Conductive foam assembly quality detection method and device and storage medium
By filtering and differentially processing the product image of conductive foam, the foam contour information is extracted, which solves the problems of missed detection and false detection in the assembly quality inspection of conductive foam, and achieves high-precision and robust inspection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHENZHEN ZHUOJIAN INTELLIGENT MANUFACTURING CO LTD
- Filing Date
- 2025-12-31
- Publication Date
- 2026-05-08
AI Technical Summary
In existing technologies, the assembly quality inspection accuracy of conductive foam is not high, and it is easy to miss or misdetect, which cannot meet the high-precision inspection requirements of automotive electronics manufacturing.
By acquiring product images of both unassembled and assembled products with conductive foam, filtering and differential processing are performed to extract foam contour information, and assembly quality is determined based on the contour information.
It improves the accuracy and robustness of conductive foam assembly quality inspection, meeting the high-precision inspection needs of electronic manufacturing and the inspection requirements of large-scale production.
Smart Images
Figure CN121998914A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the fields of machine vision inspection technology and automotive electronics manufacturing inspection technology, and in particular to a method, equipment and storage medium for inspecting the assembly quality of conductive foam. Background Technology
[0002] In the assembly of products such as vehicle domain controllers and vehicle electronic control units, conductive foam needs to reliably connect the outer shell to the ground wire of the PCBA (Printed Circuit Board Assembly) to ensure EMI (Electromagnetic Interference) performance. At this time, the assembly quality of conductive foam is crucial.
[0003] In related technologies, the main approach is to use spot analysis algorithms to extract spots from the collected product images of conductive foam in order to obtain the foam outline information of the conductive foam.
[0004] However, this implementation method has poor adaptability to grayscale features and weak anti-interference ability, making it difficult to extract stable and accurate foam contour information. It is prone to missed detection and false detection, which affects the detection accuracy of conductive foam assembly quality and thus cannot meet the high-precision detection requirements of automotive electronics manufacturing. Summary of the Invention
[0005] This application provides a method, equipment, and storage medium for inspecting the assembly quality of conductive foam, which can improve the accuracy and robustness of the method for inspecting the assembly quality of conductive foam, thereby meeting the high-precision inspection requirements of electronic manufacturing and the inspection requirements of large-scale production scenarios.
[0006] In a first aspect, embodiments of this application provide a method for inspecting the assembly quality of conductive foam, including:
[0007] Acquire a first image and a second image; wherein the first image indicates a product image without conductive foam; and the second image indicates a product image with conductive foam.
[0008] The first image and the second image are filtered respectively to obtain the filtered first image and the filtered second image;
[0009] The filtered first image and the filtered second image are subjected to differential processing to obtain a third image; wherein, the third image includes the foam outline of at least one conductive foam.
[0010] Based on the third image, the foam outline information of each conductive foam is determined, and based on the foam outline information, the assembly quality of each conductive foam is determined.
[0011] In one possible implementation, filtering is performed on the first image and the second image respectively to obtain a filtered first image and a filtered second image, including:
[0012] The first image is subjected to a first median filter to obtain the filtered first image;
[0013] The second image is subjected to a second median filter to obtain the filtered second image.
[0014] In one possible implementation, performing a first median filtering process on the first image includes:
[0015] The first image is subjected to the first median filtering process using the first circular filter template;
[0016] The second median filtering process on the second image includes:
[0017] The second image is subjected to the second median filtering process using a second circular filter template; wherein the radius of the first circular filter template is smaller than the radius of the second circular filter template.
[0018] In one possible implementation, the filtered first image and the filtered second image are subjected to differential processing to obtain a third image, including:
[0019] Determine the scene light source information of the image acquisition scene in which the product image is located;
[0020] Based on the scene light source information, determine the target scaling factor and / or target offset factor;
[0021] Based on the target scaling factor and / or the target offset factor, the filtered first image and the filtered second image are differentially processed to obtain a third image.
[0022] In one possible implementation, determining the target scaling factor and / or target offset factor based on the scene light source information includes:
[0023] Obtain preset light source information, as well as preset scaling factor and preset offset factor matched by the preset light source information;
[0024] Based on the difference information between the scene light source information and the preset light source information, the first adjustment data and the second adjustment data are determined.
[0025] After adjusting the preset scaling factor based on the first adjustment data, the target scaling factor is obtained;
[0026] After adjusting the preset offset factor according to the second adjustment data, the target offset factor is obtained.
[0027] In one possible implementation, determining the foam outline information of each of the conductive foams based on the third image includes:
[0028] Perform grayscale opening operation on the third image to obtain the fourth image;
[0029] Based on a preset grayscale threshold, the fourth image is segmented into conductive foam regions to obtain the fifth image;
[0030] The fifth image is subjected to connected component disconnection processing to obtain the foam contour information of each conductive foam.
[0031] In one possible implementation, determining the assembly quality of each conductive foam based on the foam contour information includes:
[0032] Based on the foam outline information, at least one assembly attribute information of the conductive foam is determined; wherein, each assembly attribute information has a corresponding assembly qualification requirement;
[0033] Based on the assembly attribute information and the assembly qualification requirements, the assembly quality of each conductive foam is determined.
[0034] In one possible implementation, before filtering the first image and the second image respectively, the method further includes:
[0035] Determine the conductive foam assembly area in the product image;
[0036] Based on the conductive foam assembly area, the first image and the second image are processed by region of interest extraction to obtain the processed first image and the processed second image.
[0037] Secondly, embodiments of this application provide an assembly quality inspection device for conductive foam, comprising:
[0038] An acquisition unit is configured to acquire a first image and a second image; wherein the first image indicates a product image without conductive foam; and the second image indicates a product image with conductive foam.
[0039] The filtering unit is used to perform filtering processing on the first image and the second image respectively to obtain the filtered first image and the filtered second image;
[0040] A differential unit is used to perform differential processing on the filtered first image and the filtered second image to obtain a third image; wherein the third image includes the foam outline of at least one conductive foam.
[0041] The determining unit is configured to determine the foam outline information of each conductive foam according to the third image, and to determine the assembly quality of each conductive foam according to the foam outline information.
[0042] Thirdly, embodiments of this application provide a computer device, including: a memory and a processor;
[0043] The memory stores computer-executed instructions;
[0044] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.
[0045] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.
[0046] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.
[0047] The method, apparatus, and storage medium for detecting the assembly quality of conductive foam provided in this application embodiment can first acquire a first image indicating a product image without conductive foam and a second image indicating a product image with conductive foam. Then, the first and second images are filtered to obtain filtered first and second images, respectively. Filtering the first image suppresses background noise and reduces background interference; filtering the second image weakens the complex grayscale features and specular interference of the conductive foam, thus laying the foundation for target separation. Next, the filtered first and second images are differentially processed to obtain a third image. Differential processing enhances the grayscale features of the foam region, highlighting the grayscale difference between the foam and the background, thus addressing the pain points of traditional algorithms, such as difficulty in setting thresholds and incomplete target separation. Finally, based on the foam outline of at least one conductive foam included in the third image, the foam outline information of each conductive foam is determined, and the assembly quality of each conductive foam is determined based on the foam outline information. This implementation method enables stable extraction of foam contour information, reduces the rate of missed detections and false detections, thereby improving the accuracy and robustness of the assembly quality inspection method for conductive foam, and thus meeting the high-precision inspection requirements of electronic manufacturing, as well as the inspection requirements of large-scale production scenarios. Attached Figure Description
[0048] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0049] Figure 1 A flowchart illustrating an assembly quality inspection method for conductive foam provided in this application embodiment;
[0050] Figure 2 A schematic diagram of a first image provided for an embodiment of this application;
[0051] Figure 3 A schematic diagram of a second image provided for an embodiment of this application;
[0052] Figure 4 A flowchart illustrating another method for inspecting the assembly quality of conductive foam provided in this application embodiment;
[0053] Figure 5 This is a schematic diagram of a processed first image obtained after performing region of interest extraction on a first image, as provided in an embodiment of this application.
[0054] Figure 6This is a schematic diagram of a processed second image obtained after performing region of interest extraction on a second image, as provided in an embodiment of this application.
[0055] Figure 7 A schematic diagram of a filtered first image provided in an embodiment of this application;
[0056] Figure 8 A schematic diagram of a filtered two-image representation provided in an embodiment of this application;
[0057] Figure 9 A schematic diagram of a third image provided for an embodiment of this application;
[0058] Figure 10 This is a schematic diagram of foam contour information provided in an embodiment of this application;
[0059] Figure 11 A schematic diagram of the structure of an assembly quality inspection device for conductive foam provided in an embodiment of this application;
[0060] Figure 12 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application.
[0061] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation
[0062] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.
[0063] In this document, the term "and / or" merely describes a relationship, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.
[0064] In the assembly of products such as vehicle domain controllers and vehicle electronic control units, conductive foam needs to reliably connect the outer shell to the ground wire of the PCBA (Printed Circuit Board Assembly) to ensure EMI (Electromagnetic Interference) performance. At this time, the assembly quality of conductive foam is crucial.
[0065] In related technologies, the main approach is to use spot analysis algorithms to extract spots from the collected product images of conductive foam in order to obtain the foam outline information of the conductive foam.
[0066] However, due to the non-uniform grayscale texture, dark-toned structured texture, and local highlights on the surface of conductive foam, complex visual features are formed with the housing mounting area, resulting in mixed target features in the product image of conductive foam.
[0067] Traditional spot analysis algorithms have poor adaptability to grayscale features and weak anti-interference capabilities. This makes it difficult to extract foam contour information stably and accurately when processing product images of conductive foam. As a result, it is easy to miss or misdetect, which affects the detection accuracy of conductive foam assembly quality. Consequently, the detection stability and reliability of conductive foam assembly quality cannot meet the high-precision detection requirements for EMI performance assurance in automotive electronics manufacturing, and it is difficult to adapt to large-scale production environments.
[0068] The assembly quality inspection method for conductive foam provided in this application can weaken the interference of complex grayscale, texture, noise and other features by filtering the template image of the product without foam (i.e., the first image) and the image of the product with foam (i.e., the second image), thus laying the foundation for target separation. Then, differential processing is performed to enhance the grayscale features of the foam area and highlight the grayscale difference between the foam and the background, thereby solving the pain points of traditional algorithms such as difficulty in setting thresholds and incomplete target separation. After that, foam contour information is extracted, so that accurate foam contour information can be extracted under complex grayscale features. At the same time, it can also adapt to the grayscale changes of different batches of foam, thereby improving the accuracy and robustness of the assembly quality inspection method for conductive foam, thus meeting the high-precision inspection requirements of electronic manufacturing and the inspection requirements of large-scale production scenarios.
[0069] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.
[0070] Figure 1A flowchart illustrating an assembly quality inspection method for conductive foam provided in this application embodiment is shown below. Figure 1 As shown, the method includes:
[0071] S101. Obtain a first image and a second image; wherein the first image indicates a product image without conductive foam; and the second image indicates a product image with conductive foam.
[0072] The assembly quality inspection method for conductive foam provided in this application embodiment can be applied to the assembly status inspection scenario of conductive foam and shell. Based on this, the first image can indicate an image of the shell without conductive foam, and the second image can indicate an image of the shell with conductive foam. The first image can be a locally stored image, and the second image can be an image acquired by an industrial camera.
[0073] For example, see Figure 2 and Figure 3 , Figure 2 This is a schematic diagram of a first image provided in an embodiment of this application. Figure 3 This is a schematic diagram of a second image provided for an embodiment of this application. For example... Figure 2 As shown, the outer casing may include a metal stepped portion. Conductive foam can then be fitted onto the metal stepped portion of the outer casing, resulting in... Figure 3 The grid-like conductive foam area is shown.
[0074] S102. Filter the first image and the second image respectively to obtain the filtered first image and the filtered second image.
[0075] In one example, the first and second images can be filtered according to a preset filtering algorithm to weaken the interference of complex textures.
[0076] Optionally, the preset filtering algorithm can be a median filtering algorithm, a mean drift filtering algorithm, or a bilateral filtering algorithm, etc. There is no limitation on the type of preset filtering algorithm, as long as it can be implemented.
[0077] S103. Perform differential processing on the filtered first image and the filtered second image to obtain a third image; wherein, the third image includes the foam outline of at least one conductive foam.
[0078] In one example, when performing differential processing on the filtered first image and the filtered second image, the calculation can be performed according to the formula shown in formula (1) below.
[0079] (1)
[0080] in, This represents the pixel grayscale value of the first image after filtering. This represents the pixel grayscale value of the filtered second image. Indicates the scaling factor. This represents the offset factor.
[0081] In one example, The values and The value can be a preset value or a value flexibly determined based on the scene's lighting information. Here, we will specify... The values and The method for determining the value of is not limited, and the only requirement is that it can be achieved.
[0082] In one example, when performing differential processing on the filtered first image and the filtered second image according to the above formula (1), if grayscale value overflow or underflow occurs, the image is cropped.
[0083] S104. Based on the third image, determine the foam outline information of each conductive foam, and based on the foam outline information, determine the assembly quality of each conductive foam.
[0084] In one example, image segmentation processing can be performed on the foam outline of at least one conductive foam included in the third image based on a threshold to obtain the foam outline information of the conductive foam.
[0085] In one example, the foam outline information may include at least: the set of pixel coordinates corresponding to the foam outline and the topological structure information of the foam outline, and the assembly quality of each conductive foam is determined based on the set of pixel coordinates and the topological structure information included in the foam outline information.
[0086] In one example, before performing image segmentation on the third image based on a threshold, the third image can be preprocessed first. Based on the preprocessing operation, small noise in the third image can be removed, the target contour can be smoothed, and small adhesions can be broken to further improve the accuracy of the obtained foam contour information.
[0087] The preprocessing can be morphological preprocessing or filtering and processing. There is no limitation on the preprocessing method here, as long as it can be implemented.
[0088] As described above, in this embodiment, a first image indicating a product without conductive foam and a second image indicating a product with conductive foam are first acquired. Then, the first and second images are filtered to obtain filtered first and second images, respectively. Filtering the first image suppresses background noise and reduces background interference; filtering the second image weakens the complex grayscale features and specular interference of the conductive foam, thus laying the foundation for target separation. Next, the filtered first and second images are differentially processed to obtain a third image. Differential processing enhances the grayscale features of the foam region, highlighting the grayscale difference between the foam and the background, thus addressing the pain points of traditional algorithms, such as difficulty in setting thresholds and incomplete target separation. Finally, based on the foam outline of at least one conductive foam included in the third image, the foam outline information of each conductive foam is determined, and the assembly quality of each conductive foam is determined based on the foam outline information. This implementation method enables stable extraction of foam contour information, reduces the rate of missed detections and false detections, thereby improving the accuracy and robustness of the assembly quality inspection method for conductive foam, and thus meeting the high-precision inspection requirements of electronic manufacturing, as well as the inspection requirements of large-scale production scenarios.
[0089] Figure 4 A flowchart illustrating another method for inspecting the assembly quality of conductive foam provided in this application embodiment is shown below. Figure 4 As shown, in this embodiment... Figure 1 Based on the examples, a detailed description of the assembly quality inspection method for conductive foam is provided. This method includes:
[0090] S401. Obtain a first image and a second image; wherein the first image indicates a product image without conductive foam; and the second image indicates a product image with conductive foam.
[0091] In one example, this step can be referred to the content described in S101 above, and will not be repeated in detail here.
[0092] S402. Determine the conductive foam assembly area in the product image.
[0093] In one example, the conductive foam assembly area can be a pre-defined installation area for conductive foam, in which case the conductive foam assembly area can include the corresponding coordinate range.
[0094] S403. Based on the conductive foam assembly area, perform region of interest extraction processing on the first image and the second image respectively to obtain the processed first image and the processed second image.
[0095] In one example, the region of interest can be extracted from the first image and the second image respectively, based on the coordinate range included in the conductive foam assembly area, to obtain the processed first image and the processed second image.
[0096] For example, suppose the first image is as follows: Figure 2 As shown, the second image is as follows Figure 3 As shown, see below. Figure 5 and Figure 6 , Figure 5 This is a schematic diagram of a processed first image obtained after performing region of interest extraction on a first image, as provided in an embodiment of this application. Figure 6 This is a schematic diagram illustrating a processed second image obtained after performing region of interest extraction on a second image, as provided in an embodiment of this application. Figure 5 and Figure 6 It can be seen that after performing the region of interest extraction process, the conductive foam assembly area can be obtained.
[0097] This implementation method can extract the region of interest from the first and second images based on the pre-defined conductive foam assembly area, narrowing the detection range and retaining only the preset conductive foam installation area, while eliminating background interference from non-conductive foam areas, thereby improving the accuracy of conductive foam contour detection.
[0098] S404. Filter the first image and the second image respectively to obtain the filtered first image and the filtered second image.
[0099] The first image undergoing filtering here refers to the first image obtained after the region of interest extraction process described above, and the second image undergoing filtering refers to the second image obtained after the region of interest extraction process described above.
[0100] In one example, when filtering the first image and the second image respectively, the first image can be subjected to a first median filter to obtain the filtered first image; the second image can be subjected to a second median filter to obtain the filtered second image.
[0101] At this point, the first and second images can be filtered separately using the simple and efficient median filter, which can reduce the interference of complex grayscale, texture, noise and other features while improving processing efficiency.
[0102] In one example, a median filter can be applied to the first and second images based on a preset filter template to obtain the filtered first and second images.
[0103] At this point, the first median filtering process and the second median filtering process can correspond to different filtering templates, thereby achieving differentiated filtering processing of the first image and the second image.
[0104] For example, a first median filter can be applied to the first image using a first circular filter template, and a second median filter can be applied to the second image using a second circular filter template.
[0105] The radius of the first circular filter template is smaller than the radius of the second circular filter template.
[0106] At this point, by setting the radius of the circular filter template, the generation of false targets in the filtered image can be reduced, avoiding contour breakage caused by texture interference when determining the foam contour information of the conductive foam in the subsequent process. This provides a high-quality input image for subsequent differential processing, thereby improving the integrity and reliability of foam contour information extraction.
[0107] In this embodiment, the radius of the first circular filter template can be set to 11, and the radius of the second circular filter template can be set to 1.
[0108] In one example, when performing median filtering based on the first circular filter template (or the second circular filter template), all pixel gray values within the first circular filter template (or the second circular filter template) can be collected and sorted in ascending order. The median sorting position is determined by the following formula (2), and the gray value at that position is extracted as the new gray value of the center pixel. The above operation is repeated pixel by pixel to complete the median filtering process.
[0109] (2)
[0110] Where N is the total number of pixels actually covered by the first circular filter template (or the second circular filter template).
[0111] In one example, before performing median filtering based on the first circular filter template (or the second circular filter template), the boundaries of the first image (or the second image) can be supplemented with pixels required by the first circular filter template (or the second circular filter template) using a "grayscale continuation" method (e.g., the grayscale value of virtual pixels outside the boundary is consistent with that of adjacent boundary pixels), thereby improving the effectiveness of median filtering.
[0112] In one example, in the case of Figure 5 The image shown and Figure 6 The image shown, after median filtering, can be seen in [reference needed]. Figure 7 and Figure 8 , Figure 7 This is a schematic diagram of a filtered first image provided in an embodiment of this application. Figure 8This is a schematic diagram of a filtered two-image representation provided in an embodiment of this application.
[0113] In the above embodiments, median filtering of the second image can be performed using a circular filter template with a larger radius, i.e., the first circular filter template, which can effectively reduce the specular reflection and structured texture interference of the conductive foam and preserve the continuity of the target area. At the same time, median filtering of the first image using a circular filter template with a smaller radius, i.e., the second circular filter template, can not only reduce computational complexity and improve processing efficiency, but also suppress background noise in the first image and preserve detailed features.
[0114] S405. Perform differential processing on the filtered first image and the filtered second image to obtain a third image; wherein the third image includes the foam outline of at least one conductive foam.
[0115] In one possible implementation, the filtered first image and the filtered second image can be differentially processed according to the following steps to obtain the third image.
[0116] First, determine the scene light source information of the image acquisition scene where the product image is located.
[0117] Then, based on the scene lighting information, determine the target scaling factor and / or target offset factor.
[0118] Finally, based on the target scaling factor and / or target offset factor, the filtered first image and the filtered second image are differentially processed to obtain the third image.
[0119] In one example, the target scaling factor can indicate the value in formula (1) above. The target offset factor can indicate the value in formula (1) above. .
[0120] In one example, after determining the target scaling factor and / or target offset factor, the filtered first image and the filtered second image can be differentially processed according to the above formula (1) to obtain the third image.
[0121] For example, if the target scaling factor is determined to be 6 and the target offset factor to be 5, then you can refer to... Figure 9 , Figure 9 This is a schematic diagram of a third image provided for an embodiment of this application. For example... Figure 9 As shown, based on the target scaling factor 6 and the target offset factor 5, for Figure 7 The filtered first image shown, and Figure 8 After the filtered second image shown is subjected to differential processing, the result is obtained. Figure 9 The third image shown.
[0122] In the above embodiments, differential operations can amplify the grayscale difference between the conductive foam and the background, thus solving the problem of missed detections or misjudgments caused by grayscale overlap in traditional fixed threshold segmentation. Specifically, the target scaling factor can be used to control the differential intensity, and the target offset factor can be used to adjust the baseline offset. Through their synergistic effect, the grayscale difference between the conductive foam and the background can be dynamically enhanced, thereby optimizing the separation effect of the conductive foam.
[0123] Optionally, when determining the target scaling factor and / or target offset factor based on scene lighting information, the process described below can be referred to.
[0124] First, obtain the preset light source information, as well as the preset scaling factor and preset offset factor that match the preset light source information.
[0125] In one example, preset light source information can be used to indicate the information obtained by the assembly quality inspection method of conductive foam under the test light source. For example, the preset light source information may include, but is not limited to, gray mean information (i.e., the first gray mean) and gray median information (i.e., the first gray median) under the test light source. Furthermore, during the test, preset scaling factor and preset offset factor for differential processing can be obtained under the test light source.
[0126] Then, based on the difference between the scene light source information and the preset light source information, the first adjustment data and the second adjustment data are determined.
[0127] In one example, scene light source information can be used to indicate the information obtained by the assembly quality inspection method of conductive foam under the scene light source in the actual application scenario. For example, scene light source information may include, but is not limited to, gray mean information (i.e., second gray mean) and gray median information (i.e., second gray median) under the scene light source.
[0128] At this point, the first adjustment data can be determined based on the difference between the first grayscale mean and the second grayscale mean, and the second adjustment data can be determined based on the difference between the first grayscale median and the second grayscale median.
[0129] For example, if the difference between the first grayscale mean and the second grayscale mean is greater than a preset grayscale mean threshold, the first adjustment data can be determined based on the ratio of the difference between the first grayscale mean and the second grayscale mean to the first grayscale mean; and / or, if the difference between the first grayscale median and the second grayscale median is greater than a preset grayscale median threshold, the second adjustment data can be determined based on the ratio of the difference between the first grayscale median and the second grayscale median to the first grayscale median.
[0130] Finally, after adjusting the preset scaling factor according to the first adjustment data, the target scaling factor is obtained; after adjusting the preset offset factor according to the second adjustment data, the target offset factor is obtained.
[0131] This implementation method allows for proportional adjustment of the differential processing parameters based on changes in the light source information of the image acquisition scene. This makes the differential processing more adaptable to the actual image acquisition scene, thereby improving its flexibility and versatility, and ultimately enhancing the accuracy of the differential processing results, i.e., the third image. Furthermore, dynamically adjusting the differential processing parameters improves the robustness of the differential results, ensuring stable extraction of the foam contour even in complex scenes and avoiding detection failures caused by changes in lighting or material differences.
[0132] Optionally, when performing differential processing on the filtered first image and the filtered second image, a multi-stage differential processing method can also be adopted. In this case, the differential processing of each stage can refer to the single-stage differential processing process described above, which will not be elaborated here.
[0133] Furthermore, if it is determined that the order of differential processing is not 1, filtering processing (e.g., median filtering) can be added between stages to suppress noise and avoid over-enhancement.
[0134] At this point, a multi-stage differential processing method can be used to perform differential processing on the first filtered image with low contrast and high noise and the second filtered image, thereby meeting the requirements of difference enhancement and noise suppression.
[0135] according to Figure 9 As shown in the third image, the third image can include the foam outlines of two conductive foams. At this time, the foam outline information of each conductive foam can be determined based on the third image, and the assembly quality of each conductive foam can be determined based on the foam outline information, as described below.
[0136] S406. Perform grayscale opening operation on the third image to obtain the fourth image.
[0137] In one example, the shape of the structuring element for grayscale opening can be determined based on the shape of the conductive foam. For instance, regarding the assembly shape of the conductive foam in this embodiment, grayscale opening processing can be performed on the third image based on a rectangular structuring element.
[0138] In one example, the size of the rectangular structuring element can be determined based on the size of the noise points that need to be removed. For instance, the size of the rectangular structuring element could be... .
[0139] In one example, grayscale opening can indicate whether erosion or dilation occurs first.
[0140] At this point, grayscale opening operations can be used to filter out noise (e.g., isolated noise) and obtain a more accurate conductive foam area.
[0141] S407. Based on the preset grayscale threshold, the fourth image is processed to segment the conductive foam region to obtain the fifth image.
[0142] In one example, a preset grayscale threshold can indicate the grayscale value corresponding to the conductive foam; for example, the preset grayscale threshold can be 100-255.
[0143] At this point, the conductive foam region can be segmented in the fourth image according to the preset grayscale threshold to obtain the fifth image containing the conductive foam region.
[0144] S408. Perform connected component disconnection processing on the fifth image to obtain the foam contour information of each conductive foam.
[0145] In one example, connected component disconnection processing can instruct the division of independent regions based on pixel connectivity. In this case, by using connected component disconnection processing to eliminate spurious targets with excessively small areas, accurate foam contour information of the conductive foam can be obtained.
[0146] For example, see Figure 10 , Figure 10 This is a schematic diagram of foam contour information provided in an embodiment of this application, such as... Figure 10 As shown, in the case of Figure 9 After performing grayscale opening, conductive foam region segmentation, and connected component disconnection on the third image shown, we can obtain... Figure 10 The image shows the foam outline information for each conductive foam.
[0147] In one example, as mentioned above, the foam outline information may include at least a set of pixel coordinates and topological information.
[0148] Based on this, after obtaining the foam outline information of each conductive foam, the assembly quality of each conductive foam can be determined according to the foam outline information, as described in the process below.
[0149] S409. Based on the foam outline information, determine at least one assembly attribute information of the conductive foam; wherein each assembly attribute information has a corresponding assembly qualification requirement.
[0150] In one example, assembly attribute information may include, but is not limited to: assembly area information, assembly center coordinates, and assembly deflection angle.
[0151] In one example, the assembly area information can indicate the pixel area of the effective region corresponding to the foam contour information. The pixel area of this effective region can be determined based on the number of pixels included in the pixel coordinate set, or based on the polygon area corresponding to the topology information. In this case, the assembly qualification requirement corresponding to the assembly area information is: the pixel area is greater than or equal to a preset area threshold (for example, the preset area threshold is 5000 pixels).
[0152] In one example, the assembly center coordinates can indicate the coordinates of the center point of the area corresponding to the foam contour information. The coordinates of this center point can be determined based on the geometric center of the pixel coordinate set. In this case, the assembly qualification requirement corresponding to the assembly center coordinates is: the coordinates of the center point deviate from the preset reference coordinates by less than or equal to a preset offset threshold (for example, the preset offset threshold is 5 pixels).
[0153] In one example, the assembly deflection angle can indicate the deflection angle of the area corresponding to the foam contour information, which can be determined based on the topology information. In this case, the assembly qualification requirement corresponding to the assembly deflection angle is: the deflection angle is less than or equal to a preset angle threshold (for example, the preset angle threshold is 3 degrees).
[0154] S410. Determine the assembly quality of each conductive foam based on the assembly attribute information and assembly qualification requirements.
[0155] In one example, the assembly quality of conductive foam can be used to indicate the presence or absence of conductive foam, whether the assembly position of conductive foam is qualified, and whether the assembly angle of conductive foam is qualified.
[0156] Based on this, if the pixel area indicated by the assembly area information is greater than or equal to a preset area threshold, the conductive foam is determined to "exist"; otherwise, the conductive foam is determined to be "missing". If the coordinates of the center point indicated by the assembly center coordinates deviate from the preset reference coordinates by less than or equal to a preset offset threshold, the conductive foam is determined to be "position qualified"; otherwise, the conductive foam is determined to be "offset". If the deflection angle indicated by the assembly deflection angle is less than or equal to a preset angle threshold, the conductive foam is determined to be "angle qualified"; otherwise, the conductive foam is determined to have "angle deviation".
[0157] In the above embodiments, the assembly quality of conductive foam can be determined in a multi-dimensional way based on one or more assembly attribute information and the corresponding assembly qualification requirements of each assembly attribute information. This can improve the comprehensiveness and accuracy of the identification of assembly defects of conductive foam, thereby improving the comprehensiveness, accuracy and reliability of the assembly quality of conductive foam.
[0158] Figure 11 This is a schematic diagram of the structure of an assembly quality inspection device for conductive foam provided in an embodiment of this application, as shown below. Figure 11As shown, the conductive foam assembly quality inspection device 110 provided in this embodiment includes:
[0159] The acquisition unit 1101 is used to acquire a first image and a second image; wherein the first image indicates a product image without conductive foam; and the second image indicates a product image with conductive foam.
[0160] The filtering unit 1102 is used to perform filtering processing on the first image and the second image respectively to obtain the filtered first image and the filtered second image.
[0161] The differential unit 1103 is used to perform differential processing on the filtered first image and the filtered second image to obtain a third image; wherein the third image includes the foam outline of at least one conductive foam.
[0162] The determining unit 1104 is used to determine the foam outline information of each conductive foam according to the third image, and to determine the assembly quality of each conductive foam according to the foam outline information.
[0163] In one possible implementation, the filter unit 1102 is used for:
[0164] Perform a first median filter on the first image to obtain the filtered first image;
[0165] The second image is subjected to a second median filter to obtain the filtered second image.
[0166] In one possible implementation, the filter unit 1102 is used for:
[0167] The first image is subjected to a first median filter process using a first circular filter template;
[0168] The second image is subjected to a second median filter, including:
[0169] The second image is subjected to a second median filter using a second circular filter template; wherein the radius of the first circular filter template is smaller than the radius of the second circular filter template.
[0170] In one possible implementation, the differential unit 1103 is used for:
[0171] Determine the scene light source information of the image acquisition scene where the product image is located;
[0172] Based on the scene lighting information, determine the target scaling factor and / or target offset factor;
[0173] Based on the target scaling factor and / or target offset factor, the filtered first image and the filtered second image are differentially processed to obtain the third image.
[0174] In one possible implementation, the differential unit 1103 is used for:
[0175] Obtain the preset light source information, as well as the preset scaling factor and preset offset factor that match the preset light source information;
[0176] Based on the scene light source information and the difference information between it and the preset light source information, determine the first adjustment data and the second adjustment data;
[0177] After adjusting the preset scaling factor based on the first adjustment data, the target scaling factor is obtained;
[0178] After adjusting the preset offset factor based on the second adjustment data, the target offset factor is obtained.
[0179] In one possible implementation, the determining unit 1104 is configured to:
[0180] Perform grayscale opening operation on the third image to obtain the fourth image;
[0181] Based on a preset grayscale threshold, the fourth image is segmented into conductive foam regions to obtain the fifth image;
[0182] The fifth image is processed by disconnecting connected components to obtain the foam contour information of each conductive foam.
[0183] In one possible implementation, the determining unit 1104 is configured to:
[0184] Based on the foam outline information, at least one assembly attribute information of the conductive foam is determined; wherein, each assembly attribute information has a corresponding assembly qualification requirement.
[0185] Based on the assembly attribute information and assembly qualification requirements, determine the assembly quality of each conductive foam.
[0186] In one possible implementation, the device is also used for:
[0187] Before filtering the first and second images respectively, the conductive foam assembly area in the product image is determined.
[0188] Based on the conductive foam assembly area, the first image and the second image are processed by region of interest extraction to obtain the processed first image and the processed second image.
[0189] The conductive foam assembly quality inspection device provided in this embodiment can perform the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.
[0190] Figure 12This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Figure 12 As shown, the computer device 120 provided in this embodiment includes at least one processor 1201 and a memory 1202. Optionally, the computer device 120 further includes a communication component 1203. The processor 1201, memory 1202, and communication component 1203 are connected via a bus 1204.
[0191] In a specific implementation, at least one processor 1201 executes computer execution instructions stored in memory 1202, causing at least one processor 1201 to perform the above-described method.
[0192] The specific implementation process of processor 1201 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.
[0193] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.
[0194] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.
[0195] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.
[0196] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.
[0197] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.
[0198] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.
[0199] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.
[0200] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.
[0201] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0202] In addition, the functional units in the various embodiments of the present invention 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.
[0203] 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 invention, 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 invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0204] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.
[0205] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.
Claims
1. A method for inspecting the assembly quality of conductive foam, characterized in that, include: Acquire a first image and a second image; wherein the first image indicates a product image without conductive foam; and the second image indicates a product image with conductive foam. The first image and the second image are filtered respectively to obtain the filtered first image and the filtered second image; The filtered first image and the filtered second image are subjected to differential processing to obtain a third image; wherein, the third image includes the foam outline of at least one conductive foam. Based on the third image, the foam outline information of each conductive foam is determined, and based on the foam outline information, the assembly quality of each conductive foam is determined.
2. The method according to claim 1, characterized in that, The first image and the second image are filtered respectively to obtain a filtered first image and a filtered second image, including: The first image is subjected to a first median filter to obtain the filtered first image; The second image is subjected to a second median filter to obtain the filtered second image.
3. The method according to claim 2, characterized in that, The first median filtering process on the first image includes: The first image is subjected to the first median filtering process using the first circular filter template; The second median filtering process on the second image includes: The second image is subjected to the second median filtering process using a second circular filter template; wherein the radius of the first circular filter template is smaller than the radius of the second circular filter template.
4. The method according to claim 1, characterized in that, A third image is obtained by performing a difference processing on the filtered first image and the filtered second image, including: Determine the scene light source information of the image acquisition scene in which the product image is located; Based on the scene light source information, determine the target scaling factor and / or target offset factor; Based on the target scaling factor and / or the target offset factor, the filtered first image and the filtered second image are differentially processed to obtain a third image.
5. The method according to claim 4, characterized in that, Based on the scene light source information, determine the target scaling factor and / or target offset factor, including: Obtain preset light source information, as well as preset scaling factor and preset offset factor matched by the preset light source information; Based on the difference information between the scene light source information and the preset light source information, the first adjustment data and the second adjustment data are determined. After adjusting the preset scaling factor based on the first adjustment data, the target scaling factor is obtained; After adjusting the preset offset factor according to the second adjustment data, the target offset factor is obtained.
6. The method according to claim 1, characterized in that, Based on the third image, the foam outline information of each conductive foam is determined, including: Perform grayscale opening operation on the third image to obtain the fourth image; Based on a preset grayscale threshold, the fourth image is segmented into conductive foam regions to obtain the fifth image; The fifth image is subjected to connected component disconnection processing to obtain the foam contour information of each conductive foam.
7. The method according to claim 1, characterized in that, Based on the foam contour information, the assembly quality of each conductive foam is determined, including: Based on the foam outline information, at least one assembly attribute information of the conductive foam is determined; wherein, each assembly attribute information has a corresponding assembly qualification requirement; Based on the assembly attribute information and the assembly qualification requirements, the assembly quality of each conductive foam is determined.
8. The method according to any one of claims 1-7, characterized in that, Before performing filtering processing on the first image and the second image respectively, the method further includes: Determine the conductive foam assembly area in the product image; Based on the conductive foam assembly area, the first image and the second image are processed by region of interest extraction to obtain the processed first image and the processed second image.
9. A computer device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-8.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-8.