Screen defect detection method and device based on second-order surface fitting method and equipment thereof

Abstract

The application provides a screen defect detection method and device based on a second-order curved surface fitting method and equipment thereof, which can perform fast and accurate defect detection and extraction on a gradual change picture. The screen gradual change defect detection method comprises the following steps: acquiring a gray scale gradual change image to be detected; calculating a gray value moment value and a gray value approximation parameter of the gray scale gradual change image by using a second-order curved surface algorithm; fitting and generating a smooth gradual change image according to the gray value moment value and the gray value approximation parameter; performing a difference operation on the smooth gradual change image and the gray scale gradual change image to obtain a difference image; performing threshold segmentation on the difference image to obtain a dark area defective image; and extracting defects in the dark area defective image and marking the defects.

Description

Technical Field

[0001] This invention relates to the field of screen inspection, and more specifically, to a screen defect detection method, apparatus and equipment based on second-order surface fitting. Background Technology

[0002] In the process of detecting defects in display screens using automated optical inspection equipment, the common detection method for gradient images is as follows: calculate the grayscale difference between adjacent pixels and obtain a suitable grayscale difference threshold; then, judge each pixel one by one, identifying pixels outside the grayscale difference threshold range as defective pixels. However, for images with grayscale gradients, such as 256-level grayscale images, the grayscale difference threshold between pixels is very small, leading to missed detections and false detections when using the conventional grayscale difference threshold method. Furthermore, defects in gradient images vary in shape, grayscale depth, and location, increasing the image judgment frequency and resulting in low detection efficiency. Summary of the Invention

[0003] The purpose of this invention is to provide a screen defect detection method, apparatus and equipment based on second-order surface fitting, which can quickly and accurately detect and extract defects in the aforementioned gradient images.

[0004] Specifically, the present invention includes the following:

[0005] Firstly, a screen defect detection method based on second-order surface fitting is provided. The screen gradient defect detection method includes the following steps:

[0006] Acquire the grayscale gradient image to be detected;

[0007] The grayscale moment value and grayscale approximation parameter of the grayscale gradient image are calculated using a second-order surface algorithm.

[0008] A flawless gradient image is generated by fitting parameters based on grayscale value moments and grayscale value approximations.

[0009] The difference image is obtained by subtracting the flawless gradient image and the grayscale gradient image;

[0010] Thresholding is performed on the difference image to obtain the dark area defect image. Defects in the dark area defect image are extracted and marked.

[0011] As a preferred technical solution, the steps for obtaining a grayscale gradient image with poor darkening defects include:

[0012] Turn on the display screen and acquire an image of the display screen with a grayscale value greater than 150 gray levels;

[0013] Use image segmentation methods to obtain the AA region of the display screen image;

[0014] Switch the display to a grayscale gradient image and capture the image within the AA area as the grayscale gradient image.

[0015] As a preferred technical solution, the above-mentioned second-order surface algorithm is as follows:

[0016] Image(r, c) = Alpha(rr) center ) 2 +Beta(cc center ) 2 +Gamma(rr center )*(cc center )+Delta(rr center )+Epsilon(cc center )+Zeta

[0017] Where, r center and c center α represents the center coordinates of the intersection of the AA region and the grayscale gradient image; Alpha represents the second-order coefficient in the vertical direction, Beta represents the second-order coefficient in the horizontal direction, Garnrna represents the mixed second-order coefficient, Delta represents the first-order coefficient in the vertical direction, Epsilon represents the first-order coefficient in the horizontal direction, and Zeta represents the zero-order coefficient.

[0018] As a preferred technical solution, the algorithm for generating a flawless gradient image based on grayscale value moment values ​​and grayscale value approximation parameters includes:

[0019] ImageSurface(r, c)

[0020] =Alpha(r-Row) 2 +Beta(c-Column) 2

[0021] +Gamma(r-Row)*(c-Column)+Delta(r-Row)

[0022] +Epsilon(c-Column)+Zeta

[0023] Here, the parameters Row and Column are the reference points for creating the flawless gradient image; Row and Column include the coordinates of the image center.

[0024] As a preferred technical solution, the above-mentioned method for obtaining the difference image includes subtracting the grayscale values ​​of each corresponding pixel in the flawless gradient image and the grayscale gradient image.

[0025] As a preferred technical solution, the above threshold segmentation is a threshold segmentation method based on local mean and variance.

[0026] As a preferred technical solution, the above-mentioned method for obtaining poor images in dark areas includes:

[0027] A mask of a set size is used to navigate within the difference image;

[0028] The grayscale value of the current image pixel is compared with the average grayscale value of the mask. When the grayscale value of the image pixel is lower than the average grayscale value of the corresponding mask by (StdDevScale, AbsThreshold) grayscale levels, the current image pixel is determined to be a defective pixel.

[0029] Collect and display all defective pixels to obtain a poor image of dark areas.

[0030] As a preferred technical solution, the above-mentioned extraction and marking of defects in dark area poor images includes the following steps:

[0031] Defects are filtered out by one or more of the following criteria: pixel area size, shape similarity, length and width.

[0032] Mark the defects in the image;

[0033] The marked points are replicated onto a grayscale gradient image and displayed.

[0034] Secondly, a screen defect detection device based on a second-order surface fitting method is provided. This screen gradient defect detection device includes:

[0035] Image acquisition unit, used to acquire grayscale gradient images with screen gradient defects;

[0036] The image fitting unit is used to calculate the grayscale moment value and grayscale approximation parameter of the grayscale gradient image using a second-order surface algorithm; and to fit and generate a flawless gradient image based on the grayscale moment value and grayscale approximation parameter.

[0037] The difference image generation unit is used to subtract the flawless gradient image and the grayscale gradient image to obtain the difference image.

[0038] The defect detection unit performs threshold segmentation on the image difference to obtain a dark area defect image; it extracts and marks the defects in the dark area defect image, and displays the marked points on a grayscale gradient image.

[0039] Thirdly, a screen defect detection device based on a second-order surface fitting method is provided, the screen gradient defect detection device comprising:

[0040] At least one processor; and,

[0041] A memory that is communicatively connected to at least one processor; wherein,

[0042] The memory stores instructions that can be executed by at least one processor to enable the at least one processor to perform the steps of any of the screen gradient defect detection methods in the first aspect.

[0043] The beneficial effects of this invention are as follows: This invention uses a second-order surface fitting algorithm to generate a flawless gradient image that matches the grayscale of a grayscale gradient image. Then, the flawless gradient image and the grayscale gradient image are subtracted to obtain a difference image. By extracting defects in dark areas from the difference image, gradient defects are selected from the defects within the dark areas and then marked on the grayscale gradient image. The gradient defect features are clear and obvious, enabling automated detection of the extended reality device's display screen. This greatly reduces the occurrence of low detection rates, missed detections, and high false detection rates caused by small differences in gradient images and human eye fatigue, thereby improving the efficiency and accuracy of screen defect detection equipment. This detection method can be applied to production lines for large-scale flow inspection, ensuring and extending the quality of shipped screens. Attached Figure Description

[0044] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 The image shown is a display screen image obtained in an embodiment of the present invention.

[0046] Figure 2 This is the AA region image after image segmentation according to an embodiment of the present invention;

[0047] Figure 3 This is a grayscale gradient screen obtained in an embodiment of the present invention;

[0048] Figure 4 This is a grayscale gradient image captured in an embodiment of the present invention;

[0049] Figure 5 A flawless gradient image generated by fitting data in an embodiment of the present invention;

[0050] Figure 6 This is a difference image from an embodiment of the present invention;

[0051] Figure 7 This is a defective image of a dark area according to an embodiment of the present invention;

[0052] Figure 8 This is a difference image of the screen defects marked in an embodiment of the present invention;

[0053] Figure 9 This is a grayscale gradient image used to mark screen defects in an embodiment of the present invention;

[0054] Figure 10 This is a flowchart of the screen gradient defect detection method according to an embodiment of the present invention;

[0055] Figure 11 This is a schematic diagram of the connection of the screen gradient defect detection device according to an embodiment of the present invention. Detailed Implementation

[0056] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art.

[0057] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0058] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0059] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0060] It should be noted that "multiple" as mentioned in this article refers to two or more.

[0061] Example 1

[0062] To address the low detection rate, missed detections, and false detections that occur when using the grayscale difference threshold method to detect screen gradient defects in existing technologies, this embodiment provides a screen defect detection method based on a second-order surface fitting method. Please refer to [link to relevant documentation]. Figure 10The flowchart of the screen gradient defect detection method includes the following steps:

[0063] S1: Obtain a grayscale gradient image with screen gradient defects. The method for obtaining the grayscale gradient image is as follows:

[0064] S11: After adjusting the CCD camera focal length and aperture of the AOI equipment, the display screen with the screen gradient defect is lit up on the fixture, and an image with a grayscale value greater than 150 is selected as the display screen image. Preferably, the display screen image is white or an image with a grayscale value greater than 150. The display screen image obtained in this embodiment can be found in [link to example]. Figure 1 The image is characterized by black edges and gray center, and the defects in the gray center are difficult to detect with the naked eye.

[0065] S12: Obtain the active area (AA) of the display screen image using an image segmentation method. The image segmentation method used in this step is a thresholding algorithm; preferably, a binary thresholding algorithm or an absolute thresholding algorithm is used. Please refer to [link to relevant documentation]. Figure 2 The segmented AA region is the internal area selected within the bounding box.

[0066] S13: Switch the display to a grayscale gradient image and acquire the image within the AA area as the grayscale gradient image. After extracting the AA area, display the image on the screen again as the grayscale gradient image. For details, please refer to [link to relevant documentation]. Figure 3 Then, extract the gradient image from the grayscale gradient screen, taking the same size as area AA. See [link to relevant documentation]. Figure 3 The selected area is shown in the image. The extracted grayscale gradient image can be found here. Figure 4 .

[0067] There are multiple methods for obtaining an image within the AA region as a grayscale gradient image. In this embodiment, one feasible method for obtaining a grayscale gradient image is disclosed: for example, firstly, the grayscale value of each pixel within the AA region of the grayscale gradient image is obtained in sequence, and then the obtained grayscale values ​​are filled into a blank image in sequence, with the starting coordinates being (0, 0), and the image size being consistent with the size of the AA region.

[0068] It is worth noting that, Figure 4 There are actually two black vertical lines indicating defects in the middle of the image. They are quite light in color and difficult to see with the naked eye. Please refer to [link / reference needed] for their exact location. Figure 4 The defect 001 is selected and marked with a wireframe in the image. The following section uses a combination of second-order surface fitting and the difference image method to extract the defect 001.

[0069] S2: First, calculate the grayscale moment value and grayscale approximation parameters of the grayscale gradient image using a second-order surface algorithm. The second-order surface algorithm achieves this by minimizing the distance between the grayscale value and the surface. The formula for the second-order surface algorithm is: Image(r, c) = Alpha(rr) center ) 2 +Beta(cc center ) 2 +Gamma(rr center )*(cc center )+Delta(rr center )+Epsilon(cc center )+Zeta

[0070] Where, r center and c center The center coordinates of the intersection of the AA region and the grayscale gradient image are used. The grayscale gradient image to be detected, ImageCrop, is processed using the standard "least squares" fitting method. Six fitting coefficients are calculated from AIpha (second-order coefficients in the vertical direction), Beta (second-order coefficients in the horizontal direction), Gamma (mixed second-order coefficients), Delta (first-order coefficients in the vertical direction), Epsilon (first-order coefficients in the horizontal direction), to Zeta (zero-order coefficients). In this embodiment, the six parameters of the second-order surface of the grayscale gradient image are: -1.29856e-06, 1.98322e-05, -1.65855e-07, -0.000410087, -0.0588273, 45.3191.

[0071] S3: Then, a flawless gradient image is generated by fitting the grayscale value moment value and the grayscale value approximation parameter.

[0072] A flawless gradient image is generated by fitting a grayscale surface using the moments calculated by S2 and six fitting parameters. Defects in the generated fitted image will disappear, resulting in a flawless gradient image whose size and grayscale values ​​match the grayscale gradient image. Please refer to [link to documentation]. Figure 5 The specific algorithm is as follows:

[0073] ImageSurface(r, c)

[0074] =Alpha(r-Row) 2 +Beta(c-Column) 2 +Gamma(r-Row)

[0075] *(c-Column)+Delta(r-Row)+Epsilon(c-Column)

[0076] +Zeta

[0077] Here, the parameters Row and Column are the reference points for creating the flawless gradient image. They are kept consistent with grayscale gradient images, i.e., the image center coordinates, and the grayscale value type is also consistent with ImageCrop, which is Byte type here.

[0078] S4: Subtract the flawless gradient image and the grayscale gradient image to obtain the difference image.

[0079] The grayscale values ​​of each corresponding pixel in the fitted flawless gradient image and the original grayscale gradient image are subtracted: ImageSub = (ImageSurface - ImageCrop) to obtain... Figure 6 The image shows some poor darkening defects 001, and the location of defect 001 is outlined with a dashed line.

[0080] S5: Finally, identification and labeling are performed. Thresholding is applied to the difference image to obtain the dark area defect image. Defects in the dark area defect image are extracted and labeled. The specific identification and labeling method is as follows:

[0081] S51: Use dynamic threshold segmentation based on local mean and variance or absolute threshold segmentation to segment regions with gray values ​​greater than the set standard gray value.

[0082] This embodiment uses a dynamic threshold segmentation method to extract relatively dark defects. The specific operation is as follows:

[0083] A mask of size W (width) * L (length) is used to navigate within the image. In this embodiment, the resolution of the AA area of ​​the image is relatively large, which is 3288*1974 pixels. Therefore, a mask of 100*100 pixels is used.

[0084] During the walk, the grayscale value of the current image pixel is compared with the average grayscale value of the mask. When the grayscale value of the current image pixel is lower than the average grayscale value of the corresponding mask by (StdDevScale, AbsThreshold) grayscale levels, the current image pixel is determined to be a defective pixel. Here, StdDevScale is the standard deviation multiplier factor, and AbsThreshold is the set absolute threshold.

[0085] By combining and displaying all defective pixels, a poor image of dark areas can be obtained. Please refer to [link / reference]. Figure 7 It can see the distribution and shape of all the darker pixels, among which the two vertical lines selected by the box are more obviously found to be defects 001.

[0086] S52: The segmented dark area defect image is then filtered based on pixel area size, shape similarity (rectangle similarity is used in this embodiment), length and width, etc., to finally obtain the defects in the gradient image. The defective vertical line defect 001 is marked in the difference image. Please refer to [link to relevant documentation]. Figure 8 .

[0087] S52: Finally, replicate the marked points onto the grayscale gradient image screen and display them. Please refer to [link / reference]. Figure 10 The test results are clearly labeled, making it easy for operators to carry out procedures such as random sampling and retesting.

[0088] The screen gradient defect detection method in this embodiment can quickly and accurately detect screen defects that are not easily detected by the naked eye and screen gradient defects that are not easily detected by machines, and are often missed or falsely detected.

[0089] Example 2

[0090] Please see Figure 11 This embodiment provides a screen defect detection device 100 based on a second-order surface fitting method. The screen gradient defect detection device utilizes some or all of the screen gradient defect detection methods in the first embodiment to detect screen gradient defects. It can be applied to automatic optical inspection devices. The screen gradient defect detection device includes:

[0091] Image acquisition unit 110 is used to acquire a grayscale gradient image with screen gradient defects;

[0092] Image fitting unit 120 is used to calculate the grayscale moment value and grayscale approximation parameter of the grayscale gradient image using a second-order surface algorithm; and to generate a flawless gradient image based on the grayscale moment value and grayscale approximation parameter.

[0093] The difference image generation unit 130 is used to subtract the flawless gradient image and the grayscale gradient image to obtain the difference image;

[0094] The defect detection unit 140 performs threshold segmentation on the difference image to obtain a dark area defect image; extracts and marks the defects in the dark area defect image, and displays the marked points on a grayscale gradient image.

[0095] Example 3

[0096] This embodiment provides a screen defect detection device based on a second-order surface fitting method. The screen gradient defect detection device includes:

[0097] At least one processor; and,

[0098] A memory that is communicatively connected to at least one processor; wherein,

[0099] The memory stores instructions that can be executed by at least one processor, which enables the at least one processor to perform some or all of the steps of the screen gradient defect detection method in the first embodiment.

[0100] This embodiment also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements some or all of the steps of the method of the first embodiment.

[0101] In summary, this embodiment uses a second-order surface fitting algorithm to generate a flawless gradient image that matches the size and grayscale of the grayscale gradient image. Then, the flawless gradient image and the grayscale gradient image are subtracted to obtain a difference image. Next, defects in dark areas are extracted from the difference image, and gradient defects are selected from these dark areas and marked on the grayscale gradient image. These gradient defect features are clear and obvious, enabling automated detection of display screens. This significantly reduces the occurrence of low detection rates, missed detections, and high false detection rates caused by small differences in gradient images and human eye fatigue, thereby improving the efficiency and accuracy of screen defect detection equipment. This detection method can be applied to production lines for large-scale, continuous inspection, ensuring and expanding the quality of shipped screens.

[0102] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0103] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods 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. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices or units, or may be electrical, mechanical or other forms of connection.

[0104] The units described as separate components may or may not be physically separate. As will be appreciated by those skilled in the art, the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0105] Furthermore, the functional units in the various embodiments of the present invention 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.

[0106] 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 medium. Based on this understanding, the technical solution of the present invention, 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 storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or grid device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0107] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A screen defect detection method based on second-order surface fitting, characterized in that, Includes the following steps: Acquire the grayscale gradient image to be detected; The grayscale moment value and grayscale approximation parameter of the grayscale gradient image are calculated using a second-order surface algorithm. A flawless gradient image is generated by fitting the grayscale value moment value and the grayscale value approximation parameter; The difference between the flawless gradient image and the grayscale gradient image is used to obtain the difference image; The difference image is thresholded to obtain a dark area defect image, and the defects in the dark area defect image are extracted and marked. The threshold segmentation is a threshold segmentation method based on local mean and variance; The method for acquiring poor images of dark areas includes: A mask of a set size is used to navigate within the difference image; The grayscale value of the current image pixel is compared with the grayscale mean of the mask. When the grayscale value of the image pixel is lower than the grayscale mean of the corresponding mask by a preset number of grayscale levels, the current image pixel is determined to be a defective pixel. The preset value is related to StdDevScale and AbsThreshold, where StdDevScale is the standard deviation multiplier factor and AbsThreshold is the set absolute threshold. Collect and display all defective pixels to obtain the defective image of the dark area; The process of extracting and marking defects in dark-area poor images includes the following steps: Defects are filtered out by one or more of the following criteria: pixel area size, shape similarity, length and width. The defect is marked in the difference image; The marked points are replicated onto the grayscale gradient image and displayed.

2. The screen defect detection method based on second-order surface fitting according to claim 1, characterized in that, The step of acquiring the grayscale gradient image to be detected includes: Turn on the display screen and acquire an image of the display screen with a grayscale value greater than 150 gray levels; The AA region of the display screen image is obtained using an image segmentation method; The display screen is switched to a grayscale gradient image, and the image within the AA area is obtained as the grayscale gradient image.

3. The screen defect detection method based on second-order surface fitting according to claim 2, characterized in that, The second-order surface algorithm is as follows: in, and Let be the center coordinates of the intersection of the AA region and the grayscale gradient image, where Alpha is the second-order coefficient in the vertical direction, Beta is the second-order coefficient in the horizontal direction, Gamma is the mixed second-order coefficient, Delta is the first-order coefficient in the vertical direction, Epsilon is the first-order coefficient in the horizontal direction, and Zeta is the zero-order coefficient.

4. The screen defect detection method based on second-order surface fitting according to claim 1, characterized in that, The algorithm for generating a flawless gradient image by fitting the grayscale value moments and the grayscale value approximation parameters includes: Wherein, the parameters Row and Column are the reference points for creating the flawless gradient image; Row and Column include the image center coordinates, Alpha is the second-order coefficient in the vertical direction, Beta is the second-order coefficient in the horizontal direction, Gamma is the mixed second-order coefficient, Delta is the first-order coefficient in the vertical direction, Epsilon is the first-order coefficient in the horizontal direction, and Zeta is the zero-order coefficient.

5. The screen defect detection method based on second-order surface fitting according to claim 1, characterized in that, The method for obtaining the difference image includes subtracting the grayscale value of each corresponding pixel in the flawless gradient image and the grayscale gradient image.

6. A detection device for implementing the screen defect detection method based on second-order surface fitting as described in claim 1, characterized in that, The detection device includes: Image acquisition unit, used to acquire grayscale gradient images with screen gradient defects; The image fitting unit is used to calculate the grayscale moment value and grayscale approximation parameter of the grayscale gradient image using a second-order surface algorithm. A flawless gradient image is generated by fitting the grayscale value moment value and the grayscale value approximation parameter; The difference image generation unit is used to subtract the flawless gradient image and the grayscale gradient image to obtain a difference image; The defect detection unit performs threshold segmentation on the image difference to obtain a defective image of the dark area; Defects in dark areas of the poor image are extracted and marked, and the marked points are displayed on the grayscale gradient image.

7. A screen defect detection device based on a second-order surface fitting method, characterized in that, The screen defect detection device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the steps of the screen defect detection method according to any one of claims 1 to 5.

Images