CN118247231A - Spinning quality visual identification system - Google Patents
Spinning quality visual identification system Download PDFInfo
- Publication number
- CN118247231A CN118247231A CN202410300605.6A CN202410300605A CN118247231A CN 118247231 A CN118247231 A CN 118247231A CN 202410300605 A CN202410300605 A CN 202410300605A CN 118247231 A CN118247231 A CN 118247231A
- Authority
- CN
- China
- Prior art keywords
- spinning
- area
- pore
- image
- 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
- 238000009987 spinning Methods 0.000 title claims abstract description 200
- 230000000007 visual effect Effects 0.000 title claims abstract description 35
- 230000011218 segmentation Effects 0.000 claims abstract description 29
- 238000013441 quality evaluation Methods 0.000 claims abstract description 26
- 238000004891 communication Methods 0.000 claims abstract description 3
- 239000011148 porous material Substances 0.000 claims description 187
- 238000004364 calculation method Methods 0.000 claims description 20
- 230000007547 defect Effects 0.000 claims description 20
- 230000002159 abnormal effect Effects 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 17
- 230000005856 abnormality Effects 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 8
- 230000002950 deficient Effects 0.000 claims description 3
- 230000008676 import Effects 0.000 claims description 2
- 238000001303 quality assessment method Methods 0.000 claims 6
- 238000011156 evaluation Methods 0.000 abstract description 8
- 238000004519 manufacturing process Methods 0.000 description 8
- 238000003908 quality control method Methods 0.000 description 6
- 238000000034 method Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000011158 quantitative evaluation Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000004753 textile Substances 0.000 description 1
- 238000009941 weaving Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/64—Analysis of geometric attributes of convexity or concavity
-
- 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
-
- 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
- G06T2207/30168—Image quality inspection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to the field of visual identification, and particularly discloses a spinning quality visual identification system which comprises a processor, a spinning product image acquisition module and a spinning quality visual identification module, wherein the spinning product image acquisition module and the spinning quality visual identification module are in communication connection with the processor, and the spinning quality visual identification system is used for solving the problem that the convexity and convexity of a local shadow area cannot be determined during the image identification of a spinning product; according to the invention, the spinning product image is acquired through the high-resolution camera, the gray threshold segmentation is carried out on the spinning product image, the spinning product image is segmented into a plurality of image area blocks, and the non-shadow areas are removed, so that the shadow areas in the spinning product image are obtained, the shadow areas are distinguished to be convex areas or concave areas, the quality of the spinning product is evaluated by constructing the spinning quality evaluation model, the problem that the convexity of the local shadow areas cannot be determined during the identification of the spinning product image can be effectively solved, and the evaluation accuracy and reliability of the quality of the spinning product can be improved.
Description
Technical Field
The invention relates to the field of visual identification, in particular to a spinning quality visual identification system.
Background
The quality detection of spinning products is carried out by the traditional detection method through the eyes of operators, but the detection method has the problems of high omission factor, high working strength and great influence by subjective factors of operators, and the problems can lead to the quality reduction of textiles, thereby influencing the touch comfort of customers. The visual recognition is applied to flaw recognition of spinning products, so that accuracy and efficiency of flaw recognition are improved, and the resolution of flaw types is enhanced. At present, when visual identification is carried out on a spinning product, a part of decorative areas of the spinning product are required to be uniformly designed with convex parts, but due to mechanical friction or uneven arrangement among fibers suffered in the weaving process, the spinning product has different degrees of concave-convex, so that the definition of an image has defects, more shadow areas exist in the image are compared, the concave-convex performance of the local shadow areas cannot be determined, the comfort of customers is influenced, and the image and the appearance attractiveness of the spinning product are influenced.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a spinning quality visual identification system, which is used for acquiring a spinning product image through a high-resolution camera, dividing the spinning product image into a plurality of image area blocks through gray threshold segmentation, removing a non-shadow area to obtain a shadow area in the spinning product image, distinguishing the shadow area into a convex area or a concave area, and evaluating the quality of the spinning product by constructing a spinning quality evaluation model, so that the problem that the convexity of a local shadow area cannot be determined during the identification of the spinning product image can be effectively solved, and the accuracy and the reliability of the evaluation of the quality of the spinning product can be improved, thereby solving the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions:
The spinning quality visual recognition system comprises a processor, a spinning quality image acquisition module and a spinning quality visual recognition module, wherein the spinning quality visual recognition module is in communication connection with the processor, and the spinning quality image acquisition module is used for acquiring spinning quality images through a high-resolution camera; the spinning quality visual recognition module is used for visually recognizing and evaluating the quality of a spinning product image, and comprises an image processing unit, a shadow area dividing unit, an area detecting unit and a spinning quality evaluating unit, wherein the spinning quality evaluating unit is used for evaluating the quality of the spinning product by constructing a spinning quality evaluating model, and by acquiring the pore size abnormal value of the spinning product, the total area of the image of the defect value of the concave area and the total area of G pore image blocks in the concave area, and introducing the pore size abnormal value of the spinning product, the total area of the image of the defect value of the concave area and the total area of the G pore image blocks in the concave area into the spinning quality evaluating model, and evaluating the quality of the spinning product, wherein the formula of the spinning quality evaluating model is as follows:
Wherein: zl f is a quality index of the spinning product, aq x is a defect value of a concave area, yf x is an abnormal value of pore size of the spinning product, S z is a total area of images of the spinning product with the defect value of the concave area, and S g is a total area of G pore image blocks in the concave area.
As a further scheme of the invention, the image processing unit is used for removing noise, enhancing contrast and graying the spinning product image;
The shadow region segmentation unit is used for segmenting the spinning product image into a plurality of image region blocks through gray threshold segmentation, and removing the non-shadow region to obtain a shadow region in the spinning product image;
the area detection unit is used for distinguishing the shadow area into a convex area or a concave area;
The spinning quality evaluation unit is used for evaluating the quality of the spinning product by constructing a spinning quality evaluation model.
As a further aspect of the present invention, the shadow region segmentation unit includes a non-shadow region identification subunit, a non-shadow region segmentation subunit, and a shadow region extraction subunit, wherein,
The non-shadow area identification unit is used for identifying a non-shadow area in the spinning product image;
The non-shadow region segmentation subunit is used for segmenting a non-shadow region in the spinning product image;
The shadow region extraction unit is used for extracting a residual image region in the spinning product image, wherein the residual image region is the shadow region.
As a further scheme of the invention, the non-shadow region segmentation subunit is used for segmenting the non-shadow region in the spinning product image, segmenting the spinning product image into a plurality of pore image blocks according to the spinning specified pore size, and removing the pore image blocks of the non-shadow region according to the spinning target gray value to leave the pore image blocks of the shadow region.
As a further scheme of the invention, the spinning target gray value is obtained by calculating the gray level range average value of each pore image block, the gray level ranges of the pore image blocks are arranged into a range sequence {Kh(ih,jh),…,K2(i2,j2),K1(i1,j1)}, according to the sequence from big to small, wherein, K 1(i1,j1) is the pore image block with the smallest gray level range value, K 2(i2,j2) is the pore image block with the second smallest gray level range value, and K h(ih,jh) is the pore image block with the largest gray level range value; removing the pore image blocks of the sequence {K0.4h(i0.4h,j0.4h),…,K2(i2,j2),K1(i1,j1)} of the full range of the gray level from large to small, wherein K 0.4h(i0.4h,j0.4h) is the pore image block of which the full range value is 40% of the maximum value; and comparing the gray level difference value of the spinning target gray level value of the residual level difference sequence with the spinning target gray level value, taking a pore image block with the gray level difference value larger than the spinning target gray level value as a shadow area, and marking.
As a further aspect of the present invention, the region detection means includes a concave-convex region determination means, a convex region output means, and a concave region output means; the concave-convex area distinguishing unit is used for comparing the gray value of the pore image block with the gray average value by calculating the gray average value of the pore image block in the shadow area, and distinguishing the concave-convex of the shadow area, wherein the comparison mode of the gray value of the pore image block and the gray average value is as follows:
When (when) When the aperture image block is a convex part area;
When (when) When the aperture image block is a concave area;
Wherein s Hq is the gray value of the qth aperture image block, Is the gray average of the pore image block.
As a further scheme of the invention, the spinning quality evaluation unit comprises a pore size abnormality analysis unit, a convex part area statistics unit and a quality evaluation unit, wherein the pore size abnormality analysis unit is used for extracting pore areas in pore image blocks in a spinning product image, arranging the pore areas of the pore image blocks from large to small according to numerical values, calculating pore area average values of the pore image blocks, and introducing the pore areas of the pore image blocks and the pore area average values of the pore image blocks into a pore size abnormality analysis calculation model to calculate pore size abnormality values of the spinning product, wherein the calculation formula of the abnormality analysis calculation model is as follows:
Wherein: yf x is the abnormal value of the pore size of the spinning product, For the average pore area of each pore image block, P is the total number of pore image blocks, kx pmax is the maximum pore area in pore image block P, and kx pmin is the minimum pore area in pore image block P.
As a further aspect of the present invention, the convex portion region statistics unit is configured to count pore image blocks in a concave portion region, obtain the number of pore image blocks, each pore image block area, and a pore image block area average value included in the concave portion region, and import the number of pore image blocks, each pore image block area, and the pore image block area average value in the concave portion region into a concave portion region flaw value calculation formula, and calculate a flaw value in the concave portion region in the spun yarn, where the concave portion region flaw value calculation formula is:
Wherein: aq x is a defective value of a recess region, S g is an area of a G-th aperture image block in the recess region, G is a total number of aperture image blocks in the recess region, Is the average value of the area of the pore image block in the concave part area.
The spinning quality visual identification system has the technical effects and advantages that: according to the invention, the spinning product image is acquired through a high-resolution camera, the spinning product image is divided into a plurality of image area blocks through gray threshold segmentation, and non-shadow areas are removed to obtain shadow areas in the spinning product image, the shadow areas are distinguished to be convex areas or concave areas, and the quality of the spinning product is evaluated by constructing a spinning quality evaluation model, so that the problem that the convexity of the local shadow areas cannot be determined during the identification of the spinning product image can be effectively solved, and the evaluation accuracy and reliability of the quality of the spinning product can be improved; the production efficiency can be improved, the labor cost can be reduced, and meanwhile, the subjective error can be reduced, and the consistency and accuracy of evaluation can be improved; the quality control method is convenient for finding and processing the quality problem of the spinning in time, improves the quality control efficiency on the production line, and reduces the generation of unqualified products.
Drawings
Fig. 1 is a schematic structural diagram of a spinning quality visual recognition system according to a first embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made in detail, but not necessarily with reference to the accompanying drawings. Based on the technical scheme in the invention, all other technical schemes obtained by a person of ordinary skill in the art without making creative work fall within the protection scope of the invention.
Example 1
Fig. 1 shows a schematic structural diagram of a spinning quality visual recognition system according to a first embodiment of the present invention. As shown in fig. 1, a spinning quality visual recognition system in this embodiment, a spinning quality visual recognition system, includes a processor, and a spinning quality image acquisition module and a spinning quality visual recognition module that are communicatively connected to the processor. Wherein,
The spinning product image acquisition module is used for acquiring spinning product images through a high-resolution camera;
the spinning quality visual recognition module is used for visually recognizing the spinning product image and evaluating the quality.
The spinning quality visual recognition module comprises an image processing unit, a shadow region segmentation unit, a region detection unit and a spinning quality evaluation unit;
The image processing unit is connected with the shadow region segmentation unit and is used for removing noise, enhancing contrast and graying the spinning product image;
The shadow region segmentation unit is connected with the region detection unit and is used for segmenting the spinning product image into a plurality of image region blocks through gray threshold segmentation, and removing the non-shadow region to obtain a shadow region in the spinning product image;
The area detection unit is connected with the spinning quality evaluation unit and is used for distinguishing the shadow area into a convex area or a concave area;
The spinning quality evaluation unit is used for evaluating the quality of the spinning product by constructing a spinning quality evaluation model.
The method comprises the steps of collecting a spinning product image through a high-resolution camera, dividing the spinning product image into a plurality of image area blocks through gray threshold segmentation, removing non-shadow areas to obtain shadow areas in the spinning product image, distinguishing the shadow areas into convex areas or concave areas, and evaluating the quality of the spinning product by constructing a spinning quality evaluation model, so that the problem that the convexity of a local shadow area cannot be determined during the identification of the spinning product image can be effectively solved, and the accuracy and the reliability of the evaluation of the quality of the spinning product can be improved; the production efficiency can be improved, the labor cost can be reduced, and meanwhile, the subjective error can be reduced, and the consistency and accuracy of evaluation can be improved; the quality control method is convenient for finding and processing the quality problem of the spinning in time, improves the quality control efficiency on the production line, and reduces the generation of unqualified products.
The shadow region segmentation unit comprises a non-shadow region identification subunit, a non-shadow region segmentation subunit and a shadow region extraction subunit, wherein the non-shadow region identification subunit is connected with the non-shadow region segmentation subunit, and the non-shadow region segmentation subunit is connected with the shadow region extraction subunit;
The non-shadow area identification unit is used for identifying a non-shadow area in the spinning product image;
The non-shadow region segmentation subunit is used for segmenting a non-shadow region in the spinning product image;
The shadow region extraction unit is used for extracting a residual image region in the spinning product image, wherein the residual image region is the shadow region.
Wherein the pixels of the spun yarn image share an L-level gray scale representation, wherein the number of pixels of the gray scale representation L is L N, whereby the total number of pixels of the spun yarn image is:
Wherein: z N is the total number of pixels of the spun yarn image, L is the number of pixels of the spun yarn image represented by gray levels, L i is the number of pixels of gray level represented by i, and L N is the number of pixels of gray level represented by L.
The non-shadow region segmentation subunit is used for segmenting a non-shadow region in the spinning product image, segmenting the spinning product image into a plurality of pore image blocks according to the specified pore size of spinning, and removing the pore image blocks of the non-shadow region according to the gray value of the spinning target to leave the pore image blocks of the shadow region.
The gray level range of each pore image block is calculated and the gray level range average value of each pore image block is calculated as a spinning target gray level value, the gray level ranges of the pore image blocks are arranged into a range sequence {Kh(ih,jh),…,K2(i2,j2),K1(i1,j1)}, according to the sequence from big to small, wherein K 1(i1,j1) is the pore image block with the smallest gray level range value, K 2(i2,j2) is the pore image block with the second smallest gray level range value, and K h(ih,jh) is the pore image block with the largest gray level range value; removing the pore image blocks of the sequence {K0.4h(i0.4h,j0.4h),…,K2(i2,j2),K1(i1,j1)} of the full range of the gray level from large to small, wherein K 0.4h(i0.4h,j0.4h) is the pore image block of which the full range value is 40% of the maximum value; and comparing the gray level difference value of the spinning target gray level value of the residual level difference sequence with the spinning target gray level value, taking a pore image block with the gray level difference value larger than the spinning target gray level value as a shadow area, and marking.
By dividing the spinning product image according to the aperture size specified by spinning, a non-shadow area can be accurately divided, and inaccurate division caused by shadow is avoided; the gray level range of the pore image blocks is calculated, and the pore image blocks which do not meet the conditions are removed according to the range sequence, so that a spinning target area, namely a shadow area, can be effectively extracted; by comparing the gray value with the gray value of the spinning target, the aperture image block with the gray value of which the gray value is larger than the gray value of the spinning target is used as a shadow area, so that the possibility of misjudgment is reduced, and the accuracy of segmentation is improved; the method can automatically perform image segmentation and shadow region extraction, reduce the requirement of manual intervention, and improve the processing efficiency and consistency.
The region detection unit comprises a concave-convex region judging unit, a convex region output unit and a concave region output unit, wherein the concave-convex region judging unit is respectively connected with the convex region output unit and the concave region output unit;
the concave-convex area judging unit is used for comparing the gray value of the pore image block with the gray average value by calculating the gray average value of the pore image block in the shadow area to distinguish the concave-convex performance of the shadow area;
the convex part region output unit is used for outputting the pore image blocks in the convex part region;
the concave region output unit is used for outputting the pore image blocks in the concave region.
The concave-convex area judging unit is used for calculating the gray average value of the pore image blocks in the shadow area, comparing the gray value of the pore image blocks with the gray average value, and distinguishing the concave-convex performance of the shadow area, wherein the comparison mode of the gray value of the pore image blocks and the gray average value is as follows:
When (when) When the aperture image block is a convex part area;
When (when) When the aperture image block is a concave area;
Wherein s Hq is the gray value of the qth aperture image block, Is the gray average of the pore image block.
The gray average value of the pore image blocks in the shadow area is calculated, and the gray average value of the pore image blocks is compared with the gray average value, so that the concave-convex area can be automatically distinguished, subjectivity and inconsistency of manual judgment are avoided, and accuracy of judging the concave-convex area is improved; by comparing the gray values, whether the pore image block is a concave region or a convex region can be rapidly judged, so that the judging speed of the concave-convex region is increased, and the processing efficiency is improved; the gray value of the pore image block is compared with the gray average value, so that the gray change condition of the pore image block can be better reflected, and the convexity can be more accurately judged; the judgment of the convexity is based on the relationship between the gradation value and the gradation average value, not a simple threshold value comparison, and therefore the judgment of the convexity can be performed more reliably.
The spinning quality evaluation unit comprises a pore size abnormality analysis unit, a convex part area statistics unit and a quality evaluation unit; the pore size abnormality analysis unit and the convex part area statistics unit are respectively connected with the quality evaluation unit;
the pore size abnormality analysis unit is used for analyzing the pore size abnormality value of the spinning product through a pore size abnormality analysis calculation model;
The convex part region statistics unit is used for counting and integrating pore image blocks of the concave part region;
The quality evaluation unit is used for evaluating the quality of the spinning product by constructing a spinning quality evaluation model.
The pore size anomaly analysis unit is used for extracting the pore area in each pore image block in the spinning product image, arranging the pore areas of each pore image block according to the numerical value from large to small, calculating the pore area average value of each pore image block, and introducing the pore area of each pore image block and the pore area average value of each pore image block into the pore size anomaly analysis calculation model to calculate the pore size anomaly value of the spinning product, wherein the calculation formula of the anomaly analysis calculation model is as follows:
Wherein: yf x is the abnormal value of the pore size of the spinning product, For the average pore area of each pore image block, P is the total number of pore image blocks, kx pmax is the maximum pore area in pore image block P, and kx pmin is the minimum pore area in pore image block P.
The pore areas of each pore image block in the spinning product image can be effectively extracted, and the pore image blocks are ordered according to the area from large to small, so that the size distribution condition of different pores can be intuitively known; the average level of the pore area can be obtained by calculating the average value of the pore area of each pore image block, which is helpful for judging the trend and change of the overall pore size; the pore size abnormal value can be calculated by leading the pore area and the pore area average value into an abnormal analysis calculation model, so that the abnormal condition of the pore size can be recognized, and the problem can be found and solved in time; the abnormal condition of the pore size can be quantitatively evaluated through a calculation formula, accurate positioning and quantitative evaluation of the pore size abnormality are facilitated, and a basis is provided for subsequent processing.
The convex part area counting unit is used for counting pore image blocks in the concave part area, acquiring the number of pore image blocks, the area of each pore image block and the average value of the area of the pore image blocks contained in the concave part area, and importing the number of pore image blocks, the area of each pore image block and the average value of the area of the pore image block in the concave part area into a concave part area flaw value calculation formula to calculate the flaw value of the concave part area in the spinning product, wherein the concave part area flaw value calculation formula is as follows:
Wherein: aq x is a defective value of a recess region, S g is an area of a G-th aperture image block in the recess region, G is a total number of aperture image blocks in the recess region, Is the average value of the area of the pore image block in the concave part area.
The defect value of the concave region can be calculated by counting the number of pore image blocks of the concave region, the area of each pore image block and the average value of the area of the pore image blocks and introducing the average value into a concave region defect value calculation formula, so that the quality condition of the concave region can be quantitatively evaluated; the size distribution and the number distribution situation of the concave area can be comprehensively known by counting the number and the area information of the pore image blocks in the concave area, so that the potential flaw problem can be found; the average value of the area of the pore image block in the concave area is one of important indexes for measuring the flaw degree of the concave area, and a reference basis can be provided for calculating the flaw value; the flaw degree of the concave region can be quantified through a concave region flaw value calculation formula, and quantified data support is provided for subsequent quality analysis and improvement.
The quality evaluation unit is used for evaluating the quality of the spun yarn by acquiring the abnormal pore size value of the spun yarn, the total area of the defect value spun yarn image in the concave area and the total area of the G pore image blocks in the concave area, and importing the abnormal pore size value of the spun yarn, the total area of the defect value spun yarn image in the concave area and the total area of the G pore image blocks in the concave area into the spun yarn quality evaluation model, wherein the formula of the spun yarn quality evaluation model is as follows:
Wherein: zl f is a quality index of the spinning product, aq x is a defect value of a concave area, yf x is an abnormal value of pore size of the spinning product, S z is a total area of images of the spinning product with the defect value of the concave area, and S g is a total area of G pore image blocks in the concave area.
The method comprises the steps of introducing the abnormal pore size value, the defect value of the concave area, the total image area of the spinning product and the total area of pore image blocks in the concave area of the spinning product into a spinning product quality evaluation model, comprehensively considering a plurality of quality indexes of the spinning product, and helping to understand the influence degree of each index on the quality of the spinning product; the quality problem can be found and identified in time by quantitatively evaluating the quality of the spinning product, and improvement measures are determined, so that the adjustment and improvement in the production process are guided, and the quality level of the spinning product is improved; through quantitative evaluation and analysis of the quality of the spinning yarn, problems can be found in time and effective measures can be taken, so that the production efficiency and the product quality are improved, the unqualified rate is reduced, and the enterprise competitiveness is improved.
According to the embodiment of the invention, the spinning product image is acquired through a high-resolution camera, the spinning product image is divided into a plurality of image area blocks through gray threshold segmentation, and the non-shadow areas are removed to obtain shadow areas in the spinning product image, the shadow areas are distinguished to be convex areas or concave areas, and the quality of the spinning product is evaluated by constructing a spinning quality evaluation model, so that the problem that the convexity of the local shadow areas cannot be determined during the identification of the spinning product image can be effectively solved, and the evaluation accuracy and reliability of the quality of the spinning product can be improved; the production efficiency can be improved, the labor cost can be reduced, and meanwhile, the subjective error can be reduced, and the consistency and accuracy of evaluation can be improved; the quality control method is convenient for finding and processing the quality problem of the spinning in time, improves the quality control efficiency on the production line, and reduces the generation of unqualified products.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (8)
1. The spinning quality visual recognition system comprises a processor, a spinning quality image acquisition module and a spinning quality visual recognition module, wherein the spinning quality visual recognition module is in communication connection with the processor, and the spinning quality image acquisition module is used for acquiring spinning quality images through a high-resolution camera; the spinning quality visual recognition module is used for visually recognizing a spinning product image and carrying out quality assessment, and is characterized by comprising an image processing unit, a shadow area segmentation unit, an area detection unit and a spinning quality assessment unit, wherein the spinning quality assessment unit is used for assessing the quality of the spinning product by constructing a spinning quality assessment model, and by acquiring the pore size abnormal value of the spinning product, the total area of a defect value spinning product image in a concave area and the total area of G pore image blocks in the concave area, and introducing the pore size abnormal value of the spinning product, the total area of the defect value spinning product image in the concave area and the total area of G pore image blocks in the concave area into the spinning product quality assessment model, and the quality of the spinning product is assessed, wherein the spinning product quality assessment model has the formula:
Wherein: zl f is a quality index of the spinning product, aq x is a defect value of a concave area, yf x is an abnormal value of pore size of the spinning product, S z is a total area of images of the spinning product with the defect value of the concave area, and S g is a total area of G pore image blocks in the concave area.
2. The spinning quality visual recognition system according to claim 1, wherein the image processing unit is configured to perform noise removal, contrast enhancement and graying processing on the spun yarn image;
The shadow region segmentation unit is used for segmenting the spinning product image into a plurality of image region blocks through gray threshold segmentation, and removing the non-shadow region to obtain a shadow region in the spinning product image;
the area detection unit is used for distinguishing the shadow area into a convex area or a concave area;
The spinning quality evaluation unit is used for evaluating the quality of the spinning product by constructing a spinning quality evaluation model.
3. The spinning quality visual recognition system according to claim 1, wherein the shadow region segmentation unit includes a non-shadow region recognition subunit, a non-shadow region segmentation subunit, and a shadow region extraction subunit, wherein,
The non-shadow area identification unit is used for identifying a non-shadow area in the spinning product image;
The non-shadow region segmentation subunit is used for segmenting a non-shadow region in the spinning product image;
The shadow region extraction unit is used for extracting a residual image region in the spinning product image, wherein the residual image region is the shadow region.
4. A spinning quality visual recognition system according to claim 3, wherein the non-shadow region segmentation subunit is configured to segment a non-shadow region in the spun yarn image, segment the spun yarn image into a plurality of pore image blocks according to a spinning specified pore size, reject the pore image blocks of the non-shadow region according to a spinning target gray value, and leave the pore image blocks of the shadow region.
5. A spinning quality visual recognition system according to claim 3, wherein the spinning target gray value is obtained by calculating the gray level range average value of each pore image block, and the gray level ranges of the pore image blocks are arranged into a range sequence {Kh(ih,jh),…,K2(i2,j2),K1(i1,j1)}, in the order from the top to the bottom, wherein K 1(i1,j1) is the pore image block with the smallest gray level range value, K 2(i2,j2) is the pore image block with the second smallest gray level range value, and K h(ih,jh) is the pore image block with the largest gray level range value; removing the pore image blocks of the sequence {K0.4h(i0.4h,j0.4h),…,K2(i2,j2),K1(i1,j1)} of the full range of the gray level from large to small, wherein K 0.4h(i0.4h,h0.4h) is the pore image block of which the full range value is 40% of the maximum value; and comparing the gray level difference value of the spinning target gray level value of the residual level difference sequence with the spinning target gray level value, taking a pore image block with the gray level difference value larger than the spinning target gray level value as a shadow area, and marking.
6. The spinning quality visual recognition system according to claim 1, wherein the area detection unit includes a concave-convex area discrimination unit, a convex area output unit, and a concave area output unit; the concave-convex area distinguishing unit is used for comparing the gray value of the pore image block with the gray average value by calculating the gray average value of the pore image block in the shadow area, and distinguishing the concave-convex of the shadow area, wherein the comparison mode of the gray value of the pore image block and the gray average value is as follows:
When (when) When the aperture image block is a convex part area;
When (when) When the aperture image block is a concave area;
Wherein s Hq is the gray value of the qth aperture image block, Is the gray average of the pore image block.
7. The spinning quality visual recognition system according to claim 1, wherein the spinning quality evaluation unit comprises a pore size abnormality analysis unit, a convex part area statistics unit and a quality evaluation unit, wherein the pore size abnormality analysis unit is used for extracting pore areas in pore image blocks in a spinning product image, arranging the pore areas of the pore image blocks according to the numerical values from large to small, calculating a pore area average value of the pore image blocks, and introducing the pore areas of the pore image blocks and the pore area average value of the pore image blocks into a pore size abnormality analysis calculation model to calculate pore size abnormality values of the spinning product, wherein a calculation formula of the abnormality analysis calculation model is as follows:
Wherein: yf x is the abnormal value of the pore size of the spinning product, For the average pore area of each pore image block, P is the total number of pore image blocks, kx pmax is the maximum pore area in pore image block P, and kx pmin is the minimum pore area in pore image block P.
8. The spinning quality visual recognition system according to claim 7, wherein the convex portion region statistics unit is configured to count aperture image blocks in a concave portion region, obtain a number of aperture image blocks, an area of each aperture image block, and an area average value of the aperture image blocks included in the concave portion region, and import the number of aperture image blocks, the area of each aperture image block, and the area average value of the aperture image blocks in the concave portion region into a concave portion region defect value calculation formula, and calculate a defect value of the concave portion region in the spun yarn, wherein the concave portion region defect value calculation formula is:
Wherein: aq x is a defective value of a recess region, S g is an area of a G-th aperture image block in the recess region, G is a total number of aperture image blocks in the recess region, Is the average value of the area of the pore image block in the concave part area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410300605.6A CN118247231A (en) | 2024-03-15 | 2024-03-15 | Spinning quality visual identification system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410300605.6A CN118247231A (en) | 2024-03-15 | 2024-03-15 | Spinning quality visual identification system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118247231A true CN118247231A (en) | 2024-06-25 |
Family
ID=91559668
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410300605.6A Pending CN118247231A (en) | 2024-03-15 | 2024-03-15 | Spinning quality visual identification system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118247231A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102967606A (en) * | 2012-11-02 | 2013-03-13 | 海宁市科威工业电子科技有限公司 | Textile machine fabric defect visual inspection system |
| CN103471973A (en) * | 2013-09-05 | 2013-12-25 | 东华大学 | Method for determining porosity characteristics of fabric through image method |
| CN107977954A (en) * | 2017-10-12 | 2018-05-01 | 常州信息职业技术学院 | Textile flaw detection method based on local optimum analysis |
| WO2019104767A1 (en) * | 2017-11-28 | 2019-06-06 | 河海大学常州校区 | Fabric defect detection method based on deep convolutional neural network and visual saliency |
| CN117274133A (en) * | 2022-06-09 | 2023-12-22 | 鸿海精密工业股份有限公司 | Defect detection method, electronic device and storage medium |
-
2024
- 2024-03-15 CN CN202410300605.6A patent/CN118247231A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102967606A (en) * | 2012-11-02 | 2013-03-13 | 海宁市科威工业电子科技有限公司 | Textile machine fabric defect visual inspection system |
| CN103471973A (en) * | 2013-09-05 | 2013-12-25 | 东华大学 | Method for determining porosity characteristics of fabric through image method |
| CN107977954A (en) * | 2017-10-12 | 2018-05-01 | 常州信息职业技术学院 | Textile flaw detection method based on local optimum analysis |
| WO2019104767A1 (en) * | 2017-11-28 | 2019-06-06 | 河海大学常州校区 | Fabric defect detection method based on deep convolutional neural network and visual saliency |
| CN117274133A (en) * | 2022-06-09 | 2023-12-22 | 鸿海精密工业股份有限公司 | Defect detection method, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114549522B (en) | Textile quality detection method based on target detection | |
| CN115082418B (en) | Precise identification method for automobile parts | |
| CN115294113B (en) | Quality detection method for wood veneer | |
| CN114419025A (en) | Fiberboard quality evaluation method based on image processing | |
| CN116645367B (en) | Steel plate cutting quality detection method for high-end manufacturing | |
| CN115311267B (en) | Method for detecting abnormity of check fabric | |
| CN113643276B (en) | Textile texture defect automatic detection method based on statistical analysis | |
| CN118196068B (en) | Textile printing and dyeing quality monitoring system based on artificial intelligence | |
| CN115330799B (en) | Automatic fault diagnosis method for instrument | |
| CN117273554A (en) | Textile production quality prediction method based on data identification | |
| CN118229677B (en) | Intelligent optimization method and system for vortex spinning line preparation | |
| CN114581376A (en) | Automatic sorting method and system for textile silkworm cocoons based on image recognition | |
| CN117237747B (en) | Hardware defect classification and identification method based on artificial intelligence | |
| CN113936001A (en) | Textile surface flaw detection method based on image processing technology | |
| CN118247231A (en) | Spinning quality visual identification system | |
| CN115311278A (en) | Yarn cutting method for yarn detection | |
| CN114782426A (en) | Knitted fabric broken yarn defect detection method based on artificial intelligence system | |
| CN117893467B (en) | Textile defect type identification method | |
| CN118521580B (en) | Industrial machine defect visual detection method, system and equipment based on big data | |
| CN118552524B (en) | Visual detection method and system for stamping defects of hardware | |
| CN117745730B (en) | Polyester filament yarn detection method and system based on image processing technology | |
| CN111241332B (en) | Method for searching corresponding measurement program by automatically identifying workpiece | |
| CN117274250B (en) | Visual detection method for wear defect of watch bottom cover | |
| CN118095971B (en) | AD calcium milk beverage processing technology assessment method, system and medium | |
| CN118501177A (en) | Appearance defect detection method and system for formed foil |
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 |