Mobile phone screen defect detection method, device, system, equipment and medium

Abstract

The invention discloses a mobile phone screen defect detection method, device, system and equipment and a medium. The method comprises the following steps: acquiring a defect detection requirement of a mobile phone screen to be detected; wherein the defect detection requirement is the requirement for performing defect detection on the upper surface bulge array structure of the mobile phone screen to be detected; determining a light source detection environment for the to-be-detected mobile phone screen based on the defect detection requirement; performing multi-angle shooting on the to-be-detected mobile phone screen based on the light source detection environment to obtain a detection image; and performing defect identification on the detection image to obtain target defect information of the upper surface bulge array structure. The problems that in an existing manual visual detection method, human eyes are prone to being affected by the environment, errors generated in the visual detection process are large, and the accuracy of defect detection is low are solved.

Description

Technical Field

[0001] The present application relates to the field of mobile phone detection technology, and in particular to a method, device, system, equipment and medium for detecting defects in mobile phone screens. Background Art

[0002] Lens lines are an array of raised structures located on the top surface of a mobile phone's ITO (Indium Tin Oxide) film. These structures, with arch heights up to 52.6 microns, protect the ITO film. However, lens line offset affects the film's conductivity and light transmittance. As we all know, ITO film, as a conductive film, is a component of touch screens and is widely used in smartphones, smart homes, tablets, and smart car devices. The conductivity and light transmittance of ITO film influence touch screen production in the mobile communications sector, making the quality of the lens on the ITO film crucial.

[0003] Currently, the most common inspection method used by screen manufacturers is manual visual inspection. However, the human eye is easily affected by the environment, which results in large errors during manual visual inspection and low defect detection accuracy. Summary of the Invention

[0004] In order to overcome the problem in existing manual visual inspection methods that the human eye is easily affected by the environment, resulting in large errors in the visual inspection process and low accuracy of defect detection, the present application provides a mobile phone screen defect detection method, device, system, equipment and medium.

[0005] In a first aspect, in order to solve the above technical problems, the present application provides a method for detecting defects in a mobile phone screen, comprising: obtaining a defect detection requirement of a mobile phone screen to be tested; wherein the defect detection requirement is a requirement for performing defect detection on a raised array structure on the upper surface of the mobile phone screen to be tested; Determine the light source detection environment for the mobile phone screen to be tested based on defect detection requirements; Based on the light source detection environment, the mobile phone screen to be tested is photographed from multiple angles to obtain the detection image; Defect recognition is performed on the detection image to obtain target defect information of the upper surface protrusion array structure.

[0006] Furthermore, based on the defect detection requirements, the light source detection environment for the mobile phone screen to be tested is determined, including: Obtain imaging requirements for the raised array structure on the upper surface, including contrast and clarity requirements; find target light environment parameters corresponding to the imaging requirements from a preset light environment parameter table; the target light environment parameters include light source type, relative distance between the light source and the screen of the mobile phone to be tested, and light source tilt angle; The target light source environment parameter is used to set an environment, and a light source detection environment for the mobile phone screen to be detected is obtained.

[0007] Further, the mobile phone screen to be detected is photographed at multiple angles based on the light source detection environment to obtain a detection image, including: determining a product position of the mobile phone screen to be detected based on the light source detection environment; wherein the product position is directly above a light source in the light source detection environment; Based on the product position, a camera position of a camera for photographing the mobile phone screen to be detected is determined; wherein the product position is directly below the camera position and is located in the imaging area of the camera.

[0008] The mobile phone screen to be detected located at the product position is photographed at multiple angles by the camera located at the camera position to obtain a detection image.

[0009] Further, the mobile phone screen to be detected located at the product position is photographed at multiple angles by the camera located at the camera position to obtain a detection image, including: The mobile phone screen to be detected located at the product position and at any angle is photographed by the camera located at the camera position to obtain a first image; wherein the upper surface of the mobile phone screen to be detected is vertically arranged with the camera; The mobile phone screen to be detected located at the product position is horizontally rotated by 90°; wherein the upper surface of the mobile phone screen to be detected after rotation is vertically arranged with the camera; The mobile phone screen to be detected after rotation is photographed by the camera to obtain a second image; Based on the first image and the second image, feature fusion is performed to obtain a detection image.

[0010] Further, the detection image is subjected to defect recognition to obtain target defect information of the upper surface convex array structure, including: The detection image is processed by using a preset defect detection model to obtain a predicted defect type of the upper surface convex array structure and a defect area corresponding to the predicted defect type; The defect detection area corresponding to the predicted defect type is found from a preset defect information table; When the defect area is greater than the corresponding defect detection area, the corresponding target defect type is determined as the target defect type; and the target defect information of the upper surface convex array structure is formed based on the target defect type and the corresponding defect area.

[0011] Further, the detection image is subjected to defect recognition to obtain target defect information of the upper surface convex array structure, including: Obtain a standard upper surface convex array structure for the mobile phone screen to be tested; wherein the standard upper surface convex array structure includes multiple standard convex lines, and the upper surface convex array structure includes multiple convex lines, and the positions of the standard convex lines correspond one to one to the positions of the convex lines; calculate the angle difference between the corresponding standard convex lines and the convex lines; When the angle difference is greater than a preset angle, the corresponding raised line is determined as an offset abnormal line; Target defect information of the upper surface protrusion array structure is formed based on the offset abnormal lines and the corresponding angle differences.

[0012] In a second aspect, the present application further provides a mobile phone screen defect detection device, which applies the above-mentioned mobile phone screen defect detection method, and the device includes: Light source, used to provide a light source detection environment for the mobile phone screen to be tested; The camera is used to shoot the mobile phone screen to be tested from multiple angles based on the light source detection environment to obtain the detection image.

[0013] In a third aspect, the present application also provides a mobile phone screen defect detection system, comprising: An acquisition module is used to obtain a defect detection requirement of the mobile phone screen to be tested; wherein the defect detection requirement is a requirement for defect detection of the raised array structure on the upper surface of the mobile phone screen to be tested; The detection environment determination module is used to determine the light source detection environment for the mobile phone screen to be tested based on the defect detection requirements; The shooting module is used to shoot the mobile phone screen to be tested from multiple angles based on the light source detection environment to obtain a test image; The defect recognition module is used to perform defect recognition on the detection image and obtain target defect information of the upper surface protrusion array structure.

[0014] In a fourth aspect, the present application also provides a computing device, including a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, the steps of a mobile phone screen defect detection method as described above are implemented.

[0015] In a fifth aspect, the present application also provides a computer-readable storage medium, which stores instructions. When the instructions are executed on a terminal device, the terminal device executes the steps of a method for detecting defects in a mobile phone screen.

[0016] The beneficial effects of this application are as follows: by using a light source detection environment determined by the defect detection requirements of the mobile phone screen to be tested, the mobile phone screen to be tested is photographed from multiple angles to obtain a test image. If the defect detection requirement is to detect defects in the raised array structure on the upper surface of the mobile phone screen to be tested, the test image is automatically identified for defects to obtain target defect information of the raised array structure on the upper surface, thereby achieving automated defect detection of the raised array structure on the upper surface of the mobile phone screen, eliminating errors caused by the human eye, and greatly improving the accuracy of defect detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of a method for detecting defects in a mobile phone screen, as shown in an exemplary embodiment of the present application; Figure 2 This is a schematic structural diagram of a mobile phone screen defect detection device used in a mobile phone screen defect detection method in an exemplary embodiment of the present application; Figure 3 A schematic structural diagram of a mobile phone screen defect detection system is shown as an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0018] The following examples are provided to further explain and supplement the present application and do not constitute any limitation to the present application.

[0019] The following describes a method, device, system, equipment and medium for detecting defects in a mobile phone screen according to an embodiment of the present application in conjunction with the accompanying drawings.

[0020] The mobile phone screen defect detection method provided in the embodiment of the present application can be specifically executed by a server. It should be noted that the server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms, and this is not limited here.

[0021] See also Figure 1 , Figure 1 A method for detecting defects in a mobile phone screen is shown as an exemplary embodiment of the present application. Figure 1 As shown, the present application provides a method for detecting defects in a mobile phone screen, comprising: S11, obtaining a defect detection requirement of the mobile phone screen to be tested; wherein the defect detection requirement is a requirement for defect detection of a raised array structure on the upper surface of the mobile phone screen to be tested; S12, determining a light source detection environment for the mobile phone screen to be tested based on defect detection requirements; S13, photographing the mobile phone screen to be tested from multiple angles based on the light source detection environment to obtain a detection image; S14, performing defect recognition on the detection image to obtain target defect information of the upper surface protrusion array structure.

[0022] The mobile phone screen defect detection method of the embodiment provided in the present application is to shoot the mobile phone screen to be tested from multiple angles through the light source detection environment determined by the defect detection requirements of the mobile phone screen to be tested to obtain a detection image. The defect detection requirement is to perform defect detection on the raised array structure on the upper surface of the mobile phone screen to be tested, and then the detection image is automatically identified for defects to obtain the target defect information of the raised array structure on the upper surface, thereby realizing the automated defect detection of the raised array structure on the upper surface of the mobile phone screen, eliminating the errors caused by the human eye, and greatly improving the accuracy of defect detection. At the same time, with the improvement of the defect detection accuracy, it can not only improve the work efficiency of mobile phone screen defect detection to improve the production efficiency of qualified mobile phone screens, but also ensure the defect detection rate, effectively improving the yield rate of mobile phone screens put on the market.

[0023] Optionally, determining a light source detection environment for the mobile phone screen to be tested based on defect detection requirements includes: Obtain imaging requirements for the raised array structure on the upper surface, including contrast and clarity requirements; find target light environment parameters corresponding to the imaging requirements from a preset light environment parameter table; the target light environment parameters include light source type, relative distance between the light source and the screen of the mobile phone to be tested, and light source tilt angle; The environment is set based on the target light source environment parameters to obtain the light source detection environment for the mobile phone screen to be tested.

[0024] In the embodiment provided by the present application, by pre-setting the correspondence between the shooting and imaging requirements and the light source environment parameters in the light source environment parameter table, the target light source environment parameters that match the shooting and imaging requirements of the upper surface protrusion array structure can be directly found from the light source environment parameter table based on the correspondence, thereby obtaining a light source detection environment set based on the target light source environment parameters, which is convenient for subsequent targeted multi-angle shooting of the mobile phone screen to be tested based on the light source detection environment, and can improve the image accuracy of the obtained detection image, thereby further improving the accuracy of subsequent defect detection based on the detection image.

[0025] Optionally, photographing the mobile phone screen to be tested at multiple angles based on the light source detection environment to obtain a test image includes: determining a product position of the mobile phone screen to be tested based on the light source detection environment; wherein the product position is located directly above the light source in the light source detection environment; Based on the product position, the camera position of the shooting camera for shooting the mobile phone screen to be tested is determined; wherein the product position is located directly below the camera position and is within the shooting imaging area of ​​the shooting camera.

[0026] The shooting camera located at the camera position is used to shoot the mobile phone screen to be tested at the product position at multiple angles to obtain a test image.

[0027] In the embodiment provided by this application, the product is located directly above the light source in the light source detection environment, and directly below the camera position of the camera that captures the mobile phone screen to be tested, and is within the camera's imaging area. In this way, the light source and the camera can be set on both sides of the mobile phone screen to be tested, further improving the contrast effect of the raised array structure on the upper surface of the camera's imaging. This allows the camera located at the camera position to capture the mobile phone screen to be tested at the product position from multiple angles, thereby capturing more defect comparison information in the test image, thereby improving the accuracy of subsequent defect detection.

[0028] Optionally, a shooting camera located at a camera position is used to shoot a multi-angle shot of the mobile phone screen to be tested located at a product position to obtain a test image, including: Using a shooting camera located at a camera position to shoot the screen of the mobile phone to be tested, which is located at a product position and at any angle, to obtain a first image; wherein the upper surface of the screen of the mobile phone to be tested is arranged perpendicular to the shooting camera; Rotate the screen of the mobile phone to be tested at the product position horizontally by 90°; wherein, after the rotation, the upper surface of the screen of the mobile phone to be tested is perpendicular to the camera; Using a camera to photograph the rotated screen of the mobile phone to be tested to obtain a second image; Feature fusion is performed based on the first image and the second image to obtain a detection image.

[0029] In the embodiment provided by the present application, the screen of the mobile phone to be tested located at the product position is photographed at different angles by utilizing a shooting camera located at the camera position to obtain a first image and a second image at different angles, and the first image and the second image are feature-fused so that the obtained detection image can contain defect features of the mobile phone to be tested at different angles, thereby ensuring the completeness of the defect information in the detection image, and further improving the accuracy of subsequent defect detection.

[0030] In this embodiment, the screen of the mobile phone to be tested is 0° (any angle of the initial placement can be regarded as the product angle of 0°) and 90° (the product angle is obtained by horizontally rotating the mobile phone screen to be tested at 0° by 90°). That is, when the mobile phone screen to be tested is photographed and tested, the product is photographed at two angles, which can ensure the imaging effect of the lens line. Specifically, due to the optical path design of the light source, it can simultaneously ensure that the emergent light and the lens lines of the two angles are highly overlapped, achieving the best imaging effect, so that defect features at different angles can be collected to form a detection image, thereby ensuring the completeness of the defect information in the detection image.

[0031] In an exemplary embodiment provided by the present application, in machine vision, the construction of a visual imaging system is particularly critical, which will directly affect the quality of the image and thus affect the performance of the system. Therefore, the visual imaging system constructed in the present application is: based on the target light source environment parameters including the light source type, the relative distance between the light source and the mobile phone screen to be tested, and the light source tilt angle, a light source detection environment is set, and the product position of the mobile phone screen to be tested is set directly above the light source in the light source detection environment, the upper surface of the mobile phone screen to be tested is set vertically to the shooting camera, the product position is located directly below the camera position, and is within the shooting imaging area of ​​the shooting camera. Among them, the light source type can be a line light source, the relative distance can be 60mm, and the light source tilt angle can be 15°. The line light source is used to illuminate the lens line (upper surface raised array structure) area. After research and testing, the use of a line light source as a backlight has a high contrast for the image acquisition of defects in the mobile phone screen to be tested, and can brighten the star-shaped crack defects to form the most conducive imaging effect for image processing, and ensure the stability of the image, greatly improving the detection stability and accuracy of subsequent image defect recognition.

[0032] By photographing the mobile phone screen to be tested in the above-mentioned light source detection environment, it is possible to achieve high-contrast capture of the two defects, namely the offset of the lens line (the raised array structure on the upper surface) and the star-shaped crack defect. This is conducive to the good detection of defects in the later stage of the algorithm, and to achieve stability and reliability in the detection of lens line offset and star-shaped crack defects. Among them, since the length of the star-shaped crack defect will affect the performance of the product to varying degrees, the existence of the star-shaped crack defect will damage the function of the ITO film layer of the mobile phone screen to varying degrees due to different shapes and sizes, affecting the conductivity and light transmittance of the ITO film layer, and having a direct impact on the performance and use of the mobile phone screen to be tested. Therefore, the detection of star-shaped crack defects is particularly important. The shape of the star-shaped crack defect is mostly a crack extending from the center point. The size of the star-shaped crack defect is measured based on the width and height, ranging from 15um to 40um. The width and height greater than 15um×15um are considered defects that need to be detected.

[0033] In addition, the offset detection of the lens line requires good imaging effect, which is specifically manifested in that the lens line appears as a thin line in the image. Specifically, while ensuring that the screen of the mobile phone to be tested is placed upright, adjust the angle of the light source to present a clear and thin line in the imaging field of view. During the experimental test, when the tilt angle of the light source is 15°, the imaging effect is better. Among them, adjusting the angle of the light source is mainly to make the light source lamp beads and the lens line angle highly coincide with each other to achieve the best imaging effect. The thin and long lens line shape facilitates the comparison between the algorithm and the standard lens line. According to laboratory tests, the line light source backlight can meet this requirement. Therefore, the light source type of the light source in the light source detection environment is set to a line light source.

[0034] Optionally, defect recognition is performed on the detection image to obtain target defect information of the upper surface protrusion array structure, including: processing the detection image using a preset defect detection model to obtain a predicted defect type of the upper surface protrusion array structure and a defect area corresponding to the predicted defect type; Find the defect detection area corresponding to the predicted defect type from the preset defect information table; When the defect area is larger than the corresponding defect detection area, the corresponding target defect type is determined as the target defect type; and target defect information of the upper surface protrusion array structure is formed based on the target defect type and the corresponding defect area.

[0035] In the embodiment provided by the present application, a preset defect detection model is used to process the detection image to obtain each predicted defect type of the upper surface convex array structure and the defect area corresponding to the predicted defect type. When the defect area is larger than the defect detection area of ​​the corresponding predicted defect type, the target defect type is determined as the target defect type, and target defect information of the upper surface convex array structure containing the target defect type and the corresponding defect area is formed. In this way, since when the defect area is less than or equal to the defect detection area of ​​the corresponding predicted defect type, the effect of the defect on the conductivity and light transmittance of the mobile phone screen to be tested is negligible, so it can enter the market as a qualified mobile phone screen. When the defect area is larger than the defect detection area of ​​the corresponding predicted defect type, the predicted defect type will affect the conductivity and light transmittance of the mobile phone screen to be tested, so it is necessary to detect the defect. The target defect type and the corresponding defect area of ​​the defect are formed into the target defect information of the upper surface convex array structure, which facilitates the identification of unqualified mobile phone screens based on the target defect information and improves the pass rate of mobile phone screens entering the market.

[0036] In this embodiment, the defect detection model is obtained by pre-training the initial deep learning model to meet the detection accuracy requirements. During pre-training, a large number of defect images of the raised array structure on the top surface of each mobile phone screen are first collected to enrich the training sample library. The more different defect samples, the higher the defect detection rate. Then, the initial deep learning model is used to train each defect image to ensure the detection of various defects in the raised array structure on the top surface, thus obtaining the defect detection model.

[0037] The predicted defect types include star-shaped crack defects, and the defect detection model is mainly used to identify star-shaped crack defects in the upper surface raised array structure. For star-shaped crack defects, according to the results of the survey, if the width and height of the defect exceed 15um×15um, it will affect the conductivity and light transmittance of the ITO film layer. The defect detection area corresponding to the star-shaped crack defect (the threshold for defect size control) is set to a width and height of 15um×15um. Star-shaped crack defects exceeding this threshold will be detected to form target defect information. In addition, for other specific defects of different shapes in the upper surface raised array structure, the initial deep learning model can detect specific defects by annotating these defects and conducting a large amount of training.

[0038] Optionally, defect recognition is performed on the test image to obtain target defect information of the upper surface protrusion array structure, including: obtaining a standard upper surface protrusion array structure for the mobile phone screen to be tested; wherein the standard upper surface protrusion array structure includes a plurality of standard protrusion lines, and the upper surface protrusion array structure includes a plurality of protrusion lines, and the standard protrusion lines correspond to the positions of the protrusion lines one by one; and calculating the angle difference between the corresponding standard protrusion line and the protrusion line; When the angle difference is greater than a preset angle, the corresponding raised line is determined as an offset abnormal line; Target defect information of the upper surface protrusion array structure is formed based on the offset abnormal lines and the corresponding angle differences.

[0039] In the embodiment provided by the present application, by calculating the angle difference between the corresponding standard raised lines and raised lines in the standard upper surface raised array structure and the upper surface raised array structure for the mobile phone screen to be tested, and when the angle difference is greater than a preset angle, the corresponding raised line is determined as an offset abnormal line, thereby forming target defect information of the upper surface raised array structure containing the offset abnormal line and the corresponding angle difference. In this way, since when the angle difference is less than or equal to the preset angle, the effect of the corresponding raised line on the conductivity and light transmittance of the mobile phone screen to be tested is negligible, it can enter the market as a qualified mobile phone screen, and when the angle difference is greater than the preset angle, the corresponding raised line will affect the conductivity and light transmittance of the mobile phone screen to be tested, so it is necessary to detect the defect, and then the raised line is determined as an offset abnormal line and the corresponding angle difference is formed to form the target defect information of the upper surface raised array structure, so as to facilitate the identification of unqualified mobile phone screens based on the target defect information and improve the pass rate of mobile phone screens entering the market.

[0040] In this embodiment, the offset of each raised line in the lens line (raised array structure on the upper surface) of the tested mobile phone screen is assessed by comparing the angle of each raised line with the standard raised line at the corresponding position in the lens line (standard raised array structure on the upper surface) of the standard lens, thereby calculating the angle difference between the two. The angle difference is obtained by calculating the sine of the position of the standard raised line at the corresponding position of the raised line.

[0041] In particular, the preset angle can be set to 8°. If the angle difference is greater than 8°, it is considered a lens line deviation anomaly. The raised line corresponding to the angle difference is determined as the deviation abnormality line, and the target defect information of the upper surface protrusion array structure is formed based on the deviation abnormality line and the corresponding angle difference.

[0042] The mobile phone screen defect detection method of this application, by using a line light source as a backlight, can effectively complete the image acquisition of lens line offset and star-shaped crack defects, and can improve the contrast between defects and background textures. At the same time, it can take into account the imaging effects of two angles of the lens line, and can better improve the algorithm's detection rate of defects. Thus, the following effects are achieved: (1) Fast detection speed and high efficiency, greatly improving productivity; (2) Strict testing can improve the quality and stability of mobile phone screens; (3) High accuracy, which is beneficial to improving the yield rate of ITO film layer of mobile phone screens; (4) The detection is widely used, freeing people from the boring work of lens line offset and star crack detection.

[0043] See also Figure 2 , Figure 2In an exemplary embodiment of the present application, a mobile phone screen defect detection device for a mobile phone screen defect detection method is provided. Figure 2 As shown, the present application provides a mobile phone screen defect detection device, which applies the above-mentioned mobile phone screen defect detection method, and the device includes: Light source, used to provide a light source detection environment for the mobile phone screen to be tested; The camera is used to shoot the mobile phone screen to be tested from multiple angles based on the light source detection environment to obtain the detection image.

[0044] The mobile phone screen defect detection method provided in this embodiment of the present application determines the light source detection environment based on the defect detection requirements of the mobile phone screen to be tested, creates the light source detection environment using a light source, and then uses a camera to shoot the mobile phone screen to be tested in the light source detection environment from multiple angles to obtain a detection image. The defect detection requirement is to perform defect detection on the raised array structure on the upper surface of the mobile phone screen to be tested, which facilitates automatic defect recognition of the detection image and obtains target defect information of the raised array structure on the upper surface, thereby realizing automatic defect detection of the raised array structure on the upper surface of the mobile phone screen, eliminating errors caused by the human eye, and greatly improving the accuracy of defect detection.

[0045] Figure 2 In the test, the camera is installed directly above the product (mobile phone screen to be tested) via a Z-axis slide, and the distance from the camera installation surface to the product (mobile phone screen to be tested) is 376mm. The detection accuracy is 8μm at this time. The Z-axis slide can achieve an adjustment of ±10mm. The line light source is located directly below the product (mobile phone screen to be tested), and the distance between the two is 60mm. This ensures that the image imaging effect is not affected by temperature drift and causes defocus, allowing more light to enter the camera, ensuring the brightness and uniformity of the image, so that the offset and star-shaped crack defects in the lens line (raised array structure on the upper surface) area of ​​the product (mobile phone screen to be tested) can be detected in this light source detection environment.

[0046] Among them, since different light sources can highlight different appearance defects, the selection of machine vision light sources is particularly important. Under the illumination of a suitable light source, an image with good uniformity and consistency can be obtained, which improves the recognition detection efficiency and accuracy of the visual algorithm. At the same time, the height position of the light source also has a great influence on the imaging effect. It is a necessary factor to be considered. By adjusting and fixing the height and angle of the light source, high-contrast acquisition of defects is achieved to meet the requirements of image detection. Therefore, in this application, the light source in the light source detection environment is selected as a line light source, and the distance between the two is 60mm. At the same time, the light source inclination angle of the line light source is 15°, that is, the light source lamp bead surface of the line light source faces the product (mobile phone screen to be tested), and the light source lamp bead surface is 15° relative to the horizontal position of the product (mobile phone screen to be tested). The line light source is located directly below the product (mobile phone screen to be tested), and the distance between the two is 60mm.

[0047] The shooting camera includes a linear array camera and an optical imaging telecentric lens, and the degree of fit between the linear array camera and the optical imaging telecentric lens meets the image distortion requirement when the mobile phone screen to be measured is shot, so as to reduce the image distortion of the detection image obtained by shooting. In the present application, the detection accuracy is 8 μm, and according to the accuracy test requirement, the linear array camera is selected as a 16K linear array camera. In order to cooperate with the camera and meet the image acquisition accuracy requirement, the optical imaging telecentric lens selected is a 1X lens with a focal length of 80 mm.

[0048] The mobile phone screen defect detection device is used for lens line offset and star-shaped crack defect detection of the mobile phone screen to be measured, and therefore the mobile phone screen defect detection device can also be referred to as an optical detection system. The mobile phone screen defect detection device further includes a light source controller, a Z-axis sliding table, a programmable logic controller (PLC), a power trigger line, a data line and the like. The Z-axis sliding table can adjust the height of the shooting camera installation and the working distance of the lens, so that the image is better focused, which is beneficial to image acquisition of product defect details. The data line is used for transmitting signals between components in the optical detection system, and can transmit the image signal (detection image) collected by the shooting camera to a terminal. Subsequently, the image signal (detection image) is processed by using an algorithm, and the image processing result is output, so as to obtain the target defect information of the upper surface convex array structure.

[0049] When the mobile phone screen to be measured moves to the product position in the light source detection environment with the mechanical automation platform (object table) and is in the shooting imaging area (camera field of view range) of the shooting camera, the PLC gives a trigger signal. Then the linear light source installed at a distance of 60 mm from the product is in the stroboscopic state through the logical control of the light source controller, that is, after the light source controller receives the trigger signal given by the PLC, the light source is turned on. At the same time, after the shooting camera receives the trigger signal, the 16K linear array camera and the 1X lens with a focal length of 80 mm are used to shoot the lens line (upper surface convex array structure) area on the mobile phone screen to be measured from multiple angles. The 1X lens enables the edge information of the lens line (upper surface convex array structure) to be imaged on the CCD (Charge-Coupled Device) of the 16K linear array camera, so as to obtain a detection image. The collected image is subjected to defect recognition, and the target defect information of the upper surface convex array structure is obtained.

[0050] Please refer to Figure 3 , Figure 3 A mobile phone screen defect detection system shown in an exemplary embodiment of the present application, as shown in Figure 3 , the present application provides a mobile phone screen defect detection system 300, comprising: An acquisition module 301 is used to acquire a defect detection requirement of the mobile phone screen to be tested; wherein the defect detection requirement is a requirement for performing defect detection on the raised array structure on the upper surface of the mobile phone screen to be tested; A detection environment determination module 302 is configured to determine a light source detection environment for the mobile phone screen to be tested based on defect detection requirements; The shooting module 303 is used to shoot the screen of the mobile phone to be tested from multiple angles based on the light source detection environment to obtain a detection image; The defect recognition module 304 is used to perform defect recognition on the detection image to obtain target defect information of the upper surface protrusion array structure.

[0051] The mobile phone screen defect detection system 300 of this embodiment provided by the present application uses the defect detection requirements of the mobile phone screen to be tested obtained by the acquisition module 301 to obtain the light source detection environment determined by the detection environment determination module 302, and shoots the mobile phone screen to be tested from multiple angles to obtain a detection image. The defect detection requirement is to perform defect detection on the raised array structure on the upper surface of the mobile phone screen to be tested. The defect recognition module 304 is used to automatically identify defects on the detection image to obtain target defect information of the raised array structure on the upper surface, thereby realizing automated defect detection of the raised array structure on the upper surface of the mobile phone screen, eliminating errors caused by the human eye, and greatly improving the accuracy of defect detection.

[0052] Optionally, the detection environment determination module 302 is specifically configured to: Obtain imaging requirements for the raised array structure on the upper surface, including contrast and clarity requirements; find target light environment parameters corresponding to the imaging requirements from a preset light environment parameter table; the target light environment parameters include light source type, relative distance between the light source and the screen of the mobile phone to be tested, and light source tilt angle; The environment is set based on the target light source environment parameters to obtain the light source detection environment for the mobile phone screen to be tested.

[0053] Optionally, the shooting module 303 is specifically configured to: Determine the product position of the mobile phone screen to be tested based on the light source detection environment; wherein the product position is directly above the light source in the light source detection environment; Based on the product position, the camera position of the shooting camera for shooting the mobile phone screen to be tested is determined; wherein the product position is located directly below the camera position and is within the shooting imaging area of ​​the shooting camera.

[0054] The shooting camera located at the camera position is used to shoot the mobile phone screen to be tested at the product position at multiple angles to obtain a test image.

[0055] Optionally, the shooting module 303 is specifically configured to: Using a shooting camera located at a camera position to shoot the screen of the mobile phone to be tested, which is located at a product position and at any angle, to obtain a first image; wherein the upper surface of the screen of the mobile phone to be tested is arranged perpendicular to the shooting camera; Rotate the screen of the mobile phone to be tested at the product position horizontally by 90°; wherein, after the rotation, the upper surface of the screen of the mobile phone to be tested is perpendicular to the camera; Using a camera to photograph the rotated screen of the mobile phone to be tested to obtain a second image; Feature fusion is performed based on the first image and the second image to obtain a detection image.

[0056] Optionally, the defect identification module 304 is specifically configured to: The detection image is processed using a preset defect detection model to obtain the predicted defect type of the upper surface protrusion array structure and the defect area corresponding to the predicted defect type; Find the defect detection area corresponding to the predicted defect type from the preset defect information table; When the defect area is larger than the corresponding defect detection area, the corresponding target defect type is determined as the target defect type; Target defect information of the upper surface protrusion array structure is formed based on the target defect type and the corresponding defect area.

[0057] Optionally, the defect identification module 304 is specifically configured to: Obtain a standard upper surface convex array structure for the mobile phone screen to be tested; wherein the standard upper surface convex array structure includes multiple standard convex lines, and the upper surface convex array structure includes multiple convex lines, and the positions of the standard convex lines correspond one to one to the positions of the convex lines; calculate the angle difference between the corresponding standard convex lines and the convex lines; When the angle difference is greater than a preset angle, the corresponding raised line is determined as an offset abnormal line; Target defect information of the upper surface protrusion array structure is formed based on the offset abnormal lines and the corresponding angle differences.

[0058] It should be noted that the mobile phone screen defect detection system provided in the above embodiment and the mobile phone screen defect detection method provided in the above embodiment are of the same concept, wherein the specific manner in which each module and unit performs operations has been described in detail in the method embodiment and will not be repeated here. In actual applications, the mobile phone screen defect detection system provided in the above embodiment can allocate the above functions to different functional modules as needed, that is, divide the internal structure of the system into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0059] A computing device in an embodiment of the present application includes a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, some or all steps of the above-mentioned mobile phone screen defect detection method are implemented.

[0060] Among them, the computing device can be a computer, and correspondingly, its program is computer software. The above-mentioned parameters and steps in a computing device of the present application can refer to the parameters and steps in the embodiment of a mobile phone screen defect detection method above, and will not be repeated here.

[0061] In an embodiment of the present application, a computer-readable storage medium is provided, in which instructions are stored. When the instructions are executed, the steps of the above-mentioned method for detecting defects in a mobile phone screen are executed.

[0062] The computer-readable storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0063] The technical solution of the embodiments of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method of the embodiments of the present disclosure. The aforementioned computer-readable storage medium can be a non-transitory computer-readable storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program code, or a transient computer-readable storage medium.

[0064] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. Among them, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0065] Those skilled in the art know that the present application can be implemented as a system, a method, or a computer program product. Therefore, the present disclosure can be embodied in the form of a hardware completely, a software completely (including firmware, resident software, microcode, etc.), or a combination of hardware and software, which is generally referred to as "module" or "system". Furthermore, in some embodiments, the present application can also be embodied in the form of a computer program product in one or more computer readable storage media having computer readable program code. The computer readable storage media can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any combination thereof.

[0066] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Also, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.

[0067] Although the embodiments of the present application have been shown and described above, it is understood that the above-described embodiments are exemplary and are not to be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above-described embodiments within the scope of the present application.

Claims

1. A method for detecting defects in a mobile phone screen, characterized in that: include: Obtaining a defect detection requirement for the mobile phone screen to be tested; wherein the defect detection requirement is a requirement for performing defect detection on a raised array structure on the upper surface of the mobile phone screen to be tested; Determining a light source detection environment for the mobile phone screen to be tested based on the defect detection requirements; Based on the light source detection environment, the screen of the mobile phone to be tested is photographed at multiple angles to obtain a detection image; Defect recognition is performed on the detection image to obtain target defect information of the upper surface protrusion array structure.

2. The method according to claim 1, characterized in that The determining of a light source detection environment for the mobile phone screen to be tested based on the defect detection requirement includes: Obtaining imaging requirements for the upper surface protrusion array structure, wherein the imaging requirements include contrast requirements and clarity requirements; The target light source environment parameters corresponding to the shooting imaging requirements are found from the preset light source environment parameter table; wherein, the target light source environment parameters include the light source type, the relative distance between the light source and the mobile phone screen to be tested, and the light source inclination angle; based on the target light source environment parameters, the environment is set to obtain the light source detection environment for the mobile phone screen to be tested.

3. The method according to claim 1, characterized in that The method of photographing the screen of the mobile phone to be tested at multiple angles based on the light source detection environment to obtain a detection image includes: Determining a product position of the mobile phone screen to be tested based on the light source detection environment; wherein the product position is located directly above the light source in the light source detection environment; Based on the product position, determining the camera position of a shooting camera for shooting the screen of the mobile phone to be tested; wherein the product position is located directly below the camera position and within the shooting imaging area of ​​the shooting camera; The shooting camera located at the camera position is used to shoot the mobile phone screen to be tested located at the product position at multiple angles to obtain a test image.

4. The method according to claim 3, characterized in that The method of using the shooting camera located at the camera position to shoot the mobile phone screen to be tested located at the product position at multiple angles to obtain a test image includes: Using the shooting camera located at the camera position to shoot the mobile phone screen to be tested, which is located at the product position and at any angle, to obtain a first image; wherein the upper surface of the mobile phone screen to be tested is perpendicular to the shooting camera; horizontally rotating the mobile phone screen to be tested, which is located at the product position, by 90°; wherein, after the rotation, the upper surface of the mobile phone screen to be tested is perpendicular to the shooting camera; Using the camera to shoot the rotated screen of the mobile phone to be tested to obtain a second image; Feature fusion is performed based on the first image and the second image to obtain a detection image.

5. The method according to any one of claims 1 to 4, characterized in that The performing defect recognition on the detection image to obtain target defect information of the upper surface protrusion array structure includes: Processing the detection image using a preset defect detection model to obtain a predicted defect type of the upper surface protrusion array structure and a defect area corresponding to the predicted defect type; Finding the defect detection area corresponding to the predicted defect type from a preset defect information table; When the defect area is larger than the corresponding defect detection area, the corresponding target defect type is determined as the target defect type; and target defect information of the upper surface protrusion array structure is formed based on the target defect type and the corresponding defect area.

6. The method according to any one of claims 1 to 4, characterized in that The performing defect recognition on the detection image to obtain target defect information of the upper surface protrusion array structure includes: Obtaining a standard upper surface protrusion array structure for the mobile phone screen to be tested; wherein the standard upper surface protrusion array structure includes a plurality of standard protrusion lines, and the upper surface protrusion array structure includes a plurality of protrusion lines, and the standard protrusion lines correspond to the positions of the protrusion lines one by one; Calculating the angle difference between the corresponding standard raised line and the raised line; When the angle difference is greater than a preset angle, the corresponding raised line is determined as an offset abnormal line; Target defect information of the upper surface protrusion array structure is formed based on the offset abnormal line and the corresponding angle difference.

7. A mobile phone screen defect detection device, characterized in that: The method for detecting defects in a mobile phone screen according to any one of claims 1 to 6 is applied, wherein the device comprises: Light source, used to provide a light source detection environment for the mobile phone screen to be tested; The camera is used to shoot the screen of the mobile phone to be tested at multiple angles based on the light source detection environment to obtain a detection image.

8. A mobile phone screen defect detection system, characterized in that: include: An acquisition module is used to obtain a defect detection requirement of the mobile phone screen to be tested; wherein the defect detection requirement is a requirement for performing defect detection on the protrusion array structure on the upper surface of the mobile phone screen to be tested; A detection environment determination module is used to determine the light source detection environment for the mobile phone screen to be tested based on the defect detection requirements; a shooting module is used to shoot the mobile phone screen to be tested from multiple angles based on the light source detection environment to obtain a detection image; and a defect recognition module is used to identify defects in the detection image to obtain target defect information of the upper surface protrusion array structure.

9. A computing device comprising a memory, a processor, and a program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the steps of a mobile phone screen defect detection method as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed on the terminal device, the terminal device executes the steps of a mobile phone screen defect detection method as described in any one of claims 1 to 6.

Images