Defect detection method and device based on dynamic double-threshold template and storage medium

Abstract

The application discloses a defect detection method and device based on a dynamic double-threshold template and a storage medium, and is used for improving the defect detection precision of a display screen photographed image. A plurality of batches of defect-free sample images of a target model display screen are collected. The gray extreme boundary data of each pixel point on the plurality of batches of defect-free sample images is counted; and a lower limit standard template and an upper limit standard template are generated according to the gray extreme boundary data. A regional difference amplification coefficient and a compensation offset are obtained. The dynamic detection threshold template is generated by the regional difference amplification coefficient and the compensation offset on the lower limit standard template and the upper limit standard template. The image of the to-be-tested screen body of the target model display screen is obtained. The to-be-tested screen body image is subjected to pixel-level difference with the dynamic detection threshold template, and a defect mask image is generated. The defect detection of the display screen is carried out through the defect mask image, and a first defect detection result is generated.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of display screen detection, and in particular to a defect detection method and device based on a dynamic double-threshold template and a storage medium. BACKGROUND

[0002] In the automatic optical detection method of surface defects of a display panel (such as an OLED, a Micro-LED, or an LCD), the display panel body gray scale may be unevenly distributed. Therefore, when detecting surface defects of the display panel, the prior art usually collects a plurality of captured images in batches to obtain a plurality of gray scale values of each pixel point, sorts the plurality of gray scale values of the same pixel point from small to large, takes the average value and the median value as the gray scale value of the point on a standard template Golden image, ignores the inherent gray scale difference (such as edge attenuation and non-uniform backlight) of different display areas of the display panel, directly performs difference between a to-be-detected image and the standard template Golden image, and then uses a full threshold to detect. The global fixed difference threshold leads to over-detection (such as misjudgment of bright spots as defects) in a high dynamic range or missed detection (such as fine scratches in a dark area) in a low contrast area.

[0003] Nowadays, new display screens are constantly updated and iterated, and the structure of the display screen and the pixel points are increasingly precise. The traditional gray scale uneven distribution processing method is obviously insufficient, especially for new display screens such as folding screens, spliced screens, display screens containing microcircuit modules, and quantum dot electroluminescent display screens QLED, etc. The traditional method cannot adapt to the gray scale baseline fluctuation of different specific display areas of the new display panel, such as edge brightness attenuation and non-uniform center area. At the same time, the median value and the average value obtained by sorting the gray scale will eliminate the area characteristics, leading to misjudgment in a high dynamic range, which is easy to cause over-detection and missed detection of defects, and reduces the defect detection precision of the captured image of the display screen. SUMMARY

[0004] The present application discloses a defect detection method and device based on a dynamic double-threshold template and a storage medium, for improving the defect detection precision of the captured image of the display screen.

[0005] In a first aspect, embodiments of the present application provide a defect detection method based on a dynamic double-threshold template, comprising:

[0006] Collecting a plurality of batches of defect-free sample images of a target model display screen; counting the gray scale extreme boundary data of each pixel point on the plurality of batches of defect-free sample images; generating a lower limit standard template and an upper limit standard template according to the gray scale extreme boundary data; obtaining a regional difference amplification coefficient and a compensation offset; generating a dynamic detection threshold template for the lower limit standard template and the upper limit standard template through the regional difference amplification coefficient and the compensation offset; obtaining a to-be-tested screen body image of the target model display screen; performing pixel-level difference between the to-be-tested screen body image and the dynamic detection threshold template to generate a defect mask image; and performing defect detection on the display screen through the defect mask image to generate a first defect detection result.

[0007] Optionally, the regional difference amplification coefficient includes an upper limit regional difference amplification coefficient and a lower limit regional difference amplification coefficient, the compensation offset includes an upper limit compensation offset and a lower limit compensation offset, and the dynamic detection threshold template includes a bright defect dynamic detection threshold template and a dark defect dynamic detection threshold template; the step of generating the dynamic detection threshold template for the lower limit standard template and the upper limit standard template through the regional difference amplification coefficient and the compensation offset includes: generating the bright defect dynamic detection threshold template through the upper limit regional difference amplification coefficient, the upper limit compensation offset, the lower limit standard template and the upper limit standard template; and generating the dark defect dynamic detection threshold template through the lower limit regional difference amplification coefficient, the lower limit compensation offset, the lower limit standard template and the upper limit standard template.

[0008] Optionally, the target model display screen is a quantum dot electroluminescent display screen; the step of obtaining the regional difference amplification coefficient and the compensation offset includes: determining the radial thickness distribution of the quantum dot electroluminescent display screen corresponding to each defect-free sample image; dividing each defect-free sample image into a high-thickness region and a low-thickness region according to the radial thickness distribution, the high-thickness region being a region with a radial thickness higher than an upper limit of a reference thickness range, and the low-thickness region being a region with a radial thickness higher than the upper limit of the reference thickness range; calculating the upper limit regional difference amplification coefficient and the upper limit compensation offset according to the gray scale data, the gray scale gradient data and the film reflectivity data of the high-thickness region; calculating the lower limit regional difference amplification coefficient and the lower limit compensation offset according to the gray scale data, the gray scale gradient data and the film reflectivity data of the low-thickness region; and performing average processing on the upper limit regional difference amplification coefficient, the upper limit compensation offset, the lower limit regional difference amplification coefficient and the lower limit compensation offset corresponding to each defect-free sample image.

[0009] Optionally, the defect mask image includes a bright defect mask image and a dark defect mask image; the step of performing pixel-level difference between the to-be-tested screen body image and the dynamic detection threshold template to generate the defect mask image includes: performing pixel-level difference between the to-be-tested screen body image and the bright defect dynamic detection threshold template to generate the bright defect mask image; and performing pixel-level difference between the to-be-tested screen body image and the dark defect dynamic detection threshold template to generate the dark defect mask image.

[0010] Optionally, after the step of generating the first defect detection result by defect detection of the display screen through the defect mask image, the defect detection method further comprises: performing connected component segmentation on the defect mask image to determine an abnormal region; determining a background region according to the abnormal region; performing gray difference degree analysis on the abnormal region and the background region, and performing threshold control processing of the defect to generate a second detection result; and performing defect integration analysis on the first defect detection result and the second detection result.

[0011] Optionally, the step of determining the background region according to the abnormal region comprises: determining a minimum inscribed circle radius of the abnormal region, performing inflation on the abnormal region with the radius of the inscribed circle to generate the background region; and when the background region contains other abnormal regions, removing the part of the background region intersecting with the other abnormal regions.

[0012] Optionally, the step of performing gray difference degree analysis on the abnormal region and the background region, and performing threshold control processing of the defect to generate a second detection result comprises: calculating a first gray mean value and a second gray mean value of the abnormal region and the background region; calculating a contrast attribute difference value of the defect according to the first gray mean value and the second gray mean value; and performing threshold control processing on the contrast attribute difference value to generate the second detection result.

[0013] Optionally, the step of generating the lower limit standard template and the upper limit standard template according to the gray extreme boundary data comprises: determining a boundary gray value of each pixel point according to the gray extreme boundary data and the boundary ratio; and generating the lower limit standard template and the upper limit standard template according to the boundary gray value of each pixel point.

[0014] In a second aspect, an embodiment of the present application provides a defect detection device based on a dynamic double-threshold template, comprising: a collection unit configured to collect a plurality of batches of defect-free sample images of a target model display screen; a statistical unit configured to count gray extreme boundary data of each pixel point on the plurality of batches of defect-free sample images; a first generation unit configured to generate a lower limit standard template and an upper limit standard template according to the gray extreme boundary data; a first acquisition unit configured to acquire a regional difference amplification coefficient and a compensation offset; a second generation unit configured to generate a dynamic detection threshold template by the regional difference amplification coefficient and the compensation offset on the lower limit standard template and the upper limit standard template; a second acquisition unit configured to acquire a to-be-tested screen body image of the target model display screen; a third generation unit configured to perform pixel-level difference on the to-be-tested screen body image and the dynamic detection threshold template to generate a defect mask image; and a fourth generation unit configured to generate a first defect detection result by defect detection of the display screen through the defect mask image.

[0015] Optionally, the area difference amplification coefficient comprises an upper limit area difference amplification coefficient and a lower limit area difference amplification coefficient, the compensation offset comprises an upper limit compensation offset and a lower limit compensation offset, and the dynamic detection threshold template comprises a bright defect dynamic detection threshold template and a dark defect dynamic detection threshold template; the second generation unit comprises: generating the bright defect dynamic detection threshold template by using the upper limit area difference amplification coefficient, the upper limit compensation offset, the lower limit standard template, and the upper limit standard template; and generating the dark defect dynamic detection threshold template by using the lower limit area difference amplification coefficient, the lower limit compensation offset, the lower limit standard template, and the upper limit standard template.

[0016] Optionally, the target model display screen is a quantum dot electroluminescent display screen; and the first acquisition unit specifically comprises: determining a radial thickness distribution of the quantum dot electroluminescent display screen corresponding to each defect-free sample image; dividing each defect-free sample image into a high-thickness area and a low-thickness area according to the radial thickness distribution, the high-thickness area being an area with a radial thickness higher than an upper limit of a reference thickness range, and the low-thickness area being an area with a radial thickness higher than the upper limit of the reference thickness range; calculating the upper limit area difference amplification coefficient and the upper limit compensation offset according to the gray data, the gray gradient data, and the film reflectivity data of the high-thickness area; calculating the lower limit area difference amplification coefficient and the lower limit compensation offset according to the gray data, the gray gradient data, and the film reflectivity data of the low-thickness area; and performing average processing on the upper limit area difference amplification coefficient, the upper limit compensation offset, the lower limit area difference amplification coefficient, and the lower limit compensation offset corresponding to each defect-free sample image.

[0017] Optionally, the defect mask image comprises a bright defect mask image and a dark defect mask image; and the third generation unit comprises: performing pixel-level difference between the to-be-tested screen body image and the bright defect dynamic detection threshold template to generate the bright defect mask image; and performing pixel-level difference between the to-be-tested screen body image and the dark defect dynamic detection threshold template to generate the dark defect mask image.

[0018] Optionally, after the fourth generation unit, the defect detection device further comprises: a first determination unit configured to perform connected domain segmentation on the defect mask image to determine an abnormal area; a second determination unit configured to determine a background area according to the abnormal area; a fifth generation unit configured to perform gray difference degree analysis on the abnormal area and the background area, and perform threshold control processing on the defects to generate a second detection result; and an analysis unit configured to perform defect integration analysis on the first defect detection result and the second detection result.

[0019] Optionally, the second determination unit comprises: determining a minimum inscribed circle radius of the abnormal area, and performing inflation on the abnormal area with the radius of the inscribed circle to generate the background area; and when the background area contains other abnormal areas, removing the part of the background area intersecting with the other abnormal areas.

[0020] Optionally, the fifth generating unit comprises: calculating a first gray mean value and a second gray mean value of the abnormal area and the background area; calculating a contrast attribute difference value of the defect according to the first gray mean value and the second gray mean value; performing threshold control processing on the contrast attribute difference value to generate a second detection result.

[0021] Optionally, the first generating unit comprises: determining a boundary gray value of each pixel point according to the gray extreme boundary data and the boundary proportion; and generating a lower limit standard template and an upper limit standard template according to the boundary gray value of each pixel point.

[0022] In a third aspect, an embodiment of the present application provides a defect detection device based on a dynamic double-threshold template, comprising:

[0023] a processor, a memory, an input / output unit and a bus;

[0024] the processor is connected with the memory, the input / output unit and the bus;

[0025] the memory stores a program, and the processor invokes the program to execute the defect detection method as in the first aspect and any optional defect detection method of the first aspect.

[0026] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium stores a program, and the program performs the defect detection method as in the first aspect and any optional defect detection method of the first aspect when executed on a computer.

[0027] As can be seen from the above technical solutions, the embodiments of the present application have the following advantages:

[0028] In the present application, first, a plurality of batches of defect-free sample images of a target model display screen are collected. The gray extreme boundary data of each pixel point on the plurality of batches of defect-free sample images is counted. A lower limit standard template and an upper limit standard template are generated according to the gray extreme boundary data. A region difference amplification coefficient and a compensation offset are obtained. The lower limit standard template and the upper limit standard template are generated into a dynamic detection threshold template through the region difference amplification coefficient and the compensation offset. An image of a to-be-tested screen body of the target model display screen is obtained. The image of the to-be-tested screen body is pixel-level differentiated with the dynamic detection threshold template to generate a defect mask image. The defect detection of the display screen is performed through the defect mask image to generate a first defect detection result.

[0029] By counting the gray scale extreme boundary data of each pixel point of the defect-free sample image of several batches, the allowed gray scale fluctuation range is established, and the nonlinear dynamic expansion is carried out, the corresponding lower limit standard template and upper limit standard template of the respective corresponding gray value difference characteristics are established, then the corresponding gray value difference is determined on the same pixel point according to the lower limit standard template and the upper limit standard template, the final dynamic detection threshold template is obtained through the area amplification coefficient and the compensation value offset, finally the surface abnormal area is obtained by using the image of the to-be-side screen body and the dynamic detection threshold template for difference, and the defect mask image is generated. At the same time, in the defect abnormal area generated after difference, the contrast parameter value of the defect abnormal area and the background area is compared and controlled, this method can well cope with the precision structure of the new display screen, detect the surface defect abnormal area, reduce the situation of eliminating the area characteristics, reduce the misjudgment of the high dynamic range area, avoid over-detection, missing detection and the like, and improve the defect detection precision of the display screen image. BRIEF DESCRIPTION OF DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0031] Figure 1 The first embodiment of the defect detection method based on dynamic double threshold template of the present application is a schematic diagram.

[0032] Figure 2 The first embodiment of the light source adjustment method of the imaging system of the present application is a schematic diagram.

[0033] Figure 3 The first embodiment of the method for generating area difference amplification coefficient and compensation offset of the present application is a schematic diagram.

[0034] Figure 4 The first embodiment of the method for generating defect mask image of the present application is a schematic diagram.

[0035] Figure 5 The first embodiment of the defect detection method of the present application is a schematic diagram.

[0036] Figure 6 The first embodiment of the method for determining the background area of the present application is a schematic diagram.

[0037] Figure 7 The first embodiment of the method for generating the second detection result of the present application is a schematic diagram.

[0038] Figure 8 Fig. 1 shows a schematic diagram of a first embodiment of a method for generating lower and upper standard templates for the present application;

[0039] Figure 9 Fig. 2 shows a schematic diagram of a first embodiment of a defect detection apparatus for the present application based on dynamic dual threshold templates;

[0040] Figure 10 Fig. 3 shows a schematic diagram of a second embodiment of a defect detection apparatus for the present application based on dynamic dual threshold templates. DETAILED DESCRIPTION

[0041] In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

[0042] It is to be understood that the terminology "includes", "has", "holds", "contains" and / or "comprising", when used in this specification and in the following claims, indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0043] It is also to be understood that the terminology "and / or" when used in this specification and in the following claims, refers to at least one of the items, or any combination of one or more of the items, and includes all possible combinations of one or more of the items.

[0044] As used in this specification and in the claims, the term "if" can be interpreted as meaning "when", or "once", or "in response to a determination", or "in response to detecting", as appropriate, depending on the context. Similarly, the phrase "if determined", or "if detected [the described condition or event]" can be interpreted as meaning "once determined", or "in response to a determination", or "once detected [the described condition or event]", or "in response to detecting [the described condition or event]", as appropriate, depending on the context.

[0045] In addition, in the description of the specification and in the claims of the present application, the terms "first", "second", "third", etc. are used only to distinguish descriptions, and cannot be understood as indicating or implying relative importance.

[0046] Reference within the specification of this application to "one embodiment" or "some embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. The appearances of the phrase "in one embodiment" or "in some embodiments" in various places within specifications are not necessarily all referring to the same embodiment, however, are meant to signify that a particular feature, structure, or characteristic being referred to is included in at least one embodiment of the application. The terms "including," "comprising," "having," and variations thereof are meant to encompass the terms "including but not limited to."

[0047] The different regions of the screen body have different inconsistencies, and the gray scale values at the same positions of the batch images cannot be directly used for sorting to obtain the median value and the average value as the pixel value of the point on the standard Golden image, and then the original image and the standard Golden image are directly differentiated to detect, and the gray scale value difference corresponding to the different regions of the screen body needs to be considered.

[0048] Nowadays, new display screens are constantly updated and iterated, and the display screen structure and pixel points are more and more precise. The traditional gray scale distribution uneven processing means is obviously insufficient, especially for new display screens such as folding screens, splicing screens, display screens containing microcircuit modules, and quantum dot electroluminescent display screens QLED, etc. The traditional method cannot adapt to the gray scale baseline fluctuation of different specific display regions of the new display panel, such as edge brightness attenuation, center area unevenness, etc. At the same time, the median value and the average value obtained by sorting the gray scale will eliminate the region characteristics, leading to misjudgment of the high dynamic range region, which is easy to cause defect over-checking, missing detection, etc., and reduces the defect detection precision of the display screen photographed image.

[0049] Based on this, the application discloses a defect detection method and device based on a dynamic double-threshold template and a storage medium, which are used to improve the defect detection precision of a display screen photographed image.

[0050] The technical solutions in the application will be described clearly and completely in the embodiments of the application combined with the drawings in the application. Obviously, the described embodiments are only some of the embodiments of the application, not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0051] The method of the application can be applied to a server, a device, a terminal or other devices with logical processing capability, and the application is not limited to this. For convenience of description, the following will be described taking the execution subject as a terminal as an example.

[0052] Please refer to Figure 1An embodiment of a defect detection method based on a dynamic double-threshold template is provided, including:

[0053] 101. Collecting a plurality of batches of defect-free sample images of a target display screen.

[0054] In this embodiment, the captured images of the target display screen are first obtained, and the defect-free images therein are used as samples. Specifically, before using a defect detection device to detect defects of a new display screen, a standard defect-free new display screen is first placed to collect images, and then the collected images are subjected to defect detection and image correction to obtain defect-free sample images without display screen defects, lens defects, and light source defects. A minimum of 50 batches of defect-free sample images are required.

[0055] 102. Statistically obtaining the gray value extreme boundary data of each pixel point on the plurality of batches of defect-free sample images.

[0056] 103. Generating a lower-limit standard template and an upper-limit standard template according to the gray value extreme boundary data.

[0057] Specifically, after the terminal obtains N batches of corrected defect-free sample images, the gray value of each pixel point of each image is obtained, that is, each point obtains a corresponding initial gray value set, and each point contains N pixel values. At this time, the terminal statistically obtains the gray value extreme boundary data of each pixel point on the N batches of defect-free sample images. Specifically, in order to prevent the influence of noise and stains on the image and ensure the authenticity of the creation of the Golden standard template image, the gray value extreme boundary data is calculated for each pixel point position (x, y) by statistically obtaining the gray value extreme of each pixel point of the N defect-free sample images. Then, the appropriate boundary gray value of the new display screen is selected according to the gray value extreme boundary data, and there are two boundary gray values, one is an upper-limit boundary gray value, and the other is a lower-limit boundary gray value. The lower-limit standard template and the upper-limit standard template are generated through the upper-limit boundary gray value and the lower-limit boundary gray value, and the effective area size of the lower-limit standard template and the upper-limit standard template is the same as the effective area size of the defect-free sample image.

[0058] 104. Obtaining a regional difference amplification coefficient and a compensation offset.

[0059] 105. Generating a dynamic detection threshold template for the lower-limit standard template and the upper-limit standard template through the regional difference amplification coefficient and the compensation offset.

[0060] In this embodiment, the terminal first needs to obtain the regional difference amplification coefficient and the compensation offset. Then, by using the differences in gold_max and gold_min at different positions in the lower limit standard template and the upper limit standard template, the allowable grayscale fluctuation range is established through the regional difference amplification coefficient and the compensation offset. At the same time, nonlinear dynamic expansion is performed to regenerate the dynamic detection threshold template.

[0061] The regional difference amplification factor is calculated using the display characteristics of specific regions of the novel display screen. Compared to conventional display screens, the novel display screen has different functional regions that often involve more complex usage conditions, such as the folding area of ​​a foldable screen, the splicing edge of a video wall, and the light conversion film structure of a quantum dot electroluminescent display, especially the light conversion film structure of a quantum dot electroluminescent display. These specific regions are called specific regions, and they typically require more complex defect detection to effectively detect novel defects in these special structures during use—something conventional detection methods cannot achieve. In this embodiment, the terminal calculates the regional difference amplification factor and compensation offset based on the display characteristics of the novel display screen in the specific regions. Then, it adjusts the lower and upper limit standard templates using the regional difference amplification factor and compensation offset to generate a dynamic detection threshold template. This dynamic detection threshold template improves the accuracy of subsequent defect detection in the specific regions of the novel display screen. The specific calculation method will be explained in detail later.

[0062] 106. Obtain the image of the screen to be tested for the target model display.

[0063] 107. Perform pixel-level difference between the image of the screen to be tested and the dynamic detection threshold template to generate a defect mask image.

[0064] The terminal acquires an image of the screen to be tested for the target model of the display. Then, it performs pixel-level difference analysis between the image of the screen to be tested and the dynamic detection threshold template to generate a defect mask image, that is, to generate a defect mask image capable of defect detection. This defect mask image can improve the detection effect and increase the contrast of the defect area for both screen defects and display defects on the new display.

[0065] 108. Perform defect detection on the display screen using the defect mask image and generate the first defect detection result.

[0066] Finally, the terminal can use conventional methods to perform defect detection on the display screen using the defect mask image, and generate the first defect detection result.

[0067] In this embodiment, first, a plurality of batches of defect-free sample images of a target model display screen are collected. The gray value extreme boundary data of each pixel point on the plurality of batches of defect-free sample images is counted. The lower limit standard template and the upper limit standard template are generated according to the gray value extreme boundary data. The regional difference amplification coefficient and the compensation offset are obtained. The dynamic detection threshold template is generated by the regional difference amplification coefficient and the compensation offset on the lower limit standard template and the upper limit standard template. The image of the to-be-tested screen body of the target model display screen is obtained. The pixel-level difference between the image of the to-be-tested screen body and the dynamic detection threshold template is performed to generate a defect mask image. The defect detection of the display screen is performed through the defect mask image to generate a first defect detection result.

[0068] By counting the gray value extreme boundary data of each pixel point of the plurality of batches of defect-free sample images, the allowed gray value fluctuation range is established, and the nonlinear dynamic expansion is performed. The corresponding lower limit standard template and the upper limit standard template are established for the respective corresponding gray value difference characteristics. Then, the corresponding gray value difference on the same pixel point is determined according to the lower limit standard template and the upper limit standard template. The final dynamic detection threshold template is obtained through the regional amplification coefficient and the compensation value offset. Finally, the surface abnormal area is obtained by performing the difference between the to-be-tested screen body image and the dynamic detection threshold template, and the defect mask image is generated. Meanwhile, the contrast parameter value of the defect abnormal area of the defect mask image generated after the difference is controlled. This method can well cope with the precision structure of the new display screen, detect the surface defect abnormal area, reduce the situation of eliminating the area characteristics, reduce the misjudgment of the high dynamic range area, avoid over-detection, missed detection, and the like, and improve the defect detection precision of the display screen image.

[0069] Referring to Figure 2 An embodiment of a method for generating a dynamic detection threshold template is provided in the present application, which comprises:

[0070] 201. Generate a bright defect dynamic detection threshold template through the upper limit regional difference amplification coefficient, the upper limit compensation offset, the lower limit standard template, and the upper limit standard template.

[0071] 202. Generate a dark defect dynamic detection threshold template through the lower limit regional difference amplification coefficient, the lower limit compensation offset, the lower limit standard template, and the upper limit standard template.

[0072] In this embodiment, the terminal generates a bright defect dynamic detection threshold template through the upper limit regional difference amplification coefficient, the upper limit compensation offset, the lower limit standard template, and the upper limit standard template, and the formula is as follows:

[0073] NewMaxGolden = MaxGolden + HighFactor(MaxGolden - MinGolden) + HighDelat

[0074] Next, the terminal generates a dark defect dynamic detection threshold template through the lower limit area difference amplification factor, the lower limit compensation offset, the lower limit standard template and the upper limit standard template, and the formula is as follows:

[0075] NewMinGolden = MinGolden - LowFactor * (MaxGolden - MinGolden) - LowDelat

[0076] Wherein, MaxGolden is the upper limit standard template, which can also be written as MaxGolden(x, y), (x, y) represents the corresponding pixel point position, MinGolden is the lower limit standard template. LowFactor and HighFactor are the lower limit area difference amplification factor and the upper limit area difference amplification factor of each pixel point area respectively, and LowDelat and HighDelat are the lower limit compensation offset and the upper limit compensation offset corresponding to the gray value respectively.

[0077] Please refer to Figure 3 , the target model display screen is a quantum dot electroluminescent display screen, and an embodiment of a method for generating area difference amplification factor and compensation offset is provided, which comprises:

[0078] 301. Determine the radial thickness distribution of the quantum dot electroluminescent display screen corresponding to each defect-free sample image;

[0079] In this embodiment, the preparation method of the quantum dot electroluminescent display screen (Quantum Dot Light-Emitting Diode, QLED). It is essentially to use the quantum dot material prepared in advance as the material of the light conversion film, and place it between the blue LED backlight and the front liquid crystal layer through a specific way. The quantum dot film is excited by the blue backlight, thereby emitting pure red light and green light, which is mixed with the remaining blue light to obtain high-quality white light, and then controlled by the liquid crystal pixels. It does not emit light itself.

[0080] The quantum dot electroluminescent display screen QLED in this embodiment actively emits light under the direct current driving of the quantum dot material of each pixel. This is similar to the working principle of traditional OLED, which uses quantum dots to replace the traditional light-emitting layer. A standard quantum dot electroluminescent display screen QLED adopts a "sandwich" structure, which is similar to OLED. The quantum dot electroluminescent display screen QLED mainly includes an anode, a hole transport layer, a quantum dot light-emitting layer, an electron transport layer and a cathode.

[0081] Wherein, the quantum dot light-emitting layer is the core layer of the quantum dot electroluminescent display QLED, which is composed of red, green and blue quantum dot materials. Under the action of an electric field, electrons and holes recombine in this layer to emit light of a specific color. The preparation of quantum dot electroluminescent display QLED combines the device physics of OLED and the material science of quantum dots. The core difficulty is how to accurately and non-destructively integrate the quantum dots, which are extremely sensitive to water and oxygen and whose performance is easily damaged, into a multi-layer thin film device.

[0082] In the prior art, quantum dot electroluminescent display QLED is usually prepared using quantum dot ink. First, the synthesized quantum dot particles are separated from the original solvent and dispersed in a solvent with suitable physical properties (such as boiling point, surface tension, and viscosity) to form "quantum dot ink". Then, film formation is carried out by inkjet printing. Specifically, on a substrate with prepared TFT circuit and electrode (anode), pixel pits are prepared by photolithography process, and then red, green and blue quantum dot inks are accurately sprayed into the corresponding pixel pits by high-precision inkjet printing equipment. Finally, through annealing (heating), the solvent is volatilized, leaving a uniform and flat quantum dot film. However, in the prior art, the evaporation speed of the ink is faster at the edge than at the center during drying, which can cause the quantum dot particles to gather at the edge due to the action of tension, forming a ring-shaped uneven film that is thin in the middle and thick at the edge. Even by adjusting the solvent and evaporation speed, there will still be a small amount of ring-shaped uneven film.

[0083] Such ring-shaped uneven film can affect the uniformity of light emission, making it difficult for the upper and lower limit standard templates to capture bright and dark defects when detecting defects in the image of the quantum dot electroluminescent display, thereby reducing the defect detection accuracy of the image of the quantum dot electroluminescent display.

[0084] Therefore, in this embodiment, a method for generating dynamic detection threshold templates is proposed, which adjusts the upper and lower limit standard templates using a defect-free sample image of the quantum dot electroluminescent display. Specifically, according to the radial thickness distribution in the defect-free sample image of the quantum dot electroluminescent display, the display screen reflection area affected by different thicknesses is separated by radial thickness, and then the difference amplification coefficient and compensation offset of the upper and lower limit standard templates are calculated according to the reflectivity, gray gradient and other data of the display screen reflection area.

[0085] Specifically, the terminal first determines the radial thickness distribution of the quantum dot electroluminescent display screen corresponding to each defect-free sample image. The interference effect of light reflection at the film interface can be used to analyze the reflection spectrum or the change in polarization state to obtain the film thickness distribution. It can also be an X-ray reflectometer and a white light interferometer, which is not limited here.

[0086] 302、According to the radial thickness distribution, each defect-free sample image is divided into a high-thickness area and a low-thickness area. The high-thickness area is an area with a radial thickness higher than the upper limit of the reference thickness range, and the low-thickness area is an area with a radial thickness higher than the upper limit of the reference thickness range.

[0087] Next, the terminal divides each defect-free sample image into a high-thickness area and a low-thickness area according to the radial thickness distribution. The high-thickness area is an area with a radial thickness higher than the upper limit of the reference thickness range, and the low-thickness area is an area with a radial thickness higher than the upper limit of the reference thickness range. In the preparation process of the quantum dot electroluminescent display screen, the optimal thickness of different sizes of display screens is different. Usually, a reference thickness range is generated around the optimal thickness. The area within the reference thickness range is a transition area. The upper limit standard template and the lower limit standard template can be used in the transition area, or the upper limit standard template and the lower limit standard template can be used without adjustment, because the defects in the transition area are less affected by the annular uneven film. The radial thickness affects the detection of defects by affecting the reflectivity, and the size of the gray scale gradient of the high-thickness area (usually the area of the outer circle) and the low-thickness area (usually the area of the central circle or ellipse) also affects the performance of the defect feature. Therefore, in this embodiment, a quantum dot electroluminescent display screen without serious uneven film is used, i.e. a quantum dot electroluminescent display screen with moderate uniformity. The corresponding defect-free sample images of this type of quantum dot electroluminescent display screen are obtained, and then each defect-free sample image is divided into a high-thickness area and a low-thickness area according to the radial thickness distribution.

[0088] 303、According to the gray scale data, gray scale gradient data and film reflectivity data of the high-thickness area, calculate the upper limit area difference amplification coefficient and the upper limit compensation offset;

[0089] 304、According to the gray scale data, gray scale gradient data and film reflectivity data of the low-thickness area, calculate the lower limit area difference amplification coefficient and the lower limit compensation offset;

[0090] The terminal calculates the upper limit area difference amplification factor and the upper limit compensation offset according to the gray data, the gray gradient data and the film reflectivity data of the high thickness area, and calculates the lower limit area difference amplification factor and the lower limit compensation offset according to the gray data, the gray gradient data and the film reflectivity data of the low thickness area. The upper limit area difference amplification factor is for bright defects, the lower limit area difference amplification factor is for dark defects, the amplification factor of the upper limit standard template is generated using the gray data of the high thickness area and the reflectivity and other parameters in the uneven film, and the amplification factor of the lower limit standard template is generated using the gray data of the low thickness area and the reflectivity and other parameters in the uneven film. The formula is as follows:

[0091]

[0092]

[0093] wherein HighFactor is the upper limit area difference amplification factor, LowFactor is the lower limit area difference amplification factor, is the average reflectivity of the film in the reference thickness range (i.e. the transition area), is the average reflectivity of the film in the high thickness area, is the average reflectivity of the film in the low thickness area, is the maximum pixel value in the high thickness area, is the minimum pixel value in the high thickness area, is the maximum pixel value in the low thickness area, is the minimum pixel value in the low thickness area, it should be noted that, , , and all need to remove abnormal extreme values before obtaining the maximum value and the minimum value in the remaining pixel values, is the weighted reference gradient of the transition area, is the weighted gray gradient of the high thickness area, is the weighted gray gradient of the low thickness area, is the gray mean value of the high thickness area, is the gray mean value of the low thickness area. is the contrast amplification term of the high thickness area, is the contrast amplification term of the low thickness area, is the sharpness amplification term.

[0094]

[0095]

[0096]

[0097] wherein, and are horizontal and vertical gradient weighting values, respectively, which are usually generated using horizontal and vertical dimensions (or resolutions) of the quantum dot electroluminescent display, and are average horizontal and vertical gradients in the transition region, respectively, and are average horizontal and vertical gradients in the high-thickness region, respectively, and are average horizontal and vertical gradients in the low-thickness region, respectively. The use of the gradients and reflectivity in the contrast amplification term, and the use of the sharpness amplification term, can better adjust the lower limit standard template and the upper limit standard template to generate the bright defect dynamic detection threshold template and the dark defect dynamic detection threshold template. In addition to the need for a region difference amplification coefficient to adjust the lower limit standard template and the upper limit standard template as a whole, an appropriate compensation amount needs to be generated to reduce the difference between the extreme boundaries of the lower limit standard template and the upper limit standard template.

[0098] The calculation formulas of the upper limit compensation offset HighDelta and the lower limit compensation offset LowDelta are as follows:

[0099]

[0100]

[0101] HighDelta and LowDelta are the upper limit compensation offset and the lower limit compensation offset corresponding to the gray value, respectively, and are compensation intensity coefficients of the high-thickness region and the low-thickness region, respectively. This parameter is artificially set as a constant according to experience, and is intended to adjust the boundary extreme offset of the standard template, and are standard deviations of the high-thickness region and the low-thickness region, respectively.

[0102]

[0103]

[0104] wherein, and are the number of pixel points in the high-thickness region and the number of pixel points in the low-thickness region, respectively, is the high-thickness region, is the low-thickness region, is the gray value of the i-th pixel point in the high-thickness region, Let be the grayscale value of the j-th pixel in the high-thickness region. It should be noted that here, extremely high grayscale values ​​in the high-thickness region need to be filtered out first, and extremely low grayscale values ​​in the low-thickness region need to be filtered out first. The upper limit compensation offset and lower limit compensation offset need to be calculated based on the degree of offset between the overall pixel value and the mean to determine the deviation of the boundary extreme value.

[0105] The upper and lower compensation offsets calculated using the above formulas are used to calculate the extreme value deviation for each pixel in the high and low thickness regions. The resulting upper and lower compensation offsets can eliminate the overall deviation between the lower and upper standard templates.

[0106] 305. Average the upper limit regional difference magnification factor, upper limit compensation offset, lower limit regional difference magnification factor, and lower limit compensation offset corresponding to each defect-free sample image.

[0107] The terminal can average the upper limit region difference amplification factor, upper limit compensation offset, lower limit region difference amplification factor, and lower limit compensation offset corresponding to each defect-free sample image to handle situations where high precision is not required. If higher precision is required, the upper limit region difference amplification factor, upper limit compensation offset, lower limit region difference amplification factor, and lower limit compensation offset need to be determined based on the radial thickness distribution of the screen image under test to improve the accuracy of subsequent generation of bright defect dynamic detection threshold templates and dark defect dynamic detection threshold templates.

[0108] Please see Figure 4 This application provides an embodiment of a method for generating a defect mask image, comprising:

[0109] 401. Perform pixel-level difference between the image of the screen to be tested and the dynamic detection threshold template for bright defects to generate a bright defect mask image.

[0110] 402. Perform pixel-level difference between the image of the screen to be tested and the dynamic detection threshold template for dark defects to generate a dark defect mask image.

[0111] In this embodiment, the screen image under test undergoes pixel-level differential detection. The terminal performs pixel-level differential detection between the screen image under test and the bright defect dynamic detection threshold template to generate a bright defect mask image. Each time the camera captures an image, it first acquires the screen area, then performs correction, and finally performs pixel-level differential detection between the corrected image Image(x, y) and the created NewMinGolden and NewMaxGolden. When detecting bright defects, the corresponding differential image (bright defect mask image) is HighDefectMask(x, y), as shown in the following formula:

[0112] HighDefectMask(x, y) = I(x, y) - NewMaxGolden(x, y)

[0113] And when detecting dark defects, the image to be tested is pixel-level different from the dark defect dynamic detection threshold template to generate a dark defect mask image. The corresponding difference image (dark defect mask image) is LowDefectMask(x, y), and the formula is as follows:

[0114] LowDefectMask(x, y) = NewMinGolden(x, y) - Image(x, y)

[0115] Please refer to Figure 5 An embodiment of the defect detection method provided in the present application comprises the following steps.

[0116] 501. Perform connected domain segmentation on the defect mask image to determine an abnormal area.

[0117] 502. Determine a background area according to the abnormal area.

[0118] 503. Perform gray difference degree analysis on the abnormal area and the background area, and perform threshold control processing on the defects to generate a second detection result.

[0119] 504. Perform defect integration analysis on the first defect detection result and the second detection result.

[0120] In order to further verify whether the defect is a real defect, the terminal needs to perform connected domain segmentation on the defect mask image to determine an abnormal area. Then, a background area is determined according to the position and size of the abnormal area. The abnormal area and the background area are subjected to gray difference degree analysis, and threshold control processing is performed on the defects to generate a second detection result. Finally, defect integration analysis is performed on the first defect detection result and the second detection result.

[0121] Specifically, the difference result image HighDefectMask (light defect mask image) and LowDefectMask (dark defect mask image) are subjected to connected domain segmentation. Then, the ratio of the local average gray of the abnormal area to the background average gray is calculated. According to the size of the value, the difference degree of the defect and the background is further determined, and the defect is controlled.

[0122] The specific way of determining the abnormal area is described in subsequent embodiments. The specific way of performing gray difference degree analysis on the abnormal area and the background area and performing threshold control processing on the defects to generate a second detection result is described in detail in subsequent embodiments.

[0123] Please refer to Figure 6An embodiment of a method for determining a background region provided by the present application includes the following steps:

[0124] 601. Determine the minimum inscribed circle radius of the abnormal region, and expand the abnormal region by the radius of the inscribed circle to generate a background region.

[0125] 602. When the background region contains other abnormal regions, remove the part of the background region that intersects with the other abnormal regions.

[0126] In this embodiment, the terminal uses the radius of the minimum inscribed circle of the defect region as the reference for the size of the background region, and then expands the defect region by the radius of the inscribed circle, i.e., the background region is the region after the expansion of the defect. If the expanded region contains other defect regions, the intersecting defects need to be removed.

[0127] Please refer to Figure 7 An embodiment of a method for generating a second detection result provided by the present application includes the following steps:

[0128] 701. Calculate the first and second gray mean values of the abnormal region and the background region.

[0129] 702. Calculate the contrast attribute difference value of the defect according to the first and second gray mean values.

[0130] 703. Perform threshold control processing on the contrast attribute difference value to generate a second detection result.

[0131] In this embodiment, the terminal first calculates the first and second gray mean values of the abnormal region and the background region, calculates the average gray values of the defect region (abnormal region) and the expanded region (background region) respectively, and records them as Mean and BackMean. The formula for calculating the contrast attribute difference value (Contrast value) of the defect is as follows:

[0132] Contrast = |Mean-BackMean| / (BackMean+Bias)

[0133] Where Bias = 0.0001. The larger the Contrast value, the more obvious the difference of the defect, and the greater the difference with the background. The region with Contrast > T is retained as the final defect, where T is the defect control value preset for the panel type. Finally, the terminal performs threshold control processing on the contrast attribute difference value to generate a second detection result.

[0134] Please refer to Figure 8 An embodiment of a method for generating a lower limit standard template and an upper limit standard template provided by the present application includes the following steps:

[0135] 801、determining the boundary gray value of each pixel point according to the gray value boundary data and the boundary proportion.

[0136] 802、generating the lower limit standard template and the upper limit standard template according to the boundary gray value of each pixel point.

[0137] In this embodiment, the terminal calculates the gray value boundary data of each pixel point (x, y) by counting the gray value extreme of each pixel point of N defect-free sample images, can select the front and rear 10% of the gray value of the pixel point in the batch data as the gray value boundary data, and then generates the lower limit standard template and the upper limit standard template according to the boundary gray value of each pixel point. For example, there are 50 batches (N=50), first sort the 50 gray values of the same point (such as point (1, 1)) from small to large, take the 5th (5=50*10%) value gold_min as the gray value of the point (point (1, 1)) on the MinGolden image (lower limit standard template), and take the 46th value gold_max as the gray value of the point (point (1, 1)) on the MaxGolden image (upper limit standard template). In this way, the corresponding proportion of gold_min value and gold_max value of all points is generated to generate the lower limit standard template and the upper limit standard template, wherein the proportion is obtained by previously collecting images and detecting a new display screen, counting the extreme value of the pixel points in the specific area of the image (because the specific area is more likely to cause extreme points, if there is no specific area, the conventional central area and / or edge area is directly used), detecting the proportion of extreme points, and using the proportion as the boundary proportion.

[0138] Please refer to Figure 9 An embodiment of a defect detection device based on a dynamic double-threshold template is provided in the present application, comprising:

[0139] The acquisition unit 901 is configured to acquire a plurality of batches of defect-free sample images of a target model display screen.

[0140] The statistical unit 902 is configured to count the gray value boundary data of each pixel point on the plurality of batches of defect-free sample images.

[0141] The first generation unit 903 is configured to generate the lower limit standard template and the upper limit standard template according to the gray value boundary data.

[0142] Optionally, the first generation unit 903 comprises:

[0143] determining the boundary gray value of each pixel point according to the gray value boundary data and the boundary proportion.

[0144] The lower limit standard template and the upper limit standard template are generated according to the boundary gray value of each pixel point.

[0145] The first acquisition unit 904 is configured to acquire the area difference amplification coefficient and the compensation offset.

[0146] Optionally, the target model display screen is a quantum dot electroluminescent display screen.

[0147] The first acquisition unit 904 specifically includes:

[0148] The radial thickness distribution of the quantum dot electroluminescent display screen corresponding to each defect-free sample image is determined.

[0149] According to the radial thickness distribution, each defect-free sample image is divided into a high-thickness area and a low-thickness area. The high-thickness area is an area with a radial thickness higher than the upper limit of the reference thickness range, and the low-thickness area is an area with a radial thickness higher than the upper limit of the reference thickness range.

[0150] The upper limit area difference amplification coefficient and the upper limit compensation offset are calculated according to the gray data, the gray gradient data, and the film reflectivity data of the high-thickness area.

[0151] The lower limit area difference amplification coefficient and the lower limit compensation offset are calculated according to the gray data, the gray gradient data, and the film reflectivity data of the low-thickness area.

[0152] The upper limit area difference amplification coefficient, the upper limit compensation offset, the lower limit area difference amplification coefficient, and the lower limit compensation offset corresponding to each defect-free sample image are averaged.

[0153] The second generation unit 905 is configured to generate a dynamic detection threshold template for the lower limit standard template and the upper limit standard template by using the area difference amplification coefficient and the compensation offset.

[0154] The second acquisition unit 906 is configured to acquire a to-be-tested screen body image of the target model display screen.

[0155] Optionally, the area difference amplification coefficient includes the upper limit area difference amplification coefficient and the lower limit area difference amplification coefficient, the compensation offset includes the upper limit compensation offset and the lower limit compensation offset, and the dynamic detection threshold template includes a bright defect dynamic detection threshold template and a dark defect dynamic detection threshold template.

[0156] The second generation unit 906 includes:

[0157] The bright defect dynamic detection threshold template is generated by using the upper limit area difference amplification coefficient, the upper limit compensation offset, the lower limit standard template, and the upper limit standard template.

[0158] The dark defect dynamic detection threshold template is generated through a lower limit area difference amplification coefficient, a lower limit compensation offset, a lower limit standard template, and an upper limit standard template.

[0159] The third generation unit 907 is configured to perform pixel-level difference between the to-be-tested screen body image and the dynamic detection threshold template to generate a defect mask image.

[0160] Optionally, the defect mask image includes a bright defect mask image and a dark defect mask image.

[0161] The third generation unit 907 includes:

[0162] The third generation unit 907 includes:

[0163] The third generation unit 907 includes:

[0164] The fourth generation unit 908 is configured to perform defect detection on the display screen through the defect mask image to generate a first defect detection result.

[0165] The first determination unit 909 is configured to perform connected domain segmentation on the defect mask image to determine an abnormal area.

[0166] The second determination unit 910 is configured to determine a background area according to the abnormal area.

[0167] Optionally, the second determination unit 910 includes:

[0168] The second determination unit 910 is configured to determine a background area according to the abnormal area.

[0169] When the background area contains other abnormal areas, the part of the background area intersecting with the other abnormal areas is removed.

[0170] The fifth generation unit 911 is configured to perform gray difference degree analysis on the abnormal area and the background area and threshold control processing on the defect to generate a second detection result.

[0171] Optionally, the fifth generation unit 911 includes:

[0172] The fifth generation unit 911 is configured to perform gray difference degree analysis on the abnormal area and the background area and threshold control processing on the defect to generate a second detection result.

[0173] The fifth generation unit 911 is configured to perform gray difference degree analysis on the abnormal area and the background area and threshold control processing on the defect to generate a second detection result.

[0174] The fifth generation unit 911 is configured to perform gray difference degree analysis on the abnormal area and the background area and threshold control processing on the defect to generate a second detection result.

[0175] The analysis unit 912 is configured to perform defect integration analysis on the first defect detection result and the second detection result.

[0176] Please refer to Figure 10 The application provides a defect detection device based on a dynamic double-threshold template, comprising:

[0177] The processor 1001, the memory 1002, the input / output unit 1003 and the bus 1004.

[0178] The processor 1001 is connected with the memory 1002, the input / output unit 1003 and the bus 1004.

[0179] The memory 1002 stores a program, and the processor 1001 invokes the program to perform the defect detection method in Figure 1 、 Figure 2 and Figure 3 、 Figure 4 、 Figure 5 、 Figure 6 、 Figure 7 and Figure 8 .

[0180] The application provides a computer readable storage medium, and the computer readable storage medium stores a program, and the program performs the defect detection method in Figure 1 、 Figure 2 and Figure 3 、 Figure 4 、 Figure 5 、 Figure 6 、 Figure 7 and Figure 8 when executed on a computer.

[0181] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0182] In several embodiments provided in the application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0183] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0184] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present alone, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0185] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical scheme of the present application essentially or the part that contributes to the prior art or the whole or part of the technical scheme can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, read-only memory), a random access memory (RAM, random access memory), a magnetic disk or an optical disk, and various program code storage media.

Claims

1. A defect detection method based on a dynamic dual-threshold template, characterized in that, include: Collect images of several batches of defect-free samples of the target model display screen; Statistically analyze the grayscale extreme value boundary data of each pixel on the several batches of defect-free sample images; Generate a lower limit standard template and an upper limit standard template based on the grayscale extreme value boundary data; Obtain the regional difference amplification factor and compensation offset; The steps for obtaining the regional difference magnification factor and compensation offset include: determining the radial thickness distribution of the quantum dot electroluminescent display screen corresponding to each defect-free sample image, wherein the target model display screen is a quantum dot electroluminescent display screen; dividing each defect-free sample image into a high-thickness region and a low-thickness region according to the radial thickness distribution, wherein the high-thickness region is the region whose radial thickness is higher than the upper limit of the reference thickness range, and the low-thickness region is the region whose radial thickness is higher than the upper limit of the reference thickness range; calculating the upper limit regional difference magnification factor and the upper limit compensation offset based on the grayscale data, grayscale gradient data, and thin film reflectivity data of the high-thickness region; calculating the lower limit regional difference magnification factor and the lower limit compensation offset based on the grayscale data, grayscale gradient data, and thin film reflectivity data of the low-thickness region; and averaging the upper limit regional difference magnification factor, the upper limit compensation offset, the lower limit regional difference magnification factor, and the lower limit compensation offset corresponding to each defect-free sample image; Dynamic detection threshold templates are generated from the lower limit standard template and the upper limit standard template using the regional difference amplification factor and the compensation offset. The regional difference amplification factor includes the upper limit regional difference amplification factor and the lower limit regional difference amplification factor. The compensation offset includes the upper limit compensation offset and the lower limit compensation offset. The dynamic detection threshold templates include a bright defect dynamic detection threshold template and a dark defect dynamic detection threshold template. The step of generating a dynamic detection threshold template for the lower limit standard template and the upper limit standard template using the regional difference amplification factor and the compensation offset includes: generating a bright defect dynamic detection threshold template using the upper limit regional difference amplification factor, the upper limit compensation offset, the lower limit standard template and the upper limit standard template; and generating a dark defect dynamic detection threshold template using the lower limit regional difference amplification factor, the lower limit compensation offset, the lower limit standard template and the upper limit standard template. Obtain the image of the screen to be tested for the target model display screen; The image of the screen to be tested is compared with the dynamic detection threshold template at the pixel level to generate a defect mask image; Defects in the display screen are detected using the defect mask image, generating a first defect detection result.

2. The defect detection method according to claim 1, characterized in that, The defect mask image includes a bright defect mask image and a dark defect mask image; The step of generating a defect mask image by performing pixel-level difference between the image of the screen to be tested and the dynamic detection threshold template includes: The image of the screen to be tested is compared with the dynamic detection threshold template for bright defects at the pixel level to generate a bright defect mask image; The image of the screen to be tested is compared with the dynamic detection threshold template for dark defects at the pixel level to generate a dark defect mask image.

3. The defect detection method according to any one of claims 1 to 2, characterized in that, After the step of detecting defects in the display screen using the defect mask image and generating a first defect detection result, the defect detection method further includes: The defect mask image is segmented into connected components to identify abnormal regions; Determine the background region based on the abnormal region; The grayscale difference between the abnormal region and the background region is analyzed, and a threshold control process for defects is performed to generate a second detection result. The first defect detection result and the second detection result are combined for defect integration analysis.

4. The defect detection method according to claim 3, characterized in that, The step of determining the background region based on the abnormal region includes: Determine the minimum inscribed circle radius of the abnormal region, and expand the abnormal region by the radius of the inscribed circle to generate a background region; When the background area contains other abnormal areas, the portion of the background area that intersects with the other abnormal areas is removed.

5. The defect detection method according to claim 3, characterized in that, The steps of analyzing the grayscale difference between the abnormal region and the background region, performing threshold control processing for defects, and generating a second detection result include: Calculate the first grayscale mean and the second grayscale mean of the abnormal region and the background region; The difference in contrast attribute of the defect is calculated based on the first gray-scale mean and the second gray-scale mean; The difference values ​​of the contrast attribute are subjected to threshold control processing to generate a second detection result.

6. The defect detection method according to any one of claims 1 to 2, characterized in that, The steps of generating the lower limit standard template and the upper limit standard template based on the grayscale extreme value boundary data include: The boundary gray value of each pixel is determined based on the gray-scale extreme value boundary data and boundary ratio. A lower limit standard template and an upper limit standard template are generated based on the boundary grayscale value of each pixel.

7. A defect detection device based on a dynamic dual-threshold template, characterized in that, include: The acquisition unit is used to acquire images of several batches of defect-free samples of the target model display screen; The statistical unit is used to statistically analyze the grayscale extreme value boundary data of each pixel on the several batches of defect-free sample images. The first generation unit is used to generate a lower limit standard template and an upper limit standard template based on the grayscale extreme value boundary data. The first acquisition unit is used to acquire the regional difference amplification factor and the compensation offset. The first acquisition unit specifically includes: determining the radial thickness distribution of the quantum dot electroluminescent display screen corresponding to each defect-free sample image, wherein the target model display screen is a quantum dot electroluminescent display screen; dividing each defect-free sample image into a high-thickness region and a low-thickness region according to the radial thickness distribution, wherein the high-thickness region is the region whose radial thickness is higher than the upper limit of the reference thickness range, and the low-thickness region is the region whose radial thickness is higher than the upper limit of the reference thickness range; calculating the upper limit region difference amplification factor and upper limit compensation offset based on the grayscale data, grayscale gradient data, and thin film reflectivity data of the high-thickness region; calculating the lower limit region difference amplification factor and lower limit compensation offset based on the grayscale data, grayscale gradient data, and thin film reflectivity data of the low-thickness region; and averaging the upper limit region difference amplification factor, upper limit compensation offset, lower limit region difference amplification factor, and lower limit compensation offset corresponding to each defect-free sample image; The second generation unit is used to generate dynamic detection threshold templates for the lower limit standard template and the upper limit standard template using the regional difference amplification coefficient and the compensation offset. The regional difference amplification coefficient includes the upper limit regional difference amplification coefficient and the lower limit regional difference amplification coefficient. The compensation offset includes the upper limit compensation offset and the lower limit compensation offset. The dynamic detection threshold template includes a bright defect dynamic detection threshold template and a dark defect dynamic detection threshold template. The second generation unit includes: generating a dynamic detection threshold template for bright defects using the upper limit region difference amplification factor, the upper limit compensation offset, the lower limit standard template, and the upper limit standard template; and generating a dynamic detection threshold template for dark defects using the lower limit region difference amplification factor, the lower limit compensation offset, the lower limit standard template, and the upper limit standard template. The second acquisition unit is used to acquire the image of the screen to be tested of the target model display screen; The third generation unit is used to perform pixel-level difference between the image of the screen to be tested and the dynamic detection threshold template to generate a defect mask image; The fourth generation unit is used to perform defect detection on the display screen using the defect mask image and generate a first defect detection result.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains a program that, when executed on a computer, performs the defect detection method as described in any one of claims 1 to 6.

Images