Industrial computer screen dust particle detection device and method based on artificial intelligence

Abstract

The invention relates to the technical field of screen dust particle detection, in particular to an industrial computer screen dust particle detection device and method based on artificial intelligence. The industrial electron microscope is matched with a high-power lens amplification macro lens and an image recognition algorithm, dust particles can be accurately recognized, the omission ratio and the error rate of manual visual inspection are remarkably reduced, and full-screen automatic scanning of a to-be-detected industrial computer screen is achieved through cooperation of a three-axis motor movement system and a single industrial electron microscope. In combination with a size calibration function of a microscope measurement correction ruler, a single device can adapt to detection requirements of screens with different sizes, full-screen images are automatically analyzed through an image recognition algorithm built in a computer, and a structured report containing impurity quantity, size, position coordinates and screen qualification degree is output in real time; the technical problems that in the detection process of an existing industrial computer display panel, the error rate is high, the detection cost is high, and intelligent analysis is lacked are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of screen dust particle detection, and in particular to an industrial computer screen dust particle detection device and method based on artificial intelligence. Background Art

[0002] Currently, the industrial computer display panel manufacturing industry is facing the challenge of increasingly stringent impurity detection standards. Traditional detection methods are no longer able to meet the high standards and high precision requirements of the 0.3-0.5mm micro-foreign object detection standards currently commonly implemented in the display panel industry. Current technologies mainly rely on manual visual inspection, which has three core problems: First, due to the physiological limitations of the human eye, the recognition error rate of submillimeter-level foreign objects is high. Especially in continuous operation, the missed detection rate caused by visual fatigue may exceed industry safety standards; second, to achieve full coverage of large-size screens, high-resolution imaging equipment needs to be configured with multiple optical modules working in parallel, which leads to a sharp increase in hardware costs; finally, detection data remains only in the isolated image archiving stage, lacks efficient intelligent analysis methods, and relies on manual experience to classify defect types. Summary of the Invention

[0003] In response to the shortcomings of the existing technology, the present invention provides an artificial intelligence-based industrial computer screen dust particle detection device and method, which solves the technical problems of high error rate, high detection cost and lack of intelligent analysis in the detection process of existing industrial computer display panels.

[0004] To solve the above technical problems, the present invention provides the following technical solution: an artificial intelligence-based dust particle detection device for industrial computer screens, the detection device specifically comprising:

[0005] A barcode scanner, which is connected to the computer for communication and is used to scan the barcode on the screen of the industrial computer to be tested and enter the data in the barcode into the computer;

[0006] Keyboard and mouse, which are used to connect and communicate with the computer and complete human-computer interaction;

[0007] An industrial electron microscope, which is used to connect and communicate with a computer and acquire an image of the industrial computer screen to be inspected;

[0008] A computer having a built-in image recognition algorithm for identifying impurities on an image on an industrial computer screen to be inspected;

[0009] A 3-axis motor motion system, which is used to control the industrial electron microscope to acquire an image of the industrial computer screen to be inspected along a preset trajectory according to control instructions issued by the computer;

[0010] A computer display screen is used to display the image of the industrial computer screen to be inspected and a human-computer interaction interface.

[0011] Preferably, the industrial electron microscope comprises:

[0012] USB interface 1, which is provided on the CCD sensor and is used to connect to a computer via a USB harness and transmit the image of the industrial computer screen to be inspected after being magnified by a high-power magnification macro lens;

[0013] A CCD sensor, the CCD sensor is used to capture light signals and convert them into electrical signals, and then process the electrical signals into standard USB signals and output them through USB interface 1;

[0014] a high-power magnifying macro lens, wherein the high-power magnifying macro lens is used to magnify an image of the screen of the industrial computer to be inspected, which is captured by the CCD sensor (202);

[0015] A fill light is used to illuminate the screen of the industrial computer to be inspected.

[0016] Preferably, the 3-axis motor motion system comprises:

[0017] USB interface 2, which is used to communicate with a computer and transmit control signals from the computer to the 3-axis motor, as well as to provide feedback on the position of the industrial electron microscope;

[0018] A 3-axis motor is used to control the movement of the industrial electron microscope in the x-axis, y-axis and z-axis directions;

[0019] A fixed base, the fixed base is used to fix the 3-axis motor;

[0020] An electron microscope fixing frame, wherein the electron microscope fixing frame is used to fix an industrial electron microscope;

[0021] A microscope measurement and correction ruler is used to be placed on the industrial computer screen to be tested, and an image of the microscope measurement and correction ruler and the industrial computer screen to be tested is obtained through an industrial electron microscope. The image is then processed by a computer to obtain the size of the industrial computer screen to be tested and the ratio of the image pixels of the industrial computer screen to be tested to the actual scale.

[0022] Preferably, the 3-axis motor is a 3-axis FOC motor.

[0023] A method for detecting dust particles on an industrial computer screen, the method specifically comprising the following steps:

[0024] S1. The barcode scanner scans the barcode on the screen of the industrial computer to be tested and records the screen data contained in the barcode;

[0025] S2. Determine the starting and ending points of the industrial electron microscope according to the position of the industrial computer screen to be inspected;

[0026] S3. Adjust the industrial electron microscope to capture the image of the industrial computer screen to be inspected and complete the focus;

[0027] S4. Confirm the ratio of the pixels captured by the industrial electron microscope to the actual size, and determine the image magnification ratio;

[0028] S5. The industrial electron microscope completes full-screen shooting of the industrial computer screen to be inspected according to the preset starting point, end point and trajectory to obtain a full-screen image;

[0029] S6. The computer processes the full-screen image captured by the industrial electron microscope and outputs a capture report, wherein the capture report includes the number of impurities, the size of impurities, the position of impurities, and the degree of screen qualification.

[0030] Preferably, in step S2, the starting point and the ending point are respectively two end points of one diagonal line of the screen of the industrial computer to be detected.

[0031] As a preference, the method specifically includes the following steps:

[0032] S51, the industrial electron microscope moves according to the preset starting point, end point and trajectory;

[0033] S52, real-time computer detection of the image clarity of the industrial computer screen to be inspected obtained by the industrial electron microscope;

[0034] S53. If the image clarity does not meet the preset requirement, the industrial electron microscope is controlled to move in the z-axis direction by the 3-axis motor motion system until the image clarity meets the preset requirement, and then continues to move along the preset trajectory.

[0035] Preferably, the impurity position is calculated as follows:

[0036] S61, obtaining the coordinates of the impurity and the starting point of the industrial electron microscope;

[0037] S62. Establishing a plane coordinate system using any two vertical edges of the industrial computer screen to be inspected;

[0038] S63. Output the position coordinates of the impurity in the plane coordinate system to obtain the impurity position.

[0039] By means of the above technical solution, the present invention provides an artificial intelligence-based device and method for detecting dust particles on industrial computer screens, which has at least the following beneficial effects:

[0040] 1. The present invention uses an industrial electron microscope with a high-power magnification macro lens and AI image recognition algorithm to accurately identify dust particles of 0.3mm to 1.5mm with a resolution of 3840×2160, significantly reducing the missed detection rate and error rate of manual visual inspection.

[0041] 2. The present invention realizes automatic full-screen scanning of the industrial computer screen to be inspected through a three-axis motor motion system in coordination with a single industrial electron microscope. Combined with the size calibration function of the microscope measurement correction ruler, a single device can adapt to the inspection needs of screens of different sizes, avoiding the high cost of the traditional parallel solution of multiple optical modules.

[0042] 3. The present invention automatically analyzes the full-screen image through the computer's built-in image recognition algorithm, and outputs a structured report containing the number, size, position coordinates and screen qualification of impurities in real time, solving the problem of traditional methods relying on manual experience classification and isolated archiving.

[0043] 4. The present invention detects the image clarity in real time during the scanning process and dynamically adjusts the height of the industrial electron microscope in the z-axis direction through a three-axis motor to ensure that the clarity of each frame of the image meets the preset standard when shooting in full screen. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0045] Figure 1 This is a structural block diagram of the dust particle detection device for industrial computer screens of the present invention;

[0046] Figure 2 It is a structural block diagram of the industrial electron microscope of the present invention;

[0047] Figure 3 This is a structural block diagram of the 3-axis motor motion system of the present invention;

[0048] Figure 4 This is a flow chart of the method for detecting dust particles on an industrial computer screen according to the present invention;

[0049] Figure 5 This is an operating interface for confirming the ratio of captured pixels to actual size in the present invention;

[0050] Figure 6 This is an image of impurities to be detected on the industrial computer screen of the present invention.

[0051] In the figure: 101, barcode scanner; 102, keyboard and mouse; 103, industrial electron microscope; 104, computer; 105, 3-axis motor motion system; 106, computer display; 201, USB port 1; 202, CCD sensor; 203, high-power magnification macro lens; 204, fill light; 301, USB port 2; 302, 3-axis motor; 303, fixed base; 304, electron microscope fixing frame; 305, microscope measurement correction ruler. DETAILED DESCRIPTION

[0052] To make the above-mentioned objectives, features, and advantages of the present invention more clearly understood, the present invention is further described below in detail with reference to the accompanying drawings and specific embodiments. This will enable a full understanding of how this application uses technical means to solve technical problems and achieve technical effects, and to implement the invention accordingly.

[0053] In order to solve the technical problems of high error rate, high detection cost and lack of intelligent analysis in the detection process of existing industrial computer display panels, the present invention provides an industrial computer screen dust particle detection device based on artificial intelligence, which has millimeter-level detection accuracy, multi-size rapid adaptation capability and intelligent data analysis function, and meets the economic and reliability requirements in mass production environments. Figure 1 As shown, the detection device specifically includes:

[0054] The barcode scanner 101 connected to the computer 104 for communication is used to scan the barcode on the screen of the industrial computer to be tested and enter the data in the barcode into the computer 104 to ensure that the report generated by the computer 104 corresponds to the test sample; the keyboard and mouse 102 connected to the computer 104 for communication and completion of human-computer interaction to realize human-computer interaction between the user and the computer 104; the industrial electron microscope 103 connected to the computer 104 for communication and acquisition of the image of the industrial computer screen to be tested; the computer 104 with a built-in image recognition algorithm to identify impurities on the image of the industrial computer screen to be tested, and the image recognition algorithm can be an existing algorithm such as the YOLO algorithm; the 3-axis motor motion system 105 used to control the industrial electron microscope 103 to acquire the image of the industrial computer screen to be tested along a preset trajectory according to the control instructions issued by the computer 104; the computer display screen 106 used to display the image of the industrial computer screen to be tested and the human-computer interaction interface, thereby realizing automatic acquisition through this device. The image of the industrial computer screen to be inspected is obtained and the data and the actual object are matched through the barcode. The built-in image recognition algorithm of the computer 104 is used to realize millimeter-level detection of dust particles on the industrial computer screen. The coordinated design of the 3-axis motor motion system 105 and the industrial electron microscope 103 realizes millimeter-level stable photography. When shooting, the image may definitely shake when the camera moves, resulting in unclearness. Therefore, the device can be made not to shoot when moving. The 3-axis motor motion system 105 can provide feedback on whether the movement is completed before taking a picture. The user can input the screen size, and the device can determine the distance to be moved based on the size, similar to how many times it is moved. Finally, the labels on the four corners of the screen are used to confirm that the device is in place, so that the device automatically takes a picture after it is moved into place, which significantly reduces the overall cost of the equipment and improves the adaptability of the detection system. A single device can be compatible with the comprehensive detection needs of screens of different sizes, greatly reducing the detection cost and realizing intelligent detection of industrial computer screens of different sizes to be inspected.

[0055] The following is a detailed description of a feasible structure of the industrial electron microscope 103. Figure 2 As shown, specifically including:

[0056] A USB interface 201 provided on the CCD sensor 202 is used to connect to the computer 104 via a USB harness and transmit the image of the industrial computer screen to be inspected after being magnified by the high-power magnifying macro lens 203; the CCD sensor 202 is used to capture light signals and convert them into electrical signals to complete image capture, and then the electrical signals are processed into standard USB signals and output to the computer 104 via the USB interface 201; the high-power magnifying macro lens 203 is used to amplify the image of the industrial computer screen to be inspected captured by the CCD sensor 202, generally magnifying to 20-200 times, and can clearly capture screen images in the range of 0.9mmx0.9mm to 2mmx2mm, with an output resolution of 3840x2160, which can effectively capture impurities of 0.3mm to 1.5mm located in the optical adhesive layer of the screen; the fill light 204 is used to illuminate the industrial computer screen to be inspected, ensuring that the high-power magnifying macro lens 203 can clearly capture the tiny impurities illuminated by the fill light 204.

[0057] The following provides a specific structure of a 3-axis motor motion system 105, such as Figure 3 As shown, specifically including:

[0058] A USB interface 301 for communicating with the computer 104, and transmitting control signals from the computer 104 to the 3-axis motor 302, and feedback on the position of the industrial electron microscope 103. The 3-axis motor 302 can be a 3-axis FOC motor to more accurately control the position of the industrial electron microscope 103; a 3-axis motor 302 for controlling the movement of the industrial electron microscope 103 in the x-axis, y-axis and z-axis directions; a fixed base 303 for fixing the 3-axis motor 302; an electron microscope fixing frame 304 for fixing the industrial electron microscope 103; a microscope measurement correction ruler 305 for being placed at the industrial computer screen to be tested, and obtaining an image of the microscope measurement correction ruler 305 and the industrial computer screen to be tested through the industrial electron microscope 103, and then processing the image through the computer 104 to obtain the size of the industrial computer screen to be tested and the ratio of the image pixels of the industrial computer screen to be tested to the actual scale. For example, the numbers on the scale can be identified first, and then the pixels contained in the shortest distance between the two scale lines are recorded, so that the ratio can be calculated automatically, such as Figure 5 As shown, in order to confirm the screen interface of the ratio of captured pixels to actual scale, in general, the calibration ruler needs to be placed at the edge of the screen (i.e., the non-detection area) to prevent the line of sight of the screen that needs to be measured next from being blocked. The same screen product only needs to be calibrated once, and it can be calibrated once with long-term use.

[0059] The present invention also provides a method for detecting dust particles on industrial computer screens. Figure 4As shown, the detection method specifically includes the following steps:

[0060] S1. The barcode scanner scans the barcode on the screen of the industrial computer to be tested and records the screen data contained in the barcode. Each industrial computer screen to be tested is affixed with a barcode to record the SN number of each industrial computer screen as a unique identifier. The barcode scanner records the information of the industrial computer screen to be tested by scanning the barcode and transfers the information to the computer via a USB cable. The computer then automatically creates a new industrial computer screen test project and automatically fills the information of the industrial computer screen to be tested into the project file. The computer then starts to display the images taken by the industrial electron microscope in real time through the computer display.

[0061] S2. Determine the starting point and ending point of the industrial electron microscope according to the position of the industrial computer screen to be inspected. The user places the industrial computer screen to be inspected on a fixed base, adjusts the position of the industrial electron microscope to the starting point of the inspection, and checks the picture displayed on the computer screen. During this process, the computer will prompt the user to confirm the starting point and ending point positions. The user determines the starting point and ending point positions through the mouse and keyboard. The computer receives the starting point and ending point position confirmation instructions, and records the starting point position information of the industrial electron microscope through the encoder in the 3-axis motor motion system. The starting point and ending point are preferably the two end points of one of the diagonals of the industrial computer screen to be inspected. Since the industrial computer screen to be inspected is a rectangle, the size and position of the industrial computer screen to be inspected can be calculated.

[0062] S3. Adjust the industrial electron microscope to capture the image of the industrial computer screen to be inspected and complete the focus. The computer will send a focus request to the user. The user places the microscope measurement correction ruler on the surface of the industrial computer screen to be inspected, and inputs a control signal to the computer to move the industrial electron microscope to the direction facing the microscope measurement correction ruler. Then, rotate the high-power magnification macro lens of the industrial electron microscope to select the appropriate magnification and fix it. Then, the computer controls the z-axis motor to drive the industrial electron microscope for coarse and fine adjustments. Combined with the image recognition function, the focus on the scale lines of the microscope measurement correction ruler is completed.

[0063] S4. Confirm the ratio of the pixels captured by the industrial electron microscope to the actual size, and determine the image magnification ratio.

[0064] S5. The industrial electron microscope completes full-screen shooting of the industrial computer screen to be inspected according to the preset starting point, ending point and trajectory to obtain a full-screen image. After the computer receives the start detection command, it starts to control the 3-axis motor motion system to drive the industrial electron microscope to move horizontally on the x-axis and y-axis. The industrial electron microscope can start continuous shooting in the direction from the starting point to the ending point, from top to bottom, and from left to right. In order to ensure the clarity of the image during continuous shooting, it is necessary to control the industrial electron microscope to move in the z-axis direction through the 3-axis motor motion system. The specific steps are as follows:

[0065] S51, the industrial electron microscope moves according to the preset starting point, end point and trajectory;

[0066] S52, real-time computer detection of the image clarity of the industrial computer screen to be inspected obtained by the industrial electron microscope;

[0067] S53. If the image clarity does not meet the preset requirement, the industrial electron microscope is controlled to move in the z-axis direction by the 3-axis motor motion system until the image clarity meets the preset requirement, and then continues to move along the preset trajectory.

[0068] S6. The computer processes the full screen image taken by the industrial electron microscope and outputs a shooting report, which includes the number of impurities, impurity size, impurity location and screen qualification level, such as Figure 6 The following figure shows the obtained impurity size. In order to ensure that users can check the location of impurities during manual verification, a method for calculating the impurity location is provided:

[0069] S61, obtaining the coordinates of the impurity and the starting point of the industrial electron microscope;

[0070] S62. Establishing a plane coordinate system using any two vertical edges of the industrial computer screen to be inspected;

[0071] S63. Output the position coordinates of the impurity in the plane coordinate system to obtain the impurity position.

[0072] Therefore, during the subsequent manual review, since the origin of the plane coordinate system is located at a fixed corner in step S62, after obtaining the position coordinates of the impurity, it is only necessary to use a ruler to measure the distance along the two corresponding sides of the computer screen to obtain the actual position of the impurity.

[0073] Those skilled in the art will appreciate that all or part of the steps in the above-mentioned embodiment methods can be accomplished by instructing the relevant hardware through a program. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0074] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to in detail. For the above embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For relevant parts, please refer to the partial description of the method embodiments.

[0075] The above embodiments provide a detailed introduction to the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core ideas. At the same time, for those skilled in the art, according to the ideas of the present invention, there may be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting the present invention.

Claims

1. An industrial computer screen dust particle detection device based on artificial intelligence, characterized in that: The detection device specifically includes: A barcode scanner (101), the barcode scanner (101) is connected to the computer (104) for communication, and is used to scan the barcode on the screen of the industrial computer to be detected and enter the data in the barcode into the computer (104); A keyboard and mouse (102), wherein the keyboard and mouse (102) are used to connect and communicate with a computer (104) and complete human-computer interaction; An industrial electron microscope (103) is used to connect and communicate with a computer (104) and acquire an image of the screen of the industrial computer to be inspected; A computer (104) having a built-in image recognition algorithm for identifying impurities on an image on an industrial computer screen to be detected; A three-axis motor motion system (105) is used to control the industrial electron microscope (103) to acquire an image of the industrial computer screen to be inspected along a preset trajectory according to a control instruction issued by the computer (104); A computer display screen (106) is used to display an image of the industrial computer screen to be inspected and a human-computer interaction interface.

2. The industrial computer screen dust particle detection device according to claim 1 is characterized in that: The industrial electron microscope (103) comprises: USB interface 1 (201), the USB interface 1 (201) being provided on the CCD sensor (202), and being used for connecting to the computer (104) via a USB harness and transmitting the image of the screen of the industrial computer to be inspected after being magnified by the high-power magnification macro lens (203); A CCD sensor (202), the CCD sensor (202) is used to capture the optical signal and convert it into an electrical signal, and then process the electrical signal into a standard USB signal and output it through the USB interface (201); a high-power magnifying macro lens (203), wherein the high-power magnifying macro lens (203) is used to magnify an image of the industrial computer screen to be inspected captured by the CCD sensor (202); A fill light (204) is used to illuminate the screen of the industrial computer to be inspected.

3. The industrial computer screen dust particle detection device according to claim 1, characterized in that: The three-axis motor motion system (105) includes: A second USB interface (301), wherein the second USB interface (301) is used to communicate with the computer (104), transmit a control signal from the computer (104) to the three-axis motor (302), and provide feedback on the position of the industrial electron microscope (103); A three-axis motor (302), the three-axis motor (302) is used to control the industrial electron microscope (103) to move in the x-axis, y-axis and z-axis directions; A fixed base (303), wherein the fixed base (303) is used to fix the three-axis motor (302); An electron microscope fixing frame (304), wherein the electron microscope fixing frame (304) is used to fix the industrial electron microscope (103); A microscope measurement correction ruler (305) is used to be placed on the industrial computer screen to be tested, and an image of the microscope measurement correction ruler (305) and the industrial computer screen to be tested is obtained by an industrial electron microscope (103). The image is then processed by a computer (104) to obtain the size of the industrial computer screen to be tested and the ratio of the image pixels of the industrial computer screen to be tested to the actual scale.

4. The industrial computer screen dust particle detection device according to claim 1, characterized in that: The three-axis motor (302) is a three-axis FOC motor.

5. A method for detecting dust particles using the industrial computer screen dust particle detection device according to any one of claims 1 to 4, characterized in that: The detection method specifically comprises the following steps: S1. The barcode scanner scans the barcode on the screen of the industrial computer to be tested and records the screen data contained in the barcode; S2. Determine the starting and ending points of the industrial electron microscope according to the position of the industrial computer screen to be inspected; S3. Adjust the industrial electron microscope to capture the image of the industrial computer screen to be inspected and complete the focus; S4. Confirm the ratio of the pixels captured by the industrial electron microscope to the actual size, and determine the image magnification ratio; S5. The industrial electron microscope completes full-screen shooting of the industrial computer screen to be inspected according to the preset starting point, end point and trajectory to obtain a full-screen image; S6. The computer processes the full-screen image captured by the industrial electron microscope and outputs a capture report, wherein the capture report includes the number of impurities, the size of impurities, the position of impurities, and the degree of screen qualification.

6. The dust particle detection method according to claim 5, characterized in that: In step S2, the starting point and the ending point are respectively the two end points of one diagonal line of the screen of the industrial computer to be detected.

7. The dust particle detection method according to claim 5, characterized in that: In step S5, the following steps are specifically included: S51, the industrial electron microscope moves according to the preset starting point, end point and trajectory; S52, real-time computer detection of the image clarity of the industrial computer screen to be inspected obtained by the industrial electron microscope; S53. If the image clarity does not meet the preset requirement, the industrial electron microscope is controlled to move in the z-axis direction by the 3-axis motor motion system until the image clarity meets the preset requirement, and then continues to move along the preset trajectory.

8. The dust particle detection method according to claim 5, characterized in that: The impurity position is calculated as follows: S61, obtaining the coordinates of the impurity and the starting point of the industrial electron microscope; S62. Establishing a plane coordinate system using any two vertical edges of the industrial computer screen to be inspected; S63. Output the position coordinates of the impurity in the plane coordinate system to obtain the impurity position.

Images