Method, device, equipment and medium for detecting fine cracks on surface of catalyst carrier

Abstract

This invention discloses a method, apparatus, device, and medium for detecting fine cracks on the surface of a catalyst support. The method includes: acquiring an image of the surface of a catalyst support; the image of the surface of the catalyst support includes multiple test grids; performing region detection on each test grid within the image of the surface of the catalyst support according to a preset target detection area to obtain at least one target test grid corresponding to the image of the surface of the catalyst support; determining the grid wall region corresponding to each target test grid based on the coordinates of the center pixel of each target test grid and the target detection area; determining the pixel evaluation value corresponding to each grid pixel in the corresponding grid wall region based on the grayscale value of each grid pixel in each grid wall region; and detecting fine cracks in the target test grid corresponding to the corresponding grid wall region based on the pixel evaluation value corresponding to each grid pixel in each grid wall region. This invention enables the detection of fine cracks on the surface of a catalyst support.

Description

Technical Field

[0001] This invention relates to the field of automated testing technology, and in particular to a method, apparatus, equipment and medium for detecting fine cracks on the surface of a catalyst support. Background Technology

[0002] During the production of ceramic catalyst supports, defective ceramic catalyst supports may occur. Typically, ceramic catalyst support manufacturers primarily identify these defects through manual visual inspection, a method that requires significant manpower and is costly in the long run. Furthermore, manual inspection may fail to detect minute cracks on the catalyst support surface. In addition, manual inspection is inefficient and susceptible to the subjectivity of the inspectors, resulting in low accuracy and poor stability. Summary of the Invention

[0003] This invention provides a method, apparatus, equipment, and medium for detecting fine cracks on the surface of a catalyst support, thereby improving the detection efficiency and accuracy of fine crack detection on the catalyst support surface.

[0004] According to one aspect of the present invention, a method for detecting fine cracks on the surface of a catalyst support is provided, the method comprising:

[0005] Acquire an image of the surface of the carrier under test; the image of the surface of the carrier under test includes multiple test grids;

[0006] Based on the preset target detection area, region detection is performed on each grid to be tested within the surface image of the carrier to be tested, to obtain at least one target grid to be tested corresponding to the surface image of the carrier to be tested; the connected component type of each target grid to be tested is closed.

[0007] Based on the coordinates of the center pixel of each target grid to be tested, and based on the target detection area, determine the grid wall region corresponding to each target grid to be tested;

[0008] Based on the grayscale value of each grid pixel in each grid wall region, determine the pixel evaluation value corresponding to each grid pixel in the corresponding grid wall region;

[0009] Based on the pixel evaluation value corresponding to each grid pixel point in each grid wall region, fine cracks are detected in the target grid to be tested corresponding to the grid wall region.

[0010] According to another aspect of the present invention, a device for detecting fine cracks on the surface of a catalyst support is provided, characterized in that it comprises:

[0011] The carrier image acquisition module is used to acquire an image of the surface of the carrier under test; the image of the surface of the carrier under test includes multiple grids to be tested;

[0012] The region detection module is used to perform region detection on each grid to be tested in the surface image of the carrier to be tested according to a preset target detection region, so as to obtain at least one target grid to be tested corresponding to the surface image of the carrier to be tested; the connected component type of each target grid to be tested is closed.

[0013] The grid wall region determination module is used to determine the grid wall region corresponding to each of the target grids based on the coordinates of the center pixel of each target grid to be tested and the target detection region.

[0014] The pixel evaluation value determination module is used to determine the pixel evaluation value corresponding to each grid pixel in the corresponding grid wall area based on the gray value of each grid pixel in each grid wall area.

[0015] The crack detection module is used to detect fine cracks in the target mesh corresponding to the mesh wall region based on the pixel evaluation value corresponding to each mesh pixel point in each mesh wall region.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the method for detecting fine cracks on the surface of a catalyst support according to any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the method for detecting fine cracks on the surface of a catalyst support according to any embodiment of the present invention.

[0021] This invention provides a solution that acquires an image of the surface of a carrier under test, performs region detection on each grid cell within the image based on a preset target detection area, and obtains at least one target grid cell corresponding to the surface image of the carrier under test. This achieves the determination of grid cells with closed connected components in the image of the carrier under test. Based on the coordinates of the center pixel of each target grid cell, and the target detection area, the corresponding grid wall region is determined for each target grid cell. Based on the grayscale values ​​of each grid pixel within each grid wall region, the pixel evaluation value corresponding to each grid pixel within the corresponding grid wall region is determined. Based on the pixel evaluation values ​​corresponding to each grid pixel within each grid wall region, fine cracks are detected in the target grid cells corresponding to the corresponding grid wall regions. This achieves the detection of fine cracks on the catalyst carrier surface, improving the detection efficiency and accuracy of fine cracks on the catalyst carrier surface.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1A This is a flowchart of a method for detecting fine cracks on the surface of a catalyst support according to Embodiment 1 of the present invention;

[0025] Figure 1B This is a schematic diagram of a preprocessing process for an image of the surface of a carrier under test according to Embodiment 1 of the present invention;

[0026] Figure 1C This is a schematic diagram of a region detection of a grid to be tested according to Embodiment 1 of the present invention;

[0027] Figure 1D This is a schematic diagram illustrating the determination of a grid wall region according to Embodiment 1 of the present invention;

[0028] Figure 2 This is a flowchart of a method for detecting fine cracks on the surface of a catalyst support according to Embodiment 2 of the present invention;

[0029] Figure 3A This is a flowchart of a method for detecting fine cracks on the surface of a catalyst support according to Embodiment 3 of the present invention;

[0030] Figure 3B This is a schematic diagram of the determination structure of a binarized grid region to be measured according to Embodiment 3 of the present invention;

[0031] Figure 3C This is a schematic diagram of the structure for determining the mesh wall region of a target mesh to be tested according to Embodiment 3 of the present invention;

[0032] Figure 4 This is a schematic diagram of a device for detecting fine cracks on the surface of a catalyst support according to Embodiment 4 of the present invention;

[0033] Figure 5 This is a schematic diagram of the structure of an electronic device for implementing the method for detecting fine cracks on the surface of a catalyst support according to an embodiment of the present invention. Detailed Implementation

[0034] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0035] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0036] Example 1

[0037] Figure 1A This is a flowchart of a method for detecting fine cracks on the surface of a catalyst support according to Embodiment 1 of the present invention. This embodiment is applicable to the detection of fine cracks on the surface of ceramic catalyst supports. The method can be executed by a fine crack detection device for the catalyst support surface, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1A As shown, the method includes:

[0038] S110. Obtain the surface image of the carrier under test; the surface image of the carrier under test includes multiple grids to be tested.

[0039] The image of the support surface to be tested can be an image of the surface of a ceramic catalyst support for which fine crack detection is to be performed. This image can be obtained using an industrial camera, such as a CIS (Contact Image Sensor Camera) camera. Specifically, it can be obtained by using an industrial camera to photograph the surface of the support on a ceramic support production line.

[0040] It should be noted that, because the surface of the ceramic catalyst support is honeycomb-like, the image of the surface of the support under test includes multiple test grids. Due to manufacturing errors, the sizes of these test grids may vary to some extent.

[0041] Optionally, to further improve the detection accuracy of the surface image of the carrier under test, the acquired surface image of the carrier under test can be preprocessed. The preprocessing includes applying Gaussian filtering to the surface image of the carrier under test, and then correcting the tilt of the filtered surface image to obtain a corrected surface image of the carrier under test. The corrected surface image of the carrier under test is then binarized. Based on the binarized surface image of the carrier under test, the target carrier location region containing the carrier surface contour is determined, and this target carrier location region is cropped to obtain a surface image of the carrier under test containing only the target carrier location region.

[0042] like Figure 1B The diagram illustrates a preprocessing procedure for an image of the surface of a carrier under test. The initial image of the carrier surface is tilt-corrected; the tilt-corrected image is then cropped to extract the target carrier location region, resulting in an image of the carrier surface containing only the target carrier location region.

[0043] S120. Based on the preset target detection area, perform region detection on each grid to be tested in the surface image of the carrier to be tested, and obtain at least one target grid to be tested corresponding to the surface image of the carrier to be tested; the connected component type of each target grid to be tested is closed.

[0044] The target detection area can be pre-defined by relevant technical personnel. It should be noted that since the purpose of region detection on the grid to be tested is to determine whether the connected component of the grid to be tested is closed or open, the area of ​​the determined target detection area must be larger than the area of ​​the grid to be tested, and at least able to contain the grid to be tested.

[0045] For example, if the average area of ​​each grid in the image of the surface of the carrier under test is 30 mm²2 The size of the target detection area can be preset to 40mm. 2 It should be noted that since the shape of the grid to be measured is approximately square, the preset target detection area can be a 20×20mm positive direction region. For example... Figure 1C The diagram illustrates a region detection method for a grid under test. The area of ​​the target detection region is larger than the area of ​​the grid under test.

[0046] For example, based on the preset target detection area, region detection is performed on each grid to be tested in the surface image of the carrier to be tested. Specifically, the grid to be tested at the middle position of the surface image of the carrier to be tested can be used as the starting point for traversal. Each grid to be tested in the surface image of the carrier to be tested is traversed to determine the connected component type of each grid to be tested in the surface image of the carrier to be tested. After the traversal is completed, the grid to be tested with the connected component type of closed is determined as the target grid to be tested.

[0047] Optionally, the connected component type can be determined by determining the area of ​​the connected components corresponding to the grid to be tested. If the area of ​​the connected components is greater than a preset area threshold, it indicates that the connected component type of the grid to be tested is non-closed; if the area of ​​the connected components is not greater than the preset area threshold, it indicates that the connected component type of the grid to be tested is closed. The area threshold can be preset by relevant technical personnel; for example, the area threshold could be 1.3T. 2 Where T is the average side length of the grid to be measured.

[0048] S130. Based on the coordinates of the center pixel of each target grid to be tested, determine the grid wall region corresponding to each target grid to be tested based on the target detection area.

[0049] For example, the target region corresponding to the target mesh under the target detection region can be determined. Specifically, the coordinates of the center pixel of the target detection region can be aligned with the coordinates of the center pixel of the target mesh under the target detection region, thereby accurately locating the target region corresponding to the target mesh under the target detection region. The mesh wall region of the target mesh under the target region can also be determined.

[0050] For example, such as Figure 1D The diagram illustrates the determination of a mesh wall region. The dark gray area represents the mesh wall region of the target mesh A within the target area. Specifically, this can be achieved by binarizing the target area corresponding to the target mesh A, and then extracting the binarized target area to obtain the mesh wall region corresponding to the target mesh.

[0051] S140. Based on the grayscale value of each grid pixel in each grid wall area, determine the pixel evaluation value corresponding to each grid pixel in the corresponding grid wall area.

[0052] For example, for any grid pixel within any grid wall region, its neighboring pixels can be taken, and their grayscale values ​​determined. The average of the grayscale values ​​of the grid pixel and its neighboring pixels is then used as the pixel evaluation value for that grid pixel. This pixel evaluation value is used for accurate analysis of the connected components within the grid wall region.

[0053] S150. Based on the pixel evaluation value corresponding to each grid pixel point in each grid wall region, detect fine cracks in the target grid to be tested corresponding to the grid wall region.

[0054] For example, secondary binarization can be performed on the corresponding grid wall regions based on the pixel evaluation values ​​corresponding to each grid pixel within the closed grid region. Specifically, this can be achieved by comparing the pixel evaluation value corresponding to each grid pixel with the grayscale value of the grid pixel itself, thereby determining the result of the secondary binarization of the corresponding grid wall region. Based on the secondary binarization results of each grid wall region, fine cracks are detected in the target grid to be tested. Specifically, an image detection algorithm can be used to detect connected components in the image of the secondary binarization result. If the connected component type is closed, it indicates that there are no fine cracks in the target grid to be tested; if the connected component type is open, it indicates that there are fine cracks in the target grid to be tested.

[0055] This invention provides a solution that acquires an image of the surface of a carrier under test, performs region detection on each grid cell within the image based on a preset target detection area, and obtains at least one target grid cell corresponding to the surface image of the carrier under test. This achieves the determination of grid cells with closed connected components in the image of the carrier under test. Based on the coordinates of the center pixel of each target grid cell, and the target detection area, the corresponding grid wall region is determined for each target grid cell. Based on the grayscale values ​​of each grid pixel within each grid wall region, the pixel evaluation value corresponding to each grid pixel within the corresponding grid wall region is determined. Based on the pixel evaluation values ​​corresponding to each grid pixel within each grid wall region, fine cracks are detected in the target grid cells corresponding to the corresponding grid wall regions. This achieves the detection of fine cracks on the catalyst carrier surface, improving the detection efficiency and accuracy of fine cracks on the catalyst carrier surface.

[0056] Example 2

[0057] Figure 2 This is a flowchart of a method for detecting fine cracks on the surface of a catalyst support provided in Embodiment 2 of the present invention. This embodiment is an optimization and improvement based on the above technical solutions.

[0058] Furthermore, the operation of "performing region detection on each grid cell in the surface image of the carrier under test according to the preset target detection area to obtain at least one target grid cell corresponding to the surface image of the carrier under test" is refined into "determining the average side length of each grid cell; determining the target detection area based on the average side length; selecting any grid cell with a closed connected component type from the grid cells in the surface image of the carrier under test as the starting grid cell; using the starting grid cell as the detection starting point, performing region detection on each adjacent grid cell of the starting grid cell in sequence until the region detection termination condition is met, and then terminating the detection to obtain at least one target grid cell corresponding to the surface image of the carrier under test." This improves the method for determining the target grid cell.

[0059] like Figure 2 As shown, the method includes the following specific steps:

[0060] S210. Obtain the surface image of the carrier under test; the surface image of the carrier under test includes multiple grids to be tested.

[0061] S220. Determine the average side length of each grid cell to be measured.

[0062] It should be noted that, since the sizes of the various grid cells in the image of the carrier surface vary to some extent, the average side length of each grid cell can be determined. This facilitates the subsequent determination of the target detection region size based on the average side length.

[0063] In one optional embodiment, the total side length of the surface image of the carrier under test and the number of each grid to be tested in the surface image of the carrier under test can be determined, so as to determine the average side length corresponding to each grid to be tested based on the total side length of the surface image of the carrier under test and the number of grids to be tested.

[0064] To further improve the accuracy and efficiency of determining the average side length of each grid to be tested, in another optional embodiment, determining the average side length of each grid to be tested includes: determining the carrier center region of the carrier surface image to be tested; the carrier center region includes multiple grids to be tested; determining the average gray value of each pixel row in the carrier center region; determining the total average gray value of the carrier center region based on the average gray value of each row; and determining the average side length of each grid to be tested based on the average gray value of each row and the total average gray value.

[0065] It should be noted that, due to the regularity of pixel value distribution among the grids in the image of the surface of the carrier under test—that is, the pixel value of the grid wall is smaller than the pixel value of the area within the grid wall—the pixel distribution of the entire image of the carrier under test exhibits a cyclical pattern from the first row to the last. Therefore, based on this pattern, the average side length of the grid can be determined using a Fourier transform function.

[0066] It should be noted that since the grid to be tested is uniformly distributed on the surface image of the carrier, the central region of the carrier surface image can be determined and used as the area for calculating the average side length of the grid to be tested. This reduces the amount of calculation required for the average side length and thus improves the efficiency of determining the average side length. Typically, the selected central region of the carrier can include at least 5×5 grids to be tested, and the specific number can be preset by relevant technical personnel according to actual needs.

[0067] For example, the average grayscale value of each row of pixels within the central region of the carrier is determined, as well as the average grayscale value of the central region of the carrier. Based on the average grayscale values ​​of each row and the average grayscale value, the average side length corresponding to each grid cell to be measured is determined using a preset Fourier transform function. The Fourier transform function is as follows:

[0068] f(t) = hist[i] - histavg;

[0069]

[0070] Where hist[i] represents the average gray value of the i-th row in the central region of the carrier; histavg represents the total average gray value of the central region of the carrier; and n represents the number of rows in the central region of the carrier.

[0071] For example, the independent variable ω that determines the maximum value of |F(ω)| for the function F(ω) in the complex field is T = 2π / ω, and the average side length of each grid to be measured is T = 2π / ω.

[0072] S230. Determine the target detection area based on the average side length.

[0073] It should be noted that the entire surface image of the carrier under test can be abstracted as a connected graph composed of many grid elements. For each grid element, the connected component type, the center pixel position, and its position in the mapping table are recorded. To facilitate the subsequent determination of the target grid and the corresponding grid wall regions, a corresponding mapping table can be pre-constructed to store the relevant grid information for each grid element. The grid element is the grid to be tested.

[0074] For example, if the average side length of each grid to be tested is T, the target detection area can be a square area with a side length of 2*T to ensure that the target detection area can completely cover and is larger than the area of ​​the grid to be tested.

[0075] S240. From the test grids in the surface image of the carrier to be tested, select any test grid with a closed connected domain type as the starting test grid.

[0076] For example, from each test grid in the image of the surface of the carrier under test, any test grid with a closed connectivity type is selected. The selection location is not limited; for example, it can be selected from the central region of the carrier in the image of the surface of the carrier under test. The selected closed test grid is then used as the starting test grid.

[0077] Optionally, a mapping table is constructed to store relevant mesh information of the mesh to be tested, and the relevant mesh information of the starting mesh to be tested is written into the mapping table. Specifically, the relevant mesh information of the starting mesh to be tested can be written into the middle position of the mapping table. The data type of the mapping table can be a preset mesh region, and the data format of this mesh region can be an array. For example, if the constructed mapping table is a 1000×1000 mesh region, the relevant mesh information of the starting mesh to be tested can be stored in a 500×500 mesh region. The relevant mesh information may include the coordinates of the center pixel of the mesh to be tested, the type of connected components, and its position in the mapping table.

[0078] S250. Starting from the initial test grid, perform region detection on each adjacent test grid of the initial test grid in sequence until the region detection termination condition is met, and then terminate the detection to obtain at least one target test grid corresponding to the surface image of the test carrier.

[0079] Among them, the connected component type of each target grid to be tested is closed.

[0080] For example, the initial test grid can be used as the starting point for detection, and each test grid in the surface image of the carrier to be tested can be traversed sequentially. Specifically, the adjacent test grids of the initial test grid can be determined first, the adjacent test grids can be detected, and the relevant grid information of the adjacent test grids can be written into a mapping table. Detection can be terminated when the region detection termination condition is met, thus obtaining at least one target test grid corresponding to the surface image of the carrier to be tested.

[0081] In one optional embodiment, starting from the initial grid to be tested, region detection is performed sequentially on each adjacent grid to be tested until the region detection termination condition is met, including: starting from the initial grid to be tested, performing region detection sequentially on each adjacent grid to be tested; determining whether the corresponding adjacent grid to be tested has not been detected; if so, determining whether the adjacent grid to be tested is within the detection area of ​​the surface image of the carrier to be tested; if so, determining whether the connected component type of the adjacent grid to be tested is closed; if not, terminating the detection of the adjacent grid to be tested.

[0082] For example, starting with the initial test grid, region detection is performed sequentially on each adjacent test grid. For instance, if the center point of the initial test grid is (x0, y0), the approximate positions of the center points of the eight adjacent test grids around (x0, y0) are determined. For any adjacent test grid, it is first determined whether the adjacent test grid has not been detected. If not detected, it is determined whether the adjacent test grid is within the detection area of ​​the test carrier surface image; if detected, the detection of the adjacent test grid is terminated. If the adjacent test grid is within the detection area of ​​the test carrier surface image, it is determined whether the connected component type of the adjacent test grid is closed; if the adjacent test grid is not within the detection area of ​​the test carrier surface image, the detection of the adjacent test grid is terminated. The method for determining whether an adjacent test grid is within the detection area of ​​the test carrier surface image can be to calculate the distance from the adjacent test grid to the edge of the test carrier surface image, and determine whether it is within the detection area of ​​the test carrier surface based on the distance. If the connected component type of the adjacent test grid is closed, the relevant grid information of the adjacent test grid is mapped into the mapping table, and the adjacent test grid is taken as the current test grid. The process continues to determine the adjacent test grids of the current test grid. Based on the same region detection termination condition, the adjacent test grids are judged. If the connected component type of the adjacent test grid is not closed, the detection of the adjacent test grid is terminated.

[0083] It should be noted that when the detection of a test grid is terminated, subsequent detection of its adjacent test grids will not be performed. Therefore, after the detection traversal of the test grids is completed, there may be at least one test grid that has not been detected. The area formed by the undetected test grids can be considered to be a blockage hole or a defect hole, which are relatively large defects in the surface image of the test carrier that are easily detected. After the traversal is completed, the location of the undetected test grids can be estimated based on the known test grids around the defective undetected test grids, and the grid-related information of the undetected test grids can be written into a mapping table. This facilitates subsequent defect analysis of the surface image of the test carrier by relevant technicians.

[0084] It is understandable that, since the mapping table stores the relevant grid information of all grids to be tested in the surface image of the carrier to be tested, when determining the grid wall region of each target grid to be tested, the relevant grid information of the target grid to be tested can be directly obtained from the mapping table. For example, the coordinates of the center pixel of the target grid to be tested can be obtained, which facilitates the positioning of the target grid to be tested in the target detection area.

[0085] In this optional embodiment, multiple conditions are added to the entire traversal process: it must be within the detection area; the searched grids are marked to prevent infinite repeated searches; and traversal is only allowed when the grid is a closed connected component, ensuring that the number of traversal cycles is finite and that the center point of each grid is relatively accurate.

[0086] S260. Based on the coordinates of the center pixel of each target grid to be tested, determine the grid wall region corresponding to each target grid to be tested based on the target detection area.

[0087] S270. Based on the grayscale values ​​of each grid pixel within each grid wall region, determine the pixel evaluation value corresponding to each grid pixel within the corresponding grid wall region.

[0088] S280. Based on the pixel evaluation value corresponding to each grid pixel point in each grid wall region, detect fine cracks in the target grid to be tested corresponding to the grid wall region.

[0089] This embodiment determines the average side length of each grid cell to be tested; based on the average side length, it determines the target detection region; from the grid cells to be tested in the image of the surface of the carrier under test, it selects any grid cell with a closed connected component type as the starting grid cell; using the starting grid cell as the detection starting point, it sequentially performs region detection on each adjacent grid cell to the starting grid cell until the region detection termination condition is met, thus terminating the detection and obtaining at least one target grid cell corresponding to the surface image of the carrier under test. This embodiment achieves accurate determination of the target detection region by determining the target detection region based on the average side length. By using a cyclic traversal method to determine the target grid cell, it improves the accuracy of determining the target grid cell, thereby improving the accuracy of subsequent detection of fine cracks in the target grid cell.

[0090] Example 3

[0091] Figure 3A This is a flowchart of a method for detecting fine cracks on the surface of a catalyst support provided in Embodiment 3 of the present invention. This embodiment is an optimization and improvement based on the above technical solutions.

[0092] Furthermore, the operation of "determining the mesh wall region corresponding to each target mesh based on the coordinates of the center pixel of each target mesh and the target detection area" is refined into "determining the detection mesh region corresponding to each target mesh based on the coordinates of the center pixel of each target mesh and the target detection area; performing binarization processing on each detection mesh region to obtain the binarized detection mesh region corresponding to each detection mesh region; performing region detection on each binarized detection mesh region to obtain the mesh wall region corresponding to each target mesh." This improves the method for determining the mesh wall region corresponding to the target mesh.

[0093] Furthermore, the operation of "determining the pixel evaluation value corresponding to each grid pixel in the corresponding grid wall region based on the grayscale value of each grid pixel in each grid wall region" is refined into "determining at least one grid pixel in the corresponding grid wall region; constructing the target grid detection region corresponding to the corresponding grid pixel based on the preset grid detection region and using each grid pixel as the center coordinate; determining the pixel evaluation value of the corresponding grid pixel based on the grayscale value of each pixel in the target grid detection region." This improves the method for determining the pixel evaluation value of grid pixels.

[0094] Furthermore, the operation of "detecting fine cracks in the target mesh corresponding to each grid wall region based on the pixel evaluation value of each grid pixel in each grid wall region" is refined into "determining the target binarized image corresponding to the target mesh based on the pixel evaluation value of each grid pixel in each grid wall region; and detecting fine cracks in the target mesh based on the target binarized image." This improves the method for detecting fine cracks in the target mesh.

[0095] like Figure 3A As shown, the method includes the following specific steps:

[0096] S310. Obtain an image of the surface of the carrier to be tested; the image of the surface of the carrier to be tested includes multiple grids to be tested.

[0097] S320. Based on the preset target detection area, perform region detection on each grid to be tested in the surface image of the carrier to be tested, and obtain at least one target grid to be tested corresponding to the surface image of the carrier to be tested; the connected component type of each target grid to be tested is closed.

[0098] S330. Based on the coordinates of the center pixel of each target grid to be tested, determine the grid area to be tested corresponding to each target grid to be tested based on the target detection area.

[0099] For example, the center coordinates of the target detection region can be aligned with the center pixel coordinates of the target mesh to be tested, and the entire target detection region can be used as the mesh region to be tested corresponding to the target mesh to be tested. The mesh region to be tested includes the target mesh to be tested.

[0100] S340. Perform binarization processing on each grid region to be detected to obtain the binarized grid region to be detected corresponding to each grid region to be detected.

[0101] For example, for any grid region to be tested, binarization processing is performed on the grid region to be tested. For instance, based on the grid region to be detected, a preset binarization processing algorithm can be used to binarize the grid region to be detected, resulting in the binarized grid region to be tested. The binarization processing algorithm can be preset by relevant technical personnel. For example, the binarization processing algorithm can be the OTSU algorithm (Maximum Inter-Class Variance Method).

[0102] For example, such as Figure 3B The diagram shows a schematic representation of the structure for determining a binarized grid region to be tested. The grid region to be detected in the left image is binarized to obtain the binarized grid region to be tested in the right image.

[0103] S350. Perform region detection on each binarized grid region to obtain the grid wall region corresponding to each target grid.

[0104] For example, region detection can be performed on the binarized test grid region, specifically by obtaining the grid wall regions corresponding to each target test grid. For instance... Figure 3C The diagram illustrates a structural representation of the mesh wall region determination for a target mesh to be tested. The extraction of the mesh wall region can be performed using existing image processing algorithms or tools.

[0105] S360. Determine at least one grid pixel within the corresponding grid wall region.

[0106] Among them, grid pixels are the individual pixels within the grid wall area.

[0107] S370. Using each grid pixel as the center coordinate, construct the target grid detection area corresponding to the corresponding grid pixel based on the preset grid detection area.

[0108] The grid detection area can be preset by relevant technical personnel. For example, the grid detection area can be an n×n pixel grid area centered on a grid pixel. For example, it can be a 3×3 pixel grid area, with the grid pixel located at the center of the grid detection area.

[0109] For example, for any grid wall region, based on a preset grid detection region, the target grid detection region corresponding to each grid pixel within the grid wall region can be determined.

[0110] S380. Determine the pixel evaluation value of the corresponding grid pixel based on the grayscale value of each pixel within the target grid detection area.

[0111] In one optional embodiment, the average grayscale value of each pixel within the target grid detection area can be used as the pixel evaluation value of the corresponding grid pixel. For example, if there are 9 pixels within the target grid detection area, the average grayscale value of the 9 pixels can be used as the pixel evaluation value of that grid pixel.

[0112] To improve the accuracy of determining the pixel evaluation value of grid pixels, in another optional embodiment, the pixel evaluation value of the corresponding grid pixel is determined based on the gray value of each pixel in the target grid detection area, including: determining the gray standard deviation and gray average value corresponding to the target grid detection area based on the gray value of each pixel in the target grid detection area; and determining the pixel evaluation value of the corresponding grid pixel based on the gray standard deviation and gray average value.

[0113] For example, based on the grayscale values ​​of each pixel within the target grid detection area, the grayscale standard deviation ρ(x, y) and grayscale average value m(x, y) corresponding to the target grid detection area are determined. Here, (x, y) identifies the coordinates of each pixel within the target grid detection area. Based on the grayscale standard deviation and grayscale average value, the pixel evaluation value of the corresponding grid pixel is determined. The pixel evaluation value T is determined as follows:

[0114] T = a*ρ(x, y) + b*m(x, y);

[0115] Where a and b are arbitrary positive real numbers that are predetermined.

[0116] S390. Based on the pixel evaluation values ​​corresponding to each grid pixel point within each grid wall region, determine the target binarized image corresponding to the target grid to be tested.

[0117] For example, the target grid to be measured can be binarized based on the pixel evaluation values ​​corresponding to each grid pixel within each grid wall region. The binarization process is as follows:

[0118]

[0119] Where f(x,y) represents the grayscale value of each pixel within the target grid to be measured. xyrepresents the pixel evaluation value corresponding to pixel (x, y). g(x, y) represents the pixel grayscale value after rebinarization of pixel (x, y). By comparing the pixel grayscale value of pixel (x, y) within the target test grid region with the pixel evaluation value, the target binarized image corresponding to the target test grid is obtained.

[0120] S3100. Based on the binarized images of each target, detect the fine cracks in the corresponding target's mesh.

[0121] It should be noted that by performing two binarization processes on the target mesh to be tested, and further subdividing the granularity to the pixel level during the second binarization process, the detection of minute cracks that are difficult to detect can be achieved.

[0122] For example, fine cracks in the target mesh can be detected by performing region detection on the target binarized image.

[0123] In one optional embodiment, the detection of fine cracks in the corresponding target mesh is performed based on the binarized images of each target, including: determining the area of ​​the connected component corresponding to the binarized image of each target; and detecting fine cracks in the corresponding target mesh based on the area of ​​the connected component and a preset crack judgment condition.

[0124] For example, the target binarized image can be processed using a preset image processing algorithm or tool to obtain the connected components corresponding to the target binarized image, and the area of ​​the connected components of the target binarized image can be determined. Based on the area of ​​the connected components and a preset crack judgment condition, fine cracks in the corresponding target mesh to be tested are detected. Specifically, if the area of ​​the connected components is less than a preset area threshold, it indicates that there are no fine cracks in the target mesh to be tested; if the area of ​​the connected components is not less than the preset area threshold, it indicates that there are fine cracks in the target mesh to be tested. The area threshold can be preset by relevant technical personnel.

[0125] This optional embodiment improves the accuracy of detecting fine cracks in the target mesh by detecting fine cracks based on the area of ​​the connected domain and a preset crack judgment condition.

[0126] This embodiment improves the accuracy of determining grid wall regions by binarizing each grid region to be detected, obtaining a binarized test grid region corresponding to each grid region, and then performing region detection on each binarized test grid region to obtain the grid wall region corresponding to each target test grid. By constructing the target grid detection region corresponding to each grid pixel, and determining the pixel evaluation value of each grid pixel based on the grayscale value of each pixel within the target grid detection region, the accuracy of determining the pixel evaluation value is improved, thereby improving the accuracy of subsequent detection of fine cracks. Furthermore, by determining the target binarized image corresponding to each target test grid based on the pixel evaluation value corresponding to each grid pixel within each grid wall region, and then detecting fine cracks in the corresponding target test grid based on each target binarized image, the accuracy of fine crack detection is improved.

[0127] Example 4

[0128] Figure 4 This is a schematic diagram of a device for detecting fine cracks on the surface of a catalyst support according to Embodiment 4 of the present invention. The device provided in this embodiment of the present invention is suitable for detecting fine cracks on the surface of ceramic catalyst supports. This device can be implemented in hardware and / or software, such as... Figure 4 As shown, the device specifically includes: a carrier image acquisition module 401, a region detection module 402, a grid wall region determination module 403, a pixel evaluation value determination module 404, and a crack detection module 405.

[0129] in,

[0130] The carrier image acquisition module 401 is used to acquire a surface image of the carrier under test; the surface image of the carrier under test includes multiple grids to be tested.

[0131] The region detection module 402 is used to perform region detection on each grid to be tested in the surface image of the carrier to be tested according to a preset target detection region, so as to obtain at least one target grid to be tested corresponding to the surface image of the carrier to be tested; the connected component type of each target grid to be tested is closed.

[0132] The mesh wall region determination module 403 is used to determine the mesh wall region corresponding to each of the target meshes based on the coordinates of the center pixel of each of the target meshes to be tested and the target detection region.

[0133] The pixel evaluation value determination module 404 is used to determine the pixel evaluation value corresponding to each grid pixel in the corresponding grid wall area based on the gray value of each grid pixel in each grid wall area.

[0134] The crack detection module 405 is used to detect fine cracks in the target mesh corresponding to the mesh wall region based on the pixel evaluation value corresponding to each mesh pixel point in each mesh wall region.

[0135] This invention provides a solution that acquires an image of the surface of a carrier under test, performs region detection on each grid cell within the image based on a preset target detection area, and obtains at least one target grid cell corresponding to the surface image of the carrier under test. This achieves the determination of grid cells with closed connected components in the image of the carrier under test. Based on the coordinates of the center pixel of each target grid cell, and the target detection area, the corresponding grid wall region is determined for each target grid cell. Based on the grayscale values ​​of each grid pixel within each grid wall region, the pixel evaluation value corresponding to each grid pixel within the corresponding grid wall region is determined. Based on the pixel evaluation values ​​corresponding to each grid pixel within each grid wall region, fine cracks are detected in the target grid cells corresponding to the corresponding grid wall regions. This achieves the detection of fine cracks on the catalyst carrier surface, improving the detection efficiency and accuracy of fine cracks on the catalyst carrier surface.

[0136] Optionally, the grid wall region determination module 403 includes:

[0137] The grid region determination unit is used to determine the grid region to be detected corresponding to each of the target grids based on the coordinates of the center pixel of each of the target grids to be tested and the target detection region.

[0138] The binarized grid region determination unit is used to perform binarization processing on each of the grid regions to be detected to obtain the binarized grid regions to be detected corresponding to each of the grid regions to be detected.

[0139] The mesh wall region determination unit is used to perform region detection on each of the binarized test mesh regions to obtain the mesh wall region corresponding to each of the target test meshes.

[0140] Optionally, the pixel evaluation value determination module 404 includes:

[0141] A grid pixel determination unit is used to determine at least one grid pixel within a corresponding grid wall region;

[0142] The target detection region construction unit is used to construct the target grid detection region corresponding to each grid pixel point based on the preset grid detection region, with each grid pixel point as the center coordinate.

[0143] The pixel evaluation value determination unit is used to determine the pixel evaluation value of the corresponding grid pixel based on the gray value of each pixel in the target grid detection area.

[0144] Optionally, the pixel evaluation value determination unit includes:

[0145] The grayscale standard deviation determination subunit is used to determine the grayscale standard deviation and grayscale average value of the corresponding target grid detection area based on the grayscale value of each pixel in the target grid detection area.

[0146] The pixel evaluation value determination subunit is used to determine the pixel evaluation value of the corresponding grid pixel based on the grayscale standard deviation and the grayscale average value.

[0147] Optionally, the crack detection module 405 includes:

[0148] The target binarization image determination unit is used to determine the target binarization image corresponding to the target grid to be tested based on the pixel evaluation value corresponding to each grid pixel point in each grid wall region.

[0149] The crack detection unit is used to detect fine cracks in the corresponding target mesh based on the binarized images of each target.

[0150] Optionally, the crack detection unit includes:

[0151] The connected component area determination subunit is used to determine the connected component area corresponding to each target binarized image based on each of the target binarized images;

[0152] The crack detection subunit is used to detect fine cracks in the corresponding target mesh based on the area of ​​the connected domain and a preset crack judgment condition.

[0153] Optionally, the region detection module 402 includes:

[0154] The average side length determination unit is used to determine the average side length of each of the grids to be measured.

[0155] The target detection region determination unit is used to determine the target detection region based on the average side length;

[0156] The starting test network determination unit is used to select any test grid with a closed connected domain type from each test grid in the test carrier surface image as the starting test grid;

[0157] The region detection unit is used to perform region detection on each adjacent region to be tested sequentially, starting from the initial region to be tested grid, until the region detection termination condition is met, thereby obtaining at least one target region to be tested grid corresponding to the surface image of the carrier to be tested.

[0158] Optionally, the region detection unit includes:

[0159] The region detection subunit is used to perform region detection on each adjacent grid to be tested in sequence, starting from the initial grid to be tested.

[0160] The grid judgment sub-unit is used to determine whether the corresponding adjacent grid to be tested has not been detected;

[0161] The range determination subunit is used to determine whether the adjacent test grid is within the detection area of ​​the surface image of the carrier under test if the corresponding adjacent test grid is not detected.

[0162] The connected component type determination subunit is used to determine whether the connected component type of the adjacent test grid is closed if the adjacent test grid is within the detection area of ​​the test carrier surface image.

[0163] The adjacent grid detection sub-unit is used to terminate the detection of the adjacent grid if the connected component type of the adjacent grid to be tested is not closed.

[0164] Optionally, the average side length determination unit includes:

[0165] A carrier center region determination subunit is used to determine the carrier center region of the surface image of the carrier under test; the carrier center region includes multiple grids to be tested;

[0166] The grayscale mean determination subunit is used to determine the row grayscale mean of each pixel row within the central region of the carrier;

[0167] The total grayscale mean determination subunit is used to determine the total grayscale mean of the central region of the carrier based on the grayscale mean of each row.

[0168] The average side length determination subunit is used to determine the average side length corresponding to each of the measured grids based on the average gray level of each row and the average gray level of the total grid.

[0169] The catalyst support surface fine crack detection device provided in this embodiment of the invention can execute the catalyst support surface fine crack detection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0170] Example 5

[0171] Figure 5A schematic diagram of an electronic device 50 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0172] like Figure 5 As shown, the electronic device 50 includes at least one processor 51 and a memory, such as a read-only memory (ROM) 52 and a random access memory (RAM) 53, communicatively connected to the at least one processor 51. The memory stores computer programs executable by the at least one processor. The processor 51 can perform various appropriate actions and processes based on the computer program stored in the ROM 52 or loaded into the RAM 53 from storage unit 58. The RAM 53 can also store various programs and data required for the operation of the electronic device 50. The processor 51, ROM 52, and RAM 53 are interconnected via a bus 54. An input / output (I / O) interface 55 is also connected to the bus 54.

[0173] Multiple components in electronic device 50 are connected to I / O interface 55, including: input unit 56, such as keyboard, mouse, etc.; output unit 57, such as various types of monitors, speakers, etc.; storage unit 58, such as disk, optical disk, etc.; and communication unit 59, such as network card, modem, wireless transceiver, etc. Communication unit 59 allows electronic device 50 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0174] Processor 51 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 51 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 51 performs the various methods and processes described above, such as the method for detecting fine cracks on the surface of a catalyst support.

[0175] In some embodiments, the method for detecting fine cracks on the surface of a catalyst support can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 58. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 50 via ROM 52 and / or communication unit 59. When the computer program is loaded into RAM 53 and executed by processor 51, one or more steps of the method for detecting fine cracks on the surface of a catalyst support described above can be performed. Alternatively, in other embodiments, processor 51 can be configured to perform the method for detecting fine cracks on the surface of a catalyst support by any other suitable means (e.g., by means of firmware).

[0176] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0177] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0178] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0179] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0180] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0181] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0182] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0183] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for detecting fine cracks on the surface of a catalyst support, characterized in that, include: Acquire an image of the surface of the carrier under test; the image of the surface of the carrier under test includes multiple test grids; Based on the preset target detection area, region detection is performed on each grid to be tested in the surface image of the carrier to be tested to obtain at least one target grid to be tested corresponding to the surface image of the carrier to be tested. The connected component type of each target grid to be tested is closed; Based on the coordinates of the center pixel of each target grid to be tested, and based on the target detection area, determine the grid wall region corresponding to each target grid to be tested; Based on the grayscale value of each grid pixel in each grid wall region, determine the pixel evaluation value corresponding to each grid pixel in the corresponding grid wall region; Based on the pixel evaluation value corresponding to each grid pixel point in each grid wall region, fine cracks are detected in the target grid to be tested corresponding to the grid wall region.

2. The method according to claim 1, characterized in that, The step of determining the mesh wall region corresponding to each of the target meshes based on the center pixel coordinates of each target mesh and the target detection region includes: Based on the coordinates of the center pixel of each target grid to be tested, and based on the target detection area, the detection area corresponding to each target grid to be tested is determined; Binarization is performed on each of the grid regions to be detected to obtain the corresponding binarized grid regions to be detected. Region detection is performed on each of the binarized test grid regions to obtain the grid wall regions corresponding to each target test grid.

3. The method according to claim 1, characterized in that, The step of determining the pixel evaluation value corresponding to each grid pixel in the corresponding grid wall region based on the grayscale value of each grid pixel in each of the grid wall regions includes: Identify at least one grid pixel within the corresponding grid wall region; Using each of the grid pixels as the center coordinates, and based on the preset grid detection area, a target grid detection area corresponding to the corresponding grid pixel is constructed; The pixel evaluation value of the corresponding grid pixel is determined based on the gray value of each pixel within the target grid detection area.

4. The method according to claim 3, characterized in that, The step of determining the pixel evaluation value of the corresponding grid pixel based on the grayscale value of each pixel within the target grid detection area includes: Based on the gray values ​​of each pixel within the target grid detection area, determine the gray standard deviation and gray average value corresponding to the target grid detection area. The pixel evaluation value of the corresponding grid pixel is determined based on the grayscale standard deviation and the grayscale average value.

5. The method according to claim 1, characterized in that, The step of detecting fine cracks in the target mesh corresponding to the respective mesh wall region based on the pixel evaluation value corresponding to each mesh pixel point in each of the mesh wall regions includes: Based on the pixel evaluation value corresponding to each grid pixel point within each grid wall region, determine the target binarized image corresponding to the target grid to be tested; Based on the binarized images of each target, fine cracks in the corresponding target mesh are detected.

6. The method according to claim 5, characterized in that, The step of detecting fine cracks in the corresponding target mesh based on the binarized images of each target includes: Based on each of the target binarized images, determine the area of ​​the connected component corresponding to the target binarized image; Based on the area of ​​the connected domain and a preset crack detection condition, fine cracks in the corresponding target mesh to be tested are detected.

7. The method according to any one of claims 1-6, characterized in that, The step of performing region detection on each grid cell within the surface image of the carrier under test according to a preset target detection region to obtain at least one target grid cell corresponding to the surface image of the carrier under test includes: Determine the average side length corresponding to each of the grids to be measured; The target detection area is determined based on the average side length; From each grid to be tested in the surface image of the carrier to be tested, select any grid with a closed connected domain as the starting grid to be tested; Using the initial test grid as the detection starting point, region detection is performed sequentially on each adjacent test grid of the initial test grid until the region detection termination condition is met, thereby obtaining at least one target test grid corresponding to the surface image of the test carrier.

8. The method according to claim 7, characterized in that, The process of using the initial test grid as the detection starting point and sequentially performing region detection on each adjacent test grid of the initial test grid until the region detection termination condition is met includes: Using the initial grid to be tested as the detection starting point, region detection is performed sequentially on each of the adjacent grids to be tested of the initial grid to be tested; Determine whether the corresponding adjacent grid cells to be tested have not been detected; If so, determine whether the adjacent grid to be tested is within the detection area of ​​the surface image of the carrier to be tested; If so, determine whether the connected component type of the adjacent grid to be tested is closed; If not, then the detection of the adjacent grid cell to be tested will be terminated.

9. The method according to claim 7, characterized in that, Determining the average side length corresponding to each of the grids to be tested includes: The central region of the surface image of the carrier to be tested is determined; the central region of the carrier includes multiple grids to be tested; Determine the average grayscale value of each pixel row within the central region of the carrier; Based on the average grayscale value of each row, determine the total average grayscale value of the central region of the carrier; The average side length of each grid cell to be tested is determined based on the average gray level of each row and the average gray level of the total gray level.

10. A device for detecting fine cracks on the surface of a catalyst support, characterized in that, include: The carrier image acquisition module is used to acquire an image of the surface of the carrier under test; the image of the surface of the carrier under test includes multiple grids to be tested; The region detection module is used to perform region detection on each grid to be tested in the surface image of the carrier to be tested according to the preset target detection region, so as to obtain at least one target grid to be tested corresponding to the surface image of the carrier to be tested. The connected component type of each target grid to be tested is closed; The grid wall region determination module is used to determine the grid wall region corresponding to each of the target grids based on the coordinates of the center pixel of each target grid to be tested and the target detection region. The pixel evaluation value determination module is used to determine the pixel evaluation value corresponding to each grid pixel in the corresponding grid wall area based on the gray value of each grid pixel in each grid wall area. The crack detection module is used to detect fine cracks in the target mesh corresponding to the mesh wall region based on the pixel evaluation value corresponding to each mesh pixel point in each mesh wall region.

11. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method for detecting fine cracks on the surface of a catalyst support as described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for detecting fine cracks on the surface of a catalyst support as described in any one of claims 1-9.

Images