CN117237298A - Printed fabric defect inspection method, device and computing equipment - Google Patents
Printed fabric defect inspection method, device and computing equipment Download PDFInfo
- Publication number
- CN117237298A CN117237298A CN202311193894.6A CN202311193894A CN117237298A CN 117237298 A CN117237298 A CN 117237298A CN 202311193894 A CN202311193894 A CN 202311193894A CN 117237298 A CN117237298 A CN 117237298A
- Authority
- CN
- China
- Prior art keywords
- fabric
- particles
- particle
- points
- segmentation
- 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
- 239000004744 fabric Substances 0.000 title claims abstract description 148
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000007547 defect Effects 0.000 title claims abstract description 43
- 238000007689 inspection Methods 0.000 title claims description 17
- 239000002245 particle Substances 0.000 claims abstract description 216
- 230000011218 segmentation Effects 0.000 claims abstract description 83
- 230000002159 abnormal effect Effects 0.000 claims abstract description 15
- 238000005259 measurement Methods 0.000 claims abstract description 10
- 239000011159 matrix material Substances 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 8
- 230000003595 spectral effect Effects 0.000 claims description 5
- 238000003709 image segmentation Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 abstract description 16
- 230000000694 effects Effects 0.000 description 11
- 238000007639 printing Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000009826 distribution Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000001186 cumulative effect Effects 0.000 description 3
- 238000005315 distribution function Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005215 recombination Methods 0.000 description 2
- 230000006798 recombination Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- 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
Abstract
The invention provides a method, a device and a computing device for checking defects of printed fabrics, and relates to the technical field of checking defects of printed fabrics, wherein the method comprises the following steps: according to the segmentation surface point set, eliminating error points in the segmentation surface point set to obtain a particle swarm segmentation surface; extracting single particle center points according to the particle swarm segmentation surface, and carrying out feature measurement on neighbor point clouds of the single particle center points according to the single particle center points so as to obtain single particle edge information; calculating the volume of the single particles of the fabric according to the edge information of the single particles so as to obtain the volume of the single particles; according to the volume of the single particles, the coverage rate of the particles on the fabric is obtained, and according to the coverage rate, the uniformity of the particles on the fabric is calculated; and according to the uniformity of the particles on the fabric, obtaining abnormal points of the fabric, and determining the defects of the fabric according to the abnormal points. The invention improves the accuracy and reliability of detection.
Description
Technical Field
The invention relates to the technical field of printed fabric defect inspection, in particular to a printed fabric defect inspection method, a printed fabric defect inspection device and a printed fabric defect inspection computing device.
Background
The quality of the fabric printing directly influences the appearance effect and the quality level of the fabric. Currently, detection of defects on the surface of printed fabrics is mainly dependent on manual observation. However, manual inspection has problems such as low efficiency and difficult control of precision. In order to realize automatic and efficient detection of defects on the surface of printed fabrics, an automatic detection method based on computer vision and image processing technology becomes a current research hot spot.
Image processing techniques have been used in the detection of defects on fabric surfaces. The existing defect detection algorithm carries out defect recognition according to an empirically set rule, and can realize automatic detection, but has poor stability when facing noise interference.
Disclosure of Invention
The invention aims to solve the technical problem of providing a method, a device and a computing device for checking defects of printed fabrics, and the accuracy and the reliability of detection are improved.
In order to solve the technical problems, the technical scheme of the invention is as follows:
in a first aspect, a method for inspecting defects in printed fabric, the method comprising:
acquiring a fabric image, and preprocessing and segmenting the fabric image to obtain segmentation surface base points;
determining a segmentation surface point set positioned on the surface of the fabric according to the segmentation surface base points, and removing error points in the segmentation surface point set according to the segmentation surface point set so as to obtain a particle swarm segmentation surface;
extracting single particle center points according to the particle swarm segmentation surface, and carrying out feature measurement on neighbor point clouds of the single particle center points according to the single particle center points so as to obtain single particle edge information;
calculating the volume of the single particles of the fabric according to the edge information of the single particles so as to obtain the volume of the single particles;
according to the volume of the single particles, the coverage rate of the particles on the fabric is obtained, and according to the coverage rate, the uniformity of the particles on the fabric is calculated;
and according to the uniformity of the particles on the fabric, obtaining abnormal points of the fabric, and determining the defects of the fabric according to the abnormal points.
Further, obtaining a fabric image, and preprocessing and segmenting the fabric image to obtain segmentation surface base points, including:
acquiring a fabric image;
performing histogram equalization processing on the fabric image, and performing noise removal by using a median filter to obtain a preprocessed image;
and dividing the preprocessed image to obtain dividing plane base points.
Further, determining a set of segmentation surface points on the surface of the fabric according to the segmentation surface base points, and eliminating error points in the set of segmentation surface points according to the set of segmentation surface points to obtain a particle swarm segmentation surface, wherein the method comprises the following steps:
determining a segmentation surface point set on the surface of the fabric by an image segmentation method according to the acquired segmentation surface base points;
according to the segmentation surface point set, cleaning error points to obtain cleaned data points;
calculating the distance between every two data points according to the data points after cleaning;
constructing a similarity matrix according to the distance between every two data points;
performing spectral clustering according to the similarity matrix to obtain a clustering result;
and distributing the original data points to different clusters according to the clustering result to obtain a particle swarm segmentation surface.
Further, extracting a single particle center point according to the particle swarm segmentation plane includes:
identifying individual particles on the particle swarm division surface;
calculating an average value of an x coordinate and a y coordinate of each particle pixel according to each identified particle;
determining the geometric center of each particle according to the average value of the x coordinate and the y coordinate of each particle pixel;
from the geometric center of each particle, a single particle center point is determined.
Further, according to the single particle center point, feature measurement is performed on a neighborhood point cloud of the single particle center point to obtain single particle edge information, including:
determining a neighborhood point cloud of each particle center point according to the single particle center point;
calculating characteristics of the neighborhood point clouds according to the neighborhood point clouds of each particle center point;
and extracting single particle edge information according to the characteristics of the neighborhood point cloud.
Further, according to the single particle edge information, calculating the volume of the single particle of the fabric to obtain the volume of the single particle, including:
acquiring shape information of particles according to the edge information of the single particles;
the volume of the particles is calculated from the shape information of the particles.
Further, according to the volume of the single particles, to obtain the coverage rate of the particles on the fabric, and according to the coverage rate, calculating the uniformity of the particles on the fabric, including:
calculating the total coverage rate according to the total volume of all particles and the total volume of the fabric;
dividing the fabric into a plurality of divided areas, and respectively calculating the particle coverage rate in each divided area;
and determining the uniformity of the particles on the fabric according to the total coverage rate and the particle coverage rate.
In a second aspect, a printed fabric defect inspection apparatus comprising:
the acquisition module is used for acquiring a fabric image, and preprocessing and dividing the fabric image to obtain dividing surface base points; determining a segmentation surface point set positioned on the surface of the fabric according to the segmentation surface base points, and removing error points in the segmentation surface point set according to the segmentation surface point set so as to obtain a particle swarm segmentation surface; extracting single particle center points according to the particle swarm segmentation surface, and carrying out feature measurement on neighbor point clouds of the single particle center points according to the single particle center points so as to obtain single particle edge information;
the processing module is used for calculating the volume of the single particles of the fabric according to the edge information of the single particles so as to obtain the volume of the single particles; according to the volume of the single particles, the coverage rate of the particles on the fabric is obtained, and according to the coverage rate, the uniformity of the particles on the fabric is calculated; and according to the uniformity of the particles on the fabric, obtaining abnormal points of the fabric, and determining the defects of the fabric according to the abnormal points.
In a third aspect, a computing device includes:
one or more processors;
and a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the above-described methods.
In a fourth aspect, a computer readable storage medium stores a program that when executed by a processor implements the above method.
The scheme of the invention at least comprises the following beneficial effects:
according to the scheme, defects are detected through image processing and computer vision technology, the detection accuracy and reliability are improved, defects of different types on the printed fabric including defects such as printing particle deficiency and uneven printing can be detected, the detection range is enlarged, defects of materials with repeated textures such as the printed fabric are detected through analyzing the characteristics of single printing particles, the detection adaptability is improved, the method can be applied to production detection of the printed fabric on a large scale, the production cost is reduced, and the product quality is improved.
Drawings
Fig. 1 is a schematic flow chart of a method for inspecting defects of printed fabric according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a printed fabric defect inspection apparatus according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described more closely below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As shown in fig. 1, an embodiment of the present invention proposes a method for inspecting defects of printed fabric, the method comprising:
step 11, acquiring a fabric image, and preprocessing and segmenting the fabric image to obtain segmentation surface base points;
step 12, determining a segmentation surface point set positioned on the surface of the fabric according to the segmentation surface base points, and removing error points in the segmentation surface point set according to the segmentation surface point set so as to obtain a particle swarm segmentation surface;
step 13, extracting single particle center points according to the particle swarm segmentation surface, and carrying out feature measurement on neighbor point clouds of the single particle center points according to the single particle center points so as to obtain single particle edge information;
step 14, calculating the volume of the single particles of the fabric according to the edge information of the single particles so as to obtain the volume of the single particles;
step 15, according to the volume of the single particles, the coverage rate of the particles on the fabric is obtained, and according to the coverage rate, the uniformity of the particles on the fabric is calculated;
and step 16, according to the uniformity of the particles on the fabric, obtaining abnormal points of the fabric, and determining the defects of the fabric according to the abnormal points.
In the embodiment of the invention, the defects are detected through image processing and computer vision technology, the detection accuracy and reliability are improved, different types of defects on the printed fabric including defects such as printing particle deficiency and uneven printing can be detected, the detection range is enlarged, the defects of the printed fabric and other materials with repeated textures are detected through analyzing the characteristics of single printing particles, the detection adaptability is improved, and the method can be applied to the production detection of the printed fabric on a large scale, the production cost is reduced, and the product quality is improved.
In a preferred embodiment of the present invention, the step 11 may include:
step 111, acquiring a fabric image;
step 112, performing histogram equalization processing on the fabric image, and performing noise removal by using a median filter to obtain a preprocessed image;
and step 113, segmenting the preprocessed image to obtain segmentation plane base points.
In the embodiment of the invention, the original image data of the fabric is obtained by acquiring the image data of the fabric; in step 112, byCalculating a histogram H (i) of the image, wherein i is a gray value of a pixel, and W and H are a width and a height of the image, respectively; img (x, y) is the pixel value at coordinates (x, y); [ img (x, y) =i]Is an indication function; the value of img (x, y) =i is 1, otherwise 0; then, according to->Calculating a cumulative distribution function cdf (i) of the histogram, and passing the cumulative distribution function cdf (i) through +.>Normalized to cumulative distribution function cdf n (i) The method comprises the steps of carrying out a first treatment on the surface of the Finally, filtering the image by using a median filter to obtain a filtered image, wherein a specific calculation formula is as follows: img f (x,y)＝median(img e (x′,y′)|(x′,y′)∈N(x,y))；
img e (x,y)＝cdf n (img(x,y))；
Wherein img e (x, y) is the histogram equalized image, img f (x, y) is the filtered image, N (x, y) is the neighborhood of the pixel with coordinates (x, y), and (x',y') represents the coordinates of one pixel in the neighborhood N (x, y) of coordinates (x, y), the purpose of this step is to improve the quality of the image, so that the subsequent image processing step is more accurate, the histogram equalization can improve the contrast of the image, so that the details in the image are more obvious, and the median filter can remove the noise in the image, so that the image is clearer, and the effect is that better quality image data are obtained; in step 113, based on the histogram h (i) of the image, by Calculating inter-class variance->And find out the variance between classes>A maximum threshold t, and segmenting the image by the threshold t, wherein,
img s (x,y)＝{1,in img f (x,y)>t * 0,otherwise；
wherein the specific meaning is if pixel (x, y) is in image img f The value in (a) is greater than the threshold t * Then in binarizing the image img s In which the value of the pixel will be set to 1, img s (x, y) is the segmented image and t is the threshold determined by the Otsu's method, the purpose of this step being to segment the image into a plurality of small regions, each representing a particle, which is the basis for the subsequent extraction of the particle features, the effect being to obtain segmentation surface basis points, which represent the positions of the individual particles.
In a preferred embodiment of the present invention, the step 12 may include:
step 121, determining a segmentation surface point set on the surface of the fabric by an image segmentation method according to the acquired segmentation surface base points;
step 122, cleaning the error points according to the segmentation surface point set to obtain cleaned data points;
step 123, calculating the distance between every two data points according to the cleaned data points;
step 124, constructing a similarity matrix according to the distance between every two data points;
step 125, performing spectral clustering according to the similarity matrix to obtain a clustering result;
and step 126, assigning the original data points to different clusters according to the clustering result to obtain a particle swarm segmentation surface.
In the above step 121, the process is performed byDetermining a set of segmentation points on the surface of the fabric, wherein ω i Is the weight, n is the number of pixel points, img f (x i ,y i ) Is the original image in (x i ,y i ) The pixel value of the position, t is a threshold value, and a dividing plane point set on the surface of the fabric is determined according to the acquired dividing plane base points, so that the point set of the surface of the fabric is acquired; in step 122, cleaning the error points according to the segmentation plane point set to obtain cleaned data points, wherein the step is used for removing possible noise and abnormal values so that the data are more accurate; in the above step 123, by ∈ ->Calculating a distance between every two data points, wherein D is the distance between the two data points, n is the number of dimensions, x 1i And x 2i Values of two data points in the ith dimension, beta i The weight of the ith dimension is calculated according to the cleaned data points, the distance between every two data points is calculated, the similarity or the difference between the data points is quantized, and necessary data is provided for constructing a similarity matrix; in the above step 124, according to ∈ ->Constructing a similarity matrix, wherein x ik And x jk The value of the ith and jth data point in the kth dimension, σ is the width parameter of the gaussian kernel function, similarity [ i ]][j]Representing an element in a similarity matrix, wherein i and j are indexes for representing the similarity between every pair of data points in the data set, constructing the similarity matrix according to the distance between every two data points, and expressing the relationship between the data points in the form of a matrix; in step 125, spectral clustering is performed according to the similarity matrix to obtain a clustering result, which functions to group data points according to their similarity between them; in step 126, the following calculation formula is used:
assigning raw data points into different clusters, C being the set of cluster centers, data_points i Is the value of the data point in the ith dimension, cluster_center ci The value of the clustering center in the ith dimension is that the cluster is a set of similar data points; and distributing the original data points to different clusters according to the clustering result to obtain particle swarm segmentation surfaces, wherein the function is to distribute the data points to corresponding categories so as to obtain the segmentation surfaces.
In a preferred embodiment of the present invention, the step 13 may include:
step 131, identifying individual particles on the particle group division surface;
step 132, calculating the average value of the x coordinate and the y coordinate of each particle pixel according to each identified particle;
step 133, determining the geometric center of each particle according to the average value of the x coordinate and the y coordinate of each particle pixel;
step 134, determining a single particle center point based on the geometric center of each particle.
In the embodiment of the invention, individual particles are identified on the particle swarm segmentation surface, and the purpose of this step is to identify individual particles in the image; calculating the average of the x-coordinate and the y-coordinate of each particle pixel based on each identified particle, respectively, the purpose of this step being to find the average position of each particle, which can determine the approximate position of the particle; determining the geometric center of each particle based on the average of the x-coordinate and y-coordinate of each particle pixel, the purpose of this step being to find the geometric center of each particle, which is a more accurate representation of the particle's position, which can be used for subsequent calculations and analysis; the individual particle center points are determined from the geometric center of each particle, the purpose of this step being to determine the center point of each particle in general, the effect of these steps being to identify individual particles from the image and to determine their positions.
In a preferred embodiment of the present invention, the step 13 may further include:
step 135, determining a neighborhood point cloud of each particle center point according to the single particle center point;
step 136, calculating the characteristics of the neighborhood point cloud according to the neighborhood point cloud of each particle center point;
step 137, extracting single particle edge information according to the characteristics of the neighborhood point cloud.
In the embodiment of the invention, the neighborhood point cloud of each particle center point is determined according to a single particle center point, and the purpose of the step is to find out the points around each particle center point, wherein the points form a neighborhood point cloud which can help to know the shape and structure of the particle; according to the neighborhood point cloud of each particle center point, calculating the characteristics of the neighborhood point cloud, wherein the step aims to extract the characteristics of the neighborhood point cloud, the characteristics can comprise the size, the shape, the direction and the like of the point cloud, and the characteristics can better understand the properties of the particles; extracting edge information of single particles according to the characteristics of the neighborhood point cloud, wherein the step aims at extracting the edge information of the particles, so that the shape and the size of the particles can be known; in general, the effect of these steps is to get a deeper understanding of the particle properties by computing the features of the neighborhood point cloud and extracting edge information, starting from the particle's central point.
In a preferred embodiment of the present invention, the step 14 may include:
step 141, obtaining shape information of particles according to the edge information of single particles;
in step 142, the volume of the particles is calculated from the shape information of the particles.
In the embodiment of the invention, the shape information of the particles is acquired according to the edge information of the single particles, and the purpose of the step is to acquire the shape information of the particles by analyzing the edge information of the particles, so that the structure and the characteristics of the particles can be better understood by the shape information; calculating the volume of the particles from the shape information of the particles, the purpose of this step being to calculate the volume of the particles from the shape information of the particles; in general, the effect of these steps is to obtain shape information of the particles from the edge information of the particles and further calculate the volume of the particles.
In a preferred embodiment of the present invention, the step 15 may include:
step 151, calculating the total coverage rate according to the total volume of all particles and the total volume of the fabric;
step 152, dividing the fabric into a plurality of divided areas, and respectively calculating the particle coverage rate in each divided area;
and step 153, determining the uniformity of the particles on the fabric according to the total coverage rate and the particle coverage rate.
In the embodiment of the invention, the total coverage rate is calculated according to the total volume of all particles and the total volume of the fabric, and the aim of the step is to calculate the coverage degree of the particles on the whole fabric; dividing the fabric into a plurality of divided areas, and respectively calculating the coverage rate of particles in each divided area, wherein the step aims at knowing the coverage condition of the particles in each area of the fabric, so that the distribution condition of the particles can be known; from the total coverage and the particle coverage, the uniformity of the particles on the fabric is determined, and the purpose of this step is to evaluate the uniformity of the distribution of the particles on the fabric, and if the distribution of the particles is very uniform, the coverage of the individual areas should be very close. In general, the effect of these steps is to evaluate the distribution and coverage effect of particles on the fabric by calculating the total coverage and the coverage of the individual areas.
As shown in fig. 2, an embodiment of the present invention further provides a printed fabric defect inspection apparatus 20, including:
an acquisition module 21, configured to acquire a fabric image, and perform preprocessing and segmentation on the fabric image to obtain a segmentation surface base point; determining a segmentation surface point set positioned on the surface of the fabric according to the segmentation surface base points, and removing error points in the segmentation surface point set according to the segmentation surface point set so as to obtain a particle swarm segmentation surface; extracting single particle center points according to the particle swarm segmentation surface, and carrying out feature measurement on neighbor point clouds of the single particle center points according to the single particle center points so as to obtain single particle edge information;
a processing module 22, configured to calculate a volume of the single particle of the fabric according to the edge information of the single particle, so as to obtain a volume of the single particle; according to the volume of the single particles, the coverage rate of the particles on the fabric is obtained, and according to the coverage rate, the uniformity of the particles on the fabric is calculated; and according to the uniformity of the particles on the fabric, obtaining abnormal points of the fabric, and determining the defects of the fabric according to the abnormal points.
Optionally, acquiring a fabric image, and preprocessing and segmenting the fabric image to obtain a segmentation surface base point, including:
acquiring a fabric image;
performing histogram equalization processing on the fabric image, and performing noise removal by using a median filter to obtain a preprocessed image;
and dividing the preprocessed image to obtain dividing plane base points.
Optionally, determining a set of segmentation surface points located on the surface of the fabric according to the segmentation surface base points, and removing error points in the set of segmentation surface points according to the set of segmentation surface points to obtain a particle swarm segmentation surface, including:
determining a segmentation surface point set on the surface of the fabric by an image segmentation method according to the acquired segmentation surface base points;
according to the segmentation surface point set, cleaning error points to obtain cleaned data points;
calculating the distance between every two data points according to the data points after cleaning;
constructing a similarity matrix according to the distance between every two data points;
performing spectral clustering according to the similarity matrix to obtain a clustering result;
and distributing the original data points to different clusters according to the clustering result to obtain a particle swarm segmentation surface.
Optionally, extracting a single particle center point according to the particle swarm segmentation surface includes:
identifying individual particles on the particle swarm division surface;
calculating an average value of an x coordinate and a y coordinate of each particle pixel according to each identified particle;
determining the geometric center of each particle according to the average value of the x coordinate and the y coordinate of each particle pixel;
from the geometric center of each particle, a single particle center point is determined.
Optionally, according to the single particle center point, feature measurement is performed on a neighborhood point cloud of the single particle center point to obtain single particle edge information, including:
determining a neighborhood point cloud of each particle center point according to the single particle center point;
calculating characteristics of the neighborhood point clouds according to the neighborhood point clouds of each particle center point;
and extracting single particle edge information according to the characteristics of the neighborhood point cloud.
Optionally, calculating the volume of the single particles of the fabric according to the edge information of the single particles to obtain the volume of the single particles, including:
acquiring shape information of particles according to the edge information of the single particles;
the volume of the particles is calculated from the shape information of the particles.
Optionally, according to the volume of the single particle, to obtain the coverage rate of the particle on the fabric, calculating the uniformity of the particle on the fabric according to the coverage rate, including:
calculating the total coverage rate according to the total volume of all particles and the total volume of the fabric;
dividing the fabric into a plurality of divided areas, and respectively calculating the particle coverage rate in each divided area;
and determining the uniformity of the particles on the fabric according to the total coverage rate and the particle coverage rate.
It should be noted that the apparatus is an apparatus corresponding to the above method, and all implementation manners in the above method embodiment are applicable to this embodiment, so that the same technical effects can be achieved.
Embodiments of the present invention also provide a computing device comprising: a processor, a memory storing a computer program which, when executed by the processor, performs the method as described above. All the implementation manners in the method embodiment are applicable to the embodiment, and the same technical effect can be achieved.
Embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform a method as described above. All the implementation manners in the method embodiment are applicable to the embodiment, and the same technical effect can be achieved.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc.
Furthermore, it should be noted that in the apparatus and method of the present invention, it is apparent that the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present invention. Also, the steps of performing the series of processes described above may naturally be performed in chronological order in the order of description, but are not necessarily performed in chronological order, and some steps may be performed in parallel or independently of each other. It will be appreciated by those of ordinary skill in the art that all or any of the steps or components of the methods and apparatus of the present invention may be implemented in hardware, firmware, software, or a combination thereof in any computing device (including processors, storage media, etc.) or network of computing devices, as would be apparent to one of ordinary skill in the art after reading this description of the invention.
The object of the invention can thus also be achieved by running a program or a set of programs on any computing device. The computing device may be a well-known general purpose device. The object of the invention can thus also be achieved by merely providing a program product containing program code for implementing said method or apparatus. That is, such a program product also constitutes the present invention, and a storage medium storing such a program product also constitutes the present invention. It is apparent that the storage medium may be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is apparent that the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present invention. The steps of executing the series of processes may naturally be executed in chronological order in the order described, but are not necessarily executed in chronological order. Some steps may be performed in parallel or independently of each other.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.
Claims (10)
1. A method for inspecting defects in printed fabrics, the method comprising:
acquiring a fabric image, and preprocessing and segmenting the fabric image to obtain segmentation surface base points;
determining a segmentation surface point set positioned on the surface of the fabric according to the segmentation surface base points, and removing error points in the segmentation surface point set according to the segmentation surface point set so as to obtain a particle swarm segmentation surface;
extracting single particle center points according to the particle swarm segmentation surface, and carrying out feature measurement on neighbor point clouds of the single particle center points according to the single particle center points so as to obtain single particle edge information;
calculating the volume of the single particles of the fabric according to the edge information of the single particles so as to obtain the volume of the single particles;
according to the volume of the single particles, the coverage rate of the particles on the fabric is obtained, and according to the coverage rate, the uniformity of the particles on the fabric is calculated;
and according to the uniformity of the particles on the fabric, obtaining abnormal points of the fabric, and determining the defects of the fabric according to the abnormal points.
2. A printed fabric defect inspection method according to claim 1, wherein acquiring a fabric image and preprocessing and segmenting the fabric image to obtain segmented surface base points comprises:
acquiring a fabric image;
performing histogram equalization processing on the fabric image, and performing noise removal by using a median filter to obtain a preprocessed image;
and dividing the preprocessed image to obtain dividing plane base points.
3. A printed fabric defect inspection method according to claim 2, wherein determining a set of dividing surface points on the fabric surface based on the dividing surface base points, and removing the error points in the set of dividing surface points based on the set of dividing surface points to obtain a particle swarm dividing surface comprises:
determining a segmentation surface point set on the surface of the fabric by an image segmentation method according to the acquired segmentation surface base points;
according to the segmentation surface point set, cleaning error points to obtain cleaned data points;
calculating the distance between every two data points according to the data points after cleaning;
constructing a similarity matrix according to the distance between every two data points;
performing spectral clustering according to the similarity matrix to obtain a clustering result;
and distributing the original data points to different clusters according to the clustering result to obtain a particle swarm segmentation surface.
4. A printed fabric defect inspection method according to claim 3, wherein extracting individual particle center points from the particle swarm segmentation surface comprises:
identifying individual particles on the particle swarm division surface;
calculating an average value of an x coordinate and a y coordinate of each particle pixel according to each identified particle;
determining the geometric center of each particle according to the average value of the x coordinate and the y coordinate of each particle pixel;
from the geometric center of each particle, a single particle center point is determined.
5. A printed fabric defect inspection method according to claim 4, wherein performing feature measurement on a neighborhood point cloud of a single particle center point according to the single particle center point to obtain single particle edge information comprises:
determining a neighborhood point cloud of each particle center point according to the single particle center point;
calculating characteristics of the neighborhood point clouds according to the neighborhood point clouds of each particle center point;
and extracting single particle edge information according to the characteristics of the neighborhood point cloud.
6. A printed fabric defect inspection method as claimed in claim 5 wherein calculating the individual particle volume of the fabric based on said individual particle edge information to obtain the individual particle volume comprises:
acquiring shape information of particles according to the edge information of the single particles;
the volume of the particles is calculated from the shape information of the particles.
7. A printed fabric defect inspection method according to claim 6 wherein the volume of said individual particles is used to obtain coverage of particles on the fabric and the uniformity of particles on the fabric is calculated based on said coverage, comprising:
calculating the total coverage rate according to the total volume of all particles and the total volume of the fabric;
dividing the fabric into a plurality of divided areas, and respectively calculating the particle coverage rate in each divided area;
and determining the uniformity of the particles on the fabric according to the total coverage rate and the particle coverage rate.
8. A printed fabric defect inspection device, comprising:
the acquisition module is used for acquiring a fabric image, and preprocessing and dividing the fabric image to obtain dividing surface base points; determining a segmentation surface point set positioned on the surface of the fabric according to the segmentation surface base points, and removing error points in the segmentation surface point set according to the segmentation surface point set so as to obtain a particle swarm segmentation surface; extracting single particle center points according to the particle swarm segmentation surface, and carrying out feature measurement on neighbor point clouds of the single particle center points according to the single particle center points so as to obtain single particle edge information;
the processing module is used for calculating the volume of the single particles of the fabric according to the edge information of the single particles so as to obtain the volume of the single particles; according to the volume of the single particles, the coverage rate of the particles on the fabric is obtained, and according to the coverage rate, the uniformity of the particles on the fabric is calculated; and according to the uniformity of the particles on the fabric, obtaining abnormal points of the fabric, and determining the defects of the fabric according to the abnormal points.
9. A computing device, comprising:
one or more processors;
storage means for storing one or more programs which when executed by the one or more processors cause the one or more processors to implement the method of any of claims 1-7.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a program which, when executed by a processor, implements the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311193894.6A CN117237298A (en) | 2023-09-15 | 2023-09-15 | Printed fabric defect inspection method, device and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311193894.6A CN117237298A (en) | 2023-09-15 | 2023-09-15 | Printed fabric defect inspection method, device and computing equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117237298A true CN117237298A (en) | 2023-12-15 |
Family
ID=89094239
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311193894.6A Pending CN117237298A (en) | 2023-09-15 | 2023-09-15 | Printed fabric defect inspection method, device and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117237298A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0742431A1 (en) * | 1995-05-10 | 1996-11-13 | Mahlo GmbH & Co. KG | Method and apparatus for detecting flaws in moving fabrics or the like |
| CN102221559A (en) * | 2011-03-05 | 2011-10-19 | 河海大学常州校区 | Online automatic detection method of fabric defects based on machine vision and device thereof |
| CN108447050A (en) * | 2018-03-07 | 2018-08-24 | 湘潭大学 | A kind of Surface Flaw dividing method based on super-pixel |
| CN109961437A (en) * | 2019-04-04 | 2019-07-02 | 江南大学 | A kind of conspicuousness fabric defect detection method under the mode based on machine teaching |
| CN111754495A (en) * | 2020-06-29 | 2020-10-09 | 江南大学 | Fabric surface flaw detection method based on BRDPSO algorithm |
| US20210174489A1 (en) * | 2019-12-04 | 2021-06-10 | Beijing Boe Optoelectronics Technology Co., Ltd. | Method and apparatus for detecting a screen, and electronic device |
| CN113298777A (en) * | 2021-05-21 | 2021-08-24 | 山东大学 | Cotton leaf blight detection method and system based on color features and super-pixel clustering |
| CN115311292A (en) * | 2022-10-12 | 2022-11-08 | 南通创铭伊诺机械有限公司 | Strip steel surface defect detection method and system based on image processing |
| CN115619807A (en) * | 2022-10-31 | 2023-01-17 | 盐城工学院 | Super-pixel image segmentation method based on genetic algorithm |
| CN116486091A (en) * | 2023-06-26 | 2023-07-25 | 尚宁智感(北京)科技有限公司 | Fan blade defect area rapid segmentation method and system based on artificial intelligence |
-
2023
- 2023-09-15 CN CN202311193894.6A patent/CN117237298A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0742431A1 (en) * | 1995-05-10 | 1996-11-13 | Mahlo GmbH & Co. KG | Method and apparatus for detecting flaws in moving fabrics or the like |
| CN102221559A (en) * | 2011-03-05 | 2011-10-19 | 河海大学常州校区 | Online automatic detection method of fabric defects based on machine vision and device thereof |
| CN108447050A (en) * | 2018-03-07 | 2018-08-24 | 湘潭大学 | A kind of Surface Flaw dividing method based on super-pixel |
| CN109961437A (en) * | 2019-04-04 | 2019-07-02 | 江南大学 | A kind of conspicuousness fabric defect detection method under the mode based on machine teaching |
| US20210174489A1 (en) * | 2019-12-04 | 2021-06-10 | Beijing Boe Optoelectronics Technology Co., Ltd. | Method and apparatus for detecting a screen, and electronic device |
| CN111754495A (en) * | 2020-06-29 | 2020-10-09 | 江南大学 | Fabric surface flaw detection method based on BRDPSO algorithm |
| CN113298777A (en) * | 2021-05-21 | 2021-08-24 | 山东大学 | Cotton leaf blight detection method and system based on color features and super-pixel clustering |
| CN115311292A (en) * | 2022-10-12 | 2022-11-08 | 南通创铭伊诺机械有限公司 | Strip steel surface defect detection method and system based on image processing |
| CN115619807A (en) * | 2022-10-31 | 2023-01-17 | 盐城工学院 | Super-pixel image segmentation method based on genetic algorithm |
| CN116486091A (en) * | 2023-06-26 | 2023-07-25 | 尚宁智感(北京)科技有限公司 | Fan blade defect area rapid segmentation method and system based on artificial intelligence |
Non-Patent Citations (1)
| Title |
|---|
| 张缓缓: "基于改进的加权中值滤波与 K-means 聚类的织物缺陷检测", 纺织学报, vol. 40, no. 12, 15 December 2019 (2019-12-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Oliveira et al. | Automatic road crack detection and characterization | |
| Tosta et al. | Segmentation methods of H&E-stained histological images of lymphoma: A review | |
| Cheng et al. | A novel computational approach for automatic dendrite spines detection in two-photon laser scan microscopy | |
| US20060204953A1 (en) | Method and apparatus for automated analysis of biological specimen | |
| CN114627125B (en) | Stainless steel tablet press surface quality evaluation method based on optical means | |
| CN105069818A (en) | Image-analysis-based skin pore identification method | |
| CN115294117B (en) | Defect detection method and related device for LED lamp beads | |
| CN106530281A (en) | Edge feature-based unmanned aerial vehicle image blur judgment method and system | |
| CN111476804B (en) | Efficient carrier roller image segmentation method, device, equipment and storage medium | |
| CN109886932A (en) | Gear ring of wheel speed sensor detection method of surface flaw based on SVM | |
| CN112801949A (en) | Method and device for determining discharge area in ultraviolet imaging detection technology | |
| CN110705619B (en) | Mist concentration grade discriminating method and device | |
| CN116523898A (en) | Tobacco phenotype character extraction method based on three-dimensional point cloud | |
| CN114972339A (en) | Data enhancement system for bulldozer structural member production abnormity detection | |
| CN117333489B (en) | Film damage detection device and detection system | |
| CN116777917B (en) | Defect detection method and system for optical cable production | |
| CN112950594B (en) | Method, device and storage medium for detecting surface defects of product | |
| WO2024016632A1 (en) | Bright spot location method, bright spot location apparatus, electronic device and storage medium | |
| CN117237298A (en) | Printed fabric defect inspection method, device and computing equipment | |
| Ghosh et al. | Entropy based divergence for leukocyte image segmentation | |
| CN116245879A (en) | Glass substrate flatness evaluation method and system | |
| CN114881984A (en) | Detection method and device for rice processing precision, electronic equipment and medium | |
| CN111429487B (en) | Method and device for segmenting adhesion foreground of depth image | |
| CN110619273B (en) | Efficient iris recognition method and recognition device | |
| Zaman et al. | Image segmentation of MRI image for brain tumor detection |
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 |