Display screen quality detection method, electronic device and storage medium

Abstract

The embodiments of the present application provide a quality inspection method for a display screen, an electronic device, and a storage medium, and relate to the field of image processing technology. The method comprises: obtaining an image of a display screen to be inspected, which is captured when a preset screen is displayed in the display screen to be inspected, as the image to be inspected; performing defect extraction on the image to be inspected to obtain a defect image area of ​​a target Mura defect in the display screen to be inspected in the image to be inspected; calculating attribute information of the target Mura defect based on the defect image area of ​​the target Mura defect; calculating a perceived amount of the target Mura defect based on the attribute information of the target Mura defect; the perceived amount indicates the degree of user perception of the target Mura defect; and determining a quality inspection result of the display screen to be inspected based on the perceived amount of the target Mura defect, which can improve the accuracy of display screen quality inspection, thereby ensuring product quality and improving user experience.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a display screen quality detection method, electronic equipment and storage medium. Background Art

[0002] Mura defects refer to defects that are visually perceived by users due to uneven brightness or color distribution in display devices (such as display screens) or lighting products such as liquid crystal displays (LCDs) and organic light-emitting diodes (OLEDs). This visually perceived defect will affect the display effect of the display and reduce the user experience. Therefore, the detection of Mura defects in displays is of great significance for ensuring the product quality of the display and improving the user experience. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a display screen quality detection method, electronic device and storage medium to improve the accuracy of display screen quality detection, thereby ensuring the product quality of the display screen based on the detection results and improving the user experience. The specific technical solution is as follows:

[0004] In a first aspect, in order to achieve the above-mentioned purpose, an embodiment of the present application provides a method for detecting the quality of a display screen, the method comprising:

[0005] Acquire an image of the display screen to be detected that is captured when the display screen to be detected displays a preset picture, as the image to be detected;

[0006] Extracting defects from the image to be inspected to obtain a defect image region of a target Mura defect in the display screen to be inspected in the image to be inspected;

[0007] Calculating attribute information of the target Mura defect based on the defect image area of ​​the target Mura defect;

[0008] Calculating a perceived amount of the target Mura defect based on the attribute information of the target Mura defect; wherein the perceived amount represents a user's degree of perception of the target Mura defect;

[0009] Based on the perceived amount of the target Mura defect, a quality inspection result of the display screen to be inspected is determined.

[0010] As can be seen from the above, the technical solution provided by this embodiment can determine the quality inspection result of the display screen to be inspected, and then guarantee the product quality of the display screen based on the inspection result, and improve the user experience. In addition, the perception amount representing the user's perception degree of the target Mura defect in the display screen to be inspected can be determined. The greater the perception amount, the higher the user's perception degree of the target Mura defect in the display screen to be inspected. Furthermore, the quality inspection of the display screen to be inspected based on the perception amount of the target Mura defect in the display screen to be inspected can improve the accuracy of the display screen quality inspection.

[0011] In one embodiment of the present application, the attribute information of the target Mura defect includes at least one of the following: the area, shape, contrast and position of the target Mura defect;

[0012] The area of ​​the target Mura defect is: the number of pixels in the defect image area, or the area of ​​the minimum circumscribed rectangle of the defect image area;

[0013] The shape of the target Mura defect is represented by the Hu moment of the defect image area.

[0014] In one embodiment of the present application, the defect extraction of the image to be detected to obtain a defect image area of ​​the target Mura defect in the display screen to be detected in the image to be detected includes:

[0015] The image to be inspected is input into a pre-trained defect extraction model, and an image region in the image to be inspected where a target Mura defect in the display screen to be inspected is located output by the defect extraction model is obtained as a defect image region.

[0016] In one embodiment of the present application, the defect extraction model includes a convolutional network and a deconvolutional network; the convolutional network includes a plurality of convolutional layers; the deconvolutional network includes a plurality of deconvolutional layers;

[0017] The step of inputting the image to be detected into a pre-trained defect extraction model to obtain an image region in the image to be detected where a target Mura defect in the display screen to be detected output by the defect extraction model is located as a defect image region includes:

[0018] Processing the image to be detected by a convolutional layer in the convolutional network to obtain image features of the image to be detected;

[0019] The image features of the image to be detected are processed by the deconvolution layer in the deconvolution network to obtain the target Mura defect in the display screen to be detected in the image area where the image to be detected is located, as the defect image area.

[0020] In one embodiment of the present application, the training method of the defect extraction model includes:

[0021] Acquire a sample image and a sample defect area of ​​a sample Mura defect in the sample image that is marked;

[0022] Inputting the sample image into a defect extraction model of an initial structure to obtain a predicted defect area of ​​a sample Mura defect in the sample image output by the defect extraction model;

[0023] Calculating a function value of a first loss function based on the sample defect area and the predicted defect area;

[0024] Based on the function value of the first loss function, the model parameters of the defect extraction model are adjusted until a preset convergence condition is reached to obtain a trained defect extraction model.

[0025] In one embodiment of the present application, the calculating the perceived amount of the target Mura defect based on the attribute information of the target Mura defect includes:

[0026] The attribute information of the target Mura defect is input into a pre-trained perception quantity prediction model to obtain the perception quantity of the target Mura defect.

[0027] As can be seen from the above, the technical solution provided by this embodiment takes the area, shape, contrast and position of the target Mura defect as input, and outputs the perception amount of the target Mura defect through the perception amount prediction model based on deep learning, which can improve the accuracy of the determined perception amount and further improve the accuracy of the quality inspection of the display screen. In addition, compared with the traditional method of quantifying the target Mura defect, the parameters of the perception amount prediction model based on deep learning are autonomously learned in the back propagation, and do not require manual parameter adjustment, which can more fully cover more scenarios.

[0028] In one embodiment of the present application, the perception prediction model is a multi-layer perceptron MLP; the perception prediction model includes multiple hidden layers;

[0029] The step of inputting the attribute information of the target Mura defect into a pre-trained perception quantity prediction model to obtain the perception quantity of the target Mura defect includes:

[0030] A feature matrix representing the attribute information of the target Mura defect is input into the perception amount prediction model, and the feature matrix output by the previous hidden layer is processed in sequence through the multiple hidden layers until the last hidden layer outputs the perception amount of the target Mura defect.

[0031] As can be seen from the above, the technical solution provided in this embodiment takes the area, shape, contrast and position of the target Mura defect as input, and outputs the perception amount of the target Mura defect through the perception amount prediction model based on deep learning, which can improve the accuracy of the determined perception amount and further improve the accuracy of the quality inspection of the display screen. Moreover, compared with the traditional method of quantifying the target Mura defects, the parameters of the perception amount prediction model based on deep learning are autonomously learned in the back propagation, and no manual adjustment is required, which can more fully cover more scenes. At the same time, as many features as possible can be selected for fitting according to actual needs, which is closer to the actual perception level of the human eye. Compared with other neural networks, MLP can explicitly select features and reduce dependence on the amount of data. Moreover, MLP can select the position of the target Mura defect as a feature to participate in the fitting of the perception amount, thereby improving the accuracy of the determined perception amount.

[0032] In one embodiment of the present application, the training method of the perception prediction model includes:

[0033] Acquire attribute information of sample Mura defects in a sample display screen, and annotated sample perception amounts of the sample Mura defects;

[0034] Inputting the attribute information of the sample Mura defect into the perception quantity prediction model of the initial structure to obtain the predicted perception quantity of the sample Mura defect output by the perception quantity prediction model;

[0035] Calculating a function value of a second loss function based on the sample perception amount of the sample Mura defect and the predicted perception amount;

[0036] Based on the function value of the second loss function, the model parameters of the perception quantity prediction model are adjusted until a preset convergence condition is reached to obtain a trained perception quantity prediction model.

[0037] In one embodiment of the present application, determining the quality inspection result of the display screen to be inspected based on the perceived amount of the target Mura defect includes:

[0038] Determine the maximum value of the perception amounts of multiple target Mura defects as the target perception amount;

[0039] When the target perception amount is greater than a preset threshold, determining that the quality inspection result of the display screen to be inspected is unqualified;

[0040] When the target perception amount is not greater than a preset threshold, it is determined that the quality inspection result of the display screen to be inspected is qualified.

[0041] As can be seen from the above, the technical solution provided in this embodiment determines that the quality inspection result of the display screen to be inspected is unqualified when at least one target Mura defect can be perceived by the user, thereby preventing the user from receiving unqualified products and improving the user experience.

[0042] In one embodiment of the present application, determining the quality inspection result of the display screen to be inspected based on the perceived amount of the target Mura defect includes:

[0043] For each target Mura defect in the display screen to be inspected, when the perceived amount of the target Mura defect is greater than a preset threshold, determining that a quality inspection result obtained based on the target Mura defect is unqualified;

[0044] When the perceived amount of the target Mura defect is not greater than a preset threshold, determining that the quality inspection result obtained based on the target Mura defect is qualified;

[0045] When there is an unqualified result among the quality inspection results, determining that the quality inspection result of the display screen to be inspected is unqualified;

[0046] When there is no unqualified result in each quality inspection result, it is determined that the quality inspection result of the display screen to be inspected is qualified.

[0047] As can be seen from the above, the technical solution provided in this embodiment determines that the quality inspection result of the display screen to be inspected is unqualified when at least one target Mura defect can be perceived by the user, thereby preventing the user from receiving unqualified products and improving the user experience.

[0048] In one embodiment of the present application, the step of obtaining an image of the display screen to be detected, which is captured when the display screen to be detected displays a preset picture, as the image to be detected, includes:

[0049] Using a camera to capture an image of the display screen to be detected when it displays a preset screen, and obtaining an image of the display screen to be detected with a specified grayscale as an initial image;

[0050] The image area where the display screen to be detected is located in the initial image is extracted to obtain the image to be detected.

[0051] From the above, it can be seen that the technical solution provided in this embodiment extracts the image area where the display screen is located from the initial image captured by the camera as the image to be detected, which can avoid the influence of the background image other than the display screen on the defect extraction, improve the accuracy of Mura defect extraction, and further improve the accuracy of quality inspection of the display screen.

[0052] In one embodiment of the present application, the step of obtaining an image of the display screen to be detected, which is captured when the display screen to be detected displays a preset picture, as the image to be detected, includes:

[0053] Using a camera to respectively capture images of the display screen to be detected when displaying different preset images, to obtain images of the display screen to be detected with different grayscales as initial images;

[0054] Extracting the image area where the display screen to be detected is located in each initial image respectively to obtain a plurality of images to be detected;

[0055] The determining the quality inspection result of the display screen to be inspected based on the perceived amount of the target Mura defect includes:

[0056] The quality inspection result of the display screen to be inspected is determined based on the perceived amount of the target Mura defect obtained from each image to be inspected.

[0057] As can be seen from the above, the solution provided in this embodiment obtains images of the display screen to be inspected with different grayscales, and then determines the perceived amount of the target Mura defect based on the images of the display screen to be inspected with different grayscales, and then determines the quality inspection result of the display screen to be inspected, which can improve the accuracy of quality inspection of the display screen.

[0058] In a second aspect, an embodiment of the present application further provides a quality detection system for a display screen, the system comprising: an electronic device and a camera;

[0059] The electronic device is used to light up the display screen to be detected and control the display screen to be detected to display a preset picture;

[0060] The camera is used to capture an image of the display screen to be detected when it displays a preset picture;

[0061] The electronic device is further used to obtain an image to be detected based on an image captured by the camera when the display screen to be detected displays a preset screen; perform defect extraction on the image to be detected to obtain a defect image area of ​​a target Mura defect in the display screen to be detected in the image to be detected; calculate attribute information of the target Mura defect based on the defect image area of ​​the target Mura defect; calculate a perceived amount of the target Mura defect based on the attribute information of the target Mura defect; wherein the perceived amount indicates a user's perception degree of the target Mura defect; and determine a quality inspection result of the display screen to be detected based on the perceived amount of the target Mura defect.

[0062] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0063] one or more processors and memory;

[0064] The memory is coupled to the one or more processors, and the memory is used to store computer program codes, wherein the computer program codes include computer instructions, and the one or more processors call the computer instructions to enable the electronic device to execute any of the above-mentioned display quality detection methods.

[0065] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, comprising a computer program, which, when executed on an electronic device, enables the electronic device to execute any of the above-described methods for detecting the quality of a display screen.

[0066] In a fifth aspect, an embodiment of the present application further provides a computer program product, which includes executable instructions. When the executable instructions are executed on an electronic device, the electronic device executes any of the above-mentioned display quality detection methods.

[0067] In a sixth aspect, an embodiment of the present application further provides a chip system, which is applied to an electronic device, and the chip system includes one or more processors, and the processor is used to call computer instructions so that the electronic device inputs data into the chip system, and executes any of the above-mentioned display quality detection methods to process the data and output processing results.

[0068] The beneficial effects of the solutions provided by the embodiments in the second, third, fourth, fifth and sixth aspects can refer to the beneficial effects of the solutions provided by the embodiments in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0070] Figure 1 A structural diagram of an electronic device provided in an embodiment of the present application;

[0071] Figure 2 A software structure block diagram of an electronic device provided in an embodiment of the present application;

[0072] Figure 3 A schematic diagram of the first type of Mura defect provided in an embodiment of the present application;

[0073] Figure 4 A schematic diagram of a second type of Mura defect provided in an embodiment of the present application;

[0074] Figure 5 A schematic diagram of a third type of Mura defect provided in an embodiment of the present application;

[0075] Figure 6 A schematic diagram of the fourth type of Mura defect provided in an embodiment of the present application;

[0076] Figure 7 A schematic diagram of the fifth type of Mura defect provided in an embodiment of the present application;

[0077] Figure 8 A flowchart of a first display screen quality detection method provided in an embodiment of the present application;

[0078] Fig. 9 A flowchart of obtaining an image to be detected of a display screen provided in an embodiment of the present application;

[0079] Fig.10 A schematic diagram of a defective image area determined in an embodiment of the present application;

[0080] Fig.11 A schematic diagram of a first method of determining a perception amount based on a perception amount prediction model provided in an embodiment of the present application;

[0081] Fig.12 A schematic diagram of a second method of determining a perception amount based on a perception amount prediction model provided in an embodiment of the present application;

[0082] Fig.13 A flow chart of a second display screen quality detection method provided in an embodiment of the present application;

[0083] Fig.14 A structure of a display screen quality inspection system provided in an embodiment of the present application;

[0084] Fig.15 The application provided in the embodiment of the present application is Fig.14 A flow chart of a method for detecting the quality of a display screen of the system shown;

[0085] Fig.16 A structural diagram of a chip system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0086] In order to better understand the technical solution of the present application, the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0087] In order to facilitate the clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, the words "first" and "second" are used to distinguish the same items or similar items with substantially the same functions and effects. For example, the first instruction and the second instruction are to distinguish different user instructions, and their order is not limited. Those skilled in the art can understand that the words "first" and "second" do not limit the quantity and execution order, and the words "first" and "second" do not necessarily limit them to be different.

[0088] It should be noted that, in this application, words such as "exemplarily" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplarily" or "for example" in this application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplarily" or "for example" is intended to present related concepts in a specific way.

[0089] The quality detection method of a display screen provided in the embodiment of the present application is applied to electronic devices, which may be mobile phones, tablet computers, personal digital assistants (PDAs), servers, and other devices.

[0090] For example, Figure 1 The structure diagram of the electronic device 100 is shown. The electronic device 100 may include a processor 110, a display screen 120, a camera 130, an internal memory 140, a Subscriber Identification Module (SIM) card interface 150, a Universal Serial Bus (USB) interface 160, a charging management module 170, a battery management module 171, a battery 172 with a cell and a battery protection device, a sensor module 180, a mobile communication module 190, a wireless communication module 200, an antenna 1 and an antenna 2, etc. The sensor module 180 may include a pressure sensor 180A, a fingerprint sensor 180B, a touch sensor 180C, an ambient light sensor 180D, etc.

[0091] It is to be understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0092] The processor 110 may include one or more processing units, for example: the processor 110 may include a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processor (NPU), etc. Among them, different processing units may be independent components or integrated into one or more processors. In some embodiments, the electronic device 100 may also include one or more processors 110. Among them, the controller may generate an operation control signal according to the instruction opcode and the timing signal to complete the control of fetching and executing instructions. In some other embodiments, a memory may also be provided in the processor 110 for storing instructions and data. Exemplarily, the memory in the processor 110 may be a high-speed cache memory. The memory may store instructions or data that the processor 110 has just used or circulated. If the processor 110 needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated accesses, reduces the waiting time of the processor 110, and thus improves the efficiency of the electronic device 100 in processing data or executing instructions.

[0093] In some embodiments, the processor 110 may include one or more interfaces. The interface may include an Inter-Integrated Circuit (I2C) interface, an Inter-Integrated Circuit Sound (I2S) interface, a Pulse Code Modulation (PCM) interface, a Universal Asynchronous Receiver / Transmitter (UART) interface, a Mobile Industry Processor Interface (MIPI), a General-Purpose Input / Output (GPIO) interface, a SIM card interface and / or a USB interface, etc. Among them, the USB interface 160 is an interface that complies with the USB standard specification, and specifically can be a Mini USB interface, a Micro USB interface, a USB Type C interface, etc. The USB interface 160 can be used to connect a charger to charge the electronic device 100, and can also be used to transmit data between the electronic device 100 and a peripheral device. The USB interface 160 can also be used to connect headphones to play audio through the headphones.

[0094] It is understandable that the interface connection relationship between the modules illustrated in the embodiment of the present application is for illustrative purposes only and does not constitute a structural limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may also adopt different interface connection methods in the above embodiments, or a combination of multiple interface connection methods.

[0095] The wireless communication function of the electronic device 100 can be implemented through the antenna 1, the antenna 2, the mobile communication module 190, the wireless communication module 200, the modem processor, the baseband processor, and the like.

[0096] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 100 can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve the utilization of antennas. For example, antenna 1 can be reused as a diversity antenna for a wireless local area network. In some other embodiments, the antenna can be used in combination with a tuning switch.

[0097] The electronic device 100 implements the display function through a GPU, a display screen 120, and an application processor. The GPU is a microprocessor for image processing, which connects the display screen 120 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 110 may include one or more GPUs, which execute program instructions to generate or change display information.

[0098] The display screen 120 is used to display images, videos, etc. The display screen 120 includes a display panel. The display panel may be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the electronic device 100 may include one or more display screens 120.

[0099] In some embodiments of the present application, when the display panel is made of materials such as OLED, AMOLED, FLED, etc., the above Figure 1 The display screen 120 in the embodiment can be bent. Here, the display screen 120 can be bent means that the display screen can be bent to any angle at any position and can be kept at the angle, for example, the display screen 120 can be folded in half from the middle to the left or right. It can also be folded in half from the middle to the top or bottom.

[0100] The display screen 120 of the electronic device 100 can be a flexible screen. At present, flexible screens have attracted much attention for their unique characteristics and huge potential. Compared with traditional screens, flexible screens have the characteristics of strong flexibility and bendability, which can provide users with a new interaction method based on bendable characteristics, and can meet users' more needs for electronic devices. For electronic devices equipped with a foldable display, the foldable display on the electronic device can be switched between a small screen in a folded form and a large screen in an unfolded form at any time. Therefore, users use the split-screen function on electronic devices equipped with a foldable display more and more frequently.

[0101] The electronic device 100 can realize the shooting function through the ISP, the camera 130, the video codec, the GPU, the display screen 120 and the application processor, etc., wherein the camera 130 includes a front camera and a rear camera.

[0102] The ISP is used to process the data fed back by the camera 130. For example, when shooting, the shutter is opened, and light is transmitted to the camera photosensitive element through the lens. The light signal is converted into an electrical signal, and the camera photosensitive element transmits the electrical signal to the ISP for processing and converts it into an image visible to the naked eye. The ISP can perform algorithm optimization on the noise 15, brightness and color of the image. The ISP can also optimize the exposure and color temperature of the shooting scene and other parameters. In some embodiments, the ISP can be set in the camera 130.

[0103] The camera 130 is used to take photos or videos. The object generates an optical image through the lens and projects it onto the photosensitive element. The photosensitive element can be a charge coupled device (CCD) or a complementary metal oxide semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, and then transmits the electrical signal to the ISP to be converted into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. The DSP converts the digital image signal into an image signal in a standard red green blue (RGB), YUV or other format. In some embodiments, the electronic device 100 may include 1 or N cameras 130, where N is a positive integer greater than 1.

[0104] The digital signal processor is used to process digital signals, and can process not only digital image signals but also other digital signals. For example, when the electronic device 100 is selecting a frequency point, the digital signal processor is used to perform Fourier transform on the frequency point energy.

[0105] Video codecs are used to compress or decompress digital videos. The electronic device 100 may support one or more video codecs. Thus, the electronic device 100 may play or record videos in a variety of coding formats, such as Moving Picture Experts Group (MPEG) 1, MPEG2, MPEG3, and MPEG4.

[0106] NPU is a neural network (NN) computing processor. By drawing on the structure of biological neural networks, such as the transmission mode between neurons in the human brain, it can quickly process input information and can also continuously self-learn. NPU can realize applications such as intelligent cognition of electronic device 100, such as image recognition, face recognition, voice recognition, text understanding, etc.

[0107] The internal memory 140 can be used to store one or more computer programs, which include instructions. The processor 110 can execute the above instructions stored in the internal memory 140, so that the electronic device 100 performs the quality detection method of the display screen provided in some embodiments of the present application, as well as various applications and data processing. The internal memory 140 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system; the program storage area can also store one or more applications (such as a gallery, contacts, etc.). The data storage area can store data (such as photos, contacts, etc.) created during the use of the electronic device 100. In addition, the internal memory 140 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more disk storage components, flash memory components, universal flash storage (Universal Flash Storage, UFS), etc. In some embodiments, the processor 110 can execute the quality detection method of the display screen provided in the embodiment of the present application, as well as other applications and data processing by running the instructions stored in the internal memory 140 and / or the instructions stored in the memory provided in the processor 110.

[0108] The internal memory 140 can be used to store relevant programs of the quality detection method for the display screen provided in the embodiment of the present application, and the processor 110 can be used to call the relevant programs of the quality detection method for the display screen stored in the internal memory 140 when displaying information, and execute the quality detection method for the display screen in the embodiment of the present application.

[0109] The sensor module 180 may include a pressure sensor 180A, a fingerprint sensor 180B, a touch sensor 180C, an ambient light sensor 180D, and the like.

[0110] The pressure sensor 180A is used to sense the pressure signal and can convert the pressure signal into an electrical signal. In some embodiments, the pressure sensor 180A can be set on the display screen 120. There are many types of pressure sensors 180A, for example, they can be resistive pressure sensors, inductive pressure sensors or capacitive pressure sensors. The capacitive pressure sensor can be a parallel plate including at least two conductive materials. When the force acts on the pressure sensor 180A, the capacitance between the electrodes changes, and the electronic device 100 determines the intensity of the pressure according to the change in capacitance. When the touch operation acts on the display screen 120, the electronic device 100 detects the touch operation according to the pressure sensor 180A. The electronic device 100 can also calculate the position of the touch according to the detection signal of the pressure sensor 180A. In some embodiments, touch operations acting on the same touch position but with different touch operation intensities can correspond to different operation instructions. For example: when a touch operation with a touch operation intensity less than the first pressure threshold acts on a short message application icon, an instruction to view the short message is executed; when a touch operation with a touch operation intensity greater than or equal to the first pressure threshold acts on a short message application icon, an instruction to create a new short message is executed.

[0111] The fingerprint sensor 180B is used to collect fingerprints. The electronic device 100 can use the collected fingerprint characteristics to realize functions such as unlocking, accessing application locks, taking photos, and answering calls.

[0112] The touch sensor 180C is also called a touch control device. The touch sensor 180C can be arranged on the display screen 120, and the touch sensor 180C and the display screen 120 form a touch screen, which is also called a touch control screen. The touch sensor 180C is used to detect a touch operation acting on or near it. The touch sensor 180C can pass the detected touch operation to the application processor to determine the type of touch event. A visual output related to the touch operation can be provided through the display screen 120. In other embodiments, the touch sensor 180C can also be arranged on the surface of the electronic device 100, and is arranged at a different position from the display screen 120.

[0113] The ambient light sensor 180D is used to sense the brightness of the ambient light. The electronic device 100 can adaptively adjust the brightness of the display screen 120 according to the perceived brightness of the ambient light. The ambient light sensor 180D can also be used to automatically adjust the white balance when shooting. The ambient light sensor 180D can also transmit the environmental information of the device to the GPU.

[0114] The ambient light sensor 180D is also used to obtain the brightness, light ratio, color temperature, etc. of the environment in which the camera 130 captures images.

[0115] Figure 2A software structure block diagram of an electronic device applicable to an embodiment of the present application. The software system of the electronic device can adopt a layered architecture, an event-driven architecture, a micro-core architecture, a micro-service architecture, or a cloud architecture. The layered architecture divides the software system of the electronic device into several layers, each with a clear role and division of labor. The layers communicate with each other through software interfaces. In some embodiments, the software system can be divided into three layers, namely, an application layer (applications), an application framework layer (application framework), and a driver layer (hardware abstract layer, HAL).

[0116] The application layer can include a series of application packages. The application layer runs applications by calling the application programming interface (API) provided by the application framework layer. Figure 2 As shown, the application package may include multiple applications, such as camera, photo album, browser, and music programs.

[0117] The application framework layer provides API and programming framework for the applications in the application layer. The application framework layer includes some predefined functions. Figure 2 As shown, the application framework layer may include a window manager, a content provider, a view system, a resource manager, a notification manager, and a Dynamic Host Configuration Protocol (DHCP) module.

[0118] The driver layer is a layer between hardware and software, used to drive the hardware to make it work. The driver layer can be installed with multiple drivers for driving the hardware to work. For example, camera drivers, display drivers, audio drivers, and sensor drivers.

[0119] In addition, the electronic device also includes a hardware layer, which may include a camera, a speaker, a microphone, a display screen, etc. The hardware layer is connected to the driver layer.

[0120] The application scenarios of the embodiments of the present application are described below.

[0121] There are many reasons for the Mura defect in the display screen. For example, uneven materials, uneven force during processing, extrusion and bumps caused by improper assembly, etc. Compared with obvious objective defects with clear quantitative standards (such as cracks, missing pixels, foreign objects in the bonding, etc.), Mura defects have the following characteristics:

[0122] 1. Various shapes: Mura defects have various shapes, such as dots, lines, spots or irregular shapes. The size and degree of Mura defects also vary.

[0123] For example, Figure 3 In the image shown in FIG. , the spotted Mura (which may be referred to as bright spot Mura) within the circular frame 301 is shown. Figure 4 The spotted Mura (which may be referred to as dark spot Mura) within the circular frame 401 in the image is shown. Figure 5 Linear Mura (which may be referred to as horizontal line Mura) within a rectangular frame 501 in the image shown. Figure 6 Linear Mura (which may be referred to as vertical line Mura) within a rectangular frame 601 in the image shown.

[0124] 2. Difficult to quantify: Mura defects are relatively difficult to quantify. Since Mura defects are affected by multiple factors such as brightness, color, background and observation conditions in visual perception, there is usually no unified quantification standard, which makes it difficult to quantify. For example, Figure 3 and Figure 4 Mura defects in the display are relatively easy to perceive visually. Figure 5 and Figure 6 Mura defects in the display are relatively difficult to perceive visually.

[0125] 3. Subjective differences: Different people may perceive the same mura defect in the same location differently, and may also perceive the same mura defect in different locations differently.

[0126] Based on the above characteristics of Mura defects, it is difficult to quantify Mura defects. If traditional image processing methods are used for analysis, they often have poor generalization ability and are difficult to cover most scenarios. In addition, since traditional image processing methods require manual adjustment of parameters, they are prone to seesaw phenomenon (i.e., they cannot take into account the different characteristics of Mura defects), making it difficult to meet different detection needs.

[0127] For the detection scenario of Mura defects in mobile phone displays, Mura defects include color cast, uneven display, short-term afterimage, etc. as subjective defects. In addition to detecting the area where the Mura defects are located in the display, the degree of visibility of the Mura defects should also be determined to determine the quality of the display.

[0128] For example, Figure 7 The display screen shown includes four bright spots of Mura, namely, Mura defects in rectangular frames 701, 702, 703, and 704, and one dark spot of Mura, namely, Mura defect in rectangular frame 705. Figures 3 to 6The display shown has only one mura defect. Therefore, after detecting the mura defect in the display, the quality of the display should be determined based on the mura defect in the display.

[0129] Next, the quality detection method of the display screen provided in the embodiment of the present application is described in detail through specific examples.

[0130] In one embodiment of the present application, see Figure 8 , Figure 8 A flow chart of a method for detecting the quality of a display screen provided in an embodiment of the present application, the method may include the following steps:

[0131] S801: Acquire an image of the display screen to be detected that is captured when the display screen to be detected displays a preset picture, as an image to be detected.

[0132] S802: Defect extraction is performed on the image to be inspected to obtain a defect image region of a target Mura defect in the display screen to be inspected in the image to be inspected.

[0133] S803: Calculate attribute information of the target Mura defect based on the defect image area of ​​the target Mura defect.

[0134] S804: Calculate the perceived amount of the target Mura defect based on the attribute information of the target Mura defect.

[0135] The perception amount indicates the user's perception degree of the target Mura defect in the display screen to be inspected.

[0136] S805: Determine a quality inspection result of the display screen to be inspected based on the perceived amount of the target Mura defect.

[0137] As can be seen from the above, the technical solution provided by this embodiment can determine the quality inspection result of the display screen to be inspected, and then guarantee the product quality of the display screen based on the inspection result, and improve the user experience. In addition, the perception amount representing the user's perception degree of the target Mura defect in the display screen to be inspected can be determined. The greater the perception amount, the higher the user's perception degree of the target Mura defect in the display screen to be inspected. Furthermore, the quality inspection of the display screen to be inspected based on the perception amount of the target Mura defect in the display screen to be inspected can improve the accuracy of the display screen quality inspection.

[0138] For step S801, the display screen to be tested is a display screen of a mobile phone, a computer or other device. The display screen to be tested may have been installed on a mobile phone, a computer or other device. Alternatively, the display screen to be tested may also be installed on a test device. The test device can control the display screen to be tested to light up according to the instructions of the electronic device, and control the display screen to be tested to display a preset screen.

[0139] The preset images include: a white image, and other images of different grayscales, etc. The preset image displayed on the display screen to be detected is determined based on the grayscale of the image to be detected that needs to be collected.

[0140] In one implementation, step S801 may include the following steps: photographing an image of the display screen to be detected when displaying a preset screen through a camera to obtain an image of the display screen to be detected with a specified grayscale as an initial image; extracting an image area where the display screen to be detected is located in the initial image to obtain an image to be detected.

[0141] The specified grayscale refers to a grayscale with a higher detection accuracy for the Mura defect of the display screen. The specified grayscale is obtained based on testing images of display screens with different grayscales.

[0142] See also Fig. 9 , Fig. 9 A flowchart for obtaining an image to be detected is provided in an embodiment of the present application.

[0143] The electronic device lights up the display screen to be tested and controls the display screen to be tested to display a preset picture. For example, the electronic device sends a lighting command to the test device, and the display screen to be tested in the test device is lit, and the preset picture is displayed on the display screen to be tested. Then, the electronic device sends a shooting command to the camera, calling the camera to shoot the image of the display screen to be tested when the preset picture is displayed. The camera can be an industrial camera or a colorimeter.

[0144] For example, the electronic device instructs the test device to display a white screen on the display screen to be tested, and sends a shooting instruction to the camera, calling the camera to shoot an image of the display screen to be tested when the white screen is displayed. Then, the camera returns the captured image to the electronic device, and the electronic device obtains an image of the display screen to be tested with a specified grayscale (i.e., the initial image).

[0145] The electronic device extracts the image area where the display screen to be detected is located in the initial image, and can obtain the image to be detected.

[0146] From the above, it can be seen that the technical solution provided in this embodiment extracts the image area where the display screen to be inspected is located from the initial image captured by the camera as the image to be inspected, which can avoid the influence of the background image other than the display screen to be inspected on the defect extraction, improve the accuracy of Mura defect extraction, and further improve the accuracy of quality inspection of the display screen.

[0147] In another implementation, step S801 may include the following steps: using a camera to respectively capture images of the display screen to be detected when it displays different preset screens, to obtain images of the display screen to be detected with different grayscales as initial images; and extracting the image area where the display screen to be detected is located in each initial image, to obtain multiple images to be detected.

[0148] based on Figures 3 to 6 It can be obtained that the perception degree of different Mura defects is different under different grayscales. In order to improve the accuracy of detecting the target Mura defects of the display screen to be inspected, the electronic device collects images of the display screen to be inspected when displaying different preset pictures through a camera to obtain images of the display screen to be inspected with different grayscales.

[0149] For example, Fig. 9 In an embodiment, the electronic device instructs the test device to display a white screen on the display screen to be tested, and sends a shooting instruction to the camera, calling the camera to shoot an image of the display screen to be tested when the white screen is displayed. Then, the electronic device instructs the test device to switch the display screen to be tested to display other screens with low grayscale, and the electronic device sends a shooting instruction to the camera again, calling the camera to shoot an image of the display screen to be tested when other screens are displayed. Based on this, two images of the display screen to be tested with different grayscales can be obtained. Then, the camera returns the captured image to the electronic device, and the electronic device obtains images of the display screen to be tested with different grayscales (i.e., initial images).

[0150] For each initial image captured, the electronic device extracts the image area where the display screen to be inspected is located in the initial image, and multiple images to be inspected can be obtained. Subsequently, for each image to be inspected, the perceived amount of the target Mura defect of the display screen to be inspected is determined based on the image to be inspected, and the quality inspection result of the display screen to be inspected is determined based on the perceived amount of the target Mura defect.

[0151] As can be seen from the above, the solution provided in this embodiment obtains images of the display screen to be inspected with different grayscales, and then determines the perceived amount of the target Mura defect based on the images of the display screen to be inspected with different grayscales, and then determines the quality inspection result of the display screen to be inspected, which can improve the accuracy of quality inspection of the display screen.

[0152] The electronic device extracts the image area where the display screen to be detected is located from the initial image in the following manner.

[0153] 1. Use the target detection algorithm to perform target detection on the initial image, obtain the detection frame of the image area where the display screen to be detected is located in the initial image, and extract the image area where the display screen to be detected is located according to the detection frame.

[0154] 2. Define the region in the initial image where the gray value is greater than the threshold as the region of interest (ROI). Then, extract the region of interest according to the defined region to obtain the image region where the display screen to be detected is located.

[0155] 3. The electronic device creates a mask image of the same size as the initial image and draws the region of interest on the mask image according to the size of the display screen to be inspected. Then, the mask image is applied to the initial image to extract the region of interest and obtain the image area where the display screen to be inspected is located.

[0156] After extracting the image area where the display screen to be detected is located, the electronic device can also preprocess the extracted image area, such as performing Gaussian filtering on the extracted image area to smooth and reduce noise on the extracted image area to obtain the image to be detected.

[0157] With respect to step S802 , after obtaining the image to be detected, the electronic device detects the image to be detected and determines a defect image region of a target Mura defect in the display screen to be detected.

[0158] In some embodiments, step S802 may include the following steps: inputting the image to be inspected into a pre-trained defect extraction model, obtaining an image region in the image to be inspected where a target Mura defect in the display screen to be inspected is located output by the defect extraction model as a defect image region.

[0159] The defect extraction model is a semantic segmentation network model, such as U-Net.

[0160] In some embodiments, the defect extraction model includes a convolutional network and a deconvolutional network. The convolutional network includes a plurality of convolutional layers, and the deconvolutional network includes a plurality of deconvolutional layers.

[0161] The step of determining the defect image area through the defect extraction model includes: processing the image to be detected through the convolution layer in the convolution network to obtain the image features of the image to be detected; processing the image features of the image to be detected through the deconvolution layer in the deconvolution network to obtain the image area where the target Mura defect in the display screen to be detected is located in the image to be detected as the defect image area.

[0162] See also Fig.10 , Fig.10 A schematic diagram of a method for determining a defective image area provided in an embodiment of the present application. Fig.10 In the example, a convolutional network of a defect extraction model includes three convolutional layers and a deconvolutional network includes three deconvolutional layers. In practical applications, more convolutional layers can be set for the convolutional network and more deconvolutional layers can be set for the deconvolutional network based on demand.

[0163] The image to be detected is input into the first convolution layer to obtain the image features output by the first convolution layer; the image features output by the first convolution layer are input into the second convolution layer to obtain the image features output by the second convolution layer; the image features output by the second convolution layer are input into the third convolution layer to obtain the image features output by the third convolution layer. The image features output by the third convolution layer are input into the first deconvolution layer to obtain the image features output by the first deconvolution layer; the image features output by the first deconvolution layer are input into the second deconvolution layer to obtain the image features output by the second deconvolution layer; the image features output by the second deconvolution layer are input into the third deconvolution layer to obtain the defect image area where the target mura defect in the display screen to be detected is located in the image to be detected, which is output by the third deconvolution layer. Fig.10 Three defective image areas were detected.

[0164] In some embodiments, the electronic device may train the defect extraction model of the initial structure in the following manner to obtain a trained defect extraction model.

[0165] A data set for training a defect extraction model is constructed, and the data set includes multiple data pairs. The data pair includes a sample image and a sample defect area of ​​a sample Mura defect in the sample image. The sample image is input into the defect extraction model of the initial structure to obtain a predicted defect area of ​​a sample Mura defect in the sample image output by the defect extraction model. Based on the sample defect area and the predicted defect area, the function value of the first loss function is calculated. The first loss function value represents the difference between the sample defect area and the predicted defect area. Furthermore, based on the function value of the first loss function, the model parameters of the defect extraction model are back-propagated and continuously iterated and updated until a preset convergence condition is reached to obtain a trained defect extraction model.

[0166] For step S803, the attribute information of the target Mura defect includes at least one of the following: the area, shape, contrast and position of the target Mura defect. The area of ​​the target Mura defect is: the number of pixels in the defect image area, or the area of ​​the minimum circumscribed rectangle of the defect image area. The shape of the target Mura defect is represented by the Hu moment of the defect image area. The Hu moment is an image feature with translation, rotation and scale invariance.

[0167] For each defective image area, determine the contrast of the image area at the position of the defective image area in the image to be detected, and obtain the contrast of the target Mura defect to which the defective image area belongs; and determine that the position of the defective image area in the image to be detected represents the position of the target Mura defect in the display screen to be detected.

[0168] And the number of pixels in the defect image area, or the area of ​​the minimum circumscribed rectangle of the defect image area is calculated to obtain the area of ​​the target Mura defect to which the defect image area belongs. The Hu moment of the defect image area is calculated to obtain the area of ​​the target Mura defect to which it belongs.

[0169] Hu moments are a set of invariant moments based on image moments, which are used to describe the shape characteristics of images. Hu moments remain unchanged under the rotation, scaling and mirroring transformations of images. Hu moments are composed of seven invariant moments, each of which captures different aspects of the image shape. For example, you can choose Moments represent the shape of the target Mura defect. Moment representation reflects the overall distribution characteristics of an image and is mainly related to the shape and distribution of the image.

[0170] Electronic devices can calculate the target mura defect as follows Square.

[0171] First, the common moment of the target mura defect is calculated. The common moment is the weighted sum of the pixel values ​​of each pixel in the defect image area of ​​the mura defect. The common moment is expressed as the following formula (1):

[0172] (1);

[0173] in, Represents the pixel value of the pixel at the coordinate (x, y) in the defect image area of ​​the target mura defect; p and q are non-negative integers.

[0174] Then, the central moment of the defect image area of ​​the target mura defect is calculated. The central moment is the moment relative to the image center of mass and is expressed as the following formula (2):

[0175] (2);

[0176] in,( , ) represents the coordinates of the image centroid of the defect image area of ​​the target Mura defect. The coordinates of the image centroid of the defect image area of ​​the target Mura defect are expressed as follows:

[0177] (3);

[0178] (4);

[0179] in, is the value when p is 1 and q is 0 in the above formula (1); is the value when p and q in the above formula (1) are 0 and 0 respectively; It is the value when p is 0 and q is 1 in the above formula (1).

[0180] Then, the normalized central moment of the defect image area of ​​the target mura defect is calculated. The normalized central moment is the normalized form of the central moment and can be expressed as the following formula (5):

[0181] (5);

[0182] in, ; It is the value when p is 0 and q is 0 in the above formula (2).

[0183] Finally, the defect image area of ​​the target mura defect is calculated. Moment, It is expressed as the following formula (6):

[0184] (6);

[0185] is the value when p is 2 and q is 0 in the above formula (5); is the value when p is 0 and q is 2 in the above formula (5).

[0186] With respect to step S804, different attribute information represents different aspects of the characteristics of the target Mura defect. The perceived amount of the target Mura defect is affected by different characteristics, so the perceived amount of the target Mura defect can be determined based on different attribute information.

[0187] The perceived amount of the target Mura defect is affected by characteristics such as area, shape, and contrast. The perceived amount and the characteristics of the target Mura defect can be modeled as a function, and the following formula (7) can be obtained:

[0188] (7);

[0189] Indicates perceived quantity; Represents the functional relationship between the perceived quantity and the characteristics of the target mura defect; Indicates the contrast of the target mura defect; Indicates the area of ​​the target Mura defect; represents the shape of the target Mura defect; ... represents other attribute information of the target Mura defect.

[0190] In the traditional quantification method for the target Mura defect, the characteristics of the target Mura defect used for perceptual quantity fitting are determined, and the above function is artificially designed based on experience. For example, the determination is made only based on the area of ​​the target Mura defect, that is, the above formula (1) is simplified to: .

[0191] However, the measurability of determining the perception amount based only on the area of ​​the target Mura defect is poor. If more features are selected, the complexity of the above function design and the workload of manual parameter adjustment will increase. It is often difficult to truly meet the actual perception level of the human eye in engineering, and the coverage of scenarios is insufficient and the generalization is poor.

[0192] For each target Mura defect in the display screen to be detected, a perception amount representing the user's perception of the target Mura defect is determined based on the attribute information of the target Mura defect and the perception amount prediction model. The larger the perception amount, the higher the user's perception of the target Mura defect, and the lower the quality of the display screen to be detected to which the target Mura defect belongs.

[0193] Accordingly, step S804 may include the following steps: inputting the attribute information of the target Mura defect into a pre-trained perception quantity prediction model to obtain the perception quantity of the target Mura defect.

[0194] Among them, the perception prediction model is a multilayer perceptron (MLP); the perception prediction model includes multiple hidden layers.

[0195] Accordingly, based on the attribute information of the target Mura defect and the perception amount prediction model, the step of determining the perception amount of the target Mura defect includes: inputting a feature matrix representing the attribute information of the target Mura defect into the perception amount prediction model, and sequentially processing the feature matrix output by the previous hidden layer through multiple hidden layers until the last hidden layer outputs the perception amount of the target Mura defect.

[0196] For example, see Fig.11 , Fig.11 A schematic diagram of determining a perception quantity based on a perception quantity prediction model provided in an embodiment of the present application.

[0197] The input layer Indicates the contrast of the target mura defect; Indicates the area of ​​the target Mura defect; represents the shape of the target Mura defect; ... represents other features of the target Mura defect. Represents the perception of the output layer. Each hidden layer processes the input features (such as X1, X2 and X3 in the figure) and outputs the corresponding features until the final output layer outputs The +1 of each hidden layer represents the bias matrix of the hidden layer.

[0198] Each hidden layer performs matrix multiplication on the feature matrix of the input hidden layer and the weight matrix of the hidden layer, and then performs matrix addition on the result of the matrix multiplication and the bias matrix of the hidden layer. Furthermore, the result of the matrix addition is nonlinearly transformed through the activation function of the hidden layer to obtain the feature matrix of the hidden layer output.

[0199] See also Fig.12 , Fig.12 Take the perception prediction model with 5 hidden layers and 1 output layer as an example. The number of nodes in the 5 hidden layers is 8, 32, 128, 32, and 8 respectively. The number of nodes in the output layer is 1. The number of nodes indicates the data dimension of the output of this layer. Fig.12 A rectangle in the figure represents a node.

[0200] The area, shape, contrast and position of the target Mura defect are represented as a 1×4 feature matrix input to the first hidden layer, and matrix multiplication is performed with the 4×8 weight matrix of the first hidden layer. The result of the matrix multiplication is then matrix added with the bias matrix of the first hidden layer. The result of the matrix addition is nonlinearly transformed through the activation function of the first hidden layer to obtain the 1×8 feature matrix output by the first hidden layer, that is, the nodes of the first hidden layer. The 1×8 feature matrix output by the first hidden layer is input to the second hidden layer, and matrix multiplication is performed with the 8×32 weight matrix of the second hidden layer. The result of the matrix multiplication is then matrix added with the bias matrix of the second hidden layer. The result of the matrix addition is nonlinearly transformed through the activation function of the second hidden layer to obtain the 1×32 feature matrix output by the second hidden layer, that is, the nodes of the second hidden layer. The 1×32 feature matrix output by the second hidden layer is input to the third hidden layer and matrix multiplied with the 32×128 weight matrix of the third hidden layer. The result of the matrix multiplication is then matrix added with the bias matrix of the third hidden layer. The result of the matrix addition is nonlinearly transformed through the activation function of the third hidden layer to obtain the 1×128 feature matrix output by the third hidden layer, that is, the nodes of the third hidden layer.

[0201] The 1×128 feature matrix output by the third hidden layer is input to the fourth hidden layer, and matrix multiplication is performed with the 128×32 weight matrix of the fourth hidden layer. The result of the matrix multiplication is then matrix added with the bias matrix of the fourth hidden layer. The result of the matrix addition is nonlinearly transformed through the activation function of the fourth hidden layer to obtain the 1×32 feature matrix output by the fourth hidden layer, that is, the nodes of the fourth hidden layer. The 1×32 feature matrix output by the fourth hidden layer is input to the fifth hidden layer, and matrix multiplication is performed with the 32×8 weight matrix of the fifth hidden layer. The result of the matrix multiplication is then matrix added with the bias matrix of the fifth hidden layer. The result of the matrix addition is nonlinearly transformed through the activation function of the fifth hidden layer to obtain the 1×8 feature matrix output by the fifth hidden layer, that is, the nodes of the fifth hidden layer. The 1×8 feature matrix output by the fifth hidden layer is input to the output layer and matrix multiplied with the 8×1 weight matrix of the output layer. The result of the matrix multiplication is then matrix added with the bias matrix of the output layer to obtain the 1×1 feature matrix output by the output layer, i.e., the nodes of the output layer, that is, the perceived amount of the target Mura defect.

[0202] In some embodiments, the training method of the perception prediction model includes the following steps:

[0203] A data set is constructed for training a perception quantity prediction model, and the data set includes multiple pairs of data. Each pair of data includes: attribute information of sample Mura defects in a sample display screen, and sample perception quantities of annotated sample Mura defects. The attribute information of the sample Mura defects is input into the perception quantity prediction model of the initial structure to obtain the predicted perception quantity of the sample Mura defects output by the perception quantity prediction model. Based on the sample perception quantity and the predicted perception quantity of the sample Mura defects, the function value of the second loss function is calculated, and the second loss function value represents the difference between the sample perception quantity and the predicted perception quantity. Based on the function value of the second loss function, the model parameters of the perception quantity prediction model are back-propagated and continuously iterated and updated until the preset convergence condition is reached to obtain a trained perception quantity prediction model.

[0204] As can be seen from the above, the technical solution provided in this embodiment, based on the area, shape, contrast and position of the target Mura defect as input, outputs the perception of the target Mura defect through the perception prediction model based on deep learning, which can improve the accuracy of the determined perception and further improve the accuracy of the quality inspection of the display screen. In addition, compared with the traditional method of quantifying the target Mura defect, the parameters of the perception prediction model based on deep learning are autonomously learned in the back propagation, without manual parameter adjustment, and can cover more scenes more fully. At the same time, as many features as possible can be selected for fitting according to actual needs, which is closer to the actual perception of the human eye. Compared with other neural networks (such as convolutional neural networks (CNN)), MLP can explicitly select features and reduce dependence on the amount of data. In addition, CNN will lose the position characteristics of the target Mura defect during the convolution process, and the perception of the target Mura defect is also related to the position. MLP can select the position of the target Mura defect as a feature to participate in the fitting of the perception, thereby improving the accuracy of the determined perception.

[0205] For step S805, in one implementation, if the perceived amount of the target Mura defect is determined based on an image to be detected, there is a perceived amount for each target Mura defect. Accordingly, the perceived amount of each target Mura defect is determined based on the image to be detected, and the quality inspection result of the display screen to be inspected is determined.

[0206] The electronic device determines the quality inspection result of the display screen to be inspected based on the perceived amount of each target Mura defect in the following manner.

[0207] Method 1,

[0208] The maximum value of the perception amount of multiple target Mura defects is determined as the target perception amount. When the target perception amount is greater than the preset threshold, it indicates that the user has a high degree of visual perception of the target Mura defect, and it is a defect that will be observed. It is determined that the target Mura defect observed by the user exists in the display screen to be tested, and the quality inspection result of the display screen to be tested is determined to be unqualified. When the target perception amount is not greater than the preset threshold, it indicates that the user has a low degree of visual perception of the target Mura defect, and it is a defect that will not be observed. It is determined that the target Mura defect observed by the user does not exist in the display screen to be tested, and the quality inspection result of the display screen to be tested is determined to be qualified.

[0209] For example, based on an image of the display screen to be tested, it is found that there are three Mura defects in the display screen to be tested, among which the perception amount of Mura defect 1 is 0.11, the perception amount of Mura defect 2 is 0.16, and the perception amount of Mura defect 3 is 0.21. The maximum value of the perception amounts of the three Mura defects is 0.21 (i.e., the target perception amount). When the preset threshold is 0.2, the target perception amount is greater than the preset threshold, and the quality inspection result of the display screen to be tested is determined to be unqualified; when the preset threshold is 0.3, the target perception amount is less than the preset threshold, and the quality inspection result of the display screen to be tested is determined to be qualified.

[0210] Method 2,

[0211] For each target Mura defect in the display screen to be tested, when the perceived amount of the target Mura defect is greater than the preset threshold, it indicates that the user has a high visual perception of the target Mura defect and it is a defect that will be observed, and the quality inspection result based on the target Mura defect is determined to be unqualified. When the perceived amount of the target Mura defect is not greater than the preset threshold, it indicates that the user has a low visual perception of the target Mura defect and it is a defect that will not be observed, and the quality inspection result based on the target Mura defect is determined to be qualified.

[0212] When there is an unqualified result among the multiple quality inspection results obtained based on the multiple target Mura defects, it indicates that at least one target Mura defect can be perceived by the user, and the quality inspection result of the display screen to be inspected is determined to be unqualified. When there is no unqualified result among the multiple quality inspection results obtained based on the multiple target Mura defects, it indicates that there is no target Mura defect that can be perceived by the user, and the quality inspection result of the display screen to be inspected is determined to be qualified.

[0213] For example, based on an image of the display screen to be tested, it is found that there are three Mura defects in the display screen to be tested, wherein the perception amount of Mura defect 1 is 0.11, the perception amount of Mura defect 2 is 0.16, and the perception amount of Mura defect 3 is 0.21.

[0214] When the preset threshold is 0.2, the quality inspection result obtained based on the perceived amount of Mura defect 1 is qualified, the quality inspection result obtained based on the perceived amount of Mura defect 2 is qualified, and the quality inspection result obtained based on the perceived amount of Mura defect 3 is unqualified. If there is an unqualified result among the multiple inspection results, it is determined that the quality inspection result of the display screen to be inspected is unqualified.

[0215] When the preset threshold is 0.3, the quality inspection result obtained based on the perceived amount of Mura defect 1 is qualified, the quality inspection result obtained based on the perceived amount of Mura defect 2 is qualified, and the quality inspection result obtained based on the perceived amount of Mura defect 3 is qualified. If there is no unqualified result among the multiple inspection results, it is determined that the quality inspection result of the display screen to be inspected is qualified.

[0216] In another implementation, if the perceived amount of the target Mura defect is determined based on multiple images to be detected, a perceived amount of each target Mura defect is determined based on each image to be detected. Accordingly, the quality inspection result of the display screen to be inspected is determined based on multiple perceived amounts of each target Mura defect determined based on each image to be detected.

[0217] The electronic device determines the quality inspection result of the display screen to be inspected based on the perceived amount of each target Mura defect in the following manner.

[0218] Method 1,

[0219] For each image to be tested, the maximum value of the perceived values ​​of multiple target Mura defects determined based on the image to be tested is determined as the target perceived value determined based on the image to be tested. The maximum value of the target perceived values ​​determined based on multiple images to be tested is determined as the final target perceived value. When the final target perceived value is greater than a preset threshold, the quality inspection result of the display screen to be tested is determined to be unqualified; when the final target perceived value is not greater than the preset threshold, the quality inspection result of the display screen to be tested is determined to be qualified.

[0220] For example, there are two images to be tested. Based on the first image to be tested, it is found that there are three Mura defects in the display screen to be tested, among which the perceived value of Mura defect 1 is 0.11, the perceived value of Mura defect 2 is 0.16, and the perceived value of Mura defect 3 is 0.21. The maximum value of the perceived values ​​of the three Mura defects is 0.21 (i.e., the target perceived value obtained based on the first image to be tested).

[0221] Based on the second image to be tested, there are three Mura defects in the display screen to be tested, among which the perception amount of Mura defect 1 is 0.15, the perception amount of Mura defect 2 is 0.17, and the perception amount of Mura defect 3 is 0.25. The maximum value of the perception amounts of the three Mura defects is 0.25 (that is, the target perception amount obtained based on the second image to be tested).

[0222] The maximum value of the target perception amount obtained based on the two images to be detected is 0.25, so the final target perception amount is 0.25.

[0223] When the preset threshold is 0.2, the final target perception amount is greater than the preset threshold, and the quality inspection result of the display screen to be inspected is determined to be unqualified; when the preset threshold is 0.3, the final target perception amount is less than the preset threshold, and the quality inspection result of the display screen to be inspected is determined to be qualified.

[0224] Method 2,

[0225] For each target Mura defect, when the perceived amount of the target Mura defect is greater than a preset threshold, the quality inspection result based on the target Mura defect is determined to be unqualified. When the perceived amount of the target Mura defect is not greater than the preset threshold, the quality inspection result based on the target Mura defect is determined to be qualified.

[0226] When there is an unqualified one among the multiple quality inspection results of the multiple target Mura defects obtained based on the multiple images to be inspected, the quality inspection result of the display screen to be inspected is determined to be unqualified. When there is no unqualified one among the multiple quality inspection results of the multiple target Mura defects obtained based on the multiple images to be inspected, the quality inspection result of the display screen to be inspected is determined to be qualified.

[0227] For example, there are two images to be tested. Based on the first image to be tested, it is found that there are three Mura defects in the display screen to be tested, among which the perceived value of Mura defect 1 is 0.11, the perceived value of Mura defect 2 is 0.16, and the perceived value of Mura defect 3 is 0.21. The maximum value of the perceived values ​​of the three Mura defects is 0.21 (i.e., the target perceived value obtained based on the first image to be tested).

[0228] Based on the second image to be tested, there are three Mura defects in the display screen to be tested, among which the perception amount of Mura defect 1 is 0.15, the perception amount of Mura defect 2 is 0.17, and the perception amount of Mura defect 3 is 0.25. The maximum value of the perception amounts of the three Mura defects is 0.25 (that is, the target perception amount obtained based on the second image to be tested).

[0229] When the preset threshold is 0.2, based on the first image to be detected, the quality inspection result corresponding to the Mura defect 1 is qualified, based on the first image to be detected, the quality inspection result corresponding to the Mura defect 2 is qualified, and based on the first image to be detected, the quality inspection result corresponding to the Mura defect 3 is unqualified.

[0230] Based on the first image to be detected, the quality inspection result corresponding to Mura defect 1 is qualified, based on the first image to be detected, the quality inspection result corresponding to Mura defect 2 is qualified, and based on the first image to be detected, the quality inspection result corresponding to Mura defect 3 is unqualified.

[0231] If there is an unqualified result among the above multiple test results, it is determined that the quality test result of the display screen to be tested is unqualified.

[0232] When the preset threshold is 0.3, based on the second image to be detected, the quality inspection result corresponding to Mura defect 1 is qualified, based on the second image to be detected, the quality inspection result corresponding to Mura defect 2 is qualified, and based on the second image to be detected, the quality inspection result corresponding to Mura defect 3 is qualified.

[0233] Based on the second image to be inspected, the quality inspection result corresponding to Mura defect 1 is qualified, based on the second image to be inspected, the quality inspection result corresponding to Mura defect 2 is qualified, and based on the second image to be inspected, the quality inspection result corresponding to Mura defect 3 is qualified.

[0234] If there is no unqualified result among the above multiple test results, it is determined that the quality test result of the display screen to be tested is qualified.

[0235] The preset threshold value may be obtained by a technician based on testing a sample display screen. For example, the preset threshold value may be 0.2, or the preset threshold value may be 0.3, which is not specifically limited in the embodiments of the present application.

[0236] As can be seen from the above, the technical solution provided in this embodiment determines that the quality inspection result of the display screen to be inspected is unqualified when at least one target Mura defect can be perceived by the user, thereby preventing the user from receiving unqualified products and improving the user experience.

[0237] See also Fig.13 , Fig.13 A flow chart of a method for quality inspection of a display screen provided in an embodiment of the present application is described by taking the display screen to be inspected as a mobile phone display screen as an example.

[0238] Get the initial image of the display screen to be detected, that is Fig.13 The first image on the left in the figure. The initial image includes the image area where the display screen to be detected is located and the background area. By extracting ROI, the image area where the display screen to be detected is extracted from the initial image to obtain the image to be detected, that is, Fig.13 The second image from the left.

[0239] By extracting defects from the image to be inspected, we can obtain the defect image areas of the three target Mura defects in the display screen to be inspected, namely: Fig.13 The 3 white areas in the 3rd image from the left.

[0240] Then, the defect image area of ​​the target Mura defect is quantified to obtain the perceived amount of the target Mura defect, and then the quality inspection result of the display screen to be inspected is determined. Specifically, the perceived amount of defect 1 is 0.14; the perceived amount of defect 2 is 0.33; and the perceived amount of defect 3 is 0.17. If the perceived amount of defect 1 is less than 0.2, the quality inspection result of the display screen to be inspected based on defect 1 is determined to be qualified (i.e., good product); if the perceived amount of defect 2 is greater than 0.2, the quality inspection result of the display screen to be inspected based on defect 2 is determined to be unqualified (i.e., defective product); if the perceived amount of defect 3 is less than 0.2, the quality inspection result of the display screen to be inspected based on defect 3 is determined to be qualified (i.e., good product). If there is an unqualified one among the three quality inspection results obtained based on the three target Mura defects, the quality inspection result of the display screen to be inspected is determined to be unqualified.

[0241] As can be seen from the above, the technical solution provided by this embodiment adopts a defect extraction model based on deep learning to preliminarily divide the defect image area, and obtain information such as the area, shape, contrast and position of the Mura defect to preliminarily extract the defect. Further, based on the perception quantity prediction model based on deep learning, the features that affect the Mura defect in the entire feature space are fitted with the perception quantity, so that any given Mura defect has a unique perception quantity corresponding to it, thereby quantifying the Mura defect, determining the perception quantity of Mura, and then determining the quality inspection result of the display screen, which can improve the user experience.

[0242] See also Fig.14 , Fig.14 The structure of a display screen quality inspection system provided in an embodiment of the present application includes: an electronic device 1401 and a camera 1402;

[0243] The electronic device 1401 is used to light up the display screen to be detected and control the display screen to be detected to display a preset picture;

[0244] The camera 1402 is used to capture an image of the display screen to be detected when it displays a preset picture;

[0245] The electronic device 1401 is further used to obtain an image to be detected based on an image of the display screen to be detected captured by the camera 1402 when the display screen to be detected displays a preset screen; perform defect extraction on the image to be detected to obtain a defect image area of ​​a target Mura defect in the display screen to be detected in the image to be detected; calculate attribute information of the target Mura defect based on the defect image area of ​​the target Mura defect; calculate a perceived amount of the target Mura defect based on the attribute information of the target Mura defect; wherein the perceived amount indicates a user's perception degree of the target Mura defect; and determine a quality inspection result of the display screen to be detected based on the perceived amount of the target Mura defect.

[0246] See also Fig.15 , Fig.15 The application provided in the embodiment of the present application is Fig.14 Flow chart of a method for detecting quality of a display screen of the system shown.

[0247] The electronic device includes a motion control module, a screen control module, a camera control module, a quality detection module and an information uploading module.

[0248] The test device with the display screen to be tested is installed on the fixture. The motion control module can control the opening and closing of the clamping jaws of the fixture to clamp the test device. The motion control module can also control the fixture to move and flip, and control the camera to move, so that the display screen to be tested is within the field of view of the camera to ensure that the camera can capture the image of the display screen to be tested.

[0249] The screen control module can control the test device to light up the display screen to be tested, control the display screen to be tested to switch the displayed preset screen, and control the display screen to be tested to adjust the brightness. After the camera captures the image of the display screen to be tested, the test device is controlled to turn off the display screen to be tested.

[0250] The camera control module can control the camera to adjust parameters such as exposure during shooting, and control the camera to shoot the display screen to be detected to obtain an image of the display screen to be detected.

[0251] The quality inspection module can perform quality inspection on the display screen to be inspected based on the image of the display screen to be inspected taken by the camera according to the quality inspection method provided in the embodiment of the present application, and obtain the quality inspection result of the display screen to be inspected.

[0252] The information upload module can upload the quality inspection results of the display screen to be inspected to the designated system.

[0253] In a specific implementation, the present application also provides an electronic device, which includes one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the electronic device to perform some or all of the steps in the above method embodiments.

[0254] The present application also provides a computer-readable storage medium, including a computer program, which, when executed on an electronic device, enables the electronic device to perform some or all of the steps in the above method embodiment. The above storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0255] In a specific implementation, an embodiment of the present application further provides a computer program product, which includes executable instructions. When the executable instructions are executed on an electronic device, the electronic device executes part or all of the steps in the above method embodiment.

[0256] like Fig.16 As shown, the present application also provides a chip system, which is applied to electronic devices. The chip system includes one or more processors 1601. The processor 1601 is used to call computer instructions so that the electronic device inputs the data to be processed into the chip system. The chip system processes the data based on the compilation method of the application provided in the embodiment of the present application and outputs the processing result.

[0257] In a possible implementation, the chip system also includes input and output interfaces for inputting and outputting data.

[0258] The various embodiments of the mechanism disclosed in the present application can be implemented in hardware, software, firmware or a combination of these implementation methods. The embodiments of the present application can be implemented as a computer program or program code executed on a programmable system, which includes at least one processor, a storage system (including volatile and non-volatile memory and / or storage elements), at least one input device and at least one output device.

[0259] Program code may be applied to input instructions to perform the functions described herein and to generate output information. The output information may be applied to one or more output devices in a known manner. For purposes of this application, a processing system includes any system having a processor such as, for example, a digital signal processor (DSP), a microcontroller, an application specific integrated circuit (ASIC), or a microprocessor.

[0260] Program code can be implemented with high-level programming language or object-oriented programming language to communicate with the processing system. When necessary, program code can also be implemented with assembly language or machine language. In fact, the mechanism described in this application is not limited to the scope of any specific programming language. In either case, the language can be a compiled language or an interpreted language.

[0261] In some cases, the disclosed embodiments may be implemented in hardware, firmware, software, or any combination thereof. The disclosed embodiments may also be implemented as instructions carried or stored on one or more temporary or non-temporary machine-readable (e.g., computer-readable) storage media, which may be read and executed by one or more processors. For example, the instructions may be distributed over a network or through other computer-readable media. Therefore, a machine-readable medium may include any mechanism for storing or transmitting information in a machine (e.g., computer) readable form, including but not limited to floppy disks, optical disks, optical disks, compact disc read-only memories (Compact Disc Read Only Memory, CD-ROMs), magneto-optical disks, read-only memories, random access memories, erasable programmable read-only memories (Erasable Programmable Read Only Memory, EPROM), electrically erasable programmable read-only memories (Electrically Erasable Programmable Read Only Memory, EEPROM), magnetic or optical cards, flash memory, or a tangible machine-readable memory for transmitting information (e.g., carrier waves, infrared signals, digital signals, etc.) using the Internet in electrical, optical, acoustic, or other forms of propagation signals. Accordingly, machine-readable media include any type of machine-readable media suitable for storing or transmitting electronic instructions or information in a form readable by a machine (eg, a computer).

[0262] In the accompanying drawings, some structural or method features may be shown in a specific arrangement and / or order. However, it should be understood that such a specific arrangement and / or order may not be required. Instead, in some embodiments, these features may be arranged in a manner and / or order different from that shown in the accompanying drawings of the specification. In addition, the inclusion of structural or method features in a particular figure does not mean that such features are required in all embodiments, and in some embodiments, these features may not be included or may be combined with other features.

[0263] It should be noted that the units / modules mentioned in the various device embodiments of the present application are all logical units / modules. Physically, a logical unit / module can be a physical unit / module, or a part of a physical unit / module, or can be implemented as a combination of multiple physical units / modules. The physical implementation method of these logical units / modules themselves is not the most important. The combination of functions implemented by these logical units / modules is the key to solving the technical problems proposed by the present application. In addition, in order to highlight the innovative part of the present application, the above-mentioned device embodiments of the present application do not introduce units / modules that are not closely related to solving the technical problems proposed by the present application, which does not mean that there are no other units / modules in the above-mentioned device embodiments.

[0264] It should be noted that in the examples and description of this patent, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including one" do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0265] Although the present application has been illustrated and described with reference to certain preferred embodiments thereof, it will be apparent to those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present application.

Claims

1. A method for detecting the quality of a display screen, characterized in that: The method comprises: Acquire an image of the display screen to be detected that is captured when the display screen to be detected displays a preset picture, as the image to be detected; Extracting defects from the image to be inspected to obtain a defect image region of a target Mura defect in the display screen to be inspected in the image to be inspected; Calculating attribute information of the target Mura defect based on the defect image area of ​​the target Mura defect; Calculating a perceived amount of the target Mura defect based on the attribute information of the target Mura defect; wherein the perceived amount represents a user's degree of perception of the target Mura defect; Determining a quality inspection result of the display screen to be inspected based on the perceived amount of the target Mura defect; The calculating the perceived amount of the target Mura defect based on the attribute information of the target Mura defect includes: Input the attribute information of the target Mura defect into a pre-trained perception quantity prediction model to obtain the perception quantity of the target Mura defect; wherein the attribute information of the target Mura defect includes at least one of the following: the area, shape, contrast and position of the target Mura defect; the area of ​​the target Mura defect is: the number of pixels in the defect image area, or the area of ​​the minimum circumscribed rectangle of the defect image area; the shape of the target Mura defect is represented by the Hu moment of the defect image area; the Hu moment is the Hu1 moment of the defect image area; the Hu1 moment reflects the overall distribution characteristics of the defect image area; The perception quantity prediction model is a multi-layer perceptron MLP; the perception quantity prediction model includes multiple hidden layers; the perception quantity prediction model is trained based on the attribute information of the sample Mura defect in the sample display screen and the sample perception quantity of the sample Mura defect; The step of inputting the attribute information of the target Mura defect into a pre-trained perception quantity prediction model to obtain the perception quantity of the target Mura defect includes: Inputting a feature matrix representing the attribute information of the target Mura defect into the perception amount prediction model, and sequentially processing the feature matrix output by the previous hidden layer through the multiple hidden layers until the last hidden layer outputs the perception amount of the target Mura defect; For each hidden layer, the hidden layer processes the feature matrix input to the hidden layer as follows: perform matrix multiplication on the feature matrix input to the hidden layer and the weight matrix of the hidden layer, perform matrix addition on the result of the matrix multiplication and the bias matrix of the hidden layer, perform nonlinear transformation on the result of the matrix addition through the activation function of the hidden layer, and obtain the feature matrix output by the hidden layer.

2. The method according to claim 1, characterized in that The step of extracting defects from the image to be detected to obtain a defect image region of a target Mura defect in the display screen to be detected in the image to be detected includes: The image to be inspected is input into a pre-trained defect extraction model, and an image region in the image to be inspected where a target Mura defect in the display screen to be inspected is located output by the defect extraction model is obtained as a defect image region.

3. The method according to claim 2, characterized in that The defect extraction model includes a convolutional network and a deconvolutional network; the convolutional network includes a plurality of convolutional layers; the deconvolutional network includes a plurality of deconvolutional layers; The step of inputting the image to be detected into a pre-trained defect extraction model to obtain an image region in the image to be detected where a target Mura defect in the display screen to be detected output by the defect extraction model is located as a defect image region includes: Processing the image to be detected by a convolutional layer in the convolutional network to obtain image features of the image to be detected; The image features of the image to be detected are processed by the deconvolution layer in the deconvolution network to obtain the target Mura defect in the display screen to be detected in the image area where the image to be detected is located, as the defect image area.

4. The method according to claim 3, characterized in that The training method of the defect extraction model includes: Acquire a sample image and a sample defect area of ​​a sample Mura defect in the sample image that is marked; Inputting the sample image into a defect extraction model of an initial structure to obtain a predicted defect area of ​​a sample Mura defect in the sample image output by the defect extraction model; Calculating a function value of a first loss function based on the sample defect area and the predicted defect area; Based on the function value of the first loss function, the model parameters of the defect extraction model are adjusted until a preset convergence condition is reached to obtain a trained defect extraction model.

5. The method according to claim 1, characterized in that The training method of the perception prediction model includes: Acquire attribute information of sample Mura defects in a sample display screen, and annotated sample perception amounts of the sample Mura defects; Inputting the attribute information of the sample Mura defect into the perception quantity prediction model of the initial structure to obtain the predicted perception quantity of the sample Mura defect output by the perception quantity prediction model; Calculating a function value of a second loss function based on the sample perception amount of the sample Mura defect and the predicted perception amount; Based on the function value of the second loss function, the model parameters of the perception quantity prediction model are adjusted until a preset convergence condition is reached to obtain a trained perception quantity prediction model.

6. The method according to any one of claims 1 to 5, characterized in that: The determining, based on the perceived amount of the target Mura defect, a quality inspection result of the display screen to be inspected includes: Determine the maximum value of the perception amounts of multiple target Mura defects as the target perception amount; When the target perception amount is greater than a preset threshold, determining that the quality inspection result of the display screen to be inspected is unqualified; When the target perception amount is not greater than a preset threshold, it is determined that the quality inspection result of the display screen to be inspected is qualified.

7. The method according to any one of claims 1 to 5, characterized in that: The determining the quality inspection result of the display screen to be inspected based on the perceived amount of the target Mura defect includes: For each target Mura defect in the display screen to be inspected, when the perceived amount of the target Mura defect is greater than a preset threshold, determining that a quality inspection result obtained based on the target Mura defect is unqualified; When the perceived amount of the target Mura defect is not greater than a preset threshold, determining that the quality inspection result obtained based on the target Mura defect is qualified; When there is an unqualified result among the quality inspection results, determining that the quality inspection result of the display screen to be inspected is unqualified; When there is no unqualified result in each quality inspection result, it is determined that the quality inspection result of the display screen to be inspected is qualified.

8. The method according to any one of claims 1 to 5, characterized in that: The step of obtaining an image of the display screen to be detected, which is captured when the display screen to be detected displays a preset picture, as the image to be detected, includes: Using a camera to capture an image of the display screen to be detected when it displays a preset screen, and obtaining an image of the display screen to be detected with a specified grayscale as an initial image; The image area where the display screen to be detected is located in the initial image is extracted to obtain the image to be detected.

9. The method according to any one of claims 1 to 5, characterized in that: The step of obtaining an image of the display screen to be detected, which is captured when the display screen to be detected displays a preset picture, as the image to be detected, includes: Using a camera to respectively capture images of the display screen to be detected when displaying different preset images, to obtain images of the display screen to be detected with different grayscales as initial images; Extracting the image area where the display screen to be detected is located in each initial image respectively to obtain a plurality of images to be detected; The determining the quality inspection result of the display screen to be inspected based on the perceived amount of the target Mura defect includes: The quality inspection result of the display screen to be inspected is determined based on the perceived amount of the target Mura defect obtained from each image to be inspected.

10. A display screen quality inspection system, characterized in that: The system includes: an electronic device and a camera; The electronic device is used to light up the display screen to be detected and control the display screen to be detected to display a preset picture; The camera is used to capture an image of the display screen to be detected when it displays a preset picture; The electronic device is further used to obtain an image to be detected based on an image captured by the camera when the display screen to be detected displays a preset screen; perform defect extraction on the image to be detected to obtain a defect image area of ​​a target Mura defect in the display screen to be detected in the image to be detected; calculate attribute information of the target Mura defect based on the defect image area of ​​the target Mura defect; calculate a perceived amount of the target Mura defect based on the attribute information of the target Mura defect; wherein the perceived amount indicates a user's perception of the target Mura defect; and determine a quality inspection result of the display screen to be detected based on the perceived amount of the target Mura defect; The electronic device is specifically used to input the attribute information of the target Mura defect into a pre-trained perception quantity prediction model to obtain the perception quantity of the target Mura defect; wherein the attribute information of the target Mura defect includes at least one of the following: the area, shape, contrast and position of the target Mura defect; the area of ​​the target Mura defect is: the number of pixels in the defect image area, or the area of ​​the minimum circumscribed rectangle of the defect image area; the shape of the target Mura defect is represented by the Hu moment of the defect image area; the Hu moment is the Hu1 moment of the defect image area; the Hu1 moment reflects the overall distribution characteristics of the defect image area; The perception quantity prediction model is a multi-layer perceptron MLP; the perception quantity prediction model includes multiple hidden layers; the perception quantity prediction model is trained based on the attribute information of the sample Mura defect in the sample display screen and the sample perception quantity of the sample Mura defect; The electronic device is specifically used to input a feature matrix representing the attribute information of the target Mura defect into the perception amount prediction model, and sequentially process the feature matrix output by the previous hidden layer through the multiple hidden layers until the last hidden layer outputs the perception amount of the target Mura defect; For each hidden layer, the hidden layer processes the feature matrix input to the hidden layer as follows: perform matrix multiplication on the feature matrix input to the hidden layer and the weight matrix of the hidden layer, perform matrix addition on the result of the matrix multiplication and the bias matrix of the hidden layer, perform nonlinear transformation on the result of the matrix addition through the activation function of the hidden layer, and obtain the feature matrix output by the hidden layer.

11. An electronic device, characterized in that: include: one or more processors and memory; The memory is coupled to the one or more processors, and the memory is used to store computer program codes, wherein the computer program codes include computer instructions, and the one or more processors call the computer instructions to enable the electronic device to execute the method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: The invention comprises a computer program, which, when being executed on an electronic device, enables the electronic device to execute the method according to any one of claims 1 to 9.

13. A computer program product, characterized in that The computer program product comprises executable instructions, and when the executable instructions are executed on an electronic device, the electronic device is caused to execute the method according to any one of claims 1 to 9.

14. A chip system, characterized in that: The chip system is applied to an electronic device, and the chip system includes one or more processors, and the processor is used to call computer instructions so that the electronic device inputs data into the chip system, and executes the method described in any one of claims 1-9 to process the data and then output the processing result.

Images