Method and apparatus for determining accuracy of vision system, and computer readable storage medium

Abstract

A method and apparatus for determining the accuracy of a vision system, and a computer readable storage medium. The accuracy determination method comprises: acquiring a superimposed image picture and a grayscale picture which are collected by a vision system (104) (S202), the superimposed image picture being formed by superimposing a target customized grayscale signal on the grayscale picture; determining a first grayscale signal corresponding to the superimposed image picture and a second grayscale signal corresponding to the grayscale picture (S204); acquiring a difference signal between the first grayscale signal and the second grayscale signal (S206); and determining the accuracy of the vision system (104) on the basis of the similarity between the difference signal and the target customized grayscale signal (S208).

Description

Method, device, and computer-readable storage medium for determining accuracy of a visual system

[0001] Related applications

[0002] This application claims priority to Chinese patent application number 202310944160.0, filed on July 31, 2023, entitled “Method, device, and computer-readable storage medium for determining accuracy of a visual system,” the entire text of which is hereby incorporated by reference. Technical Field

[0003] The present application relates to the field of visual imaging detection technology, and in particular to a method, device, and computer-readable storage medium for determining the accuracy of a visual system. Background Art

[0004] Display screens are prone to uneven brightness due to improper operation during the production process or use. In the field of visual inspection, a machine vision system composed of machine vision products such as cameras, video cameras, charge coupled devices (CCDs), or complementary metal oxide semiconductors (CMOSs) can capture display screen images. The display images are then sent to an image processing system for defect detection, thereby obtaining detection results for display screen brightness defects or detection results for display screen brightness defect compensation.

[0005] Therefore, in the field of visual inspection, the accuracy of inspection results is often closely related to the data acquisition accuracy of the machine vision system. However, the data acquisition accuracy of machine vision systems is easily affected by factors such as camera noise, lens distortion, dispersion, and differences in resolution, making it difficult to accurately evaluate.

[0006] Summary of the Invention

[0007] According to various embodiments of the present application, a method, apparatus, computer device, computer-readable storage medium, and computer program product for determining accuracy are provided.

[0008] In a first aspect, the present application provides a method for determining the accuracy of a visual system. The method comprises:

[0009] Acquire an overlay image and a grayscale image captured by a visual system, wherein the overlay image is formed by superimposing a target customized grayscale signal on the grayscale image;

[0010] Determining a first grayscale signal corresponding to the superimposed image frame and a second grayscale signal corresponding to the grayscale frame;

[0011] acquiring a difference signal between the first grayscale signal and the second grayscale signal; and

[0012] The accuracy of the visual system is determined according to the similarity between the difference signal and the target customized grayscale signal.

[0013] In one embodiment, determining the accuracy of the visual system based on the similarity between the difference signal and the target customized grayscale signal includes:

[0014] constructing a first multidimensional vector corresponding to the difference signal;

[0015] constructing a second multidimensional vector corresponding to the target customized grayscale signal; and

[0016] The similarity between the difference signal and the target customized grayscale signal is determined according to the first multidimensional vector and the second multidimensional vector, and the similarity is used as the accuracy.

[0017] In one embodiment, the superimposed image and the grayscale image are luminance spatial data acquired by the visual system, and determining a first grayscale signal corresponding to the superimposed image and a second grayscale signal corresponding to the grayscale image includes:

[0018] Obtaining the conversion coefficient from brightness space to grayscale space; and

[0019] The first relative brightness of the superimposed image picture and the second relative brightness of the grayscale picture are converted according to the conversion coefficient to generate the first grayscale signal and the second grayscale signal.

[0020] In one embodiment, obtaining the conversion coefficient from the luminance space to the grayscale space includes:

[0021] Acquire image frames at multiple grayscale levels captured by the visual system, and determine the imaging brightness value of the image frame at each grayscale level;

[0022] Determining a theoretical brightness value corresponding to each grayscale level according to the imaging brightness value and exposure time of the visual system at each grayscale level; and

[0023] According to the theoretical brightness value and the preset grayscale value at each grayscale level, a conversion coefficient at each grayscale level is determined.

[0024] In one embodiment, determining the conversion coefficient at each grayscale level according to the theoretical brightness value and the preset grayscale value at each grayscale level includes:

[0025] The conversion coefficient at each grayscale level is obtained according to the following calculation formula:

[0026] Wherein, i represents the number of grayscale levels corresponding to the image captured by the visual system,

[0027] k represents the order of the polynomial,

[0028] GLi represents the grayscale value at grayscale level i,

[0029] represents the kth power of the grayscale value at grayscale level i,

[0030] GVi represents the theoretical brightness value at grayscale level i, a1, a2, a3, ..., a k Represents the polynomial fitting coefficient; γ(x)=a1+a2x+a3x 2 +…·a k x k

[0031] Wherein, x represents the grayscale level, γ(x) represents the conversion coefficient at the grayscale level x,

[0032] x k is the k-th power of the grayscale value at grayscale level x before fitting.

[0033] In one embodiment, determining the conversion coefficient at each grayscale level according to the theoretical brightness value and the preset grayscale value at each grayscale level includes:

[0034] Using the imaging brightness value of the visual system at a preset grayscale level, normalizing the theoretical brightness value at each grayscale level to obtain a normalized theoretical brightness value;

[0035] Normalizing the grayscale value at each grayscale level using the grayscale threshold corresponding to the preset grayscale level to obtain a normalized grayscale value; and

[0036] The conversion coefficient at each grayscale level is determined according to the normalized theoretical brightness value and the normalized grayscale value at each grayscale level.

[0037] In one embodiment, the method further comprises:

[0038] Acquire a plurality of continuous grayscale images captured by the visual system at the same grayscale level; and

[0039] The second relative brightness is determined according to the relative brightness data of each of the plurality of consecutive grayscale images.

[0040] In one embodiment, the target customized grayscale signal is generated according to display screen defect characteristics.

[0041] In one embodiment, the display screen defect characteristics include one or more combinations of high-frequency information, low-frequency information, data of different spatial frequencies, and random noise.

[0042] In a second aspect, the present application further provides a device for determining the accuracy of a visual system. The device comprises:

[0043] An image acquisition module is used to acquire an overlay image and a grayscale image acquired by the visual system, wherein the overlay image is formed by superimposing a target customized grayscale signal on the grayscale image;

[0044] a signal determination module, configured to determine a first grayscale signal corresponding to the superimposed image frame and a second grayscale signal corresponding to the grayscale frame;

[0045] a signal extraction module, configured to obtain a difference signal between the first grayscale signal and the second grayscale signal; and

[0046] The accuracy determination module is configured to determine the accuracy of the visual system according to the similarity between the difference signal and the target customized grayscale signal.

[0047] In one embodiment, the accuracy determination module includes:

[0048] a vector construction unit, configured to construct a first multidimensional vector corresponding to the difference signal;

[0049] constructing a second multidimensional vector corresponding to the target customized grayscale signal; and

[0050] A similarity determination unit is configured to determine a similarity between the difference signal and the target customized grayscale signal according to the first multidimensional vector and the second multidimensional vector, and use the similarity as the accuracy.

[0051] In one embodiment, the superimposed image and the grayscale image are luminance spatial data acquired by the visual system.

[0052] The signal determination module is further configured to:

[0053] Obtaining the conversion coefficient from brightness space to grayscale space; and

[0054] The first relative brightness of the superimposed image picture and the second relative brightness of the grayscale picture are converted according to the conversion coefficient to generate the first grayscale signal and the second grayscale signal.

[0055] In one embodiment, the signal determination module is further configured to:

[0056] Acquire image frames at multiple grayscale levels captured by the visual system, and determine the imaging brightness value of the image frame at each grayscale level;

[0057] Determining a theoretical brightness value corresponding to each grayscale level according to the imaging brightness value and exposure time of the visual system at each grayscale level; and

[0058] According to the theoretical brightness value and the preset grayscale value at each grayscale level, a conversion coefficient at each grayscale level is determined.

[0059] In one embodiment, the signal determination module is further configured to:

[0060] The conversion coefficient at each grayscale level is obtained according to the following calculation formula:

[0061] Wherein, i represents the number of grayscale levels corresponding to the image captured by the visual system,

[0062] k represents the order of the polynomial,

[0063] GLi represents the grayscale value at grayscale level i,

[0064] represents the kth power of the grayscale value at grayscale level i,

[0065] GVi represents the theoretical brightness value at grayscale level i, a1, a2, a3, ..., a k Represents the polynomial fitting coefficient; γ(x)=a1+a2x+a3x 2 +…·a k x k

[0066] Wherein, x represents the grayscale level, γ(x) represents the conversion coefficient at the grayscale level x,

[0067] x k is the k-th power of the grayscale value at grayscale level x before fitting.

[0068] In one embodiment, the signal determination module includes:

[0069] Normalization subunit, used for:

[0070] Using the imaging brightness value of the visual system at a preset grayscale level, normalizing the theoretical brightness value at each grayscale level to obtain a normalized theoretical brightness value;

[0071] Normalizing the grayscale value at each grayscale level using the grayscale threshold corresponding to the preset grayscale level to obtain a normalized grayscale value; and

[0072] The conversion coefficient at each grayscale level is determined according to the normalized theoretical brightness value and the normalized grayscale value at each grayscale level.

[0073] In one embodiment, the apparatus further comprises:

[0074] Brightness determination module, used for:

[0075] Acquire a plurality of continuous grayscale images captured by the visual system at the same grayscale level; and

[0076] The second relative brightness is determined according to the relative brightness data of each of the plurality of consecutive grayscale images.

[0077] In one embodiment, the target customized grayscale signal is generated according to display screen defect characteristics.

[0078] In one embodiment, the display screen defect characteristics include one or more combinations of high-frequency information, low-frequency information, data of different spatial frequencies, and random noise.

[0079] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method for determining the accuracy of a visual system as described in any one of the embodiments of the first aspect.

[0080] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for determining the accuracy of a visual system as described in any one of the embodiments of the first aspect.

[0081] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the method for determining the accuracy of a visual system as described in any one of the embodiments of the first aspect.

[0082] The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below, and other features, objects, and advantages of the application will be apparent from the description, the drawings, and the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the conventional technology, the following briefly introduces the drawings required for use in the embodiments or the conventional technology descriptions. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the disclosed drawings without any creative work.

[0084] FIG1 is a diagram illustrating an application environment of a method for determining the accuracy of a visual system according to an embodiment;

[0085] FIG2 is a schematic flow chart of a method for determining the accuracy of a visual system according to one embodiment;

[0086] FIG3 is a schematic flow chart of an accuracy determination step in one embodiment;

[0087] FIG4 is a schematic flow chart of a conversion coefficient determination step in one embodiment;

[0088] FIG5 is a schematic flow chart of a conversion coefficient normalization step in one embodiment;

[0089] FIG6 is a schematic diagram of a target customized grayscale signal in one embodiment;

[0090] FIG7 is a flow chart of a method for determining the accuracy of a visual system according to another embodiment;

[0091] FIG8 is a diagram illustrating an application environment of a method for determining the accuracy of a visual system according to another embodiment;

[0092] FIG9 is a block diagram of a device for determining the accuracy of a visual system according to one embodiment;

[0093] FIG10 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0094] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0095] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0096] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0097] The method for determining the accuracy of a visual system provided in the embodiments of the present application can be applied in the application environment shown in FIG1 . Display screen 102 is located within the image acquisition area of ​​visual system 104 . Visual system 104 and computer device 106 can exchange data and communicate with each other via a bus, a local area network, or Bluetooth.

[0098] The vision system 104 may include but is not limited to machine vision products such as cameras, camera heads, charge coupled devices (CCDs), or complementary metal oxide semiconductors (CMOSs).

[0099] Computer device 106 can be a terminal, a server, or a system consisting of a terminal and a server. Terminals can include, but are not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart TVs, smart car devices, etc. Portable wearable devices can include smart watches, smart bracelets, head-mounted devices, etc. The server can be implemented as a standalone server or a server cluster consisting of multiple servers. Optionally, in some embodiments, computer device 106 can also be integrated into visual system 104.

[0100] Specifically, the computer device 106 can obtain the superimposed image and grayscale image captured by the visual system 104 for the display screen 102. The superimposed image is an image formed by superimposing an additional input target customized grayscale signal on the pure grayscale signal displayed on the display screen 102. The grayscale image in this embodiment is an image directly captured by the visual system 104 for the pure grayscale signal.

[0101] The computer device 106 may be pre-programmed with conversion logic for converting signals from the luminance domain to the grayscale domain. When implementing this conversion logic, the computer device 106 can utilize the relative luminance data of the superimposed image and the relative luminance data of the grayscale image to determine a first grayscale signal corresponding to the superimposed image (i.e., a grayscale signal restored by the computer device 106 from the relative luminance data of the superimposed image) and a second grayscale signal corresponding to the grayscale image (i.e., a grayscale signal restored by the computer device 106 from the relative luminance data of the grayscale image). A difference signal between the first grayscale signal and the second grayscale signal is obtained, and the accuracy of the image captured by the visual system 104 is determined based on the similarity between the difference signal and the target customized grayscale signal.

[0102] In this embodiment, by adopting the principle of controlling variables (taking the target customized grayscale signal as the variable), the superimposed image screen and the grayscale screen are collected respectively, and the relative brightness data of the superimposed image screen and the grayscale screen are restored in grayscale. The difference signal between the multiple grayscale signals obtained after restoration is used to simulate the target customized grayscale signal, so that the accuracy of the visual system can be determined based on the similarity between the difference signal and the target customized grayscale signal.

[0103] In one embodiment, as shown in FIG2 , a method for determining the accuracy of a visual system is provided. The method is described by taking the computer device 106 in FIG1 as an example, and includes the following steps:

[0104] Step S202: Acquire the superimposed image and grayscale image captured by the visual system.

[0105] The superimposed image can be formed by superimposing a target customized grayscale signal on a grayscale image. The grayscale image can represent the basic signal used by the display screen for display testing, also known as a base grayscale signal or a basic grayscale signal. In this embodiment, a pure grayscale signal is preferably used. The target customized grayscale signal is a customized image data signal. During testing, this signal is superimposed on the grayscale image to form a superimposed image, which is then displayed on the display screen.

[0106] Specifically, the computer device can obtain the superimposed image frame and grayscale frame captured by the visual system under the same shooting conditions for the same display screen or multiple display screens displaying the same basic grayscale signal. In one example, the superimposed image frame and grayscale frame can include one or more frames of images.

[0107] Step S204 , determining a first grayscale signal corresponding to the superimposed image frame and a second grayscale signal corresponding to the grayscale frame.

[0108] The first grayscale signal may represent a data signal in a grayscale domain extracted by the computer device from the overlaid image frame, and the second grayscale signal may represent a data signal in a grayscale domain extracted by the computer device from the grayscale frame.

[0109] Specifically, because the superimposed image and grayscale images captured by the visual system store data signals in the luminance domain, while the display screen receives data signals in the grayscale domain to display the superimposed image and grayscale images, it is necessary to convert the luminance signals of the superimposed image and grayscale images captured by the visual system.

[0110] The computer device can extract relative brightness data corresponding to the superimposed image from the brightness signal of the superimposed image. The relative brightness data corresponding to the superimposed image is converted into corresponding grayscale data based on a conversion relationship between the brightness domain and the grayscale domain. In one example, the conversion relationship between the brightness domain and the grayscale domain may include, but is not limited to, setting a brightness of 1 nit to correspond to the 15th grayscale, 2 nits to correspond to the 21st grayscale, and 500 nits to correspond to the 255th grayscale when there are 256 grayscale levels.

[0111] Similarly, by processing the brightness signal of the grayscale image with reference to the above-mentioned method for determining the first grayscale signal, the second grayscale signal corresponding to the grayscale image can be determined.

[0112] Step S206 , obtaining a difference signal between the first grayscale signal and the second grayscale signal.

[0113] The first grayscale signal and the second grayscale signal are processed in a manner of subtracting and obtaining a difference, thereby determining a difference signal (grayscale signal) between the first grayscale signal and the second grayscale signal.

[0114] Step S208 : determining the accuracy of the visual system according to the similarity between the difference signal and the target customized grayscale signal.

[0115] Specifically, since the first grayscale signal is restored from a superimposed image formed by superimposing the target customized grayscale signal on a grayscale image, and the second grayscale signal is restored directly from the grayscale image, the target customized grayscale signal can be simulated using the difference signal between the first and second grayscale signals. The accuracy of the visual system can then be determined by determining the similarity between the difference signal and the target customized grayscale signal.

[0116] The computer device can determine the similarity between the difference signal and the target customized grayscale signal by comparing the grayscale difference value at each pixel between the brightness restored difference signal and the target customized grayscale signal, or by treating both the difference signal and the target customized grayscale signal as multidimensional vector data and utilizing the similarity between the multidimensional vectors. Based on the similarity between the difference signal and the target customized grayscale signal, the accuracy of the visual system can be determined. For example, if the similarity exceeds a preset threshold, the accuracy of the visual system is determined to be high; otherwise, it is determined to be low. Alternatively, the similarity can be directly used as the accuracy of the visual system.

[0117] In the above-mentioned method for determining the accuracy of a visual system, by acquiring a superimposed image and a grayscale image captured by the visual system, the superimposed image is formed by superimposing a target customized grayscale signal on the grayscale image. A control group of display screen images formed by different signals can be formed, thereby helping to improve the accuracy of the accuracy determination method. By determining a first grayscale signal corresponding to the superimposed image and a second grayscale signal corresponding to the grayscale image, and obtaining a difference signal between the first grayscale signal and the second grayscale signal, the signal restored from the image captured by the visual system can be aligned with the original signal that formed the image, facilitating comparison between the signals. By determining the accuracy of the visual system based on the similarity between the difference signal and the target customized grayscale signal, the signal similarity can be used to quantitatively evaluate the accuracy of the image captured by the visual system.

[0118] In one embodiment, as shown in FIG3 , step S208 , determining the accuracy of the visual system based on the similarity between the difference signal and the target customized grayscale signal, includes:

[0119] Step S302: construct a first multi-dimensional vector corresponding to the difference signal.

[0120] Step S304: construct a second multidimensional vector corresponding to the target customized grayscale signal.

[0121] The difference signal can be represented in the form of a matrix. For example, a computer device can use the difference signal at each moment as a row or column of data in a matrix, thereby obtaining a matrix composed of difference signals at multiple moments. Alternatively, the computer device can use the difference signals at different grayscale levels as a row or column of data in a matrix, thereby obtaining a matrix formed by difference signals at multiple grayscale levels.

[0122] The first multidimensional vector may represent a multidimensional vector constructed using a matrix of difference signals. The dimension of the first multidimensional vector may be determined based on the length and width of the matrix. For example, if the length of the matrix is ​​M and the width is N, the dimension i of the first multidimensional vector is M*N.

[0123] Similarly, the target customized grayscale signal can also be expressed in the form of a matrix. The second multidimensional vector can represent a multidimensional vector constructed by the matrix of the target customized grayscale signal.

[0124] Specifically, the computer device can use the signal data in each row and column of the matrix of the difference signal as vector data of one dimension to construct a first multidimensional vector corresponding to the difference signal. Similarly, referring to the construction method of the first multidimensional vector, the matrix of the target customized grayscale signal is used to construct a second multidimensional vector corresponding to the target customized grayscale signal. The first and second multidimensional vectors have equal dimensions.

[0125] Step S306 : determining the similarity between the difference signal and the target customized grayscale signal based on the first multidimensional vector and the second multidimensional vector, and using the similarity as the accuracy.

[0126] Specifically, the computer device may process the first multidimensional vector and the second multidimensional vector in any one or more of the following ways to determine the similarity between the first multidimensional vector and the second multidimensional vector. The similarity between the multidimensional vectors is used to represent the similarity between the difference signal and the target customized grayscale signal, and the similarity between the difference signal and the target customized grayscale signal is used as the accuracy of the visual system:

[0127] Pearson Correlation Coefficient: It is used to measure the linear correlation between two variables. Its value range is [-1,1], where 1 indicates a perfect positive correlation, -1 indicates a perfect negative correlation, and 0 indicates no correlation.

[0128] Cosine Similarity: It is used to measure the cosine value of the angle between two vectors. The value range is [-1, 1], where 1 indicates complete similarity and -1 indicates complete dissimilarity.

[0129] Euclidean distance method: used to measure the Euclidean distance between two vectors, that is, the square root of the sum of the squares of the differences between the elements of the two vectors. The value range is [0, +∞), where 0 means exactly the same.

[0130] Manhattan distance method: It is used to measure the Manhattan distance between two vectors, that is, the sum of the absolute values ​​of the differences between the elements of the two vectors. The value range is [0, +∞), where 0 means they are exactly the same.

[0131] Optionally, in some embodiments, the computer device may obtain the similarity between the first multidimensional vector and the second multidimensional vector by referring to the following formula:

[0132] Among them, w δr It can represent the similarity between the first multidimensional vector and the second multidimensional vector, with a value range of (0 to 1.0). δr The larger the value, the higher the similarity. n can represent the number of dimensions of the first multidimensional vector and the second multidimensional vector. i It can represent the vector data under the i-th dimension in the second multidimensional vector. i It can represent vector data of the i-th dimension in the first multidimensional vector.

[0133] In this embodiment, by constructing multidimensional vectors corresponding to the difference signal and the target customized grayscale signal respectively, the similarity between the difference signal and the target customized grayscale signal is determined using the similarity solution method of the multidimensional vector, and the similarity between the difference signal and the target customized grayscale signal is used as the accuracy of the visual system, the accuracy of the similarity can be improved.

[0134] In one embodiment, since the superimposed image and the grayscale image are luminance spatial data acquired by the visual system, the computer device can determine a first grayscale signal of the superimposed image based on the first relative luminance of the superimposed image and a second grayscale signal based on the second relative luminance of the grayscale image based on the principle of converting luminance spatial data to grayscale spatial data.

[0135] The first relative brightness may represent brightness information of the superimposed image in the brightness space, and the first grayscale signal may represent grayscale information of the superimposed image in the grayscale space.

[0136] The second relative brightness may represent brightness information of the grayscale image in the brightness space. The second grayscale signal may represent grayscale information of the grayscale image in the grayscale space.

[0137] Before converting the luminance space data to the grayscale space data, the conversion coefficient γ value needs to be obtained.

[0138] Specifically, the computer device can obtain the conversion coefficient from the brightness space to the grayscale space, the first relative brightness of the superimposed image picture (which can be expressed in the form of a matrix, for example, the brightness value of each pixel in the superimposed image picture is used as an element in the matrix to construct the first relative brightness corresponding to the superimposed image picture), and the second relative brightness of the grayscale picture.

[0139] The first and second relative luminances of the superimposed image are processed based on the conversion coefficients to restore the first grayscale signal of the superimposed image in the grayscale space and the second grayscale signal of the grayscale image in the grayscale space. The imaging effect of the visual system is determined based on the similarity between the difference signal between the first and second grayscale signals and the target customized grayscale signal.

[0140] Optionally, in some embodiments, the computer device may generate the first grayscale signal and the second grayscale signal using the following calculation formula: GL_s = SQRT(GV_s / GV_255,γ) GL_base = SQRT(GV_base / GV_255,γ)

[0141] GL_s represents the theoretical grayscale signal of the overlay image in grayscale space, also known as the first grayscale signal. GV_s represents the first relative brightness of the overlay image in luminance space. GV_255 represents the imaging brightness value of the visual system at grayscale 255. GL_base represents the theoretical grayscale signal of the grayscale image in grayscale space, also known as the second grayscale signal. GV_base represents the second relative brightness of the grayscale image in luminance space. γ represents the conversion coefficient from luminance space data to grayscale space data.

[0142] In this embodiment, by obtaining the conversion coefficient from the brightness space to the grayscale space, the first relative brightness of the superimposed image in the brightness space and the second relative brightness of the grayscale image in the brightness space are restored to the corresponding first grayscale signal and second grayscale signal in the grayscale space according to the conversion coefficient. This enables a subsequent computer device to compare the difference signal between the first grayscale signal and the second grayscale signal with the target customized grayscale signal in the grayscale space, thereby improving the accuracy determination efficiency of the visual system.

[0143] In one embodiment, as shown in FIG4 , the above-mentioned implementation method of obtaining the conversion coefficient from the luminance space to the grayscale space is as follows:

[0144] Step S402: Acquire multiple grayscale images captured by the visual system and determine the brightness of each grayscale image. The image is not limited to grayscale images or superimposed images, but can be any image for which a conversion coefficient γ can be obtained.

[0145] The captured grayscale levels may include but are not limited to 8 grayscales, namely, grayscale 15, grayscale 31, grayscale 64, grayscale 96, grayscale 128, grayscale 196, grayscale 224, and grayscale 255. In other cases, any other grayscale levels may be selected, or all 256 grayscale levels may be selected.

[0146] Specifically, the computer device may define a circular area with the center of the display screen as the center and a preset distance as the radius as the region of interest. The brightness values ​​of all pixels in the image frame within the region of interest are obtained. The average brightness value of all pixels in the region of interest is used as the imaging brightness value of the image frame.

[0147] Step S404: Determine the theoretical brightness value corresponding to each gray scale level according to the imaging brightness value and exposure time of the vision system at each gray scale level.

[0148] Among them, the imaging brightness value can represent the relative brightness adopted by the vision system when collecting the image frame. In one example, in the application scenario of eliminating brightness non-uniformity of the display screen, the imaging brightness value Dn needs to satisfy 20% * M < Dn (imaging brightness value) < 60% * M, where M is the maximum brightness value in the current scenario (when the color performance parameter index of the display screen is 8 bits, the maximum brightness value is 255; when it is 12 bits, the maximum brightness value is 4095; when it is 16 bits, the maximum brightness value is 65535).

[0149] The exposure time can represent the time of sensor sampling integration when the vision system collects the image frame.

[0150] The theoretical brightness value can represent the theoretical value of the brightness of the image frame that the vision system can collect.

[0151] Specifically, since the image frame collected by the vision system needs to be imaged under the same aperture condition, in order to avoid overexposure of high gray scale imaging, different exposure times are usually adopted. The computer device can obtain the imaging brightness value and exposure time of the vision system at each gray scale level. Multiply the ratio values of the imaging brightness value and exposure time at each gray scale level to obtain the theoretical brightness value corresponding to each gray scale level.

[0152] Optionally, in some embodiments, the computer device can obtain the theoretical brightness value according to the following formula: GV i = Exp_n * Dn_n

[0153] Among them, GV i can represent the theoretical brightness value at the gray scale level i. Exp_n can represent the ratio value of the exposure time at the gray scale level i. Dn_n can represent the imaging brightness value at the gray scale level i. [[ID=XX]] [[ID=XX]]

[0154] Step S406: Determine the conversion coefficient at each gray scale level according to the theoretical brightness value and the preset gray scale value at each gray scale level. Among them, the conversion coefficient is the γ value actually responded by each pixel in the image frame. [[ID=XX]] [[ID=XX]]

[0155] Specifically, the computer device can perform arithmetic processing on the theoretical brightness value and the preset gray scale value at each gray scale level respectively by using the calculation formula, so as to obtain the conversion coefficient at each gray scale level. [[ID=XX]] [[ID=XX]]

[0156] Note: There seems to be some incorrect or duplicate tag handling in the original text. I've translated it as accurately as possible while maintaining the integrity of the provided content. You may want to review the original text for any potential errors in the tags or formatting.In this embodiment, the theoretical brightness value is determined by utilizing the imaging brightness value and exposure time of the visual system at each grayscale level, and then the conversion coefficient at each grayscale level is calculated using the theoretical brightness value corresponding to each grayscale level and the preset grayscale value, thereby improving the calculation efficiency of the conversion coefficient.

[0157] In one embodiment, the computer device may further use a polynomial least squares method to obtain a conversion coefficient at each grayscale level according to the following calculation formula, as follows:

[0158] Among them, i represents the number of grayscale levels corresponding to the image captured by the visual system, that is, the number of grayscales sampled, k represents the order of the polynomial, GL i It can represent the grayscale value at grayscale level i. It can represent the kth power of the grayscale value at grayscale level i (i=1 is the first grayscale selected, not grayscale 1, for example, the first grayscale level can be grayscale 16). i It can represent the theoretical brightness value under grayscale level i. a1,a2,a3,…,a k Can represent polynomial fitting coefficients.

[0159] The above formula can be simplified as: X*A=Y, A=(X T X) -1 X T Y. Further, the computer device can calculate the polynomial fitting coefficients A{a1, a2, a3, ..., a k That is, the conversion coefficient γ value of each pixel at different grayscale levels can be calculated to satisfy the following formula: γ(x)=a1+a2x+a3x 2 +…·a k x k

[0160] Where x represents the grayscale level. γ(x) is the conversion coefficient γ value at grayscale level x. a1, a2, a3, ..., a k are the polynomial fitting coefficients. k is the k-th power of the grayscale value at grayscale level x before fitting.

[0161] In this embodiment, the conversion coefficient is calculated by the above formula, which enables the computer device to simultaneously learn the conversion relationship between brightness space data and grayscale space data at different grayscale levels, thereby facilitating the improvement of the restoration accuracy of the first grayscale signal and the second grayscale signal.

[0162] In one embodiment, as shown in FIG5 , step S406 , determining a conversion coefficient at each grayscale level according to the theoretical brightness value and grayscale value at each grayscale level, includes:

[0163] Step S502 : using the imaging brightness value of the visual system at a preset grayscale level, normalizing the theoretical brightness value at each grayscale level to obtain a normalized theoretical brightness value.

[0164] In step S504 , the grayscale value at each grayscale level is normalized using a grayscale threshold value corresponding to a preset grayscale level to obtain a normalized grayscale value.

[0165] Step S506 : determining a conversion coefficient at each grayscale level according to the normalized theoretical brightness value and the normalized grayscale value at each grayscale level.

[0166] Specifically, a preset grayscale level may be pre-stored in the computer device. Preferably, the preset grayscale level may be 255. The imaging brightness value of the visual system at the preset grayscale level is used to normalize the theoretical brightness value at each grayscale level to obtain a normalized theoretical brightness value. The grayscale threshold corresponding to the preset grayscale level is obtained (for example, when the preset grayscale level is 255, the corresponding grayscale threshold is 255), that is, the highest grayscale at the preset grayscale level, and the grayscale value at each grayscale level is normalized to obtain a normalized grayscale value. Referring to the calculation formula provided in the above embodiment, the corresponding conversion coefficient at each grayscale level can be determined according to the normalized theoretical brightness value and the normalized grayscale value at each grayscale level.

[0167] Optionally, in some embodiments, when the highest grayscale of the target image acquisition scene of the display screen by the visual system is 255 grayscales, normalization processing can be performed according to the following formula: GV i '=GV i / GV 255 GL i =GL i / 255

[0168] Among them, GV i It can represent the theoretical brightness value at grayscale level i. i ' can represent the normalized theoretical brightness value under grayscale level i. GV 255 It can represent the imaging brightness value of the visual system at the preset grayscale level 255. GL i It can represent the grayscale value at grayscale level i. i ' can represent the normalized grayscale value at grayscale level i.

[0169] In this embodiment, the theoretical brightness values ​​and grayscale values ​​at multiple grayscale levels are normalized and then fitted to obtain corresponding conversion coefficients, thereby improving the calculation accuracy of the conversion coefficient γ.

[0170] In one embodiment, before obtaining the second grayscale signal, the method may further include obtaining a plurality of continuous grayscale images at the same grayscale level captured by a visual system, and determining a second relative brightness based on relative brightness data of each of the plurality of continuous grayscale images.

[0171] Specifically, the computer device can obtain multiple consecutive grayscale images captured by the visual system at the same grayscale level using the same shooting conditions (shooting conditions such as position, exposure time, focal length, etc.).

[0172] Obtain the relative brightness value of each grayscale image (which can be presented in a matrix format, where each data point in the matrix represents the brightness value of the pixel processed at the corresponding position). Use the maximum or minimum relative brightness value among the multiple consecutive grayscale images as the second relative brightness, or use the relative brightness value with a middle position in the order of magnitude among the multiple consecutive grayscale images as the second relative brightness, or use the average of the relative brightness values ​​of the multiple consecutive grayscale images as the second relative brightness.

[0173] Optionally, in some embodiments, the number of the consecutive multiple sheets may be 20 sheets.

[0174] Optionally, in some embodiments, the computer device may obtain the second relative brightness by referring to the following formula:

[0175] Among them, Mat base It can represent the second relative brightness. n can represent the number of consecutive images. F(x,y) can represent the relative brightness matrix data corresponding to each image.

[0176] In this embodiment, by acquiring multiple consecutive grayscale images under the same shooting conditions and using the average of the relative brightness data of the multiple images as the second relative brightness of the grayscale image, the error caused by the noise of the visual system or external noise in the grayscale image acquisition during the imaging of the visual system can be eliminated, thereby improving the acquisition accuracy of the grayscale image.

[0177] In one embodiment, the target customized grayscale signal may be generated according to display screen defect characteristics.

[0178] The display screen defect characteristics may include but are not limited to high-frequency information, low-frequency information, different spatial frequency data (expressed as the frequency of spatial line pair data), random noise, etc.

[0179] Specifically, in the application scenario of uneven brightness detection of display screens, the computer equipment can be customized to obtain the corresponding target customized grayscale signal according to the defect characteristics of the display screen. Since the signal fluctuation is small at low grayscales and the signal fluctuation is large at high grayscales. Therefore, it is preferred that the computer equipment can generate a fluctuating target customized grayscale signal within a specified range of ±15% grayscale amplitude. As shown in Figure 6, a schematic diagram of a target customized grayscale signal is provided. The frequency of the spatial line pair data in the center of the screen of Figure 6 can be from 1 to 1 (1by1) to 9 to 9 (9by 9), and the non-central area of ​​Figure 6 can be filled with random noise data. The sorting order of each spatial line pair data is not limited. Users can customize the required target customized grayscale signal according to their own project and product requirements.

[0180] In this embodiment, by generating a target customized grayscale signal based on the defect characteristics of the display screen, the style of the target customized grayscale signal can be enriched, and the imaging interference caused by high-frequency, low-frequency, and random noise that may exist in the imaging of the display screen / visual system can be reflected to the maximum extent, which can help improve the accuracy of the visual system accuracy determination method in visual inspection scenarios with different display screen defect characteristics.

[0181] In one embodiment, the display screen defect characteristics include one or more combinations of high-frequency information, low-frequency information, data of different spatial frequencies, and random noise.

[0182] In one embodiment, as shown in FIG7 , a method for determining the accuracy of a visual system is provided, comprising:

[0183] Step S702 : obtaining a superimposed image and a plurality of consecutive grayscale images captured by a visual system, and determining a first relative brightness of the superimposed image and a second relative brightness of the grayscale images.

[0184] Specifically, the computer device can obtain an overlay image captured by the visual system for the display screen, formed by superimposing a target customized grayscale signal generated based on the display screen defect characteristics on a grayscale image. A first relative brightness of the overlay image is obtained based on the brightness of pixels in the overlay image (wherein the brightness data is matrix data).

[0185] The computer device can obtain multiple continuous grayscale images formed by grayscale images collected by the visual system for the display screen, and use the relative brightness average of each grayscale image as the second relative brightness (wherein the brightness data is matrix data).

[0186] Step S704: Determine a normalized first relative brightness and a normalized second relative brightness at a target grayscale level, wherein the target grayscale level may represent a grayscale level corresponding to the superimposed image frame and the grayscale frame.

[0187] Step S706 : Based on the normalized first relative brightness at the target grayscale level and the conversion coefficient, convert the first relative brightness of the superimposed image into a first grayscale signal.

[0188] Step S708 : converting the second relative brightness of the grayscale image into a second grayscale signal based on the normalized second relative brightness at the target grayscale level and the conversion coefficient.

[0189] Optionally, in some embodiments, the computer device may obtain the first grayscale signal and the second grayscale signal by referring to the following formula: GL_s=SQRT(GV_s / GV_255,γ) GL_base=SQRT(GV_base / GV_255,γ)

[0190] Among them, GL_s can represent the theoretical grayscale signal of the superimposed image in the grayscale domain, that is, the first grayscale signal. GV_s can represent the first relative brightness of the superimposed image. GV_255 can represent the imaging brightness value of the visual system at a preset grayscale level (255 grayscale). GL_base can represent the theoretical grayscale signal of the grayscale image in the grayscale domain, that is, the second grayscale signal. GV_base can represent the second relative brightness of the grayscale image. γ is the conversion coefficient between the brightness signal and the grayscale signal.

[0191] Step S710 , obtaining a difference signal between the first grayscale signal and the second grayscale signal, and determining the accuracy of the visual system according to the difference signal and the first multidimensional vector and the second multidimensional vector corresponding to the target customized grayscale signal.

[0192] Specifically, the computer device can subtract the first grayscale signal and the second grayscale signal to obtain a difference signal. A first multidimensional vector and a second multidimensional vector corresponding to the difference signal are constructed. A cosine similarity between the first multidimensional vector and the second multidimensional vector is obtained, and the cosine similarity is used as the accuracy of the visual system.

[0193] Optionally, in some embodiments, the computer device may obtain the difference signal by referring to the following formula: S r =GL_s–GL_base;

[0194] Among them, S r It can represent the grayscale domain signal finally restored by the computer equipment, that is, the difference signal.

[0195] Optionally, in some embodiments, as shown in FIG8 , when the accuracy of the visual system is high, the computer device may process the raw data RAW Data collected by the visual system display panel to determine a first grayscale signal of the superimposed image and a second grayscale signal of the grayscale image, and output an image of the difference signal between the first grayscale signal and the second grayscale signal (in this case, due to the high accuracy of the visual system, the difference signal may be regarded as a target customized grayscale signal), thereby facilitating the detection of dot mura (a display defect characterized by uneven brightness), linear mura, and region luminance difference defects on the display screen.

[0196] In this embodiment, a target customized grayscale signal is customized based on display screen defect characteristics, and the target customized grayscale signal is superimposed on the display screen's base grayscale signal to obtain a superimposed image captured by the visual system for the display screen. This maximizes the imaging interference caused by the display screen defect characteristics on the visual system's data acquisition, thereby helping to improve the accuracy of subsequent visual system accuracy determinations. A conversion coefficient γ value is obtained by fitting luminance data at multiple grayscale levels with the grayscale values ​​of a sampled image. Based on the conversion coefficient γ value, the luminance signal is converted into a grayscale signal. The difference signal between the first grayscale signal of the superimposed image and the second grayscale signal of the grayscale image is used with the target customized grayscale signal to determine the similarity between the signals using a multidimensional vector similarity statistical method, thereby obtaining the accuracy of the visual system. This method enables quantitative assessment of the accuracy of the visual system and improves the accuracy of the accuracy determination.

[0197] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the steps or stages in other steps.

[0198] Based on the same inventive concept, embodiments of the present application also provide a device for determining the accuracy of a visual system for implementing the aforementioned method for determining the accuracy of a visual system. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the device for determining the accuracy of a visual system provided below can be found in the aforementioned limitations of the method for determining the accuracy of a visual system, and will not be further elaborated here.

[0199] In one embodiment, as shown in FIG9 , a device 900 for determining the accuracy of a visual system is provided, comprising: an image acquisition module 902 , a signal determination module 904 , a signal extraction module 906 , and an accuracy determination module 908 , wherein:

[0200] The image acquisition module 902 is used to obtain the superimposed image image and the grayscale image acquired by the visual system. The superimposed image image is formed by superimposing the target customized grayscale signal on the grayscale image.

[0201] The signal determination module 904 is configured to determine a first grayscale signal corresponding to the superimposed image frame and a second grayscale signal corresponding to the grayscale frame.

[0202] Signal extraction module 906, for obtaining a difference signal between the first grayscale signal and the second grayscale signal.

[0203] The accuracy determination module 908 is configured to determine the accuracy of the visual system according to the similarity between the difference signal and the target customized grayscale signal.

[0204] In one embodiment, the accuracy determination module 908 further includes a vector construction unit for constructing a first multidimensional vector corresponding to the difference signal and a second multidimensional vector corresponding to the target customized grayscale signal; a similarity determination unit for determining the similarity between the difference signal and the target customized grayscale signal based on the first multidimensional vector and the second multidimensional vector, and using the similarity as the accuracy.

[0205] In one embodiment, the superimposed image and the grayscale image are luminance space data acquired by a visual system. Signal determination module 904 is further configured to obtain a conversion coefficient from luminance space to grayscale space, and convert the first relative luminance of the superimposed image and the second relative luminance of the grayscale image according to the conversion coefficient to generate a first grayscale signal and a second grayscale signal.

[0206] In one embodiment, the signal determination module 904 is also used to obtain image frames at multiple grayscale levels captured by the visual system, determine the imaging brightness value of the image frame at each grayscale level, determine the theoretical brightness value corresponding to each grayscale level based on the imaging brightness value and exposure time of the visual system at each grayscale level, and determine the conversion coefficient at each grayscale level based on the theoretical brightness value and preset grayscale value at each grayscale level.

[0207] In one embodiment, the signal determination module 904 is further configured to obtain a conversion coefficient at each grayscale level according to the following calculation formula:

[0208] Among them, i represents the number of grayscale levels corresponding to the image captured by the visual system, k represents the order of the polynomial, GL i represents the grayscale value at grayscale level i, Represents the kth power of the grayscale value at grayscale level i, GV i Indicates the theoretical brightness value at grayscale level i, a1, a2, a3, ..., a k Represents the polynomial fitting coefficient; γ(x)=a1+a2x+a3x 2 +…·a k x k

[0209] Where x represents the grayscale level, γ(x) represents the conversion coefficient at grayscale level x, and x k is the k-th power of the grayscale value at grayscale level x before fitting.

[0210] In one embodiment, the signal determination module 904 includes: a normalization subunit, which is used to use the imaging brightness value of the visual system at a preset grayscale level to normalize the theoretical brightness value at each grayscale level to obtain a normalized theoretical brightness value, and use the grayscale threshold corresponding to the preset grayscale level to normalize the grayscale value at each grayscale level to obtain a normalized grayscale value, and determine the conversion coefficient at each grayscale level according to the normalized theoretical brightness value and the normalized grayscale value at each grayscale level.

[0211] In one embodiment, the accuracy determination device 900 of the visual system also includes: a brightness determination module, which is used to obtain multiple consecutive grayscale images at the same grayscale level captured by the visual system, and determine the second relative brightness based on the relative brightness data of each of the multiple consecutive grayscale images.

[0212] In one embodiment, the target customized grayscale signal is generated according to display screen defect characteristics.

[0213] In one embodiment, the display screen defect characteristics include one or more combinations of high-frequency information, low-frequency information, data of different spatial frequencies, and random noise.

[0214] Each module in the aforementioned apparatus for determining the accuracy of a visual system may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0215] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be shown in Figure 10. The computer device includes a processor, memory, a communication interface, a display screen, and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal via wired or wireless communication, and the wireless communication may be achieved via Wi-Fi, a mobile cellular network, NFC (near field communication), or other technologies. When executed by the processor, the computer program implements a method for determining the accuracy of a visual system. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen. The input device of the computer device may be a touch layer covering the display screen, or may be buttons, a trackball, or a touchpad provided on the computer device housing, or may be an external keyboard, touchpad, or mouse.

[0216] Those skilled in the art will understand that the structure shown in FIG10 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0217] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0218] In one embodiment, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0219] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0220] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0221] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0222] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A method for determining the accuracy of a visual system, characterized in that: The method comprises: Acquire a superimposed image screen and a grayscale screen collected by a visual system, wherein the superimposed image screen is formed by superimposing a target customized grayscale signal on the grayscale screen; Determine a first grayscale signal corresponding to the superimposed image picture, and a second grayscale signal corresponding to the grayscale picture; acquiring a difference signal between the first grayscale signal and the second grayscale signal; and The accuracy of the visual system is determined according to the similarity between the difference signal and the target customized grayscale signal.

2. The method according to claim 1, characterized in that Determining the accuracy of the visual system according to the similarity between the difference signal and the target customized grayscale signal includes: Constructing a first multidimensional vector corresponding to the difference signal; constructing a second multidimensional vector corresponding to the target customized grayscale signal; and The similarity between the difference signal and the target customized grayscale signal is determined according to the first multidimensional vector and the second multidimensional vector, and the similarity is used as the accuracy.

3. The method according to claim 1, characterized in that The superimposed image picture and the grayscale picture are brightness spatial data acquired by the visual system, and determining a first grayscale signal corresponding to the superimposed image picture and a second grayscale signal corresponding to the grayscale picture includes: Obtaining the conversion coefficient from brightness space to grayscale space; and The first relative brightness of the superimposed image picture and the second relative brightness of the grayscale picture are converted according to the conversion coefficient to generate the first grayscale signal and the second grayscale signal.

4. The method according to claim 3, characterized in that The step of obtaining the conversion coefficient from the brightness space to the grayscale space includes: Acquire image pictures at multiple grayscale levels captured by the visual system, and determine the imaging brightness value of the image picture at each grayscale level; Determining a theoretical brightness value corresponding to each grayscale level according to the imaging brightness value and exposure time of the visual system at each grayscale level; and According to the theoretical brightness value and the preset grayscale value at each grayscale level, a conversion coefficient at each grayscale level is determined.

5. The method according to claim 4, characterized in that Determining the conversion coefficient at each grayscale level according to the theoretical brightness value at each grayscale level and the preset grayscale value includes: The conversion coefficient at each grayscale level is obtained according to the following calculation formula: Wherein, i represents the number of grayscale levels corresponding to the image captured by the visual system, k represents the order of the polynomial, GLi represents the grayscale value at grayscale level i, represents the kth power of the grayscale value at grayscale level i, GVi represents the theoretical brightness value at grayscale level i, a1, a2, a3, …, a k represents the polynomial fitting coefficients; γ(x)=a1+a2x+a3x 2 +...·a k x k Wherein, x represents the grayscale level, γ(x) represents the conversion coefficient at the grayscale level x, x k is the kth power of the grayscale value at grayscale level x before fitting.

6. The method according to claim 4, characterized in that Determining the conversion coefficient at each grayscale level according to the theoretical brightness value at each grayscale level and the preset grayscale value includes: Using the imaging brightness value of the visual system at a preset grayscale level, normalizing the theoretical brightness value at each grayscale level to obtain a normalized theoretical brightness value; Normalizing the grayscale value at each grayscale level using the grayscale threshold value corresponding to the preset grayscale level to obtain a normalized grayscale value; and The conversion coefficient at each grayscale level is determined according to the normalized theoretical brightness value and the normalized grayscale value at each grayscale level.

7. The method according to claim 1, characterized in that The method further comprises: Acquire a plurality of continuous grayscale images at the same grayscale level captured by the visual system; and The second relative brightness is determined according to the relative brightness data of each of the plurality of consecutive grayscale images.

8. The method according to any one of claims 1 to 7, characterized in that: The target customized grayscale signal is generated according to the defect characteristics of the display screen.

9. The method according to claim 8, characterized in that The display screen defect characteristics include one or more combinations of high-frequency information, low-frequency information, data of different spatial frequencies, and random noise.

10. A device for determining the accuracy of a visual system, characterized in that: The device comprises: A picture acquisition module, used to acquire a superimposed image picture and a grayscale picture acquired by a visual system, wherein the superimposed image picture is formed by superimposing a target customized grayscale signal on the grayscale picture; A signal determination module, used to determine a first grayscale signal corresponding to the superimposed image picture, and a second grayscale signal corresponding to the grayscale picture; a signal extraction module, configured to obtain a difference signal between the first grayscale signal and the second grayscale signal; and The accuracy determination module is used to determine the accuracy of the visual system according to the similarity between the difference signal and the target customized grayscale signal.

11. The device according to claim 10, characterized in that The accuracy determination module comprises: A vector construction unit, used to construct a first multi-dimensional vector corresponding to the difference signal; constructing a second multidimensional vector corresponding to the target customized grayscale signal; and A similarity determination unit is used to determine the similarity between the difference signal and the target customized grayscale signal according to the first multidimensional vector and the second multidimensional vector, and use the similarity as the accuracy.

12. The device according to claim 10, characterized in that The superimposed image picture and the grayscale picture are brightness spatial data acquired by the visual system, The signal determination module is further used for: Obtaining the conversion coefficient from brightness space to grayscale space; and The first relative brightness of the superimposed image picture and the second relative brightness of the grayscale picture are converted according to the conversion coefficient to generate the first grayscale signal and the second grayscale signal.

13. The device according to claim 12, characterized in that The signal determination module is further used for: Acquire image pictures at multiple grayscale levels captured by the visual system, and determine the imaging brightness value of the image picture at each grayscale level; Determining a theoretical brightness value corresponding to each grayscale level according to an imaging brightness value and an exposure time of the visual system at each grayscale level; as well as According to the theoretical brightness value and the preset grayscale value at each grayscale level, a conversion coefficient at each grayscale level is determined.

14. The device according to claim 13, characterized in that The signal determination module is further used for: The conversion coefficient at each grayscale level is obtained according to the following calculation formula: Wherein, i represents the number of grayscale levels corresponding to the image captured by the visual system, k represents the order of the polynomial, GLi represents the grayscale value at grayscale level i, represents the kth power of the grayscale value at grayscale level i, GVi represents the theoretical brightness value at grayscale level i, a1, a2, a3, …, a k represents the polynomial fitting coefficients; γ(x)=a1+a2x+a3x 2 +...·a k x k Wherein, x represents the grayscale level, γ(x) represents the conversion coefficient at the grayscale level x, x k is the kth power of the grayscale value at grayscale level x before fitting.

15. The device according to claim 12, characterized in that The signal determination module comprises: Normalization subunit, used to: Using the imaging brightness value of the visual system at a preset grayscale level, normalizing the theoretical brightness value at each grayscale level to obtain a normalized theoretical brightness value; Normalizing the grayscale value at each grayscale level using the grayscale threshold value corresponding to the preset grayscale level to obtain a normalized grayscale value; and The conversion coefficient at each grayscale level is determined according to the normalized theoretical brightness value and the normalized grayscale value at each grayscale level.

16. The device according to claim 10, characterized in that The device also includes: Brightness determination module, used for: Acquire a plurality of continuous grayscale images at the same grayscale level captured by the visual system; and The second relative brightness is determined according to the relative brightness data of each of the plurality of consecutive grayscale images.

17. The device according to any one of claims 10 to 16, characterized in that The target customized grayscale signal is generated according to the defect characteristics of the display screen.

18. The device according to claim 17, characterized in that The display screen defect characteristics include one or more combinations of high-frequency information, low-frequency information, data of different spatial frequencies, and random noise.

19. A computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

20. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

21. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images