Chip multilayer ceramic capacitor pressing accuracy detection method, system and storage medium

Abstract

The application discloses a chip multilayer ceramic capacitor pressing precision detection method and system and a storage medium, and is applied to the pressing precision detection technical field, and can improve the pressing precision detection reliability, stability and detection efficiency of the chip multilayer ceramic capacitor. The method comprises the following steps: obtaining a pressing side original image of a chip multilayer ceramic capacitor and performing threshold segmentation to obtain a pressing side binary image; performing first positioning on the pressing side binary image to obtain first bottom ceramic diaphragm boundary pixels, so as to perform first image alignment on the pressing side binary image to obtain a first corrected image; obtaining second bottom ceramic diaphragm boundary pixels through horizontal direction rectangular frame selection, so as to perform second image alignment on the first corrected image to obtain a second corrected image; performing second positioning on the second corrected image to obtain first left-right boundary pixels, and obtaining second left-right boundary pixels through vertical direction rectangular frame selection, so as to calculate pressing precision data.

Description

Technical Field

[0001] The present invention relates to the technical field of pressing accuracy detection, and in particular to a pressing accuracy detection method, system and storage medium for chip-type multilayer ceramic capacitors. Background Art

[0002] Multilayer ceramic capacitors (MLCCs) are a new type of component that is indispensable in the electronics, communications, and information industries. Their small size, high capacitance, low price, high stability, and suitability for mass production make them widely used in surface mount applications in consumer electronics, such as communications, computers, and home appliances. The MLCC manufacturing process typically involves lamination, segmentation, hydrostatic pressing, binder removal, and sintering of multiple ceramic diaphragms with printed internal electrodes to produce finished ceramic capacitors. Lamination involves aligning and bonding multiple printed ceramic diaphragms to maximize the facing area between the internal electrodes. The precision of the laminated product directly impacts the quality of the finished ceramic capacitor, necessitating strict control over the production process. Related technologies primarily rely on manual spot checks, where images of the laminated area are captured and the left and right boundaries of the area are marked to measure margins and achieve lamination accuracy. However, manual inspection methods are subject to significant subjectivity, and the measured lamination width is subject to uncertainty, resulting in low reliability and stability in the test results. At the same time, the manual detection method requires offline operation, which is inefficient and difficult to achieve real-time pressing accuracy detection. Summary of the Invention

[0003] In order to solve at least one of the above technical problems, the present invention proposes a method, system and storage medium for detecting the pressing accuracy of chip multilayer ceramic capacitors, which can effectively improve the reliability and stability of the pressing accuracy detection of chip multilayer ceramic capacitors, and effectively improve the efficiency of the pressing accuracy detection.

[0004] In one aspect, an embodiment of the present invention provides a method for detecting the pressing accuracy of a chip-type multilayer ceramic capacitor, comprising the following steps:

[0005] Acquire an original image of the pressed side surface of the chip-type multilayer ceramic capacitor, perform threshold segmentation on the original image of the pressed side surface, and obtain a binary image of the pressed side surface;

[0006] Performing a first positioning on the binary image of the pressed side surface by using morphological features to obtain a first bottom ceramic diaphragm boundary pixel; wherein the morphological features include geometric features and pixel features;

[0007] performing a first image straightening on the laminated side binary image according to the boundary pixels of the first bottom ceramic diaphragm to obtain a first corrected image;

[0008] Selecting a local image of the bottom ceramic diaphragm boundary of the first corrected image through a horizontal rectangular frame to obtain a second bottom ceramic diaphragm boundary pixel;

[0009] performing a second image straightening on the first corrected image according to the boundary pixels of the second bottom ceramic diaphragm to obtain a second corrected image;

[0010] Performing a second positioning on the second corrected image by using the topographical features to obtain first left and right boundary pixels of the inner electrode lamination area in the second corrected image;

[0011] Selecting left and right boundary local images of the inner electrode lamination area in the second corrected image using a vertical rectangular frame according to the first left and right boundary pixels to obtain second left and right boundary pixels; wherein the second left and right boundary pixels include a left boundary pixel and a right boundary pixel;

[0012] The lamination accuracy data is calculated based on the left boundary pixels and the right boundary pixels.

[0013] According to the method for detecting the pressing precision of the chip multilayer ceramic capacitor, the following beneficial effects are achieved: the original image of the pressing side of the chip multilayer ceramic capacitor is first obtained, and the original image of the pressing side is converted into a binary image of the pressing side by threshold segmentation, so as to highlight the boundary of the inner electrode pressing area and the boundary of the bottom ceramic diaphragm to be detected. Then, the binary image of the pressing side is coarsely positioned by the topological feature, that is, first positioning, to obtain the first boundary pixel of the bottom ceramic diaphragm. The topological feature includes a geometric feature and a pixel feature. Then, the binary image of the pressing side is preliminarily aligned according to the first boundary pixel of the bottom ceramic diaphragm, that is, first image alignment, to obtain a first corrected image, so that the boundary direction of the bottom ceramic diaphragm in the binary image of the pressing side is preliminarily located in a horizontal straight line. Further, the boundary local image of the bottom ceramic diaphragm in the first corrected image is selected by a rectangular frame in the horizontal straight line to extract the accurately positioned boundary pixel of the bottom ceramic diaphragm, that is, the second boundary pixel of the bottom ceramic diaphragm, so that the first image is further aligned according to the second boundary pixel of the bottom ceramic diaphragm, that is, second image alignment, to obtain a second corrected image. In this way, the first corrected image is accurately aligned by the second image alignment according to the boundary pixel of the bottom ceramic diaphragm obtained by the horizontal frame selection in the first corrected image, so that the boundary direction of the bottom ceramic diaphragm in the second corrected image is in the horizontal straight line. Further, the second corrected image is second positioned by the topological feature to preliminarily position the left and right boundary pixels of the inner electrode pressing area in the second corrected image, that is, the first left and right boundary pixels. Further, the left and right boundary local image of the inner electrode pressing area in the second corrected image is selected by a vertical rectangular frame according to the first left and right boundary pixels, so that the more accurate left and right boundary local image of the inner electrode pressing area is obtained, that is, the second left and right boundary pixels. The second left and right boundary pixels include a left boundary pixel and a right boundary pixel. Then, the pressing precision data is obtained by calculation according to the left and right boundary pixels, the pressing precision of the chip multilayer ceramic capacitor is detected, and the reliability and stability of the pressing precision detection of the chip multilayer ceramic capacitor are effectively improved. Meanwhile, the efficiency of the pressing precision detection is effectively improved.

[0014] According to some embodiments of the application, the first image alignment of the binary image of the pressing side according to the first boundary pixel of the bottom ceramic diaphragm to obtain a first corrected image comprises:

[0015] a first included angle between a first bottom ceramic diaphragm boundary straight line and a horizontal straight line is fitted according to the first boundary pixel of the bottom ceramic diaphragm; wherein the first bottom ceramic diaphragm boundary straight line is fitted according to the first boundary pixel of the bottom ceramic diaphragm;

[0016] According to the first included angle, the compression side binary image is first image aligned to obtain a first corrected image.

[0017] According to some embodiments of the present application, the second image alignment of the first corrected image according to the second bottom ceramic diaphragm boundary pixel obtains a second corrected image, comprising:

[0018] According to the second bottom ceramic diaphragm boundary straight line fitted by the second bottom ceramic diaphragm boundary pixel, a second included angle with the horizontal direction straight line is obtained; wherein the second bottom ceramic diaphragm boundary straight line is fitted by the second bottom ceramic diaphragm boundary pixel;

[0019] According to the second included angle, the first corrected image is second image aligned to obtain a second corrected image.

[0020] According to some embodiments of the present application, the first positioning of the compression side binary image according to the topographic features obtains a first bottom ceramic diaphragm boundary pixel, comprising:

[0021] According to the geometric features and the pixel features of the ceramic diaphragm, the ceramic diaphragm in the compression side binary image is first positioned to obtain a ceramic diaphragm region;

[0022] According to the bottom boundary pixel of the ceramic diaphragm in the compression side binary image, the first bottom ceramic diaphragm boundary pixel is extracted to obtain the first bottom ceramic diaphragm boundary pixel.

[0023] According to some embodiments of the present application, before the step of obtaining the second bottom ceramic diaphragm boundary pixel by selecting the bottom ceramic diaphragm boundary local image of the first corrected image through the horizontal direction rectangular frame, the method further comprises:

[0024] According to the first bottom ceramic diaphragm boundary pixel, the starting pixel position parameter and the rectangular frame length-width parameter of the horizontal direction rectangular frame are determined.

[0025] According to some embodiments of the present application, the second bottom ceramic diaphragm boundary pixel is obtained by selecting the bottom ceramic diaphragm boundary local image of the first corrected image through the horizontal direction rectangular frame, comprising:

[0026] The bottom ceramic diaphragm boundary local image is selected through the horizontal direction rectangular frame;

[0027] According to the bottom ceramic diaphragm boundary local image, a transverse direction pixel gray scale integral image is constructed;

[0028] According to the transverse direction pixel gray scale integral image, the second bottom ceramic diaphragm boundary pixel is extracted.

[0029] According to some embodiments of the present application, the calculation of the pressing precision data from the left boundary pixel and the right boundary pixel comprises:

[0030] Solving a left boundary straight line according to the left boundary pixel; wherein the left boundary straight line makes the sum of pixel distances from each pixel point in the left boundary pixel to the left boundary straight line minimum;

[0031] Solving a right boundary straight line according to the right boundary pixel; wherein the right boundary straight line makes the sum of pixel distances from each pixel point in the right boundary pixel to the right boundary straight line minimum;

[0032] Calculating a pressing width of the inner electrode after pressing according to the left boundary straight line and the right boundary straight line;

[0033] Comparing the pressing width with the width data of the single ceramic diaphragm inner electrode to obtain the pressing precision data.

[0034] In another aspect, the embodiments of the present application also provide a pressing precision detection system for a chip multilayer ceramic capacitor, comprising:

[0035] A threshold segmentation module, configured to acquire a pressing side original image of the chip multilayer ceramic capacitor, and perform threshold segmentation on the pressing side original image to obtain a pressing side binary image;

[0036] A first positioning module, configured to perform first positioning on the pressing side binary image through topographic features to obtain first bottom ceramic diaphragm boundary pixels; wherein the topographic features include geometric features and pixel features;

[0037] A first alignment module, configured to perform first image alignment on the pressing side binary image according to the first bottom ceramic diaphragm boundary pixels to obtain a first corrected image;

[0038] A first selection module, configured to select a bottom ceramic diaphragm boundary local image of the first corrected image through a horizontal direction rectangular frame to obtain second bottom ceramic diaphragm boundary pixels;

[0039] A second alignment module, configured to perform second image alignment on the first corrected image according to the second bottom ceramic diaphragm boundary pixels to obtain a second corrected image;

[0040] A second positioning module, configured to perform second positioning on the second corrected image through the topographic features to obtain first left and right boundary pixels of an inner electrode pressing area in the second corrected image;

[0041] The second selection module is configured to select left and right boundary local images of the inner electrode pressing area in the second corrected image by a vertical direction rectangular frame according to the first left and right boundary pixels, and obtain second left and right boundary pixels; wherein the second left and right boundary pixels include left boundary pixels and right boundary pixels.

[0042] The pressing precision calculation module is configured to calculate the pressing precision data according to the left boundary pixels and the right boundary pixels.

[0043] In another aspect, the embodiment of the present application further provides a pressing precision detection system for a chip multilayer ceramic capacitor, comprising:

[0044] at least one processor;

[0045] at least one memory configured to store at least one program;

[0046] When the at least one program is executed by the at least one processor, the at least one processor implements the pressing precision detection method for the chip multilayer ceramic capacitor as described in the above embodiment.

[0047] In another aspect, the embodiment of the present application further provides a computer storage medium, wherein a processor executable program is stored, and the processor executable program is used to implement the pressing precision detection method for the chip multilayer ceramic capacitor as described in the above embodiment when executed by the processor. BRIEF DESCRIPTION OF DRAWINGS

[0048] Figure 1 is a flow chart of the pressing precision detection method for the chip multilayer ceramic capacitor provided by the embodiment of the present application;

[0049] Figure 2 is a principle block diagram of the pressing precision detection system for the chip multilayer ceramic capacitor provided by the embodiment of the present application;

[0050] Figure 3 is a difference sequence diagram provided by the embodiment of the present application. DETAILED DESCRIPTION

[0051] The embodiments described in the embodiments of the present application should not be regarded as limitations of the present application, and all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0052] In the following description, "some embodiments" are related to a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description herein is for describing particular embodiments only and is not intended to be limiting of the application.

[0054] Before the embodiments of the present application are introduced, first, the related terms involved in the present application are explained.

[0055] Chip multilayer ceramic capacitor (MLCC): It is a new type of component indispensable in the electronic, communication and information industry, which has the characteristics of small size, large capacitance, low price, high stability and is suitable for mass production. Therefore, chip multilayer ceramic capacitors are widely used in surface mounting of consumer electronic complete machines such as communication, computer, household appliance, etc. In the process of chip multilayer ceramic capacitor, a plurality of ceramic film sheets printed with internal electrodes are usually prepared into finished ceramic capacitors through steps such as pressing, blocking, hydrostatic pressure, glue removal, sintering, etc. Among them, pressing is to align and adhere a plurality of printed ceramic film sheets, so that the internal electrodes have the maximum facing area. The precision of the product after pressing directly affects the quality of the finished ceramic capacitor, so the production process needs to be strictly controlled. After pressing, the black internal electrode pressing area is wrapped by white ceramic material from the pressing side. Usually, the pressing width of the internal electrode after pressing can be measured from the pressing side, and compared with the width of the internal electrode of the single ceramic film sheet to evaluate the pressing precision. In the related art, the detection of MLCC pressing precision mainly relies on manual sampling inspection. The work staff places the pressed sample with the pressing side upward on the visual inspection table with measurement and detection functions, acquires the image of the pressing area by the camera, and then marks the left and right boundaries of the pressing area to measure the margin, so as to realize the detection of pressing precision. However, the manual detection method has strong subjectivity, and cannot guarantee that the marked left and right boundary lines are perpendicular to the reference surface of the bottom ceramic film sheet, resulting in uncertainty in the measured pressing width. In addition, manual detection needs offline operation, which is low in efficiency and difficult to realize real-time pressing precision detection.

[0056] Therefore, based on this, an embodiment of the present application provides a chip multilayer ceramic capacitor pressing precision detection method, system and storage medium, which can effectively improve the reliability and stability of the chip multilayer ceramic capacitor pressing precision detection, and effectively improve the efficiency of the pressing precision detection. Referring to Figure 1 The method of the embodiment of the present application includes but is not limited to steps S110, S120, S130, S140, S150, S160, S170 and S180.

[0057] Specifically, the application process of the method of the embodiment of the present application includes but is not limited to the following steps:

[0058] S110: Obtain a pressing side original image of the chip multilayer ceramic capacitor, and perform threshold segmentation on the pressing side original image to obtain a pressing side binary image.

[0059] S120: Perform first positioning on the pressing side binary image by using a topographic feature to obtain first bottom ceramic diaphragm boundary pixels. The topographic feature includes a geometric feature and a pixel feature.

[0060] S130: Perform first image alignment on the pressing side binary image according to the first bottom ceramic diaphragm boundary pixels to obtain a first corrected image.

[0061] S140: Obtain second bottom ceramic diaphragm boundary pixels by selecting a bottom ceramic diaphragm boundary local image of the first corrected image through a horizontal direction rectangular frame.

[0062] S150: Perform second image alignment on the first corrected image according to the second bottom ceramic diaphragm boundary pixels to obtain a second corrected image.

[0063] S160: Perform second positioning on the second corrected image by using the topographic feature to obtain first left and right boundary pixels of an inner electrode pressing area in the second corrected image.

[0064] S170: Obtain second left and right boundary pixels by selecting a left and right boundary local image of the inner electrode pressing area in the second corrected image through a vertical direction rectangular frame according to the first left and right boundary pixels. The second left and right boundary pixels include a left boundary pixel and a right boundary pixel.

[0065] S180: Calculate pressing precision data according to the left boundary pixel and the right boundary pixel.

[0066] In the embodiment, the embodiment first acquires a compression side original image of the chip multilayer ceramic capacitor, and performs threshold segmentation on the compression side original image to obtain a compression side binary image. Specifically, after the MLCC compression operation, the compressed sample is generally placed in the detection area of the vision system by the conveying belt or other conveying mechanism. When the sample is in place, the vision system is triggered to acquire the compression side original image of the chip multilayer ceramic capacitor. The compression side original image is obtained from the compression side of the chip multilayer ceramic capacitor, that is, the compression side original image. Then, the embodiment performs threshold segmentation on the compression side original image to obtain a binary image of the compression side original image, that is, a compression side binary image. In a threshold segmentation binarization manner, the black internal electrode compression area boundary and the bottom ceramic diaphragm boundary to be detected are highlighted. Illustratively, the lens of the vision system used for image acquisition in the embodiment is a fixed magnification telecentric lens, the magnification is 1.5 times, and the vision system is equipped with an illumination light source. At the same time, in the threshold segmentation process, the embodiment first sets the threshold value of segmentation. The threshold value can be set as a fixed threshold value, such as a fixed threshold value in the range of 90 to 150, or a corresponding threshold value calculated by the common law algorithm. Then, the embodiment compares the gray value of each pixel point in the compression side original image with the set threshold value. The gray value of the pixel point in the compression side original image ranges from 0 to 255. When the gray value of the pixel point in the compression side original image is greater than the set threshold value, the corresponding coordinate position value of the pixel point is set to 1, otherwise it is set to 0, thereby realizing the threshold segmentation operation and obtaining the compression side binary image.

[0067] Further, the embodiment performs first positioning on the compression side binary image by the topography features to obtain first bottom ceramic diaphragm boundary pixels. Specifically, the topography features include geometric features and pixel features. The embodiment performs rough positioning on the bottom ceramic diaphragm boundary by the geometric features and the pixel features of the bottom ceramic diaphragm and the compression region of the inner electrode in the compression side binary image to obtain the first bottom ceramic diaphragm boundary pixels. Then, the embodiment performs first image alignment on the compression side binary image according to the first bottom ceramic diaphragm boundary pixels to obtain a first corrected image. Specifically, the embodiment performs preliminary image alignment on the compression side binary image by the first bottom ceramic diaphragm boundary pixels to relieve the problem of the bottom ceramic diaphragm boundary inclination, so that the bottom ceramic diaphragm boundary in the compression side binary image is preliminarily located on a horizontal straight line. Then, the embodiment obtains second bottom ceramic diaphragm boundary pixels by selecting a bottom ceramic diaphragm boundary local image of the first corrected image through a horizontal direction rectangular frame. Specifically, after preliminary correction, in order to further accurately align the first corrected image, the embodiment selects the bottom ceramic diaphragm boundary pixels in the first corrected image, i.e., the second bottom ceramic diaphragm boundary pixels, by selecting the first corrected bottom ceramic diaphragm boundary local image through the horizontal direction rectangular frame. It is easy to understand that, since the first image alignment is performed on the compression side binary image by the first bottom ceramic diaphragm boundary pixels obtained through rough positioning, and the bottom ceramic diaphragm boundary in the compression side binary image is inclined, the first bottom ceramic diaphragm boundary pixels obtained through rough positioning are generally accurate, which also causes the bottom ceramic diaphragm boundary in the first corrected image not to be completely on the horizontal straight line, so that the second image alignment is needed. Further, the embodiment performs second image alignment on the first corrected image according to the second bottom ceramic diaphragm boundary pixels to obtain a second corrected image. Specifically, the embodiment further aligns the first corrected image, i.e., the second image alignment, according to the second bottom ceramic diaphragm boundary pixels obtained by accurately selecting through the horizontal direction rectangular frame, so as to obtain the second corrected image, so that the bottom ceramic diaphragm boundary in the second corrected image is on the horizontal straight line, and the problem of the compression width detection error caused by the inclination of the bottom ceramic diaphragm boundary in the image is relieved.

[0068] Further, the embodiment performs second positioning on the second corrected image through the topographic features to obtain the first left-right boundary pixels of the inner electrode pressing region in the second corrected image. Specifically, the embodiment performs preliminary positioning on the left-right boundary pixels of the inner electrode pressing region in the second corrected image through the topographic features to obtain the first left-right boundary pixels. It is easy to understand that the topographic features include geometric features and pixel features, for example, the geometric shape of the inner electrode pressing region, and the inner electrode pressing region is black and the bottom ceramic diaphragm is white, and there are different pixel features after threshold segmentation. Then, the embodiment selects the left-right boundary local image of the inner electrode pressing region in the second corrected image through a vertical direction rectangular frame according to the first left-right boundary pixels to obtain the second left-right boundary pixels. Specifically, the second left-right boundary pixels include left boundary pixels and right boundary pixels. Correspondingly, the first left-right boundary pixels also include a first left boundary pixel and a first right boundary pixel. After the left-right boundary pixels of the inner electrode pressing region in the second corrected image are preliminarily positioned through the topographic features, the embodiment selects the left-right boundary local image of the inner electrode pressing region in the second corrected image through a vertical direction rectangular frame according to the first left-right boundary pixels, so as to more accurately obtain the left boundary pixels and the right boundary pixels in the second corrected image, i.e., the second left-right boundary pixels. Then, the embodiment calculates the pressing precision data according to the left boundary pixels and the right boundary pixels, realizes the detection of the pressing precision of the chip multilayer ceramic capacitor, and effectively improves the reliability and stability of the pressing precision detection of the chip multilayer ceramic capacitor. At the same time, the embodiment can realize real-time detection, and effectively improves the efficiency of the pressing precision detection.

[0069] In some embodiments of the application, the first image alignment is performed on the pressing side binary image according to the first bottom ceramic diaphragm boundary pixels to obtain a first corrected image, including but not limited to:

[0070] A first included angle between the first bottom ceramic diaphragm boundary straight line and the horizontal direction straight line is fitted according to the first bottom ceramic diaphragm boundary pixels. The first bottom ceramic diaphragm boundary straight line is fitted through the first bottom ceramic diaphragm boundary pixels.

[0071] The first image alignment is performed on the pressing side binary image according to the first included angle to obtain a first corrected image.

[0072] In the embodiment, the first angle between the first bottom ceramic diaphragm boundary straight line and the horizontal straight line is obtained by fitting the first bottom ceramic diaphragm boundary pixels, and the first image alignment is performed on the compression side binary image according to the first angle to obtain the first corrected image. Specifically, the first bottom ceramic diaphragm boundary straight line is obtained by fitting the first bottom ceramic diaphragm boundary pixels in the embodiment. The first bottom ceramic diaphragm boundary pixels are fitted to obtain the boundary straight line of the bottom ceramic diaphragm, i.e., the first ceramic diaphragm boundary straight line. Then, the compression side binary image is rotated according to the first angle between the first bottom ceramic diaphragm boundary straight line and the horizontal straight line, so that the boundary straight line of the bottom ceramic diaphragm in the compression side binary image is in the horizontal position, and the first corrected image is obtained.

[0073] In some embodiments of the application, the second image alignment is performed on the first corrected image according to the second bottom ceramic diaphragm boundary pixels to obtain the second corrected image, including but not limited to:

[0074] A second angle between the second bottom ceramic diaphragm boundary straight line and the horizontal straight line is obtained by fitting the second bottom ceramic diaphragm boundary pixels. The second bottom ceramic diaphragm boundary straight line is obtained by fitting the second bottom ceramic diaphragm boundary pixels.

[0075] The second image alignment is performed on the first corrected image according to the second angle to obtain the second corrected image.

[0076] In the embodiment, the second angle between the second bottom ceramic diaphragm boundary straight line and the horizontal straight line is obtained by fitting the second bottom ceramic diaphragm boundary pixels, and the second image alignment is performed on the first corrected image according to the second angle to obtain the second corrected image. Specifically, the bottom ceramic diaphragm boundary pixels obtained by the preliminary positioning of the compression side binary image according to the topographic features are corrected during the first image alignment. Since the bottom ceramic diaphragm in the compression side binary image has a certain inclination, the bottom ceramic diaphragm boundary pixels obtained directly have a certain error, which also causes the bottom ceramic diaphragm boundary in the first corrected image obtained after the first image alignment to have a certain angle with the horizontal straight line. Therefore, the second image alignment is performed on the first corrected image to further alleviate the problem of the inclination of the bottom ceramic diaphragm boundary in the image. The second bottom ceramic diaphragm boundary straight line is obtained by fitting the second bottom ceramic diaphragm boundary pixels, and the first corrected image is rotated according to the second angle between the second bottom ceramic diaphragm boundary straight line and the horizontal straight line, i.e., the second angle, to obtain the second corrected image, thereby further alleviating the problem of the inclination of the bottom ceramic diaphragm boundary in the image.

[0077] In some embodiments of the present application, the first positioning of the compression side binary image by the topographic feature obtains the first bottom ceramic diaphragm boundary pixel, including but not limited to:

[0078] According to the geometric feature and the pixel feature of the ceramic diaphragm, the first positioning of the ceramic diaphragm in the compression side binary image is performed to obtain the ceramic diaphragm region.

[0079] According to the ceramic diaphragm region, the bottom boundary pixel of the ceramic diaphragm in the compression side binary image is extracted to obtain the first bottom ceramic diaphragm boundary pixel.

[0080] In the specific embodiment, the embodiment first performs the preliminary positioning, i.e., the first positioning, of the ceramic diaphragm in the compression side binary image according to the geometric feature and the pixel feature of the ceramic diaphragm to obtain the ceramic diaphragm region, and then extracts the bottom boundary pixel of the ceramic diaphragm in the compression side binary image according to the ceramic diaphragm region obtained by positioning to obtain the first bottom ceramic diaphragm boundary pixel. Specifically, the embodiment first performs the preliminary positioning according to the geometric feature and the pixel feature of the ceramic diaphragm, for example, the geometric feature of the ceramic diaphragm is a rectangle, and the pixel feature of the ceramic diaphragm is white. The embodiment preliminarily positions the region of the ceramic diaphragm in the compression side binary image according to the rectangular feature and the white pixel feature of the ceramic diaphragm to obtain the ceramic diaphragm region. Then, the embodiment extracts the bottom boundary pixel of the ceramic diaphragm in the compression side binary image through the ceramic diaphragm region to obtain the first bottom ceramic diaphragm boundary pixel.

[0081] In some embodiments of the present application, before performing the step of extracting the second bottom ceramic diaphragm boundary pixel by selecting the bottom ceramic diaphragm boundary local image of the first correction image through the horizontal direction rectangular frame, the chip multilayer ceramic capacitor compression precision detection method provided by the embodiment further includes but is not limited to:

[0082] According to the first bottom ceramic diaphragm boundary pixel, the starting pixel position parameter and the rectangular frame length-width parameter of the horizontal direction rectangular frame are determined.

[0083] In the embodiment, before the bottom ceramic diaphragm boundary partial image of the first corrected image is selected by the horizontal direction rectangular frame, the starting pixel position parameter and the length and width parameter of the horizontal direction rectangular frame are set. Specifically, the starting pixel position and the length and width parameter of the horizontal direction rectangular frame are determined according to the first bottom ceramic diaphragm boundary pixel. In the embodiment, the starting pixel position parameter and the length and width parameter of the horizontal direction rectangular frame are determined by the first bottom ceramic diaphragm boundary pixel obtained by threshold segmentation. It is easy to understand that the horizontal direction rectangular frame only needs to make the boundary of the ceramic diaphragm in the first corrected image be in the rectangular partial image region. Exemplarily, when the starting pixel position of the horizontal direction rectangular frame is (row1, col1), the length pixel is W, and the width pixel is B, that is, the upper left corner of the rectangular partial image region is located at the coordinate (row1, col1) on the image, the lower right corner is (row1+B-1, col1+W-1), and the accurate edge pixel extraction horizontal distance is set as wherein, Generally, 4 is taken.

[0084] In some embodiments of the application, the bottom ceramic diaphragm boundary partial image of the first corrected image is selected by the horizontal direction rectangular frame to obtain the second bottom ceramic diaphragm boundary pixel, including but not limited to:

[0085] The bottom ceramic diaphragm boundary partial image is selected by the horizontal direction rectangular frame.

[0086] The horizontal direction pixel gray integral image is constructed according to the bottom ceramic diaphragm boundary partial image.

[0087] The second bottom ceramic diaphragm boundary pixel is extracted according to the horizontal direction pixel gray integral image.

[0088] In the embodiment, the embodiment first selects a bottom ceramic diaphragm boundary local image by a horizontal direction rectangular frame, then constructs a horizontal direction pixel gray value integral image according to the bottom ceramic diaphragm boundary local image, and extracts a second bottom ceramic diaphragm boundary pixel according to the horizontal direction pixel gray value integral image. Specifically, the embodiment first selects a rectangular local image, i.e. the bottom ceramic diaphragm boundary local image, by a horizontal direction rectangular frame. Then, a single horizontal direction pixel gray value integral image corresponding to the rectangular local image region is generated from left to right. In the horizontal direction pixel gray value integral image, the number at the same position corresponding to the first corrected image is the sum of the gray value of the left pixel and the pixel itself. For example, the value of the horizontal direction pixel gray value integral image at (row1, col1) is the gray value of the first corrected image at (row1, col1), the value of the horizontal direction pixel gray value integral image at (row1, col1+1) is the value of the horizontal direction pixel gray value integral image at (row1, col1) plus the gray value of the first corrected image at (row1, col1+1), the value of the horizontal direction pixel gray value integral image at (row1, col1+2) is the value of the integral image at (row1, col1+1) plus the gray value of the first corrected image at (row1, col1+2), and so on, to construct the horizontal direction pixel gray value integral image. Further, in the horizontal direction pixel gray value integral image, the embodiment selects the values of the columns of col1, col1+AL, calculates the difference value sequence of the columns of col1, col1+AL, and the calculation formula is shown in the following formula (1):

[0089] t(x) = a(row1+x, col1+AL) - a(row1+x, col1) (1)

[0090] wherein, in the formula, x ranges from 0 to B-1, a(x, y) represents the value of the point (x, y) on the horizontal direction pixel gray value integral image, t(x) is the difference value sequence, and the difference value sequence is shown in the following table 1. Figure 3 The embodiment derives each point by the derivation of the discrete function, and obtains the extreme point horizontal coordinate as col1+AL according to the quadratic function fitting of the derived values. Therefore, the first accurate boundary pixel coordinate is obtained as Similarly, the second accurate boundary pixel coordinate is obtained as By analogy, until the selected column is not in the rectangular local region, to extract the accurate ceramic diaphragm bottom boundary pixel coordinate, i.e. the second bottom ceramic diaphragm boundary pixel.

[0091] It should be noted that in some embodiments of the present application, the process of obtaining the second left and right boundary pixels from the left and right boundary pixels of the first image by using the vertical direction rectangular frame to select the left and right boundary partial image of the inner electrode pressing area in the second corrected image is similar to the process of obtaining the second bottom ceramic diaphragm boundary pixel by using the horizontal direction rectangular frame to select the bottom ceramic diaphragm boundary partial image of the first corrected image. The accurate left and right boundary pixels of the inner electrode pressing area are obtained by replacing the single horizontal direction pixel gray integral graph with the first longitudinal direction pixel gray integral graph, and details are not repeated here.

[0092] In some embodiments of the present application, the pressing accuracy data is calculated according to the left and right boundary pixels, including but not limited to:

[0093] The left boundary straight line is solved according to the left boundary pixels. The left boundary straight line makes the sum of the pixel distances from each pixel point in the left boundary pixels to the left boundary straight line minimum.

[0094] The right boundary straight line is solved according to the right boundary pixels. The right boundary straight line makes the sum of the pixel distances from each pixel point in the right boundary pixels to the right boundary straight line minimum.

[0095] The pressing width of the inner electrode after pressing is calculated according to the left and right boundary straight lines.

[0096] The pressing accuracy data is obtained by comparing the pressing width with the width data of the single ceramic diaphragm inner electrode.

[0097] In the specific embodiment, the left and right boundary pixels are first fitted with straight lines to obtain the corresponding left and right boundary straight lines, and then the pressing width of the inner electrode after pressing is calculated according to the left and right boundary straight lines, so that the pressing accuracy data is obtained by comparing the pressing width with the width data of the single ceramic diaphragm inner electrode. Specifically, the left boundary straight line is solved according to the left boundary pixels, so that the sum of the pixel distances from each pixel point in the left boundary pixels to the left boundary straight line is minimum. At the same time, the right boundary straight line is solved according to the right boundary pixels, so that the sum of the pixel distances from each pixel point in the right boundary pixels to the right boundary straight line is minimum. For example, the left boundary optimal straight line, i.e. the left boundary straight line, is solved with the left boundary pixel coordinate set S2. In the process, an equivalent error model with the minimum sum of pixel distances is established as shown in the following formula (2):

[0098]

[0099] In the formula, e(s) is the error, (x i ,y i )∈S2, and n is the number of boundary pixel coordinates in S2.

[0100] Further, the embodiment takes the c1 derivative of e(s) as shown in the following formula (3):

[0101]

[0102] Next, the embodiment solves the corresponding extreme point has that is is the mean value of the horizontal coordinates of the pixel coordinates in the left boundary pixel coordinate set S2.

[0103] Further, the embodiment calculates the pressing width of the pressed inner electrode according to the left boundary straight line and the right boundary straight line solved, and compares the pressing width with the width data of the single ceramic diaphragm inner electrode to obtain the pressing precision data.

[0104] One embodiment of the present application also provides a chip multilayer ceramic capacitor pressing precision detection system, comprising:

[0105] The threshold segmentation module is configured to acquire a pressing side original image of the chip multilayer ceramic capacitor, and perform threshold segmentation on the pressing side original image to obtain a pressing side binary image.

[0106] The first positioning module is configured to perform first positioning on the pressing side binary image through the topographic features to obtain first bottom ceramic diaphragm boundary pixels.

[0107] The first alignment module is configured to perform first image alignment on the pressing side binary image according to the first bottom ceramic diaphragm boundary pixels to obtain a first corrected image.

[0108] The first selection module is configured to select a bottom ceramic diaphragm boundary local image of the first corrected image through a horizontal direction rectangular frame to obtain second bottom ceramic diaphragm boundary pixels.

[0109] The second alignment module is configured to perform second image alignment on the first corrected image according to the second bottom ceramic diaphragm boundary pixels to obtain a second corrected image.

[0110] The second positioning module is configured to perform second positioning on the second corrected image through the topographic features to obtain first left and right boundary pixels of an inner electrode pressing area in the second corrected image.

[0111] The second selection module is configured to select left and right boundary local images of the inner electrode pressing area in the second corrected image through a vertical direction rectangular frame according to the first left and right boundary pixels to obtain second left and right boundary pixels.

[0112] The lamination accuracy calculation module is used to calculate the lamination accuracy data based on the left boundary pixels and the right boundary pixels.

[0113] Reference Figure 2 One embodiment of the present invention further provides a chip-type multilayer ceramic capacitor pressing accuracy detection system, comprising:

[0114] At least one processor 210 .

[0115] At least one memory 220 is configured to store at least one program.

[0116] When the at least one program is executed by the at least one processor 210 , the at least one processor 210 implements the method for detecting the pressing accuracy of the chip-type multilayer ceramic capacitor as described in the above embodiment.

[0117] An embodiment of the present invention further provides a computer-readable storage medium, which stores computer-executable instructions. The computer-executable instructions are executed by one or more control processors, for example, to execute the steps described in the above embodiment.

[0118] Those skilled in the art will appreciate that all or some of the steps and systems in the method disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, and the computer-readable medium can include computer storage media (or non-transitory media) and communication media (or temporary media). As known to those skilled in the art, the term computer storage media is included in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data) and is volatile and non-volatile, removable, and non-removable. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory, or other memory technology, CD-ROM, digital versatile disks (DVD), or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage, or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, as is well known to those skilled in the art, communication media typically embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0119] The above is a specific description of the preferred embodiment of the present application, but the present application is not limited to the above-described embodiments, and those skilled in the art can make various equivalent modifications or replacements without departing from the spirit of the present application, and these equivalent modifications or replacements are all included in the scope defined by the claims of the present application.

Claims

1. A method for detecting the pressing accuracy of a chip multilayer ceramic capacitor, characterized in that: The following steps are involved: Acquire an original image of the pressed side surface of the chip-type multilayer ceramic capacitor, perform threshold segmentation on the original image of the pressed side surface, and obtain a binary image of the pressed side surface; Performing a first positioning on the binary image of the pressed side surface by using morphological features to obtain a first bottom ceramic diaphragm boundary pixel; wherein the morphological features include geometric features and pixel features; performing a first image straightening on the laminated side binary image according to the boundary pixels of the first bottom ceramic diaphragm to obtain a first corrected image; Selecting a local image of the bottom ceramic diaphragm boundary of the first corrected image through a horizontal rectangular frame to obtain a second bottom ceramic diaphragm boundary pixel; performing a second image straightening on the first corrected image according to the boundary pixels of the second bottom ceramic diaphragm to obtain a second corrected image; Performing a second positioning on the second corrected image by using the topographical features to obtain first left and right boundary pixels of the inner electrode lamination area in the second corrected image; Selecting left and right boundary local images of the inner electrode lamination area in the second corrected image using a vertical rectangular frame according to the first left and right boundary pixels to obtain second left and right boundary pixels; wherein the second left and right boundary pixels include a left boundary pixel and a right boundary pixel; The lamination accuracy data is calculated based on the left boundary pixels and the right boundary pixels.

2. The method for detecting the pressing accuracy of a chip-type multilayer ceramic capacitor according to claim 1, wherein: The step of performing a first image straightening on the laminated side binary image according to the first bottom ceramic diaphragm boundary pixels to obtain a first corrected image includes: Obtaining a first angle between a first bottom ceramic diaphragm boundary straight line and a horizontal straight line according to pixel fitting of the first bottom ceramic diaphragm boundary; wherein the first bottom ceramic diaphragm boundary straight line is obtained by pixel fitting of the first bottom ceramic diaphragm boundary; A first image straightening is performed on the laminated side binary image according to the first included angle to obtain a first corrected image.

3. The method for detecting the pressing accuracy of a chip-type multilayer ceramic capacitor according to claim 2, wherein: The step of performing a second image straightening on the first corrected image according to the boundary pixels of the second bottom ceramic diaphragm to obtain a second corrected image includes: Obtaining a second angle between the second bottom ceramic diaphragm boundary straight line and the horizontal straight line according to pixel fitting of the second bottom ceramic diaphragm boundary; wherein the second bottom ceramic diaphragm boundary straight line is obtained by pixel fitting of the second bottom ceramic diaphragm boundary; Perform a second image straightening on the first corrected image according to the second included angle to obtain a second corrected image.

4. The method for detecting the pressing accuracy of a chip-type multilayer ceramic capacitor according to claim 1, wherein: The first positioning of the pressed side binary image by using the topographical features to obtain the first bottom ceramic diaphragm boundary pixel includes: Performing a first positioning of the ceramic diaphragm in the pressed side binary image according to the geometric features and the pixel features of the ceramic diaphragm to obtain a ceramic diaphragm area; The bottom boundary pixels of the ceramic diaphragm in the pressed side binary image are extracted according to the ceramic diaphragm area to obtain the first bottom ceramic diaphragm boundary pixels.

5. The method for detecting the pressing accuracy of a chip-type multilayer ceramic capacitor according to claim 1, wherein: Before executing the step of selecting a local image of the bottom ceramic diaphragm boundary of the first corrected image using a horizontal rectangular frame to obtain pixels of the second bottom ceramic diaphragm boundary, the method further includes: The starting pixel position parameters and the length and width parameters of the horizontal rectangular frame are determined according to the boundary pixels of the first bottom ceramic diaphragm.

6. The method for detecting the pressing accuracy of a chip-type multilayer ceramic capacitor according to claim 1, wherein: The step of selecting a local image of the bottom ceramic diaphragm boundary of the first corrected image by using a horizontal rectangular frame to obtain a second bottom ceramic diaphragm boundary pixel includes: Selecting a local image of the bottom ceramic diaphragm boundary through the horizontal rectangular frame; Constructing a lateral pixel grayscale integral image according to the local image of the bottom ceramic diaphragm boundary; The second bottom ceramic diaphragm boundary pixels are extracted based on the lateral pixel grayscale integral image.

7. The method for detecting the pressing accuracy of a chip-type multilayer ceramic capacitor according to claim 1, wherein: The calculating and obtaining the lamination accuracy data according to the left boundary pixels and the right boundary pixels includes: Determining a left boundary line based on the left boundary pixels; wherein the left boundary line minimizes the sum of pixel distances from each pixel point in the left boundary pixels to the left boundary line; Determining a right boundary line based on the right boundary pixels; wherein the right boundary line minimizes the sum of pixel distances from each pixel point in the right boundary pixels to the right boundary line; Calculating the pressed width of the inner electrode after pressing according to the left boundary straight line and the right boundary straight line; The pressing accuracy data is obtained by comparing the pressing width with the width data of the electrode in the monolithic ceramic diaphragm.

8. A chip-type multilayer ceramic capacitor pressing accuracy detection system, characterized in that: include: a threshold segmentation module, configured to obtain an original image of the pressed side surface of the chip-type multilayer ceramic capacitor, and perform threshold segmentation on the original image of the pressed side surface to obtain a binary image of the pressed side surface; A first positioning module is configured to perform a first positioning on the pressed side binary image by using morphological features to obtain boundary pixels of the first bottom ceramic diaphragm; wherein the morphological features include geometric features and pixel features; a first straightening module, configured to perform a first image straightening on the pressed side binary image according to the boundary pixels of the first bottom ceramic diaphragm to obtain a first corrected image; a first selection module, configured to select a local image of a bottom ceramic diaphragm boundary of the first corrected image using a horizontal rectangular frame to obtain a second bottom ceramic diaphragm boundary pixel; a second correction module, configured to perform a second image correction on the first correction image according to the boundary pixels of the second bottom ceramic diaphragm to obtain a second correction image; a second positioning module, configured to perform a second positioning on the second corrected image by using the topographical features to obtain first left and right boundary pixels of the inner electrode lamination area in the second corrected image; A second selection module is configured to select, based on the first left and right boundary pixels, the left and right boundary local images of the inner electrode lamination area in the second corrected image using a vertical rectangular frame to obtain second left and right boundary pixels; wherein the second left and right boundary pixels include a left boundary pixel and a right boundary pixel; The lamination accuracy calculation module is used to calculate lamination accuracy data according to the left boundary pixels and the right boundary pixels.

9. A chip-type multilayer ceramic capacitor pressing accuracy detection system, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method for detecting the pressing accuracy of a chip-type multilayer ceramic capacitor according to any one of claims 1 to 7.

10. A computer storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to implement the method for detecting the pressing accuracy of a chip-type multilayer ceramic capacitor according to any one of claims 1 to 7 when executed by the processor.

Images