A glass glue product inspection method and system

Abstract

The present application provides a glass glue product inspection method and system, which belongs to the field of glass glue product quality inspection. The method first obtains a polished infrared image of the glass glue product packaging, determines the surface damage information domain of the glass glue product based on the polished infrared image, performs a spot scan on the glass glue product to obtain a spot scatter diagram set of the glass glue product, determines the dynamic optical information domain of the glass glue product based on the spot scatter diagram set, determines the surface damage image corresponding to the glass glue product based on the surface damage information domain and the dynamic optical information domain, and finally inspects the glass glue product based on the surface damage image, that is, the surface damage image in the present application contains defect information in both the surface damage information domain and the dynamic optical information domain. By inspecting the glass glue product through the surface damage image, the position and shape of the surface damage can be accurately determined, thereby improving the accuracy of surface damage detection during the inspection process.

Description

Technical Field

[0001] The present application relates to the field of glass glue product quality inspection, and more specifically, to a glass glue product inspection method and system. Background Art

[0002] Glass glue is a material used to bond and seal various glasses to other substrates. It is mainly divided into two categories: silicone glue and polyurethane glue (PU). Silicone glue sealant is what we usually call glass glue, which is divided into acidic and neutral types. Neutral glue is further divided into: stone sealant, mildew-proof sealant, fireproof sealant, pipe sealant, etc.

[0003] Glass glue products are made by sealing the above-mentioned glass glue in a specific container and labeling it. In addition to testing the quality of the internal glass glue, the entire product packaging also needs to be tested. After the test is completed, it can be sold if there are no surface defects. In the prior art, when inspecting the packaging of glass glue products, surface damage (bubbles, scratches, bumps, pits, etc.) is not easy to be directly observed (this is because glass glue products are different from other products. The packaging is basically covered with a variety of different colors and a large amount of text descriptions). The detection effect using the existing AOI technology is not good. Therefore, how to improve the accuracy of surface damage detection during the inspection of glass glue products has become a problem that needs to be solved urgently. Because the full text only involves the inspection of packaging, the glass glue product inspection referred to in the full text refers to the inspection of the glass glue packaging. Summary of the invention

[0004] The present application provides a glass glue product inspection method and system, which can improve the accuracy of surface damage detection during the inspection process of the glass glue product.

[0005] In a first aspect, the present application provides a glass glue product inspection method, which can be executed by a network device, or can also be executed by a chip configured in the network device, and the present application does not limit this.

[0006] Specifically, the method includes:

[0007] Acquire a polished infrared image of a glass glue product, and determine a surface damage information domain of the glass glue product according to the polished infrared image;

[0008] Performing a light spot scan on the glass glue product to obtain a light spot scatter diagram set of the glass glue product, and determining a dynamic light connection information domain of the glass glue product according to the light spot scatter diagram set;

[0009] Determine a surface damage image corresponding to the glass glue product according to the surface damage information domain and the dynamic optical connection information domain;

[0010] The glass glue product is inspected according to the surface damage image.

[0011] In conjunction with the first aspect, in certain implementations of the first aspect, obtaining a polishing infrared image of a glass adhesive product specifically includes:

[0012] Collecting real-time infrared sub-images corresponding to different surface areas of the glass glue product;

[0013] The real-time infrared sub-images corresponding to different surface areas are stitched to obtain a polished infrared image of the glass glue product.

[0014] In combination with the first aspect, in certain implementations of the first aspect, determining the surface damage information domain of the glass glue product according to the polishing infrared image specifically includes:

[0015] determining surface flatness according to pixel distribution in the polishing infrared image;

[0016] The surface damage information domain of the glass glue product is determined based on the surface flatness and the polished infrared image.

[0017] In combination with the first aspect, in certain implementations of the first aspect, determining the surface flatness according to the pixel distribution in the polishing infrared image specifically includes:

[0018] According to a preset window size, the polishing infrared image is divided into a plurality of flatness monitoring domains;

[0019] The surface flatness of the glass glue product is determined according to the image grayscale value in each flatness monitoring area.

[0020] In combination with the first aspect, in certain implementations of the first aspect, determining the surface damage information domain of the glass glue product based on the surface flatness and the polished infrared image specifically includes:

[0021] Determine a surface damage grayscale matrix of the polished infrared image;

[0022] Determining a surface damage characteristic threshold according to the surface flatness of the glass glue product;

[0023] The area in the surface damage grayscale matrix where the grayscale value is higher than the surface damage characteristic threshold is used as the surface damage information domain.

[0024] In combination with the first aspect, in some implementations of the first aspect, determining the dynamic optical information domain of the glass glue product according to the light spot scatter diagram set specifically includes:

[0025] Determine the dynamic light connection grayscale matrix of the glass glue product according to the light spot scatter diagram set;

[0026] A segmentation threshold is obtained, and the dynamic optical connection grayscale matrix is ​​segmented according to the segmentation threshold to obtain the dynamic optical connection information domain of the glass glue product.

[0027] In combination with the first aspect, in certain implementations of the first aspect, inspecting the glass glue product according to the surface damage image specifically includes:

[0028] Acquiring the surface damage image;

[0029] extracting image features from the surface damage image;

[0030] Defect detection and classification are performed on the image features, and whether the glass glue product is of qualified quality is determined based on the defect detection results.

[0031] In a second aspect, the present application provides a glass glue product inspection system, the glass glue product inspection system comprising:

[0032] An acquisition module, used to acquire a polished infrared image of a glass adhesive product;

[0033] A processing module, used for determining a surface damage information domain of the glass glue product according to the polishing infrared image;

[0034] The processing module is further used to perform a light spot scan on the glass glue product to obtain a light spot scatter diagram set of the glass glue product, and determine a dynamic light connection information domain of the glass glue product according to the light spot scatter diagram set;

[0035] The processing module is further used to determine the surface damage image corresponding to the glass glue product according to the surface damage information domain and the dynamic optical connection information domain;

[0036] An inspection module is used to inspect the glass glue product according to the surface damage image.

[0037] In a third aspect, the present application provides a computer terminal device, which includes a memory and a processor, wherein the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned glass glue product inspection method.

[0038] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one computer program, and the computer program is loaded and executed by a processor to implement the operations performed by the above-mentioned glass glue product inspection method.

[0039] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0040] In the glass glue product inspection method and system provided by the present application, first, a polished infrared image of the glass glue product is obtained, and the surface damage information domain of the glass glue product is determined according to the polished infrared image, and a spot scan is performed on the glass glue product to obtain a spot scatter diagram set of the glass glue product, and a dynamic optical information domain of the glass glue product is determined according to the spot scatter diagram set, and a surface damage image corresponding to the glass glue product is determined according to the surface damage information domain and the dynamic optical information domain, and finally the glass glue product is inspected according to the surface damage image. That is, the present application determines a surface damage information domain containing surface defect information by detecting the abnormal surface temperature of the glass glue product, and then determines the dynamic optical information domain containing surface damage according to the abnormal spot scattering, and finally obtains a surface damage image according to the surface damage information domain and the dynamic optical information domain. The surface damage image contains defect information in both the surface damage information domain and the dynamic optical information domain, and can accurately determine the position and shape of the surface damage, thereby improving the accuracy of surface damage detection during the inspection process. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 is an exemplary flow chart of a glass glue product inspection method according to some embodiments of the present application;

[0042] Figure 2 is a schematic diagram of the trajectory of spot scanning on a glass glue product in some embodiments of the present application;

[0043] Figure 3 is a schematic diagram of a process for determining the dynamic optical information domain of the glass glue product in some embodiments of the present application;

[0044] Figure 4 is a schematic diagram of exemplary hardware and / or software of a glass glue product inspection system according to some embodiments of the present application;

[0045] Figure 5 It is a structural schematic diagram of a computer terminal device for implementing a glass glue product inspection method according to some embodiments of the present application. DETAILED DESCRIPTION

[0046] The present application obtains a polished infrared image of a glass glue product, determines a surface damage information domain of the glass glue product based on the polished infrared image, performs a spot scan on the glass glue product to obtain a spot scatter diagram set of the glass glue product, determines a dynamic optical information domain of the glass glue product based on the spot scatter diagram set, determines a surface damage image corresponding to the glass glue product based on the surface damage information domain and the dynamic optical information domain, and finally inspects the glass glue product based on the surface damage image. The surface damage image contains defect information in both the surface damage information domain and the dynamic optical information domain, and can accurately determine the position and shape of the surface damage, thereby improving the accuracy of surface damage detection during the inspection process.

[0047] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of a glass glue product inspection method according to some embodiments of the present application, and the glass glue product inspection method 100 mainly includes the following steps:

[0048] In step S101, a polished infrared image of a glass adhesive product is acquired, and a surface damage information domain of the glass adhesive product is determined according to the polished infrared image.

[0049] It should be noted that the polishing infrared image is an infrared image of the surface of the glass glue product after the polishing process. The pixel points of the infrared image reflect the surface temperature of the glass glue product. In specific implementation, the polishing infrared image of the glass glue product can be obtained by an infrared camera or an infrared thermal imager. In some other embodiments, other devices or equipment that can realize infrared image acquisition can also be used, which is not limited here.

[0050] Optionally, in some embodiments, obtaining a polished infrared image of a glass adhesive product may be achieved by using the following steps:

[0051] Collecting real-time infrared sub-images corresponding to different surface areas of the glass glue product;

[0052] The real-time infrared sub-images corresponding to different surface areas are stitched to obtain a polished infrared image of the glass glue product.

[0053] It should be noted that the real-time infrared sub-image is an image of a partial area of ​​the surface of the glass glue product obtained by collecting an infrared sensor after being polished by a polishing head. The image size of the real-time infrared sub-image is usually calibrated as a constant according to the size of the polishing head used. In the present application, the polished infrared image of the glass glue product is obtained by stitching the real-time infrared sub-images corresponding to different surface areas, which can improve the clarity of the image details of the polished infrared image and avoid the phenomenon of excessive temperature difference between different surface areas.

[0054] Preferably, in some embodiments, determining the surface damage information domain of the glass glue product according to the polishing infrared image can be achieved by using the following steps:

[0055] determining surface flatness according to pixel distribution in the polishing infrared image;

[0056] The surface damage information domain of the glass glue product is determined based on the surface flatness and the polished infrared image.

[0057] In some embodiments, the surface flatness is used to quantify the flatness of the surface area of ​​the glass glue product, and is determined based on the uniformity of the surface temperature of the glass glue product after polishing. The larger the surface flatness, the flatter the surface area of ​​the glass glue product. Therefore, during the processing of the glass glue product, the sheet must first undergo a sawing process, and then a polishing process to remove the damage caused by sawing and produce a smoother surface. During the polishing process, the friction between the polishing head and the surface of the glass glue product (especially when a metal bottle is used) will generate heat. Since the flatter the surface of the glass glue product, the more uniform the heat generated by the friction with the polishing head is distributed. Therefore, during the glass glue product inspection process, the surface flatness of the glass glue product packaging can be inspected based on the heat uniformity and divergence of the surface of the glass glue product after polishing.

[0058] In some embodiments, determining the surface flatness according to the pixel distribution in the polishing infrared image can be achieved by the following steps:

[0059] According to a preset window size, the polishing infrared image is divided into a plurality of flatness monitoring domains;

[0060] The surface flatness of the glass glue product is determined according to the image grayscale value in each flatness monitoring area. In specific implementation, the surface flatness of the glass glue product can be determined according to the following formula:

[0061]

[0062] in, is the surface flatness of the glass glue product, is the number of flatness windows, The polished infrared image The grayscale mean value within the flatness window is For the The number of pixels in the smoothness window, For the The first The gray value of a pixel.

[0063] It should be noted that the flatness monitoring domain is a partial area of ​​the polishing infrared image. By dividing the polishing infrared image into multiple flatness monitoring domains, the detection accuracy of the surface detection of the glass glue product can be improved.

[0064] Optionally, in some embodiments, determining the surface damage information domain of the glass glue product based on the surface flatness and the polished infrared image can be achieved by using the following steps:

[0065] Determine a surface damage grayscale matrix of the polished infrared image;

[0066] Determining a surface damage characteristic threshold according to the surface flatness of the glass glue product;

[0067] The area in the surface damage grayscale matrix where the grayscale value is higher than the surface damage characteristic threshold is used as the surface damage information domain.

[0068] In specific implementation, the surface damage information domain includes the surface damage grayscale value and its corresponding coordinate position. In some embodiments, a three-dimensional array is used to represent the dynamic light link information domain, and each dimension is composed of a dynamic light link grayscale value and the horizontal and vertical coordinates corresponding to the dynamic light link grayscale value. The dynamic light link grayscale value reflects the degree of surface defects, and the horizontal and vertical coordinates corresponding to the dynamic light link grayscale value represent the two-dimensional position of the defect on the surface of the glass glue product.

[0069] In some embodiments, the surface damage characteristic threshold can be determined by normalizing the surface flatness and then multiplying it by a preset initial surface damage characteristic threshold. Thus, when the surface flatness of the glass glue product is high, the range of the surface damage information domain is reduced by the surface flatness, thereby improving the detection accuracy of surface defects of the glass glue product.

[0070] It should be noted that the surface damage grayscale matrix is ​​composed of surface damage grayscale values ​​at different positions on the surface of the glass glue product. The surface damage grayscale value reflects the degree of surface heat abnormality of the glass glue product at that position. Specifically, when the grayscale of the pixel at that position is low, it usually indicates that the friction between the glass glue product on the surface and the polishing head is weak due to the presence of depressions or cracks, resulting in a low temperature rise at that location. When the grayscale of the pixel at that location is high, it indicates that the glass glue product may have micro-bulges on the surface at that location, resulting in excessive friction with the polishing head. Therefore, the surface damage grayscale matrix is ​​used to identify defective parts on the surface of the glass glue product. In specific implementation, the number of rows and columns of the surface damage grayscale matrix can be the same as the image size of the polishing infrared image.

[0071] Preferably, in some embodiments, the surface damage grayscale matrix is ​​a reconstructed image matrix of the polishing infrared image, and determining the surface damage grayscale matrix of the polishing infrared image can be achieved by the following steps:

[0072] Obtaining the grayscale value of each pixel in the polished infrared image of the glass glue product;

[0073] According to the grayscale value of each pixel point in the polished infrared image of the glass glue product, the surface damage grayscale matrix of the polished infrared image is determined, wherein each surface damage grayscale value in the surface damage grayscale matrix of the polished infrared image is determined according to the following formula:

[0074]

[0075] in, is the surface damage grayscale value of the ath row and bth column in the surface damage grayscale matrix, is the gray value of the pixel at the ath row and the bth column in the polished infrared image, is the grayscale mean of all pixels in the decimated neighborhood centered on the pixel at the ath row and bth column in the polished infrared image, is the number of grayscale values ​​of pixels in the removed-center neighborhood. In some embodiments, the number of grayscale values ​​of pixels in the removed-center neighborhood is preset to 80.

[0076] In step S102, the glass glue product is subjected to a light spot scan to obtain a light spot scatter diagram set of the glass glue product, and a dynamic light connection information domain of the glass glue product is determined according to the light spot scatter diagram set.

[0077] In a specific implementation, a laser emitter can be used to emit a visible light beam to achieve spot scanning of the glass glue product. The laser emitter is located above the glass glue product, and the position of the laser emitter is adjusted by controlling an air cushion guide rail to achieve spot scanning of the glass glue product.

[0078] Optionally, in some embodiments, a spiral scanning path is used to perform spot scanning on the glass glue product, referring to Figure 2 As shown in the figure, it is a schematic diagram of the trajectory of spot scanning on the glass glue product in some embodiments of the present application. The spiral scanning path is implemented by establishing a polar coordinate system on the surface of the glass glue product with the rotation center O of the spin mechanism as the coordinate origin and the translation speed direction as the polar axis direction. The detection spot starts from the center O of the glass glue product and moves along the positive direction of the polar axis at a translation speed V, and at the same time at an angular speed It rotates around point O and eventually forms a spiral scanning path on the detection surface.

[0079] Optionally, in some embodiments, a photodetector array located below the glass glue product can be used to detect and record the outgoing light intensity of different areas of the glass glue product, and the collected light intensity data is mapped into an image grayscale matrix according to the position information. The complete light spot scatter diagram is determined by the image grayscale matrix, and then the power of the laser transmitter is adjusted. The light spot scatter diagrams corresponding to different powers are sequentially organized into the light spot scatter diagram set according to the power size in the same way.

[0080] It should be noted that, according to the MIE scattering theory, the exact solution to the scattered field intensity distribution generated by a uniform dielectric sphere of any diameter or material excited by an incident electromagnetic field can be calculated from the Maxwell equations under specific boundary conditions. Therefore, when the medium at a certain point in the glass glue product is uniform, the outgoing light intensity of the visible light spot emitted by the laser emitter should be directly proportional to the laser emitter power (incident light intensity). Therefore, when the laser emitter power rises uniformly, there is a phenomenon that the outgoing light intensity at a certain position in the light spot scatter diagram set has a low correlation with the laser emitter power, or there is an abnormal jump in the light intensity of a pixel point at a certain point in the light spot scatter diagram set. It can be judged that there may be surface damage including surface bubbles that affects the scattering light path of the incident light. The dynamic optical information domain is the area where surface damage may exist inside the marked glass glue product.

[0081] In some embodiments, reference Figure 3 As shown, this figure is a schematic diagram of a process for determining the dynamic optical information domain of the glass glue product in some embodiments of the present application. The dynamic optical information domain of the glass glue product can be determined according to the set of light spot scatter diagrams by using the following steps:

[0082] In step 1021, a dynamic light connection grayscale matrix of the glass glue product is determined according to the light spot scatter diagram set;

[0083] In step 1022, a segmentation threshold is obtained, and the dynamic optical connection grayscale matrix is ​​segmented according to the segmentation threshold to obtain the dynamic optical connection information domain of the glass glue product.

[0084] It should be noted that the dynamic light-link grayscale matrix is ​​composed of various dynamic light-link grayscale values, and in order to facilitate comparison and distinction of the surface damage area of ​​the glass glue product, the dynamic light-link grayscale matrix and the surface damage grayscale matrix have the same number of rows and columns. In some embodiments, the surface damage grayscale matrix is ​​a reconstructed image matrix of the light spot scatter diagram. In specific implementation, the dynamic light-link grayscale matrix is ​​determined according to the following formula:

[0085]

[0086] in, is the dynamic light link grayscale value of the ath row and bth column in the dynamic light link grayscale matrix, is the gray value of the pixel in the ath row and bth column of the zth spot scatter diagram in the spot scatter diagram set, is the gray value of the pixel in the ath row and bth column of the z-1th spot scatter diagram in the spot scatter diagram set, is the zth power difference, MAX[ ] is the maximum value function, z is the independent variable of the maximum value function, and in specific implementation, the value range of the independent variable of the maximum value function is determined according to the number of spot scatter diagrams in the spot scatter diagram set, which will not be repeated here.

[0087] In specific implementation, the average of all dynamic light link grayscale values ​​in the dynamic light link grayscale matrix can be used as the segmentation threshold, and the matrix area higher than the segmentation threshold can be used as the dynamic light link information domain. It should be noted that the dynamic light link information domain includes the dynamic light link grayscale value and its corresponding coordinate position. In some embodiments, a three-dimensional array is used to represent the dynamic light link information domain, and each dimension is composed of a dynamic light link grayscale value and the horizontal and vertical coordinates corresponding to the dynamic light link grayscale value, wherein the dynamic light link grayscale value represents the degree of surface damage, and the horizontal and vertical coordinates corresponding to the dynamic light link grayscale value represent the two-dimensional position of the surface damage inside the glass glue product.

[0088] In step S103, a surface damage image corresponding to the glass glue product is determined according to the surface damage information field and the dynamic optical connection information field.

[0089] It should be noted that the surface damage image is an image obtained by enhancing the area where surface damage may exist inside the glass glue product according to the degree of damage in the surface image of the glass glue product. Defect features are extracted and classified based on the surface damage image, which can improve the accuracy of surface damage detection during the inspection of the glass glue product.

[0090] In some embodiments, according to the surface damage information field and the dynamic optical link information field, determining the surface damage image corresponding to the glass glue product can be achieved by using the following steps:

[0091] Obtaining an image damage domain according to the surface damage information domain and the dynamic light connection information domain;

[0092] Obtain the surface image of the glass glue product;

[0093] The surface image of the glass glue product is damaged and enhanced according to the image damage domain to obtain a surface damage image.

[0094] Optionally, in some embodiments, before obtaining the image damage domain based on the surface damage information domain and the dynamic optical link information domain, the method also includes: normalizing the surface damage grayscale value in the surface damage information domain, and normalizing the dynamic optical link grayscale value in the dynamic optical link information domain.

[0095] Preferably, in some embodiments, obtaining the image damage domain according to the surface damage information domain and the dynamic light link information domain can be achieved by adopting the following steps:

[0096] Using the dynamic optical information domain as the initial image damage domain;

[0097] The overlapping part of the surface damage information domain and the dynamic optical information domain is used as a correction region, and the coefficients in the correction region are corrected to obtain an image damage domain.

[0098] In some embodiments, correcting the coefficients in the correction area includes: correcting the dynamic light connection grayscale value at the same coordinate position according to the surface damage grayscale value in the correction area. In specific implementation, the dynamic light connection grayscale value at the same position coordinate in the correction area can be subtracted from the surface damage grayscale value, and all negative results are set to zero to obtain the image damage domain, which includes the damage domain value and the corresponding position coordinates. In some embodiments, a three-dimensional array is used to represent the image damage domain, and each dimension is composed of a damage domain value and the horizontal and vertical coordinates corresponding to the damage domain value (damage coordinates).

[0099] It should be noted that the surface defects of the glass glue product will affect the scattering process of the incident light spot, and thus affect the accuracy of the dynamic light connection information domain. For example, surface cracks will reduce the correlation between the incident light intensity and the outgoing light intensity at a certain point, resulting in detection interference caused by surface area defects in the dynamic light connection information domain. For example, a sudden change in the grayscale value at a certain point in the light spot scatter diagram is completely caused by the surface defects of the glass glue product, and not the internal medium unevenness caused by surface damage. Therefore, it is necessary to correct the image damage domain according to the surface defects of the glass glue product. The present application corrects the dynamic light connection grayscale value at the same coordinate position by the surface damage grayscale value in the correction area to obtain the damage domain value, and enhances the damage of the surface image of the glass glue product according to the damage domain values ​​at different coordinate positions. This can avoid the interference of surface defects of the glass glue product on surface damage detection and improve the accuracy of surface damage detection during the inspection of the glass glue product.

[0100] Preferably, in some embodiments, the surface image of the glass glue product is enhanced according to the image damage domain to obtain the surface damage image, which can be achieved by the following steps:

[0101] Acquire a first damage domain value and a first damage coordinate in the image damage domain;

[0102] Determine a first pixel point to be enhanced in the surface image of the glass adhesive product according to the first damage coordinates, and perform pixel enhancement on the first pixel point to be enhanced according to the first damage threshold value;

[0103] Acquire a second damage domain value and a second damage coordinate in the image damage domain;

[0104] Determine a second pixel point to be enhanced in the surface image of the glass adhesive product according to the second damage coordinates, and perform pixel enhancement on the second pixel point to be enhanced according to the second damage threshold;

[0105] The remaining damage domain values ​​and damage coordinates in the damage domain of the image are obtained, and the above steps are repeated until pixel enhancement is completed for all pixels to be enhanced, thereby obtaining a surface damage image.

[0106] In some embodiments, the damage domain value can be used as an enhancement coefficient to enhance the grayscale value of the pixel to be enhanced. The larger the damage domain value, the greater the degree of surface damage at that location, and the larger the proportional coefficient for enhancing the grayscale value of the pixel to be enhanced, so that the pixel at that location in the surface image obtained after image enhancement is more prominent, thereby improving the accuracy of image feature comparison of surface damage during glass glue product inspection.

[0107] In step S104, the glass adhesive product is inspected according to the surface damage image.

[0108] Preferably, in some embodiments, inspecting the glass glue product according to the surface damage image can be achieved by using the following steps:

[0109] Acquiring the surface damage image;

[0110] extracting image features from the surface damage image;

[0111] Defect detection and classification are performed on the image features, and whether the glass glue product is of qualified quality is determined based on the defect detection results.

[0112] In specific implementation, the SIFT (Scale Invariant Feature Transform) method can be used to extract key points and descriptors in the image as image features. For example, the SIFT algorithm detects key points in the image at different scales and directions, and calculates the descriptors of these key points to describe the local features of the surrounding areas, and then performs feature matching with preset feature descriptors to achieve detection of image features. In some embodiments, the SIFT descriptors extracted from the surface damage image can be obtained and matched with standard defect features such as surface bubbles, scratches, protrusions, pits, surface microcracks, dislocations and stacking faults preset in the feature library, thereby achieving detection and classification of image features. When the detection finds that the number or severity of defects in the glass glue product is higher than the preset threshold, the glass glue product is judged to be unqualified, and the image features of the surface damage image are sent to the operator.

[0113] In addition, in another aspect of the present application, in some embodiments, the present application provides a glass glue product inspection system, referring to Figure 4, which is a schematic diagram of exemplary hardware and / or software of a glass glue product inspection system according to some embodiments of the present application, the glass glue product inspection system 200 includes: an acquisition module 201, a processing module 202 and an inspection module 203, which are described as follows:

[0114] Acquisition module 201, in some specific embodiments of the present application, acquisition module 201 is mainly used to acquire a polishing infrared image of a glass glue product;

[0115] Processing module 202, in some specific embodiments of the present application, processing module 202 is mainly used to determine the surface damage information domain of the glass glue product according to the polishing infrared image;

[0116] In addition, in some specific embodiments of the present application, the processing module 202 is further used to perform a light spot scan on the glass glue product to obtain a light spot scatter diagram set of the glass glue product, and determine a dynamic light connection information domain of the glass glue product according to the light spot scatter diagram set;

[0117] In addition, in some specific embodiments of the present application, the processing module 202 is further used to determine the surface damage image corresponding to the glass glue product according to the surface damage information domain and the dynamic optical connection information domain;

[0118] Inspection module 203: In some specific embodiments of the present application, the inspection module 203 is mainly used to inspect the glass glue product according to the surface damage image.

[0119] The above describes in detail an example of a glass glue product inspection method and system provided in an embodiment of the present application. It can be understood that in order to realize the above functions, the corresponding device includes a hardware structure and / or software module corresponding to executing each function.

[0120] Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed in this document, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function in the application is executed in hardware or in a computer software-driven hardware manner depends on the specific application and design constraints of the technical solution. Therefore, professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0121] In addition, the present application also provides a computer terminal device, which includes a memory and a processor, wherein the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned glass glue product inspection method.

[0122] In some embodiments, reference Figure 5 , which is a schematic diagram of the structure of a computer terminal device using a glass glue product inspection method according to some embodiments of the present application. The glass glue product inspection method in the above embodiment can be Figure 5 The computer terminal device 300 shown in the figure is implemented, and the computer terminal device 300 includes at least one communication bus 301, a communication interface 302, a processor 303 and a memory 304.

[0123] The processor 303 may be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more processors for controlling the execution of the glass glue product inspection method in the present application.

[0124] The communication bus 301 may include a pathway for transmitting information between the above-mentioned components.

[0125] The memory 304 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 304 may exist independently and be connected to the processor 303 via the communication bus 301. The memory 304 may also be integrated with the processor 303.

[0126] The memory 304 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 303. The processor 303 is used to execute the program code stored in the memory 304. The program code may include one or more software modules. The determination of the surface damage information domain in the above embodiment can be implemented by the processor 303 and one or more software modules in the program code in the memory 304.

[0127] The communication interface 302 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0128] Optionally, the computer terminal device 300 may further include a power supply 305 for providing power to various devices or circuits in the real-time computer terminal device.

[0129] In a specific implementation, as an embodiment, a computer terminal device may include multiple processors, each of which may be a single-CPU processor or a multi-CPU processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0130] The above-mentioned computer terminal device may be a general-purpose computer terminal device or a dedicated computer terminal device. In a specific implementation, the computer terminal device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer terminal device.

[0131] In addition, in other aspects of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores at least one computer program, and the computer program is loaded and executed by a processor to implement the operations performed by the above-mentioned glass glue product inspection method.

[0132] In summary, in the glass glue product inspection method and system provided by the present application disclosed in the embodiments of the present application, first, a polished infrared image of the glass glue product is obtained, and the surface damage information domain of the glass glue product is determined according to the polished infrared image, and a spot scan is performed on the glass glue product to obtain a spot scatter diagram set of the glass glue product, and the dynamic optical information domain of the glass glue product is determined according to the spot scatter diagram set, and the surface damage image corresponding to the glass glue product is determined according to the surface damage information domain and the dynamic optical information domain, and finally, the glass glue product is inspected according to the surface damage image, that is, the present application determines the surface damage information domain containing surface defect information through the abnormal surface temperature of the glass glue product, and then determines the dynamic optical information domain containing surface damage according to the abnormal spot scattering, and finally, the surface damage image is obtained according to the surface damage information domain and the dynamic optical information domain, and the surface damage image contains defect information in both the surface damage information domain and the dynamic optical information domain, which can accurately determine the position and morphology of the surface damage, thereby improving the accuracy of surface damage detection during the inspection process.

[0133] The above is only an embodiment of the present application, and the common knowledge such as the specific technical scheme or characteristics in the scheme is not described in detail here. It should be pointed out that for those skilled in the art, without departing from the technical scheme of the present application, several modifications and improvements can be made, which should also be regarded as the scope of protection of the present application, and these will not affect the effect of the implementation of the present application and the practicality of the patent.

[0134] The scope of protection claimed by this application shall be based on the content of its claims. The specific implementation methods and other records in the specification can be used to interpret the content of the claims. Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of the invention. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include these modifications and variations.

Claims

1. A glass glue product inspection method, characterized in that: include: Acquire a polished infrared image of a glass glue product, and determine a surface damage information domain of the glass glue product according to the polished infrared image; Performing a light spot scan on the glass glue product to obtain a light spot scatter diagram set of the glass glue product, and determining a dynamic light connection information domain of the glass glue product according to the light spot scatter diagram set; Determine a surface damage image corresponding to the glass glue product according to the surface damage information domain and the dynamic optical connection information domain; Inspecting the glass glue product according to the surface damage image; Wherein, determining the surface damage information domain of the glass glue product according to the polishing infrared image specifically includes: determining surface flatness according to pixel distribution in the polishing infrared image; Determining the surface damage information domain of the glass glue product based on the surface flatness and the polished infrared image; Wherein, determining the surface flatness according to the pixel distribution in the polishing infrared image specifically includes: According to a preset window size, the polishing infrared image is divided into a plurality of flatness monitoring domains; Determining the surface flatness of the glass glue product according to the image grayscale value in each flatness monitoring area; Wherein, determining the surface damage information domain of the glass glue product based on the surface flatness and the polished infrared image specifically includes: Determine a surface damage grayscale matrix of the polished infrared image; Determining a surface damage characteristic threshold according to the surface flatness of the glass glue product; The area in the surface damage gray matrix where the gray value is higher than the surface damage characteristic threshold is used as the surface damage information domain; Wherein, determining the dynamic optical information domain of the glass glue product according to the light spot scatter diagram set specifically includes: Determine the dynamic light connection grayscale matrix of the glass glue product according to the light spot scatter diagram set; Obtaining a segmentation threshold, segmenting the dynamic optical connection grayscale matrix according to the segmentation threshold, and obtaining a dynamic optical connection information domain of the glass glue product; The dynamic light connection grayscale matrix is ​​composed of each dynamic light connection grayscale value, and the dynamic light connection grayscale matrix is ​​determined according to the following formula: in, is the dynamic light link grayscale value of the ath row and bth column in the dynamic light link grayscale matrix, is the gray value of the pixel in the ath row and bth column of the zth spot scatter diagram in the spot scatter diagram set, is the gray value of the pixel in the ath row and bth column of the z-1th spot scatter diagram in the spot scatter diagram set, is the zth power difference, MAX[] is the maximum value function, and z is the independent variable of the maximum value function; Among them, a laser emitter is used to scan the light spot of the glass glue product, the position of the laser emitter is adjusted by air cushion guide control, and a photoelectric detector array is used to detect and record the outgoing light intensity of different areas of the glass glue product. The collected light intensity data is mapped to the image grayscale matrix according to the position information, and the complete light spot scatter diagram is determined by the image grayscale matrix. The power of the laser emitter is adjusted, and the light spot scatter diagrams corresponding to different powers are sequentially composed into the light spot scatter diagram set according to the power size.

2. The method according to claim 1, characterized in that Obtaining the polished infrared image of glass glue products specifically includes: Collecting real-time infrared sub-images corresponding to different surface areas of the glass glue product; The real-time infrared sub-images corresponding to different surface areas are stitched to obtain a polished infrared image of the glass glue product.

3. The method according to claim 1, characterized in that Inspecting the glass glue product according to the surface damage image specifically includes: Acquiring the surface damage image; extracting image features from the surface damage image; Defect detection and classification are performed on the image features, and whether the glass glue product is of qualified quality is determined based on the defect detection results.

4. A glass glue product inspection system, which uses the method described in any one of claims 1 to 3 to inspect glass glue products, characterized in that: The system includes: An acquisition module, used to acquire a polished infrared image of a glass adhesive product; A processing module, used for determining a surface damage information domain of the glass glue product according to the polishing infrared image; The processing module is further used to perform a light spot scan on the glass glue product to obtain a light spot scatter diagram set of the glass glue product, and determine a dynamic light connection information domain of the glass glue product according to the light spot scatter diagram set; The processing module is further used to determine the surface damage image corresponding to the glass glue product according to the surface damage information domain and the dynamic optical connection information domain; An inspection module is used to inspect the glass glue product according to the surface damage image.

5. A computer terminal device, characterized in that: The computer terminal device includes a memory and a processor, the memory stores a code, and the processor is configured to obtain the code and execute the glass glue product inspection method according to any one of claims 1 to 3.

6. A computer-readable storage medium storing at least one computer program, characterized in that: The computer program is loaded and executed by a processor to implement the operations performed by the glass glue product inspection method according to any one of claims 1 to 3.

Images