Screen color uniformity detection method, system and device and storage medium

Abstract

The invention relates to the technical field of screen detection, and discloses a screen color uniformity detection method, system and device and a storage medium, and the method comprises the steps: driving a to-be-detected screen to display a test picture; pre-illuminating a to-be-tested screen, and scanning a test picture to obtain a sample image; determining an image acquisition parameter based on the sample image; acquiring and optimizing multiple frames of images of the test picture based on the image acquisition parameters to obtain a screen color reference image; and carrying out full-region color uniformity quantitative analysis based on the screen color reference image to obtain a color uniformity detection result. According to the method, the quality of detection input is ensured from the source, environmental interference is solved, a color uniformity detection result is obtained through full-region color uniformity quantitative analysis, screen full-region role color analysis is achieved, local color defect missing detection is avoided, the detection result has objective and accurate characteristics through quantitative analysis, and the detection efficiency is improved. And meanwhile, manual operation is replaced by full-process automatic algorithm analysis, so that the detection efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of screen testing technology, specifically to a method, system, device, and storage medium for detecting screen color uniformity. Background Technology

[0002] In the quality inspection of screen modules for consumer electronics products (such as mobile phones, tablets, and watches), the uniformity of screen display color is a crucial step. Current inspection methods typically involve manual visual inspection or automated measurement using luminance / colorimeters at single points or with a small number of sampling points. However, manual inspection results are affected by subjective factors such as personnel experience and fatigue, lacking standardized and objective judgment criteria, and are inefficient. Automated inspection, on the other hand, cannot comprehensively reflect the color distribution across the entire screen display area, easily leading to missed detections. Furthermore, changes in ambient light on the production line and reflections from the screen's surface glass or coating can severely interfere with the accuracy of color information captured by the camera, resulting in unstable inspection results. Summary of the Invention

[0003] This invention provides a method, system, device, and storage medium for detecting screen color uniformity, in order to solve the problems of poor accuracy and low efficiency in existing screen color uniformity detection methods.

[0004] In a first aspect, the present invention provides a method for detecting screen color uniformity, the method comprising: Drive the screen under test to display the test screen; The screen to be tested is pre-illuminated, and the test screen is scanned to obtain multiple sample images; Image acquisition parameters are determined based on multiple sample images; The screen color reference image is obtained by acquiring and optimizing multiple frames of the test screen based on image acquisition parameters. A quantitative analysis of the color uniformity of the entire area is performed based on the screen color reference image to obtain the color uniformity detection results of the screen under test.

[0005] This invention drives the screen under test to display a test image, pre-illuminates the screen, and scans the test image to obtain multiple sample images. This accurately reflects interference from ambient light, screen reflections, and other factors, allowing for the determination of image acquisition parameters suitable for the current testing environment. Based on these parameters, a screen color reference image is acquired, ensuring the quality of the input data from the source and effectively solving the problem of environmental interference. A full-area color uniformity quantitative analysis is performed based on the screen color reference image to obtain the color uniformity detection results of the screen under test. This achieves full-area angular color analysis of the screen, avoiding missed detections of local color defects. Furthermore, standardized quantitative analysis ensures objective and accurate detection results. The fully automated algorithm analysis replaces manual operation, significantly improving testing efficiency and adapting to the high-volume testing needs of industrial production lines.

[0006] In one optional implementation, after acquiring and optimizing multiple frames of the test screen based on image acquisition parameters to obtain a screen color reference image, the method further includes: Determine whether the screen under test is flat; When the screen under test is not planar, the screen color reference image is calibrated.

[0007] This embodiment improves the adaptability and robustness of the detection by determining whether the screen under test is planar, and performs correction when it is not planar, thus ensuring the accuracy of subsequent analysis.

[0008] In one optional implementation, determining whether the screen to be tested is planar includes: Edge detection is performed on the screen color reference image to extract the screen boundary contour; Based on the geometric features of the screen boundary contour, determine whether the screen under test has curvature or tilt angle. When the screen under test has a curved surface or a tilt angle, it is determined that the screen under test is non-planar; When the screen under test has no curvature or tilt angle, it is determined that the screen under test is flat.

[0009] This embodiment extracts the boundary contour of the screen under test for geometric feature analysis, thereby determining whether the screen under test is planar or non-planar by the curvature and tilt angle of the surface. This allows for targeted initiation of subsequent distortion correction or direct color analysis, improving the accuracy and applicability of subsequent color uniformity detection. Furthermore, it eliminates the need for additional hardware, reducing detection costs.

[0010] In one optional implementation, when the screen under test is non-planar, correcting the screen color reference image includes: When the screen under test is non-planar, obtain the preset distortion correction parameters corresponding to the screen under test; For each pixel in the screen color reference image, the pixel coordinates are corrected based on preset distortion correction parameters to obtain the corrected pixel coordinates; Interpolate all the corrected pixel coordinates and integrate them to obtain the corrected screen color reference image.

[0011] This embodiment corrects the pixel coordinates in the image using preset distortion correction parameters when the screen under test is non-planar, eliminating the color space distribution distortion caused by the physical shape of the screen. This ensures that the color data extracted from any position in the image corresponds to the display color of the actual physical position of the screen, laying the foundation for subsequent accurate analysis.

[0012] In one optional implementation, a full-area color uniformity quantification analysis is performed based on a screen color reference image to obtain the color uniformity detection result of the screen under test, including: Identify the effective display area in the screen color reference image and divide the effective display area into multiple sub-regions; The effective display area is converted to a uniform color space to obtain the color feature value of each pixel in the effective display area; For each sub-region, calculate the average of the color feature values ​​of all pixels in the sub-region, and use it as the region color vector of the sub-region; Calculate the average value of the regional color vectors of all sub-regions as the overall color reference; Based on the overall color reference and the regional color vector of each sub-region, the color uniformity detection result of the screen under test is determined.

[0013] This embodiment effectively divides the region and performs uniform color space conversion to calculate the regional color vector of the sub-region and the overall color reference, providing an objective and accurate basis for color uniformity detection.

[0014] In one optional implementation, the color uniformity detection result of the screen under test is determined based on the overall color reference and the regional color vector of each sub-region, including: Calculate the color difference between the color vector of each region and the overall color reference; When the color difference corresponding to the color vectors of all regions is less than the preset threshold, the color uniformity test result of the screen under test is determined to be qualified. If the color difference corresponding to the color vector in any region is not less than a preset threshold, the color uniformity test result of the screen under test is determined to be unqualified.

[0015] This embodiment calculates the color difference between the regional color vector and the overall color reference, and determines the color uniformity detection result based on its comparison with a preset threshold, so that the detection result has the characteristics of objectivity and accuracy.

[0016] In one optional implementation, image acquisition parameters are determined based on multiple sample images, including: For each sample image, calculate the image quality evaluation index of the sample image; Obtain the image acquisition parameters corresponding to the sample image with the highest image quality evaluation index.

[0017] This embodiment selects the optimal image acquisition parameters from multiple sample images based on image quality evaluation indicators, ensuring the imaging quality of subsequent screen color reference images from the source, and laying the foundation for subsequent high-precision color uniformity analysis.

[0018] Secondly, the present invention provides a screen color uniformity detection system, the system comprising: The display driver module is used to drive the screen under test to display the test screen. A controllable lighting module is used to pre-illuminate the screen under test; The image acquisition module is used to scan the test screen to obtain multiple sample images. Based on the image acquisition parameters, it acquires and optimizes multiple frames of the test screen to obtain a screen color reference image. The processing and control module is used to determine image acquisition parameters based on multiple sample images, perform full-area color uniformity quantification analysis based on the screen color reference image, and obtain the color uniformity detection result of the screen under test.

[0019] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the screen color uniformity detection method of the first aspect or any corresponding embodiment described above.

[0020] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the screen color uniformity detection method of the first aspect or any corresponding embodiment described above. Attached Figure Description

[0021] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of a screen color uniformity detection system according to an embodiment of the present invention. Figure 2 This is a schematic diagram of another screen color uniformity detection system according to an embodiment of the present invention; Figure 3 This is a flowchart of a screen color uniformity detection method according to an embodiment of the present invention; Figure 4 This is a schematic diagram comparing a sample image and a screen color reference image according to an embodiment of the present invention; Figure 5 This is a comparative schematic diagram of image correction according to an embodiment of the present invention; Figure 6 This is a schematic diagram of a sub-region according to an embodiment of the present invention; Figure 7 This is a schematic diagram illustrating the color difference calculation principle according to an embodiment of the present invention; Figure 8 This is a flowchart of another screen color uniformity detection method according to an embodiment of the present invention; Figure 9 This is a schematic diagram of a color difference thermogram according to an embodiment of the present invention; Figure 10 This is a schematic diagram of a visual display interface according to an embodiment of the present invention; Figure 11 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0025] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0026] Current methods for testing screen color uniformity typically involve manual visual inspection or automated measurement using luminance / colorimeters at single points or with a small number of sampling points. However, manual inspection is affected by subjective factors, lacks a unified and objective judgment standard, and has low efficiency. Automated inspection, on the other hand, cannot comprehensively reflect the color distribution of the entire screen display area, making it prone to missed detections. Furthermore, interference light can affect the accuracy of color information captured by the camera, leading to unstable test results.

[0027] This invention pre-illuminates the screen under test and scans the test image to obtain multiple sample images. These sample images are then used to determine image acquisition parameters suitable for the current testing environment. Based on this, a screen color reference image is acquired, ensuring the quality of the input data from the source and effectively solving the problem of environmental interference. Based on the screen color reference image, a full-area color uniformity quantitative analysis is performed to obtain the color uniformity detection results of the screen under test. This achieves full-area angular color analysis of the screen, avoiding missed detections of local color defects. Furthermore, the standardized quantitative analysis ensures the objectivity and accuracy of the detection results. Simultaneously, the fully automated algorithm analysis replaces manual operation, significantly improving detection efficiency.

[0028] Figure 1 This is a schematic diagram of a screen color uniformity detection system according to an embodiment of the present invention, as shown below. Figure 1 As shown, the display driver module is used to drive the screen under test to display the test image; the controllable illumination module is used to pre-illuminate the screen under test; the image acquisition module is used to scan the test image to obtain multiple sample images, acquire multiple frames of the test image based on the image acquisition parameters and optimize them to obtain the screen color reference image; the processing control module is used to determine the image acquisition parameters based on multiple sample images, perform full-area color uniformity quantification analysis based on the screen color reference image, and obtain the color uniformity detection result of the screen under test.

[0029] Specifically, the display driver module is electrically connected to the screen under test (SUT) and drives it to display a preset test image for color uniformity detection, such as a uniform pure white, red, green, blue, or grayscale image across the entire screen. The controllable illumination module includes a programmable, adjustable ring-shaped LED light source, mounted around the lens of the image acquisition module, to provide stable and uniform illumination to the screen surface, suppressing ambient light and reducing the impact of specular reflections on color acquisition. The image acquisition module includes at least one industrial color camera with its optical lens mounted directly over the SUT to capture the image displayed on the screen. The processing and control module communicates with the display driver module, controllable illumination module, and image acquisition module, such as via Ethernet, USB, or GPIO, to coordinate and control the entire testing process.

[0030] Figure 2This is a schematic diagram of another screen color uniformity detection system according to an embodiment of the present invention, such as... Figure 2 As shown, during the detection process, the processing control module sends a signal to the display driver module ( Figure 2 (Not shown) A command is sent to drive the screen under test to display the test image. Next, the processing control module controls the controllable illumination module to activate pre-illumination and triggers the image acquisition module to scan and acquire sample images. Subsequently, the image acquisition module sends the sample images back to the processing control module. The processing control module performs feature analysis on the sample images, calculates suitable image acquisition parameters, and sends them back to the image acquisition module. Based on these optimized parameters, the image acquisition module performs high-precision formal acquisition of the test image, obtaining a screen color reference image, which is then sent back again. Finally, the processing control module performs full-area color uniformity quantification analysis based on the received screen color reference image to obtain the color uniformity detection result of the screen under test.

[0031] Under the coordinated control of the processing control module, each module works together to complete the entire process from screen driving display and image acquisition to color uniformity evaluation.

[0032] According to an embodiment of the present invention, a screen color uniformity detection method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0033] This embodiment provides a screen color uniformity detection method, which can be used in the aforementioned screen color uniformity detection system. Figure 3 This is a flowchart of a screen color uniformity detection method according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps: Step S301: Drive the screen under test to display the test screen.

[0034] Specifically, the display driver module drives the screen under test to randomly display a test screen specifically for color uniformity detection, and the test screen remains unchanged during a single test.

[0035] Step S302: Pre-illuminate the screen to be tested and scan the test screen to obtain multiple sample images.

[0036] Specifically, pre-illumination refers to adaptive supplemental lighting before the formal data acquisition. The controllable illumination module pre-illuminates the screen under test, and the image acquisition module scans the test screen to obtain multiple sample images, which can realistically reflect interference such as ambient light and screen reflections. Specifically, the image acquisition module uses different image acquisition parameters for each sample image. For scenarios where ambient light interference needs to be suppressed, the image acquisition module can fix the exposure and acquire images by iterating through the brightness of the light source. For scenarios where the brightness of the screen itself varies greatly, the image acquisition module can fix the light source and acquire images by iterating through the exposure time. Furthermore, the light source brightness can be coarsely adjusted first, followed by fine-tuning the exposure time, balancing efficiency and accuracy.

[0037] Step S303: Determine image acquisition parameters based on multiple sample images.

[0038] Specifically, the processing and control module analyzes the sample images to determine the optimal image acquisition parameters suitable for the current detection environment.

[0039] Step S304: Acquire multiple frames of the test screen based on the image acquisition parameters and optimize them to obtain the screen color reference image.

[0040] Specifically, the image acquisition module acquires multiple frames of the test screen based on image acquisition parameters adapted to the current environment. Through pixel-level filtering and fusion to eliminate transient interference, it obtains a high-quality screen color reference image that is non-reflective, accurately reproduces colors, and can be directly used for subsequent color analysis. This ensures the quality of the detection input data from the source, effectively solves the problem of environmental interference, and guarantees the accuracy of the detection results.

[0041] In some alternative implementations, Figure 4 This is a comparative diagram of a sample image and a screen color reference image according to an embodiment of the present invention, such as... Figure 4 As shown, the left image is a sample image acquired under conditions of ambient light interference or reflection, resulting in overexposure or color distortion in some areas. The right image is a screen color reference image, obtained through image acquisition parameter optimization and multi-frame image fusion, resulting in uniform screen color, clear details, and no interference light.

[0042] Step S305: Perform full-area color uniformity quantification analysis based on the screen color reference image to obtain the color uniformity detection result of the screen under test.

[0043] Specifically, unlike the subjective judgment of manual inspection or the incomplete coverage of automated inspection of individual sampling points, the embodiments of the present invention conduct quantitative analysis of color uniformity across the entire screen color reference image, transforming screen color uniformity into objective data indicators. This not only achieves full-area angular color analysis of the screen, avoiding missed detection of local color defects, but also ensures that the detection results are objective and accurate through standardized quantitative analysis. At the same time, the fully automated algorithm analysis replaces manual operation, significantly improving detection efficiency.

[0044] This invention drives the screen under test to display a test image, pre-illuminates the screen, and scans the test image to obtain multiple sample images. This accurately reflects interference from ambient light, screen reflections, and other factors, allowing for the determination of image acquisition parameters suitable for the current testing environment. Based on these parameters, a screen color reference image is acquired, ensuring the quality of the input data from the source and effectively solving the problem of environmental interference. A full-area color uniformity quantitative analysis is performed based on the screen color reference image to obtain the color uniformity detection results of the screen under test. This achieves full-area angular color analysis of the screen, avoiding missed detections of local color defects. Furthermore, standardized quantitative analysis ensures objective and accurate results. The fully automated algorithm analysis replaces manual operation, improving testing efficiency and adapting to the high-volume testing needs of industrial production lines.

[0045] This embodiment provides a screen color uniformity detection method, which can be used in the aforementioned screen color uniformity detection system. The method specifically includes the following steps: Step S401: Drive the screen under test to display the test screen. For details, please refer to [link to relevant documentation]. Figure 3 Step S301 of the illustrated embodiment will not be described again here.

[0046] Step S402: Pre-illuminate the screen to be tested and scan the test screen to obtain multiple sample images. For details, please refer to [link to relevant documentation]. Figure 3 Step S302 of the illustrated embodiment will not be described again here.

[0047] Step S403: Determine image acquisition parameters based on multiple sample images.

[0048] Specifically, step S403 includes: Step S4031: For each sample image, calculate the image quality evaluation index of the sample image.

[0049] Specifically, image quality evaluation indicators are calculated for each sample image to objectively assess the image imaging quality under different image acquisition parameters. These indicators can be flexibly selected based on actual detection needs: Average grayscale value: ensures the screen area is within the camera's optimal response range, avoiding overexposure or underexposure; Image entropy: measures the amount of information contained in the image; a higher entropy value indicates richer image details; Contrast ratio: measures the brightness levels of the image; moderate contrast is beneficial for subsequent color analysis; Signal-to-noise ratio: measures the image's resistance to interference; a higher signal-to-noise ratio indicates better image quality. Optionally, the above four indicators are merely examples; other indicators can also be used. Furthermore, in practical applications, a single indicator or a weighted fusion of multiple indicators can be selected; this embodiment of the invention does not impose any limitations on this.

[0050] Step S4032: Obtain the image acquisition parameters corresponding to the sample image with the highest image quality evaluation index.

[0051] Specifically, the image acquisition parameters of the sample image with the highest image quality evaluation index are used as the parameters for subsequent formal acquisition. This is the imaging configuration that is most suitable for the current detection environment, ensuring the best quality of subsequent benchmark images.

[0052] By selecting the optimal image acquisition parameters from multiple sample images based on image quality evaluation indicators, the imaging quality of subsequent screen color reference images is guaranteed from the source, laying the foundation for subsequent high-precision color uniformity analysis.

[0053] Step S404: Acquire multiple frames of the test screen based on the image acquisition parameters and optimize them to obtain a screen color reference image. For details, please refer to [link to relevant documentation]. Figure 3 Step S304 of the illustrated embodiment will not be described again here.

[0054] Step S405: Determine whether the screen to be tested is flat.

[0055] Specifically, step S405 includes: Step S4051: Perform edge detection on the screen color reference image and extract the screen boundary contour.

[0056] Specifically, edge detection algorithms (such as Canny edge detection) are used to identify locations of abrupt changes in brightness in the image, thereby extracting the contours representing the outer boundary of the screen. Optionally, the image can be grayscaled and filtered before edge detection to reduce noise interference.

[0057] Step S4052: Based on the geometric features of the screen boundary contour, determine whether the screen under test has a curved surface or a tilt angle.

[0058] Specifically, contour points located on the screen boundary contour are extracted, and straight line fitting and curve fitting are performed on the vertical contour points, with the fitting errors calculated for each. If the curve fitting error is significantly smaller than the straight line fitting error, and the curvature of all vertical contour points is within a preset range, and the curvature difference between adjacent vertical contour points is within a preset range, then the screen under test is considered to have surface curvature. The coordinates of the four corner points of the screen are extracted from the screen boundary contour, and the length of each side, the ratio of opposite side lengths, and the angle of each interior angle are calculated. The opposite side lengths of a standard rectangular screen are nearly equal, and the interior angles are all close to 90°. Therefore, if the calculated ratio of opposite side lengths deviates significantly from 1 or the interior angle deviates significantly from 90°, then the screen under test is considered to have a tilt angle.

[0059] Step S4053: When the screen under test has a curved surface or tilt angle, determine that the screen under test is non-planar.

[0060] Specifically, if the judgment result of step S4052 satisfies any one of the conditions, namely, the presence of a curved surface, a tilt angle, or both, then the display surface of the screen under test is not in an ideal planar state, and therefore the screen under test is determined to be a non-planar screen. More specifically, if the screen under test has a curved surface, it is considered to be a curved screen; if the screen under test has a tilt angle, it is considered to be installed at an angle.

[0061] Step S4054: When the screen under test does not have curvature or tilt angle, the screen under test is determined to be flat.

[0062] Specifically, if the judgment result of step S4052 is that there is neither curved surface curvature nor tilt angle, it means that the screen boundary outline conforms to the standard rectangular characteristics and the geometric shape has no obvious distortion, then the screen under test is considered to be flat.

[0063] Optionally, steps S4051-S4054 above are image contour-based judgment methods, but judgment can also be made using model information and sensors. The model information-based judgment method is suitable for batch inspection scenarios on production lines. The system can pre-establish a mapping database between screen models and shape types. Before inspection, the model information of the screen to be tested is obtained through a barcode scanner or manual selection. The processing control module queries the database based on the model information to quickly and accurately determine whether the surface to be tested is flat, curved, or tilted. The distance sensor-based judgment method is suitable for judging tilted installation scenarios. Multiple distance sensors (such as laser rangefinders and infrared sensors) can be installed near the image acquisition module, aligned with multiple preset positions on the screen surface (such as the four corners of the screen), and the distance values ​​at each preset position are collected. If the maximum difference between the distance values ​​is greater than a preset distance threshold (such as 2mm), it indicates that the screen plane is not perpendicular to the camera optical axis, and it is judged as tilted installation; if the difference is within the threshold range, it is judged as upright installation.

[0064] By extracting the boundary contour of the screen under test for geometric feature analysis, the curvature and tilt angle of the surface can be used to determine whether the screen under test is planar or non-planar. This allows for targeted distortion correction or direct color analysis, improving the accuracy and applicability of subsequent color uniformity detection. Furthermore, no additional hardware is required, reducing detection costs.

[0065] Step S406: When the screen to be tested is not planar, correct the screen color reference image.

[0066] Specifically, step S406 includes: Step S4061: When the screen under test is non-planar, obtain the preset distortion correction parameters corresponding to the screen under test.

[0067] Specifically, when the screen under test is non-planar, including curved surfaces and tilted installations, the images acquired by the image acquisition module will exhibit geometric distortion or perspective deformation, failing to accurately reflect the actual color display position of the screen. Therefore, image correction is necessary. First, the processing control module calls pre-stored distortion correction parameters that match the non-planar screen. These parameters are pre-calibrated and stored for different types of non-planar screens, used to restore the image to a standard state.

[0068] Step S4062: For each pixel in the screen color reference image, the pixel coordinates are corrected based on preset distortion correction parameters to obtain the corrected pixel coordinates.

[0069] Specifically, based on the optical distortion of curved screens and the perspective distortion of tilted screens, a suitable geometric correction algorithm model (such as perspective transformation, polynomial distortion correction model, etc.) is selected. The preset distortion correction parameters are the core operation coefficients of the algorithm model (such as perspective transformation matrix, polynomial coefficients). For each pixel in the screen color reference image, the coordinates of the pixel are substituted into the coordinate transformation formula of the corresponding geometric correction algorithm model, and the preset distortion correction parameters are used as operation coefficients to calculate the corrected pixel coordinates, which are the coordinates of the pixel in the standard planar front view.

[0070] Step S4063: Interpolate all the corrected pixel coordinates and integrate them to obtain the corrected screen color reference image.

[0071] Specifically, the corrected pixel coordinates may overlap and be missing. Direct integration would lead to pixel loss and image distortion. Therefore, the processing control module needs to interpolate all corrected pixel coordinates, and then integrate and stitch together all the interpolated pixels and their corresponding coordinates to obtain the corrected screen color reference image. This image is actually a standard planar front view of the screen under test. Interpolation refers to using algorithms such as nearest neighbor interpolation and bilinear interpolation to fill in missing pixel values ​​in pixel gaps and normalize overlapping pixel coordinates.

[0072] By correcting the pixel coordinates in the image using preset distortion correction parameters when the screen under test is non-planar, the color space distribution distortion caused by the physical shape of the screen is eliminated, ensuring that the color data extracted from any position in the image corresponds to the display color of the actual physical position of the screen, laying the foundation for subsequent accurate analysis.

[0073] In some alternative implementations, Figure 5 This is a comparative schematic diagram of image correction according to an embodiment of the present invention, such as... Figure 5 As shown, the left image is a partial color reference image of the screen located at the edge of the screen. Because the screen under test is curved, the color blocks in this part of the image are significantly distorted due to the physical curvature. The right image is the corrected image, where the color blocks are "straightened" and restored to regular rectangles, simulating a planar front view.

[0074] Step S407: Perform full-area color uniformity quantification analysis based on the screen color reference image to obtain the color uniformity detection result of the screen under test.

[0075] Specifically, step S407 includes: Step S4071: Identify the effective display area in the screen color reference image and divide the effective display area into multiple sub-regions.

[0076] Specifically, the processing control module intelligently identifies the screen color reference image, selects the effective display area of ​​the screen, that is, the area that can actually display images and present colors, excludes areas with no display function such as borders and black borders, and then uses grid lines to evenly divide the effective display area into multiple sub-areas.

[0077] In some alternative implementations, Figure 6 This is a schematic diagram of a sub-region according to an embodiment of the present invention, such as... Figure 6 As shown, the effective display area in the screen color reference image is evenly divided into 9 sub-regions, namely R1-R9.

[0078] Step S4072: Convert the effective display area to a uniform color space to obtain the color feature value of each pixel in the effective display area.

[0079] Specifically, the original pixels within the effective display area are represented using the RGB color space. This space does not correspond non-linearly to human visual perception and cannot objectively reflect color differences. Therefore, it needs to be converted to the CIE 1976 Lab uniform color space, which is a device-independent standard color space with uniformity closely matching human visual perception. The RGB values ​​are converted into corresponding L*, a*, b* values, i.e., color feature values, using a standard color space mapping formula. This eliminates the color judgment bias caused by the non-linearity of the RGB space, making subsequent color difference calculation results more closely match the actual visual perception of the human eye. Here, L* represents luminance, a* represents red-green axis chromaticity, and b* represents yellow-blue axis chromaticity.

[0080] Step S4073: For each sub-region, calculate the average value of the color feature values ​​of all pixels in the sub-region, and use it as the region color vector of the sub-region.

[0081] Specifically, for each sub-region, the average value of L*, a*, b* of all pixels in that sub-region is calculated as the region color vector of that sub-region, representing the overall color characteristics of the sub-region and avoiding interference from single-pixel noise.

[0082] Step S4074: Calculate the average value of the regional color vectors of all sub-regions as the overall color reference.

[0083] Specifically, the average value of the regional color vectors of all sub-regions is used as the overall color benchmark of the screen under test, serving as the color reference standard for the entire area of ​​the screen under test.

[0084] Step S4075: Based on the overall color reference and the regional color vector of each sub-region, determine the color uniformity detection result of the screen under test.

[0085] Specifically, step S4075 includes: Step a1: Calculate the color difference between the color vector of each region and the overall color reference.

[0086] Specifically, Figure 7 This is a schematic diagram illustrating the color difference calculation principle according to an embodiment of the present invention, as shown below. Figure 7 As shown, the CIE 1976Lab uniform color space consists of the L* axis, a* axis, and b* axis. The blue dot represents the overall color reference, denoted by (L_avg, a_avg, b_avg); the green dot represents the color vector Ri of any region, denoted by (L_i, a_i, b_i). The line connecting the two axes represents the distance between them, i.e., the color difference, expressed by the formula: This distance is the Euclidean distance. Therefore, in actual testing, the CIE 1976 standard color difference formula, which is the Euclidean distance calculation formula, is used to calculate the color difference between the color vector of each region and the overall color reference. This can quantify the degree of deviation between each sub-region and the overall screen color, ensuring the objectivity and rationality of quantifying color differences and avoiding the subjectivity of manual visual inspection.

[0087] Step a2: When the color difference corresponding to the color vectors of all regions is less than the preset threshold, the color uniformity test result of the screen under test is determined to be qualified.

[0088] Specifically, when the color difference of all sub-regions is less than the preset threshold, it indicates that the deviation of the color of each region of the screen relative to the overall benchmark is within an acceptable range, and the color distribution is consistent. Therefore, the color uniformity test result of the screen under test is determined to be qualified.

[0089] Step a3: If the color difference corresponding to the color vector in any region is not less than a preset threshold, the color uniformity test result of the screen under test is determined to be unqualified.

[0090] Specifically, if the color difference of any sub-region is not less than the preset threshold, it indicates that there is a significant color deviation in that region, and the overall color consistency of the screen does not meet the requirements. Therefore, the color uniformity test result of the screen under test is determined to be unqualified.

[0091] In some alternative implementations, Figure 8 This is a flowchart of another screen color uniformity detection method according to an embodiment of the present invention, such as... Figure 8 As shown, the display driver module drives the screen under test to display the test image, the controllable illumination module provides pre-illumination, and the image acquisition module scans the sample image so that the processing control module can determine the image acquisition parameters. Based on the image acquisition parameters, the image acquisition module acquires a color reference image of the screen. It determines whether the image is planar; if not, it corrects it based on preset distortion correction parameters and performs interpolation. The subsequent processing after correction is consistent with the processing for a planar screen under test. The processing control module identifies the effective display area and divides it into sub-regions. The processing control module performs color space conversion on the effective display area to obtain the color feature value of each pixel, thereby calculating the regional color vector of each sub-region and the overall color reference. It calculates the color difference between the color vector of each region and the overall color reference. If both are less than a preset threshold, the color uniformity test result is qualified; if any color difference is not less than the preset threshold, the color uniformity test result is unqualified.

[0092] In some optional implementations, sub-regions with color differences not less than a preset threshold are marked as exceeding the standard, and a detection report is generated based on the color difference of each sub-region. Simultaneously, a system can be formed based on the color difference of each sub-region. Figure 9The color difference heatmap shown represents the color difference value in each sub-region. The shades of color (e.g., a gradient from green to red) visually indicate the magnitude of the color difference. The legend on the right illustrates the correspondence between color and color difference. Figure 9 It can visually show the specific location and severity of uneven color.

[0093] In some alternative implementations, Figure 10 This is a schematic diagram of a visual display interface according to an embodiment of the present invention, such as... Figure 10 As shown, the system also includes a visual display interface that can display the overall color reference and the L*, a*, b* values ​​and color difference of each sub-region, as well as display model settings, parameter settings, and other content.

[0094] This invention drives the screen under test to display a test image, pre-illuminates the screen, and scans the test image to obtain multiple sample images. This accurately reflects interference from ambient light, screen reflections, and other factors, allowing for the determination of image acquisition parameters suitable for the current testing environment. Based on these parameters, a screen color reference image is acquired, ensuring the quality of the input data from the source and effectively solving the problem of environmental interference. A full-area color uniformity quantitative analysis is performed based on the screen color reference image to obtain the color uniformity detection results of the screen under test. This achieves full-area angular color analysis of the screen, avoiding missed detections of local color defects. Furthermore, standardized quantitative analysis ensures objective and accurate results. The fully automated algorithm analysis replaces manual operation, improving testing efficiency and adapting to the high-volume testing needs of industrial production lines.

[0095] The embodiments of the present invention have the following beneficial effects: (1) Achieved full-area, objective quantitative evaluation: By dividing the sub-area and calculating the color difference based on the CIE L*a*b* space, the subjective uniformity judgment is transformed into an objective and quantifiable color difference, and the test results are consistent and reliable. (2) Improved anti-interference capability and detection stability: The use of pre-illuminated scanning and multi-frame image fusion effectively overcomes the interference of changes in ambient light and screen reflection in the industrial field, ensuring the quality of the acquired images and thus improving the stability of the detection results of the entire system. (3) Enhanced adaptability to complex screen shapes: By correcting non-planar screens, it is possible to accurately evaluate the color uniformity of curved screens and tilted screens, thus expanding the application range. (4) Improved the detection efficiency and automation of the production line: The system operates fully automatically, from driving the screen and collecting images to analyzing and outputting reports, without the need for manual intervention. The detection time for a single test can be controlled within a few seconds, which greatly improves production efficiency and reduces labor costs. (5) Highly targeted and efficient: By calculating the average value, it directly addresses the specific industrial testing need of uniformity. While ensuring the scientific nature of the assessment, it has lower computational complexity, faster processing speed, and is more suitable for online real-time testing.

[0096] Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0097] The following is a detailed reference. Figure 11 The diagram illustrates a structural schematic suitable for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, a graphics processing unit, etc.) 1101, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1102 or a program loaded from memory 1108 into random access memory (RAM) 1103. The RAM 1103 also stores various programs and data required for the operation of the electronic device. The processor 1101, ROM 1102, and RAM 1103 are interconnected via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0098] Typically, the following devices can be connected to I / O interface 1105: input devices 1106 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 1107 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 1108 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1109. Communication device 1109 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 11 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0099] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 1109, or installed from a memory 1108, or installed from a ROM 1102. When the computer program is executed by the processor 1101, it performs the functions defined in the screen color uniformity detection method of the embodiments of the present invention.

[0100] Figure 11The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0101] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the screen color uniformity detection method shown in the above embodiments is implemented.

[0102] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for detecting screen color uniformity, characterized in that, The method includes: Drive the screen under test to display the test screen; The screen under test is pre-illuminated, and the test screen is scanned to obtain multiple sample images; Image acquisition parameters are determined based on the multiple sample images; Based on the image acquisition parameters, multiple frames of the test screen are acquired and optimized to obtain a screen color reference image; Based on the screen color reference image, a full-area color uniformity quantification analysis is performed to obtain the color uniformity detection result of the screen under test.

2. The method according to claim 1, characterized in that, After acquiring and optimizing multiple frames of the test screen based on the image acquisition parameters to obtain a screen color reference image, the method further includes: Determine whether the screen under test is flat; When the screen under test is not planar, the screen color reference image is calibrated.

3. The method according to claim 2, characterized in that, The step of determining whether the screen under test is flat includes: Edge detection is performed on the screen color reference image to extract the screen boundary contour; Based on the geometric features of the screen boundary contour, determine whether the screen under test has a curved surface or a tilt angle. When the screen under test has a curved surface or a tilt angle, the screen under test is determined to be non-planar. When the screen under test has no curvature or tilt angle, the screen under test is determined to be flat.

4. The method according to claim 2, characterized in that, When the screen under test is non-planar, correcting the screen color reference image includes: When the screen under test is non-planar, obtain the preset distortion correction parameters corresponding to the screen under test; For each pixel in the screen color reference image, the coordinates of the pixel are corrected based on the preset distortion correction parameters to obtain the corrected pixel coordinates; Interpolate all the corrected pixel coordinates and integrate them to obtain the corrected screen color reference image.

5. The method according to claim 1, characterized in that, The step of performing full-area color uniformity quantization analysis based on the screen color reference image to obtain the color uniformity detection result of the screen under test includes: Identify the effective display area in the screen color reference image and divide the effective display area into multiple sub-regions; The effective display area is converted to a uniform color space to obtain the color feature value of each pixel in the effective display area; For each sub-region, the average value of the color feature values ​​of all pixels in the sub-region is calculated as the region color vector of the sub-region; Calculate the average value of the regional color vectors of all sub-regions as the overall color reference; Based on the overall color reference and the regional color vector of each sub-region, the color uniformity detection result of the screen under test is determined.

6. The method according to claim 5, characterized in that, The determination of the color uniformity detection result of the screen under test based on the overall color reference and the regional color vector of each sub-region includes: Calculate the color difference between the color vector of each region and the overall color reference; When the color difference corresponding to the color vectors of all regions is less than a preset threshold, the color uniformity test result of the screen under test is determined to be qualified. If the color difference corresponding to the color vector in any region is not less than the preset threshold, the color uniformity test result of the screen under test is determined to be unqualified.

7. The method according to claim 1, characterized in that, The process of determining image acquisition parameters based on the multiple sample images includes: For each sample image, calculate the image quality evaluation index of the sample image; Obtain the image acquisition parameters corresponding to the sample image with the highest image quality evaluation index.

8. A screen color uniformity detection system, characterized in that, The system includes: The display driver module is used to drive the screen under test to display the test screen. A controllable lighting module is used to pre-illuminate the screen under test; The image acquisition module is used to scan the test screen to obtain multiple sample images, acquire multiple frames of the test screen based on the image acquisition parameters and optimize them to obtain a screen color reference image; The processing and control module is used to determine image acquisition parameters based on the multiple sample images, perform full-area color uniformity quantification analysis based on the screen color reference image, and obtain the color uniformity detection result of the screen under test.

9. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the screen color uniformity detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the screen color uniformity detection method according to any one of claims 1 to 7.

Images