Micro-LED testing equipment and testing methods

Abstract

The present application discloses a Micro-LED detection device and detection method, which belongs to the field of Micro-LED detection technology. The device includes a motion table, a laser, an objective lens, a reflector, a collector, a semi-transparent and semi-reflective mirror, a first grayscale camera, and a second grayscale camera. In the above scheme provided by the present application, when the reflector is in the first position, the light emitted after the objective lens imaging passes through the semi-transparent and semi-reflective mirror, and then enters the first grayscale camera and the second grayscale camera respectively, and then is sent to the computer through the image acquisition card; when the reflector is in the second position, the light emitted after the objective lens imaging passes through the reflector and enters the collector, and the collector calibrates the light image through the standard spectrum or chromaticity, and the calibrated light image is sent to the computer through the image acquisition card, and the computer then analyzes and calculates the calibrated light image and the light image processed by the grayscale camera, thereby realizing fast and high-precision detection of Micro-LED.

Description

Technical Field

[0001] The present application relates to the field of Micro-LED detection technology, and in particular to a Micro-LED detection device and detection method. Background Art

[0002] The yield rate of Micro-LED (Micro-Light Emitting Diode) is a key problem restricting its marketization. Photoluminescence detection at the wafer level is one of the important means to improve its yield rate.

[0003] The Micro-LED detection device in the related art has low detection speed and low accuracy during detection and cannot meet the requirements. Summary of the invention

[0004] In view of the above problems, the present application provides a Micro-LED detection device and detection method, which can solve the problems of low detection speed and low accuracy during detection of existing detection devices.

[0005] In order to solve the above technical problems, the present application proposes a Micro-LED detection device, including: a motion platform, a laser, an objective lens, a reflector, a collector, a semi-transparent and semi-reflective mirror, a first grayscale camera, a second grayscale camera, an image acquisition card and a computer, wherein the first grayscale camera is provided with a first filter, and the second grayscale camera is provided with a second filter;

[0006] The moving stage is used to carry the sample, and the light emitted by the laser can irradiate the sample and then form an image through the objective lens;

[0007] The reflector is located above the objective lens along the first direction, and has a first position and a second position relative to the objective lens. When the reflector is in the first position, the light emitted after the objective lens forms an image passes through the semi-transparent and semi-reflective mirrors and enters the first grayscale camera and the second grayscale camera respectively; when the reflector is in the second position, the light emitted after the objective lens forms an image passes through the reflector and enters the collector;

[0008] The image acquisition card is used to acquire image signals from the first grayscale camera, the second grayscale camera, and the collector into the computer.

[0009] In the technical solution of the embodiment of the present application, photoluminescence is formed after the sample is irradiated by a laser, and the light is imaged after passing through the objective lens. When the reflector is in the first position, the light emitted after the objective lens is imaged passes through the semi-transparent and semi-reflective mirror and enters the first grayscale camera and the second grayscale camera respectively. The first grayscale camera and the second grayscale camera process the light image and send it to the computer through the image acquisition card; when the reflector is in the second position, the light emitted after the objective lens is imaged passes through the reflector and enters the collector. The collector calibrates the light image through a standard spectrum or chromaticity, and the calibrated light image is sent to the computer through the image acquisition card. The computer then analyzes and calculates the calibrated light image and the light image processed by the grayscale camera, thereby realizing fast and high-precision detection of Micro-LED.

[0010] In one embodiment, the Micro-LED detection device also includes a driving member, which is connected to the moving table and is used to drive the moving table to move along a first direction, a second direction and a third direction, wherein the first direction intersects with the second direction, and the third direction intersects with a plane formed by the first direction and the second direction.

[0011] In one of the embodiments, the Micro-LED detection device further includes a driver, which is connected to the objective lens and is used to drive the objective lens to move along the second direction.

[0012] In one of the embodiments, the Micro-LED detection device further includes a focusing lens, and the focusing lens is disposed on the objective lens.

[0013] In one embodiment, the semi-transparent and semi-reflective mirror forms an angle of 45° with the first direction.

[0014] In one embodiment, the reflected light of the reflector forms an angle of 90° with the light emitted after imaging by the objective lens.

[0015] In one embodiment, a first rotating wheel is disposed on the first grayscale camera, and the first filter is disposed on the first rotating wheel.

[0016] In one embodiment, a second rotating wheel is disposed on the second grayscale camera, and the second filter is disposed on the second rotating wheel.

[0017] In one embodiment, the first filter and the second filter are both long pass filters;

[0018] Under the conditions that the peak wavelength of the luminescence spectrum of the sample is a, the half-width is b, the central wavelength of the laser light source is c, and the half-width of the excitation light source is d, the short cut-off wavelength of the long-pass filter is a-0.618b, and the long cut-off wavelength is a+0.618b.

[0019] In one embodiment, the first filter is a long pass filter or a band pass filter, and the second filter is a band pass filter or a long pass filter;

[0020] Under the conditions that the peak wavelength of the luminescence spectrum of the sample is a, the half-width is b, the central wavelength of the laser light source is c, and the half-width of the excitation light source is d, the cut-off wavelength of the long-pass filter is a-0.618b, the upper cut-off wavelength of the band-pass filter is a+0.618b, and the lower cut-off wavelength is c+1.5d.

[0021] The present application also provides a Micro-LED detection method, which is applied to the Micro-LED detection device as described in any one of the embodiments of the present application, and the Micro-LED detection method includes:

[0022] A regression model of dual optical paths and main wavelength, peak wavelength, and color purity parameters is established through an artificial intelligence algorithm; wherein the artificial intelligence algorithm includes a neural network method, a tree regression algorithm, a random forest method, and a supervised learning method.

[0023] In one of the embodiments, the Micro-LED detection method includes: placing a whiteboard on a moving table, turning on a laser, moving a reflector to a second position, and calculating a flat field correction coefficient of a collector by normalization.

[0024] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the embodiments below. The accompanying drawings are only for the purpose of illustrating the embodiments and are not to be considered as limiting the present application. Moreover, the same reference numerals are used throughout the drawings to represent the same components. In the drawings:

[0026] Figure 1 A schematic diagram of a Micro-LED detection device according to some embodiments of the present application;

[0027] Figure 2 A schematic diagram of a filter assembly according to some embodiments of the present application;

[0028] Figure 3 A schematic diagram of a light emitting parameter calculation model for some embodiments of the present application;

[0029] Figure 4 A schematic diagram of decision tree regression for some embodiments of the present application;

[0030] Figure 5 This is a schematic diagram of flat field correction according to some embodiments of the present application.

[0031] The reference numerals in the specific implementation manner are as follows:

[0032] 10. Sample; 11. Moving table; 12. Laser; 13. Driver; 14. Objective lens; 15. Reflector; 16. Collector; 17. Semi-transparent and semi-reflective mirror; 18. First grayscale camera; 19. First rotating wheel; 20. Second grayscale camera; 21. Second rotating wheel; 22. Image acquisition card; 23. Computer. DETAILED DESCRIPTION

[0033] The following embodiments of the technical solution of the present application are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0035] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0036] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0037] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0038] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0039] In the description of the embodiments of the present application, the technical terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, which are only for the convenience of describing the embodiments of the present application and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the embodiments of the present application.

[0040] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0041] Below, this application is described in detail.

[0042] The yield rate of Micro-LED (Micro-Light Emitting Diode) is a key problem restricting its marketization. Photoluminescence detection at the wafer level is one of the important means to improve its yield rate.

[0043] At present, common detection methods include those based on spectroscopy and colorimeters, but these methods are difficult to achieve both high precision and high speed. The point scanning spectral detection method can achieve high detection accuracy, but the detection speed is far from meeting the production line requirements. For methods such as colorimetric imaging, although the speed can meet the production line requirements, the detection accuracy cannot meet future needs.

[0044] In order to solve the problems of low detection speed and low accuracy in existing detection devices, such as Figure 1 As shown, the present application discloses a Micro-LED detection device, which includes: a motion stage 11, a laser 12, an objective lens 14, a reflector 15, a collector 16, a semi-transparent and semi-reflective mirror 17, a first grayscale camera 18, a second grayscale camera 20, an image acquisition card 22, and a computer 23. The first grayscale camera 18 is provided with a first filter, and the second grayscale camera 20 is provided with a second filter.

[0045] Among them, the moving table 11 is used to carry the sample 10, and the light emitted by the laser 12 can irradiate the sample 10 and then form an image through the objective lens 14; the reflector 15 is located above the objective lens 14 along the first direction, and the reflector 15 has a first position and a second position relative to the objective lens 14. When the reflector 15 is in the first position, the light emitted after the objective lens 14 forms an image passes through the semi-transparent and semi-reflective mirror 17 and enters the first grayscale camera 18 and the second grayscale camera 20 respectively; when the reflector 15 is in the second position, the light emitted after the objective lens 14 forms an image passes through the reflector 15 and enters the collector 16; the image acquisition card 22 is used to collect image signals in the first grayscale camera 18, the second grayscale camera 20, and the collector 16 into the computer 23.

[0046] In this embodiment, if Figure 1 As shown, the first direction is the X-axis direction, and the first position is the position where the reflector 15 is at h. At this time, the objective lens 14 is directly opposite to the semi-transparent and semi-reflective mirror 17, and the light emitted after the objective lens 14 forms an image can be irradiated onto the semi-transparent and semi-reflective mirror 17; the second position is the position where the reflector 15 is at i. At this time, the objective lens 14 is directly opposite to the reflector 15, and the reflector 15 is located between the objective lens 14 and the semi-transparent and semi-reflective mirror 17, and the light emitted after the objective lens 14 forms an image cannot be irradiated onto the semi-transparent and semi-reflective mirror 17.

[0047] The collector 16 in this embodiment is set with a standard spectrum and / or chromaticity before use. The collector 16 can use a spectrum\chromaticity acquisition device, such as a hyperspectral camera, a chromaticity imager, etc. The specific one can be determined according to actual conditions, and this specification embodiment does not limit this.

[0048] In the technical solution of the embodiment of the present application, photoluminescence is formed after the sample 10 is irradiated by the laser 12, and the light is imaged after passing through the objective lens 14. When the reflector 15 is in the first position, the light emitted after the objective lens 14 forms an image passes through the semi-transparent and semi-reflective mirror 17, and then enters the first grayscale camera 18 and the second grayscale camera 20 respectively. The first grayscale camera 18 and the second grayscale camera 20 process the light image and send it to the computer 23 through the image acquisition card 22; when the reflector 15 is in the second position, the light emitted after the objective lens 14 forms an image passes through the reflector 15 and then enters the collector 16. The collector 16 calibrates the light image through a standard spectrum or chromaticity, and the calibrated light image is sent to the computer 23 through the image acquisition card 22. The computer 23 then analyzes and calculates the calibrated light image and the light image processed by the grayscale camera, thereby realizing fast and high-precision detection of Micro-LED.

[0049] According to some embodiments of the present application, the Micro-LED detection device also includes a driving member (not marked in the figure), which is connected to the moving table 11 and is used to drive the moving table 11 to move along a first direction, a second direction and a third direction, wherein the first direction intersects with the second direction, and the third direction intersects with a plane formed by the first direction and the second direction.

[0050] In this embodiment, if Figure 1 As shown, the first direction is the X-axis direction, the second direction is the Y-axis direction, and the third direction is the Z-axis direction, wherein the angle between the X-axis and the Y-axis may be 80°, 85°, 90°, etc., and this embodiment is described by taking the X-axis and the Y-axis being perpendicular to each other as an example. The angle between the Z-axis and the plane formed by the X-axis and the Y-axis may be 80°, 85°, 90°, etc., and this embodiment is described by taking the Z-axis being perpendicular to the plane formed by the X-axis and the Y-axis as an example.

[0051] In this embodiment, the driving member may be a mechanical arm, an electric telescopic rod, etc., and the specific driving member may be determined according to actual conditions, and this specification does not limit this.

[0052] In this embodiment, the driving member drives the moving stage 11 to move in the X, Y, and Z directions, so that the sample 10 on the moving stage 11 can be easily moved in the X, Y, and Z directions, thereby ensuring the position of the sample 10 and the objective lens 14.

[0053] According to some embodiments of the present application, Figure 1 As shown, the Micro-LED detection device also includes a driver 13, which is connected to the objective lens 14 and is used to move the objective lens 14 along the second direction.

[0054] The driver 13 in this embodiment can be a mechanical arm, a hydraulic rod, etc. The specific one can be determined according to actual conditions, and this embodiment of the specification does not limit this.

[0055] The objective lens 14 is moved in the Y-axis direction by the driver 13 , so that the relative position of the objective lens 14 and the sample 10 on the moving stage 11 can be ensured.

[0056] According to some embodiments of the present application, the Micro-LED detection device further includes a focusing lens, which is disposed on the objective lens 14. In this way, it can be ensured that the image on the objective lens 14 is within the depth of field.

[0057] According to some embodiments of the present application, Figure 1 As shown, the semi-transparent and semi-reflective mirror 17 forms an angle of 45° with the first direction. Of course, it can be understood that the angle between the semi-transparent and semi-reflective mirror 17 and the first direction can also be 30°, 40°, etc. The specific angle can be determined according to actual conditions, and the embodiments of this specification do not limit this.

[0058] Since the semi-transparent and semi-reflective mirror 17 forms an angle of 45° with the X-axis direction, when the light emitted by the objective lens 14 after imaging is refracted by the semi-transparent and semi-reflective mirror 17, part of it will enter the first grayscale camera 18 and the other part will enter the second grayscale camera 20.

[0059] According to some embodiments of the present application, Figure 1 As shown, the reflected light of the reflector 15 forms an angle of 90° with the light emitted after the image is formed by the objective lens 14. In this way, the light emitted after the image is formed by the objective lens 14 will all enter the collector 16 after passing through the reflector 15.

[0060] According to some embodiments of the present application, a first rotating wheel 19 is disposed on the first grayscale camera 18 , and the first filter is disposed on the first rotating wheel 19 .

[0061] In this embodiment, a plurality of first optical filters are mounted on the first rotating wheel 19 , and the absorption wavelengths of the plurality of first optical filters are all different. When in use, the first rotating wheel 19 can be rotated as needed so that one of the first optical filters is directly opposite to the lens of the first grayscale camera 18 .

[0062] According to some embodiments of the present application, a second rotating wheel 21 is disposed on the second grayscale camera 20 , and a second filter is disposed on the second rotating wheel 21 .

[0063] The second rotating wheel 21 in this embodiment has the same structure as the first rotating wheel 19, and will not be described in detail here. By arranging a plurality of second optical filters on the second rotating wheel 21, and the absorption wavelengths of the plurality of second optical filters are all different, the second rotating wheel 21 can be rotated as needed to make one of the second optical filters face the second grayscale camera 20. At this time, the absorption wavelength of the second optical filter facing the second grayscale camera 20 meets the use requirements.

[0064] According to some embodiments of the present application, the first filter and the second filter are both long-pass filters; Figure 2 As shown in (a), the ordinate represents the spectral response value (unitless), the abscissa represents the wavelength, and the unit is nanometers. Under the conditions that the peak wavelength of the luminescence spectrum of sample 10 is a, the half-width is b, the central wavelength of the laser 12 light source is c, and the half-width of the excitation light source is d, the short cut-off wavelength of the long-pass filter is a-0.618b, and the long cut-off wavelength is a+0.618b.

[0065] The parameters of the sample 10 finally obtained by the computer 23 in this embodiment can adopt artificial intelligence algorithms, including supervised learning methods such as neural network method, tree regression algorithm, random forest method and support vector method.

[0066] Figure 3 It is a schematic diagram of the neural network algorithm model. When using the algorithm, the input layer, hidden layer and output layer are first constructed, wherein the input layer is the result collected by the first grayscale camera 18 and the second grayscale camera 20, and the output layer is the luminous parameters that can be calculated through the spectrum, such as the main wavelength, peak wavelength and color purity commonly used in the production line.

[0067] Hidden layers are the layers that lie between the input layer and the output layer. They are the heart of the neural network as they perform most of the computation and feature extraction. The output layer is the last layer of the neural network and is responsible for producing the final prediction or classification result.

[0068] Tree regression algorithms include but are not limited to decision tree regression, XGBoost, LightGBM, ADaBoost, GBDT, etc. Figure 4 As shown, Wi represents the value of the i-th band of the input spectrum, Ci represents the main wavelength or color purity, and Vi represents the specific threshold value corresponding to the i-th band of the spectral response.

[0069] Taking decision tree regression as an example, the parameters of the decision tree model, such as segmentation strategy, maximum depth and minimum number of samples, are adjusted according to the given spectral data. The final leaf node outputs a numerical value about the luminescence parameters, such as the main wavelength, peak wavelength and color purity.

[0070] When the detection device of this embodiment is used, the laser 12 and the collector 16 are first calibrated by the flat field calibration method.

[0071] The flat field correction method uses a white plate with uniform reflectivity to correct the inconsistency of the response of the laser 12 and the collector 16. The specific method includes selecting a white plate that can cover the detection field of view, and the white plate is detected as the scanning motion stage 11 moves. Because the white plate is uniform, theoretically the consistency of the laser 12 and the collector 16 is very good, so the acquired data is flat, but in fact it is not the case. Therefore, the flat field correction coefficient of the laser 12 and the collector 16 can be obtained through normalized calculation. Figure 5 As shown in the figure, the flat field correction coefficient is calculated, and another area is selected to verify the correction effect. From the correction results, it can be seen that the flat field correction can eliminate the errors caused by detector inconsistency and light source non-uniformity.

[0072] When the short cutoff wavelength of the long pass filter is a-0.618b and the long cutoff wavelength is a+0.618b, the data collected by the first grayscale camera 18 and the second grayscale camera 20 are first pre-processed by flat field correction and then applied subsequently.

[0073] When in use, by adjusting the position of the reflector 15, the measurement values ​​of the two grayscale cameras and the corresponding parameters collected by the collector 16 can be obtained. Then, a neural network supervised learning model is constructed, in which the input layer is the results collected by the two grayscale cameras, and the output layer is the output parameters of the collector 16, or indirect parameters that can be calculated through its parameters. Commonly used luminous parameters of the production line include the main wavelength, peak wavelength, and color purity. After training with a large amount of test set data, it can be directly applied to defect detection.

[0074] Alternatively, an XGBoost ensemble learning model is constructed, the acquisition results of the two grayscale cameras are used as the input data set, and the parameters detected by the collector 16, i.e., the spectrometer\colorimeter, are used as the corresponding labels. The data set and the label are divided into k mutually exclusive subsets, and k-fold cross validation is performed, that is, k-1 subsets are constructed as training sets, and 1 subset is used as a validation set. The learning rate, maximum depth, number of trees, etc. are set, and after completing j rounds of cross validation, the model with the best performance is selected.

[0075] According to some embodiments of the present application, the first filter is a long pass filter or a band pass filter, and the second filter is a band pass filter or a long pass filter; Figure 2 As shown in (b), the ordinate represents the spectral response value (unitless), the abscissa represents the wavelength, and the unit is nanometers. Under the conditions that the peak wavelength of the luminescence spectrum of sample 10 is a, the half-width is b, the central wavelength of the laser 12 light source is c, and the half-width of the excitation light source is d, the cut-off wavelength of the long-pass filter is a-0.618b, the upper cut-off wavelength of the band-pass filter is a+0.618b, and the lower cut-off wavelength is c+1.5d.

[0076] When in use, by changing the position of the reflector 15, the measurement values ​​of the two grayscale cameras and the parameters of the corresponding collector 16, i.e., the spectrometer\colorimeter, can be obtained. A neural network supervised learning model is constructed, in which the input layer is the results of the two grayscale cameras, and the output layer is the output parameters of the spectrometer\colorimeter, or indirect parameters that can be calculated from its parameters. Commonly used luminous parameters of the production line include the main wavelength, peak wavelength, and color purity. After training with a large amount of test set data, it can be directly applied to defect detection.

[0077] Alternatively, an XGBoost ensemble learning model is constructed, the acquisition results of the two grayscale cameras are used as the input data set, and the parameters detected by the collector 16, i.e., the spectrometer\colorimeter, are used as the corresponding labels. The data set and the label are divided into k mutually exclusive subsets, and k-fold cross validation is performed, that is, k-1 subsets are constructed as training sets, and 1 subset is used as a validation set. The learning rate, maximum depth, number of trees, etc. are set, and after completing j rounds of cross validation, the model with the best performance is selected.

[0078] The present application also provides a Micro-LED detection method, which is applied to a Micro-LED detection device as in any one of the embodiments of the present application, and the Micro-LED detection method includes:

[0079] A regression model of dual optical paths and main wavelength, peak wavelength, and color purity parameters is established through artificial intelligence algorithms; among them, artificial intelligence algorithms include neural network method, tree regression algorithm, random forest method, and supervised learning method.

[0080] According to some embodiments of the present application, the Micro-LED detection method includes: placing a whiteboard on a moving table, turning on the laser, moving the reflector to a second position, and calculating the flat field correction coefficient of the collector through normalization.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and specification of the present application. In particular, as long as there is no structural conflict, the various technical features mentioned in the various embodiments can be combined in any way. The present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions that fall within the scope of the claims.

Claims

1. A Micro-LED detection method, applied to a Micro-LED detection device, wherein the Micro-LED detection device, include: A motion stage, a laser, an objective lens, a reflector, a collector, a semi-transparent and semi-reflective mirror, a first grayscale camera, a second grayscale camera, an image acquisition card and a computer, wherein the first grayscale camera is provided with a first filter, and the second grayscale camera is provided with a second filter; The moving stage is used to carry the sample, and the light emitted by the laser can irradiate the sample and then form an image through the objective lens; The reflector is located above the objective lens along the first direction, and has a first position and a second position relative to the objective lens. When the reflector is in the first position, light emitted after imaging by the objective lens passes through the semi-transparent and semi-reflective mirrors and enters the first grayscale camera and the second grayscale camera respectively. When the reflector is in the second position, the light emitted by the objective lens after imaging passes through the reflector and enters the collector; The image acquisition card is used to collect image signals from the first grayscale camera, the second grayscale camera, and the collector into the computer; the Micro-LED detection device also includes a driving member, which is connected to the motion stage and is used to drive the motion stage to move along a first direction, a second direction, and a third direction, wherein the first direction and the second direction intersect, and the third direction intersects with a plane formed by the first direction and the second direction; the Micro-LED detection device also includes a driver, which is connected to the objective lens and is used to drive the objective lens to move along the second direction; the Micro-LED detection device also includes a focusing lens, which is arranged on the objective lens; The semi-transparent and semi-reflective mirror forms an angle of 45° with the first direction; the reflected light of the reflector forms an angle of 90° with the light emitted after imaging by the objective lens; The first grayscale camera is provided with a first rotating wheel, and the first optical filter is provided on the first rotating wheel; the second grayscale camera is provided with a second rotating wheel, and the second optical filter is provided on the second rotating wheel; The first filter and the second filter are long-pass filters or band-pass filters; the collector is a hyperspectral camera or a chromaticity imager; and the Micro-LED detection method includes: After the sample is irradiated with a laser, photoluminescence is generated, and the light is imaged after passing through the objective lens. When the reflector is in the first position, the light emitted after the objective lens image is formed passes through the semi-transparent and semi-reflective mirrors and enters the first grayscale camera and the second grayscale camera respectively. The first grayscale camera and the second grayscale camera process the light image and send it to the computer through the image acquisition card; When the reflector is in the second position, the light emitted after the objective lens imaging will pass through the reflector and enter the collector, the collector calibrates the light image through the standard spectrum or chromaticity, the calibrated light image is sent to the computer through the image acquisition card, and the computer then analyzes and calculates the calibrated light image and the light image processed by the grayscale camera; a regression model of the dual light path and the main wavelength, peak wavelength and color purity parameters is established through an artificial intelligence algorithm; wherein the artificial intelligence algorithm includes a neural network method, a tree regression algorithm, a random forest method and a supervised learning method; Construct a neural network supervised learning model, where the input layer is the results collected by two grayscale cameras, and the output layer is the collector output parameters, where the output parameters include the main wavelength, peak wavelength and color purity; Alternatively, an XGBoost integrated learning model is constructed, the acquisition results of the two grayscale cameras are used as the input data set, and the parameters detected by the collector are used as corresponding labels, wherein the parameters detected by the collector include the main wavelength, the peak wavelength and the color purity.

2. The Micro-LED detection method according to claim 1, It is characterized in that The Micro-LED detection method includes: placing a whiteboard on a moving table, turning on a laser, moving a reflector to a second position, and calculating a flat field correction coefficient of a collector by normalization.

Images