Method and device for detecting ternary material metal particles

Abstract

The invention provides a ternary material metal particle detection method and device, and the method comprises the steps: building a target high-precision XY stable motion platform, placing metal particles of metal foreign matters of a target ternary material, carrying out the partitioning of a filter membrane corresponding to the metal particles, and obtaining different regions of the filter membrane, continuously shooting the metal particles under a preset multi-directional light source through a target high-pixel camera at a target time to obtain first photos of all areas of the filter membrane, splicing the first photos of all the areas of the filter membrane to obtain a second photo, and preprocessing the second photo to obtain a pre-processed metal particle; performing binarization segmentation on the preprocessed second photo to obtain a segmented second photo, performing morphological optimization on the segmented second photo, calculating image features of the optimized second photo and determining an image feature threshold range corresponding to the image features, and judging the type of the metal particles in the second picture based on the image features and the image feature threshold range.

Description

Technical Field

[0001] This application relates to the field of metal foreign object detection technology, and more specifically, to a method and apparatus for detecting ternary material metal particles. Background Technology

[0002] Metal particle detection is a crucial technology in many industries, primarily used to ensure product and personal safety, implement precise quality control, and perform predictive equipment maintenance.

[0003] Currently, in patent CN110243732B, a full-process slurry grinding particle size online detection system with a particle size range of 2-500um is proposed. The image recognition mechanism takes pictures of the ore sample from multiple angles and performs three-dimensional reconstruction on the ore sample pictures obtained from the multiple angles to obtain the reconstructed ore sample particle shape. The size of the ore sample particles is calculated based on the particle shape. In patent CN109387460A, a polarized light-based analysis system identifies metal particles through polarized light.

[0004] However, the CN110243732B patent uses a single-shot acquisition method to collect information, which involves collecting data from all particles. This results in generally low acquisition and detection efficiency. Furthermore, the metal particles in ternary materials require high magnification to be observed, and single-shot acquisition places high demands on pixel hardware, making it difficult to achieve high magnification. In the CN109387460A patent, the measurement process is lengthy, resulting in generally low detection efficiency. Summary of the Invention

[0005] In view of this, the purpose of this application is to provide a method and apparatus for detecting metal particles in ternary materials. This method uses a high-resolution camera combined with a multi-directional light source to capture and stitch images of the metal particles in the ternary material foreign object. The second image is then preprocessed, binarized, segmented, and morphologically optimized. Finally, the type of metal particles in the second image is determined based on image features and image feature threshold ranges. This eliminates the need to collect all particles. Furthermore, by using a target-equipped high-precision XY-stabilized motion platform to segment the shooting area, high-magnification magnification of the metal particles is achieved, enabling accurate identification of the particle type. In addition, this method reduces the time required for metal particle detection and improves detection efficiency.

[0006] In a first aspect, embodiments of this application provide a method for detecting ternary material metal particles, the method comprising: A high-precision XY stable motion platform for the target is established, and metal particles of the target ternary material are placed there. The filter membrane corresponding to the metal particles is divided into different regions of the filter membrane. The metal particles are continuously photographed by a target high-pixel camera under a preset multi-directional light source for a target time period to obtain the first image of each region of the filter membrane. The first images of each region of the filter membrane are stitched together to obtain a second image, and the second image is preprocessed to obtain a preprocessed second image. The preprocessed second image is binarized and segmented to obtain the segmented second image, and the segmented second image is then morphologically optimized. Calculate the image features of the optimized second photo and determine the image feature threshold range corresponding to the image features. Based on the image features and the image feature threshold range, determine the category of metal particles in the second photo.

[0007] In one possible implementation, partitioning the filter membrane corresponding to the metal particles includes: Obtain a mapping table of filter membrane diameter and number of partitions to determine the diameter of the filter membrane; The corresponding number of partitions is obtained by matching the diameter of the filter membrane in the mapping table, and the filter membrane is partitioned based on the number of partitions.

[0008] In one possible implementation, the method further includes: Determine the movement range of the target high-precision XY stabilized motion platform; wherein, the movement range includes the longitudinal movement range and the lateral movement range; The movement of the target high-precision XY stabilized motion platform is limited by the movement range of the target high-precision XY stabilized motion platform.

[0009] In one possible implementation, the preprocessing of the second photograph includes: The color information of the second photo is converted into the corresponding black and white information, and the histogram cropping intensity range of the preset histogram equalization algorithm is determined. The contrast of the second photo is enhanced by the histogram equalization algorithm within the histogram cropping intensity range to obtain an enhanced second photo; wherein the enhanced second photo represents an enhanced grayscale image.

[0010] In one possible implementation, the binarization segmentation of the preprocessed second image includes: Determine the target adaptive threshold function; Based on the target adaptive threshold function, the image information of the preprocessed second photo is converted into binary image information to obtain the segmented second photo.

[0011] In one possible implementation, the morphological optimization of the segmented second photograph includes: The segmented second image is subjected to an opening operation based on a preset opening operation combination to remove noise from the second image; Identify the particle connectivity regions in the second image and remove particle connectivity regions whose area is smaller than a preset area threshold.

[0012] In one possible implementation, the image features include at least the particle area, roundness, aspect ratio, and surface roughness; determining the type of metal particles in the second photograph based on the image features and the image feature threshold range includes: When the area is within a first area threshold range, the aspect ratio is within a first aspect ratio threshold range, and the surface roughness is within a first surface roughness threshold range, the type of the metal particles is determined. When the area is within the second area threshold range and the aspect ratio is within the second aspect ratio threshold range, the metal particle is determined to be a fiber. When the area is within the third area threshold range and the surface roughness is within the second surface roughness threshold range, the metal particle is classified as a bubble.

[0013] Secondly, embodiments of this application also provide a detection device for ternary material metal particles, the device comprising: The partitioning module is used to establish a high-precision XY stable motion platform for the target and place metal particles of the target ternary material metal foreign matter, and partition the filter membrane corresponding to the metal particles to obtain different regions of the filter membrane. The shooting module is used to continuously photograph the metal particles under a preset multi-directional light source using a target high-pixel camera at a target time, so as to obtain the first image of each area of ​​the filter membrane. The first processing module is used to stitch together the first images of each region of the filter membrane to obtain the second image, and to preprocess the second image to obtain the preprocessed second image. The second processing module is used to perform binarization segmentation on the preprocessed second photo to obtain the segmented second photo, and to perform morphological optimization on the segmented second photo. The judgment module is used to calculate the image features of the optimized second photo and determine the image feature threshold range corresponding to the image features, and to determine the category of metal particles in the second photo based on the image features and the image feature threshold range.

[0014] In one possible implementation, the partitioning module is specifically used for: Obtain a mapping table of filter membrane diameter and number of partitions to determine the diameter of the filter membrane; The corresponding number of partitions is obtained by matching the diameter of the filter membrane in the mapping table, and the filter membrane is partitioned based on the number of partitions.

[0015] In one possible implementation, the device further includes: The determination module is used to determine the movement range of the target high-precision XY stabilized motion platform; wherein, the movement range includes a longitudinal movement range and a lateral movement range; A movement module is used to limit the movement of the target high-precision XY-stabilized motion platform based on the movement range of the target high-precision XY-stabilized motion platform.

[0016] In one possible implementation, the first processing module is specifically used for: The color information of the second photo is converted into the corresponding black and white information, and the histogram cropping intensity range of the preset histogram equalization algorithm is determined. The contrast of the second photo is enhanced by the histogram equalization algorithm within the histogram cropping intensity range to obtain an enhanced second photo; wherein the enhanced second photo represents an enhanced grayscale image.

[0017] In one possible implementation, the second processing module is specifically used for: Determine the target adaptive threshold function; Based on the target adaptive threshold function, the image information of the preprocessed second photo is converted into binary image information to obtain the segmented second photo.

[0018] In one possible implementation, the second processing module is specifically used for: The segmented second image is subjected to an opening operation based on a preset opening operation combination to remove noise from the second image; Identify the particle connectivity regions in the second image and remove particle connectivity regions whose area is smaller than a preset area threshold.

[0019] In one possible implementation, the image features include at least the area, roundness, aspect ratio, and surface roughness of the particles; the determination module is specifically used for: When the area is within a first area threshold range, the aspect ratio is within a first aspect ratio threshold range, and the surface roughness is within a first surface roughness threshold range, the type of the metal particles is determined. When the area is within the second area threshold range and the aspect ratio is within the second aspect ratio threshold range, the metal particle is determined to be a fiber. When the area is within the third area threshold range and the surface roughness is within the second surface roughness threshold range, the metal particle is classified as a bubble.

[0020] Thirdly, embodiments of this application provide an electronic device, including: a processor, a storage medium, and a bus. The storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the method for detecting ternary metal particles as described in any of the first aspects.

[0021] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the method for detecting ternary metal particles according to any one of the first aspects.

[0022] This application provides a method and apparatus for detecting ternary material metal particles. The method involves establishing a high-precision XY-stabilized motion platform and placing metal particles (metal foreign objects) of the target ternary material on it. A filter membrane corresponding to the metal particles is divided into different regions. A high-pixel camera continuously captures images of the metal particles under a preset multi-directional light source for a target time period, obtaining first images of each region of the filter membrane. These first images are then stitched together to obtain a second image. The second image is preprocessed to obtain a preprocessed second image. The preprocessed second image is then binarized and segmented to obtain a segmented second image. Morphological optimization is performed on the segmented second image. Image features of the optimized second image are calculated, and the corresponding image feature threshold range is determined. Based on the image features and the image feature threshold range, the type of metal particles in the second image is determined. This application utilizes a high-resolution camera combined with multi-directional light sources to capture and stitch photographs of metal particles in ternary material foreign objects. The second photograph undergoes preprocessing, binarization segmentation, and morphological optimization. Finally, based on image features and image feature threshold ranges, the type of metal particles in the second photograph is determined. This eliminates the need to collect all particles. Furthermore, by using a target-equipped high-precision XY-stabilized motion platform to segment the shooting area, high-magnification imaging of the metal particles is achieved, enabling accurate identification of particle types. Additionally, this reduces the time required for metal particle detection and improves detection efficiency.

[0023] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0024] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of a method for detecting ternary material metal particles according to an embodiment of this application; Figure 2 This is a schematic diagram of metal particles; Figure 3 This is a schematic diagram of the actual appearance of the filter membrane; Figure 4 This is a schematic diagram of metal particles under the adjustment of multi-directional light sources; Figure 5 This is a diagram illustrating the effect of photo stitching; Figure 6 This is a schematic diagram of the structure of a ternary material metal particle detection device provided according to an embodiment of this application; Figure 7 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0027] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0028] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0029] Given that metal particle detection is a crucial technology in many industries, primarily used to ensure product and personal safety, implement precise quality control, and perform predictive equipment maintenance.

[0030] Currently, in patent CN110243732B, a full-process slurry grinding particle size online detection system with a particle size range of 2-500um is proposed. The image recognition mechanism takes pictures of the ore sample from multiple angles and performs three-dimensional reconstruction on the ore sample pictures obtained from the multiple angles to obtain the reconstructed ore sample particle shape. The size of the ore sample particles is calculated based on the particle shape. In patent CN109387460A, a polarized light-based analysis system identifies metal particles through polarized light.

[0031] However, the CN110243732B patent uses a single-shot acquisition method to collect information, which involves collecting data from all particles. This results in generally low acquisition and detection efficiency. Furthermore, the metal particles in ternary materials require high magnification to be observed, and single-shot acquisition places high demands on pixel hardware, making it difficult to achieve high magnification. In the CN109387460A patent, the measurement process is lengthy, resulting in generally low detection efficiency.

[0032] To address this issue, this application provides a method and apparatus for detecting metal particles in ternary materials. The method involves capturing and stitching images of metal particles from ternary material foreign objects using a high-resolution camera combined with a multi-directional light source. The second image is then preprocessed, binarized, segmented, and morphologically optimized. Finally, the type of metal particles in the second image is determined based on image features and image feature threshold ranges. This eliminates the need to collect all particles. Furthermore, a high-precision XY-stabilized motion platform is used to segment the shooting area, achieving high magnification of the metal particles and accurately identifying their type. Additionally, this method reduces the time required for metal particle detection and improves detection efficiency.

[0033] Figure 1 This is a flowchart of a method for detecting ternary material metal particles according to an embodiment of this application. Figure 1 As shown in the embodiments of this application, the method for detecting ternary material metal particles may specifically include: S101. Establish a high-precision XY stable motion platform for the target and place metal particles of the target ternary material as metal foreign matter. Divide the filter membrane corresponding to the metal particles into different regions to obtain different regions of the filter membrane.

[0034] S102. The target high-pixel camera continuously photographs the metal particles under a preset multi-directional light source at a target time to obtain the first image of each area of ​​the filter membrane.

[0035] S103. The first images of each region of the filter membrane are stitched together to obtain the second image, and the second image is preprocessed to obtain the preprocessed second image.

[0036] S104. Perform binarization segmentation on the preprocessed second image to obtain the segmented second image, and perform morphological optimization on the segmented second image.

[0037] S105. Calculate the image features of the optimized second photo and determine the image feature threshold range corresponding to the image features. Based on the image features and the image feature threshold range, determine the category of metal particles in the second photo.

[0038] In the aforementioned method for detecting metal particles in ternary materials, a high-resolution camera combined with a multi-directional light source is used to capture and stitch images of the metal particles in the ternary material foreign object. The second image is then preprocessed, binarized, segmented, and morphologically optimized. Finally, the type of metal particles in the second image is determined based on image features and image feature threshold ranges. This eliminates the need to collect all particles. Furthermore, by using a target-equipped high-precision XY-stabilized motion platform to segment the shooting area, high-magnification imaging of the metal particles is achieved, enabling accurate identification of particle types. Additionally, this method reduces the time required for metal particle detection and improves detection efficiency.

[0039] The exemplary steps described above in the embodiments of this application are illustrated below with specific examples: S101, establish a high-precision XY stable motion platform for the target and place metal particles of the target ternary material metal foreign object, divide the filter membrane corresponding to the metal particles into different regions of the filter membrane.

[0040] In this embodiment, the target high-precision XY-stabilized motion platform is a movable stage that collects metal particles from the target ternary material's metallic foreign matter. The metal particles are placed on the target high-precision XY-stabilized motion platform, and the corresponding filter membrane is divided into different regions to ensure that edge particles of the filter membrane can still be captured in a frontal photograph, avoiding perspective distortion from affecting dimensional calibration for subsequent processing. For example, as... Figure 2 As shown, this represents metal particles, such as... Figure 3 The image shows the actual appearance of the filter membrane.

[0041] Optionally, when partitioning the filter membrane corresponding to the metal particles, a mapping table of filter membrane diameter and partition number is obtained to determine the filter membrane diameter; the corresponding partition number is obtained by matching the filter membrane diameter in the mapping table, and the filter membrane is partitioned based on the partition number. For example, for a filter membrane with a diameter of 25 mm, the corresponding partition number is found to be 9-12 according to the mapping table; for a filter membrane with a diameter of 47-50 mm, the corresponding partition number is found to be 18-24 according to the mapping table.

[0042] It should be noted that the movement range of the target high-precision XY stabilized motion platform is determined; the movement of the target high-precision XY stabilized motion platform is limited based on the movement range of the target high-precision XY stabilized motion platform. The movement range includes both longitudinal and lateral movement ranges.

[0043] Specifically, for example, the longitudinal and lateral movement range of a high-precision XY stabilized motion platform is limited to within 20-25mm.

[0044] S102 uses a high-resolution camera to continuously photograph metal particles under a preset multi-directional light source for a target time period, obtaining the first image of each area of ​​the filter membrane.

[0045] It should be noted that light sources from different directions produce different refractions; therefore, this application uses multi-directional light sources to adjust the shooting, taking a three-directional light source as an example. For example, as... Figure 4 The image shown represents a photograph of metal particles with light sources adjusted sequentially from three different directions.

[0046] In this embodiment of the application, the pixel count of the target high-pixel camera can be between 65 million and 100 million. The target time is the continuous shooting time. The time of a single continuous shooting is less than the target time threshold (e.g., 1 second). For example, the time of a single continuous shooting is <1 second. The target high-pixel camera is linked with a multi-directional light source to quickly and continuously shoot metal particles to obtain the first image of each region of the filter membrane in step S101 for subsequent processing.

[0047] S103, stitch together the first images of each region of the filter membrane to obtain the second image, and preprocess the second image to obtain the preprocessed second image.

[0048] In this embodiment, the second photograph represents a photograph of the complete filter membrane. The second photograph is obtained by stitching together the first photographs of various regions of the filter membrane acquired by the camera in step S102, and then preprocessing is performed. For example, such as... Figure 5 The image shown represents the result of stitching together the second photograph.

[0049] Optionally, during the preprocessing of the second image, the color information of the second image is converted into corresponding black and white information, and the histogram cropping intensity range of the preset histogram equalization algorithm is determined. Within the histogram cropping intensity range, the contrast of the second image is enhanced using the histogram equalization algorithm to obtain the enhanced second image. The enhanced second image represents the enhanced grayscale image.

[0050] Specifically, after obtaining the stitched second photo, the image needs to be preprocessed. In the preprocessing process, the color information of the second photo is first converted into black and white information, and its contrast is enhanced by a preset histogram equalization algorithm (CLAHE algorithm). Specifically, the histogram is clipped within the range of Cliplimit (e.g., 1.3-1.9) to obtain an enhanced grayscale image.

[0051] It can be added here that the histogram clipping strength, namely the Cliplimit value, can mainly enhance the wear marks on the metal surface, highlight the texture of the wear edge, and facilitate subsequent processing.

[0052] S104, perform binarization segmentation on the preprocessed second image to obtain the segmented second image, and perform morphological optimization on the segmented second image.

[0053] In this embodiment of the application, the preprocessed second photo in step S103 is binarized and segmented, and the binarized second photo is morphologically optimized.

[0054] Optionally, when performing binarization segmentation on the preprocessed second image, a target adaptive threshold function is determined; based on the target adaptive threshold function, the image information of the preprocessed second image is converted into binary image information to obtain the segmented second image.

[0055] Specifically, the adaptive threshold function can be Tadaptive(x,y)=μ(,x,y)-C, where C is a constant used to adjust the sensitivity of the threshold. The value of C is within a preset range, that is, its value range can be between 5 and 8. Based on this, the second photo is binarized and segmented, and the image information is converted into a binary image of 0 or 1, thereby improving the efficiency of subsequent processing.

[0056] Optionally, when performing morphological optimization on the segmented second image, an opening operation is performed on the segmented second image based on a preset opening operation combination to remove noise from the second image; particle connected regions in the second image are identified, and particle connected regions with an area smaller than a preset area threshold are removed.

[0057] Specifically, morphological optimization is performed on the second image. First, an opening operation is performed using the combination of Opening(BW,K)=Dilation(Erosion(BW,K),K), where K is the result element, whose characteristics include but are not limited to 3*3 / 4*3 / 4*4, to remove small noise. Second, area filtering is performed on the second image to remove regions where the area of ​​the particle connectivity region is smaller than a threshold (e.g., 10-30px).

[0058] S105, calculate the image features of the optimized second photo and determine the image feature threshold range corresponding to the image features, and determine the category of metal particles in the second photo based on the image features and the image feature threshold range.

[0059] In this embodiment, the image features include at least the area, roundness, aspect ratio, and surface roughness of the particles. The categories of metal particles in the second photograph include at least fibers, bubbles, and background. Image features outside the image feature threshold range correspond to the category of metal particles in the second photograph as background. The image features of the second photograph after morphological optimization are calculated and the image feature threshold range is determined. The category of metal particles in the second photograph is determined based on the image features and the image feature threshold range.

[0060] Among them, area ( ), roundness ( ), aspect ratio ( ), surface roughness ( It is calculated using the following formula:

[0061]

[0062]

[0063]

[0064] Optionally, when determining the type of metal particles in the second photograph based on image features and image feature threshold ranges, the type of metal particles is determined as follows: when the area is within a first area threshold range, the aspect ratio is within a first aspect ratio threshold range, and the surface roughness is within a first surface roughness threshold range; when the area is within a second area threshold range and the aspect ratio is within a second aspect ratio threshold range, the type of metal particles is determined to be fiber; when the area is within a third area threshold range and the surface roughness is within a second surface roughness threshold range, the type of metal particles is determined to be bubble.

[0065] For example, the classification of metal particles is determined as follows: True: if (0.85 ≤ ≤ 1.2)^( ≤ 2.5) ^ ( ≤ 0.25) Fiber: if ( <0.7) ^ ( >3) Bubble: if( >1.1)^ ( <0.1) Background: otherwise.

[0066] The method for detecting ternary material metal particles provided in this application embodiment establishes a target high-precision XY stable motion platform and places the target ternary material metal foreign matter metal particles. The filter membrane corresponding to the metal particles is divided into different regions of the filter membrane. The target high-pixel camera continuously captures the metal particles under a preset multi-directional light source for a target time to obtain a first image of each region of the filter membrane. The first images of each region of the filter membrane are stitched together to obtain a second image. The second image is preprocessed to obtain a preprocessed second image. The preprocessed second image is binarized and segmented to obtain a segmented second image. The segmented second image is then morphologically optimized. The image features of the optimized second image are calculated and the image feature threshold range corresponding to the image features is determined. Based on the image features and the image feature threshold range, the category of metal particles in the second image is determined. This application discloses a method for detecting metal particles in ternary materials. It uses a high-resolution camera combined with a multi-directional light source to capture and stitch images of the metal particles in the ternary material foreign object. The second image is then preprocessed, binarized, segmented, and morphologically optimized. Finally, the type of metal particles in the second image is determined based on image features and image feature threshold ranges. This eliminates the need to collect all particles. Furthermore, by using a target-equipped high-precision XY-stabilized motion platform to segment the shooting area, high-magnification imaging of the metal particles is achieved, enabling accurate identification of particle types. Additionally, this method reduces the time required for metal particle detection and improves detection efficiency.

[0067] Furthermore, the size of the metal particle is calculated based on the area in the image features.

[0068] For example, the size of metal particles can be calculated using the following formula ( ): (Equivalent diameter) Therefore, this application can accurately identify metal particles, and the obtained size is close to the true value.

[0069] Figure 6 This is a schematic diagram of the structure of a ternary material metal particle detection device provided in the embodiments of this application; as shown. Figure 6As shown, the ternary material metal particle detection device 600 of this application embodiment may specifically include: The partitioning module 601 is used to establish a high-precision XY stable motion platform for the target and place metal particles of the target ternary material metal foreign matter, and partition the filter membrane corresponding to the metal particles to obtain different regions of the filter membrane. The shooting module 602 is used to continuously shoot the metal particles under a preset multi-directional light source using a target high-pixel camera at a target time to obtain the first image of each area of ​​the filter membrane; The first processing module 603 is used to stitch together the first images of each region of the filter membrane to obtain a second image, and to preprocess the second image to obtain a preprocessed second image. The second processing module 604 is used to perform binarization segmentation on the preprocessed second photo to obtain the segmented second photo, and to perform morphological optimization on the segmented second photo. The judgment module 605 is used to calculate the image features of the optimized second photo and determine the image feature threshold range corresponding to the image features, and judge the category of metal particles in the second photo based on the image features and the image feature threshold range.

[0070] In one possible implementation, the partitioning module is specifically used for: Obtain the mapping table of filter membrane diameter and number of partitions to determine the diameter of the filter membrane; The corresponding number of partitions is obtained by matching the diameter of the filter membrane in the mapping table, and the filter membrane is partitioned based on the number of partitions.

[0071] In one possible implementation, the apparatus further includes: The determination module is used to determine the movement range of the target high-precision XY stabilized motion platform; wherein, the movement range includes the longitudinal movement range and the lateral movement range; The movement module is used to limit the movement of the target high-precision XY stabilized motion platform based on its movement range.

[0072] In one possible implementation, the first processing module is specifically used for: The color information of the second photo is converted into the corresponding black and white information, and the range of histogram cropping intensity of the preset histogram equalization algorithm is determined. The contrast of the second photo is enhanced by a histogram equalization algorithm within the histogram cropping intensity range to obtain an enhanced second photo; wherein, the enhanced second photo represents the enhanced grayscale image.

[0073] In one possible implementation, the second processing module is specifically used for: Determine the target adaptive threshold function; Based on the target adaptive threshold function, the image information of the preprocessed second photo is converted into binary image information to obtain the segmented second photo.

[0074] In one possible implementation, the second processing module is specifically used for: The second image after segmentation is subjected to an opening operation based on a preset opening operation combination to remove noise from the second image; Identify the connected regions of particles in the second image and remove connected regions of particles whose area is smaller than a preset area threshold.

[0075] In one possible implementation, the image features include at least the area, roundness, aspect ratio, and surface roughness of the particles; the determination module is specifically used for: When the area is within the first area threshold range, the aspect ratio is within the first aspect ratio threshold range, and the surface roughness is within the first surface roughness threshold range, the type of metal particles is determined. When the area is within the second area threshold range and the aspect ratio is within the second aspect ratio threshold range, the metal particle is classified as fiber. When the area is within the third area threshold range and the surface roughness is within the second surface roughness threshold range, the metal particles are classified as bubbles.

[0076] The ternary material metal particle detection device provided in this application establishes a target high-precision XY stable motion platform and places the target ternary material metal foreign object metal particles. The filter membrane corresponding to the metal particles is divided into different regions of the filter membrane. The target high-pixel camera continuously captures the metal particles under a preset multi-directional light source for a target time to obtain a first image of each region of the filter membrane. The first images of each region of the filter membrane are stitched together to obtain a second image. The second image is preprocessed to obtain a preprocessed second image. The preprocessed second image is binarized and segmented to obtain a segmented second image. The segmented second image is then morphologically optimized. The image features of the optimized second image are calculated and the image feature threshold range corresponding to the image features is determined. Based on the image features and the image feature threshold range, the category of metal particles in the second image is determined. The ternary material metal particle detection device of this application uses a high-resolution camera combined with a multi-directional light source to capture and stitch images of the metal particles in the ternary material foreign object. The second image is then preprocessed, binarized, segmented, and morphologically optimized. Finally, the type of metal particles in the second image is determined based on image features and image feature threshold ranges. This eliminates the need to collect all particles. Furthermore, by using a target-equipped high-precision XY-stabilized motion platform to segment the shooting area, high-magnification imaging of the metal particles is achieved, enabling accurate identification of particle types. In addition, the device reduces the metal particle detection time and improves detection efficiency.

[0077] like Figure 7 As shown in the embodiment of this application, an electronic device 700 includes a processor 701, a memory 702, and a bus. The memory 702 stores machine-readable instructions that can be executed by the processor 701. When the electronic device is running, the processor 701 communicates with the memory 702 via the bus, and the processor 701 executes the machine-readable instructions to perform the steps of the detection method for ternary metal particles as described above.

[0078] Specifically, the memory 702 and processor 701 mentioned above can be general-purpose memory and processor, without any specific limitations. When the processor 701 runs the computer program stored in the memory 702, it can execute the above-mentioned method for detecting ternary material metal particles.

[0079] Corresponding to the above-described method for detecting ternary metal particles, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the above-described method for detecting ternary metal particles.

[0080] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some communication interfaces; the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0081] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0082] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0083] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, 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 portion 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 deployment methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0084] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for detecting ternary material metal particles, characterized in that, The method includes: A high-precision XY stable motion platform for the target is established, and metal particles of the target ternary material are placed there. The filter membrane corresponding to the metal particles is divided into different regions of the filter membrane. The metal particles are continuously photographed by a target high-pixel camera under a preset multi-directional light source for a target time period to obtain the first image of each region of the filter membrane. The first images of each region of the filter membrane are stitched together to obtain a second image, and the second image is preprocessed to obtain a preprocessed second image. The preprocessed second image is binarized and segmented to obtain the segmented second image, and the segmented second image is then morphologically optimized. Calculate the image features of the optimized second photo and determine the image feature threshold range corresponding to the image features. Based on the image features and the image feature threshold range, determine the category of metal particles in the second photo.

2. The method according to claim 1, characterized in that, The step of partitioning the filter membrane corresponding to the metal particles includes: Obtain a mapping table of filter membrane diameter and number of partitions to determine the diameter of the filter membrane; The corresponding number of partitions is obtained by matching the diameter of the filter membrane in the mapping table, and the filter membrane is partitioned based on the number of partitions.

3. The method according to claim 1, characterized in that, The method further includes: Determine the movement range of the target high-precision XY stabilized motion platform; wherein, the movement range includes the longitudinal movement range and the lateral movement range; The movement of the target high-precision XY stabilized motion platform is limited by the movement range of the target high-precision XY stabilized motion platform.

4. The method according to claim 1, characterized in that, The preprocessing of the second photo includes: The color information of the second photo is converted into the corresponding black and white information, and the histogram cropping intensity range of the preset histogram equalization algorithm is determined. The contrast of the second photo is enhanced by the histogram equalization algorithm within the histogram cropping intensity range to obtain an enhanced second photo; wherein the enhanced second photo represents an enhanced grayscale image.

5. The method according to claim 1, characterized in that, The step of performing binarization segmentation on the preprocessed second image includes: Determine the target adaptive threshold function; Based on the target adaptive threshold function, the image information of the preprocessed second photo is converted into binary image information to obtain the segmented second photo.

6. The method according to claim 1, characterized in that, The morphological optimization of the segmented second image includes: The segmented second image is subjected to an opening operation based on a preset opening operation combination to remove noise from the second image; Identify the particle connectivity regions in the second image and remove particle connectivity regions whose area is smaller than a preset area threshold.

7. The method according to claim 1, characterized in that, The image features include at least the particle area, roundness, aspect ratio, and surface roughness; the determination of the type of metal particles in the second photograph based on the image features and the image feature threshold range includes: When the area is within a first area threshold range, the aspect ratio is within a first aspect ratio threshold range, and the surface roughness is within a first surface roughness threshold range, the type of the metal particles is determined. When the area is within the second area threshold range and the aspect ratio is within the second aspect ratio threshold range, the metal particle is determined to be a fiber. When the area is within the third area threshold range and the surface roughness is within the second surface roughness threshold range, the metal particle is classified as a bubble.

8. A detection device for ternary material metal particles, characterized in that, The device includes: The partitioning module is used to establish a high-precision XY stable motion platform for the target and place metal particles of the target ternary material metal foreign matter, and partition the filter membrane corresponding to the metal particles to obtain different regions of the filter membrane. The shooting module is used to continuously photograph the metal particles under a preset multi-directional light source using a target high-pixel camera at a target time, so as to obtain the first image of each area of ​​the filter membrane. The first processing module is used to stitch together the first images of each region of the filter membrane to obtain the second image, and to preprocess the second image to obtain the preprocessed second image. The second processing module is used to perform binarization segmentation on the preprocessed second photo to obtain the segmented second photo, and to perform morphological optimization on the segmented second photo. The judgment module is used to calculate the image features of the optimized second photo and determine the image feature threshold range corresponding to the image features, and judge the category of metal particles in the second photo based on the image features and the image feature threshold range.

9. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the method for detecting ternary metal particles as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the method for detecting ternary material metal particles as described in any one of claims 1 to 7.

Images