Method and device for detecting the aperture of a through hole of a glass sheet
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HUNAN CREATOR INFORMATION TECH CO LTD
- Filing Date
- 2022-12-28
- Publication Date
- 2026-06-16
Smart Images
Figure CN115824073B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of through-hole diameter measurement technology, and in particular to a method for detecting the through-hole diameter of a glass plate, and also to a device for detecting the through-hole diameter of a glass plate. Background Technology
[0002] After drilling holes in glass sheets (such as flat glass, inorganic glass, plexiglass, acrylic, etc.) on the production line, online detection of the through-hole diameter is an essential step. Currently, many production lines lack automated detection equipment, relying solely on manual inspection and quality control. However, manual inspection suffers from low efficiency and accuracy. Subjective factors, in particular, lead to inconsistent quality control standards for glass outputs, making it impossible to obtain the required quality data in real time. This hinders data statistics and retrieval, resulting in low automation and high labor costs. Alternatively, machine vision technology can now be used to automatically detect the through-hole diameter in glass sheets. This allows for online detection of through-hole diameter with high accuracy, meeting the requirements for through-hole inspection of sheets of varying widths and thicknesses. However, current machine vision inspection equipment requires the lens optical axis and the center of the through-hole to be aligned. When the center of the through-hole deviates from the lens optical axis, accurate measurement of the through-hole diameter becomes difficult. Summary of the Invention
[0003] This invention provides a method and apparatus for detecting the diameter of through holes in glass plates, in order to solve the technical problem that existing machine vision inspection equipment has difficulty in accurately measuring the diameter of through holes when the center of the through hole deviates from the optical axis of the lens.
[0004] According to one aspect of the present invention, a method for detecting the aperture of through holes in a glass plate is provided, comprising the following:
[0005] The focal height from the camera lens focus to the lower surface of the glass plate is calibrated;
[0006] Acquire an image of a through hole on a glass plate, determine the through hole region in the through hole image, and calculate the lower surface pixel diameter of the through hole based on the through hole region;
[0007] The pixel equivalent of the lower surface of the glass plate is obtained based on the focal height calibration;
[0008] The lower surface pixel diameter of the through hole is converted to its actual physical diameter based on the lower surface pixel equivalent of the glass plate.
[0009] Furthermore, the process of calibrating the focal height from the camera lens focus to the lower surface of the glass plate includes the following:
[0010] Select a first glass plate of a certain thickness, place the calibration object on the first glass plate, measure the first height from the upper surface of the calibration object to the lower surface of the first glass plate, and record the first pixel length of the calibration object in the camera image;
[0011] Select a second glass plate of a different thickness, place the same calibration object on the second glass plate, measure the second height from the upper surface of the calibration object to the lower surface of the second glass plate, and record the second pixel length of the calibration object in the camera image at this time;
[0012] Using the lens focus as one vertex of the triangle, and the two endpoints of the plane containing the upper surface of the calibration object in the camera's field of view during the first calibration and the two endpoints of the plane containing the upper surface of the calibration object in the camera's field of view during the second calibration, construct similar triangles.
[0013] The focal height is calculated based on the geometric relationship of similar triangles.
[0014] Furthermore, the focal height is calculated based on the following formula:
[0015]
[0016] Where H represents the focal height, L1 and L2 represent the first pixel length and the second pixel length, respectively, and d1 and d2 represent the first height and the second height, respectively.
[0017] Furthermore, the process of calculating the lower surface pixel diameter of the via based on the via region includes the following:
[0018] Obtain the coordinates of the projection point of the lens focus on the through-hole image plane;
[0019] Obtain the pixel coordinates of all points on the contour line of the through-hole region, and calculate the centroid coordinates of the through-hole region by averaging the values.
[0020] Draw a line connecting the projection point and the centroid, and rotate the line connecting the projection point and the centroid clockwise and counterclockwise around the projection point until the line leaves the through-hole region, thus obtaining two tangent points between the line and the through-hole region.
[0021] The lower surface pixel diameter of the through hole is obtained by performing circumferential fitting on a segment of arc on the contour line with two tangent points as endpoints and far from the projection point.
[0022] Furthermore, the process of obtaining the pixel equivalent of the lower surface of the glass plate based on the focal height calibration includes the following:
[0023] Select a third glass plate of a certain thickness, place the calibration object on the third glass plate, measure the third height from the upper surface of the calibration object to the lower surface of the third glass plate, and record the third pixel length of the calibration object in the camera image and the actual physical length.
[0024] Using the lens focus as one vertex of the triangle, and the two endpoints of the plane containing the upper surface of the calibration object in the camera's field of view during the third calibration, and the two endpoints of the plane containing the lower surface of the third glass plate in the camera's field of view, respectively, are used as the other two vertices to construct similar triangles;
[0025] The pixel equivalent of the lower surface of the glass plate is calculated based on the geometric relationship of similar triangles.
[0026] Furthermore, the pixel equivalent of the lower surface of the glass plate is calculated based on the following formula:
[0027]
[0028] Where ρ represents the pixel equivalent of the lower surface of the glass plate, H represents the focal height, d represents the third height, and L... mm and L pixel These represent the actual physical length of the calibrated object and the length of the third pixel, respectively.
[0029] Furthermore, the following is included before performing focus height calibration:
[0030] Adjust the camera's imaging plane to be parallel to the lower surface of the glass plate.
[0031] Furthermore, the following is included before performing focus height calibration:
[0032] Determine the range of distortion in the camera's imaging plane caused by the lens, and select a distortion-free area for imaging.
[0033] Furthermore, the following is included before performing focus height calibration:
[0034] Make sure the lens optical axis and the center of the sensor are on a straight line.
[0035] In addition, the present invention also provides a device for detecting the aperture of a through hole in a glass plate, comprising:
[0036] The first calibration module is used to calibrate the focal height from the camera lens focus to the lower surface of the glass plate;
[0037] The image processing module is used to acquire images of through holes on the glass plate, determine the through hole region in the through hole image, and calculate the lower surface pixel diameter of the through hole based on the through hole region.
[0038] The second calibration module is used to calibrate the pixel equivalent of the lower surface of the glass plate based on the focal height.
[0039] The size conversion module is used to convert the diameter of the lower surface pixels of the through hole into the actual physical diameter based on the lower surface pixel equivalent of the glass plate.
[0040] The present invention has the following effects:
[0041] The method for detecting the diameter of through holes in glass plates according to the present invention first calibrates the focal height from the lens focus of a camera to the lower surface of the glass plate. Then, an image of the through hole on the glass plate is captured by the camera. After determining the through hole region in the image, the pixel diameter of the lower surface of the through hole can be calculated. Then, based on the calibrated focal height, the pixel equivalent of the lower surface of the glass plate is obtained. Finally, based on the pixel equivalent of the lower surface of the glass plate, the pixel diameter of the lower surface of the through hole is converted into the actual physical diameter. During the through hole diameter detection process, it is not necessary to ensure that the lens optical axis and the center of the through hole are on the same straight line. It is only necessary to determine the through hole region in the image, and the pixel diameter of the lower surface of the through hole can be calculated based on the through hole region. After calculating the pixel equivalent of the lower surface of the glass plate based on the pre-calibrated focal height, the actual physical diameter of the through hole can be calculated, thereby accurately measuring the through hole diameter.
[0042] In addition, the through-hole diameter detection device for glass plates of the present invention also has the above-mentioned advantages.
[0043] In addition to the objectives, features, and advantages described above, the present invention has other objectives, features, and advantages. The invention will now be described in further detail with reference to the figures. Attached Figure Description
[0044] The accompanying drawings, which form part of this application, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:
[0045] Figure 1 This is a flowchart illustrating a preferred embodiment of the method for detecting the aperture diameter of a glass plate.
[0046] Figure 2 yes Figure 1 A schematic diagram of the sub-process of step S1.
[0047] Figure 3 This is a schematic diagram illustrating the principle of calibrating the focal height in a preferred embodiment of the present invention.
[0048] Figure 4 This is a schematic diagram of a through-hole image captured in a preferred embodiment of the present invention when the optical axis of the lens and the center of the through-hole are not on the same straight line.
[0049] Figure 5 yes Figure 1 A schematic diagram of the sub-process of step S2.
[0050] Figure 6 This is a schematic diagram illustrating the principle of calculating the diameter of a through-hole pixel in a preferred embodiment of the present invention.
[0051] Figure 7 yes Figure 1 A schematic diagram of the sub-process of step S3.
[0052] Figure 8 This is a schematic diagram illustrating the principle of calibrating the pixel equivalent of the lower surface of a glass plate in a preferred embodiment of the present invention.
[0053] Figure 9 This is a schematic diagram of the module structure of a through-hole diameter detection device for glass plates according to another embodiment of the present invention. Detailed Implementation
[0054] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, the present invention can be implemented in many different ways as defined and covered below.
[0055] Understandable, such as Figure 1 As shown, a preferred embodiment of the present invention provides a method for detecting the aperture of a through-hole in a glass plate, comprising the following:
[0056] Step S1: Calibrate the focal height from the camera lens focus to the lower surface of the glass plate;
[0057] Step S2: Obtain an image of the through hole on the glass plate, determine the through hole area in the through hole image, and calculate the lower surface pixel diameter of the through hole based on the through hole area;
[0058] Step S3: Obtain the pixel equivalent of the lower surface of the glass plate based on the focal height calibration;
[0059] Step S4: Convert the lower surface pixel diameter of the through hole to the actual physical diameter based on the lower surface pixel equivalent of the glass plate.
[0060] It is understood that the method for detecting the diameter of through-holes in glass plates in this embodiment first calibrates the focal height from the camera lens focus to the lower surface of the glass plate. Then, it uses the camera to capture an image of the through-hole on the glass plate. After determining the through-hole area in the image, the pixel diameter of the lower surface of the through-hole can be calculated. Then, based on the calibrated focal height, the pixel equivalent of the lower surface of the glass plate is obtained. Finally, based on the pixel equivalent of the lower surface of the glass plate, the pixel diameter of the lower surface of the through-hole is converted into the actual physical diameter. During the through-hole diameter detection process, it is not necessary to ensure that the lens optical axis and the center of the through-hole are on the same straight line. It is only necessary to determine the through-hole area in the image, and the pixel diameter of the lower surface of the through-hole can be calculated based on this area. After calculating the pixel equivalent of the lower surface of the glass plate based on the pre-calibrated focal height, the actual physical diameter of the through-hole can be calculated, thus allowing for accurate measurement of the through-hole diameter.
[0061] Understandable, such as Figure 2 As shown, in step S1, the process of calibrating the focal height from the camera lens focus to the lower surface of the glass plate includes the following:
[0062] Step S11: Select a first glass plate of a certain thickness, place the calibration object on the first glass plate, measure the first height from the upper surface of the calibration object to the lower surface of the first glass plate, and record the first pixel length of the calibration object in the camera image;
[0063] Step S12: Select a second glass plate of another thickness, place the same calibration object on the second glass plate, measure the second height from the upper surface of the calibration object to the lower surface of the second glass plate, and record the second pixel length of the calibration object in the camera image at this time;
[0064] Step S13: Using the lens focus as one vertex of the triangle, and using the two endpoints of the plane containing the upper surface of the calibration object in the camera's field of view during the first calibration and the two endpoints of the plane containing the upper surface of the calibration object in the camera's field of view during the second calibration as the other two vertices, construct similar triangles;
[0065] Step S14: Calculate the focal height based on the geometric relationship of similar triangles.
[0066] Specifically, first, a first glass plate of a certain thickness is selected, and the calibration object is placed on the first glass plate. The first height d1 from the upper surface of the calibration object to the lower surface of the first glass plate is measured, and the first pixel length L1 of the calibration object in the camera image at this time is recorded. Then, a second glass plate of a different thickness is selected, wherein the thickness of the second glass plate is greater than d1. The same calibration object is placed on the second glass plate, and the second height d2 from the upper surface of the calibration object to the lower surface of the second glass plate is measured. The second pixel length L2 of the calibration object in the camera image at this time is recorded. Figure 3 As shown, using the lens focal point as a common vertex, and the two endpoints of the plane containing the upper surface of the calibration object in the camera's viewpoint during the first calibration and the two endpoints of the plane containing the upper surface of the calibration object in the camera's viewpoint during the second calibration, respectively, two similar triangles are constructed. Based on the geometric relationships of similar triangles, we know that: Where ρ1 and ρ2 represent the pixel equivalents of the upper surfaces of the first and second glass plates, respectively, and C pixel H represents the total number of pixels along the width direction of the camera sensor, and H represents the focal height. Additionally, the actual physical length of the calibration object is L. mm .therefore:
[0067]
[0068]
[0069]
[0070]
[0071] It is understood that in step S2, when the optical axis of the camera lens and the center of the through-hole are not on a straight line, the through-hole image captured by the camera will be as follows: Figure 4 As shown. In a through-hole image with a bright background and a dark object, the clear outline of the through-hole region (i.e., the dark region) can be accurately extracted through the bottom cap transformation. However, other lines with insufficient contrast are difficult to identify clearly. For example, the contrast between the upper surface outline of the through-hole and the upper surface of the glass plate is low, making it difficult to accurately identify the upper surface outline of the through-hole. Therefore, current machine vision inspection equipment cannot accurately identify the outline of the bottom circle of the through-hole from the through-hole image, thus failing to accurately detect the through-hole diameter, especially when there are chamfers on the upper and lower surfaces of the through-hole, making it even more difficult to identify the bottom circle outline of the through-hole. Furthermore, when the offset distance between the lens optical axis and the center of the through-hole is different, the through-hole projection image will also be different, making it even more difficult to accurately measure the actual diameter of the through-hole. Therefore, in this invention, the outline of the through-hole region is first obtained through the bottom cap transformation. Since the through-hole region is a dark region, its contrast with the surrounding glass plate region (light region) is high, thus allowing for accurate extraction of the outline of the through-hole region. Then, the pixel diameter of the through-hole is calculated based on the through-hole region. For example, Figure 5 As shown, the process of calculating the lower surface pixel diameter of the via based on the via region includes the following:
[0072] Step S21: Obtain the coordinates of the projection point of the lens focus on the through-hole image plane;
[0073] Step S22: Obtain the pixel coordinates of all points on the contour line of the through hole region, and calculate the centroid coordinates of the through hole region by means of the average value;
[0074] Step S23: Draw a line connecting the projection point and the centroid, and rotate the line connecting the projection point and the centroid clockwise and counterclockwise with the projection point as the center, until the line leaves the through hole area, and obtain two tangent points between the line and the through hole area respectively.
[0075] Step S24: Perform circumferential fitting on a segment of arc on the contour line with two tangent points as endpoints and far from the projection point to obtain the pixel diameter of the lower surface of the through hole.
[0076] Specifically, such as Figure 6 As shown, after determining the through-hole region, the closed contour line of the projection area of the upper and lower surfaces of the through-hole onto the plane is the through-hole region contour line. At this time, it is necessary to calculate the intersection point of two arcs with different diameters on the closed contour line. First, obtain the projection point P of the lens focus on the through-hole image plane. Then, obtain the pixel coordinates of all points on the through-hole region contour line, and then calculate the coordinate value of the centroid O of the through-hole region by averaging. Due to the symmetry, the centroid O must be on the line connecting the center B of the upper surface of the through-hole and the center A of the lower surface image, that is, points A, O, and B are collinear. Then connect points P and O, and rotate the PO ray clockwise and counterclockwise with a small step angle Δθ around point P until the PO ray leaves the through-hole region, thereby obtaining the two tangent points M and N between the PO ray and the through-hole region, that is, the actual intersection points of the bottom and top circular contour lines of the through-hole. Finally, based on the MN segment of the arc on the closed contour line that is far from point P, the least squares method is used to fit the circumference, and the pixel circle of the lower surface of the through hole is obtained, thus obtaining the pixel diameter of the lower surface of the through hole.
[0077] It is understood that in step S3, since the through-hole pixel circle obtained by fitting in step S2 is formed by imaging the edge points of the through-hole on the lower surface of the glass plate, the conversion of the lower surface pixel diameter of the through-hole to the actual physical diameter requires conversion using the lower surface pixel equivalent of the glass plate. For example... Figure 7 As shown, the process of obtaining the pixel equivalent of the lower surface of the glass plate based on the focal height calibration includes the following:
[0078] Step S31: Select a third glass plate of a certain thickness, place the calibration object on the third glass plate, measure the third height from the upper surface of the calibration object to the lower surface of the third glass plate, and record the third pixel length and actual physical length of the calibration object in the camera image.
[0079] Step S32: Using the lens focus as one vertex of the triangle, and using the two endpoints of the plane containing the upper surface of the calibration object in the camera's field of view during the third calibration and the two endpoints of the plane containing the lower surface of the third glass plate in the camera's field of view as the other two vertices, construct a similar triangle;
[0080] Step S33: Calculate the pixel equivalent of the lower surface of the glass plate based on the geometric relationship of similar triangles.
[0081] Specifically, first select a third glass plate of a certain thickness, place the calibration object on the third glass plate, measure the third height d from the upper surface of the calibration object to the lower surface of the third glass plate, and record the third pixel length L of the calibration object in the camera image. pixel and actual physical length L mm It is understandable that the calibration data for this calculation could also be based on the calibration data from the first or second glass plate, thus eliminating the need for recalibration. Then, as... Figure 8 As shown, using the lens focal point as the common vertex of the triangle, and the two endpoints of the plane containing the upper surface of the calibration object in the camera's viewpoint during the third calibration, and the two endpoints of the plane containing the lower surface of the third glass plate in the camera's viewpoint, respectively, are used as the other two vertices to construct two similar triangles. Based on the geometric relationships of similar triangles, we can conclude that: Where, ρ d This represents the pixel equivalent of the calibration plane. ρ represents the pixel equivalent of the lower surface of the glass plate, therefore:
[0082]
[0083] It can be understood that in step S4, the lower surface pixel diameter of the through hole is converted into the actual physical diameter based on the lower surface pixel equivalent of the glass plate.
[0084] It is understandable that the following content is included before performing focus height calibration:
[0085] Adjust the camera's imaging plane to be parallel to the lower surface of the glass plate to prevent pixel equivalent imbalance caused by the two planes not being parallel.
[0086] In addition, the following should be included before performing focus height calibration:
[0087] Determine the range of distortion caused by the lens on the camera's imaging plane, and select a distortion-free area for imaging. The range of lens-induced distortion can be determined using graph paper.
[0088] In addition, the following should be included before performing focus height calibration:
[0089] To ensure that the lens optical axis and the sensor center are on a straight line and to avoid image distortion caused by center offset, the aperture can be moved to the center of the image to capture an image and check whether they are concentric circles for correction.
[0090] In addition, such as Figure 9 As shown, another embodiment of the present invention also provides a device for detecting the aperture of a through-hole in a glass plate, preferably employing the method described above. The device includes:
[0091] The first calibration module is used to calibrate the focal height from the camera lens focus to the lower surface of the glass plate;
[0092] The image processing module is used to acquire images of through holes on the glass plate, determine the through hole region in the through hole image, and calculate the lower surface pixel diameter of the through hole based on the through hole region.
[0093] The second calibration module is used to calibrate the pixel equivalent of the lower surface of the glass plate based on the focal height.
[0094] The size conversion module is used to convert the diameter of the lower surface pixels of the through hole into the actual physical diameter based on the lower surface pixel equivalent of the glass plate.
[0095] It is understood that the through-hole diameter detection device for glass plates in this embodiment first calibrates the focal height from the camera lens focus to the lower surface of the glass plate. Then, it uses the camera to capture an image of the through-hole on the glass plate. After determining the through-hole area in the image, the pixel diameter of the lower surface of the through-hole can be calculated. Then, based on the calibrated focal height, the pixel equivalent of the lower surface of the glass plate is obtained. Finally, based on the pixel equivalent of the lower surface of the glass plate, the pixel diameter of the lower surface of the through-hole is converted into the actual physical diameter. During the through-hole diameter detection process, it is not necessary to ensure that the lens optical axis and the center of the through-hole are on the same straight line. It is only necessary to determine the through-hole area in the image, and the pixel diameter of the lower surface of the through-hole can be calculated based on this area. After calculating the pixel equivalent of the lower surface of the glass plate based on the pre-calibrated focal height, the actual physical diameter of the through-hole can be calculated, thus allowing for accurate measurement of the through-hole diameter.
[0096] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A method for detecting the aperture of through holes in a glass plate, characterized in that, Includes the following: The focal height from the camera lens focus to the lower surface of the glass plate is calibrated; Acquire an image of a through hole on a glass plate, determine the through hole region in the through hole image, and calculate the lower surface pixel diameter of the through hole based on the through hole region; The pixel equivalent of the lower surface of the glass plate is obtained based on the focal height calibration; The lower surface pixel diameter of the through hole is converted into the actual physical diameter based on the lower surface pixel equivalent of the glass plate. The process of calculating the lower surface pixel diameter of the via based on the via region includes the following: Obtain the coordinates of the projection point of the lens focus on the through-hole image plane; Obtain the pixel coordinates of all points on the contour line of the through-hole region, and calculate the centroid coordinates of the through-hole region by averaging the values. Draw a line connecting the projection point and the centroid, and rotate the line connecting the projection point and the centroid clockwise and counterclockwise around the projection point until the line leaves the through-hole region, thus obtaining two tangent points between the line and the through-hole region. The lower surface pixel diameter of the through hole is obtained by performing circumferential fitting on a segment of arc on the contour line with two tangent points as endpoints and far from the projection point.
2. The method for detecting the aperture of through holes in a glass plate as described in claim 1, characterized in that, The process of calibrating the focal height from the camera lens focus to the lower surface of the glass plate includes the following: Select a first glass plate of a certain thickness, place the calibration object on the first glass plate, measure the first height from the upper surface of the calibration object to the lower surface of the first glass plate, and record the first pixel length of the calibration object in the camera image; Select a second glass plate of a different thickness, place the same calibration object on the second glass plate, measure the second height from the upper surface of the calibration object to the lower surface of the second glass plate, and record the second pixel length of the calibration object in the camera image at this time; Using the lens focus as one vertex of the triangle, and the two endpoints of the plane containing the upper surface of the calibration object in the camera's field of view during the first calibration and the two endpoints of the plane containing the upper surface of the calibration object in the camera's field of view during the second calibration, construct similar triangles. The focal height is calculated based on the geometric relationship of similar triangles.
3. The method for detecting the pore size of a glass plate as described in claim 2, characterized in that, The focal height is calculated using the following formula: ； Where H represents the focal height, L1 and L2 represent the first pixel length and the second pixel length, respectively, and d1 and d2 represent the first height and the second height, respectively.
4. The method for detecting the through-hole diameter of a glass plate as described in claim 2, characterized in that, The process of obtaining the pixel equivalent of the lower surface of the glass plate based on the focal height calibration includes the following: Select a third glass plate of a certain thickness, place the calibration object on the third glass plate, measure the third height from the upper surface of the calibration object to the lower surface of the third glass plate, and record the third pixel length of the calibration object in the camera image and the actual physical length. Using the lens focus as one vertex of the triangle, and the two endpoints of the plane containing the upper surface of the calibration object in the camera's field of view during the third calibration, and the two endpoints of the plane containing the lower surface of the third glass plate in the camera's field of view, respectively, are used as the other two vertices to construct similar triangles; The pixel equivalent of the lower surface of the glass plate is calculated based on the geometric relationship of similar triangles.
5. The method for detecting the through-hole diameter of a glass plate as described in claim 4, characterized in that, The pixel equivalent of the lower surface of the glass plate is calculated based on the following formula: ； in, H represents the pixel equivalent of the lower surface of the glass plate, d represents the focal height, and L represents the third height. mm and L pixel These represent the actual physical length of the calibrated object and the length of the third pixel, respectively.
6. The method for detecting the aperture of through holes in a glass plate as described in claim 1, characterized in that, The following steps are included before performing focus height calibration: Adjust the camera's imaging plane to be parallel to the lower surface of the glass plate.
7. The method for detecting the aperture of through holes in a glass plate as described in claim 1, characterized in that, The following steps are included before performing focus height calibration: Determine the range of distortion in the camera's imaging plane caused by the lens, and select a distortion-free area for imaging.
8. The method for detecting the aperture of through holes in a glass plate as described in claim 1, characterized in that, The following steps are included before performing focus height calibration: Make sure the lens optical axis and the center of the sensor are on a straight line.
9. A device for detecting the through-hole diameter of a glass plate, employing the method for detecting the through-hole diameter of a glass plate as described in any one of claims 1 to 8, characterized in that, include: The first calibration module is used to calibrate the focal height from the camera lens focus to the lower surface of the glass plate; The image processing module is used to acquire images of through holes on the glass plate, determine the through hole region in the through hole image, and calculate the lower surface pixel diameter of the through hole based on the through hole region. The second calibration module is used to calibrate the pixel equivalent of the lower surface of the glass plate based on the focal height. The size conversion module is used to convert the diameter of the lower surface pixels of the through hole into the actual physical diameter based on the lower surface pixel equivalent of the glass plate.