CN109461136B - Method for detecting fiber distribution condition in mixed fiber product - Google Patents
Method for detecting fiber distribution condition in mixed fiber product Download PDFInfo
- Publication number
- CN109461136B CN109461136B CN201811099487.8A CN201811099487A CN109461136B CN 109461136 B CN109461136 B CN 109461136B CN 201811099487 A CN201811099487 A CN 201811099487A CN 109461136 B CN109461136 B CN 109461136B
- Authority
- CN
- China
- Prior art keywords
- image
- fiber
- target
- fibers
- original
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- 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
- G01N2021/8444—Fibrous material
-
- 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)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Nonwoven Fabrics (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method for detecting fiber distribution condition in a mixed fiber product, which comprises the following steps: firstly, acquiring an original image of a mixed fiber product, and denoising and graying to obtain a low-noise gray image; setting any fiber as a target or non-target fiber; thirdly, cutting the image of 'one' into a small pixel image, and selecting a proper threshold value to process the image; extracting a non-target fiber characteristic value as noise, performing two-dimensional multistage stochastic resonance on the image of the third step, and extracting a target fiber according to a result; fifthly, carrying out binarization on the image of 'four', recombining the small images into a binarized image with the original size according to the original cutting sequence, carrying out the next step if the binarized image can show the target fiber contour, and returning to 'four' if the binarized image can not show the target fiber contour; and sixthly, counting the number of target fiber pixel points of the restored image, and giving a fiber distribution condition numerical value of the mixed fiber product. The method highlights the target fibers by extracting the characteristic values of the target fibers and the non-target fibers and removing the non-target fibers, and has the advantages of simple operation and high processing precision.
Description
Technical Field
The invention relates to the field of non-woven equipment, in particular to the detection of fiber distribution condition in a mixed fiber product.
Background
Along with the continuous development of image processing technology, because of the superiorities of high processing precision, good reproducibility, processing diversity and the like, the technology is widely used for representing the structural characteristics of the fiber web, and mainly comprises a plurality of applications including fiber orientation distribution research of the fiber web of non-woven materials, porosity detection of the fiber web and uniformity measurement of the fiber web, so as to obtain better application effects. The method combines a multistage stochastic resonance technology, can practically solve the problems by an image processing method, and has the advantages of high speed, high efficiency, high accuracy and the like.
At present, the method for researching the fiber distribution characteristics generally adopts image fusion to obtain the fiber orientation, removes noise and noise impurity points by utilizing morphological corrosion and expansion, and calculates the porosity by utilizing threshold segmentation; the method comprises the steps of acquiring a whole image, wherein the whole image is subjected to linear transformation, wherein the linear transformation comprises a contour boundary, a fiber mesh, a fiber distribution, a corrosion boundary, an expansion boundary and a non-target fiber boundary, wherein the contour boundary can be expanded by the aid of the expansion, the gaps in the mesh are removed to highlight the fiber mesh, the image is subjected to threshold segmentation, and a proper threshold is selected for processing the acquired whole image so as to study the fiber distribution; then, qualitatively and quantitatively analyzing the distribution condition of the target fibers by utilizing an image processing technology; and finally, drawing a target fiber pixel point distribution histogram according to the distribution condition of the target fibers.
Disclosure of Invention
The invention aims to provide a method for detecting the fiber distribution condition in a mixed fiber product, which can obtain the fiber distribution condition in a mixed fiber web so as to qualitatively and quantitatively analyze the structure and the performance of the mixed fiber web.
In order to solve the above technical problems, the method for detecting the fiber distribution condition in the mixed fiber product in the technical scheme adopted by the invention has the basic flow as shown in fig. 1, and specifically comprises the following steps:
firstly, collecting an original image of a product formed by mixing a plurality of fibers, and carrying out denoising and graying processing on the image to obtain a low-noise grayscale image;
secondly, according to the actual needs of engineering, any one or more fibers can be set as target fibers or non-target fibers by utilizing the difference of the photosensitivity of each fiber in the mixed fiber product.
And thirdly, cutting the low-noise gray level image integrally in a certain size and proportion according to actual precision requirements of different projects, and then selecting a proper threshold value according to the optimal imaging effect to process each cut image respectively.
Extracting characteristic values of the set non-target fibers as noise, inputting each processed cut image into two-dimensional multi-cascade stochastic resonance for processing, and extracting target fibers according to the processed result;
fifthly, performing binarization processing on each cut image of the extracted target fibers, and then recombining all the images into a binarization image with an original size according to an original cutting sequence, if the binarization image can show the target fiber contour, continuing to perform the next step, and if the target fiber contour can not be shown, directly returning to the fourth step for processing again;
and sixthly, counting the number of pixel points occupied by the target fibers of the restored image, and giving an index value of the distribution condition of the target fibers and the non-target fibers in the mixed fiber product.
Drawings
FIG. 1 is a flow chart of the present invention.
FIG. 2 is an original image of a glass/polyester fiber mixed fiber web image acquired in the present invention.
FIG. 3 is a graph of de-noising an original image of a glass/polyester fiber mixed fiber network graph according to the present invention.
FIG. 4 is an image of a glass/polyester fiber hybrid web of the present invention after inversion and order reduction.
FIG. 5 is a cut-away view of a small pixel after the talk-back stage of the present invention.
FIG. 6 is an image of a small pixel after a threshold of 0.04 according to the present invention.
FIG. 7 is a small pixel image after processing with a threshold of 0.08 according to the present invention.
FIG. 8 is the binarized image after threshold 0.04 processing according to the present invention.
FIG. 9 is a binarized image after threshold 0.08 processing according to the present invention.
Fig. 10 is a binary restoration image according to the present invention.
FIG. 11 shows the number of pixels in each column containing glass fibers according to the present invention.
FIG. 12 shows the number of pixels in each row containing glass fibers according to the present invention.
Fig. 13 is an original image of an image of a basalt/polyester fiber hybrid fiber web acquired in the present invention.
FIG. 14 is a noise reduction image of an original image of the basalt/polyester fiber hybrid fiber web of the present invention.
FIG. 15 is an image of a basalt/polyester fiber hybrid web after inversion and downscaling processing in accordance with the present invention.
Fig. 16 is a cut-away view of a small pixel after the talk-back stage of the present invention.
FIG. 17 is a small pixel image after processing with a threshold of 0.10 according to the present invention.
FIG. 18 is a small pixel image after a threshold of 0.06 process according to the present invention.
FIG. 19 is the binarized image after threshold 0.10 processing according to the present invention.
FIG. 20 is a binarized image after threshold 0.06 processing according to the present invention.
Fig. 21 shows a binarized restored image by one stochastic resonance processing according to the present invention.
Fig. 22 shows a binary restored image by the secondary stochastic resonance processing according to the present invention.
Fig. 23 shows the number of pixel points of basalt fiber contained in each line of the present invention.
Fig. 24 shows the number of pixel points containing basalt fiber per line according to the invention.
Detailed Description
Example 1:
taking a glass fiber/polyester fiber mixed fiber net product as an example, the fiber proportion and the grouping are shown in table 1 to illustrate the feasibility of the method.
TABLE 1
First, a fiber web image prepared by the 4 th group of mixed fiber ratios in table 1 is randomly acquired by an image acquisition device, the pixel size is 3000 pixels × 4000 pixels (as shown in fig. 2), and the acquired image is subjected to denoising and graying processing by a sobel filtering method and a weighted average value method (as shown in fig. 3).
Because the photosensitive capacities of the glass fiber and the polyester fiber are different, by utilizing the characteristic, the white part in the graph 2 is the glass fiber, and the black part is the polyester fiber.
Firstly, carrying out negation and order reduction processing on an acquired original image by using Matlab, wherein the result is shown in FIG. 4; cutting the image after the reduction into small pixel images with the pixel size of 32 multiplied by 52 as shown in fig. 5, and then respectively processing the small pixel images by adopting different thresholds according to the principle that the target fibers are as clear and strong in fidelity on the image as possible and the non-target fibers are displayed as little as possible as shown in fig. 6 and 7; then, binarization processing is performed on the images processed under the different thresholds, as shown in fig. 8 and 9.
Extracting a set gray information characteristic value of the non-target fiber, adding noise to the gray information characteristic value, then performing normalization processing, then respectively performing row expansion and column expansion on the gray information characteristic value, and sequentially performing stochastic resonance processing (parameters are respectively Gaussian white noise, the noise intensity is 4, h is 0.1, a is 6, and b is 12) to obtain a two-dimensional recovery small image;
carrying out binarization processing on the small images obtained by adopting the method, and then recombining all the images into a binarization image with the original size according to the original cutting sequence, as shown in FIG. 10, it can be seen from the image that the target fiber contour can be shown, so that the calculation does not need to be carried out again after the last step;
the binarized image has only two types of black pixel points and white pixel points, the number of pixel points in each row and each column of the target fiber in the restored binarized image, namely the number of white pixel points, is counted, and a histogram is drawn, as shown in fig. 11 and 12.
Example two
In order to prove that the present patent can be applied to other types of mixed fiber products, basalt fiber/polyester fiber mixed fiber net products are taken as an example, and the fiber proportion and the grouping are shown in table 2.
TABLE 2
The image processing flow is shown in fig. 1, and the specific steps are as follows:
first, a web image made of the 4 th group of mixed fiber ratios in table 2 was randomly acquired by an image acquisition device, the pixel size was 3000 pixels × 4000 pixels (as shown in fig. 13), and the acquired image was subjected to denoising and graying by a sobel filtering method and a weighted average method (as shown in fig. 14).
Because the photosensitive capacities of the glass fiber and the polyester fiber are different, by utilizing the characteristic, the white part in the graph 13 is basalt fiber, and the black part is polyester fiber.
Firstly, Matlab is used for carrying out negation and order reduction processing on an acquired original image, and the result is shown in FIG. 15; cutting the image after the reduction into small pixel images with the pixel size of 32 multiplied by 52 as shown in fig. 16, and then respectively processing the small pixel images by adopting different thresholds according to the principle that the target fibers are as clear and as high as possible on the image and the non-target fibers are displayed as little as possible as shown in fig. 17 and fig. 18; then, binarization processing is performed on the images processed under the different thresholds, as shown in fig. 19 and 20.
Extracting a set gray information characteristic value of the non-target fiber, adding noise to the gray information characteristic value, then performing normalization processing, then respectively performing row expansion and column expansion on the gray information characteristic value, and sequentially performing stochastic resonance processing (parameters are respectively Gaussian white noise, the noise intensity is 4, h is 0.1, a is 6, and b is 12) to obtain a two-dimensional recovery small image; carrying out binarization processing on the small images obtained by adopting the method, and then recombining all the images into a binarization image with the original size according to the original cutting sequence, as shown in fig. 21, it can be seen from the image that the target fiber contour can be displayed yet is not clear, so that the calculation needs to be carried out again in the last step; recalculating, re-extracting the set gray information characteristic value of the non-target fiber, adding noise to the gray information characteristic value, then performing normalization processing, then respectively performing row expansion and column expansion on the gray information characteristic value, and sequentially performing stochastic resonance processing (parameters are white gaussian noise, the noise intensity is 4, h is 0.1, a is 6, b is 12, the second-level stochastic resonance parameter is h is 0.1, a is 5, and b is 10) to obtain a two-dimensional recovery small image; the small images obtained by the method are subjected to binarization processing, and then all the images are recombined into a binarization image with the original size according to the original cutting sequence, as shown in fig. 22, it can be seen from the binarization image that the target fiber contour can be displayed, and the previous step is not required to be returned for recalculation.
The binarized image is only composed of black pixels and white pixels, the number of pixels in each row and each column of the target fiber in the restored binarized image, namely the number of white pixels, is counted, and a histogram is drawn, as shown in fig. 23 and fig. 24.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered as the technical solutions and the inventive concepts of the present invention within the technical scope of the present invention.
Claims (3)
1. A method for detecting fiber distribution in a mixed fiber product is characterized by comprising the following steps:
acquiring an original image of a product formed by mixing multiple fibers, and carrying out denoising and graying processing on the image to obtain a low-noise grayscale image;
secondly, according to the actual engineering requirements, any one or more fibers can be set as target fibers or non-target fibers by utilizing the difference of the photosensitivity of each fiber in the mixed fiber product;
cutting the low-noise gray level image integrally in a certain size and proportion according to actual precision requirements of different projects, and then selecting a proper threshold value according to the optimal imaging effect to process each cut image respectively;
extracting characteristic values of the set non-target fibers as noise, inputting each processed cut image into two-dimensional multi-cascade stochastic resonance for processing, and extracting target fibers according to the processed result;
fifthly, carrying out binarization processing on each cut image of the extracted target fibers, then recombining all the images into a binarization image with the original size according to the original cutting sequence, continuing to carry out the next step if the binarization image can show the target fiber contour, and directly returning to the fourth step to carry out the processing again if the target fiber contour cannot be shown;
and sixthly, counting the number of pixel points occupied by the target fibers of the restored image, and giving an index value of the distribution condition of the target fibers and the non-target fibers in the mixed fiber product.
2. A method as claimed in claim 1, wherein the step of cutting the original image comprises cutting the original image to obtain a cut image, and applying a threshold to the cut image.
3. The method of claim 1, wherein the two-dimensional multi-cascade stochastic resonance method is performed by increasing the number of stages to enhance the algorithmic effect.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811099487.8A CN109461136B (en) | 2018-09-20 | 2018-09-20 | Method for detecting fiber distribution condition in mixed fiber product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811099487.8A CN109461136B (en) | 2018-09-20 | 2018-09-20 | Method for detecting fiber distribution condition in mixed fiber product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109461136A CN109461136A (en) | 2019-03-12 |
| CN109461136B true CN109461136B (en) | 2022-09-27 |
Family
ID=65606837
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811099487.8A Active CN109461136B (en) | 2018-09-20 | 2018-09-20 | Method for detecting fiber distribution condition in mixed fiber product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109461136B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112164085B (en) * | 2020-09-28 | 2023-08-18 | 华南理工大学 | Fiber image segmentation and diameter statistics method based on image processing |
| CN113592811B (en) * | 2021-07-29 | 2023-08-22 | 常州大学 | Melt-blown cloth thickness consistency detection method based on image processing |
| CN113610852B (en) * | 2021-10-10 | 2021-12-10 | 江苏祥顺布业有限公司 | Yarn drafting quality monitoring method based on image processing |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101241082A (en) * | 2008-03-14 | 2008-08-13 | 东华大学 | Nonwoven fibric fibre orientation distribution measuring systems and method |
| CN101320476A (en) * | 2008-07-04 | 2008-12-10 | 中国农业大学 | Cotton foreign fiber image processing system and method |
| CN102622602A (en) * | 2012-02-28 | 2012-08-01 | 中国农业大学 | Cotton foreign fiber image online dividing method and cotton foreign fiber image online dividing system |
| CN103020609A (en) * | 2012-12-30 | 2013-04-03 | 上海师范大学 | Complex fiber image recognition method |
| CN107343115A (en) * | 2016-05-02 | 2017-11-10 | 佳能株式会社 | Image processing apparatus, image processing method and non-transitory computer-readable storage media |
-
2018
- 2018-09-20 CN CN201811099487.8A patent/CN109461136B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101241082A (en) * | 2008-03-14 | 2008-08-13 | 东华大学 | Nonwoven fibric fibre orientation distribution measuring systems and method |
| CN101320476A (en) * | 2008-07-04 | 2008-12-10 | 中国农业大学 | Cotton foreign fiber image processing system and method |
| CN102622602A (en) * | 2012-02-28 | 2012-08-01 | 中国农业大学 | Cotton foreign fiber image online dividing method and cotton foreign fiber image online dividing system |
| CN103020609A (en) * | 2012-12-30 | 2013-04-03 | 上海师范大学 | Complex fiber image recognition method |
| CN107343115A (en) * | 2016-05-02 | 2017-11-10 | 佳能株式会社 | Image processing apparatus, image processing method and non-transitory computer-readable storage media |
Non-Patent Citations (8)
| Title |
|---|
| "Influence of selected parameters of the spinning process on the state of mixing of fibers of a cotton/polyester-fibre blend yarn";Cyniak，D，等;《FIBERS & TEXTTILES IN EASTERN EUROPE》;20061001;全文 * |
| "Prediction of the Pore Size Distribution in Spunbond-Needlepunched Nonwoven Geotextiles Based on a Stochastic Simulation";zhang heng，等;《 2015 8th International Conference on Intelligent Computation Technology and Automation (ICICTA)》;20160519;全文 * |
| "图像二维随机共振研究";赵尔华;《《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》》;20120815;全文 * |
| "水刺非织造Delta高速杂乱梳理成网工艺的研究";吴凯辉;《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅰ辑》;20080615;全文 * |
| 一种用于纤维增强复合材料微观结构图像的阈值分割算法;万永菁等;《华东理工大学学报(自然科学版)》;20080415(第02期);全文 * |
| 二维随机共振参数调节的图像处理;冷永刚等;《天津大学学报》;20111015(第10期);全文 * |
| 图像识别在羊绒羊毛检测中的应用研究;杨潇等;《广西纺织科技》;20100625(第03期);全文 * |
| 山羊绒和细绵羊毛纤维的形态特征分析;彭伟良等;《上海纺织科技》;20051128(第11期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109461136A (en) | 2019-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110222306B (en) | Improved modal decomposition method suitable for internal solitary wave test flow field analysis and reconstruction | |
| CN111274865A (en) | Remote sensing image cloud detection method and device based on full convolution neural network | |
| CN109461136B (en) | Method for detecting fiber distribution condition in mixed fiber product | |
| CN111368825B (en) | Pointer positioning method based on semantic segmentation | |
| Dauwe et al. | A fast non-local image denoising algorithm | |
| CN111008651B (en) | Image reproduction detection method based on multi-feature fusion | |
| CN108549078B (en) | Cross-channel combination and detection method for radar pulse signals | |
| CN101587189B (en) | Texture elementary feature extraction method for synthetizing aperture radar images | |
| CN104282027B (en) | Circle detecting method based on Hough transformation | |
| Li et al. | Densely connected network for impulse noise removal | |
| CN108205657A (en) | Method, storage medium and the mobile terminal of video lens segmentation | |
| CN113780110A (en) | Method and device for detecting weak and small targets in image sequence in real time | |
| CN110070486A (en) | A kind of image processing method, device and electronic equipment | |
| CN113553973A (en) | Two-way attention-based camouflage object detection method | |
| CN111783732A (en) | Group mist identification method and device, electronic equipment and storage medium | |
| CN108491796B (en) | Time domain periodic point target detection method | |
| CN109003247B (en) | Method for removing color image mixed noise | |
| CN103455986B (en) | Random noise point detecting method based on fractional order differential gradient | |
| CN113063906B (en) | Method and device for detecting chlorophyll a front surface | |
| CN113888474B (en) | Intelligent detection method for target cells | |
| Bi et al. | Adaptive blind image restoration algorithm of degraded image | |
| CN113239738B (en) | Image blurring detection method and blurring detection device | |
| Li et al. | A hybrid edge detection method for cell images based on fuzzy entropy and the canny operator | |
| CN114155510A (en) | Road element detection method and device based on double-branch semantic segmentation network | |
| CN112672052A (en) | Image data enhancement method and system, electronic equipment and storage medium |
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 |