Mura defect detection method and AOI defect detection equipment

Abstract

The invention relates to the technical field of defect detection of display screens, in particular to a Mura defect detection method and AOI defect detection equipment, a substrate is located on a carrying table, the method comprises the steps that a first image of a to-be-detected area on the substrate is acquired, and the to-be-detected area comprises a first target point; acquiring a second image of an area where the second target point is located on the substrate; the second target point is a point obtained in the X-axis direction after the first target point moves a preset distance on the carrying table along with the substrate; the X-axis direction is the printing direction of the ink-jet printer; and if the second image comprises the to-be-detected area, determining that the defect type of the to-be-detected area is a first defect type, and the first defect type comprises a Mura defect. According to the invention, the accuracy of Mura defect detection can be improved, and the problem of missing detection is reduced.

Description

Technical Field

[0001] This application relates to the field of display screen defect detection technology, specifically a method for detecting Mura defects and an AOI defect detection device. Background Technology

[0002] Currently, Automatic Optical Inspection (AOI) refers to the use of optical imaging technology (usually using cameras and lenses) to acquire images of the target object, and then using certain image processing algorithms to extract information such as the target's size, position, orientation, spectral characteristics, structure, and defects from the captured images. This allows for the performance of tasks such as the inspection of display screen products. AOI defect detection equipment is widely used in the field of display screen defect detection.

[0003] However, AOI defect inspection equipment typically uses deep learning vision algorithms to learn from defect samples of display panels (also known as substrates), and all defect samples are known defects. On the one hand, new and unknown defects emerge one after another; on the other hand, the substrate yield is relatively high, meaning the number of defect samples is relatively small, while the number of non-defect samples is relatively large, leading to missed detections after deep learning. This is especially true for Mura defects in the display screen after inkjet printing, which may be mixed with dirt on the camera (such as dust or particles), air holes or threaded holes on the stage, dirt on the bottom of the substrate, etc.

[0004] Therefore, to address the issue of missed detection of Mura defects, a method for detecting Mura defects and AOI defect detection equipment are needed. Summary of the Invention

[0005] This application provides a method for detecting Mura defects and an AOI defect detection device, which can improve the accuracy of Mura defect detection and reduce the problem of missed detection.

[0006] The first aspect of this application discloses a method for detecting Mura defects. The substrate is located on a stage. The detection method includes: acquiring a first image of a region to be detected on the substrate, the region to be detected including a first target point; acquiring a second image of the region on the substrate where a second target point is located; the second target point is a point obtained by moving the first target point a preset distance along the X-axis on the stage; the X-axis is the printing direction of the inkjet printer; if the second image includes the region to be detected, then the defect type of the region to be detected is determined to be a first defect type, the first defect type including Mura defects.

[0007] In the above scheme, two images of the target point before and after it moves with the substrate are used, and both images are of the same area on the substrate. If both images include the area to be detected, it means that the area to be detected is on the substrate; this is used to determine that the defect is a Mura defect. This method is highly efficient and accurate in identifying Mura defects, and it avoids the problem of missing Mura defects. Whether the second image includes the area to be detected can be determined by calculating the similarity between the first and second images to confirm the existence of similar regions; alternatively, it can be determined by the difference between the first and second images. No further details or limitations are provided for this method.

[0008] In one possible implementation, the detection method further includes: if the second image does not include the area to be detected, then determining the defect type of the area to be detected as a second defect type, the second defect type including one or both of camera lens dirt defects and stage defects.

[0009] The above scheme aims to illustrate the situation of non-substrate defects. The second image does not include the area to be detected, indicating that the defect is on the stage. "Similar defects" such as air floating holes and threaded holes on the stage, as well as "similar defects" such as lens dirt, captured by the camera, will not move with the movement of the substrate.

[0010] In one possible implementation, the first defect type further includes a contamination defect on the bottom of the substrate; the detection method further includes: after determining that the defect type of the area to be detected is the first defect type, determining a Mura defect area in the second image; determining the Mura defect area in the second image includes: acquiring sharpness evaluation values ​​of multiple areas in the second image; the multiple areas in the second image include a first area and a second area; determining whether the sharpness evaluation values ​​of the multiple areas in the second image are greater than or equal to a preset sharpness evaluation threshold; if the sharpness evaluation value of the first area is greater than or equal to the preset sharpness evaluation threshold, then the first area is determined to be a Mura defect area; if the sharpness evaluation value of the second area is less than the preset sharpness evaluation threshold, then the second area is determined to be a contamination defect area on the bottom of the substrate.

[0011] In the above solution, when there is a dirt defect on the bottom of the substrate, the dirt defect on the bottom of the substrate can be further distinguished from the Mura defect. This is determined by judging the sharpness evaluation value of multiple regions in the second image, and the focal plane of the camera is preferably the upper surface of the substrate. At this time, the Mura defect located on the upper surface is relatively clear, while the dirt defect on the bottom of the substrate located on the lower surface is relatively blurry. The two can be distinguished by setting a preset sharpness evaluation threshold between these two sharpness evaluation values.

[0012] Furthermore, this method can be referred to as single focal plane focusing; compared to the solution described below, which involves two camera depth-of-field focusing operations, one with the camera's focal plane set on the upper surface of the substrate and the other with the focal plane set on the lower surface of the substrate.

[0013] In one possible implementation, the first defect type further includes a contamination defect on the bottom of the substrate; the detection method further includes: after determining that the defect type of the area to be detected is the first defect type, determining a Mura defect area in the second image; determining the Mura defect area in the second image includes: acquiring a third image on the substrate located in the area where the second target point is located, the third image being an image taken when the focal plane of the camera is located on the lower surface of the substrate; the second image being an image taken when the focal plane of the camera is located on the upper surface of the substrate; acquiring sharpness evaluation values ​​of multiple areas in the second image and sharpness evaluation values ​​of multiple areas in the third image; comparing the magnitude of a first sharpness evaluation value and a second sharpness evaluation value, the first sharpness evaluation value being the sharpness evaluation value of the third area in the second image, the second sharpness evaluation value being the sharpness evaluation value of the fourth area in the third image, the third area and the fourth area being the same area on the substrate; if the first sharpness evaluation value is greater than the second sharpness evaluation value, then the third area is determined to be a Mura defect area.

[0014] In the above schemes, the defect detection efficiency of the double focal plane focusing scheme is slightly lower than that of the single focal plane focusing scheme (because two images need to be taken on the upper and lower surfaces of the substrate). However, the double focal plane focusing scheme has a higher accuracy in identifying Mura defects than the single focal plane focusing scheme because it takes two images.

[0015] In one possible implementation, the detection method further includes: if the first sharpness evaluation value is less than the second sharpness evaluation value, then determining the fourth region as a dirty area on the bottom of the substrate.

[0016] The above scheme aims to disclose the judgment of defects on the bottom of the substrate. Furthermore, for defective areas, the first sharpness evaluation value will not be equal to the second sharpness evaluation value; if the first sharpness evaluation value is not equal to the second sharpness evaluation value, it indicates that there is no defect in that area.

[0017] In one possible implementation, obtaining sharpness evaluation values ​​for multiple regions in the second image specifically includes: obtaining a pixel grayscale matrix of a first region in the second image, where the first region is any region in the second image; and obtaining a sharpness evaluation value for the first region according to a preset method, wherein the preset method includes: is the grayscale value of the pixel in the x-th row and y-th column.

[0018] The above scheme specifically discloses a method for setting a sharpness evaluation value. The sharpness evaluation value of an image is calculated by using a sharpness gradient to measure the sharpness gradient between two adjacent pixels in the same row or column, and then amplified through accumulation to facilitate the judgment of the sharpness gradient.

[0019] In one possible implementation, the depth of field of the camera is less than the thickness of the substrate.

[0020] The above scheme discloses a preferred solution between the camera depth of field range and the substrate thickness. This solution makes it easier to identify Mura defects using both the single focal plane focusing scheme and the double focal plane focusing scheme, especially when using the single focal plane focusing scheme and the double focal plane focusing scheme to identify Mura defects when the camera depth of field range is greater than or equal to the substrate thickness.

[0021] In one possible implementation, both the first image and the second image are images captured when the camera's focal plane is located on the upper surface of the substrate.

[0022] At this point, since the main focus is on judging the Mura defects on the upper surface of the substrate, it is more appropriate to set the focal plane of the camera on the upper surface of the substrate.

[0023] In one possible implementation, the size of the region where the second target point is located is greater than or equal to the size of the region to be detected; and before acquiring a first image of the region to be detected on the substrate, the detection method includes: acquiring a plurality of regions to be detected on the substrate.

[0024] At this point, the size of the region containing the second target point is greater than or equal to the size of the region to be detected, allowing the second image to better determine whether there is a region to be detected. The region to be detected is the defect area of ​​the substrate, which can be obtained in various ways, not all of which will be listed here. For example, by setting a grayscale threshold for the region, the background and defects of the image can be distinguished. In this case, all defects in the substrate are selected, which facilitates further differentiation of defect types and improves the efficiency of substrate Mura defect recognition.

[0025] The second aspect of this application discloses an AOI defect detection device, including a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, and both the user interface and the network interface are used to communicate with other devices. The processor is used to execute the instructions stored in the memory so that the AOI defect detection device performs a Mura defect detection method as described in any of the above.

[0026] The beneficial effects of this application include: By taking two images of the target point before and after it moves along the substrate, and ensuring that both images are of the same area on the substrate, if both images include the area to be detected, it indicates that the area to be detected is on the substrate; this method is used to determine that the defect is a Mura defect. This method is highly efficient and accurate in identifying Mura defects, and avoids the problem of missing Mura defects. The second image does not include the area to be detected, indicating that the defect is on the stage. The "similar defects" such as air float holes and threaded holes on the stage, as well as the "similar defects" such as lens dirt, captured by the camera will not move with the movement of the substrate. In cases where there are contamination defects on the bottom of the substrate, these contamination defects can be further distinguished from Mura defects. This is done by judging the sharpness evaluation values ​​of multiple regions in the second image, with the camera's focal plane preferably located on the upper surface of the substrate. In this case, Mura defects located on the upper surface are relatively sharp, while contamination defects on the bottom of the substrate located on the lower surface are relatively blurry. A preset sharpness evaluation threshold can be set between these two sharpness evaluation values ​​to distinguish between them. The double focal plane focusing scheme has a slightly lower defect detection efficiency than the single focal plane focusing scheme (because it requires taking two images on the upper and lower surfaces of the substrate). However, because the double focal plane focusing scheme takes two images, it has a higher accuracy in identifying Mura defects compared to the single focal plane focusing scheme. Furthermore, for defective areas, the first sharpness rating value will not be equal to the second sharpness rating value; if the first sharpness rating value is not equal to the second sharpness rating value, it means that there is no defect in that area. When the camera's depth of field is less than the substrate thickness, this setting makes it easier to identify Mura defects compared to using a single focal plane focusing scheme or a double focal plane focusing scheme when the camera's depth of field is greater than or equal to the substrate thickness. When focusing on a single focal plane, selecting the upper surface of the substrate as the focal plane is to avoid missing Mura defects; the size of the area where the second target point is located is greater than or equal to the size of the area to be detected, which allows the second image to better determine whether there is an area to be detected. Attached Figure Description

[0027] Figure 1 This is a schematic diagram of a method for detecting Mura defects disclosed in this application. Figure 2 This is a schematic diagram of another method for detecting Mura defects disclosed in this application. Figure 3 This is a schematic diagram of another method for detecting Mura defects disclosed in this application. Figure 4This is a schematic diagram of a scenario for Mura defect detection disclosed in this application specification; Figure 5 This is a schematic diagram of multiple regions within an image in a Mura defect detection method disclosed in this application specification; Figure 6 This is a schematic diagram of the structure of an AOI defect detection device disclosed in this application. Detailed Implementation

[0028] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0029] In the description of the embodiments of this application, the words "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design that is described as "for example" or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design options. Rather, the use of the words "for example" or "for instance" is intended to present the relevant concepts in a specific manner.

[0030] In the description of the embodiments of this application, the term "multiple" means two or more. For example, multiple systems means two or more systems, and multiple screen terminals means two or more screen terminals. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0031] This specification discloses a method for detecting Mura defects, wherein the substrate is placed on a stage, and the detection method includes steps S101-S103.

[0032] Step S101: Obtain a first image of the area to be detected on the substrate, wherein the area to be detected includes a first target point.

[0033] Step S102: Obtain a second image on the substrate located in the area where the second target point is located; the second target point is the point obtained in the X-axis direction after the first target point moves a preset distance on the stage with the substrate; the X-axis direction is the printing direction of the inkjet printer.

[0034] Step S103: If the second image includes the region to be detected, then the defect type of the region to be detected is determined to be a first defect type, and the first defect type includes Mura defects.

[0035] At this point, by taking two images of the target point before and after it moves with the substrate, and ensuring that both images are of the same area on the substrate, if both images include the area to be detected, it indicates that the area to be detected is on the substrate; thus, the defect is identified as a Mura defect. This method is highly efficient and accurate in identifying Mura defects, and avoids the problem of missing Mura defects.

[0036] In addition, whether the second image includes the region to be detected can be determined by calculating the similarity between the first and second images to confirm whether a similar region exists; alternatively, it can be determined by the result of differentiating the first and second images. No further details or limitations will be provided for this.

[0037] Furthermore, the X-axis direction is also the transport direction of the substrate on the stage; the Y-axis direction is the movement direction of the nozzle module on the stage. The area to be inspected is the area on the substrate where defects exist, and these defects include the first type of defect.

[0038] Furthermore, the preset distance between the first target point and the second target point can be set as needed without restriction; and there is a distance mapping relationship between the first target point and the second target point, that is, when the stage is used as a reference, the two target points are spaced apart by a preset distance, and when the substrate is used as a reference, the two target points are located at the same point in the same region of the substrate. Moreover, the positions of these two target points are not restricted; they can be any point on the stage or the substrate (the point after inkjet printing). The dimensions of the area to be detected and the area where the second target point is located, as well as the size relationship between these two areas, are not restricted and can be set according to actual needs.

[0039] like Figure 4 As shown, Figure 4 An example is provided of a stage 100, a substrate 210 before movement, and a substrate 220 after movement (marked with dashed lines). Furthermore, the same region (on the substrate, this region did not move) is marked on both substrates 210 and 220: region 211 before movement on substrate 210 and region 221 after movement on substrate 220. The movement direction is the positive X-axis direction, and both regions 211 and 221 are areas to be detected. A first target point 212 and a second target point 222 are also provided; the distance between the two target points can be set as needed and is not limited. Figure 4 The example shown illustrates a case where the area to be detected is located on a substrate. When in Figure 4No area to be detected was found in region 221, while an area to be detected was found in region 211. This indicates that the area to be detected is located on the stage (e.g., air-bearing holes, air-bearing strips, etc.) or possibly on the camera lens (e.g., dust particles). This method can avoid missing Mura detections on the substrate.

[0040] In one example, the detection method further includes determining the defect type of the region to be detected as a second defect type if the second image does not include the region to be detected, the second defect type including one or both of camera lens dirt defects and stage defects.

[0041] At this point, the second image does not include the area to be inspected, indicating that the defect is on the stage. The "similar defects" captured by the camera, such as air-bearing holes and threaded holes on the stage, as well as "similar defects" like lens contamination, will not move with the substrate. (As above) Figure 4 The discussion on this topic will not be repeated here.

[0042] In one example, the first defect type can be further subdivided. The first defect type also includes contamination defects on the bottom of the substrate.

[0043] The detection method further includes: after determining that the defect type of the area to be detected is the first defect type, determining the Mura defect area in the second image; the determination of the Mura defect area in the second image includes steps S201-S203.

[0044] Step S201: Obtain the sharpness evaluation value of multiple regions in the second image; the multiple regions in the second image include the first region and the second region.

[0045] Step S202: Determine whether the sharpness evaluation value of multiple regions of the second image is greater than or equal to the preset sharpness evaluation threshold.

[0046] Step S203: If the sharpness evaluation value of the first region is greater than or equal to the preset sharpness evaluation threshold, then the first region is determined to be a Mura defect region.

[0047] Furthermore, if the clarity evaluation value of the second region is less than the preset clarity evaluation threshold, then the second region is determined to be a dirty defect area on the bottom of the substrate.

[0048] like Figure 5 As shown, Figure 5 The second image 230 is shown in the image. Figure 4Taking the image corresponding to region 211 as an example (or other image shapes), there are multiple regions, such as the first region 232 and the second region 231. The first region 232 can be exemplified as a Mura defect region, and the second region 231 can be exemplified as a dirt defect region on the bottom of the substrate.

[0049] At this point, when there is a dirt defect on the bottom of the substrate, the dirt defect on the bottom of the substrate can be further distinguished from the Mura defect. This is determined by judging the sharpness evaluation value of multiple areas in the second image, and the focal plane of the camera is preferably the upper surface of the substrate. At this point, the Mura defect located on the upper surface is relatively clear, while the dirt defect on the bottom of the substrate located on the lower surface is relatively blurry. The two can be distinguished by setting a preset sharpness evaluation threshold that is between these two sharpness evaluation values.

[0050] Furthermore, this method can be referred to as single focal plane focusing; compared to the solution described below, which involves two camera depth-of-field focusing operations, one with the camera's focal plane set on the upper surface of the substrate and the other with the focal plane set on the lower surface of the substrate.

[0051] Furthermore, selecting the upper surface of the substrate as the focal plane during single-focusing serves to prevent Mura defects from being missed. This is because contaminants on the bottom of the substrate (such as dust, particles, etc.) exhibit high contrast (sharp edges) when captured by the camera, while Mura defects located on the upper surface have low contrast. If the image of the lower surface of the substrate is captured during single-focusing, the low contrast of the Mura defect itself, combined with the out-of-focus blur (when the Mura defect is on the upper surface of the substrate, and the focal plane is on the lower surface, it is out of focus for the Mura defect), may result in the Mura defect being undetectable (i.e., missed detection).

[0052] The double focal plane focusing method has a slightly lower defect detection efficiency than the single focal plane focusing method (because it requires capturing two images on the upper and lower surfaces of the substrate). However, because it captures two images, the double focal plane focusing method has a higher accuracy in identifying Mura defects compared to the single focal plane method. The double focal plane focusing method will be explained below.

[0053] In one example, the first defect type further includes dirt defects on the bottom of the substrate; the detection method further includes: after determining that the defect type of the area to be detected is the first defect type, determining the Mura defect area in the second image; the determination of the Mura defect area in the second image includes steps S301-S304.

[0054] Step S301: Obtain a third image on the substrate located in the area where the second target point is located. The third image is an image taken when the focal plane of the camera is located on the lower surface of the substrate; the second image is an image taken when the focal plane of the camera is located on the upper surface of the substrate.

[0055] Step S302: Obtain the sharpness evaluation values ​​of multiple regions in the second image and the sharpness evaluation values ​​of multiple regions in the third image.

[0056] Step S303: Compare the magnitudes of the first sharpness evaluation value and the second sharpness evaluation value. The first sharpness evaluation value is the sharpness evaluation value of the third region in the second image, and the second sharpness evaluation value is the sharpness evaluation value of the fourth region in the third image. The third region and the fourth region are the same region on the substrate.

[0057] By comparing any identical region between the second and third images, the specific defect type of that region can be determined.

[0058] Step S304: If the first sharpness evaluation value is greater than the second sharpness evaluation value, then the third region is determined to be a Mura defect region.

[0059] At this point, the optimal condition for the two-focal-plane focusing scheme is that the camera's depth of field should be less than the substrate thickness, and the greater the difference between the two values, the better the identification effect of Mura defects (i.e., when the focal plane is on the upper surface of the substrate, defects on the upper surface of the substrate are clearer when the image is captured, while defects on the lower surface of the substrate are more blurred, making it easier to distinguish between the two). If the camera's depth of field is greater than or equal to the substrate thickness, it will affect the identification of Mura defects.

[0060] In one example, the detection method further includes: if the first sharpness evaluation value is less than the second sharpness evaluation value, then determining the fourth region as a dirty area on the bottom of the substrate.

[0061] This example illustrates the determination of defects at the bottom of the substrate.

[0062] For defective areas, the first sharpness rating will not be equal to the second sharpness rating; if the first sharpness rating is not equal to the second sharpness rating, it means that there is no defect in that area (e.g., background area).

[0063] In one example, obtaining the sharpness evaluation values ​​of multiple regions in a second image specifically includes: obtaining the pixel grayscale matrix of a first region in the second image, where the first region is any region in the second image; and obtaining the sharpness evaluation value of the first region according to a preset method, wherein the preset method includes: is the grayscale value of the pixel in the x-th row and y-th column.

[0064] At this point, the image sharpness evaluation value is calculated using a sharpness gradient approach, performing calculations on adjacent pixels in the same row or column. This gradient is amplified through summation to facilitate sharpness gradient assessment. Furthermore, grayscale differences are amplified using subtraction, sum of squares, and square roots. This is especially important after inkjet printing, as the Mura (mura) size is small and cannot emit its own light for image capture; images are only captured after a light source is applied. Using a grayscale average value in this case might lose the sharpness gradient, failing to effectively distinguish Mura defects from dirt defects on the substrate bottom.

[0065] In one example, the camera's depth of field is less than the thickness of the substrate.

[0066] At this point, a preferred scheme between the camera depth of field range and the substrate thickness is disclosed, which makes it easier to identify Mura defects using both the single focal plane focusing scheme and the double focal plane focusing scheme; especially when using the single focal plane focusing scheme and the double focal plane focusing scheme to identify Mura defects when the camera depth of field range is greater than or equal to the substrate thickness.

[0067] In one example, both the first image and the second image are images taken when the camera's focal plane is located on the upper surface of the substrate.

[0068] At this point, since the main focus is on judging the Mura defects on the upper surface of the substrate, it is more appropriate to set the focal plane of the camera on the upper surface of the substrate.

[0069] Furthermore, selecting the upper surface of the substrate as the focal plane during single-focusing is to avoid missing Mura defects. This is because contaminants on the bottom of the substrate (such as dust, particles, etc.) have high contrast (sharp edges) when captured by the camera, while Mura defects on the upper surface of the substrate have low contrast. If the image of the lower surface of the substrate is captured during single-focusing, the low contrast of the Mura defects themselves, combined with the out-of-focus blur of the captured image, may cause the Mura defects to go undetected (i.e., missed detection).

[0070] In one example, the size of the region where the second target point is located is greater than or equal to the size of the region to be detected; and before acquiring a first image of the region to be detected on the substrate, the detection method includes: acquiring a plurality of regions to be detected on the substrate.

[0071] At this point, the size of the region containing the second target point is greater than or equal to the size of the region to be detected, allowing the second image to better determine whether there is a region to be detected. The region to be detected is the defect area of ​​the substrate, which can be obtained in various ways, not all of which will be listed here. For example, by setting a grayscale threshold for the region, the background and defects of the image can be distinguished. In this case, all defects in the substrate are selected, which facilitates further differentiation of defect types and improves the efficiency of substrate Mura defect recognition.

[0072] This specification discloses an AOI defect detection device, including a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, and both the user interface and the network interface are used to communicate with other devices. The processor is used to execute the instructions stored in the memory so that the AOI defect detection device performs a Mura defect detection method as described above.

[0073] Specifically, a method for detecting Mura defects, wherein a substrate is placed on a stage, includes: acquiring a first image of a region to be detected on the substrate, the region to be detected including a first target point; acquiring a second image of the region on the substrate where a second target point is located; the second target point is a point obtained in the X-axis direction after the first target point moves a preset distance with the substrate on the stage; the X-axis direction is the printing direction of the inkjet printer; if the second image includes the region to be detected, then the defect type of the region to be detected is determined to be a first defect type, the first defect type including Mura defects.

[0074] In one example, if the second image does not include the area to be detected, then the defect type of the area to be detected is determined to be a second defect type, which includes one or both of camera lens dirt defects and stage defects.

[0075] In one example, the first defect type further includes a contamination defect on the bottom of the substrate; after determining that the defect type of the area to be detected is the first defect type, a Mura defect area is determined in the second image; determining the Mura defect area in the second image includes: acquiring the sharpness evaluation values ​​of multiple areas in the second image; the multiple areas in the second image include a first area and a second area; determining whether the sharpness evaluation values ​​of the multiple areas in the second image are greater than or equal to a preset sharpness evaluation threshold; if the sharpness evaluation value of the first area is greater than or equal to the preset sharpness evaluation threshold, then the first area is determined to be a Mura defect area; if the sharpness evaluation value of the second area is less than the preset sharpness evaluation threshold, then the second area is determined to be a contamination defect area on the bottom of the substrate.

[0076] In one example, the first defect type further includes dirt defects on the bottom of the substrate; after determining that the defect type of the area to be detected is the first defect type, a Mura defect area is determined in the second image; determining the Mura defect area in the second image includes: acquiring a third image on the substrate located in the area where the second target point is located, the third image being an image taken when the focal plane of the camera is located on the lower surface of the substrate; the second image being an image taken when the focal plane of the camera is located on the upper surface of the substrate; acquiring the sharpness evaluation values ​​of multiple areas in the second image and the sharpness evaluation values ​​of multiple areas in the third image; comparing the magnitude of the first sharpness evaluation value and the second sharpness evaluation value, the first sharpness evaluation value being the sharpness evaluation value of the third area in the second image, the second sharpness evaluation value being the sharpness evaluation value of the fourth area in the third image, the third area and the fourth area being the same area on the substrate; if the first sharpness evaluation value is greater than the second sharpness evaluation value, then the third area is determined to be a Mura defect area.

[0077] In one example, if the first sharpness rating is less than the second sharpness rating, then the fourth region is determined to be a dirty area on the bottom of the substrate.

[0078] In one example, obtaining the sharpness evaluation values ​​of multiple regions in a second image specifically includes: obtaining the pixel grayscale matrix of a first region in the second image, where the first region is any region in the second image; and obtaining the sharpness evaluation value of the first region according to a preset method, wherein the preset method includes: is the grayscale value of the pixel in the x-th row and y-th column.

[0079] In one example, the camera's depth of field is less than the thickness of the substrate.

[0080] In one example, both the first image and the second image are images taken when the camera's focal plane is located on the upper surface of the substrate.

[0081] In one example, the size of the region where the second target point is located is greater than or equal to the size of the region to be detected; and before acquiring a first image of the region to be detected on the substrate, the detection method includes: acquiring a plurality of regions to be detected on the substrate.

[0082] It should be noted that the above embodiments of the apparatus are only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0083] The specification also discloses a computer-readable storage medium that stores instructions that, when executed, perform the method described above.

[0084] This embodiment also discloses an electronic device, which may be an AOI defect detection device, to perform the above-described method. (Refer to...) Figure 6 The electronic device may include: at least one processor 601, at least one communication bus 602, display 603, network interface 604, and at least one memory 605.

[0085] The communication bus 602 is used to enable communication between these components.

[0086] The display 603 may include a display screen and a camera.

[0087] The network interface 604 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0088] The processor 601 may include one or more processing cores. The processor 601 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 605, and by calling data stored in the memory 605. Optionally, the processor 601 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 601 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 601 and may be implemented as a separate chip.

[0089] The memory 605 may include random access memory (RAM) or read-only memory. Optionally, the memory 605 may include a non-transitory computer-readable storage medium. The memory 605 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 605 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), instructions for implementing the various method embodiments described above, etc.; the data storage area may store data involved in the various method embodiments described above, etc. Optionally, the memory 605 may also be at least one storage device located remotely from the aforementioned processor 601. As shown in the figure, the memory 605, as a computer storage medium, may include an operating system, a network communication module, and application programs for a display module.

[0090] exist Figure 6 In the electronic device shown, the display 603 is mainly used to provide an input interface for the user and to obtain the user input data; while the processor 601 can be used to call the application program stored in the memory 605. When executed by one or more processors 601, the electronic device performs one or more methods as described in the above embodiments.

[0091] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0092] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0093] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the shown or discussed mutual couplings or direct couplings or communication connections may be through some service interfaces; indirect couplings or communication connections between apparatuses or units may be electrical or other forms.

[0094] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0095] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0096] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory 605 and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory 605 includes various media capable of storing program code, such as a USB flash drive, external hard drive, magnetic disk, or optical disk.

[0097] The above are merely exemplary embodiments of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Those skilled in the art will readily conceive of other embodiments of this disclosure upon considering the specification and the disclosure of practical truth. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The specification and embodiments are considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A method for detecting Mura defects, characterized in that, The substrate is located on the stage, and the detection method includes: Acquire a first image of the region to be detected on the substrate, wherein the region to be detected includes a first target point; Acquire a second image on the substrate located in the area of ​​the second target point; the second target point is the point obtained in the X-axis direction after the first target point moves a preset distance on the stage with the substrate; the X-axis direction is the printing direction of the inkjet printer; If the second image includes the region to be detected, then the defect type of the region to be detected is determined to be a first defect type, which includes Mura defects.

2. The detection method according to claim 1, characterized in that, The detection method further includes: If the second image does not include the area to be detected, then the defect type of the area to be detected is determined to be the second defect type, which includes one or both of camera lens dirt defects and stage defects.

3. The detection method according to claim 1, characterized in that, The first defect type also includes contamination defects on the bottom of the substrate; the detection method further includes: after determining that the defect type of the area to be detected is the first defect type, determining the Mura defect area in the second image; Determining the Mura defect region in the second image includes: Obtain sharpness evaluation values ​​for multiple regions in the second image; the multiple regions in the second image include a first region and a second region; Determine whether the sharpness evaluation values ​​of multiple regions of the second image are greater than or equal to a preset sharpness evaluation threshold; If the clarity evaluation value of the first region is greater than or equal to the preset clarity evaluation threshold, then the first region is determined to be a Mura defect region; if the clarity evaluation value of the second region is less than the preset clarity evaluation threshold, then the second region is determined to be a dirt defect region on the bottom of the substrate.

4. The detection method according to claim 1, characterized in that, The first defect type also includes contamination defects on the bottom of the substrate; the detection method further includes: after determining that the defect type of the area to be detected is the first defect type, determining the Mura defect area in the second image; Determining the Mura defect region in the second image includes: A third image is acquired on the substrate located in the area of ​​the second target point. The third image is an image captured when the focal plane of the camera is located on the lower surface of the substrate. The second image is an image captured when the focal plane of the camera is located on the upper surface of the substrate. Obtain the sharpness evaluation values ​​of multiple regions in the second image and multiple regions in the third image; The first sharpness evaluation value and the second sharpness evaluation value are compared. The first sharpness evaluation value is the sharpness evaluation value of the third region in the second image, and the second sharpness evaluation value is the sharpness evaluation value of the fourth region in the third image. The third region and the fourth region are the same region on the substrate. If the first sharpness rating is greater than the second sharpness rating, then the third region is determined to be a Mura defect region.

5. The detection method according to claim 4, characterized in that, The detection method further includes: If the first sharpness evaluation value is less than the second sharpness evaluation value, then the fourth region is determined to be a dirty area on the bottom of the substrate.

6. The detection method according to any one of claims 3-5, characterized in that, Obtain sharpness evaluation values ​​for multiple regions in the second image, specifically including: Obtain the pixel grayscale matrix of the first region in the second image, where the first region is any region in the second image; The sharpness evaluation value of the first region is obtained according to a preset method, the preset method including: is the grayscale value of the pixel in the x-th row and y-th column.

7. The detection method according to any one of claims 3-5, characterized in that, The camera's depth of field is less than the thickness of the substrate.

8. The detection method according to claim 1, characterized in that, Both the first image and the second image are images taken when the camera's focal plane is located on the upper surface of the substrate.

9. The detection method according to claim 1, characterized in that, The size of the region where the second target point is located is greater than or equal to the size of the region to be detected; Before acquiring the first image of the area to be detected on the substrate, the detection method includes: acquiring multiple areas to be detected on the substrate.

10. An AOI defect detection device, characterized in that, It includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, and both the user interface and the network interface are used to communicate with other devices. The processor is used to execute the instructions stored in the memory so that the AOI defect detection device can perform a Mura defect detection method as described in any one of claims 1-9.

Images