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

Abstract

The application belongs to the technical field of display screens and mainly provides a model construction method, a display screen uniformity correction method, a device and equipment, wherein the display screen uniformity correction method obtains luminance information and chrominance information of a display area to be corrected, inputs the luminance information and the chrominance information of the display area to be corrected into a display screen RGB gain prediction model established in advance, obtains estimated RGB gain output by the display screen RGB gain prediction model, and performs luminance and chrominance uniformity correction on the display area to be corrected based on the estimated RGB gain, so that the luminance information and the chrominance information of the display area to be corrected and the display screen RGB gain prediction model established in advance are used to "one-key complete" the luminance and chrominance uniformity correction on the display area to be corrected, and the technical problem that the traditional display screen luminance and chrominance uniformity correction method has low correction efficiency, needs to consume high manpower and time, and is difficult to implement frequently is solved.

Description

Technical Field

[0001] This application belongs to the field of display screen technology, and relates to a model construction method, a display screen uniformity correction method, apparatus and equipment. Background Technology

[0002] With the widespread application of LED displays in various indoor and outdoor scenarios, the requirements for their display effects are becoming increasingly stringent. Since LED displays are typically composed of multiple cabinets, each cabinet consisting of multiple light panels, the brightness and chromaticity of each cabinet or light panel will attenuate over time due to differences in the operating environment and frequency. Furthermore, when some cabinets or light panels malfunction or are damaged, requiring replacement, and the brightness and chromaticity of the newly replaced cabinets or light panels differ from the original ones, it will affect the uniformity and aesthetics of the overall LED display. Therefore, brightness and chromaticity uniformity calibration of LED displays is necessary.

[0003] However, traditional methods for correcting the uniformity of brightness and color of displays mostly rely on complex external measurement equipment and time-consuming debugging processes, which require high manpower and time costs and are difficult to implement frequently. Summary of the Invention

[0004] This application provides a model construction method, a display screen uniformity correction method, apparatus, and device, which can solve the technical problems of low correction efficiency, high labor and time costs, and difficulty in frequent implementation of current LED display screen brightness and color uniformity correction methods.

[0005] The first aspect of this application provides a method for constructing an RGB gain prediction model for a display screen, the method comprising:

[0006] Acquire the brightness and chromaticity information of the display screen when displaying test images under multiple different RGB gains;

[0007] Based on the brightness and chromaticity information corresponding to the test image displayed on the display screen under multiple different RGB gains, an RGB gain prediction model for the display screen is established.

[0008] The method for constructing the RGB gain prediction model for a display screen provided in this application has at least the following beneficial effects: This application obtains the brightness and chromaticity information corresponding to the display screen when displaying test images under multiple different RGB gains, and establishes the RGB gain prediction model for the display screen based on the brightness and chromaticity information corresponding to the display screen when displaying the test images under multiple different RGB gains. This allows for "one-click" completion of brightness and chromaticity uniformity correction of the display area to be corrected based on the RGB gain prediction model. Furthermore, for display screens spliced ​​together using display modules such as cabinets or lamp boards manufactured with the same chip, the RGB gain prediction model can be used for batch brightness and chromaticity uniformity correction. Therefore, it can greatly improve the efficiency of brightness and chromaticity uniformity correction of the display screen, solving the technical problems of low correction efficiency, high manpower and time consumption, and difficulty in frequent implementation of traditional brightness and chromaticity uniformity correction methods.

[0009] A second aspect of this application provides a method for correcting the brightness and color uniformity of a display screen, comprising:

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

[0011] The brightness and chromaticity information of the display area to be corrected are input into a pre-established RGB gain prediction model for the display screen to obtain the estimated RGB gain output by the RGB gain prediction model for the display screen.

[0012] The brightness and color uniformity of the display area to be corrected are corrected based on the estimated RGB gain.

[0013] The brightness and chromaticity uniformity correction method for a display screen provided in this application has at least the following beneficial effects: This application obtains the brightness and chromaticity information of the display area to be corrected, inputs the brightness and chromaticity information of the display area to be corrected into a pre-established display screen RGB gain prediction model, obtains the estimated RGB gain output by the display screen RGB gain prediction model, and performs brightness and chromaticity uniformity correction on the display area to be corrected based on the estimated RGB gain. This achieves "one-click" completion of brightness and chromaticity uniformity correction of the display area to be corrected based on the brightness and chromaticity information of the display area to be corrected and the pre-established display screen RGB gain prediction model. Furthermore, based on the technical solution provided in this application, for display modules such as cabinets or lamp boards manufactured using the same chip, the same display screen RGB gain prediction model can be used to "one-click" 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 displays spliced ​​together using display modules such as cabinets or lamp boards manufactured with the same chip, the brightness and color uniformity can be corrected in batches using a pre-established display RGB gain prediction model. This greatly improves the efficiency of brightness and color uniformity correction for displays and solves the technical problems of low correction efficiency, high manpower and time requirements, and difficulty in frequent implementation of traditional brightness and color uniformity correction methods.

[0014] A third aspect of this application provides an apparatus for constructing an RGB gain prediction model for a display screen, the apparatus comprising:

[0015] The first acquisition unit is used to acquire the brightness and chromaticity information corresponding to the display screen when displaying test images under multiple different RGB gains;

[0016] The construction unit is used to establish an RGB gain prediction model for the display screen based on the brightness and chromaticity information corresponding to the test image displayed on the display screen under multiple different RGB gains.

[0017] A fourth aspect of this application provides a brightness and chromaticity uniformity correction device for a display screen, the display screen brightness and chromaticity uniformity correction device comprising:

[0018] The second acquisition unit is used to acquire the brightness and chromaticity information of the display area to be calibrated on the display screen;

[0019] The estimation unit is used to input the brightness and chromaticity information of the display area to be corrected into a pre-established display RGB gain prediction model to obtain the estimated RGB gain output by the display RGB gain prediction model.

[0020] The correction unit is used to perform brightness and color uniformity correction on the display area to be corrected based on the estimated RGB gain.

[0021] A fifth aspect of this application provides an apparatus including a memory, a processor, and a computer program stored in the memory and executable on the processor. When executed by the processor, the computer program implements the steps of the method for constructing the RGB gain prediction model of the display screen as described in the first aspect, and / or the steps of the method for correcting the brightness and color uniformity of the display screen as described in the second aspect.

[0022] A sixth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method for constructing the RGB gain prediction model of the display screen as described in the first aspect, and / or the steps of the method for correcting the brightness and color uniformity of the display screen as described in the second aspect.

[0023] A seventh aspect of this application provides a computer program product, the computer program product including a computer program, which, when executed by a processor, implements the steps of the method for constructing the RGB gain prediction model of the display screen as described in the first aspect, and / or implements the steps of the method for correcting the brightness and color uniformity of the display screen as described in the second aspect.

[0024] It should be noted that the beneficial effects of the embodiments provided in the third to seventh aspects can be referred to the description of the beneficial effects of the embodiments provided in the first and second aspects, and will not be repeated here. Attached Figure Description

[0025] Figure 1 This is a schematic diagram illustrating the implementation process of the method for constructing the RGB gain prediction model for a display screen provided in this application embodiment.

[0026] Figure 2 This is a schematic diagram of the splicing structure of the display screen provided in an embodiment of this application.

[0027] Figure 3 This is a schematic diagram illustrating the implementation process of the brightness and color uniformity correction method for a display screen provided in an embodiment of this application.

[0028] Figure 4 This is a schematic diagram of a dialog box for adjusting RGB gain provided in an embodiment of this application.

[0029] Figure 5 This is a schematic diagram of the structure of the device for constructing the RGB gain prediction model for a display screen provided in an embodiment of this application.

[0030] Figure 6 A schematic diagram of the structure of the brightness and color uniformity correction device for the display screen provided in the embodiments of this application.

[0031] Figure 7 This is a schematic diagram of the device provided in an embodiment of this application. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0033] With the widespread application of LED displays in various indoor and outdoor scenarios, the requirements for their display effects are becoming increasingly stringent. Since LED displays are typically composed of multiple cabinets, each cabinet consisting of multiple light panels, the brightness and chromaticity of each cabinet or light panel will attenuate over time due to differences in the operating environment and frequency. Furthermore, when some cabinets or light panels malfunction or are damaged, requiring replacement, inconsistencies in brightness and chromaticity between the new and old cabinets or light panels will affect the uniformity and aesthetics of the overall LED display. Therefore, it is necessary to perform brightness and chromaticity uniformity correction on the spliced ​​LED display to avoid impacting image quality and user experience.

[0034] Existing calibration methods typically perform initial brightness and color calibration on the entire screen during the installation and commissioning phases to ensure that the screen initially achieves ideal brightness consistency and color accuracy. However, after an LED display has been in use for a period of time, the uniformity of the display effect often decreases due to factors such as light aging and module replacement. Without effective secondary calibration methods, the visual performance of the displayed content will be affected, especially in high-definition, high-definition color reproduction applications. However, traditional brightness and color calibration methods for displays mostly rely on complex external measurement equipment and time-consuming commissioning processes, requiring high labor and time costs and making frequent implementation difficult.

[0035] To address the aforementioned issues, this application provides a method for constructing an RGB gain prediction model for a display screen. This method can be executed by a display screen RGB gain prediction model construction device configured on a computer, server, or other device.

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

[0037] Step 101: Obtain the brightness and chromaticity information corresponding to the display screen when displaying test images under multiple different RGB gains.

[0038] It should be noted that the display screen used when establishing the RGB gain prediction model for the display screen can be a display screen that has already undergone brightness and color uniformity correction, or a display screen with a portion of it designated as a normal display area. This normal display area refers to the area where both brightness and color uniformity meet the uniformity requirements, i.e., the area where brightness and color uniformity correction has been completed.

[0039] In step 101 above, obtaining the brightness and chromaticity information corresponding to the display screen when displaying test images under multiple different RGB gains can mean obtaining the brightness and chromaticity information corresponding to the normal display area of ​​the display screen when displaying test images under multiple different RGB gains.

[0040] Specifically, in such Figure 2 The display shown is composed of 16 cabinets (numbered 1 to 16), each controlled by one or more receiver cards. During application, one or more cabinets may be replaced, a common occurrence in rental scenarios. Although each cabinet has pixel-level correction, inconsistencies in light attenuation between new and old cabinets, and between different cabinets themselves, can still cause brightness and color inconsistencies, affecting the overall viewing experience of the completed large screen. Figure 2 In the display shown, if the cabinet 15 is a replaced cabinet or a cabinet with inconsistent light decay, then the display area corresponding to the cabinet 15 is the display area to be calibrated in this application embodiment, and the remaining display areas are the normal display areas in this application embodiment.

[0041] Step 102: Based on the brightness and chromaticity information corresponding to the display screen when displaying test images under multiple different RGB gains, establish an RGB gain prediction model for the display screen.

[0042] In this embodiment, by acquiring the brightness and chromaticity information corresponding to the display screen when displaying test images under multiple different RGB gains, and based on the brightness and chromaticity information corresponding to the display screen when displaying test images under multiple different RGB gains, an RGB gain prediction model for the display screen is established. This allows for "one-click" completion of brightness and chromaticity uniformity correction of the display area to be corrected, based on the RGB gain prediction model. Furthermore, for display screens spliced ​​together using display modules such as cabinets or lamp boards manufactured with the same chip, the RGB gain prediction model can be used for batch brightness and chromaticity uniformity correction. Therefore, it can greatly improve the efficiency of brightness and chromaticity uniformity correction of the display screen, solving the technical problems of low correction efficiency, high manpower and time consumption, and difficulty in frequent implementation of traditional brightness and chromaticity uniformity correction methods.

[0043] In one embodiment of this application, in step 101 above, obtaining the brightness information and chromaticity information corresponding to the display screen when displaying test images under multiple different RGB gains can be achieved based on the following steps A01 to A02.

[0044] A01 controls the display screen to show the test image and records the current RGB gain of the display screen, as well as the corresponding brightness and chromaticity information of the display screen.

[0045] A02, repeatedly adjust the current RGB gain of the display screen multiple times, and record the brightness and chromaticity information corresponding to the display screen when displaying the test image under the adjusted RGB gain, to obtain the brightness and chromaticity information corresponding to the display screen when displaying the test image under multiple different RGB gains.

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

[0047] In one embodiment of this application, the test image in step 101 and step A01 above can be a pure white test image. Furthermore, when the test image is a pure white test image, step A01 can refer to: controlling the display screen to display the pure white test image, and recording the current RGB gain when the pure white test image is displayed in the normal display area of ​​the display screen, as well as the brightness and chromaticity information corresponding to the normal display area of ​​the display screen.

[0048] In one embodiment of this 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 can mean that each time the current RGB gain of the display screen is adjusted, one of the R gain, G gain, and B gain in the RGB gain of the normal display area is adjusted. That is, two of the gains are kept constant, and only one gain is adjusted to test the degree of influence of each gain (R gain, G gain, and B gain) on brightness and chromaticity.

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

[0050] In one embodiment of this application, the RGB gain is adjusted in fixed steps each time, with the step size being 1-10, in order to obtain a sufficient amount of luminance and chromaticity information corresponding to the RGB gain.

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

[0052] In one embodiment of this 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. Furthermore, when the test image is a pure red test image, a pure green test image, and a pure blue test image, step A01 above can refer to: controlling the display screen to display the pure red test image, the pure green test image, and the pure blue test image respectively, and recording the current RGB gain when the normal display area of ​​the display screen displays 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 above, repeatedly adjusting the current RGB gain of the display screen multiple times, can refer to: each time the current RGB gain of the display screen is adjusted, adjusting the gain of the color corresponding to the color of the test image displayed on the display screen within the current RGB gain of the display screen.

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

[0054] In one embodiment of this application, step 102 can be implemented based on the following steps B01 to B02.

[0055] Step B01: Group the brightness and chromaticity information corresponding to the test images displayed on the display screen under multiple different RGB gains according to a preset ratio to obtain the training dataset and the validation dataset.

[0056] Step B02: Use the training dataset to fit the model and use the validation dataset to validate the fitted initial RGB gain prediction model. When the rate of change of the preset loss function is less than the preset rate of change threshold, the initial RGB gain prediction model is determined as the display screen RGB gain prediction model.

[0057] For example, 80% of the luminance and chromaticity information under different RGB gains can be used as the training dataset for model training and fitting, while 20% of the luminance and chromaticity information under different RGB gains can be used as the validation dataset to verify the model's fitting effect.

[0058] In the process of establishing the RGB gain prediction model for the display screen, the loss function loss = 1 / 2 * (predict - true) can be used. 2 The model parameters are adjusted. Here, `true` represents the luminance and chrominance information input to the initial RGB gain prediction model, i.e., the true values, and `predict` represents the luminance and chrominance information corresponding to the RGB gain predicted by the initial RGB gain prediction model based on the true values ​​`true` (the RGB gain output by the initial RGB gain prediction model after inputting the true values ​​`true`). During model training and validation, if the rate of change of the loss function is less than a preset rate of change threshold, it indicates that the display screen RGB gain prediction model has been successfully trained, and the final trained initial RGB gain prediction model can be determined as the display screen RGB gain prediction model.

[0059] In one embodiment of this application, when the test image is a pure white test image, an RGB gain prediction model [R,G,B]=[R]=[R] can be established based on the luminance and chromaticity information corresponding to the pure white test image displayed under multiple different RGB gains in the normal display area of ​​the display screen. w B w Gw ]*X+B. Where, R w G w and B w Let X be the weight coefficient matrix, and let B be the feature matrix [x, y, lv], where (x, y) represents chromaticity information, lv represents luminance information, and B represents the bias parameter.

[0060] In one embodiment of this application, based on the luminance and chromaticity information corresponding to the display area of ​​the screen when displaying pure white test images under multiple different RGB gains, an RGB gain prediction model for the display screen is established: [R,G,B]=[R w B w G w During the process of ]*X+B, steps B01 to B01 above can be used as a basis.

[0061] Step B02 determines the parameters of the display screen RGB gain prediction model, namely, the weight coefficient matrix R. w G w and B w And the bias parameter B.

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

[0063] To further improve the correction effect of brightness and color uniformity, in one embodiment of this 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. 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 C03.

[0064] Step C01: Control the normal display area of ​​the screen to display a pure red test image, and record the current R gain corresponding to the normal display area, as well as the luminance and chromaticity information corresponding to the normal display area displaying the pure red test image under the current R gain; repeatedly adjust the current R gain of the normal display area, and record the luminance and chromaticity information corresponding to the normal display area displaying the pure red test image under the adjusted R gain, to obtain the luminance and chromaticity information corresponding to the normal display area displaying the pure red test image under multiple different R gains; based on the luminance and chromaticity information corresponding to the normal display area displaying the pure red test image under multiple different R gains, establish a 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 luminance and chrominance information corresponding to the normal display area displaying the pure green test image under the current G gain; repeatedly adjust the current G gain of the normal display area, and record the luminance and chrominance information corresponding to the normal display area displaying the pure green test image under the adjusted G gain, to obtain the luminance and chrominance information corresponding to the normal display area displaying the pure green test image under multiple different G gains; based on the luminance and chrominance information corresponding to the normal display area displaying the pure green test image under 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 screen to display a pure blue test image, and record the current B-gain corresponding to the normal display area, as well as the luminance and chrominance information corresponding to the normal display area displaying the pure blue test image under the current B-gain; repeatedly adjust the current B-gain of the normal display area, and record the luminance and chrominance information corresponding to the normal display area displaying the pure blue test image under the adjusted B-gain, to obtain the luminance and chrominance information corresponding to the normal display area displaying the pure blue test image under multiple different B-gains; based on the luminance and chrominance information corresponding to the normal display area displaying the pure blue test image under multiple different B-gains, establish a screen B-gain prediction model B = B b '*X b +B b .

[0067] Among them, R r G g and B b ' is the weight coefficient matrix, X r Xg and X b The feature matrix is ​​[x, y, lv], where (x, y) represents chromaticity information, lv represents luminance information, and R... b G b and B b This is the bias parameter.

[0068] The specific implementation methods of the above steps C01 to C03 can be referred to the descriptions of steps A01 to A02 and steps B01 to B02 mentioned above, and will not be repeated here.

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

[0070] Based on the RGB gain prediction model of the display screen established in the above embodiments, this application provides a method for correcting the brightness and color uniformity of a display screen. This method can be executed by a brightness and color uniformity correction device of the display screen configured on a computer, server or other device.

[0071] like Figure 3 As shown, the brightness and color uniformity correction method for the display screen provided in this application embodiment can be implemented by the following steps 201 to 203.

[0072] Step 201: Obtain the brightness and chromaticity information of the display area to be calibrated on the display screen.

[0073] Since the acquisition of luminance and chromaticity information is usually performed on a specific image region, rather than on a single pixel, to ensure the accuracy of the luminance and chromaticity information acquisition, the image region used to obtain the luminance and chromaticity information must be a solid color image region. Therefore, in this embodiment, step 201 may involve acquiring the luminance and chromaticity information of the region displaying the solid color image when displaying a solid color image (e.g., a pure white test image, a pure pink image, a pure purple image, and a pure yellow image, etc.) in all or part of the display area to be calibrated on the display screen, and using the luminance and chromaticity information of the region displaying the solid color image as the luminance and chromaticity information of the display area to be calibrated on the display screen.

[0074] To facilitate the acquisition of brightness and chromaticity information of the display area to be calibrated, in one embodiment, the display can be controlled to display a pure white test image, and the brightness and chromaticity information of the display area (i.e., the display area to be calibrated) that requires brightness and chromaticity correction under the pure white test image can be acquired. It is understood that it is also possible to control only the display area to be calibrated to display a pure white test image, and then acquire the brightness and chromaticity information of that area.

[0075] In one embodiment, the display screen can be controlled to display pure red, pure green, and pure blue test images respectively, and the brightness and chromaticity information of the display area to be calibrated can be obtained when the display screen displays the pure red, pure green, and pure blue test images respectively. Similarly, the display screen can be controlled to display only the pure red, pure green, and pure blue test images in the display area to be calibrated, and the brightness and chromaticity information of the display area to be calibrated can be obtained when displaying the test images of each color.

[0076] Step 202: Input the brightness and chromaticity information of the display area to be corrected 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.

[0077] In this embodiment, when the brightness and chromaticity information of the display area to be calibrated are obtained when the display area to be calibrated displays a pure color image other than a pure red test image, a pure green test image, and a pure blue test image (e.g., a pure white test image, a pure pink image, or other images corresponding to mixed light), then step 202 only needs to be performed once. That is, the brightness and chromaticity information obtained when the display area to be calibrated displays a pure white test image is directly input into the pre-established display screen RGB gain prediction model to obtain the estimated RGB gain output by the display screen RGB gain prediction model.

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

[0079] That is, the luminance and chromaticity information of the display area to be calibrated when displaying a pure red test image are input into the pre-established display R gain prediction model to obtain the estimated R gain output by the display R gain prediction model; the luminance and chromaticity information of the display area to be calibrated when displaying a pure green test image are input into the pre-established display G gain prediction model to obtain the estimated G gain output by the display G gain prediction model; and the luminance and chromaticity information of the display area to be calibrated when displaying a pure blue test image are input into the pre-established display B gain prediction model to obtain the estimated B gain output by the display B gain prediction model.

[0080] Step 203: Perform brightness and color uniformity correction on the display area to be corrected based on the estimated RGB gain.

[0081] By adjusting the gain values ​​(RGB gain) of the three color channels (red (R), green (G), and blue (B)) in an image, you can change the brightness and chromaticity. Increasing the gain value will make the image brighter, while decreasing the gain value will darken the image. If a certain color channel in an image is too dark or too bright, you can correct the color deviation by adjusting the gain value of the corresponding channel, restoring the image to a more accurate color representation.

[0082] In one embodiment of this application, step 203 may refer to adjusting the RGB gain of the display area to be corrected to the estimated RGB gain obtained in step 202, and saving the adjusted RGB gain to achieve brightness and color uniformity correction of the display area to be corrected.

[0083] For example, such as Figure 4The diagram shows a dialog box for adjusting RGB gain according to an embodiment of this 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 calibrated can be adjusted to the estimated RGB gain obtained in step 202. By saving the adjusted RGB gain, the brightness and color uniformity calibration of the display area to be calibrated can be completed. Based on this, this application realizes "one-click" calibration of the brightness and color uniformity of the display area to be calibrated based on the brightness and color information of the display area to be calibrated and a pre-established display RGB gain prediction model. This greatly improves the efficiency of brightness and color uniformity calibration of the display screen and solves the technical problems of low calibration efficiency, high manpower and time consumption, and difficulty in frequent implementation of traditional brightness and color uniformity calibration methods.

[0084] Specifically, when the estimated RGB gain is the RGB gain estimated based on the luminance and chromaticity information of the display area to be calibrated when displaying a pure color image other than a pure red, pure green, or pure blue test image, step 203 only needs to be performed once. That is, the RGB gain of the display area to be calibrated is directly adjusted to the estimated RGB gain.

[0085] When the estimated RGB gain includes estimated R gain, estimated G gain, and estimated B gain, step 103 above needs to be performed three times. Specifically, after inputting the luminance and chromaticity information of the display area to be calibrated (showing a pure red test image) into the pre-established display R gain prediction model to obtain the estimated R gain output by the model, the R gain in the RGB gain of the display area to be calibrated is adjusted to the estimated R gain. Similarly, after inputting the luminance and chromaticity information of the display area to be calibrated (showing a pure green test image) into the pre-established display G gain prediction model to obtain the estimated G gain output by the model, the G gain in the RGB gain of the display area to be calibrated is adjusted to the estimated G gain. Finally, after inputting the luminance and chromaticity information of the display area to be calibrated (showing a pure blue test image) into the pre-established display B gain prediction model to obtain the estimated B gain output by the model, the B gain in the RGB gain of the display area to be calibrated is adjusted to the estimated B gain. By saving the adjusted R gain, G gain, and B gain respectively, the luminance and chromaticity uniformity correction of the display area to be calibrated can be completed.

[0086] In this embodiment, when displaying a test image on the display area to be calibrated, the brightness and chromaticity information of the display area to be calibrated are acquired. This information is then input into a pre-established RGB gain prediction model for the display, yielding an estimated RGB gain output by the model. Based on this estimated RGB gain, brightness and chromaticity uniformity calibration is performed on the display area to be calibrated. This achieves "one-click" calibration of brightness and chromaticity uniformity in the display area to be calibrated using the brightness and chromaticity information of the display area to be calibrated and the pre-established RGB gain prediction model. Furthermore, based on the technical solution provided in this application, for display modules such as cabinets or lamp boards manufactured using the same chip, the same RGB gain prediction model can be used to "one-click" calibrate the brightness and chromaticity uniformity of the display area to be calibrated, eliminating the need to rebuild the RGB gain prediction model. Therefore, for displays spliced ​​together using display modules such as cabinets or lamp boards manufactured with the same chip, the uniformity of brightness and color can be corrected in batches using a pre-established display RGB gain prediction model. This greatly improves the efficiency of brightness and color uniformity correction for displays, and solves the technical problems of low correction efficiency, high manpower and time consumption, and difficulty in frequent implementation of traditional brightness and color uniformity correction methods for displays.

[0087] It should be noted that the aforementioned pre-established RGB gain prediction model for the display screen is the one described above. Figure 1 The illustrated embodiment establishes a display screen RGB gain prediction model.

[0088] In one embodiment of this application, in order to improve the accuracy of the RGB gain prediction model of the display screen and to improve the correction effect of uniformity correction of the brightness and chromaticity of the display area to be corrected, high-precision luminance meters and colorimeters can be used to collect brightness and chromaticity information when acquiring brightness and chromaticity information.

[0089] For example, when obtaining the brightness and chromaticity information of the display area to be calibrated, a luminance meter and a colorimeter can be used to measure the brightness and chromaticity of the display area to be calibrated, thereby obtaining the brightness and chromaticity information of the display area to be calibrated.

[0090] In one embodiment of this application, in addition to using a luminance meter and a colorimeter to collect luminance and chromaticity information of the display area, a high-precision device can also be used to capture images of the display area, and the luminance and chromaticity information of the display area can be obtained by recognizing the luminance and chromaticity of the captured images.

[0091] This application does not restrict the method of acquiring brightness and chromaticity information, as long as the brightness and chromaticity information of the display area (e.g., the normal display area and the display area to be calibrated) can be collected.

[0092] It should be noted that, for the sake of simplicity, the aforementioned method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions. In some embodiments of this application, certain steps may be performed in other orders as needed.

[0093] like Figure 5 As shown in the illustration, this application embodiment also provides a device for constructing an RGB gain prediction model for a display screen. This device may include a first acquisition unit 501 and a construction unit 502. The first acquisition unit 501 is used to acquire the brightness and chromaticity information corresponding to the display screen when displaying test images under multiple different RGB gains. The construction unit 502 is used to establish an RGB gain prediction model for the display screen based on the brightness and chromaticity information corresponding to the display screen when displaying test images under multiple different RGB gains.

[0094] It should be noted that, for the sake of convenience and brevity, the specific working process of the display RGB gain prediction model construction device 500 described above can be referred to the corresponding process of the display RGB gain prediction model construction method described above, and will not be repeated here. Each unit of the display RGB gain prediction model construction device 500 can execute the corresponding steps in the above-described display RGB gain prediction model construction method embodiment, so each unit will not be described in detail here; please refer to the description of the corresponding steps above for details.

[0095] like Figure 6 As shown in the illustration, this application embodiment also provides a brightness and chromaticity uniformity correction device 600 for a display screen. This device may include a second acquisition unit 601, an estimation unit 602, and a correction unit 603. The second acquisition unit 601 is used to acquire brightness and chromaticity information of the display area to be corrected on the display screen; the estimation unit 602 is used to input the brightness and chromaticity 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; and the correction unit 603 is used to perform brightness and chromaticity uniformity correction on the display area to be corrected based on the estimated RGB gain.

[0096] It should be noted that, for the sake of convenience and brevity, the specific working process of the brightness and color uniformity correction device 600 for the display screen described above can be referred to the corresponding process of the brightness and color uniformity correction method for the display screen described above, and will not be repeated here. Each unit of the brightness and color uniformity correction device 600 for the display screen can execute the corresponding steps in the aforementioned method embodiments, so each unit will not be described in detail here. For details, please refer to the description of the corresponding steps above.

[0097] like Figure 7 As shown, this application embodiment 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 aforementioned methods for constructing RGB gain prediction models for various displays, or the steps of the aforementioned methods for correcting the brightness and color uniformity of various displays, for example... Figure 1 Steps 101 to 102 shown, or, Figure 3 Steps 201 to 203 are shown.

[0098] The aforementioned computer program can be divided into one or more units, which are stored in the aforementioned memory 71 and executed by the aforementioned processor 70 to complete this application. The aforementioned one or more units can be a series of computer program instruction segments capable of performing specific functions. These instruction segments describe the process by which the computer program executes the aforementioned method for constructing the RGB gain prediction model for each display screen in the device, or the process for correcting the brightness and color uniformity of the aforementioned display screens. For example, the aforementioned computer program can be divided into... Figure 5 The diagram shows a first acquisition unit and a construction unit. The first acquisition unit acquires the brightness and chromaticity information corresponding to the display screen when it displays test images under multiple different RGB gains. The construction unit establishes an RGB gain prediction model for the display screen based on the brightness and chromaticity information corresponding to the display screen when it displays test images under multiple different RGB gains.

[0099] This application also provides a computer-readable storage medium storing a computer program that, when executed by a central processing module, implements the steps of the method for constructing a display screen RGB gain prediction model as described in any of the above embodiments, or the steps of the method for correcting the brightness and color uniformity of a display screen.

[0100] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the steps of the method for constructing the RGB gain prediction model of the display screen as described in any of the above embodiments, or the steps of the method for correcting the brightness and color uniformity of the display screen.

[0101] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0102] Those skilled in the art will recognize that the steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

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

[0104] If implemented as 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, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable storage media do not include electrical carrier signals and telecommunication signals.

[0105] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for constructing an RGB gain prediction model for a display screen, characterized in that, The construction method includes: Acquiring brightness and chromaticity information corresponding to test images displayed on the display screen under multiple different RGB gains, including: when the test image is a pure white test image, repeatedly adjusting the current RGB gain of the display screen, and adjusting one of the R gain, G gain, and B gain in the current RGB gain of the display screen each time the current RGB gain of the display screen is adjusted; when the test image includes pure red test images, pure green test images, and pure blue test images, repeatedly adjusting the current RGB gain of the display screen, and adjusting the gain of the color in the current RGB gain of the display screen that corresponds to the color of the test image displayed on the display screen each time the current RGB gain of the display screen is adjusted; Based on the brightness and chromaticity information corresponding to the test image displayed on the display screen under multiple different RGB gains, an RGB gain prediction model for the display screen is established. 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: the R gain prediction model of the display screen, the G gain prediction model of the display screen, and the B gain prediction model of the display screen. The step of establishing an RGB gain prediction model for the display screen based on the luminance and chromaticity information corresponding to the test image displayed on the display screen under multiple different RGB gains includes: Based on the brightness and chromaticity information corresponding to the display screen when displaying the pure red test image under multiple different R gains, an R gain prediction model for the display screen is established. Based on the brightness and chromaticity information corresponding to the display screen when displaying the pure green test image under multiple different G gains, a G gain prediction model for the display screen is established. Based on the luminance and chromaticity information corresponding to the pure blue test image displayed on the display screen under multiple different B-gains, a B-gain prediction model for the display screen is established.

2. The method for constructing the RGB gain prediction model for a display screen as described in claim 1, characterized in that, The acquisition of brightness and chromaticity information corresponding to the display screen when displaying test images under multiple different RGB gains includes: Control the display screen to display the test image, and record the current RGB gain of the display screen, as well as the corresponding brightness and chromaticity information of the display screen; The current RGB gain of the display screen is adjusted repeatedly, and the brightness and chromaticity information corresponding to the display screen when displaying the test image under the adjusted RGB gain are recorded to obtain the brightness and chromaticity information corresponding to the display screen when displaying the test image under multiple different RGB gains.

3. The method for constructing the RGB gain prediction model for a display screen as described in any one of claims 1-2, characterized in that, The step of establishing an RGB gain prediction model for the display screen based on the luminance and chromaticity information corresponding to the test image displayed on the display screen under multiple different RGB gains includes: The brightness and chromaticity information corresponding to the test image displayed on the display screen under multiple different RGB gains are grouped according to a preset ratio to obtain a training dataset and a validation dataset. The training dataset is used to fit the model, and the initial RGB gain prediction model is validated using the validation dataset. When the rate of change of the preset loss function is less than the preset rate of change threshold, the initial RGB gain prediction model is determined as the RGB gain prediction model of the display screen.

4. A method for correcting the brightness and color uniformity of a display screen, characterized in that, The method for correcting the brightness and color uniformity of the display screen includes: Obtain the brightness and chromaticity information of the display area to be calibrated on the display screen; The brightness and chromaticity information of the display area to be corrected are input into the pre-established display RGB gain prediction model as described in any one of claims 1-3 to obtain the estimated RGB gain output by the display RGB gain prediction model. The brightness and color uniformity of the display area to be corrected are corrected based on the estimated RGB gain.

5. The method for correcting the brightness and color uniformity of a display screen as described in claim 4, characterized in that, The step of performing brightness and color uniformity correction on the display area to be corrected based on the estimated RGB gain includes: The RGB gain of the display area to be corrected is adjusted to the estimated RGB gain, and the adjusted RGB gain is saved.

6. A device for constructing an RGB gain prediction model for a display screen, characterized in that, The construction apparatus includes: The first acquisition unit is used to acquire the brightness and chromaticity information corresponding to the display screen when displaying test images under multiple different RGB gains, including: when the test image is a pure white test image, repeatedly adjusting the current RGB gain of the display screen, and adjusting one of the R gain, G gain and B gain in the current RGB gain of the display screen each time the current RGB gain of the display screen is adjusted; when the test image includes a pure red test image, a pure green test image and a pure blue test image, repeatedly adjusting the current RGB gain of the display screen, and adjusting the gain of the color in the current RGB gain of the display screen that corresponds to the color of the test image displayed on the display screen each time the current RGB gain of the display screen is adjusted; The construction unit is used to establish an RGB gain prediction model for the display screen based on the brightness and chromaticity information corresponding to the test image displayed on the display screen under multiple different RGB gains; 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: the R gain prediction model of the display screen, the G gain prediction model of the display screen, and the B gain prediction model of the display screen. The step of establishing an RGB gain prediction model for the display screen based on the luminance and chromaticity information corresponding to the test image displayed on the display screen under multiple different RGB gains includes: Based on the brightness and chromaticity information corresponding to the display screen when displaying the pure red test image under multiple different R gains, an R gain prediction model for the display screen is established. Based on the brightness and chromaticity information corresponding to the display screen when displaying the pure green test image under multiple different G gains, a G gain prediction model for the display screen is established. Based on the luminance and chromaticity information corresponding to the pure blue test image displayed on the display screen under multiple different B-gains, a B-gain prediction model for the display screen is established.

7. A device for correcting the brightness and color uniformity of a display screen, characterized in that, The brightness and color uniformity correction device for the display screen includes: The second acquisition unit is used to acquire the brightness and chromaticity information of the display area to be calibrated on the display screen; The estimation unit is used to input the brightness information and chromaticity information of the display area to be corrected into the pre-established display RGB gain prediction model as described in any one of claims 1-3, and obtain the estimated RGB gain output by the display RGB gain prediction model. The correction unit is used to perform brightness and color uniformity correction on the display area to be corrected based on the estimated RGB gain.

8. A device, characterized in that, The device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein 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 as described in any one of claims 1-3, 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 as described in any one of claims 4-5.

Images