A testing method for the flatness of a waterproof fabric

Abstract

The present invention relates to the technical field of image processing, and particularly relates to a method for testing the flatness of a waterproof fabric, which includes: obtaining a grayscale image of the waterproof fabric; dividing the grayscale image into several regions, and obtaining the regularity degree of the texture in the region according to the distribution of the edge pixel points in the region; further obtaining the flatness factor of each region according to the regularity degree of the texture in each region; obtaining the flatness degree of each region according to the gradient direction of the edge pixel points in the region and the flatness factor of the region; screening out flat regions and wrinkled regions according to the flatness degree of the regions; and obtaining the flatness of the waterproof fabric according to the number of flat regions and the flatness degree of the wrinkled regions. By analyzing the texture features in each region, the present invention can accurately distinguish between wrinkled regions and texture abnormal regions caused by mechanical errors, avoid the interference of texture abnormal regions, and thus accurately obtain the flatness of the waterproof fabric.

Description

Technical Field

[0001] The present invention relates to the technical field of fabric flatness detection, and particularly relates to a method for testing the flatness of waterproof fabric. Background Art

[0002] In the process of producing waterproof fabric, in order to ensure the waterproof performance of the waterproof fabric, it is necessary to ensure that the fabric is flat enough so that the waterproof coating can be distributed more evenly on the waterproof fabric. When there are wrinkles in the fabric, the folded fabric in the wrinkles cannot be coated with the waterproof coating, resulting in a reduction in the waterproof performance of the waterproof fabric. Therefore, it is necessary to detect the flatness of the fabric; however, due to the influence of mechanical errors in the process of producing the fabric, there may be areas with abnormal textures in a local range of the fabric, and the areas with abnormal textures will interfere with the detection of wrinkles; that is, simply using computer vision to distinguish between different regions of the fabric cannot accurately obtain the flatness of the waterproof fabric. Summary of the Invention

[0003] The present invention provides a method for testing the flatness of waterproof fabric to solve the existing problem: simply using computer vision to distinguish between different regions of the fabric cannot accurately obtain the flatness of the waterproof fabric.

[0004] A method for testing the flatness of waterproof fabric according to the present invention adopts the following technical solutions:

[0005] Including the following steps:

[0006] Obtain the grayscale image of the waterproof fabric;

[0007] Divide the grayscale image into several regions and obtain the edge pixels in each region; according to the distribution of the edge pixels in the region, obtain the regularity degree of the texture in the region;

[0008] Select the reference region according to the regularity degree of the texture in the region; according to the difference in edge pixels between each region and the reference region, combined with the regularity degree of the texture in each region, obtain the flatness factor of each region; according to the gradient direction of all edge pixels in the grayscale image, select the reference gradient direction; according to the difference in the gradient direction of the edge pixels with different gradient directions from the reference gradient direction in each region, combined with the flatness factor of each region, obtain the flatness degree of each region; select the flat regions and the wrinkled regions according to the flatness degree of the regions;

[0009] Obtain the flatness of the waterproof fabric according to the number of flat regions and the flatness degree of the wrinkled regions.

[0010] Preferably, the method of dividing the grayscale image into several regions and obtaining the edge pixels in each region specifically includes:

[0011] Preset a regional range of a×b, and divide the grayscale image into several regions of the specification a×b; a and b are the length and width of the preset regional range; use the sobel edge detection operator to obtain the edge pixel points in all regions.

[0012] Preferably, the specific method for obtaining the regularity degree of the texture in the region includes:

[0013] For any region, record the sequence composed of the pixel points in each row of the region as the sequence of pixel points in each row, obtain the number of edge pixel points in all the sequences of pixel points in each row of the region, and the distance between adjacent edge pixel points in all the sequences of pixel points in each row; record the average value of the distances between adjacent edge pixel points in all the sequences of pixel points in each row as the reference distance of the region; obtain the regularity degree of the texture in the region according to the difference between the distances between adjacent edge pixel points in all the sequences of pixel points in each row and the reference distance of the region, and the variance of the number of edge pixel points in all the sequences of pixel points in each row.

[0014] The regularity degree of the texture in the region is negatively correlated with the difference between the distances between adjacent edge pixel points in all the sequences of pixel points in each row and the reference distance of the region, and the variance of the number of edge pixel points in all the sequences of pixel points in each row.

[0015] Preferably, the specific method for screening out the reference region according to the regularity degree of the texture in the region includes:

[0016] Preset a regularity degree threshold, and record the region with the regularity degree of the texture in the region greater than the regularity degree threshold as the reference region.

[0017] Preferably, the specific method for obtaining the flatness factor of each region includes:

[0018] Obtain the average value of the gray level quantity and the average value of the gradient value of all the edge pixel points in all the reference regions, and record them as the reference gray level quantity and the reference gradient value respectively; obtain the flatness factor of each region according to the differences between the gray level quantity and the gradient average value of all the edge pixel points in each region and the reference gray level quantity and the reference gradient value respectively, and the regularity degree of the texture in each region.

[0019] The flatness factor of each region is negatively correlated with the differences between the gray level quantity and the gradient average value of all the edge pixel points in each region and the reference gray level quantity and the reference gradient value respectively; the flatness factor of each region is positively correlated with the regularity degree of the texture in each region.

[0020] Preferably, the specific method for screening out the reference gradient direction according to the gradient direction of all the edge pixel points in the grayscale image includes:

[0021] The gradient direction with the highest frequency of occurrence among the gradient directions of all edge pixels in the grayscale image is denoted as the reference gradient direction.

[0022] Preferably, the specific method for obtaining the flatness of each region includes:

[0023] For any region, the pixels whose gradient directions are different from the reference gradient direction in this region are denoted as abnormal pixels. The region formed by adjacent abnormal pixels in this region is denoted as an abnormal sub-region, and the largest abnormal sub-region is denoted as the characteristic abnormal sub-region. According to the difference between the gradient direction of each abnormal pixel and the reference gradient direction, the flatness factor of the region, and the number of pixels in the characteristic abnormal sub-region, the flatness of the region is obtained.

[0024] Preferably, the specific method for obtaining the flatness of the region includes:

[0025] The product of the sum of the differences between the gradient directions of each abnormal pixel and the reference gradient direction in any region and the number of pixels in the characteristic abnormal sub-region is denoted as the wrinkle factor of this region; the ratio of the flatness factor of this region to the wrinkle factor of this region is normalized to obtain the flatness of this region.

[0026] Preferably, the specific method for screening out flat regions and wrinkled regions according to the flatness of the region includes:

[0027] A flatness threshold is preset. For any region, if the flatness of the region is greater than the flatness threshold, the region is a flat region; if the flatness of the region is less than or equal to the flatness threshold, the region is a wrinkled region.

[0028] Preferably, the specific method for obtaining the flatness of the waterproof fabric according to the number of flat regions and the flatness of the wrinkled regions includes:

[0029] According to the proportion of flat regions in all regions in the grayscale image of the waterproof fabric, combined with the average flatness of all wrinkled regions, the flatness of the waterproof fabric is obtained;

[0030] The flatness of the waterproof fabric is positively correlated with the proportion of flat regions in all regions in the grayscale image of the waterproof fabric; the flatness of the waterproof fabric is negatively correlated with the average flatness of all wrinkled regions.

[0031] The beneficial effects of the technical solution of the present invention are as follows: The present invention divides a grayscale image into several regions and obtains the edge pixels in each region; according to the distribution of the edge pixels in the region, the regularity degree of the texture in the region is obtained. Since the texture generated by wrinkles in the waterproof fabric is not regular, the regularity degree of the texture in the region can be obtained through the distribution of the edge pixels in the region, and whether there are wrinkles in the region is initially quantified.

[0032] Reference regions are selected according to the regularity degree of the texture in the region, and the flatness factor of each region is obtained by combining the regularity degree of the texture in each region; since the texture generated by wrinkles in each region is the shadow edge generated by light, and the gray level and gradient value of its edge are greatly different from those of the normal texture, the flatness factor of each region can be obtained based on this. The larger the flatness factor, the smaller the possibility of wrinkles in the region; according to the gradient direction of the edge pixels in the region and the flatness factor of the region, the flatness degree of each region is obtained; since the gradient direction of the edge pixels of the wrinkles is greatly different from the gradient direction of the edge pixels of the texture in the image, the flatness factor of the region can be combined based on this to accurately quantify whether there are wrinkles in the region, and then the flat regions and the wrinkled regions are obtained; according to the number of flat regions and the flatness degree of the wrinkled regions, the flatness of the waterproof fabric is obtained, and the flatness of the waterproof fabric can be accurately obtained. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0034] Figure 1 It is a step flow chart of a method for testing the flatness of a waterproof fabric according to the present invention;

[0035] Figure 2 It is a flow chart for detecting the flatness of a waterproof fabric. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0036] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following, in combination with the drawings and preferred embodiments, details the specific implementation manners, structures, features and effects of a method for testing the flatness of a waterproof fabric according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0037] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs.

[0038] The following specifically describes the specific solution of a method for testing the flatness of a waterproof fabric provided by the present invention in conjunction with the accompanying drawings.

[0039] Please refer to Figure 1 , which shows a flowchart of the steps of a method for testing the flatness of a waterproof fabric provided by an embodiment of the present invention. The method includes the following steps:

[0040] Step S001: Obtain a grayscale image of the waterproof fabric.

[0041] It should be noted that in the process of producing waterproof fabric, in order to ensure the waterproof performance of the waterproof fabric, it is necessary to ensure that the fabric is flat enough so that the waterproof coating can be more evenly distributed on the waterproof fabric; therefore, this embodiment proposes a method for testing the flatness of a waterproof fabric, and its specific application scenario is to detect the flatness of the waterproof fabric during the production process of the waterproof fabric. Therefore, it is first necessary to collect an image of the waterproof fabric.

[0042] Specifically, use an industrial high-definition camera to collect an image of the waterproof fabric and perform grayscale processing on the image of the waterproof fabric to obtain a grayscale image of the waterproof fabric.

[0043] Step S002: Divide the grayscale image into several regions and obtain the edge pixel points in each region; according to the distribution of the edge pixel points in the region, obtain the regularity degree of the texture in the region.

[0044] It should be noted that in this embodiment, the grayscale image of the waterproof fabric is decomposed into several regions, and the flatness of the waterproof fabric is obtained by analyzing the flatness of each region. Since the texture generated by wrinkles in the waterproof fabric is not regular, and since the edge pixel points can well represent the texture characteristics in the image, the regularity degree of the texture in the region can be obtained through the distribution of the edge pixel points in the region, and whether there are wrinkles in the region can be initially quantified.

[0045] Preferably, in an embodiment of the present invention, a region range of a×b is preset, and the grayscale image is divided into several regions with a specification of a×b; a and b are the length and width of the preset region range, and their specific sizes can be set according to the actual situation. This embodiment does not make a limitation. In this embodiment, a = 30 and b = 20 are described; use the sobel edge detection operator to obtain the edge pixel points in all regions; since the sobel edge detection operator is a well-known existing technology, it will not be elaborated in this embodiment.

[0046] Further, for any region, denote the sequence composed of pixel points in each row in this region as the pixel point sequence of each row, obtain the number of edge pixels in all pixel point sequences of each row in this region, and the distance between adjacent edge pixels in all pixel point sequences of each row; denote the average value of the distances between adjacent edge pixels in all pixel point sequences of each row as the reference distance of this region; according to the difference between the distances between adjacent edge pixels in all pixel point sequences of each row and the reference distance of the region, and the variance of the number of edge pixels in all pixel point sequences of each row, obtain the regularity degree of the texture in the region;

[0047] The regularity degree of the texture in the region is negatively correlated with the difference between the distances between adjacent edge pixels in all pixel point sequences of each row and the reference distance of the region, and the variance of the number of edge pixels in all pixel point sequences of each row. The specific calculation formula is as follows:

[0048]

[0049] In the formula, τ represents the regularity degree of the texture in the region; σ represents the variance of the number of edge pixels in all pixel point sequences of each row; N represents the number of pixel point sequences in the region; M i represents the number of edge pixels in the i-th pixel point sequence in the region; X i，j represents the index value of the j-th edge pixel in the i-th pixel point sequence in the region; X i，j-1 represents the index value of the (j - 1)-th edge pixel in the i-th pixel point sequence in the region; represents the reference distance of the region; || represents the absolute value function; norm{} represents the linear normalization function, and its normalization object is all regions

[0050] It should be noted that σ is the variance of the number of edge pixels in all pixel point sequences of each row in the region. The larger the value of σ, the greater the difference in the number of edge pixels among different pixel point sequences in the region, and the less regular the texture in the region; is the reference distance of the region, which represents the average value of the distances between adjacent edge pixels in all pixel point sequences of each row in the region; therefore represents the difference between the distance between adjacent edge pixels in each pixel point sequence in the region and the average value of the distances between adjacent edge pixels in all pixel point sequences of each row in the region. The greater the difference, the greater the distribution difference of the edge pixels in different pixel point sequences in the region, so the less regular the texture in the region; therefore, the smaller the value of σ and the more regular the texture in the region.

[0051] Thus, the regularity degree of the texture in each region is obtained.

[0052] Step S003: Screen out the reference area according to the regularity degree of the texture in the area; obtain the flattening factor of each area according to the difference of each area from the reference area in the edge pixels and the regularity degree of the texture in each area; screen out the reference gradient direction according to the gradient direction of all edge pixels in the grayscale image; obtain the flattening degree of each area according to the difference of the edge pixels with different gradient directions from the reference gradient direction in each area and the flattening factor of each area; screen out the flat areas and the wrinkled areas according to the flattening degree of the area.

[0053] It should be noted that the texture generated by wrinkles in each area is the shadow edge generated by light, and there are huge differences in the gray level and gradient value of its edge from those of the normal texture. Therefore, the flattening factor of each area can be obtained based on this; and in the process of obtaining the normal texture, in order to avoid the interference of the texture generated by wrinkles, it is also necessary to screen out the reference area according to the regularity degree of the texture in the area, and obtain the flattening factor of each area according to the difference of each area from the reference area in the edge pixels and the regularity degree of the texture in each area.

[0054] It should be further noted that since the wrinkles in the waterproof fabric are usually small-area wrinkles, that is, the proportion of the texture of the wrinkles in the grayscale image of the waterproof fabric is small, and since the texture generated by the wrinkles is the shadow edge generated by light, there is a large difference in the gradient direction between the edge pixels in the area with wrinkles and most of the texture edge pixels in the grayscale image. Also, since the larger the flattening factor of the area, the less the wrinkle feature exists in the area, the flattening degree of each area can be obtained by the difference in the gradient direction between each area and most of the texture edge pixels in the grayscale image, combined with the flattening factor of each area, and then the flat areas and the wrinkled areas can be screened out.

[0055] Preferably, in an embodiment of the present invention, a regularity degree threshold G is preset. The specific value of G can be set according to the actual situation and is not limited in this embodiment. In this embodiment, it is described with G = 0.9. The area with the regularity degree of the texture in the area greater than G is recorded as the reference area.

[0056] Furthermore, obtain the mean value of the gray level quantity and the mean value of the gradient value of all edge pixels in all reference areas, and record them as the reference gray level quantity and the reference gradient value respectively; obtain the flattening factor of each area according to the differences between the gray level quantity and the gradient mean value of all edge pixels in each area and the reference gray level quantity and the reference gradient value respectively, and the regularity degree of the texture in each area.

[0057] The flatness factor of each region is negatively correlated with the difference between the number of gray levels and the average gradient of all edge pixel points in each region and the reference number of gray levels and the reference gradient value, respectively; the flatness factor of each region is positively correlated with the regularity degree of the texture in each region.

[0058] In one example, its specific calculation formula is:

[0059]

[0060] In the formula, R represents the flatness factor of the region; τ represents the regularity degree of the texture in the region; W represents the number of gray levels of all edge pixel points in the region; represents the reference number of gray levels; D represents the average gradient of all edge pixel points in the region; represents the reference gradient value; || represents the absolute value function.

[0061] It should be noted that and The larger the value of, the greater the difference in the gray level and gradient value of the edge pixel points between the region and other regions with regular texture, and the greater the possibility of wrinkles in the region. Since the texture generated by wrinkles is not regular, the larger the value of τ, the smaller the possibility of wrinkles in the region. Therefore, the larger the value of R, the smaller the possibility of wrinkles in the region, and the flatter the region.

[0062] It should be further noted that the proportion of the texture of wrinkles in the gray image of the waterproof fabric is small. Therefore, the gradient direction that can represent the edge pixel points of the texture in the gray image can be screened out by the frequency of the gradient direction of each edge pixel point in the gray image. Further, based on the difference between the gradient direction of each region and the gradient direction of most texture edge pixel points in the gray image, combined with the flatness factor of each region, the flatness degree of each region can be obtained, and then the flat regions and the wrinkled regions can be screened out.

[0063] Preferably, in an embodiment of the present invention, the gradient direction with the highest frequency in the gradient directions of all edge pixel points in the gray image is denoted as the reference gradient direction;

[0064] Further, for any region, the pixel points in the region whose gradient direction is different from the reference gradient direction are denoted as abnormal pixel points, the region composed of adjacent abnormal pixel points in the region is denoted as an abnormal sub-region, and the largest abnormal sub-region is denoted as the characteristic abnormal sub-region. According to the difference between the gradient direction of each abnormal pixel point and the reference gradient direction, the flatness factor of the region, and the number of pixel points in the characteristic abnormal sub-region, the flatness degree of the region is obtained;

[0065] The product of the sum of the differences between the gradient directions of each abnormal pixel point in any region and the reference gradient direction and the number of pixel points in the characteristic abnormal sub-region is denoted as the wrinkle factor of the region; the ratio of the flatness factor of the region to the wrinkle factor of the region is normalized to obtain the flatness degree of the region. The specific calculation formula is as follows:

[0066]

[0067] In the formula, ρ represents the flatness degree of the region; n represents the number of abnormal pixel points in the region; R represents the flatness factor of the region; θ v represents the gradient direction of the v-th abnormal pixel point in the region; || represents the absolute value function; represents the reference gradient direction; m represents the number of pixel points in the characteristic abnormal sub-region; norm() represents the linear normalization function, and its normalization object is all regions

[0068] It should be noted that the larger the value of, the greater the difference between the gradient directions of all abnormal pixel points in the region and the reference gradient direction, that is, the more distinctive the gradient directions of the edge pixel points in the region. m represents the number of pixel points in the characteristic abnormal sub-region. Since in a region, wrinkles usually appear concentratedly, the largest abnormal sub-region is denoted as the characteristic abnormal sub-region. Therefore represents the wrinkle factor of the region. The smaller the wrinkle factor of the region, the flatter the region; and since the larger the value of R, the smaller the possibility of wrinkles in the region, the larger the value of ρ, the flatter the region. Further, flat regions and wrinkled regions can be obtained through the flatness degree of the region.

[0069] Preferably, in an embodiment of the present invention, a flatness degree threshold K is preset. The specific value of K can be set according to the actual situation and is not limited in this embodiment. In this embodiment, K = 0.8 is described. For any region, if the flatness degree of the region is greater than K, the region is a flat region; if the flatness degree of the region is less than or equal to K, the region is a wrinkled region.

[0070] Thus, flat regions and wrinkled regions are obtained.

[0071] Step S004: Obtain the flatness of the waterproof fabric according to the number of flat regions and the flatness degree of the wrinkled regions.

[0072] It should be noted that after analyzing the texture in each region to obtain flat regions and wrinkled regions, the flatness of the waterproof fabric can be accurately obtained by combining the proportion of flat regions in the waterproof fabric and the flatness degree of the wrinkled regions.

[0073] Preferably, in an embodiment of the present invention, the flatness of the waterproof fabric is obtained according to the proportion of the flat area in all areas of the grayscale image of the waterproof fabric, in combination with the average flatness of all the wrinkled areas.

[0074] The flatness of the waterproof fabric is positively correlated with the proportion of the flat area in all areas of the grayscale image of the waterproof fabric; the flatness of the waterproof fabric is negatively correlated with the average flatness of all the wrinkled areas.

[0075] In one example, the specific calculation formula is:

[0076]

[0077] In the formula, P represents the flatness of the waterproof fabric; H represents the number of areas in the grayscale image of the waterproof fabric; h represents the number of flat areas in the grayscale image of the waterproof fabric; z represents the number of wrinkled areas in the grayscale image of the waterproof fabric; ρ z represents the flatness of the v-th wrinkled area; exp() represents the exponential function with the natural constant as the base. In this embodiment, the exp(-α) model is used to present the inverse proportional relationship and normalization processing. α is the input of the model, and the implementer can set the inverse proportional function and normalization function according to the actual situation.

[0078] It should be noted that represents the proportion of the flat area in the waterproof fabric, the larger the value, the more flat areas in the waterproof fabric, and the flatter the waterproof fabric; represents the average flatness of all the wrinkled areas, the larger the value, the more wrinkled the wrinkled areas in the waterproof fabric; therefore the larger the value, the flatter the waterproof fabric.

[0079] Furthermore, a flatness threshold F is preset. The specific value of F can be set by the implementer according to the actual situation and is not limited in this embodiment. In this embodiment, it is described with F = 0.98. If the flatness of the waterproof fabric is greater than or equal to the flatness threshold, the waterproof fabric is flat; if the flatness of the waterproof fabric is less than the flatness threshold, the waterproof fabric is not flat.

[0080] As Figure 2 shown, it is a flowchart for detecting the flatness of the waterproof fabric.

[0081] So far, this embodiment is completed.

[0082] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for testing the flatness of a waterproof fabric, characterized in that, The method includes the following steps: Obtain a grayscale image of the waterproof fabric; Segment the grayscale image into several regions and obtain the edge pixel points in each region; according to the distribution of the edge pixel points in the region, obtain the regularity degree of the texture in the region; Select a reference region according to the regularity degree of the texture in the region; according to the difference in edge pixel points between each region and the reference region, and in combination with the regularity degree of the texture in each region, obtain the flatness factor of each region; according to the gradient directions of all the edge pixel points in the grayscale image, select a reference gradient direction; according to the difference in the gradient directions of the edge pixel points with different gradient directions from the reference gradient direction in each region, and in combination with the flatness factor of each region, obtain the flatness degree of each region; select flat regions and wrinkled regions according to the flatness degree of the regions; Obtain the flatness of the waterproof fabric according to the number of flat regions and the flatness degree of the wrinkled regions; The obtaining of the flatness degree of each region includes: for any region, record the pixel points with different gradient directions from the reference gradient direction in the region as abnormal pixel points, record the region composed of adjacent abnormal pixel points in the region as an abnormal sub-region, and record the largest abnormal sub-region as the characteristic abnormal sub-region, record the product of the sum of the differences between the gradient directions of each abnormal pixel point in any region and the reference gradient direction and the number of pixel points in the characteristic abnormal sub-region as the wrinkling factor of the region; normalize the ratio of the flatness factor of the region to the wrinkling factor of the region to obtain the flatness degree of the region.

2. The flatness test method for a waterproof fabric according to claim 1, wherein The segmenting of the grayscale image into several regions and obtaining the edge pixel points in each region includes the following specific method: Preset a area range, and divide the grayscale image into several regions with a specification of ; the and are the preset length and width of the area range respectively; use the sobel edge detection operator to obtain the edge pixel points in all regions.

3. The flatness test method for a waterproof fabric according to claim 1, wherein, The obtaining of the regularity degree of the texture in the region includes the following specific method: For any region, record the sequence composed of the pixel points in each row of the region as the pixel point sequence of each row, obtain the number of edge pixel points in all the pixel point sequences of each row in the region, and the distances between adjacent edge pixel points in all the pixel point sequences of each row; record the average value of the distances between adjacent edge pixel points in all the pixel point sequences of each row as the reference distance of the region; according to the difference between the distances between adjacent edge pixel points in all the pixel point sequences of each row and the reference distance of the region, and the variance of the number of edge pixel points in all the pixel point sequences of each row, obtain the regularity degree of the texture in the region; The regularity degree of the texture in the region is negatively correlated with the difference between the distances between adjacent edge pixel points in all the pixel point sequences of each row and the reference distance of the region, and the variance of the number of edge pixel points in all the pixel point sequences of each row.

4. The flatness test method for a waterproof fabric according to claim 1, wherein The selecting of the reference region according to the regularity degree of the texture in the region includes the following specific method: Preset a regularity degree threshold, and record the region with a regularity degree of the texture greater than the regularity degree threshold as the reference region.

5. The flatness test method for a waterproof fabric according to claim 1, wherein, The obtaining of the flatness factor of each region includes the following specific method: Obtain the average value of the gray level numbers and the average value of the gradient values of all the edge pixel points in all the reference regions, and record them as the reference gray level number and the reference gradient value respectively; Obtain the flatness factor of each region according to the number of gray levels and the gradient mean value of all edge pixel points in each region, the differences from the reference gray level number and the reference gradient value respectively, and the regularity degree of the texture in each region. The flatness factor of each region is negatively correlated with the differences between the number of gray levels and the gradient mean value of all edge pixel points in each region and the reference gray level number and the reference gradient value respectively; the flatness factor of each region is positively correlated with the regularity degree of the texture in each region.

6. The flatness test method for a waterproof fabric according to claim 1, characterized in that The specific method for screening out the reference gradient direction according to the gradient directions of all edge pixel points in the grayscale image includes: Record the gradient direction with the highest occurrence frequency among the gradient directions of all edge pixel points in the grayscale image as the reference gradient direction.

7. The flatness test method for a waterproof fabric according to claim 1, wherein The specific method for screening out the flat regions and the wrinkled regions according to the flatness degree of the regions includes: Preset a flatness degree threshold. For any region, if the flatness degree of the region is greater than the flatness degree threshold, then the region is a flat region; if the flatness degree of the region is less than or equal to the flatness degree threshold, then the region is a wrinkled region.

8. The flatness test method for a waterproof fabric according to claim 1, characterized in that, The specific method for obtaining the flatness of the waterproof fabric according to the number of flat regions and the flatness degree of the wrinkled regions includes: Obtain the flatness of the waterproof fabric according to the proportion of the flat regions in all regions in the grayscale image of the waterproof fabric, combined with the average flatness degree of all wrinkled regions. The flatness of the waterproof fabric is positively correlated with the proportion of the flat regions in all regions in the grayscale image of the waterproof fabric; the flatness of the waterproof fabric is negatively correlated with the average flatness degree of all wrinkled regions.

Images