Scratch detection method and device and electronic equipment

Abstract

The invention provides a scratch detection method. The method comprises the following steps: defining a motion plane of an object to be detected as an XY plane; detecting elements are arranged above the object to be detected at intervals, the plane where the detecting elements are located is parallel to the XY plane, the included angle between the projection of the detecting elements on the XY plane and the X direction is A degrees, and A ranges from 30 degrees to 60 degrees; the detection element moves relative to the object to be detected; and the detection element is used for photographing and detecting the to-be-detected article. According to the scratch detection method provided by the invention, the success rate of scratch detection is greatly improved, and the omission ratio is reduced.

Description

[Technical field]

[0001] The present invention relates to the technical field of scratch detection, and in particular to a scratch detection method, device and electronic equipment. [Background technology]

[0002] Linear scan cameras collect images in a continuous manner and are more suitable for applications on high-speed production lines than area scan cameras. Therefore, line scan cameras are widely used in the inspection of coils, chips, PCB boards, paper, cans and other industries.

[0003] As recorded in the prior art, the disclosure (announcement) number CN103175838A discloses a PS plate surface detection system based on machine vision, which relates to the field of industrial automation technology. The system includes: an image acquisition device, an image processing device, and a system lighting device. The image acquisition device is used to acquire the original image information of the upper surface of the PS plate; the image processing device is used to process the original image information acquired by the image acquisition device to identify the defects on the upper surface of the PS plate; the system lighting device is used to provide imaging lighting for the image acquisition device when acquiring the original image information of the upper surface of the PS plate. The present invention provides a PS plate surface detection system based on machine vision, so that in the PS detection process, it is not necessary to adopt a manual detection method, but an automatic detection by a machine, thereby reducing the missed detection rate and cost in the PS plate detection process, and improving the accuracy and production efficiency.

[0004] The publication (announcement) number is CN105866129A, which discloses an online detection method for product surface quality based on digital projection, avoiding the disadvantages of some existing detection methods, such as uncertain lighting environment, vibration during product transmission, and mutual influence of multiple defects. The implementation process is: (1) an area array camera frame is installed directly above the product production line, and then an area array camera is installed in the center of the camera frame to collect product images on the production line; (2) a digital projector is installed on one side of the area array camera at a certain height on the product production line as a white light and stripe structured light projection system; (3) timed projection and timed image acquisition are realized by programming on a computer (or industrial computer), and the collected images are processed by a digital image processing algorithm, and finally the detection of various two-dimensional and three-dimensional defects is realized; the present invention adopts a method combining digital projection and machine vision to have the ability of real-time rapid measurement and precise monitoring in the process of online detection of product surface quality.

[0005] However, the above-mentioned prior arts have not solved the following technical problem: microelectronic products such as chips or PCB boards may have scratches in various directions during the production process. If a linear array camera is used to detect scratches on the products, if the scratches on the products are parallel to the row pixels of the linear array camera, the scratches will be clearly imaged, while the scratches perpendicular to the row pixels will basically not be imaged, resulting in missed detection. [Summary of the invention]

[0006] In view of the above technical problems in the prior art, the present invention provides a scratch detection method. It includes:

[0007] Define the moving plane of the object to be detected as the XY plane;

[0008] Wherein, X represents the moving direction of the object to be detected, which is defined as the X direction, and Y represents the direction perpendicular to the X direction, which is defined as the Y direction. The XY plane is the plane where the X direction and the Y direction are located;

[0009] A detection element is arranged above the object to be detected, the surface where the detection element is located is parallel to the XY plane, the angle between the projection of the detection element on the XY plane and the X direction is A degrees, and the range of A is 30 to 60 degrees;

[0010] The detection element and the object to be detected move relative to each other;

[0011] The detection element takes a photo of the object to be detected and performs detection;

[0012] It should be noted that the plane where the detection element is located is parallel to the XY plane, and the specific meaning that the angle between the projection of the detection element on the XY plane and the X direction is A degrees can be further explained as follows:

[0013] Since the detection element includes a camera, the camera is a linear array camera, the linear array camera includes a camera chip, the camera chip is in a thin rectangular shape, and the surface with the largest surface area in the camera chip has a long side and a short side.

[0014] Furthermore, the surface where the detection element is located is parallel to the XY plane, that is, the surface with the largest surface area in the camera chip is parallel to the XY plane;

[0015] Furthermore, the angle between the long side of the surface with the largest surface area in the camera chip and the X direction is A degrees.

[0016] Preferably, the value of the A degree is 45.

[0017] Specifically, the step of arranging a detection element above the object to be detected in the air and making the surface where the detection element is located parallel to the XY plane includes:

[0018] The detection element includes a linear array camera;

[0019] Setting a calibration line along a direction A degrees from the X direction;

[0020] The angle of the line scan camera is adjusted so that the long side of the chip in the line scan camera is parallel to the calibration line.

[0021] Specifically, the steps of the detection element taking a picture of the object to be detected and performing detection include:

[0022] The line camera collects an image of the object to be detected to form a distorted image;

[0023] Performing matrix transformation on the distorted image to obtain a normal image;

[0024] Detect scratches on the object to be detected.

[0025] Specifically, the step of performing matrix transformation on the distorted image includes:

[0026]

[0027] xyw represents the coordinates of the normal image, uvh represents the coordinates of the distorted image, a 33 The value is 1, and the remaining values ​​are unknown parameters, which are determined according to the properties of the object to be detected.

[0028] Specifically, the step of the detection element taking a photo of the object to be detected and performing detection also includes:

[0029] Setting a row height in the line array camera, the row height being B rows;

[0030] When it is recognized that the object to be detected has arrived at the specified position, the linear array camera is triggered to start taking pictures;

[0031] The line camera collects an image of the object to be detected to form a distorted image;

[0032] Performing matrix transformation on the distorted image to obtain a normal image;

[0033] Detecting scratches on the object to be detected in the normal image;

[0034] The step of performing matrix transformation on the distorted image comprises:

[0035]

[0036] xyw represents the coordinates of the normal image, uvh represents the coordinates of the distorted image, a 33 The value is 1, and the remaining values ​​are unknown parameters, which are determined according to the properties of the object to be detected.

[0037] The present invention also provides a scratch detection device, comprising:

[0038] Station module; used to define the moving plane of the object to be inspected as the XY plane;

[0039] Wherein, X represents the moving direction of the object to be detected, which is defined as the X direction, and Y represents the direction perpendicular to the X direction, which is defined as the Y direction. The XY plane is the plane where the X direction and the Y direction are located;

[0040] A detection module, used for arranging a detection element above the object to be detected, wherein the surface where the detection element is located is parallel to the XY plane, and the angle between the projection of the detection element on the XY plane and the X direction is A degrees, and the range of A is 30 to 60 degrees;

[0041] A driving module, used to make the detection element and the object to be detected move relative to each other;

[0042] The processing module is used to use the detection element to take a picture of the object to be detected and perform detection.

[0043] Specifically, the detection module includes:

[0044] A calibration unit, used to set a calibration line along a direction that is A degrees to the X direction;

[0045] The adjusting unit is used to adjust the angle of the line array camera so that the long side of the chip in the line array camera is parallel to the calibration line.

[0046] Specifically, the processing module includes:

[0047] A collection unit, used for collecting images of the object to be detected by the line camera to form a distorted image;

[0048] A transformation unit, used for performing matrix transformation on the distorted image to obtain a normal image;

[0049] A scratch detection unit, used to detect scratches on the object to be detected;

[0050] The working principle of the transformation unit is as follows:

[0051]

[0052] xyw represents the coordinates of the normal image, uvh represents the coordinates of the distorted image, a 33 The value is 1, and the remaining values ​​are unknown parameters, which are determined according to the properties of the object to be detected.

[0053] The present invention also provides an electronic device, comprising:

[0054] Memory;

[0055] processor; and

[0056] A computer program stored in the memory and executable on the processor, wherein the processor implements the scratch detection method according to any one of claims 1 to 6 when executing the computer program.

[0057] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Brief Description of the Drawings

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work, among which:

[0059] Figure 1 It is a schematic flow chart of a scratch detection method disclosed by the present invention;

[0060] Figure 2 yes Figure 1 Schematic diagram of the process of step S2;

[0061] Figure 3 yes Figure 2 Schematic diagram of the process of step S23;

[0062] Figure 4 yes Figure 1 Schematic diagram of the process of step S4;

[0063] Figure 5 In another embodiment of the present invention Figure 1 Schematic diagram of the process of step S4;

[0064] Figure 6 The present invention provides a schematic diagram of the structure of a scratch detection device;

[0065] Figure 7 yes Figure 6 A schematic diagram of the structure of the detection module 02;

[0066] Figure 8 yes Figure 6 A schematic diagram of the structure of the processing module 04;

[0067] Fig. 9 yes Figure 6 A schematic diagram of the structure of the processing module 04;

[0068] Fig.10 The present invention provides an electronic device. [Specific implementation method]

[0069] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0070] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0071] In addition, in the present invention, descriptions such as "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0072] In the present invention, unless otherwise clearly specified and limited, the terms "connection", "fixation", etc. should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0073] In addition, the technical solutions between the various embodiments of the present invention can be combined with each other, but it must be based on the fact that ordinary technicians in the field can implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0074] like Figure 1 As shown, Figure 1 The present invention provides a scratch detection method. The method comprises:

[0075] S1. Define the moving plane of the object to be detected as the XY plane;

[0076] Wherein, X represents the moving direction of the object to be detected, which is defined as the X direction, and Y represents the direction perpendicular to the X direction, which is defined as the Y direction. The XY plane is the plane where the X direction and the Y direction are located;

[0077] S2. A detection element is arranged above the object to be detected, wherein the surface where the detection element is located is parallel to the XY plane, and the angle between the projection of the detection element on the XY plane and the X direction is A degrees, and the range of A is 30 to 60 degrees;

[0078] S3, the detection element and the object to be detected move relative to each other;

[0079] S4, the detection element takes a photo of the object to be detected and performs detection;

[0080] It should be noted that the plane where the detection element is located is parallel to the XY plane, and the specific meaning that the angle between the projection of the detection element on the XY plane and the X direction is A degrees can be further explained as follows:

[0081] Since the detection element includes a camera, the camera is a linear array camera, the linear array camera includes a camera chip, the camera chip is in a thin rectangular shape, and the surface with the largest surface area in the camera chip has a long side and a short side.

[0082] Furthermore, the surface where the detection element is located is parallel to the XY plane, that is, the surface with the largest surface area in the camera chip is parallel to the XY plane;

[0083] Furthermore, the angle between the long side of the surface with the largest surface area in the camera chip and the X direction is A degrees.

[0084] It should be noted that, through observation of actual production, it is known that microelectronic products such as chips or PCB boards may have scratches in various directions during the production process. Due to the friction and collision probability on the transmission belt, it is known that most of the scratches on the surface appear in a direction roughly parallel to the X direction or roughly parallel to the Y direction. Therefore, during the detection process, it is found through statistics that as long as the angle between the projection of the detection element on the XY plane and the X direction is A degrees, and the range of A is 30 to 60, the scratches of the object to be detected can be detected.

[0085] It should be noted that the relative motion between the detection element and the object to be detected may include the following possible working states:

[0086] The technical solution of the present application also includes a light source, which is fixedly connected to the detection element, and the light source and the detection element together move relative to the object to be detected; or, the light source is fixedly connected to the object to be detected, and the light source and the detection element together move relative to the object to be detected.

[0087] Furthermore, the range of A can be set to any one of 30, 40, 45, 50, and 60 degrees.

[0088] Furthermore, the value of A is preferably 45. When it is selected as 45, the angle between it and the X direction or the Y direction is the largest, that is, the possibility of detecting scratches is the greatest and the detection result is clearest.

[0089] See also Figure 2 , Figure 2 yes Figure 1 Schematic diagram of the process of step S2 in FIG. S2 includes:

[0090] S21, the detection element includes a linear array camera;

[0091] S22, setting a calibration line along a direction that is A degrees to the X direction;

[0092] S23, adjusting the angle of the line scan camera so that the long side of the chip in the line scan camera is parallel to the calibration line.

[0093] It should be noted that the process of setting the calibration line along the direction at an angle A to the X direction may be to set a steel wire or a copper wire along the direction at an angle A to the X direction.

[0094] See also Figure 3 , Figure 3 yes Figure 2 Schematic diagram of the process of step S23.

[0095] The step S23 comprises:

[0096] S231, arranging the steel wire in the direction that is A degrees to the X direction;

[0097] S232, fixing the two ends of the steel wire;

[0098] S233, turning on the light source below the steel wire, and adjusting the angle of the light source so that the steel wire is located at the exact center of the light spot generated by the light source;

[0099] S234, fixing the angle of the light source and turning off the light source;

[0100] S235, adjusting the angle of the line array camera so that the long side of the chip in the line array camera is substantially parallel to the calibration line;

[0101] S236, turning on the light source again, and observing the image of the line array camera;

[0102] S237, fine-tuning the angle of the linear array camera;

[0103] S238. When the image captured by the line array camera is uniformly black, stop fine-tuning the angle of the line array camera.

[0104] It should be noted that the above steps are a process of adjusting the angle of the line array camera, and the purpose is to adjust the angle between the long side of the camera chip of the line array camera and the X direction to 45 degrees.

[0105] See also Figure 4 , Figure 4 yes Figure 1 Schematic diagram of the process of step S4, wherein step S4 comprises:

[0106] S41, the line camera collects an image of the object to be detected to form a distorted image;

[0107] S42, performing matrix transformation on the distorted image to obtain a normal image;

[0108] S43: Detect scratches on the object to be detected in the normal image.

[0109] Specifically, the step of performing matrix transformation on the distorted image includes:

[0110]

[0111] xyw represents the coordinates of the normal image, uvh represents the coordinates of the distorted image, a 33 The value is 1, and the remaining values ​​are unknown parameters, which are determined according to the properties of the object to be detected.

[0112] In another embodiment of the present invention, the step S4 further includes:

[0113] S0041, turning on the light source again, the light source provides a suitable light-sensitive environment for taking pictures of the object to be detected;

[0114] S0042, the line camera collects an image of the object to be detected under the light-sensitive environment provided by the light source to form a distorted image;

[0115] S0043, performing matrix transformation on the distorted image to obtain a normal image;

[0116] S0044. Detect scratches on the object to be detected in the normal image.

[0117] Specifically, the step of performing matrix transformation on the distorted image includes:

[0118]

[0119] xyw represents the coordinates of the normal image, uvh represents the coordinates of the distorted image, a 33 The value is 1, and the remaining values ​​are unknown parameters, which are determined according to the properties of the object to be detected.

[0120] See also Figure 5 In another embodiment of the present invention, the Figure 5 yes Figure 1 Schematic diagram of the process of step S4, wherein step S4 comprises:

[0121] The step S4 further comprises:

[0122] S041, setting a row height in the line array camera, the row height being row B;

[0123] S042, when it is recognized that the object to be detected has arrived at the designated position, triggering the linear array camera to start taking pictures;

[0124] S043, the line camera collects an image of the object to be detected to form a distorted image;

[0125] S044, performing matrix transformation on the distorted image to obtain the normal image;

[0126] S045, detecting scratches of the object to be detected in the normal image;

[0127] It should be noted that the row height refers to the number of scanning rows of the line array camera, and the value of B is determined according to the width of the object to be detected.

[0128] The step of performing matrix transformation on the distorted image comprises:

[0129]

[0130] xyw represents the coordinates of the normal image, uvh represents the coordinates of the distorted image, a 33 The value is 1, and the remaining values ​​are unknown parameters, which are determined according to the properties of the object to be detected.

[0131] In another embodiment of the present invention, the step S4 further includes:

[0132] S00041. Turn on the light source again, so that the light source provides a suitable light-sensitive environment for taking photos of the object to be detected;

[0133] S00042. Set a row height in the line array camera, the row height being row B;

[0134] S00043. When it is recognized that the object to be detected has arrived at the designated position, the linear array camera is triggered to start taking pictures;

[0135] S00044, the line camera starts to collect images of the object to be detected under a suitable light-sensitive environment provided by the light source to form a distorted image;

[0136] S00045. Performing matrix transformation on the distorted image to obtain the normal image;

[0137] S00046. Detecting scratches on the object to be detected in the normal image;

[0138] It should be noted that the row height refers to the number of scanning rows of the line array camera, and the value of B is determined according to the width of the object to be detected.

[0139] Specifically, the step of performing matrix transformation on the distorted image includes:

[0140]

[0141] xyw represents the coordinates of the normal image, uvh represents the coordinates of the distorted image, a 33 The value is 1, and the remaining values ​​are unknown parameters, which are determined according to the properties of the object to be detected.

[0142] See also Figure 6 , Figure 6 The present invention provides a scratch detection device, which comprises:

[0143] Station module 01; used to define the moving plane of the object to be inspected as the XY plane;

[0144] Wherein, X represents the moving direction of the object to be detected, which is defined as the X direction, and Y represents the direction perpendicular to the X direction, which is defined as the Y direction. The XY plane is the plane where the X direction and the Y direction are located;

[0145] Detection module 02, used for arranging a detection element above the object to be detected, the surface where the detection element is located is parallel to the XY plane, the angle between the projection of the detection element on the XY plane and the X direction is A degrees, and the range of A is 30 to 60 degrees;

[0146] A driving module 03, used to make the detection element and the object to be detected move relative to each other;

[0147] The processing module 04 is used to use the detection element to take a picture of the object to be detected and perform detection.

[0148] See also Figure 7 , Figure 7 yes Figure 6 The structural diagram of the detection module 02 described in the figure comprises:

[0149] A calibration unit 021, used to set a calibration line along a direction that is A degrees to the X direction;

[0150] The adjusting unit 022 is used to adjust the angle of the line scan camera so that the long side of the chip in the line scan camera is parallel to the calibration line.

[0151] See also Figure 8 , Figure 8 yes Figure 6 The structural diagram of the processing module 04 is shown in FIG. 1 . Specifically, the processing module 04 includes:

[0152] A collection unit 041, used for collecting the image of the object to be detected by the line camera to form a distorted image;

[0153] A transformation unit 042, configured to perform a matrix transformation on the distorted image to obtain a normal image;

[0154] The scratch detection unit 043 is used to detect scratches on the object to be detected;

[0155] The working principle of the transformation unit 042 is as follows:

[0156]

[0157] xyw represents the coordinates of the normal image, uvh represents the coordinates of the distorted image, a33 The value is 1, and the remaining values ​​are unknown parameters, which are determined according to the properties of the object to be detected.

[0158] Fig. 9 In another embodiment of the present invention, the Fig. 9 yes Figure 6 Schematic diagram of the structure of the processing module 04; in another embodiment provided by the present invention, the processing module 04 includes:

[0159] The row height unit 0041 is used to set the row height, and the row height is set to a fixed value B rows;

[0160] Identification unit 0042, used to identify when the product arrives at a designated location, and then start taking photos;

[0161] A collection unit 0043, used for the line camera to collect the image of the object to be detected to form a distorted image;

[0162] The transformation unit 0044 is used to perform matrix transformation on the distorted image to obtain a normal image;

[0163] The scratch detection unit 0045 is used to detect scratches on the object to be detected;

[0164] The step of performing matrix transformation on the distorted image comprises:

[0165]

[0166] xyw represents the coordinates of the normal image, uvh represents the coordinates of the distorted image, a 33 The value is 1, and the remaining values ​​are unknown parameters, which are determined according to the properties of the object to be detected.

[0167] See also Fig.10 , Fig.10 The present invention provides an electronic device 001. It includes: a memory 002; a processor 003; and a computer program stored in the memory and executable on the processor, wherein the processor implements the scratch detection method according to any one of claims 1 to 6 when executing the computer program. The device and the electronic device in the present invention adopt the above method, so the corresponding technical effects are not described in detail here.

[0168] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A scratch detection method, characterized in that: include: Define the moving plane of the object to be detected as the XY plane; Wherein, X represents the moving direction of the object to be detected, which is defined as the X direction, and Y represents the direction perpendicular to the X direction, which is defined as the Y direction. The XY plane is the plane where the X direction and the Y direction are located; A detection element is arranged above the object to be detected, the surface where the detection element is located is parallel to the XY plane, the angle between the projection of the detection element on the XY plane and the X direction is A degrees, and the range of A is 30 to 60 degrees; The detection element and the object to be detected move relative to each other; The detection element takes a picture of the object to be detected and performs detection.

2. The scratch detection method according to claim 1, characterized in that: The value of the A degree is 45.

3. The scratch detection method according to claim 1, characterized in that: The step of arranging a detection element above the object to be detected, wherein the surface where the detection element is located is parallel to the XY plane, comprises: The detection element includes a linear array camera; Setting a calibration line along a direction A degrees from the X direction; The angle of the line scan camera is adjusted so that the long side of the chip in the line scan camera is parallel to the calibration line.

4. The scratch detection method according to claim 3, characterized in that: The steps of the detection element taking a picture of the object to be detected and detecting the object include: The line camera collects an image of the object to be detected to form a distorted image; Performing matrix transformation on the distorted image to obtain a normal image; Detect scratches on the object to be detected.

5. The scratch detection method according to claim 4, characterized in that: The step of performing matrix transformation on the distorted image comprises: xyw represents the coordinates of the normal image, uvh represents the coordinates of the distorted image, a 33 The value is 1, and the remaining values ​​are unknown parameters, which are determined according to the properties of the object to be detected.

6. The scratch detection method according to claim 3, characterized in that: The steps of the detection element taking a picture of the object to be detected and detecting the object include: Setting a row height in the line array camera, the row height being B rows; When it is recognized that the object to be detected has arrived at the specified position, the linear array camera is triggered to start taking pictures; The line camera collects an image of the object to be detected to form a distorted image; Performing matrix transformation on the distorted image to obtain a normal image; Detecting scratches on the object to be detected in the normal image; The step of performing matrix transformation on the distorted image comprises: xyw represents the coordinates of the normal image, uvh represents the coordinates of the distorted image, a 33 The value is 1, and the remaining values ​​are unknown parameters, which are determined according to the properties of the object to be detected.

7. A scratch detection device, characterized in that: include: Workstation module; It is used to define the moving plane of the object to be detected as the XY plane; Wherein, X represents the moving direction of the object to be detected, which is defined as the X direction, and Y represents the direction perpendicular to the X direction, which is defined as the Y direction. The XY plane is the plane where the X direction and the Y direction are located; A detection module, used for arranging a detection element above the object to be detected, wherein the surface where the detection element is located is parallel to the XY plane, and the angle between the projection of the detection element on the XY plane and the X direction is A degrees, and the range of A is 30 to 60 degrees; A driving module, used to make the detection element and the object to be detected move relative to each other; The processing module is used to use the detection element to take a picture of the object to be detected and perform detection.

8. The scratch detection device according to claim 7, characterized in that: The detection module comprises: A calibration unit, used to set a calibration line along a direction that is A degrees to the X direction; The adjusting unit is used to adjust the angle of the line array camera so that the long side of the chip in the line array camera is parallel to the calibration line.

9. The scratch detection device according to claim 8, characterized in that: The processing module comprises: A collection unit, used for collecting images of the object to be detected by the line camera to form a distorted image; A transformation unit, used for performing matrix transformation on the distorted image to obtain a normal image; A scratch detection unit, used to detect scratches on the object to be detected; The working principle of the transformation unit is as follows: xyw represents the coordinates of the normal image, uvh represents the coordinates of the distorted image, a 33 The value is 1, and the remaining values ​​are unknown parameters, which are determined according to the properties of the object to be detected.

10. An electronic device, comprising: Memory; processor; and A computer program stored in the memory and executable on the processor, wherein the processor implements the scratch detection method according to any one of claims 1 to 6 when executing the computer program.

Images