A corrugated paper quality detection method, medium and device based on indentation

Abstract

The present invention is a corrugated paper quality detection method based on indentation, comprising the following steps: obtaining images of the front and back sides of the corrugated paper to be tested, recorded as the first image and the second image, locating the indentation defect feature according to the first image and the second image; S200, after locating the indentation defect feature, moving the linear array CCD camera to the top of the indentation defect feature to be tested, collecting the indentation defect image, binarizing the indentation defect feature image, extracting the standard image centroid array, comparing the offset and deflection angle of the dot matrix and determining the concave and convex direction of the indentation defect feature; S300, establishing a three-dimensional model of the corrugated paper according to the concave and convex direction of the indentation defect feature and the structure of the corrugated paper, and performing finite element analysis to obtain its compressive strength. The present invention obtains a complete set of corrugated paper surface indentation quality detection methods by obtaining images of the front and back sides of the corrugated paper to be tested, locating the indentation defect feature, obtaining the indentation defect feature image and binarizing it to obtain the standard image centroid array.

Description

Technical Field

[0001] The invention relates to the technical field of corrugated paper quality detection, and in particular to a corrugated paper quality detection method, medium and equipment based on indentation. Background Art

[0002] Corrugated paper is a paperboard made by gluing noodle paper and corrugated paper formed by corrugating rollers. It has the advantages of low cost, light weight, and strong pressure resistance. It is widely used in various fields such as transportation packaging. In the manufacturing process of corrugated paperboard, it is inevitable that indentations will appear on the corrugated paperboard due to various reasons such as equipment failure and operational errors, which seriously affects the normal use of corrugated paperboard. Therefore, it is necessary to detect the indentation quality of corrugated paperboard. The current indentation quality detection method has the defects of being unable to accurately locate the indentation characteristics of the corrugated paperboard and being unable to accurately determine the concave and convex direction of the indentation characteristics. It cannot guide production well and eliminate the indentation quality problem in time, thus affecting the normal use and production efficiency of corrugated paperboard. Summary of the invention

[0003] The purpose of the present invention is to provide a corrugated paper quality detection method, medium and equipment based on indentation to solve the above technical problems.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A corrugated paper quality detection method based on indentation, characterized in that it comprises the following steps:

[0006] S100, obtaining images of the front and back sides of the corrugated paper to be tested, which are recorded as a first image and a second image respectively, and locating the indentation defect features according to the first image and the second image;

[0007] S200, after locating the indentation defect feature, move the linear array CCD camera to the top of the indentation defect feature to be measured, place a light source obliquely above the indentation defect feature to be measured, collect the indentation defect image, perform binarization on the indentation defect feature image, extract the standard image centroid array, compare the offset and deflection angle of the dot matrix, and determine the concave-convex direction of the indentation defect feature;

[0008] S300, establishing a three-dimensional model of the corrugated paper according to the concave-convex direction of the indentation defect characteristics and the structure of the corrugated paper, and performing finite element analysis to obtain its compressive strength, and determining whether the compressive strength is within the qualified range. If so, it is determined to be a qualified product.

[0009] The present invention is further configured that, in step S100, when locating the indentation defect feature, the following steps are included:

[0010] S101, graying the first image and the second image, obtaining the maximum area of ​​the gray area, counting the number of connected areas that are greater than 10% of the maximum area of ​​the gray area, collectively marking the connected areas, and calculating the gray value MAX of the maximum area;

[0011] S102, connect the grayscale area according to the characteristic difference of the indentation defect, and the connection method is: if the grayscale value of the connected area is greater than the maximum grayscale value MAX of the grayscale image, then retain the connected area; if the grayscale value of the connected area is less than the maximum grayscale value MAX of the grayscale image, then make the following judgment, calculate the distance {D1, D2, D3, D4, Dn-1} between the center of the connected area and the center of other connected areas, where n is the number of connected areas, if there is a value less than L / 3 in {D1, D2, D3, D4, Dn-1}, then retain the connected area, otherwise, remove the connected area, where L is the length of the area with the largest area of ​​the grayscale area;

[0012] S103, outputting a result graph, and determining the position of the indentation defect according to the number of connected regions retained on the result graph.

[0013] The present invention is further arranged that the shooting system in step S200 includes a linear array CCD camera, a light source, corrugated paper to be tested and a horizontal platform, the corrugated paper to be tested is placed on the horizontal platform, the linear array CCD camera is located above the indentation defect feature, wherein the focal length of the camera is f, the distance between the light spot of the camera and the horizontal platform is Z, and the incident angle of the light source is θ2.

[0014] The present invention further provides that when binarizing the indentation defect characteristic image, a Gaussian difference binarization method is adopted.

[0015] The present invention is further configured to obtain a standard image without indentation defect features, extract the standard image centroid array, scan the binary image of the indentation defect features in the area where the light spot is located, save the coordinates, and calculate the centroid coordinates, then the centroid coordinates are:

[0016] Xc=(x1+x2+x3+…x N ) / N

[0017] Yc=(y1+y2+y3+…y N ) / N;

[0018] Among them, x1, x2, x N are the abscissas of the first, second to Nth spot mass centers projected by the light source onto the characteristic surface of the indentation defect; Xc is the abscissa of the mass center of the binary image; y1, y2, y NThey are the ordinates of the centroids of the first, second to Nth light spots projected by the light source onto the characteristic surface of the indentation defect; Yc is the ordinate of the centroid of the binary image;

[0019] After extracting the centroid, the offset and deflection angle of each point of the indentation defect to be measured relative to the standard value of the standard image are calculated according to the standard image. The offset distance between the measured point and the standard point of the standard image is calculated using the Euclidean distance, and the formula is as follows:

[0020] ;

[0021] ;

[0022] Among them, x 11 、x 21 、x i1 are the centroid abscissas of the first, second to nth measured points respectively; x 12 、x 22 、x i2 are the horizontal coordinates of the center of mass of the first, second, and nth standard ideal points respectively; D X is the Euclidean distance between the ideal value of the horizontal axis and the measured value; 11 ,y 21 ,y i1 are the centroid ordinates of the first, second to nth measured points respectively; y 12 ,y 22 ,y i2 are the centroid ordinates of the first, second to nth standard ideal points respectively; D y is the Euclidean distance between the ideal value of the ordinate and the offset of the measured value; the angle between the straight line passing through the ideal point and the offset point and the x-axis is the deflection angle, then the deflection angle θ=arctan (D y / D X ).

[0023] The present invention is further arranged that, during the finite element analysis in step S300, a three-dimensional model of the corrugated paper is established, and corresponding indentation features are drawn at corresponding positions of the three-dimensional model according to the area and shape of the indentation, pressure is applied to the three-dimensional model, and the deformation of the model under different pressure states is analyzed, and when the corrugated paper is crushed, the compressive strength value is obtained.

[0024] The present invention is further configured to include a method for processing unqualified products. If the compressive strength is not within the qualified range, it is determined to be an unqualified product. At this time, the unqualified product is judged as follows: the difference between the unqualified product and the lower limit of the qualified range is judged. If the difference does not exceed 5%, it is repaired; otherwise, it is discarded.

[0025] The present invention also provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the indentation-based corrugated paper quality detection method.

[0026] The present invention also provides a readable storage medium on which a program is stored. When the program is executed by a processor, the indentation-based corrugated paper quality detection method is implemented.

[0027] Beneficial effects of the present invention: The present invention obtains images of the front and back sides of the corrugated paper to be tested, locates the indentation defect features, obtains the indentation defect feature images, and performs binarization processing on them to obtain a standard image centroid array. At the same time, the centroid coordinates are measured, the centroid coordinate offset and deflection angle are calculated, and the concave and convex direction of the defect feature is determined. Then, the compressive strength is obtained through finite element analysis to determine whether the compressive strength is within the qualified range. If it is within the qualified range, it is determined to be a qualified product, thereby realizing rapid detection of corrugated paper, and obtaining a complete set of corrugated paper surface indentation quality detection methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0029] Figure 1 This is a schematic diagram of the process of Example 1 of the present invention.

[0030] Figure 2 Schematic diagram of a shooting system according to Embodiment 1 of the present invention.

[0031] Figure 3 Schematic diagram of light path analysis of light source in Example 1 of the present invention. DETAILED DESCRIPTION

[0032] The following will describe the implementation methods of the present application in detail with the help of accompanying drawings and examples, so that the implementation process of how the present application uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly. Embodiment 1:

[0033] like Figure 1 As shown, this embodiment provides a corrugated paper quality detection method based on indentation, comprising the following steps:

[0034] S100, obtaining images of the front and back sides of the corrugated paper to be tested, which are recorded as a first image and a second image respectively, and locating the indentation defect features according to the first image and the second image;

[0035] S200, after locating the indentation defect feature, move the linear array CCD camera to the top of the indentation defect feature to be measured, place a light source obliquely above the indentation defect feature to be measured, collect the indentation defect image, perform binarization on the indentation defect feature image, extract the standard image centroid array, compare the offset and deflection angle of the dot matrix, and determine the concave-convex direction of the indentation defect feature. The concave-convex direction here is that since the corrugated paper is composed of an upper paperboard, a corrugated part, and a lower paperboard, that is, when a concave indentation appears on the upper paperboard, a convex part may appear on the lower paperboard, so determining it can be more accurate when establishing a three-dimensional model of the corrugated paper, so as to improve the accuracy of subsequent finite element analysis;

[0036] S300, establish a three-dimensional model of the corrugated paper according to the concave-convex direction of the indentation defect characteristics and the structure of the corrugated paper, and perform finite element analysis to obtain its compressive strength, and determine whether the compressive strength is within the qualified range. If it is within the qualified range, it is determined to be a qualified product. It also includes a method for handling unqualified products. If the compressive strength is not within the qualified range, it is determined to be an unqualified product. At this time, the unqualified product is judged as follows: the difference between the unqualified product and the lower limit of the qualified range is judged. If the difference does not exceed 5%, it is repaired; otherwise, it is rejected.

[0037] In step S100 of this embodiment, when locating the indentation defect feature, the following steps are included:

[0038] S101, graying the first image and the second image, obtaining the maximum area of ​​the gray area, counting the number of connected areas that are greater than 10% of the maximum area of ​​the gray area, collectively marking the connected areas, and calculating the gray value MAX of the maximum area;

[0039] S102, connect the grayscale area according to the characteristic difference of the indentation defect, and the connection method is: if the grayscale value of the connected area is greater than the maximum grayscale value MAX of the grayscale image, then retain the area; if the grayscale value of the connected area is less than the maximum grayscale value MAX of the grayscale image, then make the following judgment, calculate the distance {D1, D2, D3, D4, Dn-1} between the center of the connected area and the center of other connected areas, where n is the number of connected areas, if there is a value less than L / 3 in {D1, D2, D3, D4, Dn-1}, then retain the connected area, otherwise, remove the connected area, where L is the length of the area with the largest area of ​​the grayscale area;

[0040] S103, outputting a result graph, and determining the position of the indentation defect according to the number of connected regions retained on the result graph.

[0041] In this embodiment, the shooting system in step S200 is as follows Figure 2As shown, it includes a linear array CCD camera, a light source, a corrugated paper to be tested, and a horizontal platform. The corrugated paper to be tested is placed on the horizontal platform, and the linear array CCD camera is located above the indentation defect feature, wherein the focal length of the camera is f, the distance between the camera's light spot and the horizontal platform is Z, the incident angle of the light source is θ2, and the projection direction is perpendicular to the plane BC, PQ is the physical length of the indentation defect feature, h is the protrusion height of the indentation defect feature, θ1 is the angle between the reflected light and the horizontal platform surface, then h=(1 / tanθ1+1 / tanθ2) ·(∆x·Z·L) / f, where ∆x is the pixel displacement offset between the measured image and the calibration image, and L is the physical distance value represented by the unit pixel obtained by the linear array CCD camera calibration. The process of obtaining h=(1 / tanθ1+1 / tanθ2) ·(∆x·Z·L) / f is as follows:

[0042] Based on the similarity of triangles, we can conclude that PQ / AB=f / Z;

[0043] AB = (∆x·Z·L) / f;

[0044] Among them, θ2=(π / 2)-arctan(PQ / f); In addition, according to the trigonometric relationship, PQ=h / tanθ1+ h / tanθ2;

[0045] Then h=(1 / tanθ1+1 / tanθ2) ·(Δx·Z·L) / f;

[0046] This embodiment uses a Gaussian difference binarization method when binarizing the indentation defect feature image.

[0047] The light path analysis of the light source is as follows: Figure 3 As shown in the figure A and B Represent the positions of the structured light source and the camera respectively, M is the location of the indentation being measured, and the three are located at the three vertices of the triangle. M Corrugated paper showing a standard image, when the light source is located at A , the camera is located B When the light source is reflected at P When an indentation occurs, the light source A The reflection point of the irradiation is located at P 1. P P1 is the displacement distance of the image point caused by the indentation. Change the position of the light source and the camera to A 1 and B 2. At this time, the light source A 1 in M The reflection point on Q ,exist M The reflection point on 1 isQ 1. Q Q1 is the image point displacement distance caused by indentation after reducing the light source and shortening the camera distance. It can be clearly seen that P P1 > Q Q1 Therefore, the greater the distance between the light source and the camera, the more obvious the image difference is, and the more it can reflect the characteristics of the indentation.

[0048] This embodiment also includes obtaining a standard image without indentation defect features, extracting the standard image centroid array, scanning the binary image of the indentation defect feature in the area where the light spot is located, saving the coordinates, and calculating the centroid coordinates. The centroid coordinates are:

[0049] Xc=(x1+x2+x3+…x N ) / N

[0050] Yc=(y1+y2+y3+…y N ) / N;

[0051] Among them, x1, x2, x N are the abscissas of the first, second to Nth spot mass centers projected by the light source onto the characteristic surface of the indentation defect; Xc is the abscissa of the mass center of the binary image; y1, y2, y N They are the ordinates of the centroids of the first, second to Nth light spots projected by the light source onto the characteristic surface of the indentation defect; Yc is the ordinate of the centroid of the binary image;

[0052] After extracting the centroid, the offset and deflection angle of each point of the indentation defect to be measured relative to the standard value of the standard image are calculated according to the standard image. The offset distance between the measured point and the standard point of the standard image is calculated using the Euclidean distance, and the formula is as follows:

[0053] ;

[0054] ;

[0055] Among them, x 11 、x 21 、x i1 are the centroid abscissas of the first, second to nth measured points respectively; x 12 、x 22 、x i2 are the horizontal coordinates of the center of mass of the first, second, and nth standard ideal points respectively; D X is the Euclidean distance between the ideal value of the horizontal axis and the measured value; 11 ,y 21 ,y i1are the centroid ordinates of the first, second to nth measured points respectively; y 12 ,y 22 ,y i2 are the centroid ordinates of the first, second to nth standard ideal points respectively; D y is the Euclidean distance between the ideal value of the ordinate and the offset of the measured value; the angle between the straight line passing through the ideal point and the offset point and the x-axis is the deflection angle, then the deflection angle θ=arctan (D y / D X ), and judge the specific concave and convex directions of the upper and lower layers of corrugated paper according to the deflection angle.

[0056] In the finite element analysis in step S300 of this embodiment, a three-dimensional model of the corrugated paper is established, and corresponding indentation features are drawn at corresponding positions of the three-dimensional model according to the area and shape of the indentation, and pressure is applied to the three-dimensional model to analyze the deformation of the model under different pressure states. When the corrugated paper is crushed, the compressive strength value is obtained. The indentation area is calculated by the area of ​​its fitted circle. Embodiment 2:

[0057] The present invention also provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the indentation-based corrugated paper quality detection method. Embodiment 3:

[0058] The present invention also provides a readable storage medium on which a program is stored. When the program is executed by a processor, the indentation-based corrugated paper quality detection method is implemented.

[0059] The present invention obtains images of the front and back sides of the corrugated paper to be tested, locates the indentation defect features, obtains the indentation defect feature images, and performs binarization processing on them to obtain the standard image centroid array. At the same time, the centroid coordinates are measured, the centroid coordinate offset and deflection angle are calculated, and the concave and convex direction of the defect feature is determined. Then, the compressive strength of the corrugated paper is analyzed by finite element analysis to screen out qualified products and unqualified products. A complete set of corrugated paper surface indentation quality detection methods is obtained.

[0060] For example, certain words are used in the specification and claims to refer to specific components. Those skilled in the art should understand that hardware manufacturers may use different terms to refer to the same component. This specification and claims do not use differences in names as a way to distinguish components, but use differences in the functions of components as the criteria for distinction. For example, "including" mentioned throughout the specification and claims is an open term, so it should be interpreted as "including but not limited to". "Approximately" means that within an acceptable error range, those skilled in the art can solve technical problems within a certain error range and basically achieve technical effects.

[0061] It should be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a product or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such product or system. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the product or system including the elements.

[0062] The above description shows and describes several preferred embodiments of the present invention, but as before, it should be understood that the present invention is not limited to the form disclosed herein, and should not be regarded as excluding other embodiments, but can be used in various other combinations, modifications and environments, and can be modified within the scope of the invention concept of this article through the above teachings or the technology or knowledge of the relevant field. And the changes and modifications made by those skilled in the art do not depart from the spirit and scope of the present invention, and should be within the scope of protection of the claims attached to the present invention.

Claims

1. A corrugated paper quality detection method based on indentation, characterized in that: The steps include: S100, obtaining images of the front and back sides of the corrugated paper to be tested, which are recorded as a first image and a second image respectively, and locating the indentation defect features according to the first image and the second image; S200, after locating the indentation defect feature, move the linear array CCD camera in the shooting system to the top of the indentation defect feature to be measured, place a light source obliquely above the indentation defect feature to be measured, collect the indentation defect image, perform binarization on the indentation defect feature image, extract the standard image centroid array, compare the offset and deflection angle of the dot matrix, and determine the concave-convex direction of the indentation defect feature; S300, establishing a three-dimensional model of the corrugated paper according to the concave-convex direction of the indentation defect characteristics and the structure of the corrugated paper, and performing finite element analysis to obtain its compressive strength, and determining whether the compressive strength is within the qualified range. If so, the corrugated paper is determined to be a qualified product; Wherein, in step S100, when locating the indentation defect feature, the following steps are included: S101, graying the first image and the second image, obtaining the maximum area of ​​the gray area, counting the number of connected areas that are greater than 10% of the maximum area of ​​the gray area, collectively marking the connected areas, and calculating the gray value MAX of the maximum area; S102, connect the grayscale area according to the characteristic difference of the indentation defect, and the connection method is: if the grayscale value of the connected area is greater than the maximum grayscale value MAX of the grayscale image, then retain the connected area; if the grayscale value of the connected area is less than the maximum grayscale value MAX of the grayscale image, then make the following judgment, calculate the distance {D1, D2, D3, D4, Dn-1} between the center of the connected area and the center of other connected areas, where n is the number of connected areas, if there is a value less than L / 3 in {D1, D2, D3, D4, Dn-1}, then retain the connected area, otherwise, remove the connected area, where L is the length of the area with the largest area of ​​the grayscale area; S103, outputting a result graph, and determining the position of the indentation defect according to the number of connected areas retained on the result graph; It also includes obtaining a standard image without indentation defect features and extracting the standard image centroid array. At the same time, the binary image of the indentation defect feature in the area where the spot is located is scanned and the coordinates are saved, and the centroid coordinates are calculated. The centroid coordinates are: Xc=(x1+x2+x3+…x N ) / N <h2 style=";text-align:left;direction:ltr">Yc=(y1+y2+y3+…y<h2 style=";text-align:left;direction:ltr"> N <h2 style=";text-align:left;direction:ltr"> ) / N; Among them, x1, x2, x N are the abscissas of the first, second to Nth spot mass centers projected by the light source onto the surface of the indentation defect feature; Xc is the abscissa of the mass center of the binary image; y1, y2, y N They are the ordinates of the centroids of the first, second to Nth light spots projected by the light source onto the characteristic surface of the indentation defect; Yc is the ordinate of the centroid of the binary image; After extracting the centroid, the offset and deflection angle of each point of the indentation defect to be measured relative to the standard value of the standard image are calculated according to the standard image. The offset distance between the measured point and the standard point of the standard image is calculated using the Euclidean distance, and the formula is as follows: ； ； Among them, x 11 、x 21 、x i1 are the centroid abscissas of the first, second to nth measured points respectively; x 12 、x 22 、x i2 are the centroid abscissas of the first, second, and nth standard ideal points respectively; Dx is the Euclidean distance between the ideal value of the abscissa and the measured value; y is the centroid abscissa of the first, second, and nth standard ideal points respectively; Dx is the Euclidean distance between the ideal value of the abscissa and the measured value; 11 ,y 21 ,y i1 are the centroid ordinates of the first, second to nth measured points respectively; y 12 ,y 22 ,y i2 are the centroid ordinates of the first, second to nth standard ideal points respectively; Dy is the Euclidean distance between the ideal value of the ordinate and the offset of the measured value; the angle between the straight line passing through the ideal point and the offset point and the x-axis is the deflection angle, then the deflection angle θ=arctan(Dy / Dx).

2. The method for detecting corrugated paper quality based on indentation according to claim 1, characterized in that: The shooting system in step S200 includes a linear array CCD camera, a light source, corrugated paper to be tested and a horizontal platform. The corrugated paper to be tested is placed on the horizontal platform, and the linear array CCD camera is located above the indentation defect feature, wherein the focal length of the camera is f, the distance between the light spot of the camera and the horizontal platform is Z, and the incident angle of the light source is θ2.

3. The method for detecting corrugated paper quality based on indentation according to claim 2, characterized in that: When binarizing the indentation defect feature image, the Gaussian difference binarization method is used.

4. The method for detecting corrugated paper quality based on indentation according to claim 1, characterized in that: During the finite element analysis in step S300, a three-dimensional model of the corrugated paper is established, and corresponding indentation features are drawn at corresponding positions of the three-dimensional model according to the area and shape of the indentation. Pressure is applied to the three-dimensional model, and the deformation of the model under different pressure states is analyzed. When the corrugated paper is crushed, the compressive strength value is obtained.

5. The method for detecting corrugated paper quality based on indentation according to claim 4, characterized in that: It also includes a method for handling unqualified products. If the compressive strength is not within the qualified range, it is judged as an unqualified product. At this time, the unqualified product is judged as follows: the difference between the unqualified product and the lower limit of the qualified range is judged. If the difference does not exceed 5%, it is repaired; otherwise, it is discarded.

6. An electronic device, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the indentation-based corrugated paper quality detection method according to any one of claims 1 to 5.

7. A readable storage medium, characterized in that: A program is stored thereon, and when the program is executed by a processor, the indentation-based corrugated paper quality detection method described in any one of claims 1 to 5 is implemented.

Images