A method, system, device and medium for detecting an electrophoretic gas and liquid accumulation region

Abstract

The application discloses a kind of detection methods, systems, equipment and media of electrophoresis gas and liquid accumulation area, wherein the detection method is by obtaining the body-in-white data to be detected;The body-in-white data is two-dimensional slice processing, and slice image data set is obtained;Image contour identification processing is carried out to the slice image data set, and contour data set is obtained, the contour data set includes section data set and cross section data set, the section data set is the closed contour set of section image, and the cross section data set is the closed contour set of cross section image;According to the section data set, closed structured processing is carried out to the cross section data set, and detection result is obtained.The detection method can effectively reduce the time required for data preprocessing and analysis, reduce the computing resources required for data analysis, thereby effectively improving the detection efficiency of gas and liquid accumulation area.The application can be widely applied in the field of automobile electrophoresis technology.

Description

Technical Field

[0001] This invention relates to the field of automotive electrophoresis technology, and in particular to a method, system, equipment, and medium for detecting areas of gas and liquid accumulation in electrophoresis. Background Technology

[0002] In automobile manufacturing companies, the car body manufacturing process typically employs an immersion electrophoretic coating process. Electrophoretic coating utilizes an external electric field to cause pigments and resin particles suspended in an electrophoretic solution to migrate directionally and deposit onto the surface of a substrate, which is one of the electrodes. However, due to potential issues such as internal air bubbles and electrophoretic solution residues during the electrophoretic coating process, it is usually necessary to identify potential air and / or liquid accumulation areas on the car body using digital models before the electrophoretic coating process begins.

[0003] Currently, traditional methods for detecting gas and liquid accumulation in electrophoresis typically require converting CAD-formatted vehicle body data into STL mesh data before analysis. This method necessitates manual data preprocessing, which is time-consuming. Furthermore, after the data preprocessing stage, the data analysis requires significant computing resources and is also time-consuming.

[0004] Therefore, the problems existing in the current technology still need to be solved and optimized. Summary of the Invention

[0005] The purpose of this invention is to at least partially solve one of the technical problems existing in the related art.

[0006] Therefore, one objective of this invention is to provide a method for detecting gas- and liquid-accumulated regions in electrophoresis. This method can effectively reduce the time required for data preprocessing and analysis, reduce the computing resources required for data analysis, and thus effectively improve the detection efficiency of gas- and liquid-accumulated regions.

[0007] Another objective of this application is to provide a detection system for electrophoretic gas and liquid accumulation areas.

[0008] To achieve the above-mentioned technical objectives, the technical solutions adopted in the embodiments of this application include:

[0009] In a first aspect, embodiments of this application provide a method for detecting electrophoretic gas and liquid accumulation regions, including:

[0010] Obtain the data of the white body to be inspected;

[0011] The white body data is subjected to two-dimensional slicing to obtain a sliced ​​image dataset;

[0012] The slice image dataset is subjected to image contour recognition processing to obtain a contour dataset, which includes a section dataset and a cross-section dataset. The section dataset is a set of closed contours of the section image, and the cross-section dataset is a set of closed contours of the cross-section image.

[0013] Based on the cross-section dataset, the cross-section dataset is subjected to closed structure processing to obtain the detection results.

[0014] In addition, the method for detecting electrophoretic gas and liquid accumulation areas according to the above embodiments of this application may also have the following additional technical features:

[0015] Furthermore, in one embodiment of this application, the step of performing two-dimensional slicing processing on the white body data to obtain a sliced ​​image dataset includes:

[0016] Obtain the preset step threshold and step size threshold;

[0017] The white body data is subjected to view transformation processing to obtain a view dataset;

[0018] Based on the step threshold and the step size threshold, the view dataset is subjected to step slicing processing to obtain the sliced ​​image dataset.

[0019] Furthermore, in one embodiment of this application, before the step of performing image contour recognition processing on the sliced ​​image dataset to obtain a contour dataset, the detection method further includes:

[0020] The slice image dataset is processed by generating cross-sectional images and cross-sectional images from the current slice image dataset to obtain an image dataset;

[0021] The image dataset is preprocessed to obtain the updated slice image dataset.

[0022] Furthermore, in one embodiment of this application, the preprocessing of the image dataset to obtain the updated sliced ​​image dataset includes:

[0023] The image dataset is subjected to weighted grayscale conversion to obtain a grayscale image dataset;

[0024] Perform grayscale inversion processing on the grayscale image dataset to obtain a grayscale inverted image dataset;

[0025] The grayscale inverted image dataset is binarized to obtain the updated slice image dataset.

[0026] Furthermore, in one embodiment of this application, the step of performing image contour recognition processing on the sliced ​​image dataset to obtain a contour dataset includes:

[0027] The sliced ​​image dataset is subjected to morphological erosion processing to obtain an eroded image dataset;

[0028] The erosion image dataset is subjected to sharpening gradient processing to obtain a gradient image dataset;

[0029] Edge fitting processing is performed on the gradient image dataset to obtain the contour dataset.

[0030] Furthermore, in one embodiment of this application, the step of performing closed-structure processing on the cross-section dataset based on the cross-section dataset to obtain the detection result includes:

[0031] The cross-sectional dataset is subjected to effective cross-sectional contour extraction processing to obtain an intermediate dataset;

[0032] Based on the cross-section dataset, contour matching processing is performed on the intermediate dataset to obtain the region dataset;

[0033] The detection results are obtained by performing regional structuring processing on the aforementioned regional dataset.

[0034] Furthermore, in one embodiment of this application, the step of performing regional structuring processing on the regional dataset to obtain the detection result includes:

[0035] Perform region connectivity processing on the aforementioned regional dataset to obtain a connected dataset;

[0036] Perform top-bottom validation on the connected dataset to obtain a closed-structure dataset;

[0037] The closed-structure dataset is effectively extended to obtain an extended dataset;

[0038] The extended dataset is restructured to obtain the detection results.

[0039] Secondly, embodiments of this application provide a detection system for electrophoretic gas and liquid accumulation regions, comprising:

[0040] The acquisition module is used to acquire the data of the white body to be inspected;

[0041] The slicing module is used to perform two-dimensional slicing processing on the white body data to obtain a sliced ​​image dataset.

[0042] The recognition module is used to perform image contour recognition processing on the slice image dataset to obtain a contour dataset. The contour dataset includes a section dataset and a cross-section dataset. The section dataset is a set of closed contours of the section image, and the cross-section dataset is a set of closed contours of the cross-section image.

[0043] The processing module is used to perform closed-structure processing on the cross-section dataset based on the cross-section dataset to obtain the detection results.

[0044] Thirdly, embodiments of this application also provide an electronic device, including:

[0045] At least one processor;

[0046] At least one memory for storing at least one program;

[0047] When the at least one program is executed by the at least one processor, the at least one processor implements the method of the first aspect described above.

[0048] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a processor-executable program, which, when executed by the processor, is used to implement the method of the first aspect described above.

[0049] The advantages and beneficial effects of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application:

[0050] This application discloses a method, system, device, and medium for detecting electrophoretic gas and liquid accumulation regions. The method involves acquiring white body data to be detected; performing two-dimensional slicing on the white body data to obtain a slice image dataset; performing image contour recognition processing on the slice image dataset to obtain a contour dataset, which includes a section dataset and a cross-sectional dataset. The section dataset is a set of closed contours of section images, and the cross-sectional dataset is a set of closed contours of cross-sectional images. Based on the section dataset, a closed-structure processing is performed on the cross-sectional dataset to obtain the detection result. This detection method transforms the three-dimensional problem of identifying gas and liquid accumulation regions into a two-dimensional problem through two-dimensional slicing and image contour recognition of the white body data. This effectively reduces the time required in the data preprocessing stage. Furthermore, the closed-structure processing of the section and cross-sectional datasets effectively reduces the computational resources required in the data analysis stage, thereby effectively improving the detection efficiency of gas and liquid accumulation regions. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following description is provided with accompanying drawings of the relevant technical solutions in the embodiments of this application or the prior art. It should be understood that the accompanying drawings described below are only for the purpose of clearly illustrating some embodiments of the technical solutions in this application. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0052] Figure 1 A schematic flowchart illustrating a method for detecting electrophoretic gas and liquid accumulation areas provided in an embodiment of this application;

[0053] Figure 2 A schematic diagram illustrating a color view conversion of a white body panel provided in an embodiment of this application;

[0054] Figure 3 A schematic diagram of a cubic containing box provided in an embodiment of this application;

[0055] Figure 4 This is a schematic diagram of a sliced ​​image in an image contour recognition process provided in an embodiment of this application;

[0056] Figure 5 This application provides a schematic diagram of a closed contour recognition image corresponding to a certain cross-sectional image.

[0057] Figure 6 An image illustration of contour matching processing provided in this application embodiment;

[0058] Figure 7 A schematic diagram of a cross-sectional image of a white body sheet after slicing, provided for an embodiment of this application;

[0059] Figure 8 A schematic diagram of the structure of a detection system for electrophoretic gas and liquid accumulation areas provided in an embodiment of this application;

[0060] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0061] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application. The step numbers in the following embodiments are set only for ease of explanation, and there is no limitation on the order between the steps. The execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0062] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0063] Currently, traditional methods for detecting gas and liquid accumulation in electrophoresis typically require converting CAD-formatted vehicle body data into STL mesh data before analysis. This method necessitates manual data preprocessing, which is time-consuming. Furthermore, after the data preprocessing stage, the data analysis requires significant computing resources and is also time-consuming.

[0064] In view of this, embodiments of the present invention provide a method for detecting gas- and liquid-accumulated regions in electrophoresis. This method can effectively reduce the time required for data preprocessing and analysis, reduce the computing resources required for data analysis, and thus effectively improve the detection efficiency of gas- and liquid-accumulated regions.

[0065] Reference Figure 1 In this application embodiment, a method for detecting electrophoretic gas and liquid accumulation areas includes:

[0066] Step 110: Obtain the data of the white body to be inspected;

[0067] Step 120: Perform two-dimensional slicing on the white body data to obtain a sliced ​​image dataset;

[0068] Step 120 involves performing two-dimensional slicing on the white body data to obtain a sliced ​​image dataset, including:

[0069] Step 121: Obtain the preset step threshold and step size threshold;

[0070] Step 122: Perform view transformation processing on the white body data to obtain a view dataset;

[0071] Step 123: Perform step slicing processing on the view dataset according to the step threshold and the step size threshold to obtain the sliced ​​image dataset.

[0072] In this embodiment, the body-in-white data can be body data that has not yet been painted. After obtaining the body-in-white data to be inspected, data modeling can first be performed based on the body-in-white data to obtain a digital model of the body-in-white corresponding to the body-in-white data. This can be specifically implemented using NX Unigraphics software. The view transformation processing of the body-in-white data can be performed by traversing and searching the sheets of the digital model of the body-in-white to obtain all sheets corresponding to the inking of the body-in-white. Then, the color view of each sheet is transformed to obtain several view-transformed sheet views. Finally, all sheet views are used as a view dataset. For example, refer to... Figure 2 For a certain body white sheet, the color view of the sheet can be converted into a black and white view. The example in this application is only for illustration and does not constitute any limitation on this application. In other optional embodiments, different target colors can also be set and the color view of the sheet can be converted according to the target colors.

[0073] It is understood that the step threshold is used to characterize the inter-sectional spacing of the body-in-white sheet view slices, and its specific value can be any one of 1mm, 2mm, 5mm, etc., while the step size threshold is used to characterize the inter-sectional spacing of the body-in-white sheet view slices, and its specific value can also be any one of 1mm, 2mm, 5mm, etc., and can be set according to the actual situation. In this embodiment, the step threshold is 2mm and the step size threshold is 1mm as an example. The step slicing process can first determine the minimum containment area corresponding to all body-in-white sheets based on all body-in-white sheet views in the view dataset. This minimum containment area can be a circular, spherical, or cubic containment box, as shown in the reference. Figure 3 In this embodiment of the application, taking a cube containing the smallest enclosing region as an example, the starting position and the ending position in the cube containing the region can be determined first based on the three-dimensional coordinates of the cube containing the region. The starting position can be a vertex in the cube containing the region, and the ending position can be the diagonal point opposite to the vertex of the starting position. Then, starting from the starting position, the sheet view in the cube containing the region is sliced ​​in the sectional direction according to the step threshold, and the sheet view in the cube containing the region is sliced ​​in the cross-sectional direction according to the step size threshold, until the sectional position and / or cross-sectional position of the sliced ​​section reaches the ending position and then stops.

[0074] For example, the coordinates of the largest point of the cube's containing box can be used as the starting position (i.e., Figure 3 The vertex where the red circle is located), and the coordinates of the smallest point of the cube's containing box are used as the termination position (i.e., Figure 3The vertex position of the green circle in the middle is used as the negative direction of the vertical axis (Z axis) as the cross-section normal. Then, according to the step size threshold and the step threshold, all sheet views in the cube's containing box are stepped sliced, and all the sliced ​​surface images and cross-section images are used as the slice image dataset.

[0075] Step 130: Perform image contour recognition processing on the slice image dataset to obtain a contour dataset. The contour dataset includes a section dataset and a cross-section dataset. The section dataset is a set of closed contours of the section image, and the cross-section dataset is a set of closed contours of the cross-section image.

[0076] Step 130 involves performing image contour recognition processing on the sliced ​​image dataset to obtain a contour dataset, including:

[0077] Step 131: Perform morphological erosion processing on the sliced ​​image dataset to obtain an eroded image dataset;

[0078] Step 132: Perform sharpening gradient processing on the erosion image dataset to obtain a gradient image dataset;

[0079] Step 133: Perform edge fitting processing on the gradient image dataset to obtain the contour dataset.

[0080] In this embodiment of the application, the cross-sectional images and section images of the slice image dataset are both black and white color views. For a certain cross-sectional image in the slice image dataset (i.e. Figure 4 The original image shown can be processed by performing a center traversal on the pixels in the cross-sectional image. If the pixels around a pixel are all white, the pixel is kept white; otherwise, the pixel is changed to black. The same process is applied to other cross-sectional images and cross-sectional images to obtain the eroded image dataset.

[0081] Understandably, for a cross-sectional image after morphological erosion, the sharpening gradient processing can involve sequentially sharpening and gradient processing the cross-sectional image. Specifically, firstly, the cross-sectional image can be smoothed using a low-pass filter to obtain a low-frequency component image corresponding to the cross-sectional image. Then, based on the image difference between the cross-sectional image and the low-frequency component image, a template image corresponding to the cross-sectional image is determined. Finally, the sharpened cross-sectional image is determined based on the template image and the cross-sectional image. The same process applies to other cross-sectional images and section images. It is also understandable that the equivalent formula for the sharpened cross-sectional image can be expressed as:

[0082] g = src + k × m

[0083] Where g represents the sharpened cross-sectional image, src represents the cross-sectional image after morphological erosion, k is a preset coefficient, and m is the template image.

[0084] It should be noted that gradient processing can involve performing convolution operations on the sharpened slice image and / or cross-sectional image using two 3x3 matrices respectively. One matrix is ​​used to detect horizontal edges, and the other matrix is ​​used to detect vertically opposite edges. Then, the two matrices are merged with the convolution results of the slice image and / or cross-sectional image to obtain the gradient image corresponding to the slice image and / or cross-sectional image. A gradient image dataset is then generated from all slice gradient images corresponding to slice images and all cross-sectional gradient images corresponding to cross-sectional images. Specifically, the two 3x3 matrices can be Scharr operators. The examples in this application are for illustrative purposes only and do not constitute any limitation on this application.

[0085] It is worth mentioning that edge fitting processing can include edge acquisition processing and curve fitting processing. Specifically, edge acquisition processing can be based on the Laplace operator, combining the gradient and pixel position in the gradient image (including cross-sectional gradient image and section gradient image), to determine the gradient at the anchor point in the gradient image as a weighted sum of the pixel values ​​in the neighborhood of that anchor point, thereby obtaining the edge image; while curve fitting processing can be based on the Bezier curve, performing curve fitting on the edge image, and then using all the curve-fitted cross-sectional image contours as a contour dataset. It is also worth mentioning that the embodiments of this application... Figure 4 This application only shows the image contour recognition process for a certain cross-section image. For other cross-section images and cross-sectional images, the process can be easily deduced by analogy, and will not be elaborated further here.

[0086] Step 140: Based on the cross-section dataset, perform closed-structure processing on the cross-section dataset to obtain the detection results.

[0087] Step 140 involves performing closed-structure processing on the cross-section dataset based on the cross-section dataset to obtain the detection results, including:

[0088] Step 141: Perform effective cross-sectional contour extraction processing on the cross-sectional dataset to obtain an intermediate dataset;

[0089] Step 142: Based on the cross-section dataset, perform contour matching processing on the intermediate dataset to obtain the region dataset;

[0090] In this embodiment, for a cross-sectional image in the cross-sectional dataset, the effective cross-sectional contour extraction process first involves identifying the closed contours of the cross-sectional image to obtain several closed contour recognition images. These images record the contour type of the closed contours in the corresponding cross-sectional image, which can be categorized into leaky closed contours and depositional closed contours. Then, the closed contour recognition images are filtered. If a depositional closed contour contains a leaky closed contour, the depositional closed contour of the cross-sectional image is considered an invalid closed contour; otherwise, it is considered a valid closed contour. The same applies to other cross-sectional images. Finally, an intermediate dataset is generated based on all valid depositional closed contours.

[0091] For example, refer to Figure 5 , Figure 5 For a closed contour recognition image corresponding to a certain cross-sectional image, in Figure 5 In the image, when the closed profile of a cross section (i.e., the green line outline in the figure) is filled with black, it is a depositional closed profile; while when the closed profile of a cross section is filled with white, it is a leakage closed profile. The depositional closed profile of this cross section image is an invalid closed profile.

[0092] Understandably, referring to Figure 6 For a valid closed contour in the intermediate dataset, the contour matching process can first obtain a preset region threshold, and then match the closed contours of all cross-sectional images in the cross-sectional dataset. Figure 6 The cut-off closed profile shown), for this effective closed profile ( Figure 6 The effective closed contours (shown) are matched for overlap rate. When the overlap rate is greater than the region threshold, the effective closed contour is taken as a closed region. The same applies to the remaining effective closed contours. Then, all the obtained closed regions are combined to obtain the region dataset. It can also be understood that the region threshold can be set according to the actual situation, such as any one of 0.8, 0.9, 0.95, etc. The example in this application is only for illustration.

[0093] Step 143: Perform regional structuring processing on the regional dataset to obtain the detection results.

[0094] Step 143, performing region structuring processing on the region dataset to obtain the detection results, includes:

[0095] Step 1431: Perform regional connectivity processing on the regional dataset to obtain a connected dataset;

[0096] Step 1432: Perform top-bottom validation on the connected dataset to obtain a closed-structure dataset;

[0097] Step 1433: Perform effective extension processing on the closed-structure dataset to obtain an extended dataset;

[0098] Step 1434: Perform structural reconstruction processing on the extended dataset to obtain the detection results.

[0099] In this embodiment of the application, the region connectivity processing can be performed on the region dataset to determine the region connectivity. If the closed regions located at two adjacent cross sections interfere with each other in the XY plane, then the closed regions located at the two adjacent cross sections are connected to each other; otherwise, they are not connected to each other. Then, based on the result of the mutual connectivity determination, the region dataset is filtered to obtain a connected dataset.

[0100] It is understood that the top-bottom verification process is used to filter all closed regions in the connected dataset to determine the closed structure and its top and bottom. For example, in this embodiment, the connected dataset consists of a first connected subset and a second connected subset. When any two closed regions in the first connected subset are connected, and no closed region in the first connected subset is connected to any closed region in the second connected subset, then the first connected subset can be considered as a set of closed region data for a certain closed structure. It is also understood that the examples in this application are for illustrative purposes only and do not constitute any limitation on this application. For example, the connected dataset can consist of more connected subsets, and in practical applications, all closed regions in the connected dataset can be filtered to determine several closed structures existing in the connected dataset. Furthermore, for a given closed structure, the top and bottom of the closed structure can be obtained based on the first connected subset corresponding to the closed structure. Specifically, in the first connected subset, if a closed region does not have a lower-level closed region connected to it, the closed region can be considered as one of the bottoms of the closed structure; and if a closed region does not have an upper-level closed region connected to it, the closed region can be considered as one of the tops of the closed structure. The same applies to the other closed structures. Finally, all the obtained closed structures, as well as the top and bottom data corresponding to each closed structure, are integrated to obtain the closed structure dataset.

[0101] It is worth mentioning that, for a certain closed structure, the effective extension processing includes top effective verification processing, bottom effective verification processing, and structural effective verification processing. The bottom effective verification processing is used to verify the effectiveness of the bottom of the closed structure. Specifically, the bottom effective verification processing can be performed by drawing a ray downward from a certain inner point of a certain bottom of the closed structure. When the distance between the interference points is less than the bottom threshold, this bottom of the closed structure is regarded as the effective bottom of the closed structure. The other bottoms are treated similarly. The top effective verification processing is similar to the bottom effective verification processing and can be easily deduced by analogy. In addition, the bottom threshold can also be set according to the actual situation. The specific value can be any one of 0.5mm, 1mm, 2mm, etc., which will not be elaborated further in this application.

[0102] It should be noted that the valid structural verification process can be performed on any closed region of the closed structure. Specifically, it can be to determine whether there is a valid closed structure top that is lower than the closed region in the vertical direction. If the result is that there is, the closed region can be regarded as an invalid closed region. The same applies to the other closed regions. In this way, all the remaining valid closed regions of the closed structure are obtained, and all the remaining valid closed regions are used as the extended dataset.

[0103] It is worth noting that after obtaining the extended dataset, the structural reconstruction process can be based on all the remaining effective closed regions in the extended dataset, combined with the interlayer relationships between these effective closed regions, to stack them to obtain a more accurate closed structure. This closed structure is the gas and liquid accumulation risk area (i.e., the detection result) corresponding to the input white body data.

[0104] In some embodiments, prior to step 130, which involves performing image contour recognition processing on the sliced ​​image dataset to obtain a contour dataset, the detection method further includes:

[0105] Step 150: The slice image dataset is processed by generating cross-sectional images and cross-sectional images from the current slice image dataset to obtain an image dataset;

[0106] In the embodiments of this application, reference is made to Figure 7 , Figure 7 The large image in the image is a cross-sectional image, and the smaller image in the upper left corner is a sliced ​​image of the body-in-white panel. Body-in-white data typically consists of data from multiple automotive parts; therefore, after performing two-dimensional slicing on the body-in-white data, sliced ​​images and cross-sectional images can be generated based on the sliced ​​body-in-white panel view. In an optional implementation, the panel view slices can be adjusted before generating the sliced ​​images and cross-sectional images to display the target part and hide the remaining parts, thereby enabling the detection of localized areas of gas or liquid accumulation and further saving computational resources.

[0107] Step 160: Preprocess the image dataset to obtain the updated slice image dataset.

[0108] Step 160, preprocessing the image dataset to obtain the updated sliced ​​image dataset, includes:

[0109] Step 161: Perform weighted grayscale processing on the image dataset to obtain a grayscale image dataset;

[0110] Step 162: Perform grayscale inversion processing on the grayscale image dataset to obtain a grayscale inverted image dataset;

[0111] Step 163: Binarize the grayscale inverted image dataset to obtain the updated slice image dataset.

[0112] In this embodiment, for a cross-sectional image in the image dataset, weighted grayscale processing can be performed by weighted averaging. Specifically, a channel weight can be preset for each of the red, green, and blue channels in the cross-sectional image. The specific channel weights can be set according to actual conditions. Grayscale inversion processing can be performed by inverting the brightness of the grayscale cross-sectional image. Binarization processing can be performed by binarizing each pixel in the cross-sectional image according to a preset binarization threshold. When the pixel value of a pixel is greater than the binarization threshold, the pixel value is updated to 255; when the pixel value of a pixel is less than or equal to the binarization threshold, the pixel value is updated to 0. The specific binarization threshold can be set according to actual conditions. For example, the value of the binarization threshold can be any one of 100, 123, 155, etc. Furthermore, the other cross-sectional images and cross-sectional images in the image dataset are similar and can be easily deduced by analogy. This application will not elaborate further here.

[0113] The detection system for electrophoretic gas and liquid accumulation areas according to embodiments of this application is described in detail below with reference to the accompanying drawings.

[0114] Reference Figure 8 The detection system for electrophoretic gas and liquid accumulation areas proposed in this application includes:

[0115] The acquisition module 101 is used to acquire the white body data to be detected;

[0116] The slicing module 102 is used to perform two-dimensional slicing processing on the white body data to obtain a sliced ​​image dataset;

[0117] The recognition module 103 is used to perform image contour recognition processing on the slice image dataset to obtain a contour dataset. The contour dataset includes a section dataset and a cross-section dataset. The section dataset is a set of closed contours of the section image, and the cross-section dataset is a set of closed contours of the cross-section image.

[0118] The processing module 104 is used to perform closed-structure processing on the cross-section dataset based on the cross-section dataset to obtain the detection result.

[0119] It is understood that the content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0120] Reference Figure 9 This application also provides an electronic device, including:

[0121] At least one processor 201;

[0122] At least one memory 202 is used to store at least one program;

[0123] When the at least one program is executed by the at least one processor 201, the at least one processor 201 implements the method embodiment described above.

[0124] Similarly, it can be understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0125] This application also provides a computer-readable storage medium storing a program executable by a processor 201, which, when executed by the processor 201, is used to implement the above-described method embodiments.

[0126] Similarly, the content of the above method embodiments is applicable to the present computer-readable storage medium embodiments. The specific functions implemented by the present computer-readable storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0127] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this application are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0128] Furthermore, although this application is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding this application. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional technology for an engineer. Therefore, those skilled in the art can implement the application set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of this application, which is determined by the full scope of the appended claims and their equivalents.

[0129] If a function 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, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0130] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0131] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0132] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0133] In the foregoing description of this specification, the references to terms such as "one embodiment," "another embodiment," or "some embodiments," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0134] Although embodiments of this application have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the claims and their equivalents.

[0135] The above is a detailed description of the preferred embodiments of this application, but this application is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application, and these equivalent modifications or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A method for detecting regions of gas and liquid accumulation in electrophoresis, characterized in that, include: Obtain the data of the white body to be inspected; The white body data is subjected to two-dimensional slicing to obtain a sliced ​​image dataset; The slice image dataset is subjected to image contour recognition processing to obtain a contour dataset, which includes a section dataset and a cross-section dataset. The section dataset is a set of closed contours of the section image, and the cross-section dataset is a set of closed contours of the cross-section image. Based on the cross-section dataset, the cross-section dataset is subjected to closed-structure processing to obtain the detection results; The step of performing closed-structure processing on the cross-section dataset based on the cross-section dataset to obtain the detection results includes: The cross-sectional dataset is subjected to effective cross-sectional contour extraction processing to obtain an intermediate dataset; Based on the cross-section dataset, contour matching processing is performed on the intermediate dataset to obtain the region dataset; The detection results are obtained by performing regional structuring processing on the aforementioned regional dataset. The process of performing regional structuring on the regional dataset to obtain the detection results includes: The region dataset is subjected to region connectivity processing to obtain a connected dataset; the region connectivity processing is used to determine the region connectivity of the region dataset. If the closed regions of two adjacent layers interfere with each other on the plane, it is determined that the closed regions of the two adjacent layers are connected to each other. The connected dataset is subjected to top-bottom validation to obtain a closed structure dataset. The top-bottom validation is used to filter all closed regions in the connected dataset to determine the closed structure and the top and bottom of the closed structure. If a closed region does not have a lower closed region connected to it, the closed region is one of the bottoms of the closed structure. If a closed region does not have an upper closed region connected to it, the closed region is one of the tops of the closed structure. The closed structure dataset is subjected to effective extension processing to obtain an extended dataset. The effective extension processing is used to verify the validity of the bottom, top, and closed region of the closed structure. A ray is drawn downward from the inner point of the bottom of the closed structure. When the distance between the interference points is less than the bottom threshold, the bottom of the closed structure is considered as the valid bottom of the closed structure. A ray is drawn upward from the inner point of the top of the closed structure. When the distance between the interference points is less than the top threshold, the top of the closed structure is considered as the valid top of the closed structure. It is determined whether there is a valid top of the closed structure that is lower than the closed region in the vertical direction. When the determination result is yes, the closed region is considered as an invalid closed region, so as to obtain all the remaining valid closed regions of the closed structure. The extended dataset is subjected to structural reconstruction processing to obtain the detection results; the structural reconstruction processing is used to stack all remaining valid closed regions in the extended dataset, combined with the interlayer relationship between the valid closed regions.

2. The method for detecting electrophoretic gas and liquid accumulation areas according to claim 1, characterized in that, The process of performing two-dimensional slicing on the white body data to obtain a sliced ​​image dataset includes: Obtain the preset step threshold and step size threshold; The white body data is subjected to view transformation processing to obtain a view dataset; Based on the step threshold and the step size threshold, the view dataset is subjected to step slicing processing to obtain the sliced ​​image dataset.

3. The method for detecting electrophoretic gas and liquid accumulation areas according to claim 1, characterized in that, Before the step of performing image contour recognition processing on the sliced ​​image dataset to obtain the contour dataset, the detection method further includes: The slice image dataset is processed by generating cross-sectional images and cross-sectional images from the current slice image dataset to obtain an image dataset; The image dataset is preprocessed to obtain the updated slice image dataset.

4. The method for detecting electrophoretic gas and liquid accumulation areas according to claim 3, characterized in that, The preprocessing of the image dataset to obtain the updated sliced ​​image dataset includes: The image dataset is subjected to weighted grayscale conversion to obtain a grayscale image dataset; Perform grayscale inversion processing on the grayscale image dataset to obtain a grayscale inverted image dataset; The grayscale inverted image dataset is binarized to obtain the updated slice image dataset.

5. The method for detecting electrophoretic gas and liquid accumulation areas according to claim 1, characterized in that, The step of performing image contour recognition processing on the sliced ​​image dataset to obtain a contour dataset includes: The sliced ​​image dataset is subjected to morphological erosion processing to obtain an eroded image dataset; The erosion image dataset is subjected to sharpening gradient processing to obtain a gradient image dataset; Edge fitting processing is performed on the gradient image dataset to obtain the contour dataset.

6. A detection system for electrophoretic gas and liquid accumulation areas, characterized in that, include: The acquisition module is used to acquire the data of the white body to be inspected; The slicing module is used to perform two-dimensional slicing processing on the white body data to obtain a sliced ​​image dataset. The recognition module is used to perform image contour recognition processing on the slice image dataset to obtain a contour dataset. The contour dataset includes a section dataset and a cross-section dataset. The section dataset is a set of closed contours of the section image, and the cross-section dataset is a set of closed contours of the cross-section image. The processing module is used to perform closed-structure processing on the cross-section dataset based on the cross-section dataset to obtain the detection result; The step of performing closed-structure processing on the cross-section dataset based on the cross-section dataset to obtain the detection results includes: The cross-sectional dataset is subjected to effective cross-sectional contour extraction processing to obtain an intermediate dataset; Based on the cross-section dataset, contour matching processing is performed on the intermediate dataset to obtain the region dataset; The detection results are obtained by performing regional structuring processing on the aforementioned regional dataset. The process of performing regional structuring on the regional dataset to obtain the detection results includes: The region dataset is subjected to region connectivity processing to obtain a connected dataset; the region connectivity processing is used to determine the region connectivity of the region dataset. If the closed regions of two adjacent layers interfere with each other on the plane, it is determined that the closed regions of the two adjacent layers are connected to each other. The connected dataset is subjected to top-bottom validation to obtain a closed structure dataset. The top-bottom validation is used to filter all closed regions in the connected dataset to determine the closed structure and the top and bottom of the closed structure. If a closed region does not have a lower closed region connected to it, the closed region is one of the bottoms of the closed structure. If a closed region does not have an upper closed region connected to it, the closed region is one of the tops of the closed structure. The closed structure dataset is subjected to effective extension processing to obtain an extended dataset. The effective extension processing is used to verify the validity of the bottom, top, and closed region of the closed structure. A ray is drawn downward from the inner point of the bottom of the closed structure. When the distance between the interference points is less than the bottom threshold, the bottom of the closed structure is considered as the valid bottom of the closed structure. A ray is drawn upward from the inner point of the top of the closed structure. When the distance between the interference points is less than the top threshold, the top of the closed structure is considered as the valid top of the closed structure. It is determined whether there is a valid top of the closed structure that is lower than the closed region in the vertical direction. When the determination result is yes, the closed region is considered as an invalid closed region, so as to obtain all the remaining valid closed regions of the closed structure. The extended dataset is subjected to structural reconstruction processing to obtain the detection results; the structural reconstruction processing is used to stack all remaining valid closed regions in the extended dataset, combined with the interlayer relationship between the valid closed regions.

7. An electronic device, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method as described in any one of claims 1-5.

8. A computer-readable storage medium storing a processor-executable program, characterized in that, The processor-executable program, when executed by the processor, is used to implement the method as described in any one of claims 1-5.

Images