Display compensation method, brightness control model training method and related device

Abstract

The application provides a display compensation method, a brightness control model training method and related devices, wherein the display compensation method comprises: inputting the current average image level and the current brightness of a display panel into a brightness control model to obtain the corrected gray scale of each pixel on the display panel; wherein the brightness control model is trained according to a plurality of sets of training data, each set of training data comprising: brightness training data of the display panel, average image level training data corresponding to the brightness training data, and target gray scale of each pixel corresponding to the brightness training data, the pixel being able to achieve local excitation brightness at the target gray scale; determining the driving voltage required to excite each pixel of the display panel to the corrected gray scale; and outputting the corresponding driving voltage to each pixel. The application can conveniently compensate for the local excitation brightness deviation caused by the voltage drop by correcting the gray scale based on the brightness control model, without the need to modify the hardware of the display device, thereby reducing the cost.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of display, and in particular to a display compensation method, a training method of a brightness control model and related devices. BACKGROUND

[0002] OLED (Organic Light Emitting Diode) screens have been widely used in mobile phones, wearables, tablets and other scenarios.

[0003] Local excitation brightness is one of the important indicators to measure the performance of OLED screens, and is crucial for providing high-quality visual experience. Local excitation brightness is a key factor in realizing high dynamic range (HDR) content display. HDR content requires the screen to provide high brightness in a small area to reveal rich details and contrast. Local excitation brightness affects the local contrast and details of the screen display image. When watching videos or pictures, high local excitation brightness can provide clearer and more vivid visual effects. In outdoor or direct sunlight environments, high local excitation brightness can improve the visibility of the screen, so that users can clearly see the screen content even in strong light.

[0004] Local excitation brightness is the peak brightness value obtained by the local area of the screen under the premise of global excitation brightness. However, due to the voltage drop (i.e. voltage drop) caused by the internal resistance of the wiring in the PANEL (display panel) in local display, the performance of peak brightness is often affected by the deviation of brightness, chrominance and gamma curve, thereby generating local excitation brightness deviation. SUMMARY

[0005] Embodiments of the present application provide a display compensation method, a training method of a brightness control model and related devices to solve the problem of local excitation brightness deviation of a display device when displaying.

[0006] To solve the above technical problems, the present application is implemented as follows:

[0007] In a first aspect, embodiments of the present application provide a display compensation method, comprising:

[0008] inputting the current average image level and the current brightness of the display panel into a brightness control model to obtain the corrected gray scale of each pixel on the display panel; wherein the brightness control model is trained according to a plurality of training data, each set of training data comprising: brightness training data of the display panel, average image level training data corresponding to the brightness training data, and target gray scale of the pixels corresponding to the brightness training data, the pixels being able to realize local excitation brightness at the target gray scale;

[0009] determining a driving voltage required to excite the pixels of the display panel to the corrected gray scale;

[0010] outputting the corresponding driving voltage to the pixels.

[0011] In a second aspect, an embodiment of the present application provides a training method of a brightness control model, comprising:

[0012] obtaining a training data set, the training data set comprising a plurality of groups of training data, each group of training data comprising: brightness training data of a display panel, average image level training data corresponding to the brightness, and target gray scales of pixels corresponding to the brightness training data, the pixels being capable of realizing local excitation brightness at the target gray scales;

[0013] training a to-be-trained brightness control model using the training data set to obtain a brightness control model.

[0014] Optionally, the training of the original brightness control model using the training data set to obtain a brightness control model comprises:

[0015] a prediction step of inputting the brightness training data and the average image level training data corresponding to the brightness training data into the to-be-trained brightness control model to obtain predicted gray scales of the pixels output by the to-be-trained brightness control model;

[0016] an optimization step of optimizing parameters of the to-be-trained brightness control model according to the target gray scales and the predicted gray scales of the pixels;

[0017] iteratively performing the prediction step and the optimization step until a preset condition is met.

[0018] Optionally, the preset condition is that a difference between the predicted gray scales and the target gray scales is less than a preset threshold.

[0019] Alternatively, the preset condition is that an iteration number exceeds a preset number of iterations.

[0020] Optionally, the pixels comprise a plurality of single-color pixels, the parameters of the to-be-trained brightness control model corresponding to each single-color pixel being different.

[0021] The optimization step comprises:

[0022] optimizing the parameters of the to-be-trained brightness control model corresponding to each single-color pixel according to the target gray scales and the predicted gray scales of the single-color pixel.

[0023] In a third aspect, an embodiment of the present application provides a display compensation device, comprising:

[0024] The execution module is configured to input the current average image level and the current brightness of the display panel into the brightness control model to obtain a corrected gray scale of each pixel on the display panel; wherein the brightness control model is trained according to a plurality of sets of training data, and each set of the training data includes: brightness training data of the display panel, average image level training data corresponding to the brightness training data, and target gray scales of the pixels corresponding to the brightness training data, and the pixels can achieve local excitation brightness at the target gray scales;

[0025] The determination module is configured to determine a driving voltage required for exciting the pixels of the display panel to the corrected gray scales.

[0026] The output module is configured to output the corresponding driving voltage to the pixels.

[0027] In a fourth aspect, an embodiment of the present application provides a training device of a brightness control model, comprising:

[0028] The acquisition module is configured to acquire a training data set, and the training data set includes a plurality of sets of training data, and each set of the training data includes: brightness training data of a display panel, average image level training data corresponding to the brightness, and target gray scales of pixels corresponding to the brightness training data; and the pixels can achieve local excitation brightness at the target gray scales.

[0029] The training module is configured to train a to-be-trained brightness control model by using the training data set to obtain a brightness control model.

[0030] In a fifth aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, and a program or instructions stored in the memory and executable on the processor, and the program or instructions are executed by the processor to implement steps in the display compensation method according to the first aspect, or implement steps in the training method of the brightness control model according to any one of the second aspect.

[0031] In a sixth aspect, an embodiment of the present application provides a readable storage medium, and the readable storage medium stores a program or instructions, and the program or instructions are executed by a processor to implement steps in the display compensation method according to the first aspect, or implement steps in the training method of the brightness control model according to any one of the second aspect.

[0032] In a seventh aspect, an embodiment of the present application provides a computer program product, comprising computer instructions, and the computer instructions are executed by a processor to implement steps in the display compensation method according to the first aspect, or implement steps in the training method of the brightness control model according to any one of the second aspect.

[0033] In the embodiment of the present application, the average image level and the current brightness of the display panel are input into the pre-trained brightness control model to obtain the corrected gray scale of each pixel on the display panel, the driving voltage required to excite each pixel of the display panel to the corrected gray scale is determined, and the corresponding driving voltage is output to each pixel. The brightness control model is trained based on a plurality of sets of training data. Each set of training data includes: brightness training data of the display panel, average image level training data corresponding to the brightness training data, and target gray scale of each pixel corresponding to the brightness training data, at which the pixel can achieve local excitation brightness. Based on the brightness control model, the local excitation brightness deviation caused by the voltage drop can be compensated by correcting the gray scale without modifying the hardware of the display device, thereby reducing the cost. BRIEF DESCRIPTION OF DRAWINGS

[0034] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The accompanying drawings are included to provide a better understanding of the preferred embodiments, and are not to be considered as limiting of the present application. Moreover, in the drawings, like reference numerals denote similar components throughout the several views. In the drawings:

[0035] Figure 1 Schematic diagram of the principle of voltage drop;

[0036] Figure 2 Flowchart of the display compensation method of the embodiment of the present application;

[0037] Figure 3 Flowchart of the training method of the brightness control model of the embodiment of the present application;

[0038] Figure 4 Schematic diagram of the training flowchart;

[0039] Figure 5 Principle block diagram of the display compensation device of the embodiment of the present application;

[0040] Figure 6 Principle block diagram of the training device of the brightness control model of the embodiment of the present application;

[0041] Figure 7 Principle block diagram of the electronic device of the embodiment of the present application. DETAILED DESCRIPTION

[0042] With reference to the drawings and embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of the present application.

[0043] The terms "first", "second", and the like in the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second" are generally a class, not limited to the number of objects, for example, the first object can be one or more. In addition, "or" in the present application means at least one of the connected objects. For example, "A or B" covers three scenarios, namely, scenario one: including A and not including B; scenario two: including B and not including A; scenario three: including A and B. The character " / " generally represents that the objects before and after are in an "or" relationship.

[0044] In the technical solutions of the present disclosure, the terms "connected", "coupled" or "linked" and the like are not limited to physical or mechanical connections, but can include electrical connections.

[0045] In addition, the technical features involved in different embodiments of the present application described below can be combined with each other as long as there is no conflict between them.

[0046] Figure 1 The voltage drop caused by the internal resistance of the wiring in the PANEL in the local display is illustrated. Specifically, Figure 1 In the display module, the equivalent resistance of all parallel sub-pixel units in the display area is defined as Rx, and the ELVDD voltage lead resistance of the sub-pixel unit in the display module is defined as R0. In the display module, R0 is a fixed value. Rx and R0 are connected in series and pass through the same current (I). Therefore, the resistance R0 occupies a part of the voltage, that is, Vdrop = I x R0. However, in the display module, I will change according to the displayed image, so Vdrop will also change accordingly. As a result of the IR drop effect, the voltage allocated to the parallelly connected sub-pixel units in the display area also changes simultaneously, that is, Real ELVDD = ELVDD - I x R0. The phenomenon that the Real ELVDD of the sub-pixel unit is different due to different display loads is called internal resistance voltage drop (IR Drop, referred to as voltage drop in the present application).

[0047] The present application provides a display compensation method, as shown in Figure 2 as shown,Figure 2 A flowchart of a display compensation method is shown in the embodiment of the present application, which comprises:

[0048] Step 11: input the current average image level and the current brightness of the display panel into the brightness control model to obtain the corrected gray scale of each pixel on the display panel; wherein the brightness control model is obtained by training according to a plurality of sets of training data, each set of training data comprising: brightness training data of the display panel, average image level training data corresponding to the brightness training data, and target gray scale of each pixel corresponding to the brightness training data, under which the pixel can achieve local excitation brightness;

[0049] Step 12: determine the driving voltage required to excite each pixel of the display panel to the corrected gray scale;

[0050] Step 13: output the corresponding driving voltage to each pixel.

[0051] In the embodiment of the present application, the target gray scale, i.e. the gray scale that each pixel should reach under the same set of brightness training data and average image level training data after the user sets off the pressure drop, here the same set refers to the same set of training data. That is, the target gray scale, i.e. the gray scale that corrects the local excitation brightness deviation caused by the pressure drop. In the embodiment of the present application, the pixel can achieve local excitation brightness under the target gray scale, which means that each pixel can reach the local excitation brightness excluding the local excitation brightness deviation caused by the pressure drop under the target gray scale. Therefore, it can be understood that the brightness control model can output the gray scale that each pixel should have under the correction of the local excitation brightness deviation, i.e. the corrected gray scale, according to the input current average image level and current brightness.

[0052] In the embodiment of the present application, the specific method of determining the driving voltage in step 12 comprises: determining the driving voltage required to excite each pixel of the display panel to the corrected gray scale according to the preset gray scale-driving voltage mapping relationship data.

[0053] It should be noted that, in some optional embodiments, the present invention can be applied to a DDIC (Display Data Interface Controller) in a display. The DDIC is electrically connected to the display panel in the display and is used to output driving voltages to drive each pixel to emit light. The DDIC pre-stores grayscale-driving voltage mapping data; and / or, the DDIC is electrically connected to a register in the display, which pre-stores grayscale-driving voltage mapping data, and the DDIC can call the grayscale-driving voltage mapping data pre-stored in the register. Therefore, after performing the step of inputting the current average image level and current brightness of the display panel into the brightness control model to obtain the corrected grayscale of each pixel on the display panel, the DDIC can determine the driving voltage required to excite each pixel of the display panel to the corrected grayscale based on the grayscale-driving voltage mapping data, and output the corresponding driving voltage to each pixel, so that each pixel emits light according to the corrected grayscale, thereby achieving localized brightness excitation.

[0054] It should be noted that, in this embodiment of the invention, the driving voltage required to excite each pixel of the display panel to the corrected grayscale is the voltage that can offset the voltage drop after being input to each pixel, and thus can correct the local excitation brightness deviation caused by the voltage drop after being input to each pixel.

[0055] In this embodiment of the invention, the corrected grayscale of each pixel on the display panel is obtained by inputting the current average image level and current brightness of the display panel into a pre-trained brightness control model. The driving voltage required to excite each pixel of the display panel to the corrected grayscale is determined, and the corresponding driving voltage is output to each pixel. The brightness control model is trained based on multiple sets of training data. Each set of training data includes: brightness training data of the display panel, average image level training data corresponding to the brightness training data, and target grayscale of each pixel corresponding to the brightness training data. Under the target grayscale, the pixel can achieve local excitation brightness. Based on the brightness control model, it is convenient to compensate for the local excitation brightness deviation caused by voltage drop by correcting the grayscale without modifying the hardware of the display device, which is low cost.

[0056] This invention provides a training method for a brightness control model, see [link to relevant documentation]. Figure 3 As shown, Figure 3 This is a flowchart illustrating the training method of the brightness control model according to an embodiment of the present invention, including:

[0057] Step 21: obtaining a training data set, the training data set including a plurality of groups of training data, each group of training data including: brightness training data of a display panel, average image level training data corresponding to the brightness, and target gray scales of pixels corresponding to the brightness training data; the pixels can achieve local excitation brightness at the target gray scales;

[0058] Step 22: training the brightness control model to be trained by using the training data set, to obtain the brightness control model.

[0059] In the embodiment of the present application, the target gray scale is the gray scale that each pixel should reach under the same group of brightness training data and average image level training data after the user sets the offset pressure drop. Here, the same group refers to the same group of training data. That is, the target gray scale is the gray scale that corrects the local excitation brightness deviation caused by the pressure drop. In the embodiment of the present application, the pixels can achieve local excitation brightness at the target gray scales, which means that each pixel can reach the local excitation brightness excluding the local excitation brightness deviation caused by the pressure drop at the target gray scales. Therefore, it can be understood that the brightness control model trained in the embodiment of the present application can output the gray scale that corrects the local excitation brightness deviation caused by the pressure drop, that is, the correction gray scale, according to the input current average image level and current brightness.

[0060] In some embodiments of the present application, the brightness control model to be trained is optionally trained based on a genetic algorithm (GA) to improve the training efficiency. Genetic algorithm is a heuristic search algorithm that simulates natural selection and genetic principles to solve optimization problems. Genetic algorithm was proposed by John H. Holland in the 1970s and was described in detail in his book "Adaptation in Artificial and Natural Systems". The basic idea of genetic algorithm is to iteratively optimize candidate solutions by simulating the genetic and variation mechanisms in the biological evolution process.

[0061] In the embodiment of the present application, by obtaining a training data set, the training data set including a plurality of groups of training data, each group of training data including: brightness training data of a display panel, average image level training data corresponding to the brightness, and target gray scales of pixels corresponding to the brightness training data; the pixels can achieve local excitation brightness at the target gray scales; training the brightness control model to be trained by using the training data set, to obtain the brightness control model, the embodiment of the present application can train the brightness control model that corrects the local excitation brightness deviation caused by the pressure drop according to the input average image level and brightness output.

[0062] In some embodiments of the present application, the original brightness control model is optionally trained by using the training data set to obtain the brightness control model, including:

[0063] The prediction step a comprises: inputting the brightness training data and the average image level training data corresponding to the brightness training data into a brightness control model to be trained to obtain predicted gray scales of each pixel output by the current brightness control model to be trained;

[0064] The optimization step b comprises: optimizing parameters of the brightness control model to be trained according to the target gray scale and the predicted gray scale of each pixel.

[0065] The prediction step a and the optimization step b are iteratively executed until a preset condition is met.

[0066] The embodiment of the present application can realize continuous training and optimization of the brightness control model to be trained until the brightness control model is trained, thereby reducing human intervention in the training and improving the training efficiency.

[0067] In some embodiments of the present application, the preset condition is that a difference between the predicted gray scale and the target gray scale is less than a preset threshold.

[0068] Alternatively, the preset condition is that the number of iterations exceeds a preset number of times.

[0069] In the embodiment of the present application, when the preset condition is that the difference between the predicted gray scale and the target gray scale is less than the preset threshold, the preset condition is met, which means that the difference between the predicted gray scale and the target gray scale output by the current brightness control model to be trained meets the user's usage requirements, the training can be terminated, and the current brightness control model to be trained is used as the brightness control model to be trained.

[0070] In some embodiments of the present application, the preset threshold is 0.1. Under the preset threshold, the brightness control model trained by the embodiment of the present application can accurately output the corrected gray scale according to the input current average image level and current brightness.

[0071] In some embodiments of the present application, the pixels include a plurality of single-color pixels, and the parameters of the brightness control model to be trained corresponding to each single-color pixel are different.

[0072] The optimization step b comprises:

[0073] The parameters of the brightness control model to be trained corresponding to each single-color pixel are respectively optimized according to the target gray scale and the predicted gray scale of each single-color pixel.

[0074] In this embodiment of the invention, by optimizing the parameters of the brightness control model to be trained for each single-color pixel according to the target gray level and the predicted gray level of each single-color pixel, this embodiment of the invention finely distinguishes the parameters of the brightness control model to be trained for each single-color pixel and optimizes them in a targeted manner, which can achieve more accurate parameter optimization and ensure that the trained brightness control model can accurately obtain the corrected gray level.

[0075] In some embodiments of the present invention, optionally, the single-color pixel includes three types: R (red), G (green), and B (blue).

[0076] The present invention will be further described below through some specific embodiments.

[0077] Model training data collection:

[0078] See Figure 4 As shown, under white screens with APL of 10%, 20%, and 30%, 10 R / G / B data (i.e., target grayscale) are set at 1600nit, 2000nit, 2500nit, and 3000nit respectively, which are the data values ​​of the PANEL R / G / B pixels.

[0079] Model training:

[0080] Let DATA R / G / B The relation is:

[0081] DATA R =a0 R +a1 R *APL+a2 R *Lv+a3 R *APL^2+a4 R *Lv^2+a5 R *APL*lv

[0082] DATA G =a0 G +a1 G *APL+a2 G *Lv+a3 G *APL^2+a4 G *Lv^2+a5 G *APL*lv

[0083] DATA B =a0 B +a1 B *APL+a2 B *Lv+a3 B *APL^2+a4 B *Lv^2+a5B APL lv

[0084] The collected raw data is DATA R / G / B (R / G / B data, i.e. target gray scale), APL (i.e. average image level training data) and Lv (i.e. brightness training data of the display panel), and six parameters a0, a1, a2, a3, a4 and a5 are identified using a genetic algorithm, including the following key steps:

[0085] 1. Initialization of population: a group of candidate solutions is randomly generated to form an initial population. Each candidate solution is called an individual, and the set of individuals is called a population;

[0086] The population size is designed to be 100, the dimension is 6 (6 parameters), and the upper and lower limits of the parameters are [-2000, 2000].

[0087] 2. Fitness evaluation: the fitness value of each individual is calculated, which is usually related to the objective function of the problem and reflects the ability of the individual to solve the problem;

[0088] The expression of the fitness function is as follows:

[0089] F[i] = DATA[i]-

[0090] [a0+a1*APL[i]+a2*Lv[i]+a3*APL[i]^2+a4*Lv[i]^2+a5*APL[i]*lv[i]];

[0091] Where F[i] is the fitness at time i; APL[i] is the average image level at time i; Lv[i] is the brightness at time i; DATA[i] is the target gray scale at time i;

[0092] a0+a1*APL[i]+a2*Lv[i]+a3*APL[i]^2+a4*Lv[i]^2+a5*APL[i]*lv[i] is the predicted gray scale at time i, because the value of F[i] is smaller, the better.

[0093] 3. Selection: select individuals for reproduction according to their fitness values. Individuals with higher fitness values have a greater probability of being selected.

[0094] 4. Crossover: randomly select a pair of individuals from the selected individuals for crossover, and generate new offspring by exchanging some parts of the individuals.

[0095] 5. Mutation: mutate the newly generated offspring, i.e. randomly change some characteristics of the offspring individuals to increase the diversity of the population.

[0096] 6. Forming a new generation of population: new individuals generated by crossover and mutation form a new generation of population.

[0097] 7. Termination condition judgment: check whether the preset conditions are met, such as reaching the maximum number of iterations, the fitness value reaching the preset threshold, etc. If met, the algorithm ends; otherwise, return to step 2 to continue iteration.

[0098] 8. Output the optimal solution: select the individual with the highest fitness value from the final population as the optimal solution of the problem (a0, a1, a2, a3, a4, a5).

[0099] According to the identification result, the relationship between DATA R / G / B , Lv and APL (i.e. the brightness control model) is:

[0100] DATA R = a0 R + a1 R * APL + a2 R * Lv + a3 R * APL^2 + a4 R * Lv^2 + a5 R * APL * lv;

[0101] DATA G = a0 G + a1 G * APL + a2 G * Lv + a3 G * APL^2 + a4 G * Lv^2 + a5 G * APL * lv;

[0102] DATA B = a0 B + a1 B * APL + a2 B * Lv + a3 B * APL^2 + a4 B * Lv^2 + a5 B * APL * lv.

[0103] Then, the obtained brightness control model is placed in the DDIC, and the DDIC executes the step of inputting the current average image level and the current brightness of the display panel into the brightness control model to obtain the corrected gray scale of each pixel on the display panel under the instruction control of the whole machine, and after determining the driving voltage required to excite each pixel of the display panel to the corrected gray scale, the screen display output data (i.e. output the corresponding driving voltage to each pixel).

[0104] The display compensation device provided by the embodiment of the application comprises Figure 5As shown, Figure 5 This is a schematic block diagram of the compensation device according to an embodiment of the present invention. The compensation device 50 includes:

[0105] The execution module 51 is used to input the current average image level and current brightness of the display panel into the brightness control model to obtain the corrected grayscale of each pixel on the display panel; wherein, the brightness control model is trained based on multiple sets of training data, each set of training data includes: brightness training data of the display panel, average image level training data corresponding to the brightness training data, and target grayscale of each pixel corresponding to the brightness training data, under the target grayscale, the pixel can achieve local excitation brightness;

[0106] The determining module 52 is used to determine the driving voltage required to excite each pixel of the display panel to the corrected grayscale;

[0107] The output module 53 is used to output the corresponding driving voltage to each pixel.

[0108] The display compensation device provided in this application embodiment can achieve... Figure 2 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[0109] This invention provides a training device for a brightness control model, see [link to relevant documentation]. Figure 6 As shown, Figure 6 This is a schematic diagram of the training device for the brightness control model according to an embodiment of the present invention. The training device 60 for the brightness control model includes:

[0110] The acquisition module 61 is used to acquire a training data set, which includes multiple sets of training data. Each set of training data includes: brightness training data of the display panel, average image level training data corresponding to the brightness, and target grayscale of each pixel corresponding to the brightness training data; the pixel can achieve local excitation brightness under the target grayscale.

[0111] Training module 62 is used to train the brightness control model to be trained using the training data set to obtain the brightness control model.

[0112] In some embodiments of the present invention, optionally,

[0113] The training module 62 is also used for the prediction step: inputting the brightness training data and the average image level training data corresponding to the brightness training data into the brightness control model to be trained, and obtaining the predicted grayscale of each pixel output by the current brightness control model to be trained.

[0114] The training module 62 is further configured to optimize the parameters of the to-be-trained brightness control model according to the target gray scale and the predicted gray scale of each pixel.

[0115] The prediction step and the optimization step are iteratively performed until a preset condition is met.

[0116] In some embodiments of the present application, optionally,

[0117] The preset condition is that a difference between the predicted gray scale and the target gray scale is less than a preset threshold.

[0118] Alternatively, the preset condition is that an iteration number exceeds a preset number.

[0119] In some embodiments of the present application, optionally, the pixels include a plurality of single-color pixels, and the parameters of the to-be-trained brightness control model corresponding to each single-color pixel are different.

[0120] The training module 62 is further configured to optimize the parameters of the to-be-trained brightness control model corresponding to each single-color pixel according to the target gray scale and the predicted gray scale of each single-color pixel.

[0121] The display compensation device provided by the embodiments of the present application can realize Figure 3 to Figure 4 The method embodiments shown realize various processes and achieve the same technical effects, and thus details are not repeated here.

[0122] The embodiments of the present application provide an electronic device 70, as shown in Figure 7 The electronic device 70 is a principle block diagram of the embodiments of the present application, which includes a processor 71, a memory 72, and a program or instruction stored in the memory 72 and executable on the processor 71. Figure 7 The program or instruction is executed by the processor to realize the steps in any of the display compensation methods of the present application, or to realize the steps in the training method of the brightness control model.

[0123] The embodiments of the present application provide a readable storage medium, which stores a program or instruction, and the program or instruction is executed by a processor to realize various processes of the embodiments of any of the display compensation methods or the training method of the brightness control model, and achieve the same technical effects, and thus details are not repeated here.

[0124] The readable storage medium is, for example, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, etc. In some examples, the readable storage medium can be a non-transitory readable storage medium.

[0125] The embodiment of the present application further provides a computer program product comprising computer instructions, which, when executed by a processor, implement each process of the embodiment of any of the display compensation methods or each process of the embodiment of any of the training methods of the brightness control model, and achieve the same technical effects. To avoid repetition, details are not described herein.

[0126] The embodiments of the present application are described above in combination with the accompanying drawings, but the present application is not limited to the specific embodiments described above, which are merely illustrative rather than restrictive. Those of ordinary skill in the art can make many forms under the inspiration of the present application without departing from the purpose of the present application and the scope protected by the claims, which are all within the protection of the present application.

Claims

1. A display compensation method, characterized by, The method comprises the following steps: inputting the current average image level and the current brightness of the display panel into a brightness control model to obtain a corrected gray scale of each pixel on the display panel; wherein the brightness control model is trained according to a plurality of sets of training data, and each set of training data comprises brightness training data of the display panel, average image level training data corresponding to the brightness training data, and target gray scales of the pixels corresponding to the brightness training data, under which the pixels can achieve local excitation brightness; determining a driving voltage required for exciting the pixels on the display panel to the corrected gray scales; outputting the corresponding driving voltage to the pixels; obtaining the brightness control model, comprising: a prediction step: inputting the brightness training data and the average image level training data corresponding to the brightness training data into a brightness control model to be trained to obtain predicted gray scales of each pixel output by the brightness control model to be trained at present; an optimization step: optimizing parameters of the brightness control model to be trained according to the target gray scales and the predicted gray scales of the pixels; iteratively performing the prediction step and the optimization step until a preset condition is met.

2. A training method for a brightness control model, characterized in that, The method comprises the following steps: obtaining a training data set, wherein the training data set comprises a plurality of sets of training data, each set of training data comprises brightness training data of a display panel, average image level training data corresponding to the brightness, and target gray scales of each pixel corresponding to the brightness training data, under which the pixels can achieve local excitation brightness; training a brightness control model to be trained using the training data set to obtain a brightness control model, comprising: a prediction step: inputting the brightness training data and the average image level training data corresponding to the brightness training data into the brightness control model to be trained to obtain predicted gray scales of each pixel output by the brightness control model to be trained at present; an optimization step: optimizing parameters of the brightness control model to be trained according to the target gray scales and the predicted gray scales of the pixels; iteratively performing the prediction step and the optimization step until a preset condition is met.

3. The training method of the brightness control model according to claim 2, wherein the preset condition is that a difference between the predicted gray scale and the target gray scale is less than a preset threshold value; or the preset condition is that the number of iterations exceeds a preset number of times.

4. The training method of the brightness control model according to claim 2, wherein the pixels comprise a plurality of single-color pixels, and the parameters of the brightness control model to be trained corresponding to each single-color pixel are different; the optimization step comprises: optimizing the parameters of the brightness control model to be trained corresponding to each single-color pixel according to the target gray scale and the predicted gray scale of each single-color pixel, respectively. The method comprises the following steps: ​ ​ 5. A display compensation device, characterized by, ​ The execution module is configured to input the current average image level and the current brightness of the display panel into a brightness control model to obtain corrected gray scales of each pixel on the display panel; wherein the brightness control model is trained according to a plurality of sets of training data, and each set of the training data comprises brightness training data of the display panel, average image level training data corresponding to the brightness training data, and target gray scales of the pixels corresponding to the brightness training data, at which the pixels can achieve local excitation brightness; The determination module is configured to determine driving voltages required for exciting the pixels of the display panel to the corrected gray scales; The output module is configured to output corresponding driving voltages to the pixels; The training module is configured to perform the following steps to obtain the brightness control model: a prediction step: inputting the brightness training data and the average image level training data corresponding to the brightness training data into a brightness control model to be trained to obtain predicted gray scales of each pixel output by the brightness control model to be trained at present; an optimization step: optimizing parameters of the brightness control model to be trained according to the target gray scales of the pixels and the predicted gray scales; The prediction step and the optimization step are iteratively performed until a preset condition is met.

6. A device for training a luminance control model, characterized by, The acquisition module is configured to acquire a training data set, wherein the training data set comprises a plurality of sets of training data, and each set of the training data comprises brightness training data of a display panel, average image level training data corresponding to the brightness, and target gray scales of each pixel corresponding to the brightness training data, at which the pixels can achieve local excitation brightness; The training module is configured to train a brightness control model to be trained by using the training data set to obtain a brightness control model; The training module is configured to perform the following steps to obtain the brightness control model: a prediction step: inputting the brightness training data and the average image level training data corresponding to the brightness training data into the brightness control model to be trained to obtain predicted gray scales of each pixel output by the brightness control model to be trained at present; an optimization step: optimizing parameters of the brightness control model to be trained according to the target gray scales of the pixels and the predicted gray scales; The prediction step and the optimization step are iteratively performed until a preset condition is met. The program or instructions stored on the readable storage medium are executed by the processor to implement the steps in the display compensation method of claim 1 or the steps in the training method of the brightness control model of any one of claims 2 to 4.

7. An electronic device, comprising: The program or instructions stored on the readable storage medium are executed by the processor to implement the steps in the display compensation method of claim 1 or the steps in the training method of the brightness control model of any one of claims 2 to 4.

8. A readable storage medium characterized by: ​ 9. A computer program product, characterised in that, Computer program product comprising computer instructions which, when executed by a processor, implement the steps of the display compensation method according to claim 1 or the steps of the training method of the luminance control model according to any one of claims 2 to 4.

Images