CN115222761A - Polyphenyl particle product quality detection method based on computer vision technology - Google Patents
Polyphenyl particle product quality detection method based on computer vision technology Download PDFInfo
- Publication number
- CN115222761A CN115222761A CN202211140450.1A CN202211140450A CN115222761A CN 115222761 A CN115222761 A CN 115222761A CN 202211140450 A CN202211140450 A CN 202211140450A CN 115222761 A CN115222761 A CN 115222761A
- Authority
- CN
- China
- Prior art keywords
- gray level
- polyphenyl
- dependent
- gray
- evaluation
- 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
- 229920006389 polyphenyl polymer Polymers 0.000 title claims abstract description 152
- 239000002245 particle Substances 0.000 title claims abstract description 128
- 238000005516 engineering process Methods 0.000 title claims abstract description 18
- 238000001514 detection method Methods 0.000 title claims abstract description 13
- 230000001419 dependent effect Effects 0.000 claims abstract description 165
- 238000011156 evaluation Methods 0.000 claims abstract description 74
- 238000000034 method Methods 0.000 claims abstract description 27
- 239000008187 granular material Substances 0.000 claims abstract description 24
- 229940095686 granule product Drugs 0.000 claims abstract description 18
- 239000011159 matrix material Substances 0.000 claims abstract description 15
- 238000013441 quality evaluation Methods 0.000 claims abstract description 15
- 238000011077 uniformity evaluation Methods 0.000 claims abstract description 14
- 239000000126 substance Substances 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 5
- 239000004793 Polystyrene Substances 0.000 description 4
- 238000005187 foaming Methods 0.000 description 4
- 238000009413 insulation Methods 0.000 description 4
- 229920002223 polystyrene Polymers 0.000 description 4
- 229920006248 expandable polystyrene Polymers 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 239000012508 resin bead Substances 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 239000002002 slurry Substances 0.000 description 2
- 239000011324 bead Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 239000012774 insulation material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000004570 mortar (masonry) Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of quality detection of polyphenyl granule products, in particular to a method for detecting the quality of polyphenyl granule products based on a computer vision technology, which comprises the following steps: obtaining a gray level image of the polyphenyl particles, constructing a gray level dependency matrix of the image, and obtaining dependency elements corresponding to each gray level; acquiring a maximum dependent element, calculating a correlation index of the maximum dependent element, and calculating a first evaluation coefficient according to a second moment of the correlation index; obtaining a difference index of the maximum dependent element, obtaining a second evaluation coefficient according to the ratio of the difference index to the correlation index, and calculating a third evaluation coefficient according to the difference of each dependent element in the highest gray level; and obtaining uniformity evaluation according to the first, second and third evaluation coefficients, and obtaining quality evaluation of the polyphenyl granule product according to the uniformity evaluation index. The invention can accurately and efficiently detect the quality of the polyphenyl particle product.
Description
Technical Field
The invention relates to the technical field of quality detection of polyphenyl particle products, in particular to a polyphenyl particle product quality detection method based on a computer vision technology.
Background
The polystyrene particles are made by expanding and foaming expandable polystyrene resin beads as basic raw materials. The polyphenyl particles are the main aggregate of the polyphenyl particle thermal mortar, and the use of the polyphenyl particles is directly influenced by the size of the polyphenyl particles because the polyphenyl particles are mixed with other materials in the use process. In the production of polyphenyl particles, the particle size is set by adjusting relevant parameters of the production equipment. In the actual production of the polyphenyl granules, the foaming effect is influenced because the production environment of high temperature and high pressure is difficult to control. Resulting in non-uniform sized particles. Generally, the detection of the size of the polyphenyl particle is performed by sampling detection or mechanical detection, and the universality and the high efficiency are not possessed.
Disclosure of Invention
In order to solve the above technical problems, the present invention aims to provide a method for detecting the quality of a polyphenyl granule product based on a computer vision technology, which adopts the following technical scheme:
obtaining a polyphenyl particle gray image, and dividing gray levels of gray values of all pixel points on the polyphenyl particle gray image; performing connected domain processing on the pixel points corresponding to the maximum gray level to obtain the maximum connected domain as the dependent distance of the pixel points to calculate the gray level dependent matrix of the polyphenyl granule gray level image; all interdependent pixel points of the same gray level are marked as a dependent element within a dependent distance;
acquiring the dependent element with the largest number of mutually dependent pixel points in each gray level, recording the dependent element as the maximum dependent element, and calculating the correlation index of the maximum dependent element in each gray level according to the probability corresponding to the maximum dependent element in each gray level and the probabilities corresponding to other dependent elements; calculating a first evaluation coefficient according to the second moment of the correlation index;
calculating the difference index of the maximum dependent element in each gray level according to the difference value between the probability corresponding to the maximum dependent element in each gray level and the probabilities corresponding to other dependent elements; obtaining a second evaluation coefficient according to the ratio of the difference index to the correlation index; calculating a third evaluation coefficient according to the difference of the number of pixel points contained in each dependent element in the highest gray level;
obtaining uniformity evaluation according to the first evaluation coefficient, the second evaluation coefficient and the third evaluation coefficient, and obtaining quality evaluation of the polyphenyl granule product according to the uniformity evaluation index; and when the quality evaluation of the polyphenyl particle product is greater than the evaluation threshold value, the polyphenyl particle product has good quality.
Preferably, the dividing of the gray levels of all the pixel points on the gray image of the polyphenyl granules specifically comprises: the method comprises the steps of obtaining the minimum value and the maximum value of gray values of all pixel points on a polyphenyl particle gray image, and averagely dividing a gray interval between the minimum value and the maximum value into preset number of gray levels.
Preferably, the calculating the gray-level dependency matrix of the polyphenyl particle gray-level image specifically comprises: and setting the dependence distance to be the same as the maximum connected domain size, setting the dependence threshold value between elements to be 0, and acquiring a gray level dependence matrix.
Preferably, the method for acquiring the correlation index specifically includes:
wherein the content of the first and second substances,
the index of the correlation of the largest dependent element when the gray level is i,
indicating the number of interdependent pixels contained by the largest dependent element,
representing the probability of occurrence of the i-max dependent element in gray level,
and representing the probability of the occurrence of the dependent elements with the number j of the mutually dependent pixel points in the gray level i.
Preferably, the method for acquiring the first evaluation coefficient specifically includes:
wherein, DAMS represents a first evaluation coefficient,
representing the total number of gray levels in a gray-scale image of the polyphenyl particles,
and the correlation index of the maximum dependent element when the gray level is i is represented.
Preferably, the method for obtaining the difference index specifically includes:
wherein the content of the first and second substances,
the index of the difference of the maximum dependent elements when the gray level is i is represented,
indicating the number of interdependent pixels contained by the largest dependent element,
representing the probability of the occurrence of the i-max dependent element in the gray level,
and expressing the probability of the occurrence of dependent elements with the number j of mutually dependent pixel points in the gray level i.
Preferably, the method for acquiring the second evaluation coefficient specifically includes:
wherein MON is a second evaluation coefficient,
representing the total number of gray levels in a gray scale image of polyphenyl particles,
the index of the correlation of the largest dependent element when the gray level is i,
and expressing the difference index of the maximum dependent element when the gray level is i.
Preferably, the method for acquiring the third evaluation coefficient specifically includes:
wherein DEM is a third evaluation coefficient,
representing the number of dependent elements in the highest gray level,
indicating that the tth dependent element contains the number of interdependent pixels,
and the t-1 th dependent element is represented to contain the number of interdependent pixel points.
Preferably, the first evaluation coefficient, the second evaluation coefficient and the third evaluation coefficient are in a negative correlation with uniformity evaluation; the uniformity evaluation is in a positive correlation with the quality evaluation of the polyphenyl granules.
The embodiment of the invention at least has the following beneficial effects:
according to the method, a gray level dependence matrix is constructed by obtaining gray level images of stacked polyphenyl particles and according to the difference of local gray levels formed by mutual shielding of the stacked particles in the images, and dependence elements corresponding to each gray level are obtained; acquiring a maximum dependent element, calculating a correlation index of the maximum dependent element, and acquiring a first evaluation coefficient according to the difference of the correlation indexes; obtaining a difference index of the maximum dependent element, obtaining a second evaluation coefficient according to the distribution difference of the dependent elements, and calculating a third evaluation coefficient according to the difference of each dependent element in the highest gray level; and obtaining uniformity evaluation according to the first, second and third evaluation coefficients, and obtaining product quality evaluation of the polyphenyl particles according to uniformity evaluation indexes of the polyphenyl particles.
The invention can accurately and efficiently detect the quality of the polyphenyl granule product. Meanwhile, when a gray level dependence matrix is constructed, self-adaptive gray level dependence distance is obtained according to the gray level characteristics of the polyphenyl particles in the image, and the quality detection can be well carried out on the polyphenyl particles with different sizes. In the characteristic expression of the gray level dependence matrix, weighting processing is carried out according to each gray level and the correlation thereof, the characteristic difference of the image is expressed to the maximum extent, the uniformity degree of the size of the polyphenyl granules is expressed, and finally the quality of the polyphenyl granule product is judged.
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 embodiments or the description of 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 quality of a polyphenyl granule product based on computer vision technology.
Detailed Description
To further illustrate the technical means and effects of the present invention for achieving the predetermined objects, the following detailed description of the method for detecting the quality of a polyphenyl granule product based on computer vision technology, the specific implementation manner, structure, features and effects thereof according to the present invention are provided with the accompanying drawings and preferred embodiments. 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 quality detection method of polyphenyl particle products based on computer vision technology in detail with reference to the accompanying drawings.
Referring to fig. 1, a flow chart of a method for detecting the quality of a polyphenyl granule product based on computer vision technology according to an embodiment of the present invention is shown, wherein the method comprises the following steps:
acquiring a polyphenyl particle gray image, and dividing gray levels of gray values of all pixel points on the polyphenyl particle gray image; performing connected domain processing on the pixel points corresponding to the maximum gray level to obtain the maximum connected domain as the dependent distance of the pixel points, and calculating the gray level dependent matrix of the polyphenyl granule gray level image; all interdependent pixels of the same gray level are marked as a dependent element within a dependent distance.
First, the production of the polystyrene particles is performed by expansion-foaming using expandable polystyrene resin beads as a base material, and the quality of the polystyrene particles is determined by the foaming effect. The beads are expanded to form particles of a certain size, and uniformity in the size of the particles is required. The uniformity of the particle size affects the quality of the polyphenyl particle product, and the more uniform the particle size, the better the product quality. Therefore, the quality evaluation of the polyphenyl granule product is obtained by detecting the uniformity of the polyphenyl granules.
In the detection of the polyphenyl particles, the surface characteristics of the polyphenyl particles are mainly aimed at. A camera is arranged at a position corresponding to an outlet of the particle on the polyphenyl particle production line, and images of the stacked polyphenyl particles are shot. And the camera is adjusted to the appropriate angle so that only the polyphenyl particles are contained in the image.
And preprocessing the shot image to obtain a polyphenyl particle gray image. Specifically, graying is performed to obtain a grayscale image of the polyphenyl particles, so that subsequent analysis is facilitated. Meanwhile, in order to make the brightness of each region in the image uniform, the histogram of the image is equalized, and the accurate identification of the subsequent image characteristics is facilitated.
And then, carrying out gray level compression, and carrying out gray level division on gray values of all pixel points on the polyphenyl granule gray image. Specifically, the minimum value and the maximum value of the gray values of all pixel points on the polyphenyl particle gray image are obtained, and the gray interval between the minimum value and the maximum value is averagely divided into preset number of gray levels. In this embodiment, the value of the preset number is 10, that is, the gray scale interval
On average, into 10 gray levels, of which,
and
respectively representing the minimum and maximum values of the gray level.
And finally, acquiring pixel points corresponding to the maximum gray level, performing connected domain processing on adjacent pixel points in the pixel points, acquiring the maximum connected domain, setting the dependence distance to be the same as the maximum connected domain, and simultaneously setting the dependence threshold value between elements to be 0 to acquire a gray level dependence matrix. At the moment, all pixels in 8 neighborhoods of each pixel point in each dependency distance are judged, and if the gray levels of the pixels are the same as the gray levels of the pixel points, the pixels are considered as mutually dependent pixels. All interdependent pixel points of the same gray level are marked as a dependent element within a dependent distance, and the same gray level corresponds to a plurality of dependent elements on the polyphenyl particle gray level image.
The judgment of the dependency between the pixels is based on the distance between the pixels and the difference in gray level. In the present invention, the detection of the polyphenyl particles is mainly directed to the surface characteristics of the particles, and therefore, the selected dependent distance needs to reflect the characteristics of the surfaces of the polyphenyl particles.
In the gray scale image of the polyphenyl particles obtained in this embodiment, the polyphenyl particles are placed in a stack, so that a shielding condition may exist between the polyphenyl particles, and before the dependent distance is obtained, a complete polyphenyl particle needs to be identified. The surface of the polyphenyl particle is generally represented as a highlight part in an image, a pixel point with the maximum gray scale in the image is obtained, a plurality of pixel points are possibly obtained at the moment, the size of the maximum connected domain formed by the pixel points is used as the dependent distance, the maximum connected domain can be approximately used as a region formed by the polyphenyl particle, the maximum connected domain is selected as the dependent distance, and the surface characteristics of a single polyphenyl particle can be represented to the maximum degree.
Meanwhile, the polyphenyl particles are mutually shielded due to stacking, local gray level difference is formed in the image, a specific gray level dependency matrix is constructed on the basis, and subsequent analysis of the sizes of the polyphenyl particles is carried out according to the characteristic expression of the gray level dependency matrix.
Acquiring the dependent element with the largest number of mutually dependent pixel points in each gray level, marking the dependent element as the maximum dependent element, and calculating the correlation index of the maximum dependent element in each gray level according to the probability corresponding to the maximum dependent element in each gray level and the probabilities corresponding to other dependent elements; and calculating a first evaluation coefficient according to the second moment of the correlation index.
Specifically, for the gray levels corresponding to the pixel points on the polyphenyl particle gray level image, the dependent element with the largest number of mutually dependent pixel points in each gray level is obtained and recorded as the maximum dependent element, and the correlation between the maximum dependent element in each gray level and other dependent elements in the gray level is calculated, that is, the correlation index of the maximum dependent element in each gray level is calculated, and is expressed by a formula:
wherein the content of the first and second substances,
the index of the correlation of the largest dependent element when the gray level is i,
indicating the number of interdependent pixels contained by the largest dependent element,
representing the probability of the occurrence of the i-max dependent element in the gray level,
and expressing the probability of the occurrence of dependent elements with the number j of mutually dependent pixel points in the gray level i. The correlation index represents the correlation between the maximum dependent element and other dependent elements in the gray level i, and the larger the value, the higher the correlation between the maximum dependent element and other dependent elements.
In the gray-scale image of the polyphenyl particles, the surface display of some polyphenyl particles is incomplete due to the mutual shielding condition among the polyphenyl particles, and meanwhile, the brightness of the part of the surface area displayed in the gray-scale image of the polyphenyl particles with the shielding condition is changed. Generally, the more regions that are occluded, the lower the brightness of the regions displayed in the image. When the sizes of the stacked polyphenyl granules are consistent, it can be considered that the numbers of the pixel points which are dependent on each other and contained by all the dependent elements in each gray level are basically consistent or relatively close, that is, the shielding among the polyphenyl granules is considered to be uniform. Therefore, the correlation between the largest dependent element and the other dependent elements in each gray level should be relatively close.
Therefore, the size uniformity of the polyphenyl granules in the polyphenyl granule gray level image is judged according to the correlation index of the maximum dependent element in each gray level, and a first evaluation coefficient is calculated and expressed by a formula as follows:
wherein, DAMS represents a first evaluation coefficient,
representing the total number of gray levels in a gray-scale image of the polyphenyl particles,
and the correlation index of the maximum dependent element when the gray level is i is represented. The first evaluation coefficient represents a second moment of the correlation index of the largest dependent element in each gray level, and illustrates the difference of the correlation indexes of the largest dependent elements in different gray levels. Meanwhile, the second moment can represent the range of the data deviating from the mean value, and further can represent the fluctuation condition of the data. The smaller the value of the first evaluation coefficient is, the smaller the difference of the correlation indexes of the maximum dependent elements in different gray levels is, which indicates that the sizes of the polyphenyl particles are more similar and more uniform.
Calculating the difference index of the maximum dependent element in each gray level according to the difference value between the probability corresponding to the maximum dependent element in each gray level and the probabilities corresponding to other dependent elements; obtaining a second evaluation coefficient according to the ratio of the difference index to the correlation index; and calculating a third evaluation coefficient according to the difference of the number of pixel points contained in each dependent element in the highest gray level.
In particular, when the sizes of the polyphenyl particles are different, the polyphenyl particles show difference in grayscale images. That is, the sizes of the polyphenyl granules are different, so that the difference that the dependent elements in each gray level contain mutually dependent pixel points is increased, and the correlation index of the maximum dependent element in each gray level is changed. Because the polyphenyl granules are in a stacking state, the number of mutually dependent pixel points contained in the dependent elements corresponding to the surfaces of the polyphenyl granules which are not shielded on the uppermost layer is changed maximally, namely the change of the correlation index of the maximum dependent element is changed maximally. Meanwhile, the value of the correlation index of the maximum dependent element becomes small.
The polyphenyl granules under different shielding degrees are represented as the maximum dependent elements in each gray level, at the moment, the difference of the maximum dependent elements in each gray level is analyzed, namely the difference index of the maximum dependent elements in each gray level is calculated, and the formula is represented as follows:
wherein the content of the first and second substances,
the index of the difference of the maximum dependent elements when the gray level is i is represented,
indicating the number of interdependent pixels contained by the largest dependent element,
representing the probability of the occurrence of the i-max dependent element in the gray level,
and expressing the probability of the occurrence of dependent elements with the number j of mutually dependent pixel points in the gray level i. Difference index
Representing the difference between the largest dependent element and the other dependent elements in the gray level i, the larger the difference in size and number of dependent elements in the gray level, the more non-uniform the distribution of dependent elements in the gray level. The size of the dependent element indicates the number of mutually dependent pixels contained in the dependent element, and the number of the dependent element indicates the occurrence frequency of the dependent element.
In the polyphenyl particle gray level image, the larger the correlation index of the maximum dependent element of each gray level is, the smaller the dependent element correlation change of the gray level is. In order to express the difference of the dependent elements in each gray level to the maximum extent and express the uniformity of the regional distribution of the polyphenyl particles in the polyphenyl particle gray level image, the correlation index of the maximum dependent element in each gray level is taken as a weight, the difference index of the maximum dependent element in all the gray levels is analyzed, the difference of the regional distribution of the polyphenyl particles in the whole image is expressed, namely, a second evaluation coefficient is calculated, and the second evaluation coefficient is expressed by a formula:
wherein MON is a second evaluation coefficient,
representing the total number of gray levels in a gray-scale image of the polyphenyl particles,
the index of the correlation of the largest dependent element when the gray level is i,
and expressing the difference index of the maximum dependent element when the gray level is i. The second evaluation coefficient represents the distribution difference of the polyphenyl particle areas in the polyphenyl particle gray level image, and the larger the value is, the more uneven the distribution of the polyphenyl particles is.
It should be noted that, for the gray-scale image of the polyphenyl particles, the areas that show the most are the surface areas of the unmasked polyphenyl particles at the uppermost layer among the stacked polyphenyl particles, and the gray-scale level of the surface area of the unmasked polyphenyl particles at the uppermost layer is the highest. Therefore, for the representation of the surface features of the polyphenyl particles, the higher the gray level is, the more complete the polyphenyl particles can be represented, and the more accurate the representation of the gray features of the surfaces of the polyphenyl particles can be. In the image with uniform polyphenyl particle size, the dependency elements corresponding to the gray levels represented by the intact polyphenyl particles which are positioned at the uppermost layer and are not shielded are approximately equal, and the difference of the maximum dependency elements in the highest gray level can reflect the relevant characteristics of the intact polyphenyl particles which are not shielded. The dependency elements are approximately equal, and the number of the mutually dependent pixels contained in the dependency elements is approximately equal to the occurrence frequency of the dependency elements.
Calculating a third evaluation coefficient, formulated as:
wherein DEM is a third evaluation coefficient,
representing the number of dependent elements in the highest gray level,
indicating that the tth dependent element contains the number of interdependent pixels,
and the t-1 th dependent element is represented to contain the number of mutually dependent pixel points.
For the highest gray level in the gray scale image of polyphenyl particles is
Wherein all dependent elements are represented as
In the gray-level dependency matrix, the corresponding probability is
The third evaluation coefficient represents the element-dependent difference in the highest gray level. In the calculation of the third evaluation coefficient, the difference is weighted by the number of the mutually dependent pixel points contained in the dependent element, and the more the number of the mutually dependent pixel points contained in the dependent element is, the more the difference is amplified, and the characteristics of the polyphenyl granules are more represented. The larger the value of the third evaluation coefficient is, the larger the difference of the surfaces of the unmasked polyphenyl particles at the uppermost layer is, and the polyphenyl particles areThe larger the difference in size of the particles.
Step four, obtaining uniformity evaluation according to the first evaluation coefficient, the second evaluation coefficient and the third evaluation coefficient, and obtaining quality evaluation of the polyphenyl granule product according to the uniformity evaluation index; and when the quality evaluation of the polyphenyl particle product is greater than the evaluation threshold value, the polyphenyl particle product has good quality.
Specifically, for the correlation indexes obtained by the gray level image of the polyphenyl particles, the first evaluation coefficient represents the difference of the correlation indexes of the maximum dependent elements in different gray levels, the difference of the surface areas of the polyphenyl particles is reflected, and the larger the value of the first evaluation coefficient is, the lower the uniformity degree of the sizes of the polyphenyl particles is. The second evaluation coefficient takes the correlation of the maximum dependent elements in each gray level as a weight, the distribution difference of the dependent elements is represented to the maximum extent, and the larger the value of the second evaluation coefficient is, the lower the uniformity degree of the size of the polyphenyl particles is. The difference of the dependent elements in the highest gray level of the third evaluation coefficient reflects the difference of the particle surfaces of the uppermost layer in the stacked polyphenyl particles, namely the difference of the sizes of the polyphenyl particles, and the larger the value of the difference is, the larger the difference of the sizes of the polyphenyl particles is, and the lower the uniformity degree of the particles is.
Therefore, the size uniformity of the polyphenyl granules is judged according to the first evaluation coefficient, the second evaluation coefficient and the third evaluation coefficient, the uniformity index is calculated, and the uniformity index is expressed by a formula as follows:
wherein AVE is a uniformity index, DAMS is a first evaluation coefficient, MON is a second evaluation coefficient, DEM is a third evaluation coefficient, and e is a natural constant.
It should be noted that, in the production of polystyrene particles, expandable polystyrene resin beads are used as a base material to be expanded and expanded, because there are various factors affecting the expansion effect during the expansion process, and the particle sizes may be different. The polyphenyl particles are used as heat insulation materials and generally only used as heat insulation boards or heat insulation slurry in the using process, and the size of the particles influences the manufacturing of the heat insulation boards or the uniformity of the heat insulation slurry in the using process. The size uniformity of the polyphenyl particles affects the quality of the polyphenyl particle product.
The quality of the polyphenyl particle product is expressed according to the uniformity index of the polyphenyl particle size, the quality evaluation of the polyphenyl particle product is calculated, and the formula is expressed as follows:
wherein LEV is the quality evaluation of the polyphenyl particle product, and AVE is the uniformity index and represents the uniformity of the polyphenyl particle size. The larger the value of the uniformity index is, the larger the quality evaluation of the polyphenyl particle product is, and the better the quality of the polyphenyl particle product is. And setting an evaluation threshold, wherein when the quality evaluation of the polyphenyl particle product is greater than the evaluation threshold, the polyphenyl particle product has good quality. The value implementer of the evaluation threshold value can set according to the actual situation.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (9)
1. A quality detection method of a polyphenyl granule product based on a computer vision technology is characterized by comprising the following steps:
obtaining a polyphenyl particle gray image, and dividing gray levels of gray values of all pixel points on the polyphenyl particle gray image; performing connected domain processing on the pixel points corresponding to the maximum gray level to obtain the maximum connected domain as the dependent distance of the pixel points to calculate the gray level dependent matrix of the polyphenyl granule gray level image; all interdependent pixel points of the same gray level are marked as a dependent element within a dependent distance;
acquiring the dependent element with the largest number of mutually dependent pixel points in each gray level, recording the dependent element as the maximum dependent element, and calculating the correlation index of the maximum dependent element in each gray level according to the probability corresponding to the maximum dependent element in each gray level and the probabilities corresponding to other dependent elements; calculating a first evaluation coefficient according to the second moment of the correlation index;
calculating the difference index of the maximum dependent element in each gray level according to the difference value between the probability corresponding to the maximum dependent element in each gray level and the probabilities corresponding to other dependent elements; obtaining a second evaluation coefficient according to the ratio of the difference index to the correlation index; calculating a third evaluation coefficient according to the difference of the number of pixel points contained in each dependent element in the highest gray level;
obtaining uniformity evaluation according to the first evaluation coefficient, the second evaluation coefficient and the third evaluation coefficient, and obtaining quality evaluation of the polyphenyl granule product according to the uniformity evaluation index; and when the quality evaluation of the polyphenyl particle product is greater than the evaluation threshold value, the polyphenyl particle product has good quality.
2. The method for detecting the quality of the polyphenyl granule product based on the computer vision technology as claimed in claim 1, wherein the dividing of the gray level of all the pixel points on the gray level image of the polyphenyl granule is specifically as follows: the method comprises the steps of obtaining the minimum value and the maximum value of gray values of all pixel points on a polyphenyl particle gray image, and averagely dividing a gray interval between the minimum value and the maximum value into preset number of gray levels.
3. The method for detecting the quality of the polyphenyl particle product based on the computer vision technology as claimed in claim 1, wherein the step of calculating the gray level dependence matrix of the gray level image of the polyphenyl particle is specifically as follows: and setting the dependence distance to be the same as the maximum connected domain size, setting the dependence threshold value between elements to be 0, and acquiring a gray level dependence matrix.
4. The method for detecting the quality of the polyphenyl granule product based on the computer vision technology as claimed in claim 1, wherein the correlation index is obtained by:
wherein the content of the first and second substances,
the index of the correlation of the largest dependent element when the gray level is i,
indicating the number of interdependent pixels contained by the largest dependent element,
representing the probability of the occurrence of the i-max dependent element in the gray level,
and representing the probability of the occurrence of the dependent elements with the number j of the mutually dependent pixel points in the gray level i.
5. The method for detecting the quality of the polyphenyl granule product based on the computer vision technology as claimed in claim 1, wherein the method for obtaining the first evaluation coefficient specifically comprises:
wherein, DAMS represents a first evaluation coefficient,
representing the total number of gray levels in a gray-scale image of the polyphenyl particles,
and the correlation index of the maximum dependent element when the gray level is i is represented.
6. The method for detecting the quality of a polyphenyl granule product based on computer vision technology according to claim 1, wherein the difference index is obtained by:
wherein, the first and the second end of the pipe are connected with each other,
the index of the difference of the maximum dependent elements when the gray level is i is represented,
indicating the number of interdependent pixels contained by the largest dependent element,
representing the probability of the occurrence of the i-max dependent element in the gray level,
and representing the probability of the occurrence of the dependent elements with the number j of the mutually dependent pixel points in the gray level i.
7. The method for detecting the quality of the polyphenyl granule product based on the computer vision technology as claimed in claim 1, wherein the second evaluation coefficient is obtained by:
wherein MON is a second evaluation coefficient,
representing the total number of gray levels in a gray-scale image of the polyphenyl particles,
the index of the correlation of the largest dependent element when the gray level is i,
and expressing the difference index of the maximum dependent element when the gray level is i.
8. The method for detecting the quality of the polyphenyl granule product based on the computer vision technology as claimed in claim 1, wherein the third evaluation coefficient is obtained by:
wherein DEM is a third evaluation coefficient,
representing the number of dependent elements in the highest gray level,
indicating that the tth dependent element contains the number of interdependent pixels,
and the t-1 th dependent element is represented to contain the number of mutually dependent pixel points.
9. The quality inspection method for polyphenyl granule products based on computer vision technology as claimed in claim 1, wherein the first evaluation coefficient, the second evaluation coefficient and the third evaluation coefficient are in negative correlation with uniformity evaluation; the uniformity evaluation is in a positive correlation with the quality evaluation of the polyphenyl granules.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211140450.1A CN115222761A (en) | 2022-09-20 | 2022-09-20 | Polyphenyl particle product quality detection method based on computer vision technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211140450.1A CN115222761A (en) | 2022-09-20 | 2022-09-20 | Polyphenyl particle product quality detection method based on computer vision technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115222761A true CN115222761A (en) | 2022-10-21 |
Family
ID=83616903
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211140450.1A Pending CN115222761A (en) | 2022-09-20 | 2022-09-20 | Polyphenyl particle product quality detection method based on computer vision technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115222761A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115345565A (en) * | 2022-10-19 | 2022-11-15 | 南通金百吉五金制造有限公司 | Data processing-based scrap steel crushing stock yard inventory method and device |
| CN117115172A (en) * | 2023-10-25 | 2023-11-24 | 山东鲁润阿胶药业有限公司 | Donkey-hide gelatin quality detection method and system based on machine vision |
-
2022
- 2022-09-20 CN CN202211140450.1A patent/CN115222761A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115345565A (en) * | 2022-10-19 | 2022-11-15 | 南通金百吉五金制造有限公司 | Data processing-based scrap steel crushing stock yard inventory method and device |
| CN117115172A (en) * | 2023-10-25 | 2023-11-24 | 山东鲁润阿胶药业有限公司 | Donkey-hide gelatin quality detection method and system based on machine vision |
| CN117115172B (en) * | 2023-10-25 | 2024-01-12 | 山东鲁润阿胶药业有限公司 | Donkey-hide gelatin quality detection method and system based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115222761A (en) | Polyphenyl particle product quality detection method based on computer vision technology | |
| CN113689428B (en) | Mechanical part stress corrosion detection method and system based on image processing | |
| CN115082467B (en) | Building material welding surface defect detection method based on computer vision | |
| CN115311270A (en) | Plastic product surface defect detection method | |
| CN115311292A (en) | Strip steel surface defect detection method and system based on image processing | |
| CN111612784A (en) | Steel plate surface defect detection method based on classification-first YOLO network | |
| CN110837802A (en) | Facial image feature extraction method based on gray level co-occurrence matrix | |
| CN116030052B (en) | Etching quality detection method for lamination process of computer display panel | |
| CN109726649B (en) | Remote sensing image cloud detection method and system and electronic equipment | |
| CN115035114B (en) | Hay crusher state monitoring method based on image processing | |
| CN110189297B (en) | Magnetic material appearance defect detection method based on gray level co-occurrence matrix | |
| CN116363127B (en) | Image processing-based quality detection method for fully-degradable plastic product | |
| CN116091455A (en) | Steel mesh surface defect judging method based on machine vision | |
| CN112258470B (en) | Intelligent industrial image critical compression rate analysis system and method based on defect detection | |
| CN116246174B (en) | Sweet potato variety identification method based on image processing | |
| CN115082477B (en) | Semiconductor wafer processing quality detection method based on light reflection removing effect | |
| CN116542972A (en) | Wall plate surface defect rapid detection method based on artificial intelligence | |
| CN110490061B (en) | Uncertainty modeling and measuring method for remote sensing image characteristics | |
| CN117474891A (en) | Gear heat treatment defect detection method | |
| CN115222735B (en) | Metal mold quality detection method based on pockmark defects | |
| CN101710989B (en) | Method for identifying JPEG compressed digital picture | |
| CN115880181A (en) | Method, device and terminal for enhancing image contrast | |
| CN114972261A (en) | Method for identifying surface quality defects of plate strip steel | |
| CN113870341A (en) | Blast furnace sintering ore particle size detection method and system based on RGB and laser feature fusion | |
| CN116740056B (en) | Defect detection method for coating layer of whole-core high-pattern conveyer belt |
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 |