An image projection detection method and system

Abstract

The present invention provides an image projection detection method and system, which relates to the technical field of image projection detection. The present invention quickly divides the original image into multiple image regions, accurately identifies the display main body, automatically aligns the actual projection image with the original image, and divides them into corresponding projection regions, facilitating the rapid detection of image projection. Secondly, according to factors such as the content, layout, text density, contrast or visual focus of the display main body, a weight value is assigned to each projection region, and multiple weight levels are determined accordingly, enabling the prioritized processing of more important regions during the detection process, thereby optimizing the allocation of detection resources while ensuring the detection quality. Finally, when the characteristic parameters in the actual projection image exceed the calibration threshold range, they can be quickly marked as abnormal, realizing the rapid identification of abnormal regions in the projection image and improving the detection accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of image projection detection, and particularly to an image projection detection method and system. Background Art

[0002] During the projection process, due to the influence of various factors such as device performance, environmental conditions, and projection materials, the quality of the projected image often fluctuates. These fluctuations may manifest as problems such as blurred images, color distortion, uneven brightness, etc., seriously affecting the visual experience of the audience and the effect of information transmission. Therefore, it is necessary to detect image projection.

[0003] Traditional projection image detection methods often adopt a global detection strategy, that is, uniformly process and analyze the entire projected image. However, in practical applications, the projected image often contains multiple different display subjects, such as text, graphics, charts, etc., and these display subjects have significant differences in terms of content, layout, and importance. Therefore, adopting a global detection strategy often makes it difficult to accurately reflect the actual situation of different display subjects and cannot achieve priority processing of important regions.

[0004] Secondly, traditional projection image detection methods or systems are difficult to quickly identify and locate abnormal regions. With the continuous development of projection technology, the resolution and complexity of projected images are also increasing. This makes the detection work of projected images become more and more onerous, and the requirements for computing resources and time costs are also getting higher and higher. However, traditional detection methods often cannot achieve priority processing of different important regions, resulting in waste of detection resources and low detection efficiency.

[0005] Therefore, it is necessary to provide an image projection detection method and system to solve the above technical problems. Summary of the Invention

[0006] To solve the above technical problems, the present invention provides an image projection detection method and system for solving the problems that traditional projection image detection methods are difficult to accurately reflect the actual situation of different display subjects, slow in identifying abnormal regions, waste of detection resources, and low detection efficiency.

[0007] An image projection detection method provided by the present invention, the detection method includes the following steps:

[0008] Obtain the original image and divide it into multiple image regions according to the range of the display subject;

[0009] Obtain the actual projected image through an image acquisition device, and divide the actual projected image into multiple projection regions corresponding to the image regions according to the divided multiple image regions;

[0010] Assign weights to the display subjects by evaluating their importance, and combine with the preset weight threshold range to divide the multiple projected areas into different projection weight levels, where the projection weight levels specifically include low level, medium level, and high level;

[0011] Extract the characteristic parameters of the display subjects in the original image, and set corresponding verification threshold ranges for each projected area according to the extracted characteristic parameters of the display subjects in the original image, where the higher the projection weight level of the projected area, the smaller the verification threshold range;

[0012] Extract the characteristic parameters of the image information of multiple projected areas in the actual projected image through image processing technology, and compare the extracted characteristic parameters of the image information of multiple projected areas with the corresponding verification threshold ranges, and the characteristic parameters that exceed the verification threshold range are displayed as abnormal.

[0013] Preferably, the steps of obtaining the original image and dividing it into multiple image areas according to the range of the display subject are as follows:

[0014] Obtain the original image to be projected and identify the display subjects in the original image, where the display subjects include text, graphics, or charts;

[0015] Divide the original image into multiple image areas according to the content or layout of the display subject, and at the same time assign a unique identifier to each divided image area and record the boundary coordinates of each image area.

[0016] Preferably, the steps of obtaining the actual projected image through an image acquisition device and dividing the actual projected image into multiple projected areas corresponding to the image areas are as follows:

[0017] Use a projection device to project the original image onto the target surface, and obtain the actual projected image through the camera or scanning device in the image acquisition device;

[0018] Align the coordinates of the actual projected image with the coordinates of the original image according to the multiple divided image areas, and divide the actual projected image into multiple projected areas accordingly;

[0019] Record the boundary coordinates and identifiers of each projected area.

[0020] Preferably, the steps of assigning weights to the display subjects by evaluating their importance and dividing the multiple projected areas into different projection weight levels by combining with the preset weight threshold range are as follows:

[0021] Evaluate each display subject according to the text density, contrast, or visual focus range of the layout, and according to the preset multiple scoring threshold ranges, to obtain the evaluation results of each display subject;

[0022] Set corresponding weight values for multiple preset scoring threshold ranges respectively, and assign weight values corresponding to the evaluation results to each display subject according to the evaluation values of each display subject;

[0023] Assign a weight value to each projection area according to the weight value of the display subject, and divide each projection area into corresponding low, medium or high three weight levels according to the preset weight threshold range.

[0024] Preferably, extract the characteristic parameters of the display subject in the original image, and set corresponding verification threshold ranges for each projection area according to the extracted characteristic parameters of the display subject in the original image, wherein the higher the projection weight level of the projection area, the smaller the verification threshold range. The specific steps are as follows:

[0025] Extract the characteristic parameters of the display subject in the original image, wherein the characteristic parameters include color, brightness, contrast or clarity;

[0026] Set a basic verification threshold range for each characteristic parameter according to the extracted characteristic parameters, and set a weight coefficient for each weight level. Multiply the threshold nodes of the basic verification threshold range by the corresponding weight coefficient to obtain the adjusted verification threshold range.

[0027] Preferably, extract the characteristic parameters of the image information of multiple projection areas in the actual projection image through image processing technology, and compare the extracted characteristic parameters of the image information of multiple projection areas with the corresponding verification threshold ranges. The characteristic parameters exceeding the verification threshold range are displayed as abnormal. The specific steps are as follows:

[0028] Use image recognition or edge detection in image processing technology to extract the characteristic parameters of the image information of each projection area from the actual projection image;

[0029] Compare the extracted characteristic parameters with the adjusted verification threshold range to determine whether the extracted characteristic parameters belong to the adjusted verification threshold range;

[0030] Mark the projection area to which the characteristic parameters determined to exceed the verification threshold range belong as abnormal, and generate an abnormal report listing all the projection areas marked as abnormal and their characteristic parameters.

[0031] An image projection detection system, the detection system includes:

[0032] An image division module for obtaining the original image and dividing it into multiple image areas according to the range of the display subject;

[0033] The region division module is used to obtain the actual projection image through an image acquisition device, and divide the actual projection image into multiple projection regions corresponding to the image regions according to the divided multiple image regions;

[0034] The weight assignment module is used to assign weights to the display main body by evaluating the importance, and combine the preset weight threshold range to divide the multiple divided projection regions into projection weight levels. Specifically, the projection weight levels include low level, medium level and high level;

[0035] The feature extraction and definition module is used to extract the feature parameters of the display main body in the original image, and set the corresponding verification threshold range for each projection region according to the extracted feature parameters of the display main body in the original image. Among them, the higher the projection weight level of the projection region, the smaller the verification threshold range;

[0036] The feature detection module is used to extract the feature parameters of the image information of multiple projection regions in the actual projection image through image processing technology, and compare the extracted feature parameters of the image information of multiple projection regions with the corresponding verification threshold range. The feature parameters exceeding the verification threshold range are displayed as abnormal.

[0037] Compared with the related technologies, an image projection detection method and system provided by the present invention have the following beneficial effects:

[0038] The present invention quickly divides the original image into multiple image regions, accurately identifies the display main body, automatically aligns the actual projection image with the original image, and divides it into corresponding projection regions, which is convenient for quickly detecting the image projection. Secondly, according to factors such as the content, layout, text density, contrast or visual focus of the display main body, a weight value is assigned to each projection region, and multiple weight levels are accordingly set, so that more important regions can be preferentially processed during the detection process, thereby optimizing the allocation of detection resources while ensuring the detection quality. Finally, a flexible verification threshold range is set for each projection region according to the feature parameters. When the feature parameters in the actual projection image exceed the verification threshold range, it can quickly mark them as abnormal, realizing the rapid identification of abnormal regions in the projection image and improving the detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a flowchart of an image projection detection method of the present invention;

[0040] Figure 2 is a system block diagram of an image projection detection system of the present invention.<F DETAILED DESCRIPTION OF THE INVENTION

[0041] The present invention will be further described below with reference to the drawings and embodiments.

[0042] Example 1

[0043] As Figure 1 shown, an image projection detection method specifically includes the following steps:

[0044] S1. Obtain the original image and divide it into multiple image regions according to the range of the display subject;

[0045] S2. Obtain the actual projection image through an image acquisition device, and divide the actual projection image into multiple projection regions corresponding to the image regions according to the divided multiple image regions;

[0046] S3. Assign weights to the display subject by evaluating importance, and combine the preset weight threshold range to divide the multiple divided projection regions into projection weight levels, where the projection weight levels specifically include low level, medium level, and high level;

[0047] S4. Extract the characteristic parameters of the display subject in the original image, and set the corresponding verification threshold range for each projection region according to the extracted characteristic parameters of the display subject in the original image, where the higher the projection weight level of the projection region, the smaller the verification threshold range;

[0048] S5. Extract the characteristic parameters of the image information of the multiple projection regions in the actual projection image through image processing technology, and compare the extracted characteristic parameters of the image information of the multiple projection regions with the corresponding verification threshold range, and the characteristic parameters exceeding the verification threshold range are displayed as abnormal.

[0049] In the specific implementation process, the specific steps of step S1 are:

[0050] S101. Obtain the original image to be projected and identify the display subject in the original image, where the display subject includes text, graphics, or charts.

[0051] Specifically, obtain the original image to be projected through an image acquisition device such as a scanner, digital camera, or professional image acquisition software. Next, use computer vision technology in image recognition technology to analyze the original image to identify the display subject in it, where the display subject includes key information elements such as text, graphics, and charts, and these information elements need to be accurately transmitted during the projection process.

[0052] S102. Divide the original image into multiple image regions according to the content or layout of the display subject, and assign a unique identifier to each divided image region, and record the boundary coordinates of each image region.

[0053] Specifically, after identifying the display subject, the original image is divided into multiple image regions according to the content or layout characteristics of the display subject. Among them, the image regions can be divided based on the natural boundaries of the display subject (such as text paragraphs, chart frame lines, etc.), or can be divided based on preset rules (such as fixed size, fixed ratio, etc.). Then, a unique identifier is assigned to each divided image region to accurately identify and reference these regions during subsequent detection processes. Finally, the boundary coordinates of each image region are recorded, and this coordinate information is used to align the actual projection image with the original image in subsequent steps and divide the corresponding projection regions.

[0054] Exemplarily, according to the identified text regions, chart regions, and graphic regions, the original image is divided into multiple image regions. Then, a unique identifier (such as "Region 1", "Region 2", etc.) is assigned to each image region, and the boundary coordinates of each image region are recorded. In subsequent steps, these identifiers and coordinate information can be used to accurately align the actual projection image with the original image and divide the corresponding projection regions.

[0055] In the specific implementation process, the specific steps of step S2 are as follows:

[0056] S201. Use a projection device to project the original image onto the target surface, and obtain the actual projection image through a camera or a scanning device in the image acquisition device.

[0057] Specifically, project the original image to be detected onto a specified target surface through a projection device. This target surface can be a wall, a curtain, a screen, etc., and the specific choice depends on the actual application scenario and the requirements of the projection effect. During the projection process, use a camera or a scanning device in the image acquisition device to capture and record the projection image. It should be noted that in the case where both the projection device and the image acquisition device have automatic control functions, the projection and acquisition can be realized through preset programs or instructions.

[0058] S202. According to the divided multiple image regions, align the coordinates of the actual projection image with the coordinates of the original image, and divide the actual projection image into multiple projection regions accordingly.

[0059] Specifically, use image registration or image transformation in image processing technology to align the coordinates of the actual projection image with the coordinates of the original image. It should be noted that this process needs to ensure that each pixel point in the projection image can be accurately matched with the corresponding pixel point in the original image. Then, according to the divided multiple image regions, divide the actual projection image into multiple projection regions accordingly. These projection regions should correspond one by one to the image regions in the original image to ensure the accuracy of subsequent detection work.

[0060] In this embodiment, for the projection image of an enterprise's promotional materials, image processing technology is used to align the coordinates of the actual projection image with those of the original image. Then, according to the image regions (such as text regions or chart regions, etc.) divided in step S1, the actual projection image is correspondingly divided into multiple projection regions, and these projection regions correspond one-to-one with the image regions in the original image, providing an accurate data basis for subsequent detection work.

[0061] S203. Record the boundary coordinates and identifiers of each projection region.

[0062] Specifically, the boundary coordinates of each projection region are recorded by using image processing technology or manual annotation. It should be noted that this coordinate information is used to accurately locate the projection region in subsequent steps, and each projection region is assigned a unique identifier so that these regions can be accurately identified and referenced during subsequent detection.

[0063] In this embodiment, for the projection image of an enterprise's promotional materials, image processing technology automatically records the boundary coordinates of each projection region and assigns a unique identifier to it. For example, for the text region, its identifier is set to "Text_Area_1", and its boundary coordinates are recorded as (x1, y1, x2, y2). These identifier and coordinate information will be used to accurately locate the projection region during subsequent detection.

[0064] In the specific implementation process, the specific steps of step S3 are as follows:

[0065] S301. Evaluate each display subject according to the text density, contrast, or visual focus range of the layout, and based on a preset range of multiple scoring thresholds, to obtain the evaluation results of each display subject.

[0066] Specifically, text density evaluation: Text density is defined as the number of characters or pixel density per unit area, which is used to measure the density of text information in the display main body. Then, the calculated text density is compared with the preset text density scoring threshold range, and corresponding scores are given according to the comparison results; Contrast evaluation: Contrast is the brightness difference between the bright area and the dark area in an image, which affects the clarity and readability of the image. Using existing image processing software, the contrast value of each display main body can be calculated and compared with the preset contrast scoring threshold range to give corresponding scores; Layout visual focus evaluation: According to factors such as the layout position, size, and shape of the display main body in the original image, its visual focus range is evaluated. The visual focus is the area in the image that most attracts the observer's attention and usually contains the most important information. By calculating parameters such as the distance and overlap degree between the display main body and the image center or visual focus, the importance of its visual focus can be evaluated and corresponding scores can be given. Among them, multiple scoring threshold ranges are preset by humans in advance. In this embodiment, the scoring threshold ranges are set as: excellent (90 - 100 points), good (80 - 89 points), medium (70 - 79 points), passing (60 - 69 points), and failing (0 - 59 points).

[0067] S302. Set corresponding weight values for multiple preset scoring threshold ranges respectively, and assign weight values corresponding to the evaluation results to each display main body according to the evaluation values of each display main body.

[0068] Specifically, set corresponding weight values for multiple preset scoring threshold ranges respectively. Specifically, the weight values corresponding to the scoring threshold ranges of excellent (90 - 100 points), good (80 - 89 points), medium (70 - 79 points), passing (60 - 69 points), and failing (0 - 59 points) are 5, 4, 3, 2, and 1 respectively.

[0069] S303. Assign a weight value to each projection area according to the weight value of the display main body, and divide each projection area into the corresponding low, medium, or high weight levels according to the preset weight threshold range.

[0070] Specifically, for each projection area, calculate the weighted average of the weight values of all display main bodies it contains, that is, multiply the weight value of each display main body by its corresponding importance coefficient, then add up all the products, and divide by the sum of the importance coefficients of all display main bodies. It should be noted that the importance coefficient is defined according to the difference of each display main body in the projection image each time.

[0071] In this embodiment, there are two projection areas A and B. Area A contains two display elements: a chart (weight value is 3) and a text paragraph (weight value is 2); Area B also contains two display elements: a picture (weight value is 2) and a table (weight value is 1). At the same time, the importance coefficients of the chart, text paragraph, picture, and table are set to 1.5, 1.2, 1.0, and 0.8 respectively. Then, the weighted average weight value of Area A can be calculated as: (3 × 1.5 + 2 × 1.2) ÷ (1.5 + 1.2) = 2.7 ÷ 2.7 = 1.0 (where the sum of the importance coefficients of Area A is 1.5 + 1.2 = 2.7); the weighted average weight value of Area B can be calculated as: (2 × 1.0 + 1 × 0.8) ÷ (1.0 + 0.8) = 2.8 ÷ 1.8 ≈ 1.56 (the sum of the importance coefficients of Area B is 1.0 + 0.8 = 1.8).

[0072] In the specific implementation process, the specific steps of step S4 are as follows:

[0073] S401. Extract the characteristic parameters of the display elements in the original image. Among them, the characteristic parameters include color, brightness, contrast, or sharpness.

[0074] Specifically, preprocess the obtained original image, including denoising and contrast enhancement operations. According to the type of the display element and the detection requirements, select the characteristic parameters for extraction. In this embodiment, the characteristic parameters include color, brightness, contrast, or sharpness. Use existing image processing algorithms or software to extract the characteristic parameters of the preprocessed original image. Exemplarily, use the color space conversion algorithm to extract color features, use the histogram statistics method to extract brightness and contrast features, use the edge detection algorithm to extract sharpness features, etc.

[0075] S402. Set a basic verification threshold range for each characteristic parameter according to the extracted characteristic parameters, and set a weight coefficient for each weight level. Multiply the threshold nodes of the basic verification threshold range by the corresponding weight coefficients to obtain the adjusted verification threshold range.

[0076] In this embodiment, a verification threshold range for basic feature parameters such as color, brightness, and contrast is set. Then, according to the weight values assigned to each projection area in step S3, a weight coefficient is set for each weight level. Finally, we multiply the threshold nodes of the basic verification threshold range by the corresponding weight coefficients to obtain the adjusted verification threshold range. For the brightness feature parameter, the basic verification threshold range is set to [100, 200]. For the projection areas with a high-level weight level, it is adjusted to [120, 240]; for the projection areas with a low-level weight level, it is adjusted to [80, 160].

[0077] In the specific implementation process, the specific steps of step S5 are as follows:

[0078] S501. Use image recognition or edge detection in image processing technology to extract the image information feature parameters of each projection area from the actual projection image.

[0079] Specifically, preprocess the actual projection image, including denoising and enhancing the contrast operation. Perform recognition and edge detection on the preprocessed image, which is specifically implemented through existing deep learning algorithms to facilitate accurately identifying the boundaries of each projection area and extracting the image information feature parameters within the projection area. According to the feature parameters (such as color, brightness, contrast, sharpness, etc.) set in step S4, use image processing software to extract the corresponding feature parameter values from the image information of each projection area.

[0080] S502. Compare the extracted feature parameters with the adjusted verification threshold range to determine whether the extracted feature parameters belong to the adjusted verification threshold range.

[0081] Specifically, compare the feature parameter values of each projection area extracted in step S501 with the adjusted verification threshold range. According to the comparison results, classify the feature parameters of each projection area into two categories: feature parameters that belong to the adjusted verification threshold range and feature parameters that exceed the verification threshold range.

[0082] S503. Mark the projection areas to which the feature parameters that are judged to exceed the verification threshold range belong as abnormal, and generate an exception report listing all the projection areas marked as abnormal and their feature parameters.

[0083] Specifically, according to the comparison result in step S502, mark the projection area to which the feature parameters exceeding the verification threshold range belong as abnormal, which is convenient for quickly identifying the abnormal area in the projection image. Then, use image processing software to automatically generate an abnormal report, which should include all the marked abnormal projection areas, their feature parameter values, and the type of abnormality (such as exceeding the upper or lower limit of the verification threshold range). Secondly, output the generated abnormal report to the user or relevant management personnel so that they can take timely measures for repair or improvement.

[0084] Embodiment 2

[0085] As Figure 2 shown, an image projection detection system applied to an image projection detection method specifically includes:

[0086] An image division module, configured to obtain an original image and divide it into multiple image regions according to the range of the display subject;

[0087] A region division module, configured to obtain an actual projection image through an image acquisition device, and divide the actual projection image into multiple projection regions corresponding to the image regions according to the divided multiple image regions;

[0088] A weight assignment module, configured to assign weights to the display subject by evaluating the importance, and combine the preset weight threshold range to divide the multiple divided projection regions into projection weight levels, where the projection weight levels specifically include low level, medium level, and high level;

[0089] A feature extraction and definition module, configured to extract the feature parameters of the display subject in the original image, and set corresponding verification threshold ranges for each projection region according to the extracted feature parameters of the display subject in the original image, where the higher the projection weight level of the projection region, the smaller the verification threshold range;

[0090] A feature detection module, configured to extract the feature parameters of the image information of multiple projection regions in the actual projection image through image processing technology, and compare the extracted feature parameters of the image information of multiple projection regions with the corresponding verification threshold ranges, and the feature parameters exceeding the verification threshold range are displayed as abnormal.

[0091] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in one block or multiple blocks.

[0092] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program. This program can be stored in a computer-readable storage medium, which includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM), or other optical disc memories, magnetic disk memories, tape memories, or any other medium that can be used to carry or store data and is computer-readable.

[0093] It should also be noted that the term "comprising", "including", or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity, or device comprising a series of elements not only includes those elements but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, commodity, or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of another identical element in the process, method, commodity, or device comprising the element.

Claims

1. An image projection detection method, characterized in that, The detection method includes the following steps: Obtain the original image and divide it into multiple image regions according to the range of the display subject, where the display subject includes text, graphics, or charts; Obtain the actual projection image through an image acquisition device, and divide the actual projection image into multiple projection regions corresponding to the image regions according to the divided multiple image regions; Assign weights to the display subject by evaluating importance, and combine the preset weight threshold range to divide the multiple divided projection regions into projection weight levels, where the projection weight levels specifically include low level, medium level, and high level; Extract the characteristic parameters of the display subject in the original image, and set corresponding verification threshold ranges for each projection region according to the extracted characteristic parameters of the display subject in the original image. Among them, the higher the projection weight level of the projection region, the smaller the verification threshold range. Among them, the characteristic parameters of the display subject include color, brightness, contrast, or clarity; Extract the characteristic parameters of the image information of multiple projection regions in the actual projection image through image processing technology, and compare the extracted characteristic parameters of the image information of multiple projection regions with the corresponding verification threshold ranges. The characteristic parameters that exceed the verification threshold range are displayed as abnormal.

2. The image projection detection method according to claim 1, wherein The specific steps of obtaining the original image and dividing it into multiple image regions according to the range of the display subject are as follows: Obtain the original image to be projected and identify the display subject in the original image; Divide the original image into multiple image regions according to the content or layout of the display subject, and assign a unique identifier to each divided image region, and record the boundary coordinates of each image region.

3. A method for image projection detection according to claim 1, characterized in that, The specific steps of obtaining the actual projection image through an image acquisition device and dividing the actual projection image into multiple projection regions corresponding to the image regions according to the divided multiple image regions are as follows: Use a projection device to project the original image onto the target surface, and obtain the actual projection image through the camera or scanning device in the image acquisition device; Align the coordinates of the actual projection image with the coordinates of the original image according to the divided multiple image regions, and divide the actual projection image into multiple projection regions accordingly; Record the boundary coordinates and identifiers of each projection region.

4. A method for image projection detection according to claim 1, characterized in that, The specific steps of assigning weights to the display subject by evaluating importance and combining the preset weight threshold range to divide the multiple divided projection regions into projection weight levels are as follows: Evaluate each display subject according to the size of the text density, the size of the contrast, or the visual focus range of the layout according to the preset multiple scoring threshold ranges to obtain the evaluation values of each display subject; Set corresponding weight values for the preset multiple scoring threshold ranges respectively, and assign weight values corresponding to the evaluation values to each display subject according to the evaluation values of each display subject; Assign a weight value to each projection region according to the weight value of the display subject, and divide each projection region into corresponding projection weight levels according to the preset weight threshold range.

5. A method for image projection detection according to claim 1, characterized in that, Extract the characteristic parameters of the displayed subject in the original image, and set corresponding verification threshold ranges for each projection area according to the extracted characteristic parameters of the displayed subject in the original image. Among them, the higher the projection weight level of the projection area, the smaller the verification threshold range. The specific steps are as follows: Extract the characteristic parameters of the displayed subject in the original image; Set a basic verification threshold range for each characteristic parameter according to the extracted characteristic parameters, and set a weight coefficient for each weight level. Multiply the threshold nodes of the basic verification threshold range by the corresponding weight coefficients to obtain the adjusted verification threshold range.

6. The image projection detection method according to claim 5, characterized in that, Extract the characteristic parameters of the image information of multiple projection areas in the actual projection image through image processing technology, and compare the extracted characteristic parameters of the image information of multiple projection areas with the corresponding verification threshold ranges. The characteristic parameters exceeding the verification threshold range are displayed as abnormal. The specific steps are as follows: Use image recognition or edge detection in image processing technology to extract the characteristic parameters of the image information of each projection area from the actual projection image; Compare the characteristic parameters of the image information extracted from the actual projection image with the adjusted verification threshold range to determine whether the characteristic parameters of the image information extracted from the actual projection image belong to the adjusted verification threshold range; Mark the projection area to which the characteristic parameters exceeding the verification threshold range belong as abnormal, and generate an abnormal report listing all the projection areas marked as abnormal and their characteristic parameters.

7. An image projection detection system, applied to an image projection detection method according to any one of claims 1-6, characterized in that, The detection system includes: An image division module for obtaining the original image and dividing it into multiple image areas according to the range of the displayed subject; A region division module for obtaining the actual projection image through an image acquisition device and dividing the actual projection image into multiple projection areas corresponding to the image areas according to the divided multiple image areas; A weight assignment module for assigning weights to the displayed subject by evaluating importance, and combining the preset weight threshold range to divide the multiple divided projection areas into projection weight levels, where the projection weight levels specifically include low level, medium level, and high level; A feature extraction and definition module for extracting the characteristic parameters of the displayed subject in the original image, and setting corresponding verification threshold ranges for each projection area according to the extracted characteristic parameters of the displayed subject in the original image. Among them, the higher the projection weight level of the projection area, the smaller the verification threshold range; A feature detection module for extracting the characteristic parameters of the image information of multiple projection areas in the actual projection image through image processing technology, and comparing the extracted characteristic parameters of the image information of multiple projection areas with the corresponding verification threshold ranges. The characteristic parameters exceeding the verification threshold range are displayed as abnormal.

Images