Color cast detection method and equipment of display device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of display, and particularly discloses a color cast detection method and equipment of a display device, electronic equipment and a storage medium. The method comprises: controlling the display device to display a test picture; acquiring a shot image of the test picture; inputting the shot image into a preset color cast detection model, extracting RGB data from the shot image through the color cast detection model, converting the RGB data into CIE color coordinate data, and detecting and outputting a color cast probability value of the display device; and determining a color cast detection result of the display device according to the color cast probability value. In this way, the color cast probability value of the display device can be predicted in combination with the trained color cast detection model, then the color cast detection result is determined according to the color cast probability value, and compared with traditional manual observation and subjective judgment, the color cast detection efficiency is effectively improved. And the color cast detection model is combined with CIE color coordinate data, so that a color cast probability value can be obtained more accurately, and the detection accuracy is further improved.

Description

Technical Field

[0001] The present application relates to the field of display technology, and in particular to a method and device for detecting color deviation of a display device, an electronic device, and a storage medium. Background Art

[0002] Organic light-emitting diode (OLED) display is a new display technology with advantages such as self-luminescence, high contrast, and fast response time. It is widely used in smart phones, TVs, computer monitors, etc. However, OLED display may have color cast problems during the production process, that is, the color display of different areas on the screen is inconsistent, which will seriously affect the display effect of the display. Therefore, color cast testing of OLED display is an essential part of the production process.

[0003] However, the current color deviation test is inefficient and prone to misjudgment and missed judgment. Summary of the invention

[0004] Based on this, it is necessary to provide a color shift detection method for a display device, a color shift detection device, an electronic device, and a computer-readable storage medium to address the above problems.

[0005] According to a first aspect of an embodiment of the present application, a method for detecting color cast of a display device is provided, the method comprising:

[0006] Controlling the display device to display a test screen;

[0007] Acquire a captured image of the test screen;

[0008] Inputting the captured image into a preset color shift detection model, so as to extract RGB data from the captured image through the color shift detection model, and after converting the RGB data into CIE color coordinate data, detecting and outputting a color shift probability value of the display device;

[0009] A color cast detection result of the display device is determined according to the color cast probability value.

[0010] In one of the embodiments, the color shift detection method further includes a step of establishing the color shift detection model, wherein the sample images used to establish the color shift detection model include a plurality of collected color shift images and a plurality of non-color shift images.

[0011] In one of the embodiments, the color shift detection method further includes: storing the collected color shift images and non-color shift images in a database by using big data processing technology.

[0012] In one of the embodiments, the database uses a HiDUP distributed file system.

[0013] In one embodiment, the step of establishing the color shift detection model includes:

[0014] Use the deep learning framework to initially build a color cast detection model;

[0015] A plurality of color-biased images and a plurality of non-color-biased images are input into the color-biased detection model to train the color-biased detection model, wherein during the training process, RGB data of each of the color-biased images and each of the non-color-biased images is extracted and the RGB data is converted into CIE color coordinate data to train the color-biased detection model.

[0016] In one of the embodiments, the step of training the color cast detection model includes a forward propagation stage and a back propagation stage;

[0017] In the forward propagation stage, the color cast probability value of the input image is predicted by the color cast detection model;

[0018] In the back propagation stage, the error value between the predicted value and the true value of the color cast detection model is calculated, and the parameters in the color cast detection model are updated by the gradient descent method.

[0019] In one embodiment, the step of determining the color cast detection result of the display device according to the color cast probability value includes:

[0020] When the color deviation probability value exceeds a first threshold, determining that the color deviation detection result of the display device is that color deviation exists;

[0021] When the color deviation probability value is lower than a second threshold, determining that the color deviation detection result of the display device is that there is no color deviation;

[0022] The first threshold is higher than the second threshold.

[0023] In one embodiment, the step of determining the color cast detection result of the display device according to the color cast probability value further includes:

[0024] When the color cast probability value is between the second threshold and the first threshold, it is determined that the color cast detection result of the display device is to be determined.

[0025] In one embodiment, the first threshold is 0.85, and the second threshold is 0.65.

[0026] According to a second aspect of an embodiment of the present application, a color shift detection device is provided, including:

[0027] A shooting module, used for acquiring a shooting image of a test screen;

[0028] A control module is used to control the display device to display a test screen, and input the captured image of the test screen acquired by the shooting module into a preset color shift detection model, so as to extract RGB data from the captured image through the color shift detection model, and after converting the RGB data into CIE color coordinate data, detect and output the color shift probability value of the display device; and determine the color shift detection result of the display device according to the color shift probability value.

[0029] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the color cast detection method for a display device as described above.

[0030] According to a third aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the color cast detection method for a display device as described above are implemented.

[0031] The color deviation detection method of the display device provided in the embodiment of the present application first controls the display device to display a test screen, then obtains a captured image of the test screen, and then inputs the captured image into a preset color deviation detection model. After extracting RGB data from the captured image through the color deviation detection model and converting the RGB data into CIE color coordinate data, the color deviation probability value of the display device is detected and output, and finally the color deviation detection result of the display device is determined according to the color deviation probability value. In this way, the color deviation probability value of the display device can be predicted in combination with the trained color deviation detection model, and then the color deviation detection result is determined according to the color deviation probability value. Compared with traditional manual observation and subjective judgment, the color deviation detection efficiency is effectively improved, and the occurrence of misjudgment and missed judgment caused by human subjective factors is avoided. At the same time, in this embodiment, the color deviation detection model combined with the CIE color coordinate data can more accurately obtain the color deviation probability value, further improving the detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A flowchart of a method for detecting color shift of a display device provided in one embodiment of the present application;

[0033] Figure 2 Schematic diagram of color deviation and non-color deviation in RGB coordinate system;

[0034] Figure 3 Schematic diagram of color deviation and non-color deviation in the CIE coordinate system;

[0035] Figure 4 A flowchart of step S100 in a method for detecting color shift of a display device provided in an embodiment of the present application;

[0036] Figure 5 A schematic diagram of the structure of a color deviation detection device provided in one embodiment of the present application;

[0037] Figure 6 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0038] In order to facilitate the understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. The preferred embodiments of the present application are given in the drawings. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to understand the disclosure of the present application more thoroughly and comprehensively.

[0039] In this application, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0040] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0042] Organic light-emitting diode (OLED) display is a new display technology with advantages such as self-luminescence, high contrast, and fast response time. It is widely used in smart phones, TVs, computer monitors, etc. However, OLED display may have color cast problems during the production process, that is, the color display of different areas on the screen is inconsistent, which will seriously affect the display effect of the display. Therefore, color cast testing of OLED display is an essential part of the production process.

[0043] The existing color deviation test method is mainly based on manual observation and subjective judgment. This method is not only inefficient, but also may lead to misjudgment and missed judgment due to the influence of personal subjective factors. Therefore, how to improve the efficiency and accuracy of color deviation detection is particularly important in this field.

[0044] In order to solve the above problems, embodiments of the present application provide a color cast detection method for a display device, a color cast detection device, an electronic device, and a computer-readable storage medium.

[0045] In one embodiment, a color shift detection method for a display device is provided, by which the color shift detection efficiency and accuracy of the display device can be effectively improved.

[0046] Reference Figure 1 The color cast detection method of the display device provided in this embodiment includes the following steps:

[0047] Step S200: Control the display device to display a test screen.

[0048] In order to detect whether the display device has color deviation, it is first necessary to light up the display device, that is, control the display device to display a preset test screen. The test screen can be set according to the actual test requirements, and can be a screen of a predetermined color, such as a full white or full black screen or a grayscale screen between full white and full black. In this embodiment, the display device can be an OLED display device, specifically a display device with an OLED display screen on a mobile phone or a tablet computer.

[0049] Step S400: Acquire a captured image of the test screen.

[0050] When the display device is lit, the test screen displayed on the display device can be photographed by the photographing module to obtain a photographed image of the test screen.

[0051] Specifically, the shooting module may be a camera or the like.

[0052] Step S600: input the captured image into a preset color shift detection model to extract RGB data from the captured image through the color shift detection model, and after converting the RGB data into CIE color coordinate data, detect and output the color shift probability value of the display device.

[0053] After obtaining the captured image of the test screen, the captured image can be input into the preset color shift detection model, and the captured image can be subjected to color shift detection by the trained color shift detection model, thereby outputting the color shift probability value of the display device. Before the color shift detection model predicts the color shift probability value, RGB data is first extracted from the captured image, and the RGB data is converted into CIE color coordinate data. In the prediction process, the CIE color coordinate data can be combined for prediction.

[0054] If the color cast probability value is predicted only by RGB data, the accuracy of the color cast probability value outputted is low because RGB data cannot clearly distinguish the color cast area from the non-color cast area. Figure 2 , in the RGB coordinate system, the color shift area ( Figure 2 The area where the dots are located) and the non-color cast area ( Figure 2 In order to improve the accuracy of color shift detection, in this embodiment, the RGB data is converted into CIE color coordinate data (CIE_X, CIE_Y, CIE_Z). Since the CIE color coordinate data can more clearly distinguish the color shift area from the non-color shift area, the reference Figure 3 , in the CIE coordinate system, the color shift area ( Figure 3 The area where the dots are located) and the non-color cast area ( Figure 3 Therefore, compared with the prediction of the color shift probability value only through RGB data, the color shift probability value can be obtained more accurately by combining CIE color coordinate data, thereby improving the detection accuracy.

[0055] In this embodiment, an open source image processing library OpenCV may be used, which provides a rich set of image processing functions to facilitate the reading, conversion, and storage of images.

[0056] Step S800: Determine a color cast detection result of the display device according to the color cast probability value.

[0057] After the color shift probability value output by the color shift detection model is obtained, the color shift detection result of the display device can be determined according to the color shift probability value.

[0058] The color deviation detection method of the display device provided in the embodiment of the present application first controls the display device to display a test screen, then obtains a captured image of the test screen, and then inputs the captured image into a preset color deviation detection model. After extracting RGB data from the captured image through the color deviation detection model and converting the RGB data into CIE color coordinate data, the color deviation probability value of the display device is detected and output, and finally the color deviation detection result of the display device is determined according to the color deviation probability value. In this way, the color deviation probability value of the display device can be predicted in combination with the trained color deviation detection model, and then the color deviation detection result is determined according to the color deviation probability value. Compared with traditional manual observation and subjective judgment, the color deviation detection efficiency is effectively improved, and the occurrence of misjudgment and missed judgment caused by human subjective factors is avoided. At the same time, in this embodiment, the color deviation detection model combined with the CIE color coordinate data can more accurately obtain the color deviation probability value, further improving the detection accuracy.

[0059] In one of the embodiments, the color shift detection method further includes: step S100, a step of establishing the color shift detection model, wherein the sample images used to establish the color shift detection model include a plurality of collected color shift images and a plurality of non-color shift images.

[0060] That is, a large number of color-biased images and non-color-biased images can be collected in advance as sample images required for establishing a color-biased detection model. In a specific example, 1,000 color-biased images and 1,000 non-color-biased images can be collected in advance as sample images for model training, wherein the resolution of each image can be the resolution of the display device, such as 2700*2400.

[0061] Reference Figure 4 In one embodiment, step S100, i.e., the step of establishing the color shift detection model, includes:

[0062] Step S110: Use a deep learning framework to preliminarily build a color cast detection model.

[0063] Specifically, you can use the deep learning framework TensorFlow to build a preliminary color cast detection model for use after training.

[0064] Step S120, inputting a plurality of color-biased images and a plurality of non-color-biased images into the color-biased detection model to train the color-biased detection model, wherein during the training process, RGB data of each of the color-biased images and each of the non-color-biased images is extracted and the RGB data is converted into CIE color coordinate data to train the color-biased detection model.

[0065] After building a preliminary color shift detection model, it can be trained. Specifically, a large number of color shift images and non-color shift images can be obtained as sample images and input into the color shift detection model. During the training process, the RGB data of each input image can be first extracted, and then the RGB data can be converted into CIE color coordinate data, and the color shift detection model can be trained in combination with the CIE color coordinate data. This can avoid the problem of cross-region overlap between the RGB curve and the color temperature when the RGB data is directly applied, which can easily cause misjudgment.

[0066] In one embodiment, step S120, that is, the step of training the color cast detection model includes a forward propagation stage and a back propagation stage.

[0067] In the forward propagation stage, the color cast probability value of the input image is predicted by the color cast detection model;

[0068] In the back propagation stage, the error value between the predicted value and the true value of the color cast detection model is calculated, and the parameters in the color cast detection model are updated by the gradient descent method.

[0069] The parameters in the color shift detection model may include RGB data, CIE color coordinate data, and the median average of the above data.

[0070] In addition, in this embodiment, the collected color-biased images and non-color-biased images can be stored in a database through big data processing technology, wherein the database can use a Hadoop distributed file system, thereby effectively managing and processing a large amount of image data.

[0071] In one embodiment, step S800, i.e., the step of determining the color cast detection result of the display device according to the color cast probability value, includes:

[0072] Step S810: When the color cast probability value exceeds a first threshold, determining that the color cast detection result of the display device is that color cast exists;

[0073] Step S820: When the color cast probability value is lower than a second threshold, determining that the color cast detection result of the display device is that there is no color cast;

[0074] In this embodiment, the first threshold is higher than the second threshold.

[0075] Therefore, by comparing the color shift probability value output by the color shift detection model with each threshold value, the color shift detection result of the display device can be determined, and the detection efficiency is high.

[0076] In practical applications, the first threshold may be 0.85, and the second threshold may be 0.65, that is, when the color cast probability value is greater than 0.85, it can be determined that the display device has a color cast problem, and when the color cast probability value is less than 0.65, it can be determined that the display device does not have a color cast problem.

[0077] In one embodiment, step S800, i.e., the step of determining the color cast detection result of the display device according to the color cast probability value, further includes:

[0078] Step S830: When the color cast probability value is between the second threshold and the first threshold, determining that the color cast detection result of the display device is to be determined.

[0079] Back to the above example, that is, when the color cast probability value is between 0.65 and 0.85, the color cast detection result of the display device is actually to be determined. At this time, it is necessary to manually perform color cast detection on the display device.

[0080] Reference Figure 5 In one embodiment, a color shift detection device is provided, including a shooting module 100 and a control module 200.

[0081] The shooting module 100 is used to obtain a captured image of the test screen, and specifically, the shooting module 100 may include a camera, etc. The control module 200 is used to control the display device to display the test screen, and input the captured image of the test screen obtained by the shooting module into a preset color shift detection model, so as to extract RGB data from the captured image through the color shift detection model, and after converting the RGB data into CIE color coordinate data, detect and output the color shift probability value of the display device; and determine the color shift detection result of the display device according to the color shift probability value.

[0082] For specific contents of the control module 200 in the color cast detection device provided in this embodiment, reference may be made to the specific description in the color cast detection method for a display device provided in the aforementioned embodiment, and will not be repeated here.

[0083] By using the color deviation detection device provided in the present embodiment to detect color deviation of the display device, the color deviation probability value of the display device can be predicted in combination with a trained color deviation detection model, and then the color deviation detection result can be determined based on the color deviation probability value. Compared with traditional manual observation and subjective judgment, the color deviation detection efficiency is effectively improved, and misjudgment and missed judgment due to human subjective factors are avoided. At the same time, in the present embodiment, the color deviation detection model combined with the CIE color coordinate data can more accurately obtain the color deviation probability value, further improving the detection accuracy.

[0084] In one embodiment, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0085] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may be a server, and its internal structure diagram may be as follows: Figure 6 As shown. The electronic device includes a processor, a memory and a network interface connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store various types of data involved in a color deviation detection method for a display device. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a color deviation detection method for a display device is implemented.

[0086] Those skilled in the art will understand that Figure 6 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0087] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0088] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical storage, etc. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0089] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0090] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the patent. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for detecting color shift of a display device, characterized in that: The color shift detection method comprises: Controlling the display device to display a test screen; Acquire a captured image of the test screen; Inputting the captured image into a preset color shift detection model, so as to extract RGB data from the captured image through the color shift detection model, and after converting the RGB data into CIE color coordinate data, detecting and outputting a color shift probability value of the display device; A color cast detection result of the display device is determined according to the color cast probability value.

2. The color cast detection method for a display device according to claim 1, characterized in that: The color deviation detection method further comprises the step of establishing the color deviation detection model, wherein the sample images used to establish the color deviation detection model include a plurality of collected color deviation images and a plurality of non-color deviation images; Preferably, the color deviation detection method further comprises: storing the collected color deviation images and non-color deviation images in a database by using big data processing technology; Preferably, the database adopts the HiDUP distributed file system.

3. The color cast detection method for a display device according to claim 2, characterized in that: The step of establishing the color shift detection model comprises: Use the deep learning framework to initially build a color cast detection model; A plurality of color-biased images and a plurality of non-color-biased images are input into the color-biased detection model to train the color-biased detection model, wherein during the training process, RGB data of each of the color-biased images and each of the non-color-biased images is extracted and the RGB data is converted into CIE color coordinate data to train the color-biased detection model.

4. The method for detecting color shift of a display device according to claim 3, wherein: The step of training the color cast detection model includes a forward propagation stage and a back propagation stage; In the forward propagation stage, the color cast probability value of the input image is predicted by the color cast detection model; In the back propagation stage, the error value between the predicted value and the true value of the color cast detection model is calculated, and the parameters in the color cast detection model are updated by the gradient descent method.

5. The method for detecting color shift of a display device according to claim 1, wherein: The step of determining the color cast detection result of the display device according to the color cast probability value comprises: When the color deviation probability value exceeds a first threshold, determining that the color deviation detection result of the display device is that color deviation exists; When the color deviation probability value is lower than a second threshold, determining that the color deviation detection result of the display device is that there is no color deviation; The first threshold is higher than the second threshold.

6. The method for detecting color shift of a display device according to claim 5, wherein: The step of determining the color cast detection result of the display device according to the color cast probability value further includes: When the color cast probability value is between the second threshold and the first threshold, it is determined that the color cast detection result of the display device is to be determined.

7. The method for detecting color shift of a display device according to claim 5, wherein: The first threshold is 0.85, and the second threshold is 0.

65.

8. A color deviation detection device, characterized in that: include: A shooting module, used for acquiring a shooting image of a test screen; A control module is used to control the display device to display a test screen, and input the captured image of the test screen acquired by the shooting module into a preset color shift detection model, so as to extract RGB data from the captured image through the color shift detection model, and after converting the RGB data into CIE color coordinate data, detect and output the color shift probability value of the display device; and determine the color shift detection result of the display device according to the color shift probability value.

9. An electronic device, characterized in that: include: 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, the steps of the color cast detection method for a display device as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the color cast detection method for a display device as described in any one of claims 1 to 7 are implemented.

Images