A material defect re-inspection method, device and material defect detection system

Abstract

The embodiment of the present invention discloses a material defect re-inspection method, device and material defect detection system, the method comprising: judging whether an NG picture is a picture to be re-inspected; wherein a black filling area exists in the picture to be re-inspected; if the NG picture is a picture to be re-inspected, judging whether the picture to be re-inspected is a false point. The present invention reduces the false point rate of material defect detection, reduces the workload of manual re-inspection, and improves the overall detection efficiency of material defects.

Description

Technical Field

[0001] Embodiments of the present invention relate to the technical field of material defect detection, and in particular, to a material defect re-inspection method, device and material defect detection system. Background Art

[0002] At present, Automatic Vision Inspection (AVI) machines have been widely used in material defect detection. Material defects are detected by AVI machines, and then manual re-inspection is performed based on the defects detected by the AVI machines. The materials here can be display modules, battery modules, and any other products that can be inspected by AVI machines.

[0003] However, the NG images output by the existing AVI machine have a high false point rate, resulting in a large workload for manual re-inspection and reducing the overall efficiency of material defect detection. Specifically, when the AVI machine performs material defect detection, the material is often not accurately placed at the detection position. At this time, the AVI machine will perform a deflection correction on the collected material image, and after the deflection correction, the image edge will be filled with black, that is, filled with black. The image filled with black is directly judged by the AVI machine as an NG image and transferred to the subsequent manual re-inspection procedure. However, the actual situation is that the materials corresponding to such NG images often do not have defects or the defects that exist are acceptable defects that customers can accept, that is, such NG images are false points and should not be transferred to the subsequent manual re-inspection procedure. For example, in one application scenario, when the AVI machine is performing material defect detection, the material needs to be flipped over. However, the material often tilts when it is flipped to the reverse side. At this time, the AVI machine will perform a deflection correction and fill the edge of the image with black after the correction. The image filled with black will be directly judged as an NG image by the AVI machine, and the NG image will be manually re-inspected. However, most of these NG images are actually false points and do not need to be re-inspected. This not only increases the workload of re-inspection, but also reduces the overall efficiency of material defect detection.

[0004] The above problems need to be solved urgently. Summary of the invention

[0005] In order to solve the related technical problems, the present invention provides a material defect re-inspection method, device and material defect detection system to solve the problems mentioned in the above background technology part.

[0006] To achieve the above objectives, the embodiments of the present invention adopt the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a material defect re-inspection method, comprising:

[0008] Determine whether the NG picture is a picture to be rechecked; wherein there is a black filled area in the picture to be rechecked;

[0009] If the NG picture is a picture to be rechecked, it is determined whether the picture to be rechecked is a false point.

[0010] Re-inspect the NG images output by the AVI machine. First, determine whether it is the image to be re-inspected by judging whether there is a black filled area in the NG image, and then determine whether the image to be re-inspected is a false point. This reduces the false point rate of material defect detection, reduces the workload of manual re-inspection, and improves the overall efficiency of material defect detection.

[0011] As an optional implementation manner, the step of determining whether the NG picture is a picture to be rechecked further includes:

[0012] If the NG picture is a picture to be reviewed, a black filled area in the picture to be reviewed is identified.

[0013] After determining that there is a black filled area in the NG picture, the NG picture is determined to be a picture to be re-inspected, and the black filled area in the picture to be re-inspected is identified. The identified black filled area is used to determine whether the picture to be re-inspected is a false point, thereby reducing the false point rate of material defect detection, reducing the workload of manual re-inspection, and improving the overall detection efficiency of material defects.

[0014] As an optional implementation manner, the step of identifying the black filled area in the image to be reviewed further includes:

[0015] Generate a second master image according to the black-filled area in the image to be reviewed and its corresponding master image; wherein the second master image has a black-filled area;

[0016] Perform RGB comparison detection on the second master image and the image to be re-inspected to determine whether the image to be re-inspected has a rejection defect. If no rejection defect exists, the image to be re-inspected is determined to be a false point; wherein the rejection defect refers to a material defect that is unacceptable to the customer.

[0017] By performing RGB comparison detection on the second master image and the image to be re-inspected, the image to be re-inspected that does not have rejection defects is determined to be a false point. This not only reduces the false point rate of material defect detection, reduces the workload of manual re-inspection, and improves the overall efficiency of material defect detection, but also the defect detection method through RGB comparison detection is simple, direct and efficient. Whether it is a false point is determined by judging whether the image to be re-inspected has rejection defects, which is more in line with the actual needs of users and further reduces the false point rate.

[0018] As an optional implementation manner, performing RGB comparison detection on the second master image and the image to be re-inspected includes:

[0019] The pixel range of RGB detection is adjusted, and RGB comparison detection is performed on the second master image and the image to be re-inspected.

[0020] By adjusting the pixel range of RGB detection, RGB comparison detection of the second master image and the image to be re-inspected is achieved, and the detection result is stable and reliable.

[0021] As an optional implementation manner, the step of identifying the black filled area in the image to be reviewed further includes:

[0022] Generate a new NG picture according to the black-filled area in the picture to be reviewed and the target area corresponding to its master image, wherein the area in the new NG picture corresponding to the black-filled area in the picture to be reviewed is replaced by the target area corresponding to the master image;

[0023] The new NG picture is identified through AI detection to determine whether the new NG picture has a rejection defect. If no rejection defect exists, the new NG picture is determined to be a false point; wherein the rejection defect refers to a material defect that is unacceptable to the customer.

[0024] Generate a new NG picture, use AI detection to determine whether the new NG picture has rejection defects, and determine whether the new NG picture is a false point based on the judgment result. The detection is accurate and efficient, which reduces the false point rate of material defect detection, reduces the workload of manual re-inspection, and improves the overall detection efficiency of material defects.

[0025] As an optional implementation, the AI ​​detection is implemented based on a preset false point AI detection model. By establishing a false point AI detection model, false point judgment of NG pictures is realized, ensuring the accuracy and efficiency of false point judgment.

[0026] As an optional implementation manner, the step of identifying the black filled area in the image to be reviewed further includes:

[0027] Generate a new NG picture according to the black-filled area in the picture to be reviewed and the target area corresponding to its master image, wherein the area in the new NG picture corresponding to the black-filled area in the picture to be reviewed is replaced by the target area corresponding to the master image;

[0028] Perform RGB comparison detection on the new NG picture to determine whether the new NG picture has a rejection defect. If no rejection defect exists, determine that the new NG picture is a false point; wherein the rejection defect refers to a material defect that is unacceptable to the customer.

[0029] Generate a new NG picture, and determine whether the new NG picture has rejection defects through RGB comparison detection. Determine whether the new NG picture is a false point based on the judgment result, making false point detection simpler, direct and efficient.

[0030] In a second aspect, an embodiment of the present invention provides a material defect re-inspection device, which adopts the material defect re-inspection method described in any one of the embodiments of the first aspect above, including:

[0031] A re-inspection picture judgment module is used to judge whether the NG picture is a picture to be re-inspected; wherein there is a black filled area in the picture to be re-inspected;

[0032] The false point defect re-inspection module is used to determine whether the picture to be re-inspected is a false point when it is determined that the NG picture is a picture to be re-inspected.

[0033] The technical solution of this embodiment re-inspects the NG images output by the AVI machine through a material defect re-inspection device composed of a re-inspection image judgment module and a false point defect re-inspection module, thereby reducing the false point rate of material defect detection, reducing the workload of manual re-inspection, and improving the overall material defect detection efficiency.

[0034] In the third aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the material defect re-inspection method described in any one of the embodiments of the first aspect. The technical solution of this embodiment re-inspects the NG images output by the AVI machine, reduces the false point rate of material defect detection, reduces the workload of manual re-inspection, and improves the overall detection efficiency of material defects.

[0035] In a fourth aspect, an embodiment of the present invention provides a material defect re-inspection system, which includes the material defect re-inspection device described in the embodiment of the second aspect.

[0036] The material defect re-inspection system proposed in this embodiment re-inspects the NG images output by the AVI machine through the material defect re-inspection device, thereby reducing the false point rate of material defect detection, reducing the workload of manual re-inspection, and improving the overall material defect detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate and understand the technical solutions in the embodiments of the present invention, the following briefly introduces the background technology of the present invention and the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the contents of the embodiments of the present invention and these drawings without paying any creative work.

[0038] Figure 1 A flow chart of a material defect re-inspection method provided in Embodiment 1 of the present invention;

[0039] Figure 2 A schematic diagram of a picture to be reviewed with a black filled area provided in the second embodiment of the present invention;

[0040] Figure 3 A schematic diagram of a master image corresponding to the image to be reviewed provided in the second embodiment of the present invention;

[0041] Figure 4 A schematic diagram of comparing the image to be reviewed and the master image provided in the second embodiment of the present invention;

[0042] Figure 5 A schematic diagram of the structure of a material defect re-inspection device provided in Embodiment 5 of the present invention;

[0043] Figure 6 This is a schematic diagram of the application of the material defect re-inspection system provided in Example 6 of the present invention. DETAILED DESCRIPTION

[0044] In order to make the technical problems solved by the present invention, the technical solutions adopted and the technical effects achieved clearer, the technical solutions of the embodiments of the present invention will be further described in detail below in conjunction with the accompanying drawings. 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0045] Embodiment 1

[0046] Please refer to Figure 1 As stated, Figure 1 This is a flow chart of a material defect re-inspection method provided in Embodiment 1 of the present invention. As shown in the figure, the material defect re-inspection method 100 in this embodiment includes:

[0047] S101. Determine whether the NG picture is a picture to be rechecked; wherein there is a black filled area in the picture to be rechecked;

[0048] S102. If the NG picture is a picture to be rechecked, determine whether the picture to be rechecked is a false point.

[0049] The technical solution of this embodiment adds a material defect re-inspection procedure between the AVI machine and manual re-inspection. By judging whether there is a black filled area in the NG picture, it is judged whether it is a picture to be re-inspected. The NG picture with black filled area output by the AVI machine is re-inspected to judge whether the picture to be re-inspected is a false point, which reduces the false point rate of material defect detection, reduces the workload of manual re-inspection, and improves the overall material defect detection efficiency.

[0050] Embodiment 2

[0051] The material defect re-inspection method in this embodiment includes:

[0052] S201. Determine whether the NG picture is a picture to be rechecked; wherein there is a black filled area in the picture to be rechecked;

[0053] S202. If the NG picture is a picture to be rechecked, determine whether the picture to be rechecked is a false point.

[0054] Exemplarily, the step of determining whether the NG picture is a picture to be reviewed further includes:

[0055] If the NG picture is a picture to be reviewed, a black filled area in the picture to be reviewed is identified.

[0056] In this embodiment, after determining that there is a black filled area in the NG picture, the NG picture is determined to be a picture to be re-inspected, and the black filled area in the picture to be re-inspected is identified. The identified black filled area is used to determine whether the picture to be re-inspected is a false point, thereby reducing the false point rate of material defect detection, reducing the workload of manual re-inspection, and improving the overall detection efficiency of material defects.

[0057] Exemplarily, the step of identifying the black filled area in the image to be reviewed further includes:

[0058] Generate a second master image according to the black-filled area in the image to be reviewed and its corresponding master image; wherein the second master image has a black-filled area;

[0059] Perform RGB comparison detection on the second master image and the image to be re-inspected to determine whether the image to be re-inspected has a rejection defect. If no rejection defect exists, the image to be re-inspected is determined to be a false point; wherein the rejection defect refers to a material defect that is unacceptable to the customer. In order to facilitate an intuitive understanding of the solution of this embodiment, for example, Figure 2 As stated, Figure 2 A schematic diagram of a picture to be reviewed with a black filled area provided in the second embodiment of the present invention is shown in FIG. Figure 3 As stated, Figure 3 A schematic diagram of a master image corresponding to the image to be reviewed provided in the second embodiment of the present invention, such as Figure 4 As shown, Figure 4 A schematic diagram of comparing the image to be reviewed and the master image provided in the second embodiment of the present invention, Figure 2 and Figure 4 The black rectangular area on the right is the black fill area.

[0060] In this embodiment, RGB comparison detection is performed on the second master image and the picture to be re-inspected, and the picture to be re-inspected that does not have rejection defects is determined as a false point. This not only reduces the false point rate of material defect detection, reduces the workload of manual re-inspection, and improves the overall material defect detection efficiency, but also the defect detection method through RGB comparison detection is simple, direct, and efficient. Whether it is a false point is determined by judging whether the picture to be re-inspected has rejection defects, which is more in line with the actual needs of users and further reduces the false point rate.

[0061] Exemplarily, performing RGB comparison detection on the second master image and the image to be re-inspected includes:

[0062] The pixel range of RGB detection is adjusted, and RGB comparison detection is performed on the second master image and the image to be re-inspected.

[0063] In this embodiment, the RGB comparison detection of the second master image and the image to be re-inspected is achieved by adjusting the pixel range of the RGB detection, and the detection result is stable and reliable.

[0064] Embodiment 3

[0065] The material defect re-inspection method in this embodiment includes:

[0066] S301. Determine whether the NG picture is a picture to be rechecked; wherein there is a black filled area in the picture to be rechecked;

[0067] S302. If the NG picture is a picture to be rechecked, determine whether the picture to be rechecked is a false point.

[0068] Exemplarily, the step of determining whether the NG picture is a picture to be reviewed further includes:

[0069] If the NG picture is a picture to be reviewed, a black filled area in the picture to be reviewed is identified.

[0070] In this embodiment, after determining that there is a black filled area in the NG picture, the NG picture is determined to be a picture to be re-inspected, and the black filled area in the picture to be re-inspected is identified. The identified black filled area is used to determine whether the picture to be re-inspected is a false point, thereby reducing the false point rate of material defect detection, reducing the workload of manual re-inspection, and improving the overall detection efficiency of material defects.

[0071] Exemplarily, the step of identifying the black filled area in the image to be reviewed further includes:

[0072] Generate a new NG picture according to the black-filled area in the picture to be reviewed and the target area corresponding to its master image, wherein the area in the new NG picture corresponding to the black-filled area in the picture to be reviewed is replaced by the target area corresponding to the master image;

[0073] Perform RGB comparison detection on the new NG picture to determine whether the new NG picture has a rejection defect. If no rejection defect exists, determine that the new NG picture is a false point; wherein the rejection defect refers to a material defect that is unacceptable to the customer.

[0074] In this embodiment, a new NG picture is generated, and RGB comparison detection is used to determine whether the new NG picture has a rejection defect. Based on the determination result, it is determined whether the new NG picture is a false point, which makes false point detection simpler, more direct, and more efficient, reduces the false point rate of material defect detection, reduces the workload of manual re-inspection, and improves the overall material defect detection efficiency. Moreover, by determining whether the new NG picture has a rejection defect, it is determined whether it is a false point, which better meets the actual needs of users and further reduces the false point rate.

[0075] Embodiment 4

[0076] The material defect re-inspection method in this embodiment includes:

[0077] S401. Determine whether the NG picture is a picture to be rechecked; wherein there is a black filled area in the picture to be rechecked;

[0078] S402. If the NG picture is a picture to be rechecked, determine whether the picture to be rechecked is a false point.

[0079] Exemplarily, the step of determining whether the NG picture is a picture to be reviewed further includes:

[0080] If the NG picture is a picture to be reviewed, a black filled area in the picture to be reviewed is identified.

[0081] In this embodiment, after determining that there is a black filled area in the NG picture, the NG picture is determined to be a picture to be re-inspected, and the black filled area in the picture to be re-inspected is identified. The identified black filled area is used to determine whether the picture to be re-inspected is a false point, thereby reducing the false point rate of material defect detection, reducing the workload of manual re-inspection, and improving the overall detection efficiency of material defects.

[0082] Exemplarily, the step of identifying the black filled area in the image to be reviewed further includes:

[0083] Generate a new NG picture according to the black-filled area in the picture to be reviewed and the target area corresponding to its master image, wherein the area in the new NG picture corresponding to the black-filled area in the picture to be reviewed is replaced by the target area corresponding to the master image;

[0084] The new NG picture is identified through AI detection to determine whether the new NG picture has a rejection defect. If no rejection defect exists, the new NG picture is determined to be a false point; wherein the rejection defect refers to a material defect that is unacceptable to the customer.

[0085] In this embodiment, a new NG picture is generated, and AI detection is used to determine whether the new NG picture has a rejection defect. Based on the judgment result, it is determined whether the new NG picture is a false point. The detection is accurate and efficient, which reduces the false point rate of material defect detection, reduces the workload of manual re-inspection, and improves the overall material defect detection efficiency. Moreover, by determining whether the new NG picture has a rejection defect, it is determined whether it is a false point, which is more in line with the actual needs of users and further reduces the false point rate.

[0086] Exemplarily, the AI ​​detection is implemented based on a preset false point AI detection model.

[0087] In this embodiment, a false point AI detection model is established to realize false point judgment of NG pictures, thereby ensuring the accuracy and efficiency of false point judgment.

[0088] Embodiment 5

[0089] Please refer to Figure 5 As stated, Figure 5 This is a schematic diagram of the structure of a material defect re-inspection device provided in Embodiment 5 of the present invention. As shown in the figure, the material defect re-inspection device 500 in this embodiment adopts the material defect re-inspection method proposed in any one of Embodiments 1 to 4, including:

[0090] The re-inspection picture determination module 501 is used to determine whether the NG picture is a picture to be re-inspected; wherein there is a black filled area in the picture to be re-inspected;

[0091] The false point defect re-inspection module 502 is used to determine whether the picture to be re-inspected is a false point when it is determined that the NG picture is a picture to be re-inspected.

[0092] The technical solution of this embodiment re-inspects the NG image output by the AVI machine through the material defect re-inspection device 500 composed of the re-inspection image judgment module 501 and the false point defect re-inspection module 502, thereby reducing the false point rate of material defect detection, reducing the workload of manual re-inspection, and improving the overall material defect detection efficiency; moreover, by judging whether the image to be re-inspected has a rejection defect, it is determined whether it is a false point, rather than judging the material as a defective material if there is a defect, which is more in line with the actual needs of users and further reduces the false point rate.

[0093] Embodiment 6

[0094] Please refer to Figure 6 As stated, Figure 6 This is a schematic diagram of the application of a material defect re-inspection system provided in the sixth embodiment of the present invention. In this embodiment, the material defect re-inspection system 600 includes the material defect re-inspection device 500 proposed in the fifth embodiment above.

[0095] It should be noted that in this embodiment Figure 6 The working process of the AVI machine 601, the working process of the material defect re-inspection device 602, and the working process of the VRS machine 603 are all applicable to the first to fifth embodiments.

[0096] The material defect re-inspection system 600 proposed in this embodiment re-inspects the NG image output by the AVI machine 601 through the material defect re-inspection device 500, and determines whether it is a false point by judging whether there is a rejection defect in the image to be re-inspected, rather than judging the material as a defective material if there is a defect. This is more in line with the actual needs of users, reduces the false point rate of material defect detection, reduces the workload of manual re-inspection, and improves the overall detection efficiency of material defects.

[0097] Embodiment 7

[0098] An embodiment of the present invention provides a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement the material defect re-inspection method proposed in any one of the above-mentioned embodiments one to four, thereby reducing the false point rate of material defect detection, reducing the workload of manual re-inspection, and improving the overall detection efficiency of material defects; moreover, by judging whether a new NG image has a rejection defect, determining whether it is a false point, it is more in line with the actual needs of users and further reduces the false point rate.

[0099] It should be noted that the above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0100] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A material defect re-inspection method, characterized in that: include: Determine whether the NG picture is a picture to be rechecked; wherein there is a black filled area in the picture to be rechecked; If the NG picture is the picture to be re-inspected, the black-filled area in the picture to be re-inspected is identified, and a second master image is generated according to the black-filled area in the picture to be re-inspected and its corresponding master image; wherein, there is a black-filled area in the second master image, and an RGB comparison test is performed on the second master image and the picture to be re-inspected to determine whether there is a rejection defect in the picture to be re-inspected, and if there is no rejection defect, the picture to be re-inspected is determined to be a false point; wherein, the rejection defect refers to a material defect that is unacceptable to the customer; wherein, the RGB comparison test is performed on the second master image and the picture to be re-inspected, including: adjusting the pixel range of the RGB test, and performing an RGB comparison test on the second master image and the picture to be re-inspected.

2. A material defect re-inspection device, characterized in that: The device adopts the material defect re-inspection method according to claim 1, comprising: A re-inspection picture judgment module is used to judge whether the NG picture is a picture to be re-inspected; wherein there is a black filled area in the picture to be re-inspected; The false point defect re-inspection module is used to determine whether the picture to be re-inspected is a false point when it is determined that the NG picture is a picture to be re-inspected.

3. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the material defect re-inspection method as claimed in claim 1.

4. A material defect detection system, characterized in that: The system includes the material defect re-inspection device as described in claim 2.

Images