Product defect detection method and device based on artificial intelligence and electronic equipment

Abstract

The invention provides a product defect detection method based on artificial intelligence. The method comprises the following steps: placing a to-be-detected product below a light source; turning on the light source to enable the light source to emit light; recording an image of the to-be-detected product under the light source, and defining the image as a first image; forming an image of black and white stripes between the light source and the product to be detected; recording an image of the to-be-detected product under the action of the light source and the black and white stripes, and defining the image as a second image; and comparing the first image with the second image, and identifying the defect. According to the invention, dust and white pocks on the product can be effectively distinguished, leak detection and error detection are prevented, and the detection efficiency and accuracy are improved.

Description

[Technical field]

[0001] The present invention relates to the technical field of product defect detection, and in particular to an artificial intelligence-based product defect detection method, device and electronic equipment. [Background technology]

[0002] Consumer electronic products such as mobile phones, computers, and tablets contain a large number of metal electronic components, which play a role in ensuring the performance and durability of the equipment. Due to the manufacturing process and processing environment of metal electronic components, the surface of the above-mentioned metal electronic components often has white pitting defects. At the same time, since the production environment of metal electronic components is not a dust-free workshop, there will be a lot of dust on its surface.

[0003] If there are white pitting on the surface of metal electronic components, it will affect the product performance, so they need to be screened out for repair or replacement, while metal electronic components with only dust on the surface can be processed and used in the next process. Therefore, in the actual processing technology, it is very important to distinguish the white pitting from the dust.

[0004] The prior art usually uses coaxial light for shooting. Although it can form an image in one time to distinguish the white spots from the dust, if the white spots are slight, they will appear as black spots like the dust, making it impossible to distinguish the white spots from the dust, resulting in misjudgment and missed detection. [Summary of the invention]

[0005] In view of the above technical problems in the prior art, the present invention provides a product defect detection method based on artificial intelligence. It includes:

[0006] Placing the product to be inspected under a light source;

[0007] Turning on the light source so that the light source emits light;

[0008] Recording the image of the product to be inspected under the light source, which is defined as the first image;

[0009] forming an image of black and white stripes between the light source and the product to be inspected;

[0010] Recording the imaging of the product to be inspected under the action of the light source and the black and white stripes, which is defined as the second imaging;

[0011] The first image is compared with the second image, and the defect is identified.

[0012] Specifically, a liquid crystal display screen is arranged between the light source and the product to be detected, and the light source received by the product to be detected is the light source processed by the liquid crystal display screen.

[0013] It should be noted that in forming the image of black and white stripes between the light source and the product to be inspected, a liquid crystal display screen is arranged between the light source and the product to be inspected, and the light source is a backlight module, which emits light, and then the light passes through the liquid crystal display screen, and then the image of black and white stripes is presented on the liquid crystal screen, and finally the light is transmitted to the defective object.

[0014] Specifically, the step of recording the imaging of the product to be inspected under the light source, defined as the first imaging, includes:

[0015] Recognize that the product to be inspected has arrived at a designated position, and then illuminate the product to be inspected with the light source;

[0016] Collecting a surface image of the product to be inspected;

[0017] The first image is formed.

[0018] Specifically, the step of recording the imaging of the product to be inspected under the action of the light source and the black and white stripes, which is defined as the second imaging, includes:

[0019] Determine the size of the black and white stripes;

[0020] Draw the image of the black and white stripes, and store the image of the black and white stripes in a specified path;

[0021] Sending a trigger signal to the light source, so that the light source emits light under the action of the trigger signal;

[0022] Retrieving the image of the black and white stripes, so that the light emitted by the light source passes through the image of the black and white stripes and then irradiates the surface of the product to be inspected;

[0023] Collecting a surface image of the product to be inspected;

[0024] The second image is formed.

[0025] It should be noted that when the light source passes through the liquid crystal display screen, the image of the black and white stripes is presented on the liquid crystal display screen.

[0026] Specifically, the step of comparing the first image with the second image to identify the defect includes:

[0027] Collecting position information of defects in the first imaging, and storing the position information of defects in the first imaging in a first text file;

[0028] Collecting position information of defects in the second image, and storing the position information of defects in the second image in a second text file;

[0029] Reading the first text file and the second text file;

[0030] Mapping the position information of the defect in the first imaging in the first text file and the position information of the defect in the second imaging in the second text file onto the same coordinate axis;

[0031] Calculating a ratio of an intersection and a union between the position information of the defect in the first imaging and the position information of the defect in the second imaging, which is defined as an intersection-to-union ratio;

[0032] Setting a threshold value, when the intersection-over-union ratio is greater than or equal to the threshold value, determining that the position information corresponds to dust;

[0033] When the intersection-and-union ratio is less than the threshold, it is determined that the position information corresponds to a white pockmark.

[0034] The present invention also provides a product defect detection device based on artificial intelligence, comprising:

[0035] A workstation module, used for placing the product to be inspected under the light source;

[0036] A light source module, used to turn on the light source so that the light source emits light;

[0037] A black and white stripe module, used for forming a black and white stripe image between the light source and the product to be inspected;

[0038] A camera module, used to record the image of the product to be detected under the light source, which is defined as the first image; and at the same time, used to record the image of the product to be detected under the light source and the black and white stripes, which is defined as the second image;

[0039] A processing module is used to compare the first image and the second image to identify the defect.

[0040] It should be noted that the workstation module can not only be used to place the product to be inspected under the light source; at the same time, a driving device can be designed inside the workstation module to drive the product to be inspected so that the product to be inspected reaches a specified position.

[0041] Specifically, the light source module includes a switch control unit and a light emitting unit, the light emitting unit is used to emit light, and the switch control unit is used to receive a trigger signal to determine whether the light emitting unit is opened or closed.

[0042] Specifically, the camera module includes:

[0043] An identification unit, used for identifying that the product to be detected has arrived at a designated position, and then irradiating the light source onto the product to be detected;

[0044] A collection unit, used for collecting the surface image of the product to be inspected;

[0045] An imaging unit is used to form the first image.

[0046] Specifically, the camera module includes:

[0047] A size recognition unit, used to determine the size of the black and white stripes;

[0048] A black and white stripe drawing unit, used for drawing the image of the black and white stripes and storing the image of the black and white stripes in a specified path;

[0049] A trigger unit, used to send a trigger signal to the light source, and the light source emits light under the action of the trigger signal;

[0050] An identification unit, used to retrieve the image of the black and white stripes, so that the light emitted by the light source passes through the image of the black and white stripes and then irradiates the surface of the product to be detected;

[0051] A collection unit, used for collecting the surface image of the product to be inspected;

[0052] An imaging unit is used to form the second image.

[0053] Specifically, the processing module includes:

[0054] an acquisition unit, configured to acquire position information of defects in the first imaging, and store the position information of defects in the first imaging in a first text file; acquire position information of defects in the second imaging, and store the position information of defects in the second imaging in a second text file;

[0055] A reading unit, configured to read the first text file and the second text file;

[0056] A mapping unit, configured to map the position information of the defect in the first imaging in the first text file and the position information of the defect in the second imaging in the second text file onto the same coordinate axis;

[0057] a calculation unit, configured to calculate a ratio of an intersection and a union between the position information of the defect in the first imaging and the position information of the defect in the second imaging, which is defined as an intersection-to-union ratio;

[0058] The comparison unit is used to set a threshold value. When the intersection-and-union ratio is greater than or equal to the threshold value, it is determined that the position information corresponds to dust; when the intersection-and-union ratio is less than the threshold value, it is determined that the position information corresponds to white pockmarks.

[0059] The present invention also provides an electronic device, comprising:

[0060] Memory;

[0061] processor; and

[0062] A computer program stored in the memory and executable on the processor, wherein the scratch detection method is implemented when the processor executes the computer program.

[0063] 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

[0064] 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:

[0065] Figure 1 The present invention provides a flowchart of a product defect detection method based on artificial intelligence;

[0066] Figure 2 Yes Figure 1 The schematic flow chart of step S3 shown;

[0067] Figure 3 Yes Figure 1 The schematic flow chart of step S5 shown;

[0068] Figure 4 Yes Figure 1 The schematic flow chart of step S6 shown;

[0069] Figure 5 It is a structural schematic diagram of a product defect detection device based on artificial intelligence provided by the present invention;

[0070] Figure 6 Yes Figure 5 The structural diagram of the photographing module 04 is shown;

[0071] Figure 7 Yes Figure 5 A schematic structural diagram of the photographing module 04 in another embodiment shown;

[0072] Figure 8 Yes Figure 5 The structural diagram of the processing module 05 is shown in FIG.

[0073] Fig. 9 The present invention provides an electronic device. [Specific implementation method]

[0074] 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.

[0075] 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.

[0076] 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.

[0077] 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.

[0078] 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.

[0079] like Figure 1 As shown, Figure 1 The present invention provides a flow chart of a product defect detection method based on artificial intelligence. It includes:

[0080] S1. Place the product to be tested under a light source;

[0081] S2, turning on the light source so that the light source emits light;

[0082] S3, recording the image of the product to be inspected under the light source, which is defined as the first image;

[0083] S4, forming a black and white striped image between the light source and the product to be inspected;

[0084] S5, recording the imaging of the product to be inspected under the action of the light source and the black and white stripes, which is defined as the second imaging;

[0085] S6. Compare the first image and the second image to identify the defect.

[0086] Specifically, a liquid crystal display screen is arranged between the light source and the product to be detected, and the light source received by the product to be detected is the light source processed by the liquid crystal display screen.

[0087] It should be noted that in forming the image of black and white stripes between the light source and the product to be inspected, a liquid crystal display screen is arranged between the light source and the product to be inspected, and the light source is a backlight module, which emits light, and then the light passes through the liquid crystal display screen, and then the image of black and white stripes is presented on the liquid crystal screen, and finally the light is transmitted to the object to be inspected.

[0088] It should be noted that a white picture can also be set between the light source and the product to be inspected, and the white picture is presented on the LCD screen. The light source is a backlight module, which emits light, and then the light passes through the LCD screen, and then a white image is presented on the LCD screen, and finally the light is transmitted to the defective object.

[0089] It should be further explained that the white image and the black and white striped image can be in electronic format or in paper format.

[0090] It should be noted that, in one embodiment of the present invention, the white image and the black-and-white striped image are stored in a memory, and the two can be stored in the same path or in different paths.

[0091] After the light source is turned on, when it is triggered for the first time, the white image is retrieved and a photo of the object to be detected is taken. When it is triggered for the second time, the black and white striped image is retrieved and a photo of the object to be detected is taken. Figure 2 As shown, Figure 2 Yes Figure 1 The flowchart of step S3 is shown in FIG.

[0092] The step S3 comprises:

[0093] S31, recognizing that the product to be inspected has arrived at a designated position, and then irradiating the light source onto the product to be inspected;

[0094] S32, collecting the surface image of the product to be inspected;

[0095] S33, forming the first image.

[0096] like Figure 3 As shown, Figure 3 Yes Figure 1 The flowchart of step S5 is shown in FIG.

[0097] The step S5 comprises:

[0098] S51, determining the size of the black and white stripes;

[0099] S52, drawing the image of the black and white stripes, and storing the image of the black and white stripes in a specified path;

[0100] S53, sending a trigger signal to the light source, and the light source emits light under the action of the trigger signal;

[0101] S54, retrieving the image of the black and white stripes, so that the light emitted by the light source passes through the image of the black and white stripes and then irradiates the surface of the product to be inspected;

[0102] S55, collecting the surface image of the product to be inspected;

[0103] S56: forming the second image.

[0104] It should be noted that when the light source passes through the liquid crystal display screen, the image of the black and white stripes is presented on the liquid crystal display screen.

[0105] like Figure 4 As shown, Figure 4 Yes Figure 1 The flowchart of step S6 is shown in FIG.

[0106] The step S6 comprises:

[0107] S61, collecting position information of defects in the first imaging, and storing the position information of defects in the first imaging in a first text file;

[0108] S62, collecting position information of defects in the second image, and storing the position information of defects in the second image in a second text file;

[0109] S63, reading the first text file and the second text file;

[0110] S64, mapping the position information of the defect in the first imaging in the first text file and the position information of the defect in the second imaging in the second text file onto the same coordinate axis;

[0111] S65, calculating a ratio of an intersection and a union between the position information of the defect in the first imaging and the position information of the defect in the second imaging, which is defined as an intersection-to-union ratio;

[0112] S66, setting a threshold, and when the intersection-over-union ratio is greater than or equal to the threshold, determining that the position information corresponds to dust;

[0113] S67: When the intersection-over-union ratio is less than the threshold, it is determined that the position information corresponds to a white pockmark.

[0114] like Figure 5 As shown, Figure 5 The present invention provides a structural schematic diagram of a product defect detection device 1 based on artificial intelligence. A product defect detection device 1 based on artificial intelligence includes:

[0115] Station module 01, used to place the product to be inspected under the light source;

[0116] The light source module 02 is used to turn on the light source so that the light source emits light;

[0117] Black and white stripe module 03, used to form a black and white stripe image between the light source and the product to be inspected;

[0118] The camera module 04 is used to record the image of the product to be detected under the light source, which is defined as the first image; and at the same time, it is used to record the image of the product to be detected under the light source and the black and white stripes, which is defined as the second image;

[0119] The processing module 05 is used to compare the first image with the second image to identify the defect.

[0120] like Figure 6 As shown, Figure 6 Yes Figure 5The structural diagram of the photographing module 04 shown in FIG. 04 includes:

[0121] The identification unit 041 is used to identify that the product to be detected has arrived at a specified position, and then the light source is irradiated onto the product to be detected;

[0122] The acquisition unit 042 is used to acquire the surface image of the product to be inspected;

[0123] The imaging unit 043 is used to form the first image.

[0124] like Figure 7 As shown, Figure 7 Yes Figure 5 The structural diagram of the photographing module 04 in another embodiment is shown, and the photographing module 04 includes:

[0125] A size recognition unit 41, used to determine the size of the black and white stripes;

[0126] A black and white stripe drawing unit 42 is used to draw the image of the black and white stripes and store the image of the black and white stripes in a specified path;

[0127] A trigger unit 43, used to send a trigger signal to the light source, and the light source emits light under the action of the trigger signal;

[0128] The recognition unit 44 is used to retrieve the image of the black and white stripes, so that the light emitted by the light source passes through the image of the black and white stripes and then irradiates the surface of the product to be detected;

[0129] A collection unit 45, used for collecting the surface image of the product to be inspected;

[0130] The imaging unit 46 is configured to form the second image.

[0131] like Figure 8 As shown, Figure 8 Yes Figure 5 The structural diagram of the processing module 05 shown in FIG. 05 includes:

[0132] The acquisition unit 051 is used to acquire the position information of the defect in the first imaging, and store the position information of the defect in the first imaging into a first text file; acquire the position information of the defect in the second imaging, and store the position information of the defect in the second imaging into a second text file;

[0133] A reading unit 052, configured to read the first text file and the second text file;

[0134] A mapping unit 053, configured to map the position information of the defect in the first imaging in the first text file and the position information of the defect in the second imaging in the second text file onto the same coordinate axis;

[0135] A calculation unit 054, used to calculate the ratio of the intersection and the union between the position information of the defect in the first imaging and the position information of the defect in the second imaging, which is defined as the intersection-to-union ratio;

[0136] The comparison unit 055 is used to set a threshold value. When the intersection-and-union ratio is greater than or equal to the threshold value, it is determined that the position information corresponds to dust; when the intersection-and-union ratio is less than the threshold value, it is determined that the position information corresponds to white spots.

[0137] It should be noted that the present application defines the location of the white spots by comparing and screening images with and without black and white stripes for multiple times.

[0138] Furthermore, the step of reading the first text file and the second text file further includes the following steps:

[0139] Using an algorithm to train a first imaging in the first imaging to generate a first training model of the first imaging, wherein the first training model has location information for identifying defects in the first imaging;

[0140] Using an algorithm to train a second imaging in the second imaging to generate a second training model of the second imaging, wherein the second training model has location information for identifying defects in the second imaging;

[0141] If there is a product to be inspected that contains the position information of the defect in the first imaging and the position information of the defect in the second imaging;

[0142] then using the first training model to detect location information of defects in the first imaging;

[0143] The second training model is used to detect the position information of the defect in the second imaging.

[0144] Furthermore, the step of detecting the position information of the defect in the first imaging by the first training model includes:

[0145] The first training model detects position information of a defect in the first imaging;

[0146] The position information of the defect in the first imaging corresponds to a rectangular frame;

[0147] The rectangular frame records the category information and coordinate information of the position information of the defect in the first imaging;

[0148] The category information may be dust or white spots;

[0149] The coordinate information may be the upper left corner coordinates and the lower right corner coordinates of the rectangular frame.

[0150] Further, a threshold is set, and when the intersection-and-union ratio is greater than or equal to the threshold, it is determined that the position information corresponds to dust; when the intersection-and-union ratio is less than the threshold, the step of determining that the position information corresponds to white pockmarks includes:

[0151] The greater the value of the intersection-over-combination ratio is, the higher the degree of overlap between the position information of the defect in the first imaging and the position information of the defect in the second imaging is.

[0152] When the value of the AND ratio is greater than or equal to 1, it is judged that the value of the AND ratio indicates that the position information of the defect in the first imaging coincides with the position information of the defect in the second imaging, that is, the defect in the first imaging and the defect in the second imaging are the same target, that is, dust.

[0153] At this time, the coordinate information of the dust is deleted, and what remains is the coordinate information of the white pockmarks.

[0154] like Fig. 9 As shown, Fig. 9 The present invention further provides an electronic device 001, comprising: a memory 002; a processor 003; and a computer program stored in the memory and executable on the processor, wherein the scratch detection method is implemented when the processor executes the computer program.

[0155] 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 product defect detection method based on artificial intelligence, characterized in that: include: Placing the product to be inspected under a light source; Turning on the light source so that the light source emits light; Recording the image of the product to be inspected under the light source, which is defined as the first image; forming an image of black and white stripes between the light source and the product to be inspected; Recording the imaging of the product to be inspected under the action of the light source and the black and white stripes, which is defined as the second imaging; The first image is compared with the second image, and the defect is identified.

2. The product defect detection method based on artificial intelligence according to claim 1, characterized in that: A liquid crystal display screen is arranged between the light source and the product to be detected, and the light received by the product to be detected is the light emitted by the light source after being processed by the liquid crystal display screen.

3. The product defect detection method based on artificial intelligence according to claim 1, characterized in that: The step of recording the imaging of the product to be inspected under the light source, defined as the first imaging, comprises: Recognize that the product to be inspected has arrived at a designated position, and then illuminate the product to be inspected with the light source; Collecting a surface image of the product to be inspected; The first image is formed.

4. The product defect detection method based on artificial intelligence according to claim 1, characterized in that: The step of recording the imaging of the product to be inspected under the action of the light source and the black and white stripes, which is defined as the second imaging, comprises: Determine the size of the black and white stripes; Draw the image of the black and white stripes, and store the image of the black and white stripes in a specified path; Sending a trigger signal to the light source, so that the light source emits light under the action of the trigger signal; Retrieving the image of the black and white stripes, so that the light emitted by the light source passes through the image of the black and white stripes and then irradiates the surface of the product to be inspected; Collecting a surface image of the product to be inspected; The second image is formed.

5. The product defect detection method based on artificial intelligence according to claim 1, characterized in that: The step of comparing the first image with the second image to identify the defect comprises: Collecting position information of defects in the first imaging, and storing the position information of defects in the first imaging in a first text file; Collecting position information of defects in the second image, and storing the position information of defects in the second image in a second text file; Reading the first text file and the second text file; Mapping the position information of the defect in the first imaging in the first text file and the position information of the defect in the second imaging in the second text file onto the same coordinate axis; Calculating a ratio of an intersection and a union between the position information of the defect in the first imaging and the position information of the defect in the second imaging, which is defined as an intersection-to-union ratio; Setting a threshold value, when the intersection-over-union ratio is greater than or equal to the threshold value, determining that the position information corresponds to dust; When the intersection-and-union ratio is less than the threshold, it is determined that the position information corresponds to a white pockmark.

6. A product defect detection device based on artificial intelligence, characterized in that: include: A workstation module, used for placing the product to be inspected under the light source; A light source module, used to turn on the light source so that the light source emits light; A black and white stripe module, used for forming a black and white stripe image between the light source and the product to be inspected; A camera module, used to record the image of the product to be detected under the light source, which is defined as the first image; and at the same time, used to record the image of the product to be detected under the light source and the black and white stripes, which is defined as the second image; A processing module is used to compare the first image and the second image to identify the defect.

7. The product defect detection device based on artificial intelligence as claimed in claim 6, characterized in that: The camera module includes: An identification unit, used for identifying that the product to be detected has arrived at a designated position, and then irradiating the light source onto the product to be detected; A collection unit, used for collecting the surface image of the product to be inspected; An imaging unit is used to form the first image.

8. The product defect detection device based on artificial intelligence as claimed in claim 6, characterized in that: The camera module includes: A size recognition unit, used to determine the size of the black and white stripes; A black and white stripe drawing unit, used for drawing the image of the black and white stripes and storing the image of the black and white stripes in a specified path; A trigger unit, used to send a trigger signal to the light source, and the light source emits light under the action of the trigger signal; An identification unit, used to retrieve the image of the black and white stripes, so that the light emitted by the light source passes through the image of the black and white stripes and then irradiates the surface of the product to be detected; A collection unit, used for collecting the surface image of the product to be inspected; An imaging unit is used to form the second image.

9. The product defect detection device based on artificial intelligence as claimed in claim 6, characterized in that: The processing module comprises: an acquisition unit, configured to acquire position information of defects in the first imaging, and store the position information of defects in the first imaging in a first text file; acquire position information of defects in the second imaging, and store the position information of defects in the second imaging in a second text file; A reading unit, configured to read the first text file and the second text file; A mapping unit, configured to map the position information of the defect in the first imaging in the first text file and the position information of the defect in the second imaging in the second text file onto the same coordinate axis; a calculation unit, configured to calculate a ratio of an intersection and a union between the position information of the defect in the first imaging and the position information of the defect in the second imaging, which is defined as an intersection-to-union ratio; The comparison unit is used to set a threshold value. When the intersection-and-union ratio is greater than or equal to the threshold value, it is determined that the position information corresponds to dust; when the intersection-and-union ratio is less than the threshold value, it is determined that the position information corresponds to white pockmarks.

10. An electronic device, characterized in that: include: 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 5 when executing the computer program.

Images