B (en) | Feature extraction and detection method for fabric defects | |
CN117152159B (en) | Method and system for detecting printing flaws of complex cloth | |
CN109472779A (en) | A kind of yarn appearance characteristic parameter extraction and analysis method based on morphosis | |
CN116894840B (en) | Spinning proofing machine product quality detection method and system | |
CN110189298A (en) | A kind of image processing algorithm of quick detection yarn evenness | |
CN115311278B (en) | Yarn segmentation method for yarn detection | |
CN111681181A (en) | Method for evaluating fabric surface pilling degree | |
CN109671088A (en) | A kind of digitizing solution of Yarn filoplume characteristic parameter | |
CN107239761A (en) | Fruit tree branch pulling effect evaluation method based on skeleton Corner Detection | |
Pan et al. | Color clustering analysis of yarn-dyed fabric in HSL color space |
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 |