Display panel defect detection method, device and electronic equipment

Abstract

The display panel fault determination method, device and electronic equipment provided by the embodiments of the present application can reduce the error accumulation caused by fixed step search and the dependence of the existing positioning scheme on the positioning map by adjusting the search step length in the search process, and can more accurately and quickly realize the search and positioning of the fault area in the display panel.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of display device, in particular to a display panel defect detection method and device and electronic equipment. BACKGROUND

[0002] In the bad point repair or display uneven repair (Demura) operation of the display panel, it is usually necessary to first use a charge-coupled device (CCD) camera to shoot a picture of the display panel in the working state, so as to determine the position of the pixel to be repaired according to the shot picture. Accurate positioning of the pixel to be repaired is very important for subsequent repair operations. However, due to the defects such as bad points and bright points of the display panel itself, the pixel positioning will deviate. Especially when there is a large area of defects in the display panel, the existing positioning algorithm, such as chessboard positioning algorithm or nine-point calibration algorithm, is difficult to position the pixel group or the positioning position deviates greatly, and cannot provide effective data support for subsequent repair operations. SUMMARY

[0003] In order to overcome the above-mentioned deficiencies in the prior art, the purpose of the present application is to provide a display panel defect detection method, which comprises:

[0004] acquiring a display panel to be tested in a set display state under the display gray scale map;

[0005] determining the positions corresponding to a plurality of normally displayed pixels in the display area on the gray scale map as initialized search starting points, and recording the plurality of search starting points to a shared knowledge board;

[0006] for each search starting point, determining a target step size, and searching from the search starting point according to the target step size to determine a target detection area of a preset size;

[0007] determining whether there is a normally displayed pixel in the target detection area according to the gray scale values of each position in the target detection area;

[0008] if there is, recording the position corresponding to the normally displayed pixel and the currently used target step size to the shared knowledge board, taking the position corresponding to the normally displayed pixel as a new search starting point, and continuing to search using the target step size;

[0009] if there is not, adjusting the target step size according to the search starting point and the gray scale value distribution of each position in the target detection area, and continuing to search from the search starting point using the adjusted target step size;

[0010] After the search action reaches a set end condition, a region with display defects on the display panel is determined according to the recorded positions corresponding to the normally displayed pixels.

[0011] In a possible implementation, the step of determining, as the search starting points, positions corresponding to normally displayed pixels in the display region on the gray scale diagram includes:

[0012] randomly determining a plurality of starting points on the gray scale diagram;

[0013] For each starting point, a point closest to the starting point position and having a gray scale value greater than a first set threshold is determined as the search starting point.

[0014] In a possible implementation, the step of determining a target step length includes:

[0015] If the search starting point is an initialized search starting point, a preset initial step length is used as the target step length.

[0016] If the search starting point is not an initialized search starting point, an optimal step length is determined as the target step length according to a plurality of step lengths recorded in a shared knowledge board.

[0017] Preferably, the method further includes:

[0018] The preset initial step length is determined according to a resolution and a pixel arrangement relationship of the display panel to be tested.

[0019] In a possible implementation, after the step of determining, as initialized search starting points, positions corresponding to normally displayed pixels in the display region on the gray scale diagram, the method further includes:

[0020] An average value of the gray scale values of the initialized search starting points is calculated, and the average value is recorded as a gray scale judgment threshold.

[0021] The step of determining, according to the gray scale values of each position in the target detection region, whether there is a normally displayed pixel in the target detection region includes:

[0022] A maximum gray scale value in each position in the target detection region is obtained as an adaptive value of the target detection region.

[0023] An absolute value of a difference between the adaptive value and the gray scale judgment threshold is calculated to determine whether the absolute value is less than a set second threshold.

[0024] If yes, it is determined that there is a normally displayed pixel in the target detection region, and a position with the maximum gray scale value in the target detection region is determined as a position corresponding to the normally displayed pixel.

[0025] If not, it is determined that there is no normally displayed pixel in the target detection region.

[0026] In a possible implementation, the step of adjusting the target step size according to the search starting point and the gray value distribution of each position in the target detection region comprises:

[0027] The adjusted target step size is determined according to the following formula:

[0028] v i+1 = ω * v i + c1 * r1 * (p i - x i ) + c2 * r2 * (p g - x i )

[0029] wherein v i is the current target step size, v i+1 is the adjusted target step size, ω is an inertia weight, c1 and c2 are acceleration constants, r1 and r2 are random numbers in the range of (0, 1); x i is the current search starting point; p i is a local optimal position in the target detection region, p g is a global optimal position of the target detection region, the local optimal position is the first position with the maximum gray value in the target detection region, and the global optimal position is the center position of the target detection region; (p i - x i ) is the local optimal position.

[0030] wherein if the gray values of each position in the target detection region are the same, c1 = 1 and c2 = 1; if there are positions with different gray values in the target detection region, the value range of c1 and c2 is [0, 1];

[0031] The step of continuing the search from the search starting point using the adjusted target step size comprises:

[0032] The position of the next target detection region is determined according to the following formula:

[0033] x i+1 = x i + α * v i

[0034] wherein x i+1 is the coordinate of the next target detection region.

[0035] If the gray values of each position in the target detection region are the same, α > 1; if there are positions with different gray values in the target detection region, α = 1.

[0036] Preferably, if the gray value of each position in the target detection region is the same, the value range of a is [1, 5].

[0037] In a possible implementation, the determining that the search action reaches the set end condition comprises:

[0038] For each search path starting from the initialized search starting point, when the search times of the search path are greater than the total number of pixels of the display panel to be tested, and when the position corresponding to the normally displayed pixel newly determined in the search path is the position recorded in the shared knowledge board, it is determined that the search path ends the search.

[0039] When each of the search paths ends the search, it is determined that the search action reaches the set end condition.

[0040] In a possible implementation, the determining of the area with display defects on the display panel according to the recorded positions corresponding to the normally displayed pixels comprises:

[0041] The positions recorded in the shared knowledge board are deduplicated, and the area with display defects on the display panel is determined according to the positions corresponding to the normally displayed pixels after deduplication.

[0042] Another object of the present application is to provide a display panel defect detection device, which comprises:

[0043] An image acquisition module is configured to acquire a display gray image of a display panel to be tested in a set display state.

[0044] A starting point initialization module is configured to determine positions corresponding to normally displayed pixels in a display area on the gray image as initialized search starting points, and record the search starting points in a shared knowledge board.

[0045] A step determination module is configured to determine, for each search starting point, a target step, and perform search according to the target step from the search starting point to determine a target detection region of a preset size.

[0046] The search detection module is configured to determine whether a normally displayed pixel exists in the target detection area according to a gray value of each position in the target detection area; if the normally displayed pixel exists, record a position corresponding to the normally displayed pixel and the target step currently used to a shared knowledge board, take the position corresponding to the normally displayed pixel as a new search starting point, and continue the search using the target step; if the normally displayed pixel does not exist, adjust the target step according to the search starting point and a gray value distribution of each position in the target detection area, and continue the search using the adjusted target step from the search starting point.

[0047] The defect area determination module is configured to determine a region with a display defect on the display panel according to the recorded positions corresponding to the normally displayed pixels after the search action reaches a set ending condition.

[0048] Another purpose of the present application is to provide an electronic device, comprising a processor and a machine readable storage medium, the machine readable storage medium stores machine executable instructions, when the machine executable instructions are executed by the processor, the display panel defect detection method provided by the present application is implemented.

[0049] Another purpose of the present application is to provide a machine readable storage medium, the machine readable storage medium stores machine executable instructions, when the machine executable instructions are executed by one or more processors, the display panel defect detection method provided by the present application is implemented.

[0050] Compared with the prior art, the present application has the following beneficial effects:

[0051] The display panel fault determination method, device and electronic device provided by the present application can weaken the error accumulation caused by fixed step search and the dependence of the existing positioning scheme on the positioning map, and can more accurately and quickly realize the search and positioning of the fault region in the display panel. BRIEF DESCRIPTION OF DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation to the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0053] Figure 1 The step flow chart of the display panel defect detection method provided by the present application is shown in the figure.

[0054] Figure 2A schematic diagram of a target detection area provided by an embodiment of the present application is shown in FIG. 1.

[0055] Figure 3 A schematic diagram of an electronic device provided by an embodiment of the present application is shown in FIG. 2.

[0056] Figure 4 A functional module schematic diagram of a display panel defect detection device provided by an embodiment of the present application is shown in FIG. 3. DETAILED DESCRIPTION

[0057] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in detail with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments of the present application. The components of the embodiments of the present application described and shown in the accompanying drawings can be arranged and designed in various different configurations.

[0058] Therefore, the detailed description of the embodiments of the present application provided below in the accompanying drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without making creative efforts fall within the scope of protection of the present application.

[0059] It should be noted that: similar reference numerals and letters represent similar items in the following drawings, therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0060] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "vertical", "horizontal", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the present application is usually placed, which is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the indicated device or element must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second", "third" and the like are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0061] It should be noted that the different features in the embodiments of the present application can be combined with each other without conflict.

[0062] Please refer to Figure 1 , Figure 1 A step flowchart of a display panel defect detection method provided by the present embodiment is shown in FIG. 4, and the method will be described in detail below.

[0063] In step S110, a display panel gray scale image of the display panel to be tested in a set display state is obtained.

[0064] In this embodiment, the display panel to be tested in a display state is captured by a CCD camera to obtain a display panel gray scale image of the display panel to be tested. The resolution of the display panel gray scale image obtained by the CCD camera is greater than the display resolution of the display panel to be tested, and the content in the display panel gray scale image can include pixels in the display panel to be tested and gaps between the pixels. It can be understood that, due to the different resolutions of the display panel gray scale image and the display panel to be tested, the area between two adjacent actual pixels in the display panel to be tested can correspond to multiple pixels on the display panel gray scale image.

[0065] In step S120, positions corresponding to multiple normally displayed pixels in the display area on the display panel gray scale image are determined as initialized search starting points, and the multiple search starting points are recorded to a shared knowledge board.

[0066] In this embodiment, the positions corresponding to the multiple normally displayed pixels can be randomly determined on the display panel gray scale image as the initialized search starting points.

[0067] For example, the gray scale value corresponding to the normally displayed pixel on the display panel gray scale image should be large, and therefore, in this embodiment, multiple starting points can be randomly determined on the display panel gray scale image, and then for each starting point, a point closest to the starting point and having a gray scale value greater than a first set threshold value is determined as the search starting point.

[0068] In step S130, for each search starting point, a target step length is determined, and a target detection area of a preset size is determined by searching from the search starting point according to the target step length.

[0069] In this embodiment, for each search starting point, a target step length is determined, and a target detection area of a preset size is determined by searching from the search starting point according to the target step length.

[0070] For each search starting point, when searching according to the target step length, a region of a preset size outside the target step length around the search starting point can be determined as the target detection area. For example, the preset size can be a 3*3 pixel region on the display panel gray scale image or a 5*5 pixel region on the display panel gray scale image.

[0071] In step S140, whether there is a normally displayed pixel in the target detection area is determined according to the gray scale values of the positions in the target detection area.

[0072] If there is a normally displayed pixel in the target detection area, step S150 is performed.

[0073] If there is no normally displayed pixel in the target detection area, step S160 is performed.

[0074] In step S150, the position corresponding to the normally displayed pixel and the target step length currently used are recorded in the shared knowledge board, the position corresponding to the normally displayed pixel is taken as a new search starting point, and the search is continued using the target step length.

[0075] If there is a normally displayed pixel in the target detection area, it can be considered that the target step length currently used is approximately consistent with the interval between normally displayed pixels, so the position corresponding to the newly searched normally displayed pixel can be taken as a new search starting point, and the search is continued using the target step length.

[0076] In step S160, the target step length is adjusted according to the search starting point and the gray value distribution of each position in the target detection area, and the search is continued using the adjusted target step length from the search starting point.

[0077] If there is no normally displayed pixel in the target detection area, it can be considered that there is a pixel with a display defect on the current search path, or the target step length currently used is not appropriate, so the target step length needs to be adjusted and the search is re-performed.

[0078] In step S170, after the search action reaches a set end condition, the positions corresponding to each normally displayed pixel recorded are used to determine the area with a display defect on the display panel.

[0079] In this embodiment, after the search is performed through the above steps, the positions corresponding to each normally displayed pixel are recorded in the shared knowledge board, so that the area with a display defect other than the normally displayed pixel can be determined according to the positions corresponding to each normally displayed pixel.

[0080] Based on the above design, in the scheme provided in this embodiment, by adjusting the search step length in the search process, the error accumulation caused by fixed step length search and the dependence of the existing positioning scheme on the positioning map can be reduced, and the search and positioning of the fault area in the display panel can be more accurately and quickly realized.

[0081] In a possible implementation, when the target step length is determined in step S130, if the search starting point is an initialized search starting point, a preset initial step length is taken as the target step length. For example, the preset initial step length can be determined according to the resolution and pixel arrangement relationship of the display panel to be measured.

[0082] If the search starting point is not the initialized search starting point, an optimal step length is determined as the target step length according to a plurality of step lengths recorded in the shared knowledge board. For example, the step length with the highest frequency recorded in the shared knowledge board is determined as the optimal step length.

[0083] In one possible implementation, the adjusted target step length is determined in step S160 according to the following formula:

[0084] v i+1 = ω * v i + c1 * r1 * (p i - x i ) + c2 * r2 * (p g - x i )

[0085] where v i is the current target step length, v i+1 is the adjusted target step length, ω is an inertia weight, c1 and c2 are acceleration constants, r1 and r2 are random numbers in the range of (0, 1), x i is the current search starting point, p i is a local optimal position in the target detection region, and p g is a global optimal position of the target detection region, the local optimal position is the position with the largest gray value in the target detection region, and the global optimal position is the center position of the target detection region. i -x i is the local optimal position.

[0086] If the gray values of all positions in the target detection region are the same, the target step length is smaller than the optimal step length, and therefore a magnification coefficient needs to be added, the proportion needs to be increased, and the search step length needs to be increased. In this case, c1 = 1 and c2 = 1. If there are positions with different gray values in the target detection region, the values of c1 and c2 are in the range of [0, 1].

[0087] The calculation of (p i -x i ) represents the deviation between the local optimal position and the current pixel position, and the new target step length is dynamically adjusted according to the value, which can prevent the accumulation of errors caused by the local optimum when searching for pixel groups subsequently. The calculation of (p g -x i ) represents the deviation between the local optimal position and the current pixel position, and the new target step length is dynamically adjusted according to the value, which can weaken the influence of the local optimal step length on the overall search, so that most of the pixel groups are searched according to the optimal step length in the search process.

[0088] The position of the next target detection region can be determined according to the following formula in step S160:

[0089] x i+1 = x i + a * v i

[0090] wherein x i+1 is the coordinate of the next target detection region;

[0091] If the gray scale values of the positions in the target detection region are the same, it indicates that the target step is smaller than the optimal step, and the coefficient a needs to be enlarged in order to find the actual position of the pixel on the display panel, and therefore a>1 is set. If there are positions with different gray scale values in the target detection region, a=1.

[0092] Preferably, if the gray scale values of the positions in the target detection region are the same, the search step needs to be increased. If the search step is too large, the pixel cluster will be skipped, resulting in the loss of the pixel cluster during the search. Therefore, the value range of a can be set as [1, 5].

[0093] Based on the above design, in the present embodiment, the particle swarm algorithm and the knowledge board collaborative search algorithm are introduced in the search process, so that the search process can use the prior information and update the prior information at the same time, and the problem that the search process cannot update the step and falls into local optimization when encountering a large area of bad pixel is avoided.

[0094] In a possible implementation, in step S140, it can be determined whether a position in the target detection region corresponds to a normally displayed pixel according to the size of the gray scale value of the position.

[0095] For example, in one example, the position with a gray scale value greater than the first set threshold value can be determined as the position corresponding to the normally displayed pixel.

[0096] In another example, after step S110, the average of the gray scale values of the initialized search starting points can be calculated, and the average is recorded as the gray scale judgment threshold value.

[0097] Then in step S140, the maximum gray scale value in the target detection region is obtained as the fitness value of the target detection region, and it is determined whether the absolute value of the difference between the fitness value and the gray scale judgment threshold value is less than a set second threshold value. If yes, it is determined that there is a normally displayed pixel in the target detection region, and the position with the maximum gray scale value in the target detection region is determined as the position corresponding to the normally displayed pixel. If no, it is determined that there is no normally displayed pixel in the target detection region.

[0098] For example, it is assumed that the average of the gray scale values determined in step S110 is Graybest , the gray scale judgment threshold is threshold, please refer to Figure 2 , assuming Figure 2 The region shown by the thick line frame in is a target detection region, and the gray scale value of the position with a large gray scale value in the target detection region is 116. It is determined whether | 116-Gray best |<threshold is established. If it is established, the position with a gray scale value of 116 in the target detection region is the position corresponding to the normally displayed pixel; if it is not established, there is no normally displayed pixel in the target detection region.

[0099] In a possible implementation, in step S170, when determining whether the search action reaches the set end condition, for each search path with the initialized search starting point as the starting point, when the search number of the search path is greater than the total number of pixels of the display panel to be tested, and when the position corresponding to the normally displayed pixel newly determined in the search path is the position recorded in the shared knowledge board, it is determined that the search path ends the search.

[0100] If the search number of the search path is greater than the total number of pixels of the display panel to be tested, it indicates that the search path may have searched all positions on the display panel, and it can be determined that the search path can end the search. If the position corresponding to the normally displayed pixel newly determined in the search path is the position recorded in the shared knowledge board, and the repeated path will be searched, it can be determined that the search path can end the search.

[0101] When each of the search paths ends the search, it is determined that the search action reaches the set end condition.

[0102] In a possible manner, for different search paths, there may be repeated recorded positions, and therefore in step S170, the recorded positions in the shared knowledge board can be deduplicated, and according to the positions corresponding to the normally displayed pixels after deduplication, the area with a display defect on the display panel is determined.

[0103] The embodiment also provides an electronic device, which can be a device with data processing capability, for example, a server, a personal computer, a notebook computer, etc. The electronic device can run the display panel defect detection method provided in the embodiment.

[0104] Please refer to Figure 3 , Figure 3 The block schematic diagram of the electronic device 100. The electronic device 100 includes a display panel defect detection apparatus 110, a machine readable storage medium 120, and a processor 130.

[0105] The machine readable storage medium 120 and the processor 130 are electrically connected with each other directly or indirectly to realize data transmission or interaction. For example, the elements can be electrically connected with each other through one or more communication buses or signal lines. The display panel defect detection apparatus 110 includes at least one software function module stored in the machine readable storage medium 120 in the form of software or firmware or solidified in an operating system (OS) of the electronic device 100. The processor 130 is configured to execute the executable modules stored in the machine readable storage medium 120, such as the software function modules and computer programs included in the display panel defect detection apparatus 110.

[0106] The machine readable storage medium 120 can be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. The machine readable storage medium 120 is configured to store a program, and the processor 130 executes the program after receiving an execution instruction to execute the display panel defect detection method provided in the embodiments.

[0107] The processor 130 can be an integrated circuit chip with a processing capability. The processor can be a general purpose processor, including a central processing unit (CPU), a network processor (NP), etc. The processor can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The processor can realize or execute the disclosed methods, steps and logic block diagrams in the embodiments of the present application. The general purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0108] Please refer to Figure 4The embodiment also provides a display panel defect detection device 110, which comprises at least one function module stored in a machine readable storage medium 120 in the form of software. Functionally, the display panel defect detection device 110 can comprise an image acquisition module 111, a starting point initialization module 112, a step length determination module 113, a search detection module 114 and a defect area determination module 115.

[0109] The image acquisition module 111 is configured to acquire a display panel gray scale image of a display panel to be detected in a set display state.

[0110] In the embodiment, the image acquisition module 111 can be configured to perform Figure 1 The specific description of the image acquisition module 111 can refer to the description of step S110.

[0111] The starting point initialization module 112 is configured to determine the positions of a plurality of normally displayed pixels in the display area on the gray scale image as initialized search starting points, and record the search starting points to a shared knowledge board.

[0112] In the embodiment, the starting point initialization module 112 can be configured to perform Figure 1 The specific description of the starting point initialization module 112 can refer to the description of step S120.

[0113] The step length determination module 113 is configured to determine a target step length for each search starting point, and search from the search starting point according to the target step length to determine a target detection area with a preset size.

[0114] In the embodiment, the step length determination module 113 can be configured to perform Figure 1 The specific description of the step length determination module 113 can refer to the description of step S130.

[0115] The search detection module 114 is configured to determine whether there is a normally displayed pixel in the target detection area according to the gray scale values of each position in the target detection area; if there is, record the position corresponding to the normally displayed pixel and the currently used target step length to the shared knowledge board, use the position corresponding to the normally displayed pixel as a new search starting point, and continue searching using the target step length; if there is not, adjust the target step length according to the search starting point and the gray scale value distribution of each position in the target detection area, and continue searching from the search starting point using the adjusted target step length.

[0116] In the embodiment, the search detection module 114 can be configured to performFigure 1 The specific description of the search detection module 114 can refer to the description of steps S140-S160.

[0117] The defect area determination module 115 is configured to determine the area with display defects on the display panel according to the recorded positions corresponding to the normally displayed pixels after the search action reaches the set ending condition.

[0118] In this embodiment, the defect area determination module 115 can be configured to perform Figure 1 The specific description of the defect area determination module 115 can refer to the description of step S170.

[0119] To sum up, the display panel fault determination method, device and electronic equipment provided by the embodiments of the present application can reduce the error accumulation caused by fixed step search and the dependence of the existing positioning scheme on the positioning map by adjusting the search step length in the search process, and can more accurately and quickly search and position the fault area in the display panel.

[0120] The technical features of the above-described embodiments can be combined arbitrarily. To make the description concise, all possible combinations of the technical features in the above-described embodiments are not described, but as long as the combinations of the technical features do not exist, they should be considered as the scope of the present application.

[0121] The above-described embodiments only express several embodiments of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for detecting defects of a display panel, characterized in that, The method comprises: acquiring a display surface gray scale image of a display panel to be tested in a set display state; determining positions corresponding to a plurality of normally displayed pixels in a display area on the gray scale image as initial search starting points, and recording the search starting points to a shared knowledge board; for each search starting point, determining a target step length, and performing a search from the search starting point according to the target step length to determine a target detection area of a preset size; determining whether there is a normally displayed pixel in the target detection area according to gray scale values of positions in the target detection area; if there is, recording a position corresponding to the normally displayed pixel and the currently used target step length to the shared knowledge board, using the position corresponding to the normally displayed pixel as a new search starting point, and continuing the search using the target step length; if there is not, adjusting the target step length according to the search starting point and the gray scale value distribution of positions in the target detection area, and continuing the search from the search starting point using the adjusted target step length; after a search action reaches a set end condition, determining a region with display defects on the display panel according to positions corresponding to the normally displayed pixels recorded; wherein, after the step of determining positions corresponding to a plurality of normally displayed pixels in a display area on the gray scale image as initial search starting points, the method further comprises: calculating an average value of gray scale values of the initial search starting points, and recording the average value as a gray scale determination threshold value; the step of determining whether there is a normally displayed pixel in the target detection area according to gray scale values of positions in the target detection area comprises: acquiring a maximum gray scale value in the target detection area as an adaptive value of the target detection area; calculating whether an absolute value of a difference between the adaptive value and the gray scale determination threshold value is less than a set second threshold value; if yes, determining that there is a normally displayed pixel in the target detection area, and determining a position with the maximum gray scale value in the target detection area as a position corresponding to the normally displayed pixel; if no, determining that there is not a normally displayed pixel in the target detection area.

2. The method of claim 1, wherein, the step of determining positions corresponding to a plurality of normally displayed pixels in a display area on the gray scale image as search starting points comprises: randomly determining a plurality of starting points on the gray scale image; for each starting point, determining a point closest to the starting point position and having a gray scale value greater than a first set threshold value as the search starting point.

3. The method of claim 1, wherein, the step of determining a target step length comprises: if the search starting point is an initial search starting point, using a preset initial step length as the target step length; if the search starting point is not an initial search starting point, determining an optimal step length from a plurality of step lengths recorded in the shared knowledge board as the target step length.

4. The method of claim 3, wherein, the method further comprises: determining the preset initial step length according to a resolution and a pixel arrangement relationship of the display panel to be tested.

5. The method of claim 1, wherein, the step of adjusting the target step length according to the search starting point and the gray scale value distribution of positions in the target detection area comprises: The adjusted target step length is determined according to the following formula: wherein, is the target step size, is the adjusted target step size, is the inertia weight, and is the acceleration constant, and is a random number in the range of (0, 1); is the current search starting point; is the local optimal position in the target detection area, is the global optimal position of the target detection area, the local optimal position is the first position with the maximum gray value in the target detection area, and the global optimal position is the center position of the target detection area; is the local optimal position; If the gray scale values of the positions in the target detection region are the same, then , If there are positions with different gray scale values in the target detection region, then and The value interval of is [0, 1]. The step of continuing searching from the search starting point using the adjusted target step length comprises: The position of the next target detection region is determined according to the following formula: wherein, is the coordinate of the next target detection region; is a step coefficient; If the gray value of each position in the target detection region is the same, then 1; if there are positions with different gray values in the target detection region, then = 1.

6. The method of claim 5, wherein, If the gray value of each position in the target detection region is the same, then the value range of the parameter is [1, 5].

7. The method of claim 1, wherein, The step of determining whether the search action reaches the set ending condition comprises: For each search path starting from the initialized search starting point, when the search times of the search path are greater than the total number of pixels of the display panel to be tested, and when the position corresponding to the newly determined normally displayed pixel in the search path is the position recorded in the shared knowledge board, it is determined that the search path ends the search; When all the search paths end the search, it is determined that the search action reaches the set ending condition.

8. The method of claim 1, wherein, The step of determining the area with display defects on the display panel according to the recorded positions corresponding to the normally displayed pixels comprises: The positions recorded in the shared knowledge board are de-duplicated, and the area with display defects on the display panel is determined according to the de-duplicated positions corresponding to the normally displayed pixels.

9. A display panel defect detection apparatus characterized by comprising: The device comprises: An image acquisition module is configured to acquire a display gray scale image of a display panel to be tested in a set display state; A starting point initialization module is configured to determine positions corresponding to normally displayed pixels in a display area on the gray scale image as initialized search starting points, and record the search starting points in a shared knowledge board; A step length determination module is configured to determine, for each search starting point, a target step length, and search from the search starting point according to the target step length to determine a target detection region with a preset size; A search detection module is configured to determine whether there is a normally displayed pixel in the target detection region according to the gray scale values of each position in the target detection region; if there is, record the position corresponding to the normally displayed pixel and the currently used target step length in the shared knowledge board, use the position corresponding to the normally displayed pixel as a new search starting point, and continue searching using the target step length; if not, adjust the target step length according to the search starting point and the gray scale value distribution of each position in the target detection region, and continue searching from the search starting point using the adjusted target step length; A defect area determination module is configured to determine, after the search action reaches the set ending condition, an area with display defects on the display panel according to the recorded positions corresponding to the normally displayed pixels; The starting point initialization module is further configured to: Calculate the average value of the gray scale values of each initialized search starting point, and record the average value as a gray scale determination threshold value; The search detection module is further configured to: Acquire the maximum gray scale value in each position in the target detection region as an adaptive value of the target detection region; Calculate whether the absolute value of the difference between the adaptive value and the gray scale determination threshold value is less than a set second threshold value; If yes, it is determined that there is a normally displayed pixel in the target detection region, and the position with the maximum gray scale value in the target detection region is determined as the position corresponding to the normally displayed pixel; If not, it is determined that there is no normally displayed pixel in the target detection region.

10. An electronic device, comprising: A machine readable storage medium storing machine executable instructions that, when executed by a processor, implement the method of any one of claims 1-8.

11. A machine-readable storage medium, characterized in that, A machine readable storage medium storing machine executable instructions that, when executed by one or more processors, implement the method of any one of claims 1-8.

Images