Model construction method, display screen uniformity correction method, device and equipment

Abstract

The invention belongs to the technical field of display screens, and mainly provides a model construction method, a display screen uniformity correction method, a display screen uniformity correction device and display screen uniformity correction equipment. Inputting the brightness information and the chromaticity information of the display area to be corrected into a pre-established display screen RGB gain prediction model to obtain an estimated RGB gain output by the display screen RGB gain prediction model, and performing brightness and chromaticity uniformity correction on the display area to be corrected based on the estimated RGB gain. The brightness and chromaticity uniformity correction of the to-be-corrected display area is realized by one key based on the brightness information and chromaticity information of the to-be-corrected display area and the pre-established display screen RGB gain prediction model, and the problems that a traditional display screen brightness and chromaticity uniformity correction method is low in correction efficiency and needs to consume relatively high manpower and time are solved; and frequent implementation is difficult.

Description

Technical Field

[0001] This application belongs to the technical field of display screens, and relates to a method for constructing a model, a method, device and equipment for correcting the uniformity of a display screen. Background Art

[0002] With the wide application of LED display screens in various indoor and outdoor scenarios, the requirements for their display effects are becoming increasingly strict. Since an LED display screen is usually composed of multiple boxes spliced together, and each box is obtained by splicing multiple lamp boards. After long-term operation, the brightness and chromaticity of each box or lamp board will decay due to differences in the usage environment and frequency. In addition, when some boxes or lamp boards fail or are damaged and need to be replaced with new ones, if the brightness and chromaticity of the newly replaced boxes or lamp boards are inconsistent with those of the original boxes or lamp boards, it will affect the uniformity and aesthetics of the overall display effect of the LED display screen. Therefore, it is necessary to correct the brightness and chromaticity uniformity of the LED display screen.

[0003] However, most of the traditional methods for correcting the brightness and chromaticity uniformity of display screens rely on complex external measurement devices and time-consuming debugging processes, which require high labor costs and time costs and are difficult to implement frequently. Summary of the Invention

[0004] This application provides a method for constructing a model, a method, device and equipment for correcting the uniformity of a display screen, which can solve the technical problems that the current method for correcting the brightness and chromaticity uniformity of an LED display screen has low correction efficiency, requires high labor costs and time costs, and is difficult to implement frequently.

[0005] In the first aspect of the embodiments of this application, a method for constructing an RGB gain prediction model of a display screen is provided. The construction method includes:

[0006] Obtaining the corresponding brightness information and chromaticity information respectively when the display screen displays a test image at multiple different RGB gains;

[0007] Based on the corresponding brightness information and chromaticity information respectively when the display screen displays the test image at the multiple different RGB gains, establishing the RGB gain prediction model of the display screen.

[0008] The method for constructing the RGB gain prediction model of the display screen provided by this application has at least the following beneficial effects: By obtaining the corresponding brightness information and chromaticity information when the display screen displays test images at multiple different RGB gains, and based on the brightness information and chromaticity information corresponding to the display screen when displaying the test images at the multiple different RGB gains, the RGB gain prediction model of the display screen is established, so that when it is necessary to perform uniformity correction of brightness and chromaticity on the to-be-corrected display area of the display screen, the uniformity correction of brightness and chromaticity of the to-be-corrected display area can be "completed in one key" based on this RGB gain prediction model of the display screen. Moreover, for display screens assembled by splicing display modules such as boxes or lamp boards manufactured using the same chip, the RGB gain prediction model of this display screen can be used for batch uniformity correction of brightness and chromaticity. Therefore, the efficiency of uniformity correction of brightness and chromaticity of the display screen can be greatly improved, solving the technical problems of low correction efficiency of the traditional methods for uniformity correction of brightness and chromaticity of display screens, high labor and time consumption, and difficulty in frequent implementation.

[0009] The second aspect of the embodiment of this application provides a method for uniformity correction of brightness and chromaticity of a display screen, including:

[0010] Obtain the brightness information and chromaticity information of the to-be-corrected display area of the display screen;

[0011] Input the brightness information and chromaticity information of the to-be-corrected display area into the pre-established RGB gain prediction model of the display screen to obtain the estimated RGB gain output by the RGB gain prediction model of the display screen;

[0012] Perform uniformity correction of brightness and chromaticity on the to-be-corrected display area based on the estimated RGB gain.

[0013] The method for correcting the brightness and chromaticity uniformity of the display screen provided by this application has at least the following beneficial effects: By obtaining the brightness information and chromaticity information of the display area to be corrected on the display screen, and inputting the brightness information and chromaticity information of the display area to be corrected into the pre-established display screen RGB gain prediction model, the estimated RGB gain output by the display screen RGB gain prediction model is obtained, and based on the estimated RGB gain, the brightness and chromaticity uniformity of the display area to be corrected is corrected, realizing the "one-key completion" of the brightness and chromaticity uniformity correction of the display area to be corrected based on the brightness information and chromaticity information of the display area to be corrected and the pre-established display screen RGB gain prediction model. In addition, based on the technical solution provided by this application, for display modules such as boxes or lamp boards manufactured using the same chip, when performing brightness and chromaticity uniformity correction, the same display screen RGB gain prediction model can be used to "one-key complete" the brightness and chromaticity uniformity correction of the display area to be corrected, without having to re-establish the display screen RGB gain prediction model. Therefore, for display screens spliced from display modules such as boxes or lamp boards manufactured using the same chip, the pre-established display screen RGB gain prediction model can be used for batch brightness and chromaticity uniformity correction, greatly improving the efficiency of the brightness and chromaticity uniformity correction of the display screen, and solving the technical problems of low correction efficiency, high manpower and time consumption, and difficulty in frequent implementation of the traditional brightness and chromaticity uniformity correction methods for display screens.

[0014] The third aspect of the embodiments of this application provides a device for constructing a display screen RGB gain prediction model, and the construction device includes:

[0015] A first acquisition unit, configured to acquire the brightness information and chromaticity information respectively corresponding when the display screen displays a test image at multiple different RGB gains;

[0016] A construction unit, configured to establish the display screen RGB gain prediction model based on the brightness information and chromaticity information respectively corresponding when the display screen displays the test image at the multiple different RGB gains.

[0017] The fourth aspect of the embodiments of this application provides a device for correcting the brightness and chromaticity uniformity of a display screen, and the device for correcting the brightness and chromaticity uniformity of the display screen includes:

[0018] A second acquisition unit, configured to acquire the brightness information and chromaticity information of the display area to be corrected on the display screen;

[0019] An estimation unit, configured to input the brightness information and chromaticity information of the display area to be corrected into the pre-established display screen RGB gain prediction model, and obtain the estimated RGB gain output by the display screen RGB gain prediction model;

[0020] A calibration unit for performing brightness and chromaticity uniformity calibration on the display area to be calibrated based on the predicted RGB gain.

[0021] A fifth aspect of the embodiments of the present application provides a device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps of the method for constructing a display screen RGB gain prediction model described in the first aspect above, and / or implements the steps of the method for calibrating the brightness and chromaticity uniformity of the display screen described in the second aspect above.

[0022] A sixth aspect of the embodiments of the present application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the steps of the method for constructing a display screen RGB gain prediction model described in the first aspect above, and / or implements the steps of the method for calibrating the brightness and chromaticity uniformity of the display screen described in the second aspect above.

[0023] A seventh aspect of the embodiments of the present application provides a computer program product including a computer program. When the computer program is executed by a processor, it implements the steps of the method for constructing a display screen RGB gain prediction model described in the first aspect above, and / or implements the steps of the method for calibrating the brightness and chromaticity uniformity of the display screen described in the second aspect above.

[0024] It should be noted that the beneficial effects of the embodiments provided in the above third aspect to seventh aspect can refer to the description of the beneficial effects of the embodiments provided in the first aspect and second aspect above, and will not be elaborated here. Description of the Drawings

[0025] Figure 1 It is a schematic flowchart of the implementation of the method for constructing a display screen RGB gain prediction model provided by the embodiments of the present application.

[0026] Figure 2 It is a schematic diagram of the splicing structure of the display screen provided by the embodiments of the present application.

[0027] Figure 3 It is a schematic flowchart of the implementation of the method for calibrating the brightness and chromaticity uniformity of the display screen provided by the embodiments of the present application.

[0028] Figure 4 It is a schematic diagram of a dialog box for adjusting RGB gain provided by the embodiments of the present application.

[0029] Figure 5 It is a schematic diagram of the structure of the device for constructing a display screen RGB gain prediction model provided by the embodiments of the present application.

[0030] Figure 6 Schematic structural diagram of the brightness and chromaticity uniformity correction device for the display screen provided by the embodiment of the present application.

[0031] Figure 7 Schematic structural diagram of the device provided by the embodiment of the present application. Detailed implementation manners

[0032] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0033] With the wide application of LED display screens in various indoor and outdoor scenarios, the requirements for their display effects are becoming increasingly strict. Since an LED display screen is usually composed of multiple boxes spliced together, and each box is obtained by splicing multiple lamp boards. After long-term operation, the brightness and chromaticity of each box or lamp board will decay due to differences in the usage environment and frequency. In addition, when some boxes or lamp boards fail or are damaged and need to be replaced with new boxes or lamp boards, and the brightness and chromaticity of the newly replaced boxes or lamp boards are inconsistent with those of the original boxes or lamp boards, it will affect the uniformity and aesthetics of the overall display effect of the LED display screen. Based on this, it is necessary to correct the brightness and chromaticity uniformity of the spliced LED display screen to avoid affecting the image quality and user experience.

[0034] Existing correction methods usually perform initial brightness and chromaticity calibration on the entire screen during the installation and commissioning phase to ensure that the screen reaches ideal brightness consistency and chromaticity accuracy in the initial stage. However, after the LED display screen has been in use for a period of time, due to reasons such as light decay aging and module replacement, the uniformity of the display effect often decreases. Without effective secondary correction means, it will affect the visual performance of the displayed content, especially in application scenarios with high definition and high-definition color reproduction. However, most traditional methods for correcting the brightness and chromaticity of display screens rely on complex external measurement devices and time-consuming debugging processes, which require high labor costs and time costs and are difficult to implement frequently.

[0035] In view of the above problems, the embodiment of the present application provides a method for constructing a display screen RGB gain prediction model, which is used to construct a display screen RGB gain prediction model. The method for constructing the display screen RGB gain prediction model can be executed by a construction device of the display screen RGB gain prediction model configured on devices such as a computer or a server.

[0036] As Figure 1 shown, the method for constructing the display screen RGB gain prediction model provided by the embodiment of the present application can be implemented in the following manner of step 101 to step 102.

[0037] Step 101: Obtain brightness information and chromaticity information corresponding to a display screen displaying a test image at multiple different RGB gains.

[0038] It should be noted that the display used in establishing the display RGB gain prediction model can be a display that has completed brightness and color uniformity correction, or a portion of the display can be a normal display area. The normal display area refers to an area where both brightness uniformity and color uniformity meet uniformity requirements, that is, an area that has completed brightness uniformity and color uniformity correction.

[0039] In the above step 101, obtaining the brightness information and chromaticity information corresponding to the display screen when displaying the test image at multiple different RGB gains may refer to: obtaining the brightness information and chromaticity information corresponding to the normal display area of the display screen when displaying the test image at multiple different RGB gains.

[0040] Specifically, in Figure 2 The display screen shown is made up of 16 cabinets, numbered 1 to 16, each controlled by one or more receiving cards. During the application process, it is possible that one or more cabinets may be replaced, which is more common in rental scenarios. Although each cabinet has pixel-level correction, there may still be problems such as inconsistent light attenuation between new and old cabinets, and between cabinets, which may cause brightness inconsistencies and affect the overall large-screen viewing effect after the splicing is completed. Figure 2 In the display screen shown, the cabinet 15 is a replaced cabinet or a cabinet with inconsistent light attenuation. The display area corresponding to the cabinet 15 is the display area to be corrected in the embodiment of the present application, and the remaining display areas are the normal display areas in the embodiment of the present application.

[0041] Step 102 : establishing a display screen RGB gain prediction model based on the brightness information and chromaticity information corresponding to the display screen when displaying the test image at multiple different RGB gains.

[0042] In the embodiments of the present application, by obtaining the corresponding brightness information and chromaticity information when the display screen displays a test image at multiple different RGB gains, and based on the corresponding brightness information and chromaticity information when the display screen displays the test image at multiple different RGB gains, an RGB gain prediction model of the display screen is established, so that when it is necessary to perform uniformity correction of brightness and chromaticity on the to-be-corrected display area of the display screen, the uniformity correction of brightness and chromaticity of the to-be-corrected display area can be "completed in one key" based on the RGB gain prediction model of the display screen. Moreover, for a display screen assembled by splicing display modules such as boxes or lamp boards manufactured using the same chip, the RGB gain prediction model of the display screen can be used to perform batch uniformity correction of brightness and chromaticity. Therefore, the efficiency of uniformity correction of brightness and chromaticity of the display screen can be greatly improved, and the technical problems of low correction efficiency, high labor and time consumption, and difficulty in frequent implementation of the traditional methods for uniformity correction of brightness and chromaticity of the display screen are solved.

[0043] In an embodiment of the present application, in the above step 101, when obtaining the corresponding brightness information and chromaticity information when the display screen displays a test image at multiple different RGB gains, it can be implemented based on the following steps A01 to A02.

[0044] A01, control the display screen to display a test image, and record the current RGB gain of the display screen, as well as the corresponding brightness information and chromaticity information of the display screen.

[0045] A02, repeat the adjustment of the current RGB gain of the display screen multiple times, and record the corresponding brightness information and chromaticity information when the display screen displays the test image at the adjusted RGB gain, so as to obtain the corresponding brightness information and chromaticity information when the display screen displays the test image at multiple different RGB gains.

[0046] Similarly, the above step A01 may refer to: controlling the normal display area of the display screen to display a test image, and recording the current RGB gain of the display screen, as well as the corresponding brightness information and chromaticity information of the normal display area of the display screen to obtain the normal display area of the display screen.

[0047] In an embodiment of the present application, the test image in the above step 101 and the above step A01 may be a pure white test image. Moreover, when the test image is a pure white test image, the above step A01 may refer to: controlling the display screen to display a pure white test image, and recording the current RGB gain when the normal display area of the display screen displays the pure white test image, as well as the corresponding brightness information and chromaticity information of the normal display area of the display screen.

[0048] In an embodiment of the present application, when the test image displayed in the normal display area is a pure white test image, the repeated adjustment of the current RGB gain of the display screen in step A02 above may refer to: when adjusting the current RGB gain of the display screen each time, adjusting one of the R gain, G gain, and B gain in the RGB gain of the normal display area. That is, fixing two of the gains unchanged and only adjusting one of the gains to test the influence degree of each gain (R gain, G gain, and B gain) on brightness and chromaticity.

[0049] Specifically, when adjusting the R gain in the RGB gain, the G gain and B gain remain unchanged; when adjusting the G gain in the RGB gain, the R gain and B gain remain unchanged; when adjusting the B gain in the RGB gain, the R gain and G gain remain unchanged.

[0050] In an embodiment of the present application, the RGB gain is adjusted by a fixed step each time, and the step size can be 1-10 to obtain sufficient brightness information and chromaticity information corresponding to the RGB gain.

[0051] In the embodiment of the present application, during the establishment process of the display screen RGB gain prediction model, the normal display area of the display screen can be controlled to display a pure white test image, and the current RGB gain corresponding to the normal display area is recorded, as well as the brightness information and chromaticity information corresponding to the normal display area when displaying this pure white test image at the current RGB gain. Then, the current RGB gain of the normal display area is adjusted repeatedly for multiple times, and the brightness information and chromaticity information corresponding to the normal display area when displaying the pure white test image at the adjusted RGB gain are recorded. Furthermore, the brightness information and chromaticity information corresponding to the normal display area when displaying the pure white test image at multiple different RGB gains are obtained (including the brightness information and chromaticity information corresponding before adjusting the RGB gain, that is, the brightness information and chromaticity information corresponding when displaying the pure white test image at the current RGB gain).

[0052] In an embodiment of the present application, the test image in the above steps can also be a pure red test image, a pure green test image, and a pure blue test image. And when the test image is a pure red test image, a pure green test image, and a pure blue test image, step A01 above may refer to: controlling the display screen to display a pure red test image, a pure green test image, and a pure blue test image respectively, and recording the current RGB gain of the normal display area of the display screen when displaying the pure red test image, the pure green test image, and the pure blue test image, as well as the brightness information and chromaticity information corresponding to the normal display area of the display screen. Step A02, repeatedly adjusting the current RGB gain of the display screen for multiple times, may refer to: when adjusting the current RGB gain of the display screen each time, adjusting the gain of the color corresponding to the color of the test image displayed on the display screen in the current RGB gain of the display screen.

[0053] In an embodiment of the present application, after obtaining the brightness information and chromaticity information respectively corresponding to the display screen when displaying test images under multiple different RGB gains, the above-mentioned step 102 can be executed to obtain the RGB gain prediction model of the display screen.

[0054] In an embodiment of the present application, step 102 can be implemented based on the following manner from step B01 to step B02.

[0055] Step B01: Group the brightness information and chromaticity information respectively corresponding to the display screen when displaying test images under multiple different RGB gains according to a preset ratio to obtain a training data set and a validation data set.

[0056] Step B02: Use the training data set for model fitting, and use the validation data set to verify the initially obtained RGB gain prediction model after fitting. When the change rate of the preset loss function is less than the preset change rate threshold, determine the initially obtained RGB gain prediction model as the RGB gain prediction model of the display screen.

[0057] For example, use 80% of the brightness information and chromaticity information under different RGB gains as the training data set for model training and fitting, and use 20% of the brightness information and chromaticity information under different RGB gains as the validation data set for verifying the fitting effect of the model.

[0058] Among them, during the establishment process of the RGB gain prediction model of the display screen, the parameters of the model can be adjusted based on the loss function loss = 1 / 2 * (predict - true) 2 where true is the brightness information and chromaticity information input into the initially obtained RGB gain prediction model, that is, the true value, and predict is the brightness information and chromaticity information corresponding to the test image when displayed under the RGB gain predicted by the initially obtained RGB gain prediction model based on the true value true for the normal display area (after inputting the true value true into the initially obtained RGB gain prediction model, the RGB gain output by the initially obtained RGB gain prediction model). When the change rate of the loss function loss is less than the preset change rate threshold during the model training and verification process, it indicates that the RGB gain prediction model of the display screen has been trained, and the finally trained initially obtained RGB gain prediction model can be determined as the RGB gain prediction model of the display screen.

[0059] In an embodiment of the present application, when the test image is a pure white test image, the RGB gain prediction model of the display screen [R, G, B] = [R w , B w , Gw *X + B. Wherein, R w , G w and B w are weight coefficient matrices, X is a feature matrix [x, y, lv], where (x, y) is chromaticity information and lv is luminance information, and B is a bias parameter.

[0060] In an embodiment of the present application, based on the luminance information and chromaticity information respectively corresponding when a pure white test image is displayed at multiple different RGB gains in the normal display area of the display screen, a display screen RGB gain prediction model [R, G, B] = [R w , B w , G w *X + B, the parameters of the display screen RGB gain prediction model can be determined based on the above steps B01 to

[0061] Step B02, that is, the weight coefficient matrices R w , G w and B w and the bias parameter B.

[0062] In an embodiment of the present application, after training the display screen RGB gain prediction model, when a true value true' of a certain luminance information and chromaticity information is input to the display screen RGB gain prediction model, the display screen RGB gain prediction model will output an estimated RGB gain. When a pure white test image is displayed at this estimated RGB gain in the normal display area, the deviation (predict' - true') / true' * 100% between the corresponding luminance information and chromaticity information predict' and the true value true' of the luminance information and chromaticity information input to the display screen RGB gain prediction model will be within a preset range, that is, a color difference range and a luminance difference range that are difficult for the human eye to perceive. Specifically, the deviation of the chromaticity information is within 0.3%, and the deviation of the luminance information is within 2%.

[0063] In order to further improve the correction effect of luminance and chromaticity uniformity, in an embodiment of the present application, the test image may include a pure red test image, a pure green test image, and a pure blue test image; correspondingly, the display screen RGB gain prediction model may include: a display screen R gain prediction model, a display screen G gain prediction model, and a display screen B gain prediction model. Among them, the display screen R gain prediction model, the display screen G gain prediction model, and the display screen B gain prediction model can be implemented based on the following steps C01 to step C03.

[0064] Step C01: Control the normal display area of the display screen to display a pure red test image, and record the current R gain corresponding to the normal display area, as well as the brightness information and chromaticity information corresponding to the pure red test image displayed by the normal display area at the current R gain; Repeat adjusting the current R gain of the normal display area multiple times, and record the brightness information and chromaticity information corresponding to the pure red test image displayed by the normal display area at the adjusted R gain, so as to obtain the brightness information and chromaticity information corresponding to the pure red test image displayed by the normal display area at multiple different R gains; Based on the brightness information and chromaticity information corresponding to the pure red test image displayed by the normal display area at multiple different R gains, establish a display screen R gain prediction model R = R r *X r +R b 。

[0065] Step C02: Control the normal display area of the display screen to display a pure green test image, and record the current G gain corresponding to the normal display area, as well as the brightness information and chromaticity information corresponding to the pure green test image displayed by the normal display area at the current G gain; Repeat adjusting the current G gain of the normal display area multiple times, and record the brightness information and chromaticity information corresponding to the pure green test image displayed by the normal display area at the adjusted G gain, so as to obtain the brightness information and chromaticity information corresponding to the pure green test image displayed by the normal display area at multiple different G gains; Based on the brightness information and chromaticity information corresponding to the pure green test image displayed by the normal display area at multiple different G gains, establish a display screen G gain prediction model G = G g *X g +G b 。

[0066] Step C03: Control the normal display area of the display screen to display a pure blue test image, and record the current B gain corresponding to the normal display area, as well as the brightness information and chromaticity information corresponding to the pure blue test image displayed by the normal display area at the current B gain; Repeat adjusting the current B gain of the normal display area multiple times, and record the brightness information and chromaticity information corresponding to the pure blue test image displayed by the normal display area at the adjusted B gain, so as to obtain the brightness information and chromaticity information corresponding to the pure blue test image displayed by the normal display area at multiple different B gains; Based on the brightness information and chromaticity information corresponding to the pure blue test image displayed by the normal display area at multiple different B gains, establish a display screen B gain prediction model B = B b ’*X b +B b 。

[0067] Among them, R r 、G g and B b ’ are weight coefficient matrices, X r 、Xg and X b is a feature matrix, specifically [x, y, lv], where (x, y) is chromaticity information and lv is luminance information, R b , G b and B b are bias parameters.

[0068] The specific implementation manners of the above steps C01 to C03 can refer to the descriptions of the foregoing steps A01 to A02 and steps B01 to B02, and will not be elaborated here.

[0069] It should be noted that when the normal display area displays single-channel images such as a pure red test image, a pure green test image, and a pure blue test image, the measurement of the luminance information and chromaticity information based on red light, blue light, and green light will be more accurate than the measurement of the luminance information and chromaticity information of the corresponding white light (mixed light) when displaying a pure white test image. Therefore, the established display screen R gain prediction model, display screen G gain prediction model, and display screen B gain prediction model can accurately predict the RGB gain, and can ensure that the luminance uniformity of each color channel can be independently and accurately corrected. Therefore, when using the display screen R gain prediction model, display screen G gain prediction model, and display screen B gain prediction model to perform uniformity correction on the luminance and chromaticity of the display area to be corrected, a better correction effect can be achieved.

[0070] Based on the display screen RGB gain prediction models established in the above various embodiments, the embodiment of the present application provides a method for correcting the luminance and chromaticity uniformity of a display screen. This method for correcting the luminance and chromaticity uniformity can be executed by a device for correcting the luminance and chromaticity uniformity of a display screen configured on a computer, a server, and other devices.

[0071] As Figure 3 shown, the method for correcting the luminance and chromaticity uniformity of the display screen provided by the embodiment of the present application can be implemented in the following manner of steps 201 to 203.

[0072] Step 201, obtain the luminance information and chromaticity information of the display area to be corrected of the display screen.

[0073] Since the acquisition of luminance information and chrominance information is usually performed on a certain image area, rather than on a single pixel of the image, in order to ensure the accuracy of the acquisition of luminance information and chrominance information, it is necessary to ensure that the image area used to obtain the luminance information and chrominance information is a pure-color image area. Therefore, in the embodiments of the present application, the above step 201 may be to obtain the luminance information and chrominance information of the area where the pure-color image (such as a pure-white test image, a pure-pink image, a pure-violet image, a pure-yellow image, etc.) is displayed in all or part of the area to be corrected on the display screen, and use the luminance information and chrominance information of the area where the pure-color image is displayed as the luminance information and chrominance information of the area to be corrected on the display screen.

[0074] To facilitate the acquisition of the luminance information and chrominance information of the area to be corrected on the display screen, in one embodiment, the display screen may be controlled to display a pure-white test image, and the luminance information and chrominance information of the area to be corrected (i.e., the area to be corrected) on the display screen at this time can be obtained under the pure-white test image. It can be understood that the area to be corrected on the display screen can also be controlled to display only the pure-white test image, and the luminance information and chrominance information of the area to be corrected at this time can be obtained.

[0075] In one embodiment, the display screen can also be controlled to display a pure-red test image, a pure-green test image, and a pure-blue test image respectively, and the luminance information and chrominance information of the area to be corrected on the display screen when the display screen displays the pure-red test image, the pure-green test image, and the pure-blue test image can be obtained respectively. Similarly, the area to be corrected on the display screen can also be controlled to display the pure-red test image, the pure-green test image, and the pure-blue test image respectively, and the luminance information and chrominance information of the area to be corrected when each color test image is displayed can be obtained.

[0076] Step 202: Input the luminance information and chrominance information of the area to be corrected into the pre-established display screen RGB gain prediction model to obtain the predicted RGB gain output by the display screen RGB gain prediction model.

[0077] In the embodiments of the present application, when the luminance information and chrominance information of the area to be corrected are the luminance information and chrominance information obtained when the area to be corrected displays a pure-color image other than the pure-red test image, the pure-green test image, and the pure-blue test image (such as an image corresponding to mixed light such as a pure-white test image, a pure-pink image, etc.), the above step 202 only needs to be executed once. That is, the luminance information and chrominance information obtained when the area to be corrected displays the pure-white test image are directly input into the pre-established display screen RGB gain prediction model to obtain the predicted RGB gain output by the display screen RGB gain prediction model.

[0078] When the brightness information and chromaticity information of the display area to be calibrated include the brightness information and chromaticity information obtained respectively when the display area to be calibrated displays pure red test images, pure green test images, and pure blue test images, the above step 202 needs to be executed three times. In this case, the display screen RGB gain prediction model includes: a display screen R gain prediction model, a display screen G gain prediction model, and a display screen B gain prediction model; the estimated RGB gain output by the display screen RGB gain prediction model includes an estimated R gain, an estimated G gain, and an estimated B gain.

[0079] That is, input the brightness information and chromaticity information when the display area to be calibrated displays pure red test images into the pre-established display screen R gain prediction model to obtain the estimated R gain output by the display screen R gain prediction model; input the brightness information and chromaticity information when the display area to be calibrated displays pure green test images into the pre-established display screen G gain prediction model to obtain the estimated G gain output by the display screen G gain prediction model; input the brightness information and chromaticity information when the display area to be calibrated displays pure blue test images into the pre-established display screen B gain prediction model to obtain the estimated B gain output by the display screen B gain prediction model.

[0080] Step 203, perform brightness and chromaticity uniformity calibration on the display area to be calibrated based on the estimated RGB gain.

[0081] By adjusting the gain values (RGB gain) of the three color channels of red (R), green (G), and blue (B) in the image, the brightness and chromaticity of the image can be changed. Among them, increasing the gain value will make the image brighter, while decreasing the gain value will make the image darker. If a certain color channel in the image is too dark or too bright, the color deviation can be corrected by adjusting the gain value of the corresponding channel to restore the image to a more accurate color representation.

[0082] In an embodiment of the present application, the above step 203 may refer to adjusting the RGB gain of the display area to be calibrated to the estimated RGB gain obtained in step 202 and saving the adjusted RGB gain to achieve brightness and chromaticity uniformity calibration of the display area to be calibrated.

[0083] For example, as Figure 4As shown in the figure, it is a dialog box for adjusting the RGB gain provided by the embodiment of the present application. By sliding the slider in the dialog box or changing the value in the dialog box, the RGB gain of the display area to be corrected can be adjusted to the predicted RGB gain obtained in step 202. By saving the adjusted RGB gain, the brightness and chromaticity uniformity correction of the display area to be corrected can be completed. Based on this, the present application realizes the brightness and chromaticity uniformity correction of the display area to be corrected "in one key" based on the brightness information and chromaticity information of the display area to be corrected and the pre-established RGB gain prediction model of the display screen, greatly improving the efficiency of the brightness and chromaticity uniformity correction of the display screen, and solving the technical problems of the low correction efficiency of the traditional brightness and chromaticity uniformity correction method of the display screen, the need to consume a high amount of manpower and time, and the difficulty in frequent implementation.

[0084] Among them, when the predicted RGB gain is the RGB gain predicted based on the brightness information and chromaticity information when the display area to be corrected displays a pure color image other than the pure red test image, pure green test image, and pure blue test image, the above step 203 only needs to be executed once. That is, directly adjust the RGB gain of the display area to be corrected to the predicted RGB gain.

[0085] When the predicted RGB gain includes the predicted R gain, predicted G gain, and predicted B gain, the above step 103 needs to be executed three times. That is, after inputting the brightness information and chromaticity information when the display area to be corrected displays a pure red test image into the pre-established R gain prediction model of the display screen and obtaining the predicted R gain output by the R gain prediction model of the display screen, adjust the R gain in the RGB gain of the display area to be corrected to the predicted R gain; after inputting the brightness information and chromaticity information when the display area to be corrected displays a pure green test image into the pre-established G gain prediction model of the display screen and obtaining the predicted G gain output by the G gain prediction model of the display screen, adjust the G gain in the RGB gain of the display area to be corrected to the predicted G gain; after inputting the brightness information and chromaticity information when the display area to be corrected displays a pure blue test image into the pre-established B gain prediction model of the display screen and obtaining the predicted B gain output by the B gain prediction model of the display screen, adjust the B gain in the RGB gain of the display area to be corrected to the predicted B gain. By separately saving the adjusted R gain, G gain, and B gain, the brightness and chromaticity uniformity correction of the display area to be corrected can be completed.

[0086] In the embodiments of the present application, when a test image is displayed in the display area to be corrected of the display screen, the brightness information and chromaticity information of the display area to be corrected are obtained, and the brightness information and chromaticity information of the display area to be corrected are input into a pre-established display screen RGB gain prediction model, and the predicted RGB gain output by the display screen RGB gain prediction model is obtained. Based on the predicted RGB gain, the brightness and chromaticity uniformity correction of the display area to be corrected is performed, realizing the brightness and chromaticity uniformity correction of the display area to be corrected with "one key" based on the brightness information and chromaticity information of the display area to be corrected and the pre-established display screen RGB gain prediction model. In addition, based on the technical solution provided by the present application, for display modules such as boxes or lamp boards manufactured using the same chip, when performing brightness and chromaticity uniformity correction, the same display screen RGB gain prediction model can be used to "one key" complete the brightness and chromaticity uniformity correction of the display area to be corrected, without the need to re-establish the display screen RGB gain prediction model. Therefore, for display screens assembled by splicing display modules such as boxes or lamp boards manufactured using the same chip, the pre-established display screen RGB gain prediction model can be used to perform batch brightness and chromaticity uniformity correction. Therefore, the efficiency of the brightness and chromaticity uniformity correction of the display screen can be greatly improved, solving the technical problems of low correction efficiency, high labor and time consumption, and difficulty in frequent implementation in the traditional brightness and chromaticity uniformity correction methods of display screens.

[0087] It should be noted that the above-mentioned pre-established display screen RGB gain prediction model is the display screen RGB gain prediction model established for the embodiments shown above. Figure 1

[0088] In an embodiment of the present application, in order to improve the accuracy of the display screen RGB gain prediction model and the correction effect of the brightness and chromaticity uniformity correction of the display area to be corrected, when obtaining the brightness information and chromaticity information, a high-precision luminance meter and chrominance meter can be used to collect the brightness and chromaticity.

[0089] For example, when obtaining the brightness information and chromaticity information of the display area to be corrected, a luminance meter and a chrominance meter can be used to measure the brightness and chromaticity of the display area to be corrected, and the brightness information and chromaticity information of the display area to be corrected are obtained.

[0090] In an embodiment of the present application, in addition to using a luminance meter and a chrominance meter to collect the brightness information and chromaticity information of the display area, an image displayed in the display area can also be photographed by a high-precision device, and the brightness and chromaticity of the photographed image are identified to obtain the brightness information and chromaticity information of the display area.

[0091] ​This application does not limit the acquisition methods of luminance information and chrominance information, as long as the luminance information and chrominance information of the display area (for example, the normal display area and the display area to be corrected) can be collected.

[0092] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence. In some embodiments of this application, certain steps can be performed in other orders as needed.

[0093] Such as Figure 5 As shown in the figure, an embodiment of this application further provides a device for constructing a display screen RGB gain prediction model. The construction device may include: a first acquisition unit 501 and a construction unit 502. Among them, the first acquisition unit 501 is used to acquire the corresponding luminance information and chrominance information respectively when the display screen displays a test image at multiple different RGB gains; the construction unit 502 is used to establish a display screen RGB gain prediction model based on the corresponding luminance information and chrominance information when the display screen displays a test image at multiple different RGB gains.

[0094] It should be noted that, for the convenience and conciseness of description, the specific working process of the device 500 for constructing the display screen RGB gain prediction model described above can refer to the corresponding process of the method for constructing the display screen RGB gain prediction model described above, and will not be elaborated here. Each unit of the device 500 for constructing the display screen RGB gain prediction model can respectively execute the corresponding steps in the method embodiment for constructing the display screen RGB gain prediction model described above, so each unit will not be elaborated here. For details, please refer to the description of the corresponding steps above.

[0095] Such as Figure 6 As shown in the figure, an embodiment of this application further provides a device 600 for correcting the luminance and chrominance uniformity of a display screen. The device for correcting the luminance and chrominance uniformity of the display screen may include a second acquisition unit 601, an estimation unit 602, and a correction unit 603. Among them, the second acquisition unit 601 is used to acquire the luminance information and chrominance information of the display area to be corrected of the display screen; the estimation unit 602 is used to input the luminance information and chrominance information of the display area to be corrected into a pre-established display screen RGB gain prediction model to obtain the estimated RGB gain output by the display screen RGB gain prediction model; the correction unit 603 is used to perform luminance and chrominance uniformity correction on the display area to be corrected based on the estimated RGB gain.

[0096] It should be noted that, for the convenience and brevity of description, the specific working process of the display brightness and chromaticity uniformity correction device 600 described above can refer to the corresponding process of the display brightness and chromaticity uniformity correction method described above, and will not be elaborated here. Each unit of the display brightness and chromaticity uniformity correction device 600 can respectively execute the corresponding steps in the foregoing method embodiments, so the units will not be elaborated here. For details, please refer to the description of the corresponding steps above.

[0097] As Figure 7 shown, an embodiment of the present application also provides a device. The device may include: a processor 70, a memory 71, and a computer program 72 stored in the memory 71 and executable on the processor 70. When the processor 70 executes the computer program 72, it implements the steps of the foregoing method for constructing the RGB gain prediction model of each display screen, or the steps of the foregoing method for correcting the brightness and chromaticity uniformity of each display screen. For example, Figure 1 the steps 101 to 102 shown, or, Figure 3 the steps 201 to 203 shown.

[0098] The foregoing computer program may be divided into one or more units, and the foregoing one or more units are stored in the foregoing memory 71 and executed by the foregoing processor 70 to complete the present application. The foregoing one or more units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the process of the foregoing computer program for executing the method for constructing the RGB gain prediction model of each display screen in the device, or the process of the foregoing method for correcting the brightness and chromaticity uniformity of each display screen. For example, the foregoing computer program may be divided into Figure 5 the first acquisition unit and the construction unit shown. The first acquisition unit is used to acquire the brightness information and chromaticity information respectively corresponding to the display screen when displaying a test image at multiple different RGB gains; the construction unit is used to establish an RGB gain prediction model of the display screen based on the brightness information and chromaticity information respectively corresponding to the display screen when displaying a test image at multiple different RGB gains.

[0099] An embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a central processing module, it implements the steps of the method for constructing the RGB gain prediction model of the display screen described in any of the foregoing embodiments, or the steps of the method for correcting the brightness and chromaticity uniformity of the display screen.

[0100] The embodiments of the present application also provide a computer program product including instructions. When it runs on a computer, it causes the computer to execute the steps of the method for constructing a display screen RGB gain prediction model or the steps of the method for correcting the brightness and chromaticity uniformity of a display screen described in any of the above embodiments.

[0101] In the above embodiments, the descriptions of the respective embodiments have their own focuses. For parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0102] Those of ordinary skill in the art can realize that the steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0103] In the embodiments provided by the present application, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of each component is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple components can be combined or integrated into another system, or a feature can be ignored or not executed.

[0104] If it is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above method embodiments of the present application, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0105] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for constructing an RGB gain prediction model of a display screen, characterized in that The construction method includes: Obtaining the corresponding brightness information and chromaticity information respectively when the display screen displays a test image under multiple different RGB gains; Based on the brightness information and chromaticity information corresponding respectively when the display screen displays the test image under the multiple different RGB gains, establishing the RGB gain prediction model of the display screen.

2. The method for constructing the display screen RGB gain prediction model according to claim 1, characterized in that The obtaining of the corresponding brightness information and chromaticity information respectively when the display screen displays a test image under multiple different RGB gains includes: Controlling the display screen to display a test image, and recording the current RGB gain of the display screen, as well as the corresponding brightness information and chromaticity information of the display screen; Repeating the adjustment of the current RGB gain of the display screen multiple times, and recording the corresponding brightness information and chromaticity information when the display screen displays the test image under the adjusted RGB gain, so as to obtain the corresponding brightness information and chromaticity information respectively when the display screen displays the test image under multiple different RGB gains.

3. The construction method of the RGB gain prediction model of the display screen according to claim 2, wherein When the test image is a pure white test image, the repeating the adjustment of the current RGB gain of the display screen multiple times includes: when adjusting the current RGB gain of the display screen each time, adjusting one of the R gain, G gain and B gain in the current RGB gain of the display screen; When the test image includes a pure red test image, a pure green test image and a pure blue test image, the repeating the adjustment of the current RGB gain of the display screen multiple times includes: when adjusting the current RGB gain of the display screen each time, adjusting the gain of the color corresponding to the color of the test image displayed by the display screen in the current RGB gain of the display screen.

4. The method for constructing the RGB gain prediction model of the display screen according to claim 3, wherein, When the test image includes a pure red test image, a pure green test image and a pure blue test image, the RGB gain prediction model of the display screen includes: an R gain prediction model of the display screen, a G gain prediction model of the display screen, and a B gain prediction model of the display screen; The establishing of the RGB gain prediction model of the display screen based on the brightness information and chromaticity information corresponding respectively when the display screen displays the test image under the multiple different RGB gains includes: Based on the brightness information and chromaticity information corresponding respectively when the display screen displays the pure red test image under multiple different R gains, establishing the R gain prediction model of the display screen; Based on the brightness information and chromaticity information corresponding respectively when the display screen displays the pure green test image under multiple different G gains, establishing the G gain prediction model of the display screen; Based on the brightness information and chromaticity information corresponding respectively when the display screen displays the pure blue test image under multiple different B gains, establishing the B gain prediction model of the display screen.

5. The method for constructing the display screen RGB gain prediction model according to any one of claims 1-4, characterized in that, The establishing of the RGB gain prediction model of the display screen based on the brightness information and chromaticity information corresponding respectively when the display screen displays the test image under the multiple different RGB gains includes: Group the brightness information and chromaticity information corresponding to the test image displayed by the display screen at multiple different RGB gains according to a preset ratio to obtain a training data set and a validation data set; Use the training data set for model fitting, and use the validation data set to verify the initially obtained RGB gain prediction model. When the change rate of a preset loss function is less than a preset change rate threshold, determine the initially obtained RGB gain prediction model as the RGB gain prediction model of the display screen.

6. A method for correcting the brightness and chromaticity uniformity of a display screen, characterized in that, The method for correcting the brightness and chromaticity uniformity of the display screen includes: Obtain the brightness information and chromaticity information of the display area to be corrected of the display screen; Input the brightness information and chromaticity information of the display area to be corrected into a pre-established RGB gain prediction model of the display screen to obtain the estimated RGB gain output by the RGB gain prediction model of the display screen; Based on the estimated RGB gain, perform brightness and chromaticity uniformity correction on the display area to be corrected.

7. The method for correcting the brightness and chromaticity uniformity of the display screen according to claim 6, characterized in that, The performing brightness and chromaticity uniformity correction on the display area to be corrected based on the estimated RGB gain includes: Adjust the RGB gain of the display area to be corrected to the estimated RGB gain, and save the adjusted RGB gain.

8. An apparatus for constructing an RGB gain prediction model of a display screen, characterized in that, The construction device includes: A first acquisition unit, configured to acquire the brightness information and chromaticity information respectively corresponding to the test image displayed by the display screen at multiple different RGB gains; A construction unit, configured to establish the RGB gain prediction model of the display screen based on the brightness information and chromaticity information respectively corresponding to the test image displayed by the display screen at the multiple different RGB gains.

9. A brightness and chromaticity uniformity correction device for a display screen, characterized in that, The device for correcting the brightness and chromaticity uniformity of the display screen includes: A second acquisition unit, configured to acquire the brightness information and chromaticity information of the display area to be corrected of the display screen; An estimation unit, configured to input the brightness information and chromaticity information of the display area to be corrected into a pre-established RGB gain prediction model of the display screen to obtain the estimated RGB gain output by the RGB gain prediction model of the display screen; A correction unit, configured to perform brightness and chromaticity uniformity correction on the display area to be corrected based on the estimated RGB gain.

10. A device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps of the method for constructing the RGB gain prediction model of the display screen according to any one of claims 1-5, and / or, when the computer program is executed by the processor, it implements the steps of the method for correcting the brightness and chromaticity uniformity of the display screen according to any one of claims 6-7.

Images