A method and system for polymer material inspection based on image analysis

Abstract

The application relates to the technical field of material testing, and relates to a high polymer material testing method and system based on image analysis, which comprises the following steps: collecting images of high polymer materials to obtain high polymer material images, performing pretreatment operations to obtain pretreated material images, identifying a defect region set in the pretreated material images, performing feature extraction on the defect regions to obtain defect region parameters, comparing the defect region parameters with defect thresholds to obtain defect deviation values, judging the defect conditions of the defect regions, confirming the high polymer materials as preliminary qualified materials if all the defect conditions are acceptable defects, performing accelerated aging tests to obtain aging test materials, performing image detection on the aging test materials to obtain detected defect regions, comparing the defect regions with the detected defect regions to obtain defect region expansion values, and obtaining material detection results. The application can solve the problem of low testing result accuracy in the current high polymer material testing process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of material inspection, and in particular to a high polymer material inspection method and system based on image analysis. BACKGROUND

[0002] With the continuous development of the material industry, the demand for high polymer materials is increasing. In the production and application process of high polymer materials, in order to ensure product quality, high polymer materials need to be inspected.

[0003] The traditional high polymer material inspection method is mainly completed by physical performance test combined with manual observation and recording, lacking systematic analysis and quantitative characterization of high polymer material defects. In addition, the traditional inspection method focuses on the mechanical properties, thermal properties and other macroscopic indicators of high polymer materials, and it is difficult to detect the subtle defects of high polymer materials. Therefore, there is a problem of low accuracy of inspection results in the current high polymer material inspection process. SUMMARY

[0004] The present application provides a high polymer material inspection method and system based on image analysis, which mainly aims to solve the problem of low accuracy of inspection results in the current high polymer material inspection process.

[0005] To achieve the above purpose, the present application provides a high polymer material inspection method based on image analysis, which comprises:

[0006] Confirming the high polymer material inspection environment, wherein the high polymer material inspection environment comprises: high polymer material to be detected, image acquisition unit, image processing unit;

[0007] Using the image acquisition unit to acquire images of high polymer materials to obtain high polymer material images;

[0008] Pretreatment operation is performed on the high polymer material image to obtain a pretreated material image;

[0009] Using the image processing unit to identify a defect region set in the pretreated material image;

[0010] From the defect region set, defect regions are sequentially extracted, and the following operations are performed on the extracted defect regions;

[0011] Feature extraction is performed on the defect region to obtain a defect region parameter;

[0012] The defect region parameter is compared with a preset defect threshold to obtain a defect deviation value;

[0013] determine a defect condition of the defect region according to the defect bias value, wherein the defect condition is an irreparable defect, a repairable defect or an acceptable defect;

[0014] if the defect condition is the irreparable defect or the repairable defect, obtain a material inspection file based on the defect condition;

[0015] if the defect condition is the acceptable defect, confirm the polymer material as a preliminary qualified material;

[0016] place the preliminary qualified material in a pre-constructed test container for an accelerated aging test to obtain an aging test material;

[0017] perform image detection on the aging test material to obtain a detected defect region;

[0018] compare the defect region with the detected defect region to obtain a defect region expansion value;

[0019] obtain a material detection result according to the defect region expansion value, wherein the material detection result is durability compliance or durability non-compliance;

[0020] if the material detection result is the durability compliance, mark the preliminary qualified material as a target qualified material and generate a material inspection file;

[0021] if the material detection result is the durability non-compliance, mark the preliminary qualified material as a non-compliant material and generate a material inspection file;

[0022] complete the polymer material inspection based on image analysis according to the material inspection file.

[0023] Optionally, the pre-processing operation on the polymer material image to obtain a pre-processed material image comprises:

[0024] performing gray scale processing on the polymer material image to obtain a gray scale processed image;

[0025] performing noise recognition on the gray scale processed image to obtain a noise type;

[0026] obtaining a filter algorithm according to the noise type;

[0027] removing noise from the gray scale processed image by using the filter algorithm to obtain a noise-reduced image;

[0028] performing edge-preserving filter processing on the noise-reduced image to obtain an edge-enhanced image;

[0029] removing a non-material region image in the edge-enhanced image to obtain the pre-processed material image.

[0030] Optionally, the high polymer material image is subjected to gray scale processing to obtain a gray scale processing image, including:

[0031] An RGB three-channel pixel value set of the high polymer material image is obtained, wherein the RGB three-channel pixel value set refers to a collection of RGB three-channel pixel values of all pixel points in the high polymer material image, and the RGB three-channel pixel value includes a red channel pixel value, a green channel pixel value, and a blue channel pixel value.

[0032] The RGB three-channel pixel values are sequentially extracted from the RGB three-channel pixel value set.

[0033] The RGB three-channel pixel values are converted into gray scale values by using a pre-constructed gray scale formula, wherein the gray scale formula is as follows:

[0034]

[0035] wherein, the gray scale value is represented by G, the red channel pixel value of the pixel point is represented by R, the green channel pixel value of the pixel point is represented by G, the blue channel pixel value of the pixel point is represented by B, the weight coefficient of the red channel pixel value, the weight coefficient of the green channel pixel value, and the weight coefficient of the blue channel pixel value are represented by a, b, and c respectively.

[0036] The gray scale values are mapped to a preset gray scale value interval to obtain standard gray scale values.

[0037] The high polymer material image is converted into a gray scale processing image according to the standard gray scale values.

[0038] Optionally, the image processing unit is used to identify a defect region set in the pre-processed material image, including:

[0039] The image processing unit is used to extract a gray scale value set of the pre-processed material image.

[0040] A gray scale threshold set is confirmed in the gray scale value set.

[0041] An optimal gray scale threshold is calculated according to the gray scale threshold set and a pre-constructed threshold calculation formula, wherein the threshold calculation formula is as follows:

[0042]

[0043] wherein, the optimal gray scale threshold is represented by Gopt, the proportion of pixel points with a gray scale value less than or equal to a gray scale threshold in total pixel points is represented by p, an average value of the gray scale values corresponding to the pixel points with the gray scale value less than or equal to the gray scale threshold value, an average value of the gray scale values corresponding to all the pixel points, a proportion of the pixel points with the gray scale value greater than the gray scale threshold value in all the pixel points, an average value of the gray scale values corresponding to the pixel points with the gray scale value greater than the gray scale threshold value;

[0044] confirming a set of local defect regions based on the preprocessed material image, wherein the set of local defect regions comprises a plurality of local defect regions, and the gray scale value corresponding to each pixel point in the local defect region is greater than the optimal gray scale threshold value;

[0045] performing connectivity analysis on the set of local defect regions, and identifying a set of defect regions, wherein the set of defect regions comprises one or more defect regions, and the defect region comprises one or more local defect regions.

[0046] Optionally, the feature extraction on the defect region is performed to obtain a defect region parameter, comprising:

[0047] calculating an average gray scale value of the pixel points in the defect region;

[0048] performing geometric feature extraction on the defect region to obtain a geometric feature value;

[0049] counting the total number of local defect regions in the defect region to obtain a branch number;

[0050] detecting the number of holes in the defect region;

[0051] calculating the difference between the branch number and the number of holes to obtain an Euler number;

[0052] constructing the defect region parameter according to the average gray scale value, the geometric feature value and the Euler number.

[0053] Optionally, the geometric feature extraction on the defect region to obtain the geometric feature value comprises:

[0054] determining the pixel area of the defect region, and converting the pixel area into a defect area by using a preset pixel conversion ratio;

[0055] extracting a set of boundary pixel points of the defect region by using a preset boundary tracking algorithm;

[0056] converting the set of boundary pixel points into an ordered boundary chain code by using a preset chain code encoding rule;

[0057] sequentially extracting a first boundary chain code point from the ordered boundary chain code, and performing the following operation on the extracted first boundary chain code point;

[0058] determining a second boundary chain code point in the ordered boundary chain code by using the first boundary chain code point, wherein the second boundary chain code point is adjacent to and lags behind the first boundary chain code point;

[0059] calculating a Euclidean distance between the first boundary chain code point and the second boundary chain code point;

[0060] accumulating the Euclidean distance to obtain a boundary perimeter;

[0061] calculating a geometric feature value according to the defect area and the boundary perimeter.

[0062] Optionally, the comparing the defect area parameter with the preset defect threshold value to obtain a defect deviation value comprises:

[0063] standardizing the defect area parameter to obtain a standard defect area parameter;

[0064] calculating a defect value according to the standard defect area parameter;

[0065] comparing the defect value with a defect threshold value to obtain a defect deviation value.

[0066] Optionally, the determining a defect condition of the defect area according to the defect deviation value comprises:

[0067] when the defect deviation value is less than a preset first deviation threshold value, confirming the defect condition as an acceptable defect;

[0068] when the defect deviation value is greater than or equal to the first deviation threshold value and less than a preset second deviation threshold value, confirming the defect condition as a repairable defect;

[0069] when the defect deviation value is greater than or equal to the second deviation threshold value, confirming the defect condition as an unrepairable defect.

[0070] Optionally, the placing the preliminary qualified material in a pre-constructed test container for an accelerated aging test to obtain an aging test material comprises:

[0071] obtaining an environmental parameter adjusting device;

[0072] adjusting parameters of the test container by using the environmental parameter adjusting device to obtain a test container set, wherein the test container set comprises a first test container, a second test container and a third test container, the temperature, humidity and illumination of the first test container are respectively a preset test temperature, a standard humidity and a standard illumination, the temperature, humidity and illumination of the second test container are respectively a standard temperature, a preset test humidity and a standard illumination, and the temperature, humidity and illumination of the third test container are respectively a standard temperature, a standard humidity and a preset test illumination;

[0073] The preliminary qualified materials are respectively placed into a first test container, a second test container and a third test container, and are taken out after a preset time interval, so as to obtain a preliminary aging test material set;

[0074] An appearance integrity detection is performed on each preliminary aging test material in the preliminary aging test material set, so as to obtain an appearance detection result, wherein the appearance detection result is with scratch damage or without scratch damage;

[0075] If the appearance detection result is with scratch damage, a preset scratch prevention processing scheme is triggered, and the step of placing the preliminary qualified materials into the first test container, the second test container and the third test container is returned until the appearance detection result is without scratch damage.

[0076] If the appearance detection result is without scratch damage, the preliminary aging test material is confirmed as an aging test material.

[0077] To achieve the above object, the application further provides a high polymer material inspection system based on image analysis, comprising:

[0078] An environment confirmation module is configured to confirm a high polymer material inspection environment, wherein the high polymer material inspection environment comprises a high polymer material to be detected, an image acquisition unit and an image processing unit.

[0079] An image processing module is configured to acquire an image of the high polymer material by using the image acquisition unit, to obtain a high polymer material image, to perform a pretreatment operation on the high polymer material image, to obtain a pretreated material image, and to identify a defect region set in the pretreated material image by using the image processing unit.

[0080] A defect determination module is configured to sequentially extract a defect region from the defect region set, and to perform the following operations on the extracted defect region: to extract a feature of the defect region, to obtain a defect region parameter, to compare the defect region parameter with a preset defect threshold, to obtain a defect deviation value, and to determine a defect condition of the defect region according to the defect deviation value, wherein the defect condition is an irreparable defect, a repairable defect or an acceptable defect, if the defect condition has the irreparable defect or the repairable defect, a material inspection file is obtained based on the defect condition, and if the defect condition is the acceptable defect, the high polymer material is confirmed as a preliminary qualified material.

[0081] The durability test module is used for placing the preliminary qualified material in a pre-built test container for accelerated aging test, obtaining an aging test material, performing image detection on the aging test material, obtaining a detection defect area, comparing the defect area with the detection defect area, obtaining a defect area expansion value, and obtaining a material detection result according to the defect area expansion value, wherein the material detection result is durability compliance or durability non-compliance, if the material detection result is durability compliance, the preliminary qualified material is marked as a target qualified material, and a material inspection file is generated, and if the material detection result is durability non-compliance, the preliminary qualified material is marked as a non-compliant material, and a material inspection file is generated.

[0082] To solve the above problems, the application further provides an electronic device, which comprises:

[0083] The memory stores at least one instruction, and the processor executes the instruction stored in the memory to realize the above-mentioned polymer material inspection method based on image analysis.

[0084] To solve the above problems, the application further provides a computer readable storage medium, which stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to realize the above-mentioned polymer material inspection method based on image analysis.

[0085] The application is to solve the problems described in the background art. First, the high polymer material testing environment is confirmed, which includes the high polymer material to be detected, an image acquisition unit, and an image processing unit. The image acquisition unit is used to acquire the image of the high polymer material. The high polymer material image may be affected by environmental light interference, material surface reflection, and other factors. Therefore, the high polymer material image is preprocessed to obtain a pretreated material image that can highlight the characteristics of the high polymer material. Then, the image processing unit identifies a set of defect regions in the pretreated material image. In order to analyze the defect regions, the defect regions are extracted from the set of defect regions in sequence, and the following operations are performed on the extracted defect regions. The characteristics of the defect regions are extracted to obtain defect region parameters. In order to determine the defect condition of the defect region, the defect region parameters are compared with the preset defect threshold to obtain a defect deviation value. The defect condition of the defect region is determined according to the defect deviation value, wherein the defect condition is an irreparable defect, a repairable defect, or an acceptable defect. If there is an irreparable defect or a repairable defect in the defect condition of all defect regions, a material testing file is obtained based on the defect condition. If the defect condition of all defect regions is an acceptable defect, the high polymer material can be confirmed as a preliminary qualified material. In order to measure the material durability of the preliminary qualified material, the preliminary qualified material is placed in a pre-constructed test container for accelerated aging test to obtain an aging test material. The aging test material is subjected to image detection, and the defect regions in the aging test material image are analyzed and identified. The defect regions are compared with the detected defect regions to obtain a defect region expansion value. The defect expansion value can reflect the change range of the defect region. Therefore, the material detection result can be obtained according to the defect region expansion value, wherein the material detection result is durability standard or durability not standard. If the material detection result is durability standard, the preliminary qualified material is marked as a target qualified material, and a material testing file is generated. If the material detection result is durability not standard, the preliminary qualified material is marked as a non-standard material, and a material testing file is generated. Based on the material testing file, the high polymer material testing based on image analysis is completed. Therefore, the application can solve the problem of low accuracy of the testing result in the current high polymer material testing process. BRIEF DESCRIPTION OF DRAWINGS

[0086] Figure 1 The flowchart of the high polymer material testing method based on image analysis provided by an embodiment of the application is shown in the figure.

[0087] Figure 2 The functional module diagram of the high polymer material testing system based on image analysis provided by an embodiment of the application is shown in the figure.

[0088] Figure 3A structural schematic diagram of an electronic device for implementing the image analysis based polymer material inspection method according to an embodiment of the present application is shown in FIG. 1.

[0089] Legend of reference signs:

[0090] 1. electronic device; 10, processor; 11, memory; 12, bus.

[0091] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0092] It should be understood that the specific embodiments described herein are merely intended to explain the present application and not to limit the present application.

[0093] An image analysis based polymer material inspection method is provided in the embodiments of the present application. The execution subject of the image analysis based polymer material inspection method includes, but is not limited to, at least one of electronic devices such as a server and a terminal, which can be configured to execute the method provided in the embodiments of the present application. In other words, the image analysis based polymer material inspection method can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0094] Reference Figure 1 A flowchart of the image analysis based polymer material inspection method according to an embodiment of the present application is shown in FIG. 1. In the embodiment, the image analysis based polymer material inspection method includes:

[0095] S1, confirming a polymer material inspection environment, wherein the polymer material inspection environment includes a polymer material to be detected, an image acquisition unit and an image processing unit.

[0096] It should be noted that the polymer material refers to a material processed and shaped by using a high molecular compound as a main component, including plastic, rubber, fiber, paint, adhesive, etc. The image acquisition unit refers to a device for acquiring an image of the polymer material, including an industrial camera (such as a CCD or CMOS sensor), a light source (such as a ring light source or a back light source), etc. The image processing unit refers to a computing device for defect analysis of the acquired image of the polymer material, specifically a hardware processor (such as a GPU or FPGA) and image processing software running thereon.

[0097] S2, image acquisition unit is used for collecting image of high polymer material, and a high polymer material image is obtained; the high polymer material image is pretreated to obtain a pretreated material image; and an image processing unit is used for identifying a defect region set in the pretreated material image.

[0098] It should be explained that the image acquisition refers to photographing the surface and overall shape of the high polymer material by using the image acquisition unit to obtain the image of the high polymer material. The high polymer material image refers to the image obtained by image acquisition and capable of reflecting the defect condition of the high polymer material.

[0099] In detail, the pretreatment operation on the high polymer material image to obtain the pretreated material image comprises:

[0100] The high polymer material image is subjected to gray scale processing to obtain a gray scale processing image;

[0101] The gray scale processing image is subjected to noise identification to obtain a noise type;

[0102] The filter algorithm is obtained according to the noise type;

[0103] The filter algorithm is used for removing noise from the gray scale processing image to obtain a noise reduction image;

[0104] The noise reduction image is subjected to edge-preserving filter processing to obtain an edge enhancement image;

[0105] The non-material region image in the edge enhancement image is removed to obtain the pretreated material image.

[0106] It should be understood that the pretreatment operation refers to a series of operations (such as gray scale processing, noise removal, etc.) on the high polymer material image to eliminate interference information and highlight image features. The pretreated material image refers to the material image obtained after the pretreatment operation, which retains the key feature information of the high polymer material and can be used for subsequent identification of the defect region. The gray scale processing refers to converting the high polymer material image into a gray scale image, that is, converting the RGB three-channel pixel value of the high polymer material image into a gray scale value. The gray scale processing image refers to the image obtained after the high polymer material image is subjected to gray scale processing, and each pixel point of the image represents the brightness information in the form of a gray scale value.

[0107] It needs to be explained that the noise recognition refers to determining the type of noise existing in the gray processing image by analyzing the local statistical characteristics (such as: variance, histogram kurtosis) of the gray processing image. The noise type refers to the category of the interference signal determined after noise recognition, such as salt and pepper noise, Gaussian noise, etc. The filtering algorithm refers to the image denoising method determined according to the noise type, for example: median filtering, Gaussian filtering, etc. The selection of the filtering algorithm is related to the noise type, and the noise type can be selected to select the filtering algorithm for filtering the noise type by combining the commonly known knowledge, for example: salt and pepper noise is usually matched with median filtering algorithm, median filtering can eliminate isolated extreme gray value pixels, and has inhibitory effect on pulse noise; Gaussian noise is usually matched with Gaussian filtering algorithm, and Gaussian filtering can smooth the noise while preserving the details of the image by weighting and averaging the gray values around the pixel points.

[0108] The noise removal refers to performing convolution operation on the gray processing image by the selected filtering algorithm, reducing the noise signal in the gray processing image, and improving the definition and signal-to-noise ratio of the gray processing image. The denoising image refers to the image obtained after the noise removal operation on the gray processing image. The edge preserving filtering processing refers to using filtering algorithm (such as: bilateral filtering, guided filtering) to smooth the denoising image while maintaining the edge sharpness, so as to avoid the outline edge of the image of the high molecular material in the denoising image being blurred. The purpose of noise removal is to remove the discrete or high frequency noise in the gray processing image, and the purpose of edge preserving filtering processing is to remove the residual fine noise in the denoising image while protecting the edge outline of the image of the high molecular material in the denoising image.

[0109] The edge enhanced image refers to the image obtained after the edge preserving filtering processing on the denoising image. The non-material area image refers to the image area in the edge enhanced image that is irrelevant to the high molecular material to be detected, including: background environment (such as: desktop, air, etc.), reflection of the shooting device, etc. The non-material area image does not contain the characteristic information of the high molecular material to be detected, and needs to be removed by cropping, masking, etc.

[0110] Specifically, the gray processing of the high molecular material image to obtain a gray processing image comprises:

[0111] Obtaining an RGB three-channel pixel value set of the high molecular material image, wherein the RGB three-channel pixel value set refers to a set of RGB three-channel pixel values of all pixel points in the high molecular material image, and the RGB three-channel pixel value includes red channel pixel value, green channel pixel value and blue channel pixel value;

[0112] Sequentially extracting RGB three-channel pixel values from the RGB three-channel pixel value set;

[0113] The RGB three-channel pixel values are converted into a gray value by using a pre-constructed gray-scale formula, wherein the gray-scale formula is as follows:

[0114]

[0115] wherein, represents a gray value, represents a red channel pixel value of a pixel point, represents a green channel pixel value of a pixel point, represents a blue channel pixel value of a pixel point, respectively represent a preset weight coefficient of a red channel pixel value, a weight coefficient of a green channel pixel value, and a weight coefficient of a blue channel pixel value;

[0116] The gray value is mapped to a preset gray value interval to obtain a standard gray value;

[0117] According to the standard gray value, the high polymer image is converted into a gray processing image.

[0118] It should be noted that the gray value interval refers to a preset numerical interval for regulating the range of gray values, which is [0, 255] in this embodiment, wherein 0 corresponds to black and 255 corresponds to white, and the numerical values in the interval correspond to different gray levels from black to white in turn. The standard gray value refers to a numerical value obtained by mapping the gray value calculated by the gray-scale formula to the preset gray value interval, which is within the gray value interval and can uniformly represent the brightness of the pixel point. When the gray value is within the [0, 255] interval, the standard gray value after mapping is consistent with the gray value, and when the gray value is not within the [0, 255] interval, the numerical value less than 0 is mapped to 0 and the numerical value greater than 255 is mapped to 255. In the gray-scale formula, The specific numerical value of can be set according to the color characteristics of the high polymer material and the image analysis requirements, and in this embodiment, the weight distribution consistent with the visual characteristics of the human eye can be used, i.e. = 0.299, = 0.587, = 0.114.

[0119] For example, the red channel pixel value of a pixel point in a high polymer material image is 200, the green channel pixel value is 150, and the blue channel pixel value is 100. Substituting into the gray-scale formula can obtain a gray value of 162.4. The gray values of this image are concentrated in the [50, 200] interval, so after mapping, the gray values of this image are stretched and mapped to the [0, 255] interval, and the standard gray value of the pixel point is 191.

[0120] Further, the image processing unit is used to identify a set of defect regions in the pre-processed material image, including:

[0121] The image processing unit is used to extract a set of gray scale values of the pre-processed material image;

[0122] A set of gray scale thresholds is confirmed in the set of gray scale values;

[0123] An optimal gray scale threshold is calculated according to the set of gray scale thresholds and a pre-constructed threshold calculation formula, wherein the threshold calculation formula is as follows:

[0124]

[0125] wherein, represents the optimal gray scale threshold, represents a proportion of pixel points with a gray scale value less than or equal to the gray scale threshold in total pixel points, represents an average value of gray scale values of pixel points with a gray scale value less than or equal to the gray scale threshold, represents an average value of gray scale values of all pixel points, represents a proportion of pixel points with a gray scale value greater than the gray scale threshold in total pixel points, represents an average value of gray scale values of pixel points with a gray scale value greater than the gray scale threshold;

[0126] A set of local defect regions is confirmed based on the pre-processed material image, wherein the set of local defect regions includes a plurality of local defect regions, and a gray scale value of each pixel point in the local defect region is greater than the optimal gray scale threshold;

[0127] The set of local defect regions is subjected to connectivity analysis, and a set of defect regions is identified, wherein the set of defect regions includes one or more defect regions, and the defect region includes one or more local defect regions.

[0128] It needs to be explained that the gray threshold set refers to a set of gray values extracted from the gray value set of the pre-processed material image, which can be used as a segmentation limit to distinguish the defect area from the normal area, where the gray threshold set is the same as the gray value set. The optimal gray threshold refers to the optimal segmentation threshold calculated by the threshold calculation formula, which can maximize the difference between the gray values of the defect area and the normal area. The connectivity analysis refers to the spatial correlation judgment of each pixel point in the local defect area set by the neighborhood connectivity standard (such as 4-neighborhood or 8-neighborhood rule). If there is at least one common neighborhood connection (such as under the 4-neighborhood rule, the pixel points of two regions are directly adjacent through one of the up, down, left, and right directions; under the 8-neighborhood rule, it also includes adjacent connection through diagonal direction) between the pixel points in two local defect areas, they are clustered into the same defect area. The defect area refers to the area clustered by the local area set with common neighborhood connection relationship after the connectivity analysis of the local defect area, and the defect area set refers to the set composed of all defect areas.

[0129] For example, the total number of pixels of a certain pre-processed material image is 640, when the gray threshold is 120, 0.6875, 36.8, 0.31, 107.8, 59, the inter-class variance under this gray threshold can be calculated as 1077.07, when the gray threshold is 150, the calculated inter-class variance is 4175.7, which is the maximum inter-class variance, so 150 is the optimal gray threshold.

[0130] S3, from the defect area set, extract the defect area in sequence, and perform the following operations on the extracted defect area. Feature extraction is performed on the defect area to obtain defect area parameters. The defect area parameters are compared with the preset defect threshold to obtain a defect deviation value. According to the defect deviation value, the defect condition of the defect area is determined.

[0131] In detail, the defect condition is an irreparable defect, a repairable defect, or an acceptable defect.

[0132] It should be understood that the feature extraction refers to extracting feature information of the defect area from the defect area and performing quantitative calculation on the feature information, and the feature information includes gray scale features (such as gray scale mean value, gray scale variance), geometric features (such as area, perimeter), etc. The defect area parameter refers to a series of quantitative indexes obtained by feature extraction for describing the characteristics of the defect area, for example, the gray scale mean value is 180, the geometric feature value is 3.2, and the Euler number is 2. The defect threshold refers to a critical value preset for judging the defect severity of the defect area. The defect deviation value refers to the difference between the defect value obtained after the defect area parameter is standardized and the defect threshold. The irreparable defect refers to that the defect deviation value of the defect area is greater than or equal to the second deviation threshold, the defect degree is serious, and the structure integrity, mechanical properties or use function of the polymer material have been irreversibly damaged, which cannot be eliminated or controlled within an acceptable range by rework, repair and other methods. The repairable defect refers to that the defect deviation value of the defect area is greater than or equal to the first deviation threshold and less than the second deviation threshold, the defect degree is moderate, although it has a certain influence on the material properties, but through a specific repair process (such as filling, polishing, coating covering, etc.), the defect can be eliminated or controlled within an acceptable range. The acceptable defect refers to that the defect deviation value of the defect area is less than the first deviation threshold, the defect degree is slight, and the influence on the mechanical properties, structure integrity and use function of the polymer material is within an acceptable range.

[0133] Specifically, the feature extraction on the defect area to obtain the defect area parameter includes:

[0134] calculating the gray scale mean value of the pixel points in the defect area;

[0135] performing geometric feature extraction on the defect area to obtain a geometric feature value;

[0136] counting the total number of local defect areas in the defect area to obtain a branch number;

[0137] detecting the number of holes in the defect area;

[0138] calculating the difference between the branch number and the number of holes to obtain an Euler number;

[0139] constructing the defect area parameter according to the gray scale mean value, the geometric feature value and the Euler number.

[0140] It should be noted that the gray mean value refers to the arithmetic mean value of the gray values of all pixel points in the defect area. The geometric feature value refers to a value calculated from the defect area and the boundary perimeter, reflecting the complexity of the shape of the defect area. The hole number refers to the number of non-local defect areas completely surrounded by the local defect area inside the defect area. The Euler number refers to the difference between the total number of initial defect areas and the hole number, which can reflect the connectivity and complexity of the defect area.

[0141] Further, the geometric feature extraction of the defect area obtains a geometric feature value, comprising:

[0142] Determining the pixel area of the defect area, and converting the pixel area into a defect area by using a preset pixel conversion ratio;

[0143] Extracting the boundary pixel point set of the defect area by using a preset boundary tracking algorithm;

[0144] Converting the boundary pixel point set into an ordered boundary chain code by using a preset chain code encoding rule;

[0145] Extracting a first boundary chain code point from the ordered boundary chain code in sequence, and performing the following operations on the extracted first boundary chain code point;

[0146] Determining a second boundary chain code point in the ordered boundary chain code by using the first boundary chain code point, wherein the second boundary chain code point is adjacent to and lags behind the first boundary chain code point;

[0147] Calculating the Euclidean distance between the first boundary chain code point and the second boundary chain code point;

[0148] Accumulating the Euclidean distance to obtain a boundary perimeter;

[0149] Calculating the geometric feature value according to the defect area and the boundary perimeter, and the calculation formula is as follows:

[0150]

[0151] wherein, the geometric feature value is represented by G, the defect area is represented by A, and the boundary perimeter is represented by P.

[0152] It needs to be explained that the pixel area refers to the total number of pixel points in the defect area. The pixel conversion ratio refers to the conversion coefficient between the preset pixel number and the actual physical area (for example: in an image with a resolution of 100 pixels / mm, 1 pixel corresponds to an actual area of 0.01 mm², and the pixel conversion ratio is 0.01 mm² / pixel). The defect area refers to the actual physical area of the defect area obtained by converting the pixel area using the pixel conversion ratio. The boundary tracking algorithm refers to an algorithm for extracting boundary pixel points in a target area in an image, which can sequentially find all pixel points constituting the boundary along the edge of the defect area, thereby determining the outline of the defect area. Optionally, an eight-neighbor boundary tracking algorithm is used as the boundary tracking algorithm. The boundary pixel point set refers to a set of all pixel points constituting the boundary of the defect area extracted by the boundary tracking algorithm.

[0153] It needs to be explained that the chain code encoding rule refers to encoding the positional relationship between the boundary pixel points using a specific direction encoding method, and converting the boundary pixel point set into an ordered chain code sequence. Optionally, 8-direction encoding is used as the chain code encoding rule. The ordered boundary chain code refers to the chain code point sequence arranged in a clockwise or counterclockwise direction obtained by encoding the boundary pixel point set according to the chain code encoding rule. The first boundary chain code point refers to a chain code point extracted in order from the ordered boundary chain code. When calculating the boundary perimeter, the first boundary chain code point needs to be taken as the starting point and the Euclidean distance is calculated with the subsequent second boundary chain code point. The calculation method of the Euclidean distance is a prior art and will not be described here. The boundary perimeter refers to the total length obtained by sequentially accumulating the Euclidean distances between all adjacent first and second boundary chain code points in the ordered boundary chain code.

[0154] For example, the defect area of a certain defect area is 32 square millimeters, and the boundary perimeter is 16 millimeters, and the geometric feature value is 8.

[0155] In detail, the comparison of the defect area parameters with the preset defect threshold value to obtain a defect deviation value includes:

[0156] The defect area parameters are standardized to obtain standard defect area parameters;

[0157] The defect value is calculated according to the standard defect area parameters, and the calculation formula is as follows:

[0158]

[0159] wherein, represents the defect value, represents the weight coefficient of the th feature value, represents the weight coefficient of the a characteristic value of a standard defect area parameter, a defect standard corresponding to the characteristic value of the standard defect area parameter; a characteristic value of a standard defect area parameter,

[0160] comparing the defect value with a defect threshold value to obtain a defect deviation value.

[0161] It should be understood that the standardization processing refers to mapping the characteristic indexes with different dimensions, different orders of magnitude, such as gray mean value, geometric characteristic value, Euler number, etc. in the defect area parameter to the same dimensionless value interval by using a unified mathematical transformation method (such as: Z-score standardization, normalization conversion, etc.), and converting into a dimensionless and same order of magnitude standardized value. The defect value refers to a comprehensive value calculated by weighted summation based on the standardized defect area parameter.

[0162] For example, the standard defect area parameter of a certain defect area is: the standard gray mean value , the standard geometric characteristic value , the standard Euler number , the set gray mean value standard , the geometric characteristic value standard , the Euler number standard , and the weight coefficients of the three characteristic items are , , respectively. The defect value can be calculated as 0.49.

[0163] Specifically, the defect condition of the defect area is determined according to the defect deviation value, including:

[0164] When the defect deviation value is less than a preset first deviation threshold value, the defect condition is confirmed as an acceptable defect;

[0165] When the defect deviation value is greater than or equal to the first deviation threshold value and less than a preset second deviation threshold value, the defect condition is confirmed as a repairable defect;

[0166] When the defect deviation value is greater than or equal to the second deviation threshold value, the defect condition is confirmed as an irreparable defect.

[0167] It should be explained that the first deviation threshold value refers to a critical value preset for distinguishing between acceptable defects and repairable defects. The second deviation threshold value refers to a critical value preset for distinguishing between repairable defects and irreparable defects. For example, when the first deviation threshold value is 0.5 and the second deviation threshold value is 1.2, if the defect deviation value of a certain defect area is 0.3, it is determined as an acceptable defect.

[0168] S4, if the defect condition exists an unrepairable defect or a repairable defect, obtaining a material inspection file based on the defect condition, if the defect condition is all acceptable defects, confirming the polymer material as a preliminary qualified material.

[0169] It should be noted that the material inspection file refers to an information file used to record various types of data generated during the inspection of the polymer material, including characteristic parameters of the defect area (such as average gray value, geometric characteristic value, Euler number), defect deviation value, defect condition determination result, inspection time, etc. The preliminary qualified material refers to a polymer material whose defect condition of all defect areas is an acceptable defect after defect condition determination.

[0170] S5, placing the preliminary qualified material in a pre-constructed test container for accelerated aging test to obtain an aging test material, and performing image detection on the aging test material to obtain a detected defect area.

[0171] It should be understood that the test container refers to a device for placing the preliminary qualified material, which can control internal temperature, humidity, illumination and other parameters in cooperation with an environmental parameter adjusting device, such as an aging oven, an environmental test chamber, etc. The accelerated aging test refers to accelerating the natural aging process of the polymer material by artificially adjusting the test environment parameters (such as increasing temperature, humidity, illumination intensity, etc.). The aging test material refers to the material obtained after the preliminary qualified material is subjected to the accelerated aging test. The image detection refers to a process of image acquisition on the aging test material by the image acquisition unit, and after the acquired image is preprocessed, the preprocessed aging test material image is subjected to defect area recognition and other operations by the image processing unit. The detected defect area refers to the defect area of the aging test material image recognized by the image detection.

[0172] In detail, the preliminary qualified material is placed in a pre-constructed test container for accelerated aging test to obtain an aging test material, including:

[0173] obtaining an environmental parameter adjusting device;

[0174] adjusting the parameters of the test container by the environmental parameter adjusting device to obtain a test container set, wherein the test container set includes a first test container, a second test container and a third test container, the temperature, humidity and illumination of the first test container are respectively a preset test temperature, a standard humidity and a standard illumination, the temperature, humidity and illumination of the second test container are respectively a standard temperature, a preset test humidity and a standard illumination, and the temperature, humidity and illumination of the third test container are respectively a standard temperature, a standard humidity and a preset test illumination;

[0175] placing the preliminary qualified materials into the first test container, the second test container and the third test container respectively, and taking them out after a preset time interval, to obtain a preliminary aging test material set;

[0176] detecting the appearance integrity of each preliminary aging test material in the preliminary aging test material set to obtain an appearance detection result, wherein the appearance detection result is with scratch damage or without scratch damage;

[0177] if the appearance detection result is with scratch damage, triggering a preset scratch prevention processing scheme, and returning to the step of placing the preliminary qualified materials into the first test container, the second test container and the third test container respectively until the appearance detection result is without scratch damage;

[0178] if the appearance detection result is without scratch damage, confirming the preliminary aging test material as an aging test material.

[0179] It should be explained that the environmental parameter adjusting device refers to a device capable of controlling and adjusting the temperature, humidity, light and other environmental parameters in the test container, such as an ultrasonic humidifier, a PID temperature controller, etc. The parameter adjustment refers to adjusting the environmental parameters of the three test containers to the preset values respectively by the parameter adjusting device, so that the first test container highlights the high temperature influence, the second test container highlights the high humidity influence, and the third test container highlights the strong light influence. The test temperature refers to the accelerated aging temperature preset according to the type of the preliminary qualified material, for example, for polypropylene material, it can be set to 65°C; for polyvinyl chloride material, it can be set to 75°C. The test humidity refers to the relative humidity preset according to the type of the preliminary qualified material, for example, for polystyrene material, it can be set to 65% RH. The test light refers to the light condition preset according to the type of the preliminary qualified material, for example, for polypropylene material, it can be set to 6000 lx. The time interval refers to the duration of the preliminary qualified material in the test container.

[0180] It should be understood that the standard temperature refers to the ambient temperature used as a reference in the accelerated aging test, which can be set to 25°C in this embodiment. The standard humidity refers to the relative humidity used as a reference in the accelerated aging test, which can be set to 50%RH in this embodiment. The standard illumination refers to the illumination conditions used as a reference in the accelerated aging test, which can be set to 1000 lx in this embodiment. The preliminary aging test material set refers to the collection of materials taken from the three test containers that have undergone aging treatment but have not undergone appearance inspection. The appearance integrity inspection refers to the inspection of the surface of the preliminary aging test materials using a low-magnification microscope to determine whether there are scratches or damage (if the length of the scratch is ≥0.5 mm and the depth is ≥5 micrometers, then the scratch is considered scratch damage). The anti-scratch treatment plan refers to a series of measures taken to avoid the recurrence of scratches when scratch damage is detected, such as: replacing the test container with a container made of polytetrafluoroethylene with a smooth inner wall, using soft silicone tweezers to handle the materials, and laying a 2-3 mm thick sponge cushioning pad at the bottom of the test container, etc.

[0181] S6. Compare the defect area with the detected defect area to obtain the defect area expansion value, and obtain the material test result based on the defect area expansion value.

[0182] The test results for the material indicate whether its durability meets or fails to meet the standards.

[0183] It should be understood that the defect area expansion value refers to the rate of change of the defect area calculated by comparing the defect area with the detected defect area. For example, if the defect area is 5 square millimeters and the detected defect area is 8 square millimeters, then the defect area expansion value is... The durability standard is defined as follows: the defect area expansion value does not exceed the preset durability threshold, indicating that the aging test material can maintain stable performance within the expected service life and meets the preset performance requirements. The durability failure is defined as the defect area expansion value exceeding the preset durability threshold, indicating that the aging test material cannot maintain stable performance within the expected service life and does not meet the performance requirements. For example, if the durability threshold is 0.2, and the defect area expansion value is 0.25, then the material test result is determined to be durability failure.

[0184] S7. If the material test results show that the durability meets the standard, the preliminarily qualified material will be marked as the target qualified material and a material inspection file will be generated. If the material test results show that the durability does not meet the standard, the preliminarily qualified material will be marked as the substandard material and a material inspection file will be generated.

[0185] It should be noted that the target qualified material refers to the preliminary qualified material which passes the accelerated aging test and the material inspection result is that the durability is up to standard. The unqualified material refers to the preliminary qualified material which passes the accelerated aging test but the material inspection result is that the durability is not up to standard.

[0186] S8. Complete the polymer material inspection based on image analysis according to the material inspection file.

[0187] It should be explained that after the inspection of the material is completed, the material inspection file needs to be summarized, and the various data of the polymer material recorded in the material inspection file during the inspection process need to be archived and confirmed, so as to complete the whole process inspection work from image collection analysis to the confirmation of the qualification of the polymer material.

[0188] The application is to solve the problems described in the background art. First, the high polymer material test environment is confirmed, which includes the high polymer material to be detected, an image acquisition unit, and an image processing unit. The image acquisition unit is used to acquire images of the high polymer material. The high polymer material images may be affected by environmental light interference, material surface reflection, and other factors. Therefore, the high polymer material images are preprocessed to obtain preprocessed material images that can highlight the characteristics of the high polymer material. Then, the image processing unit identifies a set of defect regions in the preprocessed material images. To analyze the defect regions, the defect regions are extracted from the set of defect regions one by one, and the following operations are performed on the extracted defect regions. The defect regions are characterized to obtain defect region parameters. To determine the defect condition of the defect regions, the defect region parameters are compared with the preset defect threshold to obtain a defect deviation value. The defect condition of the defect region is determined according to the defect deviation value, wherein the defect condition is an irreparable defect, a repairable defect, or an acceptable defect. If there is an irreparable defect or a repairable defect in the defect condition of all defect regions, a material test file is obtained based on the defect condition. If the defect condition of all defect regions is an acceptable defect, the high polymer material can be confirmed as a preliminary qualified material. To measure the material durability of the preliminary qualified material, the preliminary qualified material is placed in a pre-constructed test container for accelerated aging test to obtain an aging test material. The aging test material is subjected to image detection, and the defect regions in the aging test material image are analyzed and identified. The defect regions are compared with the detected defect regions to obtain a defect region expansion value. The defect expansion value can reflect the change amplitude of the defect region. Therefore, the material detection result can be obtained according to the defect region expansion value, wherein the material detection result is durability compliance or durability non-compliance. If the material detection result is durability compliance, the preliminary qualified material is marked as a target qualified material, and a material test file is generated. If the material detection result is durability non-compliance, the preliminary qualified material is marked as a non-compliant material, and a material test file is generated. Based on the material test file, the high polymer material test based on image analysis is completed. Therefore, the application can solve the problem of low test result accuracy in the current high polymer material test process.

[0189] As Figure 2 shown, it is a functional module diagram of the high polymer material test system based on image analysis provided by an embodiment of the application.

[0190] The image analysis based polymer material inspection system 100 can be installed in an electronic device. According to the implemented functions, the image analysis based polymer material inspection system 100 can include an environment confirmation module 101, an image processing module 102, a defect determination module 103, and a durability test module 104. The modules in the present application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete a fixed function, which are stored in the memory of the electronic device.

[0191] The environment confirmation module 101 is configured to confirm a polymer material inspection environment, wherein the polymer material inspection environment includes a polymer material to be detected, an image acquisition unit, and an image processing unit.

[0192] The image processing module 102 is configured to acquire an image of the polymer material by using the image acquisition unit, to obtain a polymer material image, to perform a pre-processing operation on the polymer material image to obtain a pre-processed material image, and to identify a set of defect regions in the pre-processed material image by using the image processing unit.

[0193] The defect determination module 103 is configured to sequentially extract a defect region from the set of defect regions and perform the following operations on the extracted defect region: extracting a feature of the defect region to obtain a defect region parameter, comparing the defect region parameter with a preset defect threshold to obtain a defect deviation value, and determining a defect condition of the defect region according to the defect deviation value, wherein the defect condition is an irreparable defect, a repairable defect, or an acceptable defect. If the defect condition includes an irreparable defect or a repairable defect, a material inspection file is obtained based on the defect condition. If the defect condition is an acceptable defect, the polymer material is confirmed as a preliminary qualified material.

[0194] The durability test module 104 is configured to place the preliminary qualified material in a pre-constructed test container for accelerated aging test to obtain an aging test material, to perform image detection on the aging test material to obtain a detected defect region, to compare the defect region with the detected defect region to obtain a defect region expansion value, and to obtain a material detection result according to the defect region expansion value, wherein the material detection result is durability compliance or durability non-compliance. If the material detection result is durability compliance, the preliminary qualified material is marked as a target qualified material, and a material inspection file is generated. If the material detection result is durability non-compliance, the preliminary qualified material is marked as a non-compliant material, and a material inspection file is generated.

[0195] In detail, the modules in the image analysis based polymer material inspection system 100 in the embodiments of the present application are used as described above. Figure 1The image analysis-based polymer material inspection method and the electronic device provided by the present application have the same technical means and can achieve the same technical effects, and thus details are not described herein.

[0196] As shown in Figure 3 FIG. 1 is a structural schematic diagram of an electronic device for implementing an image analysis-based polymer material inspection method according to an embodiment of the present application.

[0197] The electronic device 1 can include a processor 10, a memory 11 and a bus 12, and can further include a computer program stored in the memory 11 and executable on the processor 10, such as an image analysis-based polymer material inspection method program.

[0198] The memory 11 includes at least one type of readable storage medium, such as a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 11 includes both an internal storage unit and an external storage device of the electronic device 1. The memory 11 can be used not only to store application software and various data installed in the electronic device 1, such as the code of the image analysis-based polymer material inspection method program, but also to temporarily store data that has been output or will be output.

[0199] The processor 10 can be composed of an integrated circuit in some embodiments, such as a single packaged integrated circuit or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors and combinations of various control chips, etc. The processor 10 is the control core of the electronic device, which connects various components of the electronic device through various interfaces and lines, executes or runs programs or modules stored in the memory 11 (such as the image analysis-based polymer material inspection method program, etc.), and calls data stored in the memory 11 to perform various functions and process data of the electronic device 1.

[0200] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to enable connection and communication between the memory 11, the at least one processor 10, etc.

[0201] Figure 3 Only the electronic device with components is shown, and those skilled in the art can understand that, Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and can include fewer or more components than shown, or combine certain components, or different component arrangements.

[0202] For example, although not shown, the electronic device 1 can also include a power supply (such as a battery) to power each component. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, so that the power management device can implement functions such as charge management, discharge management, and power consumption management. The power supply can also include one or more direct current or alternating current power supplies, recharging devices, power supply fault detection circuits, power supply converters or inverters, power supply status indicators, etc. The electronic device 1 can also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which are not described here.

[0203] Further, the electronic device 1 can also include a network interface, which can optionally include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), and is typically used to establish a communication connection between the electronic device 1 and other electronic devices.

[0204] Optionally, the electronic device 1 can also include a user interface, which can be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally a standard wired interface, a wireless interface. Optionally, in some embodiments, the display can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, etc. The display can also be appropriately referred to as a display screen or a display unit, and is used to display information processed in the electronic device 1 and to display a visualized user interface.

[0205] The image analysis-based polymer material inspection method program stored in the memory 11 in the electronic device 1 is a combination of multiple instructions, which, when running in the processor 10, can realize:

[0206] Confirming a polymer material inspection environment, wherein the polymer material inspection environment includes: a polymer material to be detected, an image acquisition unit, and an image processing unit;

[0207] Using the image acquisition unit to perform image acquisition on the polymer material to obtain a polymer material image;

[0208] Performing a preprocessing operation on the polymer material image to obtain a preprocessed material image;

[0209] Using the image processing unit to identify a set of defect regions in the preprocessed material image;

[0210] Sequentially extracting defect regions from the set of defect regions, and performing the following operations on the extracted defect regions;

[0211] Performing feature extraction on the defect regions to obtain defect region parameters;

[0212] Comparing the defect region parameters with a preset defect threshold to obtain a defect deviation value;

[0213] Determining a defect condition of the defect regions according to the defect deviation value, wherein the defect condition is an irreparable defect, a repairable defect, or an acceptable defect;

[0214] If the defect condition includes an irreparable defect or a repairable defect, obtaining a material inspection file based on the defect condition;

[0215] If the defect condition is an acceptable defect, confirming the polymer material as a preliminary qualified material;

[0216] Placing the preliminary qualified material in a pre-constructed test container for accelerated aging testing to obtain an aging test material;

[0217] Performing image detection on the aging test material to obtain a detected defect region;

[0218] Comparing the defect region with the detected defect region to obtain a defect region expansion value;

[0219] Obtaining a material detection result according to the defect region expansion value, wherein the material detection result is durability compliance or durability non-compliance;

[0220] If the material detection result is durability compliance, marking the preliminary qualified material as a target qualified material and generating a material inspection file;

[0221] If the material detection result is that the durability is not up to standard, the preliminarily qualified material is marked as unqualified material, and a material inspection file is generated;

[0222] According to the material inspection file, the high polymer material inspection based on image analysis is completed.

[0223] Specifically, the specific implementation method of the processor 10 to the above instructions can refer to Figures 1 to 3 The description of related steps in the corresponding embodiments will not be repeated here.

[0224] Further, the modules / units integrated in the electronic device 1, if realized in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. The computer readable storage medium can be volatile or non-volatile. For example, the computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory).

[0225] The application also provides a computer readable storage medium, the readable storage medium stores a computer program, the computer program can realize the following when being executed by the processor of the electronic device:

[0226] Confirm the high polymer material inspection environment, wherein the high polymer material inspection environment includes: high polymer material to be detected, an image acquisition unit, and an image processing unit;

[0227] The image acquisition unit is used to acquire images of the high polymer material to obtain high polymer material images;

[0228] The high polymer material images are preprocessed to obtain preprocessed material images;

[0229] The image processing unit is used to identify a set of defect regions in the preprocessed material images;

[0230] The defect regions are sequentially extracted from the set of defect regions, and the following operations are performed on the extracted defect regions;

[0231] The defect regions are subjected to feature extraction to obtain defect region parameters;

[0232] The defect region parameters are compared with preset defect thresholds to obtain defect deviation values;

[0233] According to the defect deviation values, the defect conditions of the defect regions are determined, wherein the defect conditions are unrepairable defects, repairable defects, or acceptable defects;

[0234] if the defect condition is an unrepairable defect or a repairable defect, obtaining a material inspection record based on the defect condition;

[0235] if the defect condition is an acceptable defect, confirming the high polymer material as a preliminary qualified material;

[0236] placing the preliminary qualified material in a pre-constructed test container for an accelerated aging test to obtain an aging test material;

[0237] performing image detection on the aging test material to obtain a detected defect area;

[0238] comparing the defect area with the detected defect area to obtain a defect area expansion value;

[0239] obtaining a material detection result according to the defect area expansion value, wherein the material detection result is durability compliance or durability non-compliance;

[0240] if the material detection result is durability compliance, marking the preliminary qualified material as a target qualified material and generating a material inspection record;

[0241] if the material detection result is durability non-compliance, marking the preliminary qualified material as a non-compliant material and generating a material inspection record;

[0242] completing high polymer material inspection based on image analysis according to the material inspection record.

[0243] In several embodiments provided in the present application, it should be understood that the disclosed devices, systems and methods can be implemented in other manners. For example, the above-described system embodiments are merely illustrative; actual implementation can have different divisions.

[0244] The modules described as separate components can or can not be physically separated, and the components shown as modules can or can not be physical units, i.e., they can be located in one place or distributed to multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment.

[0245] In addition, each functional module in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional modules.

[0246] It is apparent for a person skilled in the art that the application is not limited to the details of the above-described exemplary embodiments, but that the application can be implemented in other concrete forms without departing from the spirit or essential characteristics of the application.

[0247] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application but not to limit the present application, and although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced without departing from the spirit and scope of the present application.

Claims

1. A method for inspecting a high molecular material based on image analysis, characterized by, The method comprises: Confirming a high polymer material inspection environment, wherein the high polymer material inspection environment comprises: a high polymer material to be detected, an image acquisition unit, and an image processing unit; Image acquisition is performed on the high polymer material by using the image acquisition unit to obtain a high polymer material image; Pretreatment is performed on the high polymer material image to obtain a pretreated material image; Defect area sets are identified in the pretreated material image by using the image processing unit; Defect areas are sequentially extracted from the defect area sets, and the following operations are performed on the extracted defect areas; Feature extraction is performed on the defect areas to obtain defect area parameters; The defect area parameters are compared with preset defect thresholds to obtain defect deviation values; The defect conditions of the defect areas are determined according to the defect deviation values, wherein the defect conditions are unrepairable defects, repairable defects, or acceptable defects; If the defect conditions include unrepairable defects or repairable defects, a material inspection file is obtained based on the defect conditions; If the defect conditions are all acceptable defects, the high polymer material is confirmed as a preliminary qualified material; The preliminary qualified material is placed in a pre-constructed test container for accelerated aging test to obtain an aging test material; Image detection is performed on the aging test material to obtain detected defect areas; The defect areas are compared with the detected defect areas to obtain defect area expansion values; A material detection result is obtained according to the defect area expansion values, wherein the material detection result is durability compliance or durability non-compliance; If the material detection result is durability compliance, the preliminary qualified material is marked as a target qualified material, and a material inspection file is generated; If the material detection result is durability non-compliance, the preliminary qualified material is marked as a non-compliant material, and a material inspection file is generated; The high polymer material inspection based on image analysis is completed according to the material inspection file.

2. The image analysis-based polymer material inspection method according to claim 1, wherein The pretreatment of the high polymer material image to obtain a pretreated material image comprises: Gray processing is performed on the high polymer material image to obtain a gray-processed image; Noise identification is performed on the gray-processed image to obtain noise types; A filter algorithm is obtained according to the noise types; Noise removal is performed on the gray-processed image by using the filter algorithm to obtain a noise-reduced image; Edge-preserving filter processing is performed on the noise-reduced image to obtain an edge-enhanced image; Non-material area images in the edge-enhanced image are removed to obtain the pretreated material image.

3. The image analysis-based polymer material inspection method according to claim 2, wherein The gray processing of the high polymer material image to obtain a gray-processed image comprises: An RGB three-channel pixel value set of the high polymer material image is obtained, wherein the RGB three-channel pixel value set refers to a collection of RGB three-channel pixel values of all pixel points in the high polymer material image, and the RGB three-channel pixel values include red channel pixel values, green channel pixel values, and blue channel pixel values; RGB three-channel pixel values are sequentially extracted from the RGB three-channel pixel value set; The RGB three-channel pixel values are converted into gray values by using a pre-constructed gray conversion formula, wherein the gray conversion formula is as follows: wherein, represents a gray value, represents a red channel pixel value of a pixel point, represents a green channel pixel value of a pixel point, represents a blue channel pixel value of a pixel point, , , respectively represent a preset weight coefficient of a red channel pixel value, a weight coefficient of a green channel pixel value, and a weight coefficient of a blue channel pixel value. mapping the gray value to a preset gray value interval to obtain a standard gray value; converting the high polymer material image into a gray processing image according to the standard gray value.

4. The image analysis-based polymer material inspection method according to claim 3, wherein The image processing unit is used to identify a defect region set in the preprocessed material image, including: extracting a gray value set of the preprocessed material image by using the image processing unit; confirming a gray threshold set in the gray value set; calculating an optimal gray threshold according to the gray threshold set and a pre-constructed threshold calculation formula, wherein the threshold calculation formula is as follows: wherein, represents the optimal gray scale threshold value, represents the proportion of the pixel points with the gray scale value less than or equal to the gray scale threshold value in the total pixel points, represents the average value of the gray scale values corresponding to the pixel points with the gray scale value less than or equal to the gray scale threshold value, represents the average value of the gray scale values corresponding to all the pixel points, represents the proportion of the pixel points with the gray scale value greater than the gray scale threshold value in the total pixel points, represents the average value of the gray scale values corresponding to the pixel points with the gray scale value greater than the gray scale threshold value. confirming a local defect region set based on the preprocessed material image, wherein the local defect region set includes a plurality of local defect regions, and the gray value corresponding to each pixel point in the local defect region is greater than the optimal gray threshold; performing connectivity analysis on the local defect region set and identifying a defect region set, wherein the defect region set includes one or more defect regions, and the defect region includes one or more local defect regions.

5. The image analysis-based polymer material inspection method according to claim 4, wherein The feature extraction of the defect region includes: calculating the gray mean value of the pixel points in the defect region; performing geometric feature extraction on the defect region to obtain a geometric feature value; counting the total number of local defect regions in the defect region to obtain a branch number; detecting the number of holes in the defect region; calculating the difference between the branch number and the number of holes to obtain the Euler number; constructing the defect region parameter according to the gray mean value, the geometric feature value and the Euler number.

6. The image analysis-based polymer material inspection method according to claim 5, wherein, The geometric feature extraction of the defect region includes: determining the pixel area of the defect region and converting the pixel area into a defect area by using a preset pixel conversion ratio; extracting a boundary pixel point set of the defect region by using a preset boundary tracking algorithm; transforming the boundary pixel point set into an ordered boundary chain code by using a preset chain code encoding rule; extracting a first boundary chain code point from the ordered boundary chain code in sequence, and performing the following operations on the extracted first boundary chain code point; determining a second boundary chain code point in the ordered boundary chain code by using the first boundary chain code point, wherein the second boundary chain code point is adjacent and lagging behind the first boundary chain code point; calculating the Euclidean distance between the first boundary chain code point and the second boundary chain code point; accumulating the Euclidean distance to obtain a boundary perimeter; calculating the geometric feature value according to the defect area and the boundary perimeter.

7. The image analysis-based polymer material inspection method according to claim 6, wherein The comparison of the defect region parameter with a preset defect threshold value includes: performing standardization processing on the defect region parameter to obtain a standard defect region parameter; calculating a defect value according to the standard defect region parameter; comparing the defect value with the defect threshold value to obtain a defect deviation value.

8. The image analysis-based polymer material inspection method according to claim 7, wherein The determination of the defect condition of the defect region according to the defect deviation value includes: when the defect deviation value is less than a preset first deviation threshold value, confirming the defect condition as an acceptable defect; when the defect deviation value is greater than or equal to the first deviation threshold value and less than a preset second deviation threshold value, confirming the defect condition as a repairable defect; When the defect deviation value is greater than or equal to a second deviation threshold, the defect condition is confirmed as an unrepairable defect.

9. The image analysis-based polymer material inspection method according to claim 8, wherein, The preliminary qualified material is placed in a pre-constructed test container for an accelerated aging test, and an aging test material is obtained. An environmental parameter adjustment device is acquired. The test container is adjusted in parameters by using the environmental parameter adjustment device, and a test container set is obtained, wherein the test container set includes a first test container, a second test container, and a third test container, the temperature, humidity, and illumination of the first test container are respectively a preset test temperature, a standard humidity, and a standard illumination, the temperature, humidity, and illumination of the second test container are respectively a standard temperature, a preset test humidity, and a standard illumination, and the temperature, humidity, and illumination of the third test container are respectively a standard temperature, a standard humidity, and a preset test illumination. The preliminary qualified material is respectively placed in the first test container, the second test container, and the third test container, and is taken out after a preset time interval, and a preliminary aging test material set is obtained. Each preliminary aging test material in the preliminary aging test material set is subjected to an appearance integrity detection, and an appearance detection result is obtained, wherein the appearance detection result is with scratch damage or without scratch damage. If the appearance detection result is with scratch damage, a preset scratch prevention processing scheme is triggered, and the step of placing the preliminary qualified material in the first test container, the second test container, and the third test container is returned until the appearance detection result is without scratch damage. If the appearance detection result is without scratch damage, the preliminary aging test material is confirmed as an aging test material.

10. An image analysis-based polymer material inspection system, characterized by, The system comprises: An environment confirmation module is configured to confirm a high polymer material inspection environment, wherein the high polymer material inspection environment comprises a high polymer material to be detected, an image acquisition unit, and an image processing unit. An image processing module is configured to acquire an image of the high polymer material by using the image acquisition unit, to obtain a high polymer material image, to perform a preprocessing operation on the high polymer material image to obtain a preprocessed material image, and to identify a set of defect regions in the preprocessed material image by using the image processing unit. A defect determination module is configured to sequentially extract a defect region from the set of defect regions, and to perform the following operations on the extracted defect region: to extract a feature of the defect region to obtain a defect region parameter, to compare the defect region parameter with a preset defect threshold to obtain a defect deviation value, and to determine a defect condition of the defect region according to the defect deviation value, wherein the defect condition is an unrepairable defect, a repairable defect, or an acceptable defect, to acquire a material inspection file based on the defect condition if the defect condition includes the unrepairable defect or the repairable defect, and to confirm the high polymer material as a preliminary qualified material if the defect condition is the acceptable defect. The durability test module is used for placing the preliminary qualified material in a pre-built test container for accelerated aging test, obtaining an aging test material, performing image detection on the aging test material, obtaining a detection defect area, comparing the defect area with the detection defect area, obtaining a defect area expansion value, and obtaining a material detection result according to the defect area expansion value, wherein the material detection result is durability up to standard or durability not up to standard, if the material detection result is durability up to standard, the preliminary qualified material is marked as a target qualified material, and a material inspection file is generated, and if the material detection result is durability not up to standard, the preliminary qualified material is marked as a non-standard material, and a material inspection file is generated.

Images