Micro LED display defect detection method and device
In the detection of defects of Micro LED displays, the use of initial inspection equipment to screen out hyperspectral data in the region of interest and upload it, the problems of low detection efficiency and high hardware requirements caused by large data volume of hyperspectral imager are solved, and more efficient The detection and lower hardware requirements have promoted the industrial application of Micro LED defect detection.
Patent Information
- Application Number
- CN202410944228.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-15
- Publication Date
- 2024-11-08
AI Technical Summary
Among the existing Micro LED defect detection methods, the hyperspectral imager has huge data volume during data processing, resulting in low detection efficiency and high hardware requirements, which affects industrial applications.
The initial inspection device obtains the area of interest information in the target area of the Micro LED display, and only uploads the hyperspectral data of the area of interest for defect detection, reducing the amount of data received by the host computer and reducing the data processing hardware requirements.
It improves the efficiency of Micro LED defect detection, reduces hardware requirements, and promotes the large-scale application of hyperspectral imaging devices in Micro LED defect detection.
Smart Images

Figure CN118918801A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of defect detection technology, and more specifically, to a Micro LED display defect detection method and device. Background Art
[0002] Light Emitting Diode (LED) is a common light-emitting device that emits light by releasing energy through the recombination of electrons and holes. Micro Light Emitting Diode Display (Micro LED) is a display that displays images by integrating a high-density, tiny-sized LED array on the original substrate. Each LED in the array can emit light by itself and can be independently positioned and lit. The size of a single LED chip in the array reaches the micron level, and the number of LED chips in a Micro LED may reach millions or even tens of millions. How to simultaneously, quickly and accurately detect defective chips in a large number of LED chips in Micro LED is one of the important issues facing the industrialization of Micro LED.
[0003] At present, Micro LED defect detection is mainly achieved through high-resolution industrial cameras, brightness meters and colorimeters, etc., to detect brightness or chromaticity. However, the premise of accurate brightness and chromaticity detection is that the spectrum does not change, and the current change during the Micro LED imaging process will cause the spectrum to shift, thereby affecting the results of brightness and chromaticity detection. Therefore, spectral data needs to be obtained during the brightness and chromaticity measurement process, and the array spectrum data is required to fully reflect the defects of the pixel points. Hyperspectral imaging (HSI) can measure the spectrum of Micro LED through an external scanning platform or a built-in platform, but the hyperspectral information of each pixel of Micro LED will be measured during the measurement process. The data processing volume is huge, and the bandwidth transmission and data processing capabilities of the instrument are extremely high, which seriously affects the efficiency of detection. Summary of the invention
[0004] In view of the defects existing in the related technologies, the embodiments of the present application provide a Micro LED display defect detection method and device, aiming to solve the problem of huge data processing volume in the process of defect detection based on a hyperspectral imager.
[0005] In a first aspect, an embodiment of the present application provides a Micro LED display defect detection method, which is applied to a hyperspectral imaging device, comprising:
[0006] Acquire regional information of an area of interest containing suspected defects in a target area of the Micro LED display to be tested, where the regional information of the area of interest is determined based on a first image of the target area taken by a preliminary inspection device, including position information of the area of interest in the target area and a size of the area of interest, where the preliminary inspection device is a device for detecting brightness and / or chromaticity of the Micro LED display to be tested;
[0007] Based on the regional information of the region of interest, determining the hyperspectral data of the region of interest;
[0008] The hyperspectral data of the area of interest is sent to the host computer for defect detection in the target area.
[0009] In some embodiments, obtaining the region information of the region of interest containing suspected defects in the target region of the Micro LED display to be tested includes:
[0010] receiving area information of the region of interest sent by the initial inspection device, where the area information is determined by the initial inspection device based on the first image; or,
[0011] Receive area information of the region of interest sent by the host computer, where the area information is determined by the initial inspection device or the host computer based on the first image.
[0012] In some embodiments, determining hyperspectral data for a region of interest includes:
[0013] The target area is photographed to obtain a second image, and hyperspectral data of the second image is generated, and the hyperspectral data of the region of interest is filtered out from the hyperspectral data of the second image based on the region information of the region of interest; or,
[0014] The target area is photographed to obtain a second image, the second image is cropped based on the area information of the area of interest to obtain a third image, and hyperspectral data of the area of interest is generated based on the third image; or,
[0015] Based on the area information of the area of interest, the area of interest is photographed to obtain a fourth image, and based on the fourth image, hyperspectral data of the area of interest is generated.
[0016] In a second aspect, the embodiment of the present application further provides a Micro LED display defect detection method, which is applied to a host computer, comprising:
[0017] Receiving hyperspectral data of an area of interest containing suspected defects in a target area of the Micro LED display to be tested sent by a hyperspectral imaging device, wherein the area information of the area of interest is determined based on a first image of the target area taken by a preliminary inspection device, including position information of the area of interest in the target area and a size of the area of interest, wherein the preliminary inspection device is a device for detecting brightness and / or chromaticity of the Micro LED display to be tested;
[0018] Defect detection in the target area is performed based on the hyperspectral data of the area of interest.
[0019] In some embodiments, the method further comprises:
[0020] Get the region information of the area of interest;
[0021] The regional information of the area of interest is sent to the hyperspectral imaging device.
[0022] In some embodiments, obtaining region information of a region of interest includes:
[0023] receiving a first image sent by a preliminary inspection device, and determining area information of an area of interest based on the first image; or,
[0024] Receive area information of the region of interest sent by the initial inspection device, where the area information is determined by the initial inspection device based on the first image.
[0025] In a third aspect, an embodiment of the present application further provides a display defect detection system, comprising:
[0026] A preliminary inspection device is used to capture a target area of the Micro LED display to be tested to obtain a first image, wherein the first image is used to determine area information of an area of interest containing defects within the target area, including position information of the area of interest within the target area and a size of the area of interest;
[0027] A hyperspectral imaging device, used to perform the method described in the first aspect or any possible implementation manner of the first aspect;
[0028] A host computer is used to execute the method described in the second aspect or any possible implementation manner of the second aspect.
[0029] In some embodiments, the initial inspection equipment is one or more of an industrial camera, a colorimeter, and a photometer.
[0030] In a fourth aspect, an embodiment of the present application further provides a display defect detection device, comprising:
[0031] an acquisition module, configured to acquire region information of a region of interest containing suspected defects in a target region of the Micro LED display to be tested, wherein the region information of the region of interest is determined based on a first image of the target region taken by a preliminary inspection device, including position information of the region of interest in the target region and a size of the region of interest, wherein the preliminary inspection device is a device for detecting brightness and / or chromaticity of the Micro LED display to be tested;
[0032] A determination module, used for determining the hyperspectral data of the region of interest based on the region information of the region of interest;
[0033] The sending module is used to send the hyperspectral data of the area of interest to the host computer for defect detection in the target area.
[0034] In some embodiments, the acquisition module specifically includes:
[0035] A first receiving unit is configured to receive region information of a region of interest sent by a preliminary inspection device, where the region information is determined by the preliminary inspection device based on the first image; or
[0036] The second receiving unit is used to receive the region information of the region of interest sent by the host computer, where the region information is determined by the initial inspection device or the host computer based on the first image.
[0037] In some embodiments, the determination module specifically includes:
[0038] A first generating unit is used to photograph the target area to obtain a second image, generate hyperspectral data of the second image, and filter out the hyperspectral data of the region of interest from the hyperspectral data of the second image based on the region information of the region of interest; or
[0039] A second generating unit is configured to photograph the target area to obtain a second image, crop the second image based on the area information of the region of interest to obtain a third image, and generate hyperspectral data of the region of interest based on the third image; or
[0040] The third generating unit is used to photograph the region of interest based on the region information of the region of interest to obtain a fourth image, and generate hyperspectral data of the region of interest based on the fourth image.
[0041] In a fifth aspect, an embodiment of the present application further provides a display defect detection device, comprising:
[0042] A receiving module, configured to receive hyperspectral data of an area of interest containing suspected defects within a target area of the Micro LED display to be tested, sent by a hyperspectral imaging device, wherein area information of the area of interest is determined based on a first image of the target area taken by a preliminary inspection device, including position information of the area of interest within the target area and a size of the area of interest, wherein the preliminary inspection device is a device for detecting brightness and / or chromaticity of the Micro LED display to be tested;
[0043] The detection module is used to detect defects in the target area based on the hyperspectral data of the area of interest.
[0044] In some embodiments, the apparatus further comprises:
[0045] An acquisition module, used for acquiring area information of an area of interest;
[0046] The sending module is used to send the area information of the area of interest to the hyperspectral imaging device.
[0047] In some embodiments, the acquisition module specifically includes:
[0048] A first receiving unit is configured to receive a first image sent by a preliminary inspection device, and determine area information of an area of interest based on the first image; or
[0049] The second receiving unit is used to receive the area information of the area of interest sent by the initial inspection device, where the area information is determined by the initial inspection device based on the first image.
[0050] In a sixth aspect, an embodiment of the present application also provides a hyperspectral imaging device, comprising: at least one memory for storing programs; and at least one processor for executing the programs stored in the memory. When the program stored in the memory is executed, the processor is used to execute the method described in the first aspect or any possible implementation of the first aspect.
[0051] In the seventh aspect, an embodiment of the present application also provides a host computer, including: at least one memory for storing programs; at least one processor for executing the programs stored in the memory, when the program stored in the memory is executed, the processor is used to execute the method described in the second aspect or any possible implementation of the second aspect.
[0052] In an eighth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method described in the first aspect or any possible implementation of the first aspect, or executes the method described in the second aspect or any possible implementation of the second aspect.
[0053] In the ninth aspect, an embodiment of the present application also provides a computer program product. When the computer program product runs on a processor, the processor executes the method described in the first aspect or any possible implementation of the first aspect, or executes the method described in the second aspect or any possible implementation of the second aspect.
[0054] In the Micro LED display defect detection method and apparatus provided in the embodiments of the present application, a hyperspectral imaging device obtains regional information of an area of interest containing suspected defects within a target area of the Micro LED display to be tested. The regional information of the area of interest is determined by a first image taken by a primary inspection device that detects the brightness and / or chromaticity of the Micro LED display to be tested, and includes position information of the area of interest within the target area and the size of the area of interest, thereby uploading only the hyperspectral data of the area of interest to a host computer for defect detection of the target area. Since the area of interest is only a small part of the target area of the Micro LED display to be tested, the amount of hyperspectral data received by the host computer is greatly reduced, thereby improving the detection efficiency and reducing the hardware requirements for processing hyperspectral data, thereby promoting the large-scale application of hyperspectral imaging devices in Micro LED defect detection. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] In order to more clearly illustrate the technical solutions in the present application or related technologies, the following is a brief introduction to the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0056] Figure 1 This is one of the flow charts of the Micro LED display defect detection method provided in the embodiment of the present application;
[0057] Figure 2 This is the second flow chart of the Micro LED display defect detection method provided in the embodiment of the present application;
[0058] Figure 3 Schematic diagram of the architecture of a Micro LED display defect detection system provided in an embodiment of the present application;
[0059] Figure 4 This is the third flow chart of the Micro LED display defect detection method provided in the embodiment of the present application;
[0060] Figure 5 This is one of the structural schematic diagrams of the Micro LED display defect detection device provided in the embodiment of the present application;
[0061] Figure 6 This is the second structural schematic diagram of the Micro LED display defect detection device provided in the embodiment of the present application;
[0062] Figure 7 is a schematic diagram of the structure of a hyperspectral imaging device provided in an embodiment of the present application;
[0063] Figure 8 It is a structural diagram of the host computer provided in the embodiment of the present application. DETAILED DESCRIPTION
[0064] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0065] Figure 1 FIG. 1 is one of the flow charts of the Micro LED display defect detection method provided in the embodiment of the present application, such as Figure 1 As shown, the execution subject of the method is a hyperspectral imaging device, such as a hyperspectral imager, and the method includes at least the following steps:
[0066] S101, obtaining area information of an area of interest containing suspected defects in a target area of the Micro LED display to be tested.
[0067] Among them, the regional information of the region of interest is determined based on the first image taken by the initial inspection device of the target area, including the position information of the region of interest in the target area and the size of the region of interest. The initial inspection device is a device for detecting the brightness and / or chromaticity of the MicroLED display to be tested.
[0068] Specifically, the target area refers to the area of the Micro LED display to be tested that can be photographed by the imaging device (hyperspectral imaging device and initial inspection device) at a certain shooting position and shooting angle when the Micro LED display to be tested is placed in a specified position. The target area can be the entire or partial area of the Micro LED display to be tested. The region of interest (ROI) refers to the area in the image that is designated as requiring special attention and processing, specifically refers to the area containing suspected defects within the target area. The target area may contain one or more regions of interest, and the shape of the region of interest can be regular or irregular. The initial inspection equipment refers to equipment that performs initial defect detection on the brightness and / or chromaticity of the Micro LED display to be tested, such as a high-resolution industrial camera, a brightness meter, a colorimeter, etc.
[0069] In the process of using hyperspectral imaging equipment for Micro LED defect detection, the focus should be on areas that may have abnormal brightness or other defects. It is not necessary to obtain hyperspectral data of all pixels in the area. Therefore, before using hyperspectral imaging equipment for defect detection, consider using an initial inspection device to perform preliminary detection of Micro LED defects and screen out areas of interest with suspected defects. The subsequent hyperspectral imaging equipment only needs to determine the hyperspectral data of the area of interest rather than the hyperspectral data of the entire target area, thereby reducing the amount of hyperspectral data and improving detection efficiency.
[0070] The hyperspectral imaging device obtains the regional information of the region of interest containing the suspected defect in the target area of the Micro LED display to be tested, and the regional information at least includes the position information of the region of interest in the target area and the size of the region of interest, and the regional information is determined by the first image taken by the initial inspection device on the target area. Among them, the regional information of the region of interest is determined by the first image taken by the initial inspection device on the target area, which can be implemented by the defect detection algorithm related to the existing initial inspection device.
[0071] It can be imagined that when performing the initial inspection using the first image taken by the initial inspection equipment, very accurate detection results are not required. The probability of containing defect-free pixels in the area of interest can be controlled by adjusting the threshold in the relevant defect detection algorithm, so as to facilitate the subsequent use of hyperspectral imaging equipment for defect detection.
[0072] S102: Determine hyperspectral data of the region of interest based on the region information of the region of interest.
[0073] Specifically, the hyperspectral imaging device uses the acquired regional information of the region of interest to determine the hyperspectral data of the region of interest.
[0074] S103, sending the hyperspectral data of the area of interest to a host computer to perform defect detection in the target area.
[0075] Specifically, the hyperspectral imaging device only sends the hyperspectral data of the region of interest to the host computer for defect detection in the target region, rather than sending the hyperspectral data of the entire target region to the host computer.
[0076] In the Micro LED display defect detection method provided in the embodiment of the present application, a hyperspectral imaging device obtains regional information of an area of interest containing suspected defects within a target area of the Micro LED display to be tested. The regional information of the area of interest is determined by a first image taken by a primary inspection device that detects the brightness and / or chromaticity of the Micro LED display to be tested. The area information includes position information of the area of interest within the target area and the size of the area of interest, so that only the hyperspectral data of the area of interest is uploaded to a host computer for defect detection of the target area. Since the area of interest is only a small part of the target area of the Micro LED display to be tested, the amount of hyperspectral data received by the host computer is greatly reduced, thereby improving the detection efficiency and reducing the hardware requirements for processing hyperspectral data, thereby promoting the large-scale application of hyperspectral imaging equipment in Micro LED defect detection.
[0077] In some embodiments, S101 specifically includes:
[0078] receiving area information of the region of interest sent by the initial inspection device, where the area information is determined by the initial inspection device based on the first image; or,
[0079] Receive area information of the region of interest sent by the host computer, where the area information is determined by the initial inspection device or the host computer based on the first image.
[0080] Specifically, the area information of the area of interest containing suspected defects in the target area of the Micro LED display to be tested obtained by the hyperspectral imaging device can be sent by the host computer or the initial inspection device.
[0081] Optionally, the hyperspectral imaging device receives the area information of the area of interest sent by the preliminary inspection device. The preliminary inspection device and the hyperspectral imaging device can communicate directly. After the preliminary inspection device captures the target area to obtain a first image, the internal processor runs a relevant defect detection algorithm to determine the area information of the area of interest containing suspected defects in the target area based on the first image, and the preliminary inspection device sends the area information of the area of interest to the hyperspectral imaging device.
[0082] Optionally, the hyperspectral imaging device receives the regional information of the region of interest sent by the host computer. After the initial inspection device captures the target area to obtain the first image, if the internal processor of the initial inspection device runs the relevant defect detection algorithm to determine the regional information of the region of interest containing suspected defects in the target area based on the first image, since the initial inspection device and the hyperspectral imaging device do not communicate directly, the host computer is used as a forwarding node, and the host computer receives the regional information of the region of interest sent by the initial inspection device and forwards it to the hyperspectral imaging device; if the host computer runs the relevant defect detection algorithm to determine the regional information of the region of interest containing suspected defects in the target area, the initial inspection device sends the captured first image to the host computer, and the host computer determines the regional information of the region of interest based on the first image and sends it to the hyperspectral imaging device.
[0083] In the display defect detection method provided in the embodiment of the present application, a hyperspectral imaging device obtains regional information of an area of interest containing suspected defects in a target area of the Micro LED display to be tested sent by a host computer or a preliminary inspection device, and further clarifies a scheme for obtaining the regional information of the area of interest. The hyperspectral imaging device sends the hyperspectral data of the area of interest to the host computer for defect detection of the target area, which greatly reduces the amount of hyperspectral data received by the host computer, improves detection efficiency, and reduces hardware requirements for processing hyperspectral data, thereby promoting large-scale application of hyperspectral imaging devices in Micro LED defect detection.
[0084] In some embodiments, S102 specifically includes:
[0085] The target area is photographed to obtain a second image, and hyperspectral data of the second image is generated, and the hyperspectral data of the region of interest is filtered out from the hyperspectral data of the second image based on the region information of the region of interest; or,
[0086] The target area is photographed to obtain a second image, the second image is cropped based on the area information of the area of interest to obtain a third image, and hyperspectral data of the area of interest is generated based on the third image; or,
[0087] Based on the area information of the area of interest, the area of interest is photographed to obtain a fourth image, and based on the fourth image, hyperspectral data of the area of interest is generated.
[0088] Specifically, the hyperspectral imaging device determines the hyperspectral data of the region of interest based on the regional information of the region of interest, which may be achieved in the following three ways:
[0089] Method 1: The hyperspectral imaging device captures the target area to obtain a second image, generates hyperspectral data of the second image, and screens out the hyperspectral data of the area of interest from the hyperspectral data of the second image based on the area information of the area of interest.
[0090] The hyperspectral imaging device and the initial inspection device take images of the Micro LED display to be tested, and should both shoot the target area of the Micro LED display to be tested, which can be achieved by setting the placement of the Micro LED display to be tested, the shooting angle and shooting position of the shooting device, etc. The hyperspectral imaging device shoots the target area to obtain a second image, and after generating the second image, which is the complete hyperspectral data of the target area, the hyperspectral data of the area of interest in the second image is further screened.
[0091] The hyperspectral imaging device can shoot the target area through the relevant instructions sent by the host computer, for example, it can trigger the shooting of the target area after receiving the shooting instruction sent by the host computer, for example, it can trigger the shooting of the target area after receiving the area information of the area of interest sent by the host computer; it can also be triggered under certain conditions, such as the Micro LED display to be tested on the detection production line is transmitted at a certain transmission rate, and when the Micro LED display to be tested is transmitted to the shooting position corresponding to the hyperspectral imaging device, the target area is photographed. This is not limited in the embodiments of the present application.
[0092] It should be noted that the hyperspectral imaging device can photograph the target area to obtain a second image after receiving the area information of the area of interest sent by the host computer; it can also receive the area information of the area of interest sent by the host computer after photographing the target area to obtain the second image; or it can receive the area information of the area of interest sent by the host computer while photographing the target area to obtain the second image. This is not limited to the embodiments of the present application.
[0093] Method 2: photograph the target area to obtain a second image, crop the second image based on regional information of the region of interest to obtain a third image, and generate hyperspectral data of the region of interest based on the third image.
[0094] The hyperspectral imaging device can capture the target area to obtain the second image by referring to method 1. After the second image is captured, the second image is cropped based on the regional information of the region of interest to obtain the third image. The hyperspectral data corresponding to the third image is the hyperspectral data of the region of interest. Since the region of interest may be one or more regions within the target area, the third image may also be one or more images, and the number of images is the same as the number of regions of interest. By cropping the second image, the amount of hyperspectral data required to obtain the hyperspectral imaging data can be effectively reduced.
[0095] Method 3: Based on the area information of the area of interest, the area of interest is photographed to obtain a fourth image, and hyperspectral data of the area of interest is generated based on the fourth image.
[0096] After the hyperspectral imaging device obtains the regional information of the region of interest containing suspected defects in the target area, the hyperspectral imaging device can only shoot the region of interest to obtain a fourth image. Since the region of interest may be one or more regions in the target area, the fourth image may also be one or more images, and the number of images is the same as the number of regions of interest. The hyperspectral imaging device shoots the region of interest by adjusting the shooting parameters of the hyperspectral imaging device, the placement position of the Micro LED display to be tested, etc.
[0097] The Micro LED display defect detection method provided in the embodiment of the present application further clarifies how the hyperspectral imaging device obtains the hyperspectral data of the area of interest, effectively reducing the amount of hyperspectral data transmitted by the hyperspectral imaging device to the host computer.
[0098] Figure 2 FIG. 2 is a flow chart of a method for detecting defects in a Micro LED display provided in an embodiment of the present application. Figure 2 As shown, the execution subject of the method is a host computer, and the method at least includes the following steps:
[0099] S201, receiving hyperspectral data of an area of interest containing suspected defects in a target area of a Micro LED display to be tested sent by a hyperspectral imaging device.
[0100] Among them, the regional information of the region of interest is determined based on the first image taken by the initial inspection device of the target area, including the position information of the region of interest in the target area and the size of the region of interest. The initial inspection device is a device for detecting the brightness and / or chromaticity of the MicroLED display to be tested.
[0101] Specifically, the target area refers to the area of the Micro LED display to be tested that can be photographed by the imaging device (hyperspectral imaging device and initial inspection device) at a certain shooting position and shooting angle when the Micro LED display to be tested is placed in a specified position. The target area can be the entire or partial area of the Micro LED display to be tested. The region of interest refers to the area in the image that is designated as requiring special attention and processing, specifically refers to the area containing suspected defects within the target area. The target area may contain one or more regions of interest, and the shape of the region of interest can be regular or irregular. The initial inspection equipment refers to equipment that performs initial defect detection on the brightness and / or chromaticity of the Micro LED display to be tested, such as a high-resolution industrial camera, a brightness meter, a colorimeter, etc.
[0102] The host computer receives the hyperspectral data of the area of interest sent by the hyperspectral imaging device, not the hyperspectral data of the entire target area.
[0103] The hyperspectral imaging device only feeds back the hyperspectral data of the region of interest, which is achieved by obtaining the region information of the region of interest containing the suspected defect in the target area of the Micro LED display to be tested, and the region information at least includes the position information of the region of interest in the target area and the size of the region of interest, and the region information is determined by the first image of the target area taken by the initial inspection device. Among them, the region information of the region of interest is determined by the first image obtained by the initial inspection device taking the target area, which can be achieved by the existing defect detection algorithm related to the initial inspection device.
[0104] S202: Perform defect detection in the target area based on the hyperspectral data of the area of interest.
[0105] Specifically, the host computer completes defect detection in the region of interest based on the hyperspectral data of the region of interest, and at the same time considers that there are no defects in the non-region of interest in the target area, thereby completing defect detection in the entire target area and detecting defects with spectral shift.
[0106] In the Micro LED display defect detection method provided in the embodiment of the present application, the host computer only receives the hyperspectral data of the area of interest containing suspected defects in the target area of the Micro LED display to be tested sent by the hyperspectral imaging device, and completes the defect detection of the target area based on the hyperspectral data of the area of interest. Since the area of interest is only a small part of the target area of the Micro LED display to be tested, the amount of hyperspectral data received by the host computer is greatly reduced, which improves the detection efficiency and reduces the hardware requirements for processing hyperspectral data, thereby promoting the large-scale application of hyperspectral imaging equipment in MicroLED defect detection.
[0107] In some embodiments, the method further comprises:
[0108] Get the region information of the area of interest;
[0109] The regional information of the area of interest is sent to the hyperspectral imaging device.
[0110] Specifically, the region information of the region of interest containing suspected defects in the target area of the Micro LED display to be tested can be sent by the host computer to the hyperspectral imaging device. The host computer first obtains the region information of the region of interest, and then sends the region information of the region of interest to the hyperspectral imaging device, so that the hyperspectral imaging device can screen and feedback the hyperspectral data of the region of interest.
[0111] In some embodiments, obtaining region information of a region of interest includes:
[0112] receiving a first image sent by a preliminary inspection device, and determining area information of an area of interest based on the first image; or,
[0113] Receive area information of the region of interest sent by the initial inspection device, where the area information is determined by the initial inspection device based on the first image.
[0114] Specifically, the region information of the region of interest acquired by the host computer may be determined by the host computer itself based on the first image sent by the initial inspection device, or may be the region information of the region of interest received from the initial inspection device.
[0115] Optionally, the host computer determines the area information of the region of interest based on the first image sent by the initial inspection device. The defect detection algorithm related to the initial inspection device runs on the host computer, the host computer receives the first image of the target area shot by the initial inspection device, and runs the relevant defect detection algorithm to determine the area information of the region of interest.
[0116] Optionally, the host computer receives the area information of the region of interest sent by the initial inspection device. The defect detection algorithm related to the initial inspection device runs on the initial inspection device, and the initial inspection device takes a first image of the target area, runs the relevant defect detection algorithm to determine the area information of the region of interest and sends it to the host computer.
[0117] It can be imagined that when performing the initial inspection using the first image taken by the initial inspection equipment, very accurate detection results are not required. The probability of containing defect-free pixels in the area of interest can be controlled by adjusting the threshold in the relevant defect detection algorithm, so as to facilitate the subsequent use of hyperspectral imaging equipment for defect detection.
[0118] In the Micro LED display defect detection method provided in the embodiment of the present application, the host computer uses the first image of the target area taken by the initial inspection device to determine the area of interest containing defects in the target area, or the initial inspection device uses the first image to determine the area of interest containing defects in the target area and then feeds it back to the host computer, so that the host computer can send the area of interest to the hyperspectral imaging device, thereby receiving the hyperspectral data that only contains the area of interest in the target area fed back by the hyperspectral imaging device, thereby greatly reducing the amount of hyperspectral data that the host computer needs to process.
[0119] Figure 3 is a schematic diagram of the architecture of a Micro LED display defect detection system provided in an embodiment of the present application, such as Figure 3 As shown, the system at least includes a preliminary inspection device 301 , a hyperspectral imaging device 302 and a host computer 303 .
[0120] The initial inspection device 301 is used to capture a target area of the Micro LED display to be tested to obtain a first image, and the first image is used to determine the area information of the area of interest containing defects in the target area, including the position information of the area of interest in the target area and the size of the area of interest.
[0121] Optionally, when the defect detection algorithm is running on the initial inspection device, the initial inspection device 301 determines the region of interest containing defects in the target area based on the first image and uploads it to the host computer 303 or directly sends it to the hyperspectral imaging device 302 .
[0122] Optionally, when the defect detection algorithm is running on the host computer 303, the initial inspection device 301 uploads the captured first image to the host computer 303 to determine the region of interest containing defects in the target area.
[0123] Optionally, the initial inspection device 301 is one or more of an industrial camera, a colorimeter, and a luminance meter. When there are multiple initial inspection devices 301, the host computer can use multiple first images taken by multiple initial inspection devices 301 to comprehensively determine the region of interest, or the host computer uses the initial regions of interest determined by multiple initial inspection devices 301 to comprehensively obtain the final region of interest.
[0124] The hyperspectral imaging device 302 is used to execute the method described in the aforementioned method embodiment using the hyperspectral imaging device as the execution subject.
[0125] The host computer 303 is used to execute the method described in the above method embodiment with the host computer as the execution subject.
[0126] The technical solution provided in the embodiment of the present application is further illustrated below by using a specific example.
[0127] Figure 4 FIG. 3 is a flow chart of a defect detection method for a Micro LED display provided in an embodiment of the present application. Figure 4 As shown, the method at least includes: first, using an industrial camera to capture an image of the Micro LED display to be tested, and running a defect detection algorithm to determine the regional information of the area of interest; the host computer sends the regional information of the area of interest to the hyperspectral imager; the hyperspectral imager obtains the hyperspectral data of the area of interest and uploads it to the host computer. Since the area of interest is only a small part of the Micro LED shooting area to be tested, the data can be ignored. The majority, therefore, can significantly reduce the amount of hyperspectral data that the host computer needs to process, and reduce the requirements for transmission bandwidth and computing power.
[0128] Figure 5 is one of the structural schematic diagrams of the Micro LED display defect detection device provided in the embodiment of the present application, such as Figure 5, the device at least comprises:
[0129] An acquisition module 501 is used to acquire region information of a region of interest containing suspected defects in a target region of the Micro LED display to be tested, where the region information of the region of interest is determined based on a first image of the target region taken by a preliminary inspection device, including position information of the region of interest in the target region and a size of the region of interest, where the preliminary inspection device is a device for detecting brightness and / or chromaticity of the Micro LED display to be tested;
[0130] A determination module 502 is used to determine the hyperspectral data of the region of interest based on the region information of the region of interest;
[0131] The sending module 503 is used to send the hyperspectral data of the region of interest to the host computer for defect detection in the target region.
[0132] In some embodiments, the acquisition module 501 specifically includes:
[0133] A first receiving unit is configured to receive region information of a region of interest sent by a preliminary inspection device, where the region information is determined by the preliminary inspection device based on the first image; or
[0134] The second receiving unit is used to receive the region information of the region of interest sent by the host computer, where the region information is determined by the initial inspection device or the host computer based on the first image.
[0135] In some embodiments, the determination module 502 specifically includes:
[0136] A first generating unit is used to photograph the target area to obtain a second image, generate hyperspectral data of the second image, and filter out the hyperspectral data of the region of interest from the hyperspectral data of the second image based on the region information of the region of interest; or
[0137] A second generating unit is configured to photograph the target area to obtain a second image, crop the second image based on the area information of the region of interest to obtain a third image, and generate hyperspectral data of the region of interest based on the third image; or
[0138] The third generating unit is used to photograph the region of interest based on the region information of the region of interest to obtain a fourth image, and generate hyperspectral data of the region of interest based on the fourth image.
[0139] It is understandable that the detailed functional implementation of each of the above-mentioned units / modules can be referred to the introduction in the above-mentioned method embodiment with the hyperspectral imaging device as the execution subject, and no further description is given here. It should be understood that the above-mentioned device is used to execute the method in the above-mentioned embodiment, and the corresponding program module in the device has a similar implementation principle and technical effect as described in the above-mentioned method. The working process of the device can refer to the corresponding process in the above-mentioned method, and no further description is given here.
[0140] Figure 6 2 is a schematic diagram of the structure of the Micro LED display defect detection device provided in the embodiment of the present application. Figure 6 , the device at least comprises:
[0141] A receiving module 601 is used to receive hyperspectral data of an area of interest containing suspected defects in a target area of the Micro LED display to be tested sent by a hyperspectral imaging device, wherein the area information of the area of interest is determined based on a first image of the target area taken by a preliminary inspection device, including position information of the area of interest in the target area and a size of the area of interest, and the preliminary inspection device is a device for detecting brightness and / or chromaticity of the Micro LED display to be tested;
[0142] The detection module 602 is used to perform defect detection in the target area based on the hyperspectral data of the area of interest.
[0143] In some embodiments, the apparatus further comprises:
[0144] An acquisition module, used for acquiring area information of an area of interest;
[0145] The sending module is used to send the area information of the area of interest to the hyperspectral imaging device.
[0146] In some embodiments, the acquisition module specifically includes:
[0147] A first receiving unit is configured to receive a first image sent by a preliminary inspection device, and determine area information of an area of interest based on the first image; or
[0148] The second receiving unit is used to receive the area information of the area of interest sent by the initial inspection device, where the area information is determined by the initial inspection device based on the first image.
[0149] It is understandable that the detailed functional implementation of each of the above-mentioned units / modules can be referred to the introduction in the above-mentioned method embodiment with the host computer as the execution subject, and no further description is given here. It should be understood that the above-mentioned device is used to execute the method in the above-mentioned embodiment, and the corresponding program module in the device has a similar implementation principle and technical effect as described in the above-mentioned method. The working process of the device can refer to the corresponding process in the above-mentioned method, and no further description is given here.
[0150] Figure 7 is a schematic diagram of the structure of a hyperspectral imaging device provided in an embodiment of the present application, such as Figure 7 As shown, the electronic device may include: a processor 701, a communication interface 702, a memory 703 and a communication bus 704, wherein the processor 701, the communication interface 702 and the memory 703 communicate with each other through the communication bus 704. The processor 701 may call the software instructions in the memory 703 to execute the method described in the above embodiment with the hyperspectral imaging device as the execution subject.
[0151] In addition, the logic instructions in the above-mentioned memory 703 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the relevant technology or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present application.
[0152] Figure 8 is a schematic diagram of the structure of the host computer provided in the embodiment of the present application, such as Figure 8 As shown, the electronic device may include: a processor 801, a communication interface 802, a memory 803 and a communication bus 804, wherein the processor 801, the communication interface 802 and the memory 803 communicate with each other via the communication bus 804. The processor 801 may call the software instructions in the memory 803 to execute the method described in the above embodiment with the host computer as the execution subject.
[0153] In addition, the logic instructions in the above-mentioned memory 803 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the relevant technology or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present application.
[0154] Based on the method in the above embodiment, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method in the above embodiment with the hyperspectral imaging device as the execution subject, or executes the method in the above embodiment with the host computer as the execution subject.
[0155] Based on the method in the above embodiment, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method in the above embodiment with the hyperspectral imaging device as the execution subject, or executes the method in the above embodiment with the host computer as the execution subject.
[0156] It is understandable that the processor in the embodiment of the present application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.
[0157] The method steps in the embodiments of the present application can be implemented by hardware, or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (Random Access Memory, RAM), flash memory, read-only memory (Read-Only Memory, ROM), programmable read-only memory (Programmable ROM, PROM), erasable programmable read-only memory (Erasable PROM, EPROM), electrically erasable programmable read-only memory (Electrically EPROM, EEPROM), registers, hard disks, mobile hard disks, CD-ROMs or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.
[0158] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loading and executing computer program instructions on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted by a computer-readable storage medium. The computer instructions can be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server, a data center, etc. that contains one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.
[0159] It should be understood that the various numerical numbers involved in the embodiments of the present application are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application.
[0160] It is easy for those skilled in the art to understand that the above are only preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of protection of the present application.
Claims
1. A Micro LED display defect detection method, characterized in that: Applications in hyperspectral imaging equipment include: Acquire area information of an area of interest containing suspected defects in a target area of the Micro LED display to be tested, where the area information of the area of interest is determined based on a first image taken by a preliminary inspection device of the target area, including position information of the area of interest within the target area and a size of the area of interest, wherein the preliminary inspection device is a device for detecting brightness and / or chromaticity of the Micro LED display to be tested; Based on the area information of the area of interest, determining the hyperspectral data of the area of interest; The hyperspectral data of the region of interest is sent to a host computer to perform defect detection on the target region.
2. The Micro LED display defect detection method according to claim 1, characterized in that: The obtaining of the region information of the region of interest containing suspected defects in the target region of the Micro LED display to be tested includes: receiving area information of a region of interest sent by the initial inspection device, where the area information is determined by the initial inspection device based on the first image; or, Receive area information of a region of interest sent by the host computer, where the area information is determined by the initial inspection device or the host computer based on the first image.
3. The Micro LED display defect detection method according to claim 1, characterized in that: The step of determining the hyperspectral data of the region of interest comprises: The target area is photographed to obtain a second image, hyperspectral data of the second image is generated, and the hyperspectral data of the region of interest is filtered out from the hyperspectral data of the second image based on the region information of the region of interest; or The target area is photographed to obtain a second image, the second image is cropped based on the area information of the region of interest to obtain a third image, and the hyperspectral data of the region of interest is generated based on the third image; or, Based on the area information of the area of interest, the area of interest is photographed to obtain a fourth image, and based on the fourth image, hyperspectral data of the area of interest is generated.
4. A method for detecting defects in a Micro LED display, characterized in that: Applied to the host computer, including: Receive hyperspectral data of an area of interest containing suspected defects in a target area of the Micro LED display to be tested sent by a hyperspectral imaging device, wherein the area information of the area of interest is determined based on a first image taken by a preliminary inspection device of the target area, including position information of the area of interest within the target area and a size of the area of interest, wherein the preliminary inspection device is a device for detecting brightness and / or chromaticity of the Micro LED display to be tested; Defect detection of the target area is performed based on the hyperspectral data of the area of interest.
5. The Micro LED display defect detection method according to claim 4, characterized in that: The method further comprises: Acquire the area information of the area of interest; The region information of the region of interest is sent to the hyperspectral imaging device.
6. The Micro LED display defect detection method according to claim 5, characterized in that: The acquiring the area information of the area of interest includes: receiving the first image sent by the initial inspection device, and determining the area information of the region of interest based on the first image; or, Receive area information of the region of interest sent by the initial inspection device, where the area information is determined by the initial inspection device based on the first image.
7. A Micro LED display defect detection system, characterized in that: include: A preliminary inspection device, used for photographing a target area of the Micro LED display to be tested to obtain a first image, wherein the first image is used to determine area information of an area of interest containing defects within the target area, including position information of the area of interest within the target area and a size of the area of interest; A hyperspectral imaging device, used to perform the display defect detection method according to any one of claims 1 to 3; A host computer, used to execute the display defect detection method as described in any one of claims 4 to 6.
8. The Micro LED display defect detection system according to claim 7, characterized in that: The initial inspection equipment is one or more of an industrial camera, a colorimeter and a brightness meter.
9. A Micro LED display defect detection device, characterized in that: include: an acquisition module, configured to acquire area information of an area of interest containing suspected defects within a target area of the Micro LED display to be tested, wherein the area information of the area of interest is determined based on a first image captured by a preliminary inspection device of the target area, including position information of the area of interest within the target area and a size of the area of interest, wherein the preliminary inspection device is a device for detecting brightness and / or chromaticity of the Micro LED display to be tested; A determination module, configured to determine the hyperspectral data of the region of interest based on the region information of the region of interest; The sending module is used to send the hyperspectral data of the region of interest to a host computer for defect detection of the target region.
10. A Micro LED display defect detection device, characterized in that: include: A receiving module, configured to receive hyperspectral data of an area of interest containing suspected defects within a target area of a Micro LED display to be tested sent by a hyperspectral imaging device, wherein area information of the area of interest is determined based on a first image taken by a preliminary inspection device of the target area, including position information of the area of interest within the target area and a size of the area of interest, wherein the preliminary inspection device is a device for detecting brightness and / or chromaticity of the Micro LED display to be tested; A detection module is used to perform defect detection on the target area based on the hyperspectral data of the area of interest.
