CN115266536B - Method for detecting water absorption performance of paper diaper - Google Patents
Method for detecting water absorption performance of paper diaper Download PDFInfo
- Publication number
- CN115266536B CN115266536B CN202211170963.7A CN202211170963A CN115266536B CN 115266536 B CN115266536 B CN 115266536B CN 202211170963 A CN202211170963 A CN 202211170963A CN 115266536 B CN115266536 B CN 115266536B
- Authority
- CN
- China
- Prior art keywords
- target pixel
- pixel block
- image
- water absorption
- paper diaper
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 129
- 238000010521 absorption reaction Methods 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 30
- 239000013598 vector Substances 0.000 claims abstract description 32
- 229910000365 copper sulfate Inorganic materials 0.000 claims abstract description 26
- ARUVKPQLZAKDPS-UHFFFAOYSA-L copper(II) sulfate Chemical compound [Cu+2].[O-][S+2]([O-])([O-])[O-] ARUVKPQLZAKDPS-UHFFFAOYSA-L 0.000 claims abstract description 26
- 238000001514 detection method Methods 0.000 claims abstract description 26
- 238000011156 evaluation Methods 0.000 claims abstract description 12
- 239000011159 matrix material Substances 0.000 claims description 48
- 230000008859 change Effects 0.000 abstract description 7
- 210000002700 urine Anatomy 0.000 description 7
- 238000009792 diffusion process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000035515 penetration Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000008961 swelling Effects 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/08—Investigating permeability, pore-volume, or surface area of porous materials
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/08—Investigating permeability, pore-volume, or surface area of porous materials
- G01N2015/0813—Measuring intrusion, e.g. of mercury
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Dispersion Chemistry (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention relates to the technical field of paper diaper water absorption detection, in particular to a method for detecting the water absorption performance of a paper diaper. The method comprises the following steps: respectively obtaining surface images of the diaper when the diaper does not absorb water and after the copper sulfate solution is completely diffused, and graying the surface images to obtain a first image and a second image; obtaining a uniform water absorption description factor of the diaper by using the gradient of each pixel in the second image and the mean value of the information entropy; pixel blocks containing the edges of the detected reference prints in the first image and the second image are respectively a target pixel block and a pixel block to be matched; obtaining a motion vector of each target pixel block based on the similarity of each target pixel block and each pixel block to be matched by using a three-step search method; and obtaining the water absorption performance evaluation index of the paper diaper based on the motion vector and the water absorption uniformity description factor of each target pixel block. The invention accurately detects the water absorption performance of the paper diaper through the uniform water absorption description factor after water absorption and the change condition of the movement of the detection reference mark edge caused by the water absorption of the paper diaper.
Description
Technical Field
The invention relates to the technical field of paper diaper water absorption detection, in particular to a method for detecting the water absorption performance of a paper diaper.
Background
The paper diaper is convenient to use, so that the paper diaper becomes a daily product for infants and people with special requirements, along with improvement of life quality, the quality requirement of people on the paper diaper is higher and higher, the design of the paper diaper is developed towards the direction of being thinner, healthier and more environment-friendly, and new requirements are provided for the qualities of better absorbability, quicker diffusivity, stronger leak resistance and the like.
The water absorption performance is generally evaluated according to the water permeability and the rewet rate, but a very important factor is that after the paper diaper absorbs water, partial expansion of the paper diaper cannot be caused, namely whether the water absorption is uniform or not, according to the characteristic, a tester usually judges the water absorption performance of the paper diaper according to the working experience during detection, and a unified method for evaluating the water absorption performance of the paper diaper is needed.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a method for detecting the water absorption performance of a paper diaper, which adopts the following technical scheme:
one embodiment of the invention provides a method for detecting water absorption performance of an intelligent warehouse, which comprises the following steps: manually making a detection reference mark on the paper diaper; respectively obtaining surface images of the diaper when the diaper does not absorb water and after the copper sulfate solution is completely diffused, and graying the surface images to obtain a first image and a second image; obtaining a water receiving point based on a difference image of the first image and the second image; acquiring information entropy of each pixel based on the occurrence frequency of the gray value of the pixel in the neighborhood of each pixel in the second image; obtaining a water absorption uniformity description factor of the diaper by using the gray gradient of each pixel in the second image and the mean value of the information entropy of each pixel;
dividing the first image and the second image into pixel blocks with the same size respectively, wherein the pixel blocks containing the edges of the detection reference impressions in the first image and the second image are a target pixel block and a pixel block to be matched respectively; taking the center point of the target pixel block as the circle center, and obtaining the radius of the circle based on the distance between the center point of the target pixel block and the water receiving point to obtain a characteristic circle; equally dividing the characteristic circle by using the diameter passing through the circle center to obtain a plurality of fan-shaped areas, and trisecting the radius of the characteristic circle by using a concentric circle smaller than the radius of the characteristic circle to obtain different sub-areas;
forming a characteristic matrix of the target pixel blocks based on the number of the target pixel blocks in each sub-region in the characteristic circle; obtaining a result of weighted summation of absolute values of differences between elements in the characteristic matrix of the pixel block to be matched and corresponding elements of the characteristic matrix of the target pixel block, wherein the number of division areas in the result of weighted summation and the characteristic circle is the similarity between the target pixel block and the pixel block to be matched; obtaining a motion vector of each target pixel block based on the similarity of each target pixel block and each pixel block to be matched by using a three-step search method; and obtaining the water absorption performance evaluation index of the paper diaper based on the motion vector and the water absorption uniformity description factor of each target pixel block.
Preferably, the artificially making a detection reference mark on the diaper comprises: the method comprises the following steps of (1) flatly laying the paper diapers, and if the paper diapers have textures, deepening the textures according to the textures to obtain detection reference marks to divide a water absorption area of the paper diapers into a plurality of areas; if the paper diaper has no texture, a detection reference mark is made in the water absorption area of the paper diaper manually, and the water absorption area of the paper diaper is divided into a plurality of areas.
Preferably, obtaining the water receiving point based on a difference image of the first and second images comprises; and if a plurality of pixels with the maximum gray value exist in the difference image, selecting the pixel at the central position from the pixels with the maximum gray value as the water receiving point.
Preferably, the water uptake uniformity description factor is:
wherein Q represents a water absorption uniformity describing factor; f is the average of the gray gradients of the middle pixels of the second image;
representing a gray scale gradient of a u-th pixel in the second image; n represents the number of pixels in the second image; h represents the mean value of the information entropy of each pixel in the second image.
Preferably, obtaining the radius of the circle based on the distance between the center point of the target pixel block and the water-receiving point comprises: setting an initial diameter, the radius of the circle is:
wherein r is the radius of the circle,
is the initial diameter; x and y are respectively the abscissa and the ordinate of the center point of the target pixel block;
and
respectively the abscissa and the ordinate of the water receiving point.
Preferably, the forming the feature matrix of the target pixel block based on the number of the target pixel blocks in each sub-region in the feature circle comprises: and the element of each row in the characteristic matrix is the number of target pixel blocks in each sub-region in each sector region, wherein if one target pixel block is distributed in a plurality of sub-regions in one sector region, the number of pixels belonging to the target pixel block in each sub-region in which the target pixel block is distributed is obtained, and the sub-region with the largest number of pixels is the sub-region in which the target pixel block is positioned.
Preferably, the similarity between the target pixel block and the pixel block to be matched is as follows:
wherein T represents the similarity between the target pixel block and the pixel block to be matched;
the element in the ith row and jth column of the feature matrix representing the target pixel block,
representing the ith row and the jth column in the characteristic matrix of the pixel block to be matched;
representing the weight of the element of the ith row in the feature matrix,
representing the weight of the j column element in the characteristic matrix; the weights of the elements in the ith row in the feature matrix are as follows:
wherein,
representing the offset angle of the central line in the sector area corresponding to the ith row in the characteristic matrix;
representing the deviation angle of a connecting line between the central point of the target pixel block and the water receiving point; the offset angle is an included angle between a straight line and the x axis of the rectangular coordinate system; wherein
Comprises the following steps:
wherein x and y are respectively the abscissa and the ordinate of the center point of the target pixel block;
and
respectively is the abscissa and ordinate of the water receiving point;
the weight of the element in the jth column in the feature matrix is:
wherein j represents the jth column in the feature matrix;
and representing the weight of the j-th column element in the feature matrix.
Preferably, the obtaining of the water absorption performance evaluation index of the paper diaper based on the motion vector and the water absorption uniformity description factor of each target pixel block comprises: obtaining the mean value of the modes of the motion vectors corresponding to all the target pixel blocks; obtaining the standard deviation of the module of the motion vector corresponding to all the target pixel blocks; obtaining a uniform expansion index according to the mean value and the standard deviation of the modes of the motion vectors corresponding to all the target pixel blocks, wherein the uniform expansion index and the mean value and the standard deviation of the modes of the motion vectors corresponding to all the target pixel blocks are in a negative correlation relationship; the ratio of the water absorption uniformity description factor to the expansion uniformity index is an evaluation index of the water absorption performance of the paper diaper.
The embodiment of the invention at least has the following beneficial effects: according to the invention, through setting an experimental scene, a detection reference mark is artificially made on the paper diaper before the paper diaper absorbs water, meanwhile, a colored copper sulfate solution is used for simulating urine, the copper sulfate solution has a color, the diffusion condition of the solution on the surface of the paper diaper can be more clearly observed after the paper diaper absorbs the solution, a water absorption uniformity description factor is obtained by analyzing a surface image of the paper diaper after absorbing the copper sulfate solution, and the water absorption uniformity of the paper diaper is accurately obtained; meanwhile, the change condition of the edge of the reference mark is detected on the surface of the paper diaper before and after the solution is absorbed, so that the expansion condition of the paper diaper after the solution is absorbed is visually reflected; the water absorption performance of the paper diaper is accurately detected through the water absorption uniform description factor after water absorption and the change condition of the movement of the detection reference mark edge caused by the water absorption of the paper diaper, and meanwhile, the detection standard of the water absorption performance of the paper diaper is given.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for detecting the water absorption performance of a diaper.
Detailed Description
In order to further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description of the method for detecting the water absorption performance of the paper diaper according to the present invention with reference to the accompanying drawings and preferred embodiments is provided below. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following describes a specific scheme of the method for detecting the water absorption performance of the paper diaper provided by the invention in detail with reference to the accompanying drawings.
Example 1:
the main application scenarios of the invention are as follows: the water absorption test was performed using a copper sulfate solution as a simulated urine. A certain amount of simulated urine is used for carrying out a penetration experiment on the flat and well-placed paper diaper, namely, the urine is dropped onto the paper diaper at a certain speed, a beaker is placed below the paper diaper, and the leaked simulated urine is collected. For the prominent experiment effect, do benefit to the observation and draw the experimental result, tile the back with panty-shape diapers, the people is for being divided into a plurality of regions with panty-shape diapers, if panty-shape diapers have the texture promptly, just deepen according to its texture, obtain and detect the benchmark impression, if there is not the texture, then draw a plurality of detection benchmark impressions on panty-shape diapers, the impression is drawn along the panty-shape diapers level, draw deeply many times and make the impression in the experimentation, also can keep easily detecting the state after absorbing water promptly.
Referring to fig. 1, a flow chart of a method for detecting the water absorption performance of a paper diaper according to an embodiment of the present invention is shown, the method includes the following steps:
firstly, manually making a detection reference mark on a paper diaper; respectively obtaining surface images of the diaper when the diaper does not absorb water and after the copper sulfate solution is completely diffused, and graying the surface images to obtain a first image and a second image; obtaining a water receiving point based on a difference image of the first image and the second image; obtaining the information entropy of each pixel based on the frequency of the occurrence of the gray value of the pixel in the neighborhood of each pixel in the second image; and obtaining a water absorption uniformity description factor of the diaper by using the gray gradient of each pixel in the second image and the mean value of the information entropy of each pixel.
Firstly, the diapers are produced according to batches during workshop production, so the invention aims at performing sampling inspection on the diapers of the same batch to obtain the water absorption performance of the diapers of the same batch. In order to better observe the absorption of urine on the paper diaper, the test of the water absorption performance of the paper diaper is carried out by using copper sulfate solution to simulate the urine. A certain amount of copper sulfate solution is used for carrying out a permeation experiment on the flat and well-placed paper diaper, namely, the copper sulfate solution is dripped onto the paper diaper at a certain speed, a beaker is placed below the paper diaper, and the leaked copper sulfate solution is collected. And shooting the surface image of the paper diaper without adding the copper sulfate solution by using a camera and graying the image to obtain a first image.
The water permeating into the beaker is photographed by using a camera, and the beaker is read by using a neural network to obtain the permeation quantity K of the paper diaper. Setting the threshold value c =20mm, and when the required penetration amount K is larger than the threshold value c, the disqualification of the paper diaper can be directly reported without carrying out the next analysis. If the permeation quantity is qualified, the water absorption performance of the paper diaper is obtained by analyzing the final diffusion condition of the copper sulfate solution on the paper diaper. And shooting a surface image of the paper diaper after the copper sulfate solution is diffused on the paper diaper by using a camera, and graying to obtain a second image, wherein the first image and the second image only contain a water absorption area in the paper diaper.
Further, the more uniform the distribution of the copper sulfate solution on the paper diaper is detected, which indicates that the paper diaper has better water absorption performance. Wherein, the distribution of the copper sulfate solution on the paper diaper is analyzed by color difference analysis, namely, if the copper sulfate solution is proper, the color of the paper diaper obtained after detection is uniform. At this time, a water receiving point needs to be found according to a difference image of the first image and the second image, wherein the water receiving point is a place where the paper diaper receives the copper sulfate solution, it needs to be noted that the place where the copper sulfate solution is received in the actual process is an area, but in the invention, one pixel represents the whole area where the copper sulfate solution is received; and if a plurality of pixels with the maximum gray value exist, selecting the pixel at the central position from the pixels with the maximum gray value as a water receiving point, and marking the water receiving point in the first image and the second image.
Finally, obtaining a gray gradient image of the second image by using a Sobel operator, wherein the pixel value of each pixel in the gray gradient image is the gray gradient of each pixel in the second image; based on the gray level image, the image gradients can be observed to converge from the periphery to the water receiving points, and the value of each gray level gradient is very small, namely the gray level change of the image is very uniform; the water uptake uniformity profiling factor thus obtained was:
wherein Q represents a water absorption uniformity description factor; f is the average of the gray scale gradients of the middle pixels of the second image;
representing a gray scale gradient of a u-th pixel in the second image; n represents the number of pixels in the second image; h represents an average value of information entropy of each pixel in the second image. The smaller the average value f of the gray scale gradient of the pixels in the second image is, and the smaller the standard deviation of the gray scale gradient is, the smaller the average value H of the information entropy of each pixel in the second image is, and the smaller Q is, the more uniform the gray scale change is.
Wherein H is the average value of the information entropies of all pixels in the second image, and the smaller the entropy value is, the more uniform the paper diaper absorbs the copper sulfate solution, that is, the more uniform the color of the copper sulfate solution on the paper diaper is, the information entropy reflects the number of colors contained around one pixel and the complexity of the colors, wherein the average value of the information entropies of all the pixels in the second image is as follows:
wherein,
represents the information entropy of the o-th pixel in the second image,
is the frequency of occurrence of pixels with a grey value m in the neighborhood of one pixel 8 in the second image.
Dividing the first image and the second image into pixel blocks with the same size respectively, wherein the pixel blocks containing the edges of the detection reference marks in the first image and the second image are respectively a target pixel block and a pixel block to be matched; taking the center point of the target pixel block as the circle center, and obtaining the radius of the circle based on the distance between the center point of the target pixel block and the water receiving point to obtain a characteristic circle; the characteristic circle is equally divided by the diameter passing through the center of the circle to obtain a plurality of fan-shaped areas, and the radius of the characteristic circle is equally divided by the concentric circle smaller than the radius of the characteristic circle to obtain different sub-areas.
First, although a diaper expands due to water absorption after water absorption, a high-quality diaper uniformly distributes water to other parts after water absorption at a certain part, so that the part receiving water is not very expanded, and the smaller the expansion degree, the stronger the subsequent water absorption performance, so that the water absorption performance of the diaper can be evaluated by detecting the average expansion degree and the highest expansion degree of the diaper after water absorption. In order to reduce the amount of calculation, the first image and the second image are partitioned to obtain pixel blocks of the same size, where the size of the pixel blocks is N × N, preferably, N in this embodiment has a value of 5, and the size is set by an implementer according to actual conditions during actual use. And obtaining the edge of the detection reference mark in the first image and the second image, wherein the first image comprises a pixel block for detecting the edge of the reference mark as a target pixel block, and the second image comprises a pixel block for detecting the edge of the reference mark as a pixel block to be matched.
The expansion degree of the paper diaper after washing water is judged according to the magnitude of a motion vector model, namely the larger the motion vector of the edge of the reference mark, the smaller the motion vector is, and the smaller the expansion degree is.
Then, the motion vector for detecting the edge of the reference mark is generally obtained by using a three-step search method, but the block matching criterion in the three-step search method only considers the gray scale change, whereas in the present invention, since the color-containing copper sulfate solution renders the image, it is easy to match different pixel blocks to the position of the non-corresponding pixel block when matching is performed, and the matching error is increased. Whether the distribution situation of the target pixel blocks around each target pixel block is similar to the distribution situation of the pixel blocks to be matched around the pixel blocks to be matched or not needs to be considered, and the similarity between the target pixel blocks and the pixel blocks to be matched is obtained.
Further, taking a target pixel block as an example, a center point of the target pixel block is obtained, and a circle is drawn by taking the center point as a circle center, wherein an initial diameter of the circle is set
Then the radius of the circle is:
wherein r is the radius of the circle,
is the initial diameter; x and y are respectively the abscissa and the ordinate of the center point of the target pixel block;
and
respectively the abscissa and ordinate of the water receiving point. And the circle is referred to as a feature circle of the target pixel block. Dividing the characteristic circle into fan-shaped areas with the same size through multiple diameters of the center of the characteristic circle, wherein the central angle of each fan-shaped area is equal, preferably, 8 fan-shaped areas are obtained in the embodiment, and the central angle of each fan-shaped area is 45 degrees; and simultaneously, trisecting the radius of the characteristic circle by using two concentric circles in the characteristic circle to obtain different sub-areas, wherein the characteristic circle has 24 sub-areas in total, and one sector area comprises 3 sub-areas.
Thirdly, forming a characteristic matrix of the target pixel blocks based on the number of the target pixel blocks in each sub-area in the characteristic circle; obtaining a result of weighted summation of absolute values of differences between elements in the feature matrix of the pixel block to be matched and corresponding elements of the feature matrix of the target pixel block, wherein the number of the weighted summation result and divided areas in the feature circle is the similarity between the target pixel block and the pixel block to be matched; obtaining a motion vector of each target pixel block based on the similarity of each target pixel block and each pixel block to be matched by using a three-step search method; and obtaining the water absorption performance evaluation index of the paper diaper based on the motion vector and the water absorption uniformity description factor of each target pixel block.
Firstly, counting the number of target pixel blocks of each sub-region in each sector region, and if one target pixel block is distributed in a plurality of sub-regions in one sector region, obtaining the number of pixels belonging to the target pixel block in each sub-region in which the target pixel block is distributed, wherein the sub-region with the largest number of pixels is the sub-region in which the target pixel block is located. The number of target pixel blocks in each sub-region in each sector region is utilized to construct a feature matrix of the target pixel blocks corresponding to the feature circle, each sector region has three sub-regions, and 8 sector regions are shared, so the size of the feature matrix is 8 × 3, the elements of each line in the feature matrix are the number of the target pixel blocks in each sub-region in each sector region, the first element of each line is the number of the target pixel blocks in the sub-region closest to the circle center in the sector region, the third element is the number of the target pixel blocks in the sub-region closest to the circumference of the feature circle, and the second element is the number of the target pixel blocks in the middle sub-region.
The feature matrix of each target pixel block in the first image can be obtained, and the feature matrix of each pixel block to be matched in the second image can also be obtained according to the method for obtaining the feature matrix of each target pixel block in the first image.
Further, the similarity between the target pixel block and the pixel block to be matched is characterized through the similarity between the characteristic matrix of each target pixel block and the characteristic matrix of each pixel block to be matched; taking a target pixel block and a pixel block to be matched as an example, obtaining the similarity between the target pixel block and the pixel block to be matched:
wherein T represents the similarity between the target pixel block and the pixel block to be matched,
the element in the ith row and jth column of the feature matrix representing the target pixel block,
representing the ith row and the jth column in the characteristic matrix of the pixel block to be matched;
representing the weight of the element of the ith row in the feature matrix,
representing the weight of the element of the jth column in the characteristic matrix; the weights of the elements in the ith row in the feature matrix are:
wherein,
representing the offset angle of a central line in a sector area corresponding to the ith row in the characteristic matrix;
representing the deviation angle of a connecting line between the central point of the target pixel block and the water receiving point; the offset angle is an included angle between a straight line and the x axis of the rectangular coordinate system.
According to the analysis of the diffusion rule of the copper sulfate solution at the water receiving point, when a certain detection reference impression absorbs water and expands, the expansion direction is that the water receiving point is taken as the center and the detection reference impression expands towards the periphery, so that the motion vector of the target pixel block has a high probability that the target pixel block moves outwards along the direction of the water receiving point, the motion situation of the target pixel block in the direction is probably the most consistent for the pixel block, and the motion difference of other target pixel blocks around the target pixel block is larger as the directions are inconsistent due to the diffusion property, so that in the process of weight design, the weight is given to the pixel block which deviates from the direction more, the weight is smaller, and the weight is given to the pixel block which deviates from the direction more, the weight is larger.
Wherein
Comprises the following steps:
wherein x and y are respectively the abscissa and the ordinate of the center point of the target pixel block;
and
respectively is the abscissa and ordinate of the water receiving point;
the weight of the element in the jth column in the feature matrix is:
wherein j represents the jth column in the feature matrix;
the weight values of the j-th row of elements in the characteristic matrix are expressed, and according to the sub-regions in the characteristic circle, the closer to the target pixel block, the more important the description of the target pixel block is, that is, if the target pixel block closer to the center of the characteristic circle in the sub-region closest to the center of the characteristic circle in the sector region and the sub-region closest to the edge of the characteristic circle in the sector region has a greater influence on the distribution of the target pixel block around the target pixel block corresponding to the characteristic circle, the closer to the target pixel block at the center of the characteristic circle, the more sensitive the value is, the more sensitive the difference between the distribution of the target pixel block around the center of the characteristic circle and the distribution of the target pixel block to be matched around the target pixel block to be matched can be judged, and the similarity between the target pixel block and the pixel block to be matched can be described more easily. In obtaining
And
these two values then need to be normalized separately.
Furthermore, the motion vector of each target pixel block is obtained by combining a three-step search method according to the similarity between the target pixel block in the first image and the pixel block to be matched in the second image
Obtaining the mean of the modes of all motion vectors:
wherein,
representing the mean of the modes of all motion vectors, wherein l represents the motion vectors corresponding to a total of l target pixel blocks in the first image;
representing the v-th motion vector. Meanwhile, the standard deviation of the modulus of the motion vector corresponding to all the target pixel blocks is obtained:
obtaining a swelling uniformity index P according to the mean value and the standard deviation of the modes of the motion vectors corresponding to all the target pixel blocks:
wherein, P represents the expansion uniformity index, and when the average value of the modes of all the motion vectors is smaller, the standard deviation of the modes of the motion vectors is smaller, which indicates that the expansion is uniform and the lump phenomenon does not occur.
Finally, obtaining a water absorption performance evaluation index A of the paper diaper, wherein the water absorption performance evaluation index of the paper diaper is the ratio of a water absorption uniformity description factor and an expansion uniformity index of the paper diaper; when the paper diaper absorbs the copper sulfate solution, the more uniform the color change of the surface, namely the smaller the water absorption uniformity description factor, the smaller the surface expansion after water absorption, and the more uniform the expansion, namely the larger the expansion uniformity index, the better the water absorption performance of the paper diaper; setting a water absorption performance threshold epsilon, preferably, the value of epsilon in this embodiment is 0.18, if the water absorption performance evaluation index is less than or equal to the water absorption performance threshold, it indicates that the water absorption performance of the paper diaper is excellent, and indicates that the quality of the paper diapers produced in the same batch is qualified, and if the water absorption performance evaluation index is greater than the water absorption performance threshold, it indicates that the quality of the paper diapers produced in the batch is likely to be unqualified, and further detection is required.
It should be noted that: the sequence of the above embodiments of the present invention is only for description, and does not represent the advantages or disadvantages of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, which is intended to cover any modifications, equivalents, improvements, etc. within the spirit and scope of the present invention.
Claims (5)
1. A method for detecting the water absorption performance of a paper diaper is characterized by comprising the following steps: manually making a detection reference mark on the paper diaper; respectively obtaining surface images of the diaper when the diaper does not absorb water and after the copper sulfate solution is completely diffused, and graying the surface images to obtain a first image and a second image; obtaining a water receiving point based on a difference image of the first image and the second image; obtaining the information entropy of each pixel based on the frequency of the occurrence of the gray value of the pixel in the neighborhood of each pixel in the second image; obtaining a water absorption uniformity description factor of the diaper by using the gray gradient of each pixel in the second image and the mean value of the information entropy of each pixel;
dividing the first image and the second image into pixel blocks with the same size respectively, wherein the pixel blocks containing the edges of the detection reference imprints in the first image and the second image are respectively a target pixel block and a pixel block to be matched; taking the center point of the target pixel block as the circle center, and obtaining the radius of the circle based on the distance between the center point of the target pixel block and the water receiving point to obtain a characteristic circle; equally dividing the characteristic circle by using the diameter passing through the circle center to obtain a plurality of fan-shaped areas, and trisecting the radius of the characteristic circle by using a concentric circle smaller than the radius of the characteristic circle to obtain different sub-areas;
forming a characteristic matrix of the target pixel blocks based on the number of the target pixel blocks in each sub-region in the characteristic circle; obtaining a result of weighted summation of absolute values of differences between elements in the characteristic matrix of the pixel block to be matched and corresponding elements of the characteristic matrix of the target pixel block, wherein the number of division areas in the result of weighted summation and the characteristic circle is the similarity between the target pixel block and the pixel block to be matched; obtaining a motion vector of each target pixel block based on the similarity of each target pixel block and each pixel block to be matched by using a three-step search method; obtaining the water absorption performance evaluation index of the paper diaper based on the motion vector and the water absorption uniformity description factor of each target pixel block;
the obtaining of the water receiving point based on the difference image of the first and second images comprises: the first image and the second image are subjected to difference to obtain a difference image, the pixel with the largest gray value in the difference image is obtained as a water receiving point, and if a plurality of pixels with the largest gray value are obtained, the pixel at the center position is selected from the pixels with the largest gray value as the water receiving point;
the water absorption uniformity description factor is as follows:
wherein Q represents a water absorption uniformity describing factor; f is the average of the gray gradients of the middle pixels of the second image;
representing a gray scale gradient of a u-th pixel in the second image; n represents the number of pixels in the second image; h represents the mean value of the information entropy of each pixel in the second image;
the similarity between the target pixel block and the pixel block to be matched is as follows:
wherein T represents the similarity between the target pixel block and the pixel block to be matched;
the element in the ith row and jth column of the feature matrix representing the target pixel block,
representing the ith row and the jth column in the characteristic matrix of the pixel block to be matched;
representing the weight of the element of the ith row in the feature matrix,
representing the weight of the element of the jth column in the characteristic matrix; the weights of the elements in the ith row in the feature matrix are:
wherein,
representing the offset angle of the central line in the sector area corresponding to the ith row in the characteristic matrix;
representing the deviation angle of a connecting line between the central point of the target pixel block and the water receiving point; the offset angle is an included angle between a straight line and the x axis of the rectangular coordinate system; wherein
Comprises the following steps:
wherein x and y are respectively the abscissa and the ordinate of the center point of the target pixel block;
and
respectively the abscissa and the ordinate of the water receiving point;
the weight of the element in the jth column in the feature matrix is:
wherein j represents the jth column in the feature matrix;
and representing the weight of the j-th column element in the feature matrix.
2. The method for detecting the water absorption performance of the paper diaper as claimed in claim 1, wherein the artificially making a detection reference mark on the paper diaper comprises: the method comprises the following steps of (1) flatly laying the paper diapers, and if the paper diapers have textures, deepening the textures according to the textures to obtain detection reference marks to divide a water absorption area of the paper diapers into a plurality of areas; if the paper diaper has no texture, a detection reference mark is made in the water absorption area of the paper diaper manually, and the water absorption area of the paper diaper is divided into a plurality of areas.
3. The method as claimed in claim 1, wherein the obtaining the radius of the circle based on the distance between the center point of the target pixel block and the water receiving point comprises: setting an initial diameter, the radius of the circle is:
wherein r is the radius of the circle,
is the initial diameter; x and y are respectively the abscissa and the ordinate of the center point of the target pixel block;
and
respectively the abscissa and ordinate of the water receiving point.
4. The method for detecting the water absorption performance of the paper diaper as claimed in claim 1, wherein the forming of the feature matrix of the target pixel blocks based on the number of the target pixel blocks in each sub-area in the feature circle comprises: and the element of each line in the characteristic matrix is the number of target pixel blocks in each sub-region in each sector region, wherein if one target pixel block is distributed in a plurality of sub-regions in one sector region, the number of pixels belonging to the target pixel block in each sub-region in which the target pixel block is distributed is obtained, and the sub-region with the largest number of pixels is the sub-region in which the target pixel block is located.
5. The method for detecting the water absorption performance of the paper diaper according to claim 1, wherein the obtaining of the water absorption performance evaluation index of the paper diaper based on the motion vector and the water absorption uniformity description factor of each target pixel block comprises: obtaining the mean value of the modes of the motion vectors corresponding to all the target pixel blocks; obtaining the standard deviation of the module of the motion vector corresponding to all the target pixel blocks; obtaining a uniform expansion index according to the mean value and the standard deviation of the modes of the motion vectors corresponding to all the target pixel blocks, wherein the uniform expansion index and the mean value and the standard deviation of the modes of the motion vectors corresponding to all the target pixel blocks are in a negative correlation relationship; the ratio of the water absorption uniformity description factor to the expansion uniformity index is an evaluation index of the water absorption performance of the paper diaper.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211170963.7A CN115266536B (en) | 2022-09-26 | 2022-09-26 | Method for detecting water absorption performance of paper diaper |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211170963.7A CN115266536B (en) | 2022-09-26 | 2022-09-26 | Method for detecting water absorption performance of paper diaper |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115266536A CN115266536A (en) | 2022-11-01 |
| CN115266536B true CN115266536B (en) | 2022-12-13 |
Family
ID=83756160
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211170963.7A Active CN115266536B (en) | 2022-09-26 | 2022-09-26 | Method for detecting water absorption performance of paper diaper |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115266536B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116664583B (en) * | 2023-08-02 | 2023-10-13 | 长沙康威日用品有限公司 | Paper diaper water absorption diffusivity detection method based on artificial intelligence |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2448980A1 (en) * | 2001-05-29 | 2002-12-05 | Tissueinformatics, Inc. | Robust stain detection and quantification for histological specimens based on a physical model for stain absorption |
| CN101625759A (en) * | 2009-07-30 | 2010-01-13 | 重庆医科大学 | Image quality evaluation method |
| CN103778655A (en) * | 2014-01-28 | 2014-05-07 | 西安理工大学 | Color natural image calculation artifying method based on self-adaption ink painting spreading |
| WO2015186518A1 (en) * | 2014-06-06 | 2015-12-10 | 三菱電機株式会社 | Image analysis method, image analysis device, image analysis system, and portable image analysis device |
| CN105973760A (en) * | 2016-07-13 | 2016-09-28 | 湖南康程护理用品有限公司 | Paper diaper urine diffusion path detection system and method |
| CN107228812A (en) * | 2016-03-24 | 2017-10-03 | 香港理工大学 | Moisture absorption and the detection method and device of transmission in weaving face fabric |
| CN107833247A (en) * | 2017-11-29 | 2018-03-23 | 合肥赑歌数据科技有限公司 | A kind of image texture extracting method based on matrix analysis |
| CN109803619A (en) * | 2016-11-30 | 2019-05-24 | 尤妮佳股份有限公司 | Absorber and its manufacturing method and absorbent commodity |
| CN113920121A (en) * | 2021-12-14 | 2022-01-11 | 武汉亚美高工艺制品有限公司 | Artwork printing streak detection method and system based on image processing |
| CN114782562A (en) * | 2022-06-18 | 2022-07-22 | 南通寝尚纺织品有限公司 | Garment fabric dip dyeing monitoring method based on data identification and artificial intelligence system |
| CN114782823A (en) * | 2022-06-14 | 2022-07-22 | 江西省水利科学院 | Rock-fill dam volume weight detection method based on drilling coring and in-hole image recognition |
| CN114782419A (en) * | 2022-06-17 | 2022-07-22 | 山东水利建设集团有限公司 | Water conservancy construction gradient detection method |
| CN115049835A (en) * | 2022-08-16 | 2022-09-13 | 众烁精密模架(南通)有限公司 | Data preprocessing method based on die-casting die defect identification |
| CN115063420A (en) * | 2022-08-16 | 2022-09-16 | 江苏美克美斯自动化科技有限责任公司 | Detection and evaluation method for mixing performance of intelligent mixing machine |
| CN115082470A (en) * | 2022-08-22 | 2022-09-20 | 启东市固德防水布有限公司 | Waterproof cloth performance detection method and system based on image recognition |
| CN115100436A (en) * | 2022-08-29 | 2022-09-23 | 江苏永银化纤有限公司 | Colored silk dyeing method based on image recognition |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110717922A (en) * | 2018-07-11 | 2020-01-21 | 普天信息技术有限公司 | Image definition evaluation method and device |
| CN113989313B (en) * | 2021-12-23 | 2022-03-22 | 武汉智博通科技有限公司 | Edge detection method and system based on image multidimensional analysis |
-
2022
- 2022-09-26 CN CN202211170963.7A patent/CN115266536B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2448980A1 (en) * | 2001-05-29 | 2002-12-05 | Tissueinformatics, Inc. | Robust stain detection and quantification for histological specimens based on a physical model for stain absorption |
| CN101625759A (en) * | 2009-07-30 | 2010-01-13 | 重庆医科大学 | Image quality evaluation method |
| CN103778655A (en) * | 2014-01-28 | 2014-05-07 | 西安理工大学 | Color natural image calculation artifying method based on self-adaption ink painting spreading |
| WO2015186518A1 (en) * | 2014-06-06 | 2015-12-10 | 三菱電機株式会社 | Image analysis method, image analysis device, image analysis system, and portable image analysis device |
| CN107228812A (en) * | 2016-03-24 | 2017-10-03 | 香港理工大学 | Moisture absorption and the detection method and device of transmission in weaving face fabric |
| CN105973760A (en) * | 2016-07-13 | 2016-09-28 | 湖南康程护理用品有限公司 | Paper diaper urine diffusion path detection system and method |
| CN109803619A (en) * | 2016-11-30 | 2019-05-24 | 尤妮佳股份有限公司 | Absorber and its manufacturing method and absorbent commodity |
| CN107833247A (en) * | 2017-11-29 | 2018-03-23 | 合肥赑歌数据科技有限公司 | A kind of image texture extracting method based on matrix analysis |
| CN113920121A (en) * | 2021-12-14 | 2022-01-11 | 武汉亚美高工艺制品有限公司 | Artwork printing streak detection method and system based on image processing |
| CN114782823A (en) * | 2022-06-14 | 2022-07-22 | 江西省水利科学院 | Rock-fill dam volume weight detection method based on drilling coring and in-hole image recognition |
| CN114782419A (en) * | 2022-06-17 | 2022-07-22 | 山东水利建设集团有限公司 | Water conservancy construction gradient detection method |
| CN114782562A (en) * | 2022-06-18 | 2022-07-22 | 南通寝尚纺织品有限公司 | Garment fabric dip dyeing monitoring method based on data identification and artificial intelligence system |
| CN115049835A (en) * | 2022-08-16 | 2022-09-13 | 众烁精密模架(南通)有限公司 | Data preprocessing method based on die-casting die defect identification |
| CN115063420A (en) * | 2022-08-16 | 2022-09-16 | 江苏美克美斯自动化科技有限责任公司 | Detection and evaluation method for mixing performance of intelligent mixing machine |
| CN115082470A (en) * | 2022-08-22 | 2022-09-20 | 启东市固德防水布有限公司 | Waterproof cloth performance detection method and system based on image recognition |
| CN115100436A (en) * | 2022-08-29 | 2022-09-23 | 江苏永银化纤有限公司 | Colored silk dyeing method based on image recognition |
Non-Patent Citations (2)
| Title |
|---|
| Comparison of image-based methods for determining the inline mixing uniformity of pesticides in direct nozzle injection systems;Xiang Dai 等;《ScienceDirect》;20200103;第157-175页 * |
| 基于灰度共生矩阵相似图的图像质量评价方法;孙荣荣;《计算机应用》;20200710;第第40卷卷;第177-179页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115266536A (en) | 2022-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113408423B (en) | Aquatic product target real-time detection method suitable for TX2 embedded platform | |
| Fotheringham | Scale-independent spatial analysis | |
| CN110415257B (en) | Gas-liquid two-phase flow overlapped bubble image segmentation method | |
| CN115266536B (en) | Method for detecting water absorption performance of paper diaper | |
| CN111507976B (en) | Defect detection method and system based on multi-angle imaging | |
| CN107229930A (en) | A kind of pointer instrument numerical value intelligent identification Method and device | |
| CN109613006A (en) | A kind of fabric defect detection method based on end-to-end neural network | |
| CN107240112B (en) | Individual X corner extraction method in complex scene | |
| CN101894257A (en) | Method for evaluating quality of multi-scale gradual iris image | |
| CN106680086A (en) | Video extensometer applied to high-speed tensile experiment of plastic material | |
| CN104992183B (en) | The automatic testing method of well-marked target in natural scene | |
| CN104331693B (en) | A kind of printed matter symmetry detection methods and system | |
| CN106937109B (en) | The method that low cost judges resolution ratio of camera head level | |
| CN113935998A (en) | Rubber and plastic part mottling detection method based on machine vision | |
| CN101968877A (en) | Coded mark point design method for double-layer arc | |
| CN110033012A (en) | A kind of production method for tracking target based on channel characteristics weighted convolution neural network | |
| CN109840497A (en) | A kind of pointer-type water meter reading detection method based on deep learning | |
| CN108830899A (en) | A kind of center of circle detection method that the quick self-adapted angle point based on geometrical characteristic combines | |
| CN110366244A (en) | A kind of WiFi fingerprint indoor orientation method | |
| CN109975307A (en) | Bearing surface defect detection system and detection method based on statistics projection training | |
| CN115841491A (en) | Quality detection method of porous metal material | |
| CN113052110B (en) | Three-dimensional interest point extraction method based on multi-view projection and deep learning | |
| CN107194917A (en) | In-orbit SAR image change detection based on DAP and ARELM | |
| CN115311293B (en) | Rapid matching method for printed matter pattern | |
| CN117169247A (en) | Metal surface defect multi-dimensional detection method and system based on machine vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A testing method for water absorption performance of diapers Effective date of registration: 20231017 Granted publication date: 20221213 Pledgee: Jiangsu Nantong Rural Commercial Bank Co.,Ltd. Xingdong Branch Pledgor: Nantong Junru sanitary products Co.,Ltd. Registration number: Y2023980061386 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |