A method and system for coating

Abstract

This application relates to the field of glass manufacturing technology, and in particular to a coating method and system. Current glass coating systems typically use separate equipment for pre- and post-coating inspections, connected by a conveyor belt. Such systems require a high level of cleanliness in the factory environment. This application provides a coating method that includes performing a first defect inspection on the material to be inspected, coating the qualified material, performing a second defect inspection on the coated material to obtain a second inspection result, and classifying the coated material based on the second inspection result. This significantly reduces the cleanliness requirements of the production environment and lowers factory investment while ensuring accuracy and efficiency.

Description

Technical Field

[0001] This application relates to the field of glass preparation technology, and in particular to a coating method and system. Background Technology

[0002] Glass products are increasingly used in modern life, especially in the electronics industry. In the production of these glass products, which require high cleanliness, a lamination process is typically required before shipment. Traditionally, glass inspection, lamination, and post-lamination inspection are performed by multiple machines connected by a conveyor belt. To ensure that the products are not contaminated during transport, extremely high cleanliness standards are required for the factory.

[0003] With the rapid development of science and technology and industrial capabilities, glass products are increasingly used in electronic products, such as the most common mobile phone screens. Simultaneously, the quality requirements for glass products are becoming increasingly stringent, necessitating testing for light transmittance, uniformity, impurities, bubbles, and water ripples. Before leaving the factory, these glass products require a protective film to be applied to their surface to prevent scratches or dust particles from causing contamination. Furthermore, this protective film must not form air bubbles between the film and the glass. In traditional processing, glass quality inspection, film coating, and post-coating inspection are performed by multiple machines connected by conveyor belts. An additional cleaning process is required before coating, demanding a high level of cleanliness from the factory. Summary of the Invention

[0004] 1. Technical problems to be solved

[0005] Current glass coating systems typically use separate equipment for pre- and post-coating inspections, connected by a conveyor belt. This approach places high demands on the cleanliness of the factory environment. This application provides a coating method and system.

[0006] 2. Technical Solution

[0007] To achieve the above objectives, this application provides a coating method, which includes performing a first defect detection on the material to be tested, coating the qualified material, performing a second defect detection on the coated material to obtain a second detection result, and classifying the coated material according to the second detection result.

[0008] Another embodiment provided in this application is as follows: the first defect detection of the material to be tested includes placing the material to be tested, conveying the material to be tested to the testing and coating mechanism, visually aligning the material to be tested, and then performing the first defect detection on the material to be tested.

[0009] Another embodiment provided in this application is: the first defect detection includes detecting the uniformity, light transmittance, cracks, scratches, dust, glass shards, bubbles, fingerprints, watermarks, teeth, and openings of the material to be tested.

[0010] Another implementation method provided in this application is as follows: the uniformity and transmittance detection includes collecting a light source sample, collecting an image of the material to be detected, converting the light source sample into a first grayscale image, converting the image of the material to be detected into a second grayscale image, calculating the data difference image between the first grayscale image and the second grayscale image, performing threshold segmentation based on a preset value of the transmittance of the material to be detected and the data difference image to obtain a binarized image, calculating the connected components of the binarized image, obtaining the label matrix, state matrix and centroid matrix of different connected components, and judging the uniformity and transmittance after calculating the pixel mean value of the corresponding connected component region in the data difference image based on the state matrix.

[0011] Another implementation method provided in this application is as follows: the detection of cracks, scratches, dust, glass shards, bubbles, fingerprints, and watermarks includes setting a region of interest, acquiring a detection image of the material to be detected, converting the detection image into a third grayscale image, performing Gaussian filtering on the third grayscale image to smooth the image and remove interference to obtain a second image, using a local threshold segmentation algorithm to perform threshold segmentation on the second image to obtain a third image, performing edge detection on the third image to extract defect contour information, statistically analyzing the defect information based on the defect contour information, comparing the defect information with the detection standard to obtain all suspicious defects of the material to be detected, and determining whether the material to be detected is qualified.

[0012] Another implementation method provided in this application is as follows: the tooth edge and opening detection includes setting a mask, extracting the region of interest, multiplying the region of interest mask with the image of the material to be detected to obtain the region of interest image; performing Gaussian filtering on the region of interest image to obtain a fourth image, converting the fourth image into a fourth grayscale image, binarizing the information of the fourth grayscale image to obtain a second binarized image, obtaining the second connected component in the second binarized image, calculating the size of the second connected component, and comparing the calculation result with the detection standard value to determine whether the material to be detected is qualified.

[0013] Another embodiment provided in this application is: the second defect detection includes detecting bubbles and dust in the coating.

[0014] This application also provides a coating system corresponding to the coating method, including a feeding assembly line, a feeding mechanism, a coating inspection mechanism, a unloading mechanism, and a control and analysis mechanism; the feeding assembly line, the coating inspection mechanism, and the unloading mechanism are arranged sequentially; the feeding assembly line is connected to the control and analysis mechanism, the feeding mechanism is connected to the control and analysis mechanism, the coating inspection mechanism is connected to the control and analysis mechanism, and the unloading mechanism is connected to the control and analysis mechanism; the coating inspection mechanism is used to perform pre-coating inspection, coating, and post-coating inspection on the material, and transmit the data to the control and analysis mechanism.

[0015] Another embodiment provided in this application is: the detection and coating mechanism is multiple, and the feeding mechanism is a robotic arm.

[0016] Another embodiment provided in this application is as follows: the detection and coating mechanism includes a first image acquisition device, a second image acquisition device, and a coating machine. The first image acquisition device is connected to the control and analysis mechanism, the second image acquisition device is connected to the control and analysis mechanism, and the coating machine is connected to the control and analysis mechanism.

[0017] 3. Beneficial effects

[0018] Compared with the prior art, the beneficial effects of the coating method and system provided in this application are as follows:

[0019] The coating method provided in this application greatly reduces the cleanliness requirements of the production environment and reduces the investment of the factory while ensuring accuracy and efficiency.

[0020] The coating method provided in this application employs different detection algorithms for different defects, which greatly reduces the false detection rate.

[0021] The coating method provided in this application is an integrated method that combines detection, coating, and post-coating detection, reducing the chance of contamination and lowering the requirements for the factory environment; at the same time, in order to improve efficiency, a multi-station parallel solution is designed.

[0022] The coating method provided in this application improves production efficiency because it involves multiple coating detection mechanisms operating in parallel at multiple stations.

[0023] The coating system provided in this application integrates the testing procedures before and after coating into one device, simplifying the production line and reducing the cleanliness requirements of the factory.

[0024] The coating method provided in this application can simplify the glass product coating production line, reduce factory cleanliness requirements, and improve testing efficiency through parallel processing. Attached Figure Description

[0025] Figure 1This is a schematic diagram of the coating system structure of this application;

[0026] Figure 2 This is a schematic diagram of the main interface of the control analysis software of this application;

[0027] Figure 3 This is a schematic diagram of the testing organization structure in this application;

[0028] Figure 4 This is a schematic diagram of the terminal device in this application. Detailed Implementation

[0029] In the following, specific embodiments of this application will be described in detail with reference to the accompanying drawings. Based on these detailed descriptions, those skilled in the art will be able to clearly understand and implement this application. Without departing from the principles of this application, features from various embodiments can be combined to obtain new implementations, or certain features from some embodiments can be substituted to obtain other preferred implementations.

[0030] See Figures 1-4 This application provides a coating method, which includes performing a first defect detection on the material to be tested, coating the qualified material, performing a second defect detection on the coated material to obtain a second detection result, and classifying the coated material according to the second detection result.

[0031] Furthermore, the first defect detection of the material to be tested includes placing the material to be tested, conveying the material to be tested to the testing and coating mechanism, visually aligning the material to be tested, and then performing a first defect detection on the material to be tested.

[0032] This application integrates three main functions: pre-coating inspection, coating, and post-coating inspection of glass products. It achieves full automation of processing and sorting. The system process mainly includes the following six steps:

[0033] (1) When the product is introduced from the production line, the placement position is random. (1) After passing through the clamping mechanism at the end of the feeding production line mechanism 1, the product will be uniformly placed at a fixed angle. Then the mechanical suction cup of the feeding mechanism 2 will pick up the material from the end of the production line to the inspection and coating mechanism. (2) Since the mechanical suction cup of the feeding mechanism 2 will place the material into the clamp of the inspection and coating mechanism, there will be a certain positional deviation. The inspection and coating mechanism has an infrared laser beam parallel to the inspection and coating mechanism on both sides of the length and width. The inspection and coating mechanism makes a fine adjustment so that the laser beam is not blocked by the edge of the material, thereby achieving accurate positioning of the material. (3) The inspection and coating mechanism moves to the inspection station 8, and the system starts multiple defect detection. (4) Based on the detection results, it is decided whether to coat the product and complete the coating. (5) Defect detection after coating. (6) The unloading mechanism 3 unloads the product into the production line, and the control and analysis mechanism 4 makes distinctions based on the detection results.

[0034] Furthermore, the first defect detection includes detecting the uniformity, light transmittance, cracks, scratches, dust, glass shards, bubbles, fingerprints, watermarks, teeth, and openings of the material to be tested.

[0035] Furthermore, the uniformity and transmittance detection includes acquiring a light source sample, acquiring an image of the material to be detected, converting the light source sample into a first grayscale image, converting the image of the material to be detected into a second grayscale image, calculating the data difference image between the first grayscale image and the second grayscale image, performing threshold segmentation based on a preset value of the transmittance of the material to be detected and the data difference image to obtain a binarized image, calculating the connected components of the binarized image, obtaining the label matrix, state matrix, and centroid matrix of different connected components, and determining the uniformity and transmittance based on the mean pixel value of the corresponding connected component region in the data difference image according to the state matrix.

[0036] Furthermore, the detection of cracks, scratches, dust, glass shards, bubbles, fingerprints, and watermarks includes setting a region of interest, acquiring a detection image of the material to be detected, converting the detection image into a third grayscale image, applying Gaussian filtering to the third grayscale image to smooth the image and remove interference to obtain a second image, using a local threshold segmentation algorithm to perform threshold segmentation on the second image to obtain a third image, performing edge detection on the third image to extract defect contour information, statistically analyzing the defect information based on the defect contour information, comparing the defect information with detection standards to obtain all suspected defects of the material to be detected, and determining whether the material to be detected is qualified.

[0037] Furthermore, the tooth edge and opening detection includes setting a mask, extracting the region of interest (ROI), multiplying the ROI mask with the image of the material to be detected to obtain an ROI image; performing Gaussian filtering on the ROI image to obtain a fourth image, converting the fourth image into a fourth grayscale image, binarizing the information of the fourth grayscale image to obtain a second binarized image, calculating the second connected component in the second binarized image, calculating the size of the second connected component, and comparing the calculation result with the detection standard value to determine whether the material to be detected is qualified.

[0038] Furthermore, the second defect detection includes detecting bubbles and dust on the coating.

[0039] This application also provides a coating system corresponding to the coating method, including a feeding assembly line 1, a feeding mechanism 2, a coating inspection mechanism, a unloading mechanism 3, and a control and analysis mechanism 4; the feeding assembly line 1, the coating inspection mechanism, and the unloading mechanism 3 are arranged sequentially; the feeding assembly line 1 is connected to the control and analysis mechanism 4, the feeding mechanism 2 is connected to the control and analysis mechanism 4, the coating inspection mechanism is connected to the control and analysis mechanism 4, and the unloading mechanism 3 is connected to the control and analysis mechanism 4; the coating inspection mechanism is used to perform pre-coating inspection, coating, and post-coating inspection on the material, and transmit the data to the control and analysis mechanism 4.

[0040] The feeding assembly line 1, feeding mechanism 2, inspection and coating mechanism and unloading mechanism 3 interact with the control and analysis mechanism 4. The control and analysis mechanism 4 controls the feeding assembly line 1, feeding mechanism 2, inspection and coating mechanism and unloading mechanism 3 and processes the collected data.

[0041] Furthermore, there are multiple detection and coating mechanisms, and the feeding mechanism 2 is a robotic arm.

[0042] Furthermore, the detection and coating mechanism includes a first image acquisition unit, a second image acquisition unit, and a coating machine 5. The first image acquisition unit is connected to the control and analysis mechanism 4, the second image acquisition unit is connected to the control and analysis mechanism 4, and the coating machine 5 is connected to the control and analysis mechanism 4. The detection and coating mechanism includes a detection station 8, which is used in conjunction with the first image acquisition unit, the second image acquisition unit, and the coating machine 5.

[0043] Example

[0044] (1) Incoming material defect detection

[0045] Because glass product suppliers have varying factory inspection standards, and incoming glass products may be contaminated during transportation and unpacking, detailed inspection is necessary before lamination to eliminate defective materials. This application focuses on detailed inspection of the following defects: uniformity, light transmittance, cracks, scratches, dust, glass shards, bubbles, fingerprints, watermarks, jagged edges, and openings. Based on the characteristics of these defects, they are categorized into three main types:

[0046] 1) Uniformity and light transmittance

[0047] 2) Cracks, scratches, fingerprints, water stains, dust, glass shards, bubbles

[0048] 3) Toothed edges and openings

[0049] To better detect these defects, the image acquisition process in this application was specifically designed. For example... Figure 3 As shown: Two high-resolution cameras are installed. The first image acquisition unit includes a first camera 6 and a light source, with the first camera 6 located directly above the inspection station 8. The second image acquisition unit includes a second camera 7 and a light source, with the second camera 7 located above and to the side of the inspection station 8. Two strip light sources are positioned to the side of the inspection station 8; a surface light source is positioned directly below the inspection station 8. Different detection methods are used when detecting different types of defects.

[0050] 1) Uniformity and light transmittance

[0051] First, collect light source samples. At testing station 8, without placing any object under test, turn off the two side strip light sources, turn on the lower surface light source, and use the image acquisition device directly above to collect surface light source sample A.

[0052] Then, acquire the image of the glass to be inspected. Place the glass panel to be inspected at inspection station 8, turn off the strip light sources on both sides, turn on the surface light source below, and use the image acquisition device directly above to acquire the image B to be inspected.

[0053] Finally, the software analysis yielded the following results:

[0054] ① Convert the surface light source sample A and the image to be inspected B into 8-bit grayscale images respectively to obtain A. gray and B gray .

[0055] ②Then, obtain the difference image C between the two images. diff You can directly use OpenCV's absdiff function:

[0056] absdiff(A gray B gray C diff )

[0057] ③Then, based on the preset values ​​a and b for the product's light transmittance, the difference image C is... diff Perform threshold segmentation:

[0058] threshold(C diff D bin (a, b, THRESH-BINARY)

[0059] Obtain the binarized image D bin .

[0060] ④ Next, we will analyze image D. bin Find the connected components:

[0061] connectedComponentsWithStats(D bin O label O stat O centroid )

[0062] The label matrices O for different connected components are obtained respectively. label The state matrix O of the connected components stat And the centroid matrix O of the connected domain certroid .

[0063] ⑤ Finally, based on the connected component state matrix O stat The difference image C is obtained sequentially. diff The average pixel value within the corresponding connected region is calculated. If the average value is greater than the threshold set by the software, the light transmittance at that location is deemed unqualified. After calculating the average pixel value within the corresponding connected region in all difference images, the variance is calculated. If the variance value is greater than the threshold set by the software, the light transmittance uniformity of the material is deemed unqualified.

[0064] 2) Cracks, scratches, fingerprints, water stains, dust, glass shards, bubbles

[0065] First, the Region of Interest (ROI) of detection station 8 is set by software. This information is used to remove irrelevant areas when acquiring images.

[0066] Next, acquire the detection images. Turn on the area light source below detection station 8, and the first camera 6 and the second camera 7 each capture an image; turn off the area light source, turn on the strip light sources on both sides, and the first camera 6 and the second camera 7 each capture an image. This yields four images to be detected.

[0067] Next, the acquired images will be analyzed one by one. The analysis process is as follows:

[0068] ① Convert the image to an 8-bit grayscale image to obtain P. gray

[0069] cvtColor(P roi P gray (COLOR_RGB2GRAY)

[0070] Among them, P roi The image is the result of ROI processing.

[0071] ② Apply Gaussian filtering to the image to smooth it and remove interference.

[0072] GaussianBlur(P gray P gaus Size(3, 3), 0)

[0073] Among them, P gaus This is the output image after Gaussian filtering. Size(3,3) is the size of the Gaussian kernel, and the last parameter 0 represents the standard deviation in the x-direction.

[0074] ③ During actual product production and inspection, a pass / fail standard is pre-set. To better extract all defects exceeding the set value from the image, while filtering out minor flaws within the standard range, thresholding and subsequent processing of the image is required. Considering the unevenness of the actual lighting environment, a global thresholding algorithm cannot take into account the situation in all parts of the image, thus affecting the segmentation effect. Therefore, a local thresholding algorithm is needed here.

[0075] adaptiveThreshold(P gaus P th ,255,ADAPTIVE_THRESH_MEAN_C,THRESH_BINARY,n,c)

[0076] Among them, P th This is the output image after using local thresholding; parameter three "255" represents the maximum value of the pixel. Here, an 8-bit grayscale image is used, so the maximum value is 255; ADAPTIVE_THRESH_MEAN_C indicates the method of calculating the average value of pixels in the local neighborhood and then eliminating the constant C; THRESH_BINARY indicates the thresholding type; parameter six "n" indicates the neighborhood size used when calculating the local threshold; parameter seven "c" indicates the constant C that needs to be corrected when calculating the threshold, which needs to be set in the software according to the actual lighting conditions.

[0077] ④ The image of a normal product under illumination should be continuous and smooth. However, if there are obvious defects, there will be obvious discontinuities near these defects. By performing edge detection on the image after threshold segmentation, the contours of these defects can be extracted.

[0078] Canny(p th P edge (min, max)

[0079] Here, the parameters min and max represent the minimum and maximum thresholds for edge detection.

[0080] ⑤ Once the defect contour information is obtained, the algorithm can be used to statistically analyze each individual defect:

[0081] connectedComponentsWithStats(P edge Q label Q stat Q centroid )

[0082] Among them, O label The label matrix for all defects; O stat The state matrix for all defect images; O certroid For the centroid matrix of all defects

[0083] Finally, after inspecting four images of a material, the defect information in the images is compared with the test standards one by one to identify all the suspected defects of the material, and then it is determined whether the material is qualified.

[0084] 3) Toothed edges and openings

[0085] For tooth edges and opening edges, a rounded chamfer is typically applied, resulting in some differences in characteristics compared to the central area. These areas need to be extracted and processed separately during inspection. The processing flow is as follows:

[0086] First, a mask is set using software to extract the region of interest (ROI). The ROI mask is then multiplied by the image to be processed to obtain the ROI image. Image values ​​within the ROI remain unchanged, while image values ​​outside the ROI are all 0. This function can be accomplished using the following OpenCV command:

[0087] bitwise_and(P in P in P out (mask)

[0088] Among them, P in These are complete images captured by the first and second cameras, where mask is a mask set by the software, and P... out The image after masking out irrelevant areas.

[0089] Then, the following steps are used for testing:

[0090] ① For image P out Gaussian filtering is performed to remove some interference from the image, resulting in P.blur .

[0091] ②Transfer image P blur Convert to 8-bit grayscale image P gray .

[0092] ③ Set an appropriate threshold to binarize the image information to obtain P. bin This makes the edges of the glass teeth and the opening edges in the image clearer.

[0093] ④ Obtain the image P bin The connected components in the data are identified, and the size of each connected component is calculated. Then, the values ​​are compared with the preset detection standard values ​​for normal materials.

[0094] If the largest connected component 'a' is within the specified range, then there is a problem with the edge.

[0095] b. Does there exist a connected component with a very small value? If so, it should be a defect. Use the minimum bounding rectangle to mark the defect.

[0096] c calculates the area of ​​the connected components of the target with openings. If the area exceeds the set range, the opening is abnormal, and the opening is marked using the minimum bounding rectangle.

[0097] ⑤ If any abnormality exists in the above steps, mark the material as abnormal; otherwise, mark it as qualified.

[0098] After the inspection is completed, the control mechanism takes corresponding actions based on the inspection results. If the incoming material has no defects exceeding the standard, the control and analysis mechanism 4 is notified to proceed to the lamination process; if the incoming material is unqualified, the inspection and lamination mechanism returns directly from the inspection station 8 to the loading station, and the unloading mechanism 3 directly removes it from the inspection and lamination mechanism and places it on the conveyor belt, flowing to the unqualified area. Then, the loading mechanism 2 picks up the next material to be tested and sends it to the inspection and lamination mechanism.

[0099] (2) Covering

[0100] Materials that pass inspection will begin the lamination process.

[0101] First, the two strip light sources descend to their stopping positions and turn off;

[0102] Then, the laminating machine 7, located above the inspection station 8, descends and completes a series of laminating operations under the operation of the mechanism.

[0103] The laminating machine includes a film winding assembly, rollers, positioning sensors, a vacuum assembly, and a film cutting assembly. Specifically: the film winding assembly feeds the adhesive tape for lamination; the rollers peel the film from the winding mechanism and roll it onto the glass product; the positioning sensors determine the start and end positions of the lamination process; the vacuum assembly, in conjunction with the rollers, removes air from between the film and the glass material to prevent air bubbles; and the film cutting assembly cuts the edges of the lamination based on the positioning sensors, with excess film being collected from the other end of the winding mechanism.

[0104] (3) Post-coating testing

[0105] After lamination is completed, the product needs to be tested to determine whether the lamination is qualified.

[0106] The main items tested include air bubbles and dust.

[0107] First, the organization prepares to enter the testing process. The laminating machine 7 rises, and the strip light sources on both sides of the testing station 8 rise.

[0108] Then, images for inspection are acquired. The area light source below inspection station 8 is turned on, and the first camera 7 and the second camera 7 each capture an image; the area light source is turned off, and the strip light sources on both sides are turned on, and the first camera 6 and the second camera 7 each capture an image. Four images to be inspected are obtained.

[0109] Next, the images are checked in sequence, using the same method as in Method 2 for incoming material defect detection.

[0110] (4) Feeding

[0111] After the inspection is completed, the inspection and coating mechanism returns to the loading position, and the unloading mechanism 3 unloads the product onto different conveyor belts according to the inspection results.

[0112] This application also provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in any of the above method embodiments.

[0113] The terminal device in this embodiment includes: at least one processor ( Figure 4 (Only one is shown in the diagram) a processor, a memory, and a computer program stored in the memory and executable on the at least one processor, which, when executing the computer program, implements the steps in any of the following embodiments of metabolic pathway prediction methods.

[0114] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. This terminal device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that this is merely an example of a terminal device and does not constitute a limitation on the terminal device. It may include more or fewer components than illustrated, or a combination of certain components, or different components; for example, it may also include input / output devices, network access devices, etc.

[0115] The processor referred to can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0116] In some embodiments, the memory may be an internal storage unit of the terminal device, such as a hard drive or memory. In other embodiments, the memory may be an external storage device of the terminal device, such as a plug-in hard drive, smart media card (MC), secure digital (SD) card, flash card, etc.

[0117] Furthermore, the memory may include both internal storage units and external storage devices of the terminal device. The memory is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory can also be used to temporarily store data that has been output or will be output.

[0118] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0119] This application provides a computer program product that, when run on a terminal device, enables the terminal device to implement the steps described in the above-described method embodiments. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods described in this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the above-described method embodiments. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to a camera / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, such as a USB flash drive, a portable hard drive, a magnetic disk, or an optical disk. In some jurisdictions, computer-readable media may not be electrical carrier signals or telecommunication signals, according to legislation and patent practice.

[0120] In the embodiments provided in this application, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0121] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0122] The embodiments described above are merely illustrative of the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application. In the above embodiments, the descriptions of each embodiment have different focuses; parts not described or detailed in a certain embodiment can be referred to the relevant descriptions of other embodiments.

[0123] Although this application has been described above with reference to specific embodiments, those skilled in the art will understand that many modifications can be made to the configurations and details disclosed in this application within the principles and scope of the disclosure. The scope of protection of this application is determined by the appended claims, and the claims are intended to cover all modifications included in the literal meaning or scope of equivalents of the technical features in the claims.

Claims

1. A coating system, the coating system comprising a coating detection mechanism and a feeding mechanism, the coating detection mechanism comprising a first camera, a second camera, and a coating machine, characterized in that: Two strip light sources are provided on the side of the inspection station, and a surface light source is provided directly below it. After the inspection and coating mechanism moves to the inspection station, the coating machine is located above the inspection station, the first camera is located directly above the inspection station, and the second camera is located on the side above the inspection station. The glass products are inspected before coating, after coating, and after coating at the inspection station. After the material is placed on the material, the inspection coating mechanism moves to the inspection station to perform the first defect inspection on the material. The first defect inspection includes uniformity and transmittance inspection. During the uniformity and transmittance inspection, the two side strip light sources are turned off and the surface light source is turned on. The first camera acquires the image to be inspected. Based on the image to be inspected and the light source sample image, it is determined whether there are uniformity and transmittance defects. The light source sample image is obtained by the first camera acquiring the surface light source sample image when no material is placed on the inspection station, the two side strip light sources are turned off, and the surface light source is turned on. The first defect inspection also includes crack, scratch, fingerprint, water stain, dust, glass shard, and bubble inspection. During the crack, scratch, fingerprint, water stain, dust, glass shard, and bubble inspection, the surface light source is first turned on, and the first camera and the second camera each acquire an image. Then the surface light source is turned off, the strip light source is turned on, and the first camera and the second camera each acquire an image. The inspection is performed based on the four images to be inspected. The laminating machine descends after the bar lights on both sides are lowered to their stopping positions and turned off. It then applies a film to the qualified materials. After lamination, the laminating machine rises, the bar lights on both sides of the inspection station rise, and the surface light source below the inspection station turns on. The first and second cameras each capture an image. Then, the surface light source turns off, the bar lights on both sides turn on, and the first and second cameras each capture an image, resulting in four images to be inspected. Based on these four images, a second defect inspection is performed on the laminated material to obtain a second inspection result. The inspection and laminating mechanism then returns to the loading position, and the unloading mechanism sorts and unloads the laminated materials onto different conveyor belts according to the second inspection result.

2. The coating system as described in claim 1, characterized in that: The step of determining whether there are uniformity and transmittance defects based on the image to be inspected and the light source sample image includes converting the light source sample image into a first grayscale image, converting the image to be inspected into a second grayscale image, calculating the data difference image between the first grayscale image and the second grayscale image, performing threshold segmentation based on a preset value of transmittance of the material to be inspected and the data difference image to obtain a binarized image, calculating the connected components of the binarized image, obtaining the label matrix, state matrix and centroid matrix of different connected components, and calculating the pixel mean of the corresponding connected component region in the data difference image based on the state matrix to determine the uniformity and transmittance.

3. The coating system as described in claim 1, characterized in that: The detection of cracks, scratches, dust, glass shards, bubbles, fingerprints, and watermarks includes setting a region of interest, acquiring a detection image of the material to be detected, converting the detection image into a third grayscale image, applying Gaussian filtering to the third grayscale image to smooth the image and remove interference to obtain a second image, using a local threshold segmentation algorithm to perform threshold segmentation on the second image to obtain a third image, performing edge detection on the third image to extract defect contour information, statistically analyzing the defect information based on the defect contour information, comparing the defect information with detection standards to obtain all suspected defects of the material to be detected, and determining whether the material to be detected is qualified.

4. The coating system as described in claim 1, characterized in that: The first defect detection also includes edge and opening detection, which includes setting a mask, extracting the region of interest, and multiplying the region of interest mask with the image of the material to be detected to obtain the region of interest image; A fourth image is obtained by performing Gaussian filtering on the region of interest image. The fourth image is then converted into a fourth grayscale image. The information of the fourth grayscale image is binarized to obtain a second binarized image. The second connected component in the second binarized image is obtained, and the size of the second connected component is calculated. The calculation result is compared with the detection standard value to determine whether the material to be detected is qualified.

5. The coating system as described in claim 1, characterized in that: The second defect inspection includes detecting bubbles and dust in the coating.

6. The coating system as claimed in claim 1, characterized in that: The coating system also includes a feeding mechanism, which is a robotic arm.

7. The coating system as claimed in claim 1, characterized in that: The detection coating mechanism comprises multiple units.

Images