Fastener size measurement method and system based on structured contour line

Abstract

The invention belongs to the technical field of testing and measuring, and particularly relates to a fastener size measuring method and system based on a structured contour line. The method comprises the following steps: placing a calibration block on a detection platform for image acquisition, and taking an upper edge line of the calibration block as a reference line; the calibration block is taken down, and the fastener is placed on a detection platform for image acquisition; extracting a plurality of feature points from the outer contour of the fastener image, calculating a symmetric line for representing the symmetry axis of the fastener, and correcting the outer contour line of the image based on the symmetric line; according to the corrected outer contour line, a cylindrical surface outer contour straight line and a conical surface outer contour straight line of the fastener are determined, and two intersection points of the cylindrical surface outer contour straight line and the conical surface outer contour straight line on the left side and the right side of the fastener are calculated respectively; determining the distance from the midpoint of the connecting line of the two intersection points to the datum line; and determining the processing precision of the fastener according to the distance and a preset distance threshold value. According to the invention, the measurement precision of the dimension of the fastener is improved.

Description

Technical Field

[0001] This application belongs to the field of test and measurement technology, specifically relating to a fastener dimension measurement method and system based on structured contour lines. Background Technology

[0002] With the rapid development of the aviation manufacturing industry, the level of automation in aircraft manufacturing continues to rise, and the requirements for the quality of aircraft parts are becoming increasingly stringent. In the field of aircraft manufacturing, whether it is the connection between the wings and the fuselage, the assembly of various engine components, or the fixing of cabin equipment, a large number of fasteners such as screws are used. The quality of fasteners is directly related to the flight safety and operational reliability of the aircraft.

[0003] In the context of large-scale production of aircraft parts and high-speed operation of production lines, traditional manual inspection methods for fasteners suffer from problems such as low efficiency, poor accuracy, and easy fatigue, making it difficult to meet the quality control requirements of large-scale, high-speed production lines. Meanwhile, conventional visual inspection methods are often inaccurate in critical dimension measurements under environments with strong light noise and many interferences, making it difficult to meet the requirements of high-precision inspection. Summary of the Invention

[0004] To address the aforementioned problems, the first aspect of this application provides a fastener dimension measurement method based on structured contour lines, mainly comprising:

[0005] Step S1: Place the calibration block on the detection platform to acquire images, adjust the position of the calibration block so that the upper and lower edge lines of the acquired calibration block image are parallel, and use the upper edge line of the calibration block as the baseline.

[0006] Step S2: Remove the calibration block and place the fastener on the testing platform for image acquisition. The fastener is a countersunk screw, which is placed on the original calibration block position on the testing platform with the head facing down and the shank facing up.

[0007] Step S3: Extract several feature points from the outer contour of the fastener image, calculate the symmetry line used to characterize the symmetry axis of the fastener, and correct the outer contour line of the image based on the symmetry line.

[0008] Step S4: Based on the corrected outer contour line, determine the cylindrical outer contour line and the conical outer contour line of the fastener, and calculate the first intersection point of the cylindrical outer contour line and the conical outer contour line on the left side of the fastener, and the second intersection point of the cylindrical outer contour line and the conical outer contour line on the right side of the fastener.

[0009] Step S5: Determine the distance from the midpoint of the line connecting the first intersection point and the second intersection point to the baseline;

[0010] Step S6: Determine the fastener processing accuracy based on the distance and the preset distance threshold.

[0011] Preferably, step S1 further includes:

[0012] The upper and lower edge feature points of the calibration block image are extracted by an edge detection algorithm. The upper and lower edge feature point sets are fitted respectively to generate two imaging lines. The average distance between the two imaging lines is calculated as the calibration height. The parallelism of the two imaging lines is verified. If the deviation exceeds the threshold, the position of the calibration block is readjusted until the parallelism requirement is met.

[0013] Preferably, when fitting the set of edge feature points to generate the imaging line of the upper or lower edge, the method further includes:

[0014] Multiple imaging lines are generated through multiple measurements, and the standard deviation of the slope and the standard deviation of the intercept are determined.

[0015] When the slope standard deviation exceeds the slope standard deviation threshold, or the intercept standard deviation exceeds the intercept standard deviation threshold, readjust the calibration block position or check the imaging system.

[0016] Preferably, when fitting the set of edge feature points to generate the imaging line of the upper or lower edge, the method further includes:

[0017] Different imaging lines are obtained at different time points to establish the correspondence between time points, the slope of the imaging line and the intercept, and to generate a reference table;

[0018] Based on the time the baseline was used, a new slope and intercept were interpolated from the lookup table to generate a baseline adapted to the current time.

[0019] Preferably, in step S2, the acquired fastener image is denoised and binarized using median filtering and the OTSU algorithm.

[0020] Preferably, step S4 further includes:

[0021] Step S41: For the outer contour of the cone, select its two endpoints and midpoint, and fit the straight line of the outer contour of the cone using the least squares method. One endpoint of the outer contour of the cone is selected from the intersection area of ​​the outer contour of the cylinder and the outer contour of the cone.

[0022] Step S42: Calculate the sum of squared residuals of the two outer contour lines of the cone. If the sum of squared residuals exceeds the residual threshold, then select a point in the intersection area as the endpoint of the outer contour of the cone.

[0023] The second aspect of this application provides a fastener dimension measurement system based on structured contour lines, mainly comprising:

[0024] The baseline determination module is used to place the calibration block on the detection platform for image acquisition, adjust the position of the calibration block so that the upper and lower edge lines of the acquired calibration block image are parallel, and use the upper edge line of the calibration block as the baseline.

[0025] The fastener image acquisition module is used to remove the calibration block and place the fastener on the detection platform for image acquisition. The fastener is a countersunk screw, which is placed on the original calibration block position on the detection platform with the head facing down and the shank facing up.

[0026] The outer contour correction module is used to extract several feature points from the outer contour of the fastener image, calculate the symmetry line used to characterize the symmetry axis of the fastener, and correct the outer contour line of the image based on the symmetry line.

[0027] The intersection calculation module is used to determine the cylindrical outer contour line and the conical outer contour line of the fastener based on the corrected outer contour line, and to calculate the first intersection point of the cylindrical outer contour line and the conical outer contour line on the left side of the fastener, and the second intersection point of the cylindrical outer contour line and the conical outer contour line on the right side of the fastener.

[0028] The distance calculation module is used to determine the distance from the midpoint of the line connecting the first intersection point and the second intersection point to the baseline.

[0029] The machining accuracy determination module is used to determine the machining accuracy of the fastener based on the distance and a preset distance threshold.

[0030] Preferably, the baseline determination module includes:

[0031] The calibration block adjustment unit is used to extract the upper and lower edge feature points of the calibration block image through the edge detection algorithm, fit the upper and lower edge feature point sets respectively, generate two imaging lines, calculate the average distance between the two imaging lines as the calibration height, verify the parallelism of the two imaging lines, and readjust the position of the calibration block if the deviation exceeds the threshold until the parallelism requirement is met.

[0032] Preferably, the calibration block adjustment unit includes:

[0033] The linear fitting subunit is used to generate multiple imaging lines through multiple measurements and determine the standard deviation of the slope and the standard deviation of the intercept.

[0034] The threshold determination subunit is used to readjust the position of the calibration block or check the imaging system when the slope standard deviation exceeds the slope standard deviation threshold or the intercept standard deviation exceeds the intercept standard deviation threshold.

[0035] Preferably, the calibration block adjustment unit includes:

[0036] The lookup table generation sub-unit is used to obtain different imaging lines at different time points in order to establish the correspondence between time points, the slope of the imaging line and the intercept, and generate a lookup table.

[0037] The linear parameter adjustment subunit is used to interpolate new slopes and intercepts in the lookup table based on the time the baseline is used, thereby generating a baseline adapted to the current time.

[0038] This application improves the measurement accuracy of fastener dimensions. Attached Figure Description

[0039] Figure 1 This is a flowchart of a preferred embodiment of the fastener dimension measurement method based on structured contour lines in this application.

[0040] Figure 2 This is a schematic diagram showing the fastener structure and measurement dimensions. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in the embodiments of this application will be described in more detail below with reference to the accompanying drawings. In the drawings, the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The described embodiments are only some, not all, of the embodiments of this application. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. The embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0042] This application provides a fastener dimension measurement method based on structured contour lines, such as Figure 1 As shown, it mainly includes:

[0043] Step S1: Place the calibration block on the detection platform to acquire images, adjust the position of the calibration block so that the upper and lower edge lines of the acquired calibration block image are parallel, and use the upper edge line of the calibration block as the baseline.

[0044] Step S2: Remove the calibration block and place the fastener on the testing platform for image acquisition. The fastener is a countersunk screw, which is placed on the original calibration block position on the testing platform with the head facing down and the shank facing up.

[0045] Step S3: Extract several feature points from the outer contour of the fastener image, calculate the symmetry line used to characterize the symmetry axis of the fastener, and correct the outer contour line of the image based on the symmetry line.

[0046] Step S4: Based on the corrected outer contour line, determine the cylindrical outer contour line and the conical outer contour line of the fastener, and calculate the first intersection point of the cylindrical outer contour line and the conical outer contour line on the left side of the fastener, and the second intersection point of the cylindrical outer contour line and the conical outer contour line on the right side of the fastener.

[0047] Step S5: Determine the distance from the midpoint of the line connecting the first intersection point and the second intersection point to the baseline;

[0048] Step S6: Determine the fastener processing accuracy based on the distance and the preset distance threshold.

[0049] like Figure 2 As shown, calibration block 1 is typically a square block placed on the testing platform. Its purpose is to provide a baseline A. The plane of the testing platform is not used as the baseline because, firstly, the plane of the testing platform is difficult to measure, and secondly, the contact surface between the fastener 2 to be tested and the testing platform is uneven, which can easily introduce measurement errors. Calibration block 1 has a specified height H0. Fastener 2 is a countersunk screw, and the height P of its conical part must be strictly controlled. This application determines whether the height P of the conical part meets the processing requirements by measuring the height difference H between the bottom surface P1P2 of the countersunk screw and the baseline A.

[0050] In step S1 of this application, it is first necessary to ensure that the upper and lower edge lines of the calibration block 1 are parallel, that is, that is, that it is facing the camera.

[0051] In some alternative implementations, step S1 further includes:

[0052] The upper and lower edge feature points of the calibration block image are extracted by an edge detection algorithm. The upper and lower edge feature point sets are fitted respectively to generate two imaging lines. The average distance between the two imaging lines is calculated as the calibration height. The parallelism of the two imaging lines is verified. If the deviation exceeds the threshold, the position of the calibration block is readjusted until the parallelism requirement is met.

[0053] In this embodiment, a calibration block is placed on a detection platform, and the imaging line of its upper edge is fitted as a baseline to ensure that the baseline is parallel to the platform, providing a stable reference for subsequent height measurement. A high-precision calibration block (3mm thick) with known precise dimensions is fixed on the detection platform, ensuring that its contact surface with the platform is flat and without tilt. An industrial camera with a calibration is used to acquire images of the calibration block, and the light source angle is adjusted to make the upper edge of the calibration block clear. A telecentric lens is used to reduce perspective distortion and ensure that the imaging line is consistent with the actual physical edge. A high-resolution industrial camera is used to acquire images of the calibration block, and the feature points of the upper and lower edges of the calibration block are extracted by an edge detection algorithm. The edge point set is fitted using the RANSAC algorithm to generate two high-precision imaging lines, and their average distance is calculated as the calibration height. The line parameters are optimized by the least squares method, and the parallelism between the line and the detection platform is verified. If the deviation exceeds the threshold, the position of the calibration block is readjusted until the parallelism requirement is met. The calibration height should be close to the thickness of the calibration block, i.e., close to 3mm. If the calibration block deviates significantly from 3mm, the position of the calibration block needs to be readjusted or the imaging system needs to be checked.

[0054] In some alternative implementations, when fitting the set of edge feature points to generate the imaging line for the upper or lower edge, the method further includes:

[0055] Multiple imaging lines are generated through multiple measurements, and the standard deviation of the slope and the standard deviation of the intercept are determined.

[0056] When the slope standard deviation exceeds the slope standard deviation threshold, or the intercept standard deviation exceeds the intercept standard deviation threshold, readjust the calibration block position or check the imaging system.

[0057] Taking the imaging line at the top edge as an example, which is the baseline, multiple feature points at the top edge are collected each time the baseline is fitted. Then, the least squares method is used to fit the line, and the parameters of the fitted line for the j-th time are determined, which is the slope of the fitted line. and the intercept of the fitted line .

[0058] Next, the stability of the baseline is assessed by calculating the standard deviation:

[0059] ;

[0060] ;

[0061] In the formula, and These represent the standard deviation of the slope and the standard deviation of the intercept, respectively, used to assess the stability of the baseline. and It is the first The slope and intercept of the fitted line. The average slope Here, M represents the average intercept, and M is the number of repeated imaging iterations. and If all values ​​are less than the set threshold, the baseline is considered stable. or If the threshold is exceeded, the calibration block position needs to be readjusted or the imaging system needs to be checked.

[0062] In some alternative implementations, when fitting the set of edge feature points to generate the imaging line for the upper or lower edge, the method further includes:

[0063] Different imaging lines are obtained at different time points to establish the correspondence between time points, the slope of the imaging line and the intercept, and to generate a reference table;

[0064] Based on the time the baseline was used, a new slope and intercept were interpolated from the lookup table to generate a baseline adapted to the current time.

[0065] This embodiment establishes a dynamic calibration model for the baseline. When the parameters of the detection platform or camera change, the calibration block is automatically triggered to re-image and update the baseline. The verified baseline parameters are stored in the system calibration file as an absolute reference for fastener height measurement.

[0066] Step S2 is used for image acquisition of the fasteners. High-resolution industrial cameras are used to acquire fastener images according to the fastener inspection requirements, with a ring light source used to reduce shadows and ensure clear image quality.

[0067] In some optional implementations, in step S2, the acquired fastener image is denoised and binarized using median filtering and the OTSU algorithm. This embodiment can eliminate light noise interference, ensure image clarity, and thus meet the high-precision requirements of fastener inspection, namely, the requirement for high-precision measurement of fastener dimensions. This requirement includes accurately measuring the fastener dimensions to ensure they meet strict design standards and meet the micron-level measurement requirements, with a measurement accuracy of ±0.002mm. Simultaneously, by measuring the fastener dimensions, it is determined whether the fastener is out of tolerance, i.e., whether the actual size is within the allowable deviation range. If the actual height deviation exceeds the deviation threshold, the fastener size is determined to be out of tolerance, triggering an alarm or sorting mechanism to ensure that the fastener quality meets the standards.

[0068] This embodiment uses a high-resolution industrial camera (4000*3036 pixels) with a telecentric lens (0.3x magnification) to acquire fastener images. This ensures the camera has sufficient pixel density and imaging accuracy to clearly capture the subtle features of the fasteners. A ring light source is used to uniformly illuminate the fasteners, effectively reducing shadows on the fastener surface caused by the angle of the light, ensuring uniform lighting on all parts of the fasteners, and avoiding local overexposure or underexposure to ensure consistent overall image brightness. Camera parameters are dynamically adjusted according to the ambient light to obtain high-contrast original fastener images. The acquired fastener images are processed by median filtering to eliminate salt-and-pepper noise and random interference while preserving edge information. The OTSU algorithm is applied to automatically calculate the optimal threshold, and the image is binarized to separate the fastener target from the background. After binarization, morphological operations are used to further remove small noise and fill contour gaps to ensure the integrity of the fastener's outer contour.

[0069] In step S3, a multi-scale gradient fusion-based edge detection algorithm is used, combining the dual-threshold characteristic of the Canny operator and the direction sensitivity of the Sobel operator to perform edge detection on the fastener image, outputting an accurate set of edge points and reducing noise interference in contour extraction. For the discrete edge point set output by edge detection, a high-frequency Fourier fitting technique is used to decompose the contour line into fundamental frequency components and high-frequency components. The fundamental frequency component represents the overall geometry of the contour, while the high-frequency components capture local details. By preserving the fundamental frequency and key high-frequency components and filtering out high-frequency interference corresponding to random noise, a smooth and feature-preserving structured contour line is generated. Geometric constraint optimization is then applied to the fitted structured contour line, utilizing the symmetry of the fastener to constrain the directional consistency of the contour line. The key features of the contour line are fitted using the least squares method to generate a globally consistent symmetrical line.

[0070] Specifically, firstly, several key feature points on the contour line are selected and fitted to obtain the axis of symmetry of the contour line. Then, for the half-contour points of the fastener... Calculate the points symmetric about the axis of symmetry. :

[0071] ;

[0072] ;

[0073] ;

[0074] ;

[0075] In the formula, Through S key feature points Calculate the slope of the axis of symmetry. It is the intercept of the axis of symmetry.

[0076] New key feature points are selected from the adjusted contour points to represent the main geometric features of the contour. The selected new key feature points are then fitted using the least squares method to update the linear equation of the axis of symmetry.

[0077] Next, in step S4, the intersection point of the cylindrical outer contour and the conical outer contour of the fastener is determined, such as... Figure 2 As shown, this means calculating points P1 and P2.

[0078] For the cylindrical outer contour, the RANSAC algorithm is used to fit the straight line of the cylindrical outer contour, eliminating outliers. This algorithm involves multiple random samplings, fitting straight lines, and calculating residuals, ultimately selecting the fitting result with the smallest residual. For the conical outer contour, it is crucial to ensure that the selected contour points are appropriate. Specifically, in some optional implementations, step S4 further includes:

[0079] Step S41: For the outer contour of the cone, select its two endpoints and midpoint, and fit the straight line of the outer contour of the cone using the least squares method. One endpoint of the outer contour of the cone is selected from the intersection area of ​​the outer contour of the cylinder and the outer contour of the cone.

[0080] Step S42: Calculate the sum of squared residuals of the two outer contour lines of the cone. If the sum of squared residuals exceeds the residual threshold, then select a point in the intersection area as the endpoint of the outer contour of the cone.

[0081] In this embodiment, the above steps ensure the adaptability of the conical outer contour to the gradient region. The sum of squared residuals of the two fitted lines is calculated. If the sum of squared residuals exceeds a residual threshold, the contour line segmentation points are adjusted and refitted until convergence. The intersection coordinates P1 and P2 are calculated by simultaneously solving the equations of the cylindrical and conical outer contour lines. In step S5, based on the fastener design specifications and the intersection coordinates P1 and P2, the midpoint of the step surface is located as a representative point of the step surface, which is the transition region between the cylindrical and conical surfaces. The vertical distance from the midpoint of the step surface to the baseline A is calculated. Finally, in step S6, the actual height deviation is calculated based on the fastener design height. This calculated height deviation is then used as the measurement result of the fastener height and compared with a preset deviation threshold. If the actual height deviation exceeds the deviation threshold, the fastener size is determined to be out of tolerance, triggering an alarm or sorting mechanism.

[0082] A second aspect of this application provides a fastener dimension measurement system based on structured contour lines, corresponding to the above-described method, mainly comprising:

[0083] The baseline determination module is used to place the calibration block on the detection platform for image acquisition, adjust the position of the calibration block so that the upper and lower edge lines of the acquired calibration block image are parallel, and use the upper edge line of the calibration block as the baseline.

[0084] The fastener image acquisition module is used to remove the calibration block and place the fastener on the detection platform for image acquisition. The fastener is a countersunk screw, which is placed on the original calibration block position on the detection platform with the head facing down and the shank facing up.

[0085] The outer contour correction module is used to extract several feature points from the outer contour of the fastener image, calculate the symmetry line used to characterize the symmetry axis of the fastener, and correct the outer contour line of the image based on the symmetry line.

[0086] The intersection calculation module is used to determine the cylindrical outer contour line and the conical outer contour line of the fastener based on the corrected outer contour line, and to calculate the first intersection point of the cylindrical outer contour line and the conical outer contour line on the left side of the fastener, and the second intersection point of the cylindrical outer contour line and the conical outer contour line on the right side of the fastener.

[0087] The distance calculation module is used to determine the distance from the midpoint of the line connecting the first intersection point and the second intersection point to the baseline.

[0088] The machining accuracy determination module is used to determine the machining accuracy of the fastener based on the distance and a preset distance threshold.

[0089] In some alternative implementations, the baseline determination module includes:

[0090] The calibration block adjustment unit is used to extract the upper and lower edge feature points of the calibration block image through the edge detection algorithm, fit the upper and lower edge feature point sets respectively, generate two imaging lines, calculate the average distance between the two imaging lines as the calibration height, verify the parallelism of the two imaging lines, and readjust the position of the calibration block if the deviation exceeds the threshold until the parallelism requirement is met.

[0091] In some alternative implementations, the calibration block adjustment unit includes:

[0092] The linear fitting subunit is used to generate multiple imaging lines through multiple measurements and determine the standard deviation of the slope and the standard deviation of the intercept.

[0093] The threshold determination subunit is used to readjust the position of the calibration block or check the imaging system when the slope standard deviation exceeds the slope standard deviation threshold or the intercept standard deviation exceeds the intercept standard deviation threshold.

[0094] In some alternative implementations, the calibration block adjustment unit includes:

[0095] The lookup table generation sub-unit is used to obtain different imaging lines at different time points in order to establish the correspondence between time points, the slope of the imaging line and the intercept, and generate a lookup table.

[0096] The linear parameter adjustment subunit is used to interpolate new slopes and intercepts in the lookup table based on the time the baseline is used, thereby generating a baseline adapted to the current time.

[0097] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for measuring the dimensions of fasteners based on structured contour lines, characterized in that, Includes the following steps: Step S1: Place the calibration block on the detection platform to acquire images, adjust the position of the calibration block so that the upper and lower edge lines of the acquired calibration block image are parallel, and use the upper edge line of the calibration block as the baseline. Step S2: Remove the calibration block and place the fastener on the testing platform for image acquisition. The fastener is a countersunk screw, which is placed on the original calibration block position on the testing platform with the head facing down and the shank facing up. Step S3: Extract several feature points from the outer contour of the fastener image, calculate the symmetry line used to characterize the symmetry axis of the fastener, and correct the outer contour line of the image based on the symmetry line. Step S4: Based on the corrected outer contour line, determine the cylindrical outer contour line and the conical outer contour line of the fastener, and calculate the first intersection point of the cylindrical outer contour line and the conical outer contour line on the left side of the fastener, and the second intersection point of the cylindrical outer contour line and the conical outer contour line on the right side of the fastener. Step S5: Determine the distance from the midpoint of the line connecting the first intersection point and the second intersection point to the baseline; Step S6: Determine the fastener processing accuracy based on the distance and the preset distance threshold.

2. The fastener dimension measurement method based on structured contour lines according to claim 1, characterized in that, Step S1 further includes: The upper and lower edge feature points of the calibration block image are extracted by an edge detection algorithm. The upper and lower edge feature point sets are fitted respectively to generate two imaging lines. The average distance between the two imaging lines is calculated as the calibration height. The parallelism of the two imaging lines is verified. If the deviation exceeds the threshold, the position of the calibration block is readjusted until the parallelism requirement is met.

3. The fastener dimension measurement method based on structured contour lines according to claim 2, characterized in that, When fitting a set of edge feature points to generate an imaging line for the upper or lower edge, the process further includes: Multiple imaging lines are generated through multiple measurements, and the standard deviation of the slope and the standard deviation of the intercept are determined. When the slope standard deviation exceeds the slope standard deviation threshold, or the intercept standard deviation exceeds the intercept standard deviation threshold, readjust the calibration block position or check the imaging system.

4. The fastener dimension measurement method based on structured contour lines according to claim 2, characterized in that, When fitting a set of edge feature points to generate an imaging line for the upper or lower edge, the process further includes: Different imaging lines are obtained at different time points to establish the correspondence between time points, the slope of the imaging line and the intercept, and to generate a reference table; Based on the time the baseline was used, a new slope and intercept were interpolated from the lookup table to generate a baseline adapted to the current time.

5. The fastener dimension measurement method based on structured contour lines according to claim 1, characterized in that, In step S2, the acquired fastener images are denoised and binarized using median filtering and the OTSU algorithm.

6. The fastener dimension measurement method based on structured contour lines according to claim 1, characterized in that, Step S4 further includes: Step S41: For the outer contour of the cone, select its two endpoints and midpoint, and fit the straight line of the outer contour of the cone using the least squares method. One endpoint of the outer contour of the cone is selected from the intersection area of ​​the outer contour of the cylinder and the outer contour of the cone. Step S42: Calculate the sum of squared residuals of the two conical outer contour lines. If the sum of squared residuals exceeds the residual threshold, then select a new point in the intersection area as the endpoint of the conical outer contour.

7. A fastener dimension measurement system based on structured contour lines, characterized in that, include: The baseline determination module is used to place the calibration block on the detection platform for image acquisition, adjust the position of the calibration block so that the upper and lower edge lines of the acquired calibration block image are parallel, and use the upper edge line of the calibration block as the baseline. The fastener image acquisition module is used to remove the calibration block and place the fastener on the detection platform for image acquisition. The fastener is a countersunk screw, which is placed on the original calibration block position on the detection platform with the head facing down and the shank facing up. The outer contour correction module is used to extract several feature points from the outer contour of the fastener image, calculate the symmetry line used to characterize the symmetry axis of the fastener, and correct the outer contour line of the image based on the symmetry line. The intersection calculation module is used to determine the cylindrical outer contour line and the conical outer contour line of the fastener based on the corrected outer contour line, and to calculate the first intersection point of the cylindrical outer contour line and the conical outer contour line on the left side of the fastener, and the second intersection point of the cylindrical outer contour line and the conical outer contour line on the right side of the fastener. The distance calculation module is used to determine the distance from the midpoint of the line connecting the first intersection point and the second intersection point to the baseline. The machining accuracy determination module is used to determine the machining accuracy of the fastener based on the distance and a preset distance threshold.

8. The fastener dimension measurement system based on structured contour lines according to claim 7, characterized in that, The baseline determination module includes: The calibration block adjustment unit is used to extract the upper and lower edge feature points of the calibration block image through the edge detection algorithm, fit the upper and lower edge feature point sets respectively, generate two imaging lines, calculate the average distance between the two imaging lines as the calibration height, verify the parallelism of the two imaging lines, and readjust the position of the calibration block if the deviation exceeds the threshold until the parallelism requirement is met.

9. The fastener dimension measurement system based on structured contour lines according to claim 8, characterized in that, The calibration block adjustment unit includes: The linear fitting subunit is used to generate multiple imaging lines through multiple measurements and determine the standard deviation of the slope and the standard deviation of the intercept. The threshold determination subunit is used to readjust the position of the calibration block or check the imaging system when the slope standard deviation exceeds the slope standard deviation threshold or the intercept standard deviation exceeds the intercept standard deviation threshold.

10. The fastener dimension measurement system based on structured contour lines according to claim 8, characterized in that, The calibration block adjustment unit includes: The lookup table generation sub-unit is used to obtain different imaging lines at different time points in order to establish the correspondence between time points, the slope of the imaging line and the intercept, and generate a lookup table. The linear parameter adjustment subunit is used to interpolate new slopes and intercepts in the lookup table based on the time the baseline is used, thereby generating a baseline adapted to the current time.

Images