Fine metal wire diameter measuring method, system and equipment based on fuzzy detection and medium

Abstract

The invention discloses a fine metal wire diameter measurement method, system and equipment based on fuzzy detection and a medium, belongs to the technical field of metal wire diameter measurement in the cable industry, and aims to solve the technical problem of how to realize automatic measurement of the wire diameter of a fine metal wire, ensure non-contact pixel-level measurement precision, improve production line efficiency and reduce production cost. According to the technical scheme, the method comprises the steps that a thin metal wire image is collected based on backlight projection, an area array light source conducts backlight, the outline of the thin metal wire is projected to a curtain, and an industrial camera is used for collecting and shooting the curtain to obtain the thin metal wire image; removing blurred images based on a Laplacian technology: extracting a Laplacian image from the acquired image, calculating a variance of the Laplacian image, and judging the blurring degree of the image according to the variance; measuring multi-position line diameters based on local binarization; and eliminating line diameter measurement interference based on numerical sorting.

Description

Technical Field

[0001] The invention relates to the technical field of metal wire diameter measurement in the cable industry, and in particular to a method, system, equipment and medium for measuring the diameter of a thin metal wire based on fuzzy detection. Background Art

[0002] In the field of cable manufacturing, especially in the production process of fine metal wires (such as copper wires, aluminum wires, etc.), the measurement of wire diameter is an important quality control link. However, the characteristics of the fine metal wires themselves and the characteristics of their production process make the measurement of wire diameters difficult. During the continuous production of fine metal wires, manual shutdowns for manual caliper measurements will lead to slow production lines and affect production speeds. The reflective properties of fine metal wires also make it difficult to accurately locate the target area by directly using industrial cameras to shoot and measure. The high-speed production line of fine metal wires is also prone to jitter and blur in the captured images, and the dust and water droplets left in the production process of fine metal wires will interfere with the measurement accuracy.

[0003] Traditional manual measurement methods have disadvantages such as being unable to meet the needs of high-speed production, equipment jitter easily interfering with the imaging of thin metal wires, reflections from thin metal wires interfering with imaging, contact measurement easily damaging products, and high-speed image acquisition easily becoming blurred.

[0004] Therefore, how to realize the automatic measurement of the diameter of fine metal wires, ensure non-contact pixel-level measurement accuracy, improve production line efficiency and reduce labor costs is a technical problem that needs to be solved urgently. Summary of the invention

[0005] The technical task of the present invention is to provide a method, system, equipment and medium for measuring the diameter of a thin metal wire based on fuzzy detection to solve the problem of how to realize automatic measurement of the diameter of a thin metal wire, ensure non-contact pixel-level measurement accuracy, improve production line efficiency and reduce labor costs.

[0006] The technical task of the present invention is achieved in the following way: a method for measuring the diameter of a thin metal wire based on fuzzy detection, the method is specifically as follows:

[0007] Capture the image of the fine metal wire based on backlight projection: The array light source is backlit, and the outline of the fine metal wire is projected onto the screen. The screen is captured and photographed using an industrial camera to obtain the image of the fine metal wire. The grayscale value of the projection image of the fine metal wire area on the screen is low, while the area without the thin metal wire is illuminated by the light source, and the image grayscale value is high.

[0008] Eliminate blurry images based on Laplace technology: extract Laplace images from the captured images, calculate the variance of the Laplace images, and determine the blurriness of the images based on the variance;

[0009] Measuring wire diameters at multiple locations based on local binarization;

[0010] Eliminate wire diameter measurement interference based on numerical sorting.

[0011] Preferably, the thin metal wire image is binarized with a fixed threshold to segment the thin metal wire region and obtain a grayscale image I.

[0012] Preferably, the blurred image is removed based on the Laplace technique as follows:

[0013] Apply the Laplacian operator to the grayscale image I to perform convolution operation to obtain the Laplacian image I L , where the Laplace operator is as follows:

[0014]

[0015] For Laplacian image I L Calculate the variance using the following formula:

[0016]

[0017] Where W and H are the width and height of the image respectively; μ is the average grayscale value of the image, and the calculation formula is as follows:

[0018]

[0019] If the variance σ 2 If it is greater than the specified threshold T, it means that the current image is clear;

[0020] If the variance σ 2 If it is not greater than the specified threshold T, it means that the current image is blurred and the corresponding image can be discarded.

[0021] Preferably, the line diameters at multiple locations are measured based on local binarization as follows:

[0022] Use fixed grayscale threshold segmentation to obtain the binary image I B ;

[0023] For the binary image I B Select n ROI areas and calculate the line diameter in each ROI area.

[0024] More preferably, for the binary image I B Select n ROI areas and calculate the line diameter in each ROI area as follows:

[0025] The height and width of each ROI area are the same, and the longitudinal coordinates of the center points of all ROI areas are the same. The horizontal coordinate of the center point of each ROI area is calculated as follows:

[0026]

[0027] Where i is an integer from 1 to n;

[0028] In each ROI area, the vertical height difference D between the upper and lower edges is calculated, and the angle θ between the upper edge and the horizontal plane in the current ROI area is calculated. Then the pixel width of the line diameter in the current ROI area is d = D·cosθ. The pixel width of the line diameter in all ROI areas is calculated to obtain {d 1 ,d 2 ...d n}.

[0029] Preferably, the wire diameter measurement interference is eliminated based on numerical sorting as follows:

[0030] In order to eliminate the interference of water droplets or dust, 1 ,d 2 ...d n}Sort in ascending order, remove the first 1 / 3 and the last 1 / 3, take the average of the remaining data to obtain the pixel width of the thin metal wire diameter in the current image, and multiply the pixel width of the thin metal wire diameter in the current image by the conversion coefficient to obtain the actual width of the thin metal wire diameter.

[0031] A thin metal wire diameter measurement system based on fuzzy detection, the system comprising:

[0032] An image acquisition module is used to acquire the image of the thin metal wire based on backlight projection, specifically: an array light source is used for backlighting, the outline of the thin metal wire is projected onto the screen, and an industrial camera is used to capture and shoot the screen to obtain the image of the thin metal wire;

[0033] The blurred image removal module is used to extract the Laplace image from the acquired image, calculate the variance of the Laplace image, determine the blurriness of the image based on the variance, and remove the blurred image:

[0034] A measurement module for measuring wire diameters at multiple locations based on local binarization;

[0035] Interference elimination module is used to eliminate wire diameter measurement interference based on numerical sorting.

[0036] As a preferred embodiment, the working process of the fuzzy image removal module is as follows:

[0037] (1) Apply the Laplacian operator to the grayscale image I to perform convolution operation to obtain the Laplacian image I L , where the Laplace operator is as follows:

[0038]

[0039] (2) For the Laplacian image I L Calculate the variance using the following formula:

[0040]

[0041] Where W and H are the width and height of the image respectively; μ is the average grayscale value of the image, and the calculation formula is as follows:

[0042]

[0043] If the variance σ 2 If it is greater than the specified threshold T, it means that the current image is clear;

[0044] If the variance σ 2 If it is not greater than the specified threshold T, it means that the current image is blurred and the corresponding image can be removed;

[0045] The working process of the measurement module is as follows:

[0046] (1) Apply fixed grayscale threshold segmentation to grayscale image I to obtain binary image I B ;

[0047] (2) Binarized image I B Select n ROI areas and calculate the line diameter in each ROI area respectively; the details are as follows:

[0048] ① The height and width of each ROI area are the same, and the longitudinal coordinates of the center points of all ROI areas are the same. The horizontal coordinate of the center point of each ROI area is calculated as follows:

[0049]

[0050] Where i is an integer from 1 to n;

[0051] ② Calculate the vertical height difference D between the upper and lower edges in each ROI area, and calculate the angle θ between the upper edge of the current ROI area and the horizontal plane. Then the pixel width of the line diameter in the current ROI area is d = D·cosθ. Calculate the pixel width of the line diameter in all ROI areas and get {d 1 ,d 2 ...d n};

[0052] The working process of the interference removal module is as follows: 1 ,d 2 ...d n}Sort in ascending order, remove the first 1 / 3 and the last 1 / 3, take the average of the remaining data to obtain the pixel width of the thin metal wire diameter in the current image, and multiply the pixel width of the thin metal wire diameter in the current image by the conversion coefficient to obtain the actual width of the thin metal wire diameter.

[0053] An electronic device comprising: a memory and at least one processor;

[0054] Wherein, the memory stores a computer program;

[0055] The at least one processor executes the computer program stored in the memory, so that the at least one processor performs the thin metal wire diameter measurement method based on blur detection as described above.

[0056] A computer-readable storage medium stores a computer program, and the computer program can be executed by a processor to implement the above-mentioned method for measuring the diameter of a thin metal wire based on fuzzy detection.

[0057] The thin metal wire diameter measurement method, system, device and medium based on fuzzy detection of the present invention have the following advantages:

[0058] (1) The present invention measures the diameter of the thin metal wire according to the characteristics of the thin metal wire itself and the production process, ensuring non-contact pixel-level measurement accuracy, effectively improving production line efficiency, and significantly reducing labor costs;

[0059] (ii) The present invention uses backlight projection technology to perform contour imaging based on the reflective properties of thin metal wires, replacing manual shutdown measurement, improving production line production efficiency, and enabling 24-hour all-day testing;

[0060] (III) Aiming at the characteristics of high-speed movement of the production line and the jitter of thin metal wires, the present invention adopts fuzzy image rejection technology based on Laplace technology to significantly improve the accuracy of visual measurement of wire diameter;

[0061] (IV) The present invention adopts a numerical sorting method in view of the production characteristics of the production line, which effectively avoids the problem of dust and water droplets remaining interfering with the wire diameter measurement;

[0062] (V) The backlight projection technology proposed by the present invention to avoid interference from reflections from thin metal wires does not require manual measurement without stopping the machine, which greatly reduces labor costs and improves workshop production efficiency and safety levels;

[0063] (VI) The present invention is based on a numerical sorting method, which effectively avoids the problem of dust and water droplets remaining interfering with wire diameter measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The present invention is further described below in conjunction with the accompanying drawings.

[0065] Attached Figure 1 It is a flowchart of a thin metal wire diameter measurement method based on fuzzy detection;

[0066] Attached Figure 2 This is a screenshot of the collected backlit projection image. DETAILED DESCRIPTION

[0067] The following is a detailed description of the thin metal wire diameter measurement method, system, device and medium based on fuzzy detection of the present invention with reference to the accompanying drawings and specific embodiments.

[0068] Embodiment 1:

[0069] As attached Figure 1 As shown, this embodiment provides a method for measuring the diameter of a thin metal wire based on fuzzy detection, and the method is specifically as follows:

[0070] S1. Capturing the image of the thin metal wire based on backlight projection: The array light source is backlit, and the outline of the thin metal wire is projected onto the screen. The screen is captured and photographed using an industrial camera to obtain the image of the thin metal wire;

[0071] S2. Eliminate blurred images based on Laplace technology: extract Laplace images from the collected images, calculate the variance of the Laplace images, and determine the blurriness of the images based on the variance;

[0072] S3, measuring line diameters at multiple locations based on local binarization;

[0073] S4. Eliminate wire diameter measurement interference based on numerical sorting.

[0074] As attached Figure 2 As shown, the projection image grayscale value of the thin metal wire area in step S1 of this embodiment on the screen is relatively low, and the grayscale value is less than 10, while the area without thin metal wire occlusion is illuminated by the light source, and the image grayscale value is relatively high, and the grayscale value is greater than 90. The thin metal wire image is binarized by a fixed threshold to segment the thin metal wire area to obtain a grayscale image I.

[0075] In step S2 of this embodiment, the blur image is removed based on the Laplace technique as follows:

[0076] S201, applying the Laplacian operator to the grayscale image I to perform a convolution operation to obtain a Laplacian image I L , where the Laplace operator is as follows:

[0077]

[0078] S202, Laplace image I L Calculate the variance using the following formula:

[0079]

[0080] Where W and H are the width and height of the image respectively; μ is the average grayscale value of the image, and the calculation formula is as follows:

[0081]

[0082] If the variance σ 2 If it is greater than the specified threshold T, it means that the current image is clear;

[0083] If the variance σ 2 If it is not greater than the specified threshold T, it means that the current image is blurred and the corresponding image can be discarded.

[0084] The measurement of line diameters at multiple locations based on local binarization in step S3 of this embodiment is specifically as follows:

[0085] S301, in the collected thin metal wire projection image, the thin metal wire area is horizontally distributed in the image; the grayscale image I is segmented by referencing a fixed grayscale threshold to obtain a binary image I B ;

[0086] S302, binarization image I B 30 ROI areas were selected and the line diameter in each ROI area was calculated.

[0087] In step S302 of this embodiment, the binary image I B Select 30 ROI areas and calculate the line diameter in each ROI area as follows:

[0088] S30201. The height and width of each ROI region are the same, and the longitudinal coordinates of the center points of all ROI regions are the same. The abscissa of the center point of each ROI region is calculated as follows:

[0089]

[0090] Where i is an integer from 1 to 30;

[0091] S30202. Calculate the vertical height difference D between the upper and lower edges in each ROI region, and calculate the angle θ between the upper edge of the current ROI region and the horizontal plane. Then the pixel width of the line diameter in the current ROI region is d=D·cosθ. Calculate the pixel width of the line diameter in all ROI regions to obtain {d 1 ,d 2 ...d 30}.

[0092] In step S4 of this embodiment, the elimination of interference in line diameter measurement based on numerical sorting is specifically as follows:

[0093] In order to eliminate the interference of water droplets or dust, 1 ,d 2 ...d 30}Sort in ascending order, remove the first 1 / 3 and the last 1 / 3, take the average of the remaining data to obtain the pixel width of the thin metal wire diameter in the current image, and multiply the pixel width of the thin metal wire diameter in the current image by the conversion coefficient to obtain the actual width of the thin metal wire diameter.

[0094] Embodiment 2:

[0095] This embodiment provides a thin metal wire diameter measurement system based on fuzzy detection, the system comprising:

[0096] The image acquisition module is used to acquire the image of the thin metal wire based on backlight projection. Specifically, the planar array light source is used for backlighting, and the outline of the thin metal wire is projected onto the screen. The screen is captured and photographed by an industrial camera to obtain the image of the thin metal wire. The grayscale value of the projection image of the thin metal wire area on the screen is low, and the grayscale value is less than 10. The area without thin metal wire occlusion is illuminated by the light source, and the image grayscale value is high, and the grayscale value is greater than 90. The thin metal wire area can be easily segmented by binary segmentation with a fixed threshold.

[0097] The blurred image removal module is used to extract the Laplace image from the acquired image, calculate the variance of the Laplace image, determine the blurriness of the image based on the variance, and remove the blurred image:

[0098] A measurement module for measuring wire diameters at multiple locations based on local binarization;

[0099] Interference elimination module is used to eliminate wire diameter measurement interference based on numerical sorting.

[0100] The working process of the blurred image removal module in this embodiment is as follows:

[0101] (1) Apply the Laplacian operator to the grayscale image I to perform convolution operation to obtain the Laplacian image I L , where the Laplace operator is as follows:

[0102]

[0103] (2) For the Laplacian image I L Calculate the variance using the following formula:

[0104]

[0105] Where W and H are the width and height of the image respectively; μ is the average grayscale value of the image, and the calculation formula is as follows:

[0106]

[0107] If the variance σ 2 If it is greater than the specified threshold T, it means that the current image is clear;

[0108] If the variance σ 2 If it is not greater than the specified threshold T, it means that the current image is blurred and the corresponding image can be discarded.

[0109] The working process of the measurement module in this embodiment is as follows:

[0110] (1) Apply fixed grayscale threshold segmentation to grayscale image I to obtain binary image I B ;

[0111] (2) Binarized image I B Select 30 ROI areas and calculate the line diameter in each ROI area; the details are as follows:

[0112] ① The height and width of each ROI area are the same, and the longitudinal coordinates of the center points of all ROI areas are the same. The horizontal coordinate of the center point of each ROI area is calculated as follows:

[0113]

[0114] Where i is an integer from 1 to 30;

[0115] ② Calculate the vertical height difference D between the upper and lower edges in each ROI area, and calculate the angle θ between the upper edge of the current ROI area and the horizontal plane. Then the pixel width of the line diameter in the current ROI area is d = D·cosθ. Calculate the pixel width of the line diameter in all ROI areas and get {d 1 ,d 2 ...d 30}.

[0116] The working process of the interference removal module in this embodiment is specifically as follows: 1 ,d 2 ...d 30}Sort in ascending order, remove the first 1 / 3 and the last 1 / 3, take the average of the remaining data to obtain the pixel width of the thin metal wire diameter in the current image, and multiply the pixel width of the thin metal wire diameter in the current image by the conversion coefficient to obtain the actual width of the thin metal wire diameter.

[0117] Embodiment 3:

[0118] This embodiment also provides an electronic device, including: a memory and a processor;

[0119] Wherein, the memory stores computer-executable instructions;

[0120] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the thin metal wire diameter measurement method based on fuzzy detection in any embodiment of the present invention.

[0121] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor may be a microprocessor or any conventional processor, etc.

[0122] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the terminal, etc. In addition, the memory can also include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SMC), a secure digital (SD) card, a flash memory card, at least one disk storage period, a flash memory device, or other volatile solid-state storage devices.

[0123] Embodiment 4:

[0124] This embodiment also provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions are loaded by a processor, so that the processor executes the thin metal wire diameter measurement method based on fuzzy detection in any embodiment of the present invention. Specifically, a system or device equipped with a storage medium can be provided, on which a software program code that implements the functions of any of the above embodiments is stored, and a computer (or CPU or MPU) of the system or device reads and executes the program code stored in the storage medium.

[0125] In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.

[0126] The storage medium embodiments for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RYM, DVD-RW, DVD+RW), a magnetic tape, a non-volatile memory card, and a ROM. Alternatively, the program code can be downloaded from a server computer via a communication network.

[0127] In addition, it should be clear that the functions of any of the above embodiments can be implemented not only by executing the program code read by the computer, but also by enabling an operating system operating on the computer to complete part or all of the actual operations based on instructions from the program code.

[0128] In addition, it can be understood that the program code read from the storage medium is written to a memory provided in an expansion board inserted into the computer or written to a memory provided in an expansion unit connected to the computer, and then based on the instructions of the program code, a CPU installed on the expansion board or the expansion unit is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above-mentioned embodiments.

[0129] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for measuring the diameter of a thin metal wire based on fuzzy detection, characterized in that: The method is as follows: Capture the image of the thin metal wire based on backlight projection: The array light source is backlit, and the outline of the thin metal wire is projected onto the screen. The screen is captured and photographed using an industrial camera to obtain the image of the thin metal wire. Eliminate blurry images based on Laplace technology: extract Laplace images from the captured images, calculate the variance of the Laplace images, and determine the blurriness of the images based on the variance; Measuring wire diameters at multiple locations based on local binarization; Eliminate wire diameter measurement interference based on numerical sorting.

2. The method for measuring the diameter of a thin metal wire based on fuzzy detection according to claim 1, characterized in that: The thin metal wire image is binarized with a fixed threshold to segment the thin metal wire region and obtain a grayscale image I.

3. The method for measuring the diameter of a thin metal wire based on fuzzy detection according to claim 1 or 2, characterized in that: The specific details of removing blurry images based on Laplace technology are as follows: Apply the Laplacian operator to the grayscale image I to perform convolution operation to obtain the Laplacian image I L , where the Laplace operator is as follows: For Laplacian image I L Calculate the variance using the following formula: Where W and H are the width and height of the image respectively; μ is the average grayscale value of the image, and the calculation formula is as follows: If the variance σ 2 If it is greater than the specified threshold T, it means that the current image is clear; If the variance σ 2 If it is not greater than the specified threshold T, it means that the current image is blurred and the corresponding image can be discarded.

4. The method for measuring the diameter of a thin metal wire based on fuzzy detection according to claim 3, characterized in that: The specific measurement of multi-position line diameter based on local binarization is as follows: Use fixed grayscale threshold segmentation to obtain the binary image I B ; For the binary image I B Select n ROI areas and calculate the line diameter in each ROI area.

5. The method for measuring the diameter of a thin metal wire based on fuzzy detection according to claim 4, characterized in that: For the binary image I B Select n ROI areas and calculate the line diameter in each ROI area as follows: The height and width of each ROI area are the same, and the longitudinal coordinates of the center points of all ROI areas are the same. The horizontal coordinate of the center point of each ROI area is calculated as follows: Where i is an integer from 1 to n; In each ROI area, the vertical height difference D between the upper and lower edges is calculated, and the angle θ between the upper edge and the horizontal plane in the current ROI area is calculated. Then the pixel width of the line diameter in the current ROI area is d=D·cosθ. The pixel width of the line diameter in all ROI areas is calculated to obtain {d1, d2...d n }.

6. The method for measuring the diameter of a thin metal wire based on fuzzy detection according to claim 5, characterized in that: Eliminating interference in wire diameter measurement based on numerical sorting is as follows: For {d1,d2...d n }Sort in ascending order, remove the first 1 / 3 and the last 1 / 3, take the average of the remaining data to obtain the pixel width of the thin metal wire diameter in the current image, and multiply the pixel width of the thin metal wire diameter in the current image by the conversion coefficient to obtain the actual width of the thin metal wire diameter.

7. A thin metal wire diameter measurement system based on fuzzy detection, characterized in that: The system includes: An image acquisition module is used to acquire the image of the thin metal wire based on backlight projection, specifically: an array light source is used for backlighting, the outline of the thin metal wire is projected onto the screen, and an industrial camera is used to capture and shoot the screen to obtain the image of the thin metal wire; The blurred image removal module is used to extract the Laplace image from the acquired image, calculate the variance of the Laplace image, determine the blurriness of the image based on the variance, and remove the blurred image: A measurement module for measuring wire diameters at multiple locations based on local binarization; Interference elimination module is used to eliminate wire diameter measurement interference based on numerical sorting.

8. The thin metal wire diameter measurement system based on fuzzy detection according to claim 7, characterized in that: The working process of the fuzzy image removal module is as follows: (1) Apply the Laplacian operator to the grayscale image I to perform convolution operation to obtain the Laplacian image I L , where the Laplace operator is as follows: (2) For the Laplacian image I L Calculate the variance using the following formula: Where W and H are the width and height of the image respectively; μ is the average grayscale value of the image, and the calculation formula is as follows: If the variance σ 2 If it is greater than the specified threshold T, it means that the current image is clear; If the variance σ 2 If it is not greater than the specified threshold T, it means that the current image is blurred and the corresponding image can be removed; The working process of the measurement module is as follows: (1) Apply fixed grayscale threshold segmentation to grayscale image I to obtain binary image I B ; (2) Binarized image I B Select n ROI areas and calculate the line diameter in each ROI area respectively; the details are as follows: ① The height and width of each ROI area are the same, and the longitudinal coordinates of the center points of all ROI areas are the same. The horizontal coordinate of the center point of each ROI area is calculated as follows: Where i is an integer from 1 to n; ② Calculate the vertical height difference D between the upper and lower edges in each ROI area, and calculate the angle θ between the upper edge of the current ROI area and the horizontal plane. Then the pixel width of the line diameter in the current ROI area is d = D·cosθ. Calculate the pixel width of the line diameter in all ROI areas and get {d1, d2...d n }; The working process of the interference removal module is as follows: n }Sort in ascending order, remove the first 1 / 3 and the last 1 / 3, take the average of the remaining data to obtain the pixel width of the thin metal wire diameter in the current image, and multiply the pixel width of the thin metal wire diameter in the current image by the conversion coefficient to obtain the actual width of the thin metal wire diameter.

9. An electronic device, characterized in that: include: memory and at least one processor; Wherein, the memory stores a computer program; The at least one processor executes the computer program stored in the memory, so that the at least one processor performs the thin metal wire diameter measurement method based on blur detection according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which can be executed by a processor to implement the thin metal wire diameter measurement method based on fuzzy detection as described in any one of claims 1 to 6.

Images