Printing quality detection method and system, medium and product

Abstract

The invention provides a printing quality detection method and system, a medium and a product, and relates to the technical field of printing. The method comprises the following steps: establishing a corresponding relation between a target printing result and an actual printing result by acquiring standard image data and printed finished product image data; dividing image data by using a region recognition model, extracting key regions (such as characters, complex patterns and color transition contents) and non-key regions (such as pure color, background and blank contents), and ensuring that pixel coordinate ranges of the key regions and the non-key regions are in one-to-one correspondence; and further calculating the similarity between the key area and the non-key area through a printing similarity matching model, and carrying out weighted calculation to obtain the comprehensive similarity. And finally, accurately judging whether the printing quality is qualified or not by comparing the comprehensive similarity with a preset threshold value. The high-precision and differentiated detection of the printing quality is realized, and the accuracy, objectivity and efficiency of the printing quality detection are improved.

Description

Technical Field

[0001] The present application relates to the field of printing technology, and in particular to a printing quality detection method, system, medium and product. Background Art

[0002] With the rapid development of printing technology, print quality requirements are constantly increasing. During the printing process, due to various factors such as equipment status, ink ratio, and paper quality, the actual printed product often deviates from the expected result. This deviation not only affects the visual performance and functionality of the printed product, but can also lead to reduced customer satisfaction and increased production costs. Therefore, accurate print quality inspection is crucial for ensuring print quality and improving production efficiency.

[0003] Commonly used print quality inspection methods typically assess the overall quality of printed content. This approach works well for simple images or regular content, but it lacks accuracy and reliability when dealing with complex printed content. Summary of the Invention

[0004] The present application provides a printing quality detection method, system, medium and product for alleviating the problem of insufficient accuracy and reliability of printing quality detection when faced with complex printed content.

[0005] In the first aspect, the present application provides a printing quality detection method, comprising: obtaining standard image data and printed product image data corresponding to the current printed product, the standard image data being the target printing result of the current printed product, and the printed product image data being the actual printing result of the current printed product; inputting the standard image data into a preset area recognition model to obtain a first area division result, the first area division result including a first key area and a first non-key area, the first key area including text, complex patterns and color transition content, the first non-key area including solid color, background and blank content; inputting the printed product image data into the preset area recognition model to obtain a first area division result, the first area division result including a first key area and a first non-key area, the first key area including text, complex patterns and color transition content, and the first non-key area including solid color, background and blank content; A region recognition model is used to obtain a second region division result, where the second region division result includes a second key region and a second non-key region, and the pixel coordinate range of the second region division result maintains a one-to-one correspondence with the pixel coordinate range of the first region division result; the first region division result and the second region division result are input into a preset printing similarity matching model to obtain key region similarity and non-key region similarity; the key region similarity and the non-key region similarity are weightedly calculated to obtain a comprehensive similarity; when the comprehensive similarity is greater than or equal to a preset comprehensive similarity threshold, it is determined that the printing quality of the current printed product is qualified. By employing the above technical solution, standard image data and finished product image data of the current printed product are acquired, clarifying the correspondence between the target printing effect and the actual printing result. Next, by inputting the standard image data and finished product image data into a preset region recognition model, critical and non-critical regions are divided, allowing the content of the printed product to be differentiated based on importance. The two sets of region division results are then input into a print similarity matching model to calculate the similarity between the critical and non-critical regions, thereby enabling precise matching based on the characteristics of each region. Finally, a weighted calculation yields a comprehensive similarity, which comprehensively and objectively reflects the overall quality of the printed product. Different content has varying degrees of importance to print quality. Therefore, by performing differentiated processing of the image data through region division, the influence and importance of key content is avoided from being diluted, thereby reducing the reliability of the print quality inspection results. This effectively ensures the accuracy and reliability of print quality inspections when dealing with complex printed content.

[0006] In combination with some embodiments of the first aspect, in some embodiments, the key area and the non-key area respectively include multiple blocks, and the key area similarity and the non-key area similarity are weightedly calculated to obtain a comprehensive similarity, specifically including: determining the area influence factor corresponding to each block according to the block area of ​​each block in the key area and the non-key area; adjusting the key area similarity or the non-key area similarity corresponding to each block according to the area influence factor; and weighting the adjusted key area similarity and the non-key area similarity to obtain a comprehensive similarity. By adopting the above technical solution, first, the key areas and non-key areas are divided into multiple blocks, and the area influence factor is determined according to the area of ​​each block, which can effectively quantify the degree of influence of each block on the overall similarity. Then, the similarity corresponding to the block is adjusted using the area influence factor, so that the similarity calculation of each block can reflect the importance of its actual area. Finally, by performing a weighted calculation on the adjusted similarity, the obtained comprehensive similarity can more accurately reflect the printing quality, especially when the printed product contains large areas of similar or different areas, which can avoid the deviation of the overall evaluation due to local details. Therefore, this method further improves the objectivity and regional specificity of the detection results.

[0007] In combination with some embodiments of the first aspect, in some embodiments, the similarity of the key area or the similarity of the non-key area corresponding to each block is adjusted according to the area influence factor, specifically including: determining the shape influence factor corresponding to each block according to the shape regularity of each block; adjusting the similarity of the key area or the similarity of the non-key area corresponding to each block according to the shape influence factor and the area influence factor. By adopting the above technical solution, while adjusting tile similarity based on the area influence factor, a shape influence factor is added. This allows the similarity calculation to not only consider the tile area but also reflect the complexity of the tile's shape. Complex-shaped tiles often involve more printed details or key content. The introduction of the shape influence factor allows for a more refined evaluation of the similarity of these tiles. The combined adjustment of both the area and shape influence factors makes the similarity calculation results more sensitive to complex content, thereby improving the quality inspection capabilities for printed details and ensuring the applicability and accuracy of the technical solution in detecting complex printed content.

[0008] In combination with some embodiments of the first aspect, in some embodiments, after weighted calculation of the adjusted key area similarity and the non-key area similarity to obtain a comprehensive similarity, the method further includes: when the comprehensive similarity is less than a preset comprehensive similarity threshold, determining that the printing quality of the current printed product is unqualified; comparing each of the blocks of the current printed product one by one to determine whether the key area similarity or the non-key area similarity corresponding to each block is lower than the average block similarity, the average block similarity being the ratio of the sum of the key area similarity and the non-key area similarity to the number of blocks; if so, determining the corresponding block as a defective block and generating an alarm signal, the alarm signal including the pixel coordinate range and defect type of the defective block. By adopting this technical solution, when the overall similarity falls below a preset threshold, the specific defective block can be quickly located by comparing the similarity of each block one by one. Furthermore, by determining whether the block similarity falls below the average block similarity, possible defect areas can be accurately identified, and an alarm signal is generated, including the pixel coordinate range and defect type of the defective block. This refined defect location and marking method not only helps quickly identify printing problems, but also clearly defines the specific defect location and type, facilitating subsequent adjustments and improvements, significantly improving detection efficiency and the accuracy of problem feedback.

[0009] In combination with some embodiments of the first aspect, in some embodiments, after obtaining the standard image data and printed product image data corresponding to the current printed product, the method also includes: performing a shooting quality assessment on the printed product image data based on the standard image data to obtain a quality assessment value, and the shooting quality assessment includes detecting the resolution, contrast and brightness distribution of the printed product image data; if the quality assessment value is lower than a preset quality assessment threshold, the printed product image data is determined to be unqualified, and a reshoot is immediately requested. By employing this technical solution, after acquiring both standard and finished print image data, the print image data is first evaluated for quality. This effectively ensures that the image data used for testing possesses sufficient resolution, contrast, and brightness distribution. If the quality assessment falls below a preset threshold, the image data is immediately deemed unqualified and a retake is requested, effectively preventing errors in test results caused by data quality issues. This mechanism ensures that subsequent testing processes are based on high-quality data, thereby improving overall test accuracy and reliability.

[0010] In combination with some embodiments of the first aspect, in some embodiments, after obtaining the standard image data and printed product image data corresponding to the current printed product, the method also includes: performing edge detection on the standard image data to obtain image edge features; based on the image edge features, performing feature correction on the printed product image data to generate corrected printed product image data, and the feature correction includes rotation correction and scale normalization of the image. By employing this technical solution, edge detection is performed after acquiring standard image data, extracting clear image edge features. Based on these edge features, feature correction is performed on the finished print image data, including image rotation correction and scale normalization. This effectively eliminates deviations introduced by angle or scale issues during the capture process. The corrected finished print image data more closely matches the true characteristics of the standard image data, providing a more accurate basis for consistency comparison during subsequent quality inspections. This process significantly improves the accuracy and consistency of print quality inspections.

[0011] In combination with some embodiments of the first aspect, in some embodiments, after performing feature correction on the printed product image data based on the edge features of the image to generate corrected printed product image data, the method further includes: obtaining the standard resolution of the standard image data and the finished product resolution of the corrected printed product image data; determining whether the standard resolution is consistent with the finished product resolution; if not, adjusting the standard resolution and / or the finished product resolution so that the standard resolution is equal to the finished product resolution. By employing this technical solution, after feature correction, the standard resolution and the finished product resolution are further determined and their consistency is determined, ensuring the resolution consistency of the standard image and the corrected finished product image. If the resolutions are inconsistent, adjustments are made to equalize them, effectively avoiding matching errors caused by resolution differences. This method can further improve the matching accuracy of the standard and finished product images during the comparison process, ensuring the objectivity and consistency of the test results, and providing more precise technical support for print quality inspection.

[0012] In a second aspect, an embodiment of the present application provides a printing quality inspection system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the printing quality inspection system to perform the method described in the first aspect and any possible implementation of the first aspect.

[0013] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions. When the computer program product is run on a printing quality inspection system, the printing quality inspection system executes the method described in the first aspect and any possible implementation of the first aspect.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium comprising instructions. When the instructions are executed on a printing quality inspection system, the printing quality inspection system executes the method described in the first aspect and any possible implementation of the first aspect.

[0015] It is understood that the print quality inspection system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the methods provided in the embodiments of this application. Therefore, the beneficial effects achievable by these methods can be referenced to the beneficial effects of the corresponding methods and will not be further elaborated here.

[0016] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. By acquiring standard image data and printed product image data, applying a region division model, and performing weighted calculation of comprehensive similarity, the system can differentiate between key and non-key areas of printed products, and comprehensively reflect the quality of printing through comprehensive similarity. This effectively solves the problem of insufficient precision in the overall evaluation of printed images in related technologies, and thus achieves accuracy and objectivity in printing quality inspection of complex printed content.

[0017] 2. By dividing key and non-key areas into blocks and adjusting the similarity based on the area influence factor determined by the block area, the impact of each block on the overall similarity can be quantified more accurately. This effectively solves the problem of inaccurate detection results due to differences in regional characteristics in related technologies, thereby achieving a more refined and targeted evaluation of printing quality.

[0018] 3. Due to the adoption of a shooting quality assessment mechanism for the image data of the finished printed product, including detection of resolution, contrast and brightness distribution, and requesting reshooting when the quality assessment value is lower than the threshold, it is possible to ensure high-quality input of the inspection data from the source, effectively solving the problem in related technologies where low-quality image data affects the printing quality inspection results, thereby achieving high accuracy and reliability of printing quality inspection. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a structural diagram of a printing quality inspection device in an embodiment of the present application; Figure 2 This is a flow chart of a printing quality inspection method according to an embodiment of the present application; Figure 3 This is another flow chart of the printing quality detection method in the embodiment of the present application; Figure 4 It is a schematic diagram of the physical device structure of the printing quality detection system in the embodiment of the present application. DETAILED DESCRIPTION

[0020] The terms used in the following examples of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification of the present application, the singular expressions "a", "an", "above", "the", and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations of one or more of the listed items.

[0021] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0022] For ease of understanding, the following Figure 1 This article introduces an application scenario of printing quality inspection.

[0023] After the printing press completes printing, the printed product is transported to the print quality inspection device for print quality inspection. When the printed product reaches the image acquisition area of ​​the print quality inspection device, the print quality inspection system uses the image acquisition device of the print quality inspection device to obtain image data of the finished product. This image data is processed to obtain the print quality inspection results for the current product.

[0024] See also Figure 1 , Figure 1 1 is a schematic diagram of a structure of a printing quality inspection device in an embodiment of the present application, wherein the printing quality inspection device 110 includes a finished product image shooting device 111 and a printed product conveying device 112 .

[0025] In the actual application of printing quality inspection, the main function of the printing quality inspection device 110 is to conduct real-time inspection and quality assessment of the actual printing effect of printed products. It includes the following core components: Finished product image capture device 111: This device is a core component of the print quality inspection system and is typically composed of hardware such as an industrial-grade camera and a high-precision scanner. It can capture or scan the entire printed product at high resolution and convert the image of the physical printed product into digital data for obtaining the actual image data of the printed product (i.e., the image data of the printed product). In application, the finished product image capturing device 111 ensures that the captured printed product image data has sufficient clarity and detail through precise focusing, adjusting exposure time, and partitioned acquisition.

[0026] Printed material transport equipment 112: This equipment transports printed materials from the output of the printing press to the imaging area of ​​the inspection device. Typically consisting of an automated conveyor belt and positioning devices, it controls the speed, stopping position, and angle of the printed material's transport, ensuring that the printed material is in the correct position and orientation when imaged, preventing image quality from being affected by positional offset or tilt.

[0027] In application, the printed matter conveying device 112 can be seamlessly connected to the printing production line to achieve integrated operation of printing and testing.

[0028] For ease of understanding, the following describes the process of a printing quality inspection method provided by this implementation, which can be applied to a printing quality inspection system (hereinafter referred to as the inspection system), in combination with the above scenario. Figure 2 , is a flow chart of the printing quality detection method in an embodiment of the present application.

[0029] S201, obtaining standard image data and printed product image data corresponding to a current printed product, wherein the standard image data is a target printing result of the current printed product, and the printed product image data is an actual printing result of the current printed product; The "current printed product" represents the printed product currently being processed by the inspection system for quality inspection. The "standard image data" refers to the ideal image file of the current printed product, representing a digital representation of the desired visual effect. The "finished product image data" refers to the actual image data captured by the image acquisition device after the current printed product is actually produced by the printing equipment, reflecting the actual appearance of the printed product. Image acquisition devices, such as industrial-grade cameras and high-precision scanners, can convert the physical form of the printed product into digital image information. During the printing production process, when a printed product is delivered to the quality inspection station by the printing equipment, the inspection system sends an image acquisition command to the image acquisition device. For standard image data, the inspection system directly retrieves it from a pre-built database that stores standard images corresponding to the current product. To acquire image data for the finished product, the inspection system controls the image acquisition device to capture the printed product at high resolution. For large printed products, a method of capturing and stitching images in separate areas is used to ensure complete surface information is captured. Ultimately, both standard image data corresponding to the current product and image data for the finished product are obtained.

[0030] S202: Input the standard image data into a preset region recognition model to obtain a first region division result, where the first region division result includes a first key region and a first non-key region, where the first key region includes text, complex patterns, and color transition content, and the first non-key region includes solid colors, background, and blank content; Among them, the region recognition model is an intelligent model built into the detection system and trained based on deep learning algorithms (such as convolutional neural networks (CNN). After training with a large amount of image data of different types, it has the ability to accurately analyze image content and divide regions; the first region division result refers to the image region classification result obtained after the standard image data is processed by the region recognition model; the first key area is used to represent the part of the standard image that plays a decisive role in printing quality and visual communication, including text (such as the title and text content of the book), complex patterns (such as illustrations and trademark graphics on posters) and color transition content (such as gradient backgrounds and light and shadow effect areas); the first non-key area refers to the relatively minor part of the standard image, including solid color fill areas (such as backgrounds with a single background color), background decorative elements (such as simple line textures) and white space (blank areas reserved for highlighting the main body). The region recognition model is built using deep learning technology, aiming to achieve precise region segmentation of input image data. First, a training dataset is constructed, collecting image samples from a variety of printed material types. These samples are precisely labeled, clearly marking each region's category (e.g., text, complex patterns, color transitions, solid backgrounds, white space), and the corresponding pixel coordinate range. To improve the model's robustness and generalization capabilities, the dataset is augmented with data operations such as rotation, scaling, translation, and noise addition to simulate the diverse variations found in real-world scenarios.

[0031] The core architecture of the model utilizes a convolutional neural network (CNN), which takes image data as input and outputs the region category and corresponding location coordinates for each pixel. During training, the image first passes through several convolutional layers to extract local features such as texture, edges, and shape. Pooling layers gradually reduce the dimensionality, preserving key feature information. Subsequently, through multiple layers of convolution and activation functions, the network gradually learns the relationship between global and local features. Finally, the feature map is mapped to the classification space through a fully connected layer and normalized using the Softmax function, outputting the probability of each pixel belonging to a different region category.

[0032] Model training utilizes a cross-entropy loss function on labeled data, combined with a backpropagation algorithm to optimize network weights and ensure high accuracy on the training data. After training, when image data is input, the model automatically analyzes the image and outputs a segmentation result, including key areas (such as text, complex patterns, and color transitions) and non-key areas (such as solid colors, backgrounds, and white space). It also provides the category identifier and pixel coordinate range for each area to ensure accurate and consistent results.

[0033] After the detection system acquires the standard image data, it provides a region recognition model for region division. Specifically, the detection system preprocesses the standard image data according to the format and parameters required by the model, including adjusting the image resolution, color mode conversion, etc., and then inputs the preprocessed image data into the preset region recognition model. After receiving the data, the model uses its internal multi-layer neural network structure to analyze and extract the pixel information, color distribution, shape features, etc. in the image layer by layer. Based on the key features and pattern recognition rules learned during the training process, the model divides the standard image data into a first key area and a first non-key area, and assigns corresponding identification and pixel coordinate information to each area.

[0034] S203: Input the printed product image data into the region recognition model to obtain a second region division result, where the second region division result includes a second key region and a second non-key region, and a pixel coordinate range of the second region division result maintains a one-to-one correspondence with the pixel coordinate range of the first region division result; Among them, the second area division result refers to the image area classification result generated after the printed product image data is processed by the area recognition model; the second key area is the part of the printed product image corresponding to the first key area of ​​the standard image, which contains the text, complex patterns and color transition content after actual printing; the second non-key area is the part of the printed product image corresponding to the first non-key area of ​​the standard image, which contains the solid color, background and blank content after actual printing; the pixel coordinate range represents the position and size information of each area in the image on the two-dimensional plane, which is a key parameter to ensure that the first area division result and the second area division result can accurately correspond and be effectively compared. After completing the regional division of the standard image data, the detection system then processes the image data of the printed product. Specifically, the detection system also pre-processes the image data of the printed product to make it meet the input requirements of the regional recognition model, and then inputs the processed image data into the regional recognition model. The model restarts the analysis program and performs feature extraction and regional division on the image data of the printed product using the same algorithm and rules as those used to process the standard image data, obtaining a second regional division result. During the division process, the detection system strictly controls the pixel coordinate range of the second regional division result output by the model, so that it maintains a one-to-one correspondence with the pixel coordinate range of the first regional division result, ensuring that the key areas and non-key areas in the printed product image completely match the corresponding areas in the standard image in terms of position and size.

[0035] S204: Input the first region division result and the second region division result into a preset printing similarity matching model to obtain key region similarity and non-key region similarity; The printing similarity matching model is an intelligent model built within the detection system based on image processing and pattern recognition technologies. It is used to compare and analyze the similarity between the results of two image region divisions. Key area similarity represents the numerical similarity between the second key area of ​​the printed product image and the first key area of ​​the standard image. A higher value indicates that the printing quality of the key area is closer to the standard. Non-key area similarity refers to the numerical similarity between the second non-key area of ​​the printed product image and the first non-key area of ​​the standard image, reflecting the printing quality of non-key areas. For example, when printing a card with complex patterns and text, key area similarity is used to measure the difference between the print clarity and color accuracy of the pattern and text on the card and the standard image, while non-key area similarity is used to evaluate the printing quality of non-key areas such as the card background color. After the detection system obtains the first area division result of the standard image data and the second area division result of the printed product image data, it enters the printing quality similarity evaluation link. Specifically, the detection system unifies the format and organizes the data of the first area division result and the second area division result according to the input requirements of the printing similarity matching model to ensure that the area information, pixel coordinates and other data in the two results are accurate. Subsequently, the detection system inputs the organized data into the preset printing similarity matching model. After receiving the data, the model first compares the key areas of the two results pixel by pixel or feature by feature, and calculates multiple indicators such as color difference, shape matching, texture similarity, etc. to comprehensively obtain the key area similarity value; then, the non-key areas are analyzed and compared in the same way to obtain the non-key area similarity value.

[0036] S205, performing weighted calculation on the key area similarity and the non-key area similarity to obtain a comprehensive similarity; The comprehensive similarity is a weighted calculation of the key area similarity and non-key area similarity, resulting in a comprehensive value used to assess print quality. It considers the impact of different parts of a printed product on overall quality. For example, when evaluating the print quality of a color album, the key area similarity reflects the print quality of the images and text, while the non-key area similarity reflects the print quality of the blank page background, borders, and other parts. The comprehensive similarity provides a comprehensive evaluation of the entire album's print quality. After obtaining the similarity of key areas and non-key areas, the detection system conducts a comprehensive evaluation of the printing quality. Specifically, the detection system first obtains pre-set weight parameters. These weight parameters are based on factors such as the type of printed matter, the importance of key areas and non-key areas in affecting quality, etc. For example, for promotional posters, since text and patterns are the core of conveying information, the weight of key areas may be set to 0.7 and the weight of non-key areas to 0.3. Then, the detection system multiplies the key area similarity by the key area weight, and the non-key area similarity by the non-key area weight according to the weighted calculation formula, and then adds the two products to obtain a comprehensive similarity value.

[0037] S206 : When the comprehensive similarity is greater than or equal to a preset comprehensive similarity threshold, it is determined that the printing quality of the current printed product is qualified.

[0038] The preset comprehensive similarity threshold is a pre-set value in the detection system that serves as a standard for judging whether printing quality is acceptable or not. This threshold is determined based on factors such as the quality requirements of the printed product and the level of production process. For example, for high-precision art album printing, the preset comprehensive similarity threshold may be set at 0.9, while for ordinary leaflet printing, the threshold may be 0.8. Acceptable printing quality means that the similarity between the actual printing effect of the current printed product and the standard image meets or exceeds the preset standard, thus meeting the quality requirements.

[0039] After the detection system calculates the comprehensive similarity, it determines the printing quality. Specifically, the detection system compares the calculated comprehensive similarity value with the preset comprehensive similarity threshold. If the comprehensive similarity is greater than or equal to the preset comprehensive similarity threshold, it means that the overall printing effect of the current printed product in the key area and non-key area is within an acceptable range compared with the standard image, and the printing quality has met the expected requirements. At this time, the detection system determines that the printing quality of the current printed product is qualified, and generates a qualified report, records the relevant detection data, and sends a signal to the subsequent production process, allowing the printed product to enter the next link such as packaging and warehousing; if the comprehensive similarity is less than the preset comprehensive similarity threshold, the printing quality is determined to be unqualified, triggering the unqualified processing process, and isolating, reworking, and other operations on the printed product.

[0040] By adopting the above technical solution, the present application provides a printing quality detection method, which establishes a direct correspondence between the target printing effect and the actual printing result by acquiring standard image data and printed product image data, providing an accurate data basis for subsequent quality detection; the image data is divided into regions through the regional recognition model, and differential processing is performed on key areas and non-key areas, and the one-to-one correspondence between the two in the pixel coordinate range is ensured, thereby improving the degree of refinement of detection and the accuracy of regional matching; further, through the printing similarity matching model, the similarity of key areas and non-key areas is calculated separately, accurately reflecting the differences in printing effects in different areas; finally, the comprehensive similarity is obtained through weighted calculation and compared with the preset threshold to quickly determine whether the overall quality of the printed product is qualified. This method effectively solves the problems of insufficient printing quality detection accuracy and imperfect processing of regional characteristic differences in related technologies for complex printed content, thereby improving the accuracy of printing quality detection.

[0041] In the above embodiments, the present application determines print quality by acquiring standard image data of a printed product and image data of a finished product, dividing the data into regions, and calculating the similarity of the corresponding regions. In practical applications, the acquisition of the finished product image data may result in unclear images, leading to misjudgments of print quality. In some embodiments, after acquiring the finished product image data, the image quality can be evaluated to avoid misjudgments of print quality due to errors in acquiring the finished product image data.

[0042] The following is a supplement to the scenario of this embodiment. After combining the above scenario, the following is a further and more specific description of the process of the method provided by this embodiment. Figure 3 , is another flow chart of the printing quality detection method in an embodiment of the present application.

[0043] S301 , obtaining standard image data and printed product image data corresponding to a current printed product, wherein the standard image data is a target printing result of the current printed product, and the printed product image data is an actual printing result of the current printed product. Step S301 is similar to step S201 described in the above embodiment and will not be described again here. Please refer to the description in the corresponding step.

[0044] S302 : Perform a shooting quality assessment on the image data of the printed product according to the standard image data to obtain a quality assessment value. The shooting quality assessment includes detecting the resolution, contrast, and brightness distribution of the image data of the printed product. Capture quality assessment involves a comprehensive examination of the resolution, contrast, and brightness distribution of the printed image data. Resolution indicates the density of pixels within an image, contrast refers to the ratio of the brightness between the brightest and darkest parts of an image, and brightness distribution indicates the distribution of brightness across image regions. The quality assessment value is a quantified value derived from the capture quality assessment results using a specific algorithm. Higher values ​​indicate better capture quality of the printed image data.

[0045] After obtaining the standard image data and printed product image data corresponding to the current printed product, the detection system performs a shooting quality assessment on the printed product image data. Specifically, the detection system first detects the resolution of the printed product image data, calculates the number of pixels per unit length or unit area, and compares it with the preset resolution standard to determine whether the image is clear. Next, the contrast of the image is detected, the brightness difference between the bright and dark parts of the image is analyzed, and the vividness of the color is evaluated. Then, the brightness distribution is detected, and by counting the brightness values ​​of each area of ​​the image, it is determined whether there is uneven brightness. Finally, the detection system substitutes the detection results of resolution, contrast and brightness distribution into a pre-set evaluation algorithm, calculates the quality evaluation value, and compares the value with the preset quality evaluation threshold. If it is lower than the threshold, the printed product image data is judged to be unqualified.

[0046] S303: If the quality evaluation value is lower than the preset quality evaluation threshold, the printed product image data is determined to be unqualified, and a request is immediately made to retake the image. The preset quality assessment threshold is a pre-set value within the inspection system that measures the quality of image data captured for finished printed products. This value is determined based on factors such as actual print quality inspection requirements and equipment performance. A failure determination means that the currently captured image data fails to meet the requirements for subsequent print quality inspections. When the inspection system completes the shooting quality assessment of the printed product image data and calculates the quality assessment value, it compares this value with the preset quality assessment threshold. Specifically, if the quality assessment value is less than the preset quality assessment threshold, the inspection system determines that the currently acquired printed product image data is unqualified and immediately sends a reshoot request to the shooting device responsible for shooting the printed product image, such as an industrial camera, etc., while recording the unqualified information, including the shooting time, possible problems, etc., and adjusting the parameter settings of the shooting device. After receiving the reshoot request, the shooting device will reshoot the printed product to generate new printed product image data. The inspection system will once again conduct a shooting quality assessment on the new data until the image data is qualified.

[0047] S304: Perform edge detection on the standard image data to obtain image edge features.

[0048] Edge detection refers to the process by which a detection system uses mathematical algorithms to identify and extract the boundaries of objects in an image. By analyzing changes in pixel grayscale values ​​within the image, it identifies locations where drastic changes in grayscale values ​​occur. These locations are the edges of the image. Image edge features refer to information about the boundaries of objects in an image obtained through edge detection, including edge length, direction, and curvature. These features can reflect the shape and structure of the object. For example, in an image printed with a trademark, edge detection can extract the boundary outline of the trademark pattern. Information such as the shape and corners of the trademark boundary constitutes the image edge features. After ensuring the image data of the finished printed product is qualified, the inspection system begins processing the standard image data to obtain key information for subsequent image analysis. Specifically, the inspection system uses sophisticated edge detection algorithms such as the Canny algorithm and the Sobel operator to process each pixel in the standard image data. The algorithm calculates the grayscale variation of each pixel and its neighboring pixels. When the grayscale variation exceeds a certain threshold, the pixel is considered to be on the edge of the image. By traversing the entire standard image data, the inspection system can accurately extract the image's edges.

[0049] S305 , performing feature correction on the printed product image data according to the image edge feature to generate corrected printed product image data, wherein the feature correction includes rotation correction and scale normalization of the image.

[0050] Among them, feature correction refers to the operation of the detection system to perform geometric transformation and size adjustment on the printed product image data based on the image edge features of the standard image data, with the purpose of making the printed product image data consistent with the standard image data in angle and size, so as to facilitate subsequent accurate similarity comparison. Rotation correction is part of feature correction, which refers to the operation of the detection system to rotate the image to the correct direction by calculating the tilt angle of the printed product image data, such as adjusting the printed product image that was tilted when shooting to a horizontal or vertical state. Scale normalization is also a key step in feature correction, which refers to the detection system to enlarge or reduce the printed product image data according to the size specifications of the standard image data so that the two match in size, such as adjusting the printed product image that is too large or too small to the same resolution and size as the standard image. After acquiring the image edge features of the standard image data, the detection system begins to process the image data of the finished print product to eliminate image deviations caused by factors such as shooting angle and distance. Specifically, the detection system first analyzes whether the image data of the finished print product is tilted based on the image edge features. By calculating the angular deviation of the edge, it determines the tilt direction and angle of the image. Then, it uses a rotation algorithm, such as affine transformation, to rotate the image to the correct angle to complete the rotation correction. Next, the detection system compares the size information of the standard image data, including resolution, aspect ratio, etc., with the size difference of the finished print product image data. Based on the difference, it selects an appropriate scaling algorithm, such as bilinear interpolation, bicubic interpolation, etc., to scale the finished print product image data so that the two are consistent in size. Finally, it generates the corrected finished print product image data, laying the foundation for subsequent accurate printing quality inspection.

[0051] S306 , obtaining the standard resolution of the standard image data and the finished product resolution of the corrected printed product image data. Standard resolution refers to the pixel density specification set by the standard image data of the current printed product. It measures the number of pixels per unit length or unit area of ​​the standard image and determines the clarity and level of detail of the standard image. Finished product resolution refers to the pixel density of the printed product image data after feature correction, reflecting the clarity of the actual printed product image. For example, the finished product resolution of a captured and corrected printed product image may differ from the standard resolution due to factors such as the performance of the capturing equipment and the correction process. Acquisition refers to the process by which the detection system extracts standard resolution and finished product resolution data from storage locations or processing results. S307: Determine whether the standard resolution is consistent with the finished product resolution. After the inspection system obtains the standard resolution and the finished product resolution, it determines whether the two are equal. If they are equal, the subsequent area division steps are carried out; if not, the resolution is adjusted before proceeding to the subsequent steps.

[0052] S308: If they are inconsistent, adjust the standard resolution and / or the finished product resolution to make the standard resolution equal to the finished product resolution. After completing the consistency judgment of the standard resolution and the finished product resolution, and the result is inconsistent, the detection system adjusts the resolution. Specifically, the system will first analyze the numerical difference between the standard resolution and the finished product resolution. If the standard resolution is higher than the finished product resolution, the system will select a suitable magnification algorithm to process the printed product image data. While adding pixels, the grayscale value or color value of the newly added pixels is calculated through the interpolation algorithm to ensure a smooth transition of the image; if the standard resolution is lower than the finished product resolution, the printed product image data is reduced to remove redundant pixels, and an algorithm is used to retain the key information of the image. In some cases, the standard image data can also be adjusted in resolution accordingly, or both can be processed at the same time, so that the standard resolution and the finished product resolution are ultimately equal, preparing for subsequent printing quality inspection based on image area division and similarity matching.

[0053] S309. Input the standard image data into a preset area recognition model to obtain a first area division result, where the first area division result includes a first key area and a first non-key area. The first key area includes text, complex patterns, and color transition content, and the first non-key area includes pure color, background, and blank content. S310. Input the printed product image data into the region recognition model to obtain a second region division result, wherein the second region division result includes a second key region and a second non-key region, and the pixel coordinate range of the second region division result maintains a one-to-one correspondence with the pixel coordinate range of the first region division result. S311 , inputting the first region division result and the second region division result into a preset printing similarity matching model to obtain key region similarity and non-key region similarity. Steps S309 to S311 are similar to steps S202 to S204 in the above embodiment and are not described again here. Please refer to the description of the corresponding steps.

[0054] In steps S309 and S310, the first key area and the first non-key area, and the second key area and the second non-key area are obtained, respectively. The key areas (first key area, second key area) and the non-key areas (first non-key area, second non-key area) each include multiple tiles. Tiles refer to image segments with different content within the corresponding area, such as text fragments, independent images, and white space.

[0055] S312 : Determine the area impact factor corresponding to each block according to the block area of ​​each block in the key area and the non-key area. Tile area represents the number of image pixels occupied by each tile. This is calculated by counting the total number of pixels within the tile. For example, a text tile consisting of 100×100 pixels has a tile area of ​​10,000 pixels. The area impact factor is a weighting coefficient assigned to each tile by the inspection system based on its size, according to specific rules. It measures the impact of tile area on print quality assessment.

[0056] After completing the area division and similarity determination of the standard image data and the printed product image data, the detection system determines the area impact factor of each block. Specifically, the system first traverses all the blocks in the key area and non-key area, and calculates the block area and the total block area of ​​each block by counting the number of pixels contained in each block. The ratio of the area of ​​each block to the total block area is calculated and determined as the area impact factor corresponding to each block, which is recorded as A. i .

[0057] S313 : Determine a shape influence factor corresponding to each of the blocks according to the shape regularity of each of the blocks.

[0058] Shape regularity is a quantitative description of the regularity of a block's shape, measuring how closely the block's shape approaches a standard geometric shape (such as a rectangle or circle). The closer the shape is to a standard geometric shape, the higher the regularity. For example, a regular square text box block has a higher shape regularity than an irregular hand-drawn pattern block. The shape influence factor is a weight coefficient assigned to each block by the detection system based on its shape regularity, using a specific algorithm. It reflects the influence of the block's shape in print quality assessment. Blocks with high regularity generally have a more stable reference value in print quality assessment and have a relatively high shape influence factor.

[0059] After determining the area influence factor of each block, the detection system determines the shape influence factor. Specifically, the detection system uses edge detection, contour fitting and other algorithms to analyze the shape of each block. First, extract the edge contour of the block, and then try to fit it into a standard geometric shape. By calculating the difference between the actual contour and the fitted shape, the shape regularity is quantified. For example, the least squares method is used to calculate the error between the block contour and the ideal rectangle. The smaller the error, the higher the shape regularity. Then, the detection system determines the shape influence factor for each block according to the pre-set shape regularity-influence factor mapping table, which is recorded as S i .

[0060] S314 : Adjust the key area similarity or the non-key area similarity corresponding to each image block according to the shape influence factor and the area influence factor. After obtaining the shape influence factor and area influence factor of each block, the detection system begins to adjust the similarity of the key area and the similarity of the non-key area. This process is to comprehensively consider the block area and block shape factors of the block, correct the original similarity calculation results, and make the evaluation more in line with the actual printing situation. Specifically, the detection system performs a weighted combination of the shape influence factor and the area influence factor for each block, and then multiplies it with the original block similarity value to obtain the adjusted similarity value. The detection system performs the above adjustment calculations on all blocks in the key area and non-key area in turn, and updates the similarity value corresponding to each block, so as to obtain more accurate key area similarity and non-key area similarity data.

[0061] S315 , performing weighted calculation on the adjusted similarity of the key region and the similarity of the non-key region to obtain a comprehensive similarity. After completing the adjustment of the key area similarity and the non-key area similarity, the detection system calculates the comprehensive similarity. Specifically, based on the adjusted key area similarity and the non-key area similarity, as well as the key area weight coefficient α and the non-key area weight coefficient β, the comprehensive similarity is calculated. The calculation formula is:

[0062] Among them, α+β=1 and α>β, X1 is the similarity of key areas, X2 is the similarity of non-key areas, N k and N n The number of tiles in the key area and non-key area, respectively, and the area impact factor A i satisfy , shape influence factor S i Satisfy 0≤S i ≤1.

[0063] S316: Determine whether the comprehensive similarity is less than a preset comprehensive similarity threshold.

[0064] S317 : When the comprehensive similarity is less than a preset comprehensive similarity threshold, it is determined that the printing quality of the current printed product is unqualified. Unqualified printing quality means that the detection system concludes that the overall similarity between the image data of the printed product and the standard image data does not meet the qualified standards by comparing the comprehensive similarity with the comprehensive similarity threshold. There may be problems such as blurred text, incomplete patterns, and color deviation.

[0065] S318 , comparing each of the image blocks of the current printed product one by one to determine whether the key region similarity or the non-key region similarity corresponding to each image block is lower than the average image block similarity, where the average image block similarity is the ratio of the sum of the key region similarity and the non-key region similarity to the number of images blocks.

[0066] After the detection system determines that the printing quality of the current printed product is unqualified, in order to accurately locate the specific area causing the quality problem, the block similarity is analyzed in detail. By comparing the similarity of each block with the overall average level, the blocks with obvious defects are found. Specifically, the detection system first traverses each block in the critical area and non-critical area, and obtains the critical area similarity or non-critical area similarity value corresponding to each block. Then, the detection system calculates the average block similarity based on the previously calculated critical area similarity, non-critical area similarity and the total number of blocks. Next, the detection system compares the similarity value of each block with the average block similarity one by one to determine whether it is lower than the average level, so as to determine which blocks may have printing defects. S319 : If yes, the corresponding image block is determined as a defective image block and an alarm signal is generated. The alarm signal includes the pixel coordinate range and defect type of the defective image block. Defective blocks are image blocks whose similarity, determined by the inspection system to be below average after comparing each block's similarity with the average block similarity, indicating printing quality issues, such as blocks with missing text strokes or pattern color deviations. Alarm signals are prompts generated by the inspection system after identifying defective blocks. They notify operators of the specific quality issues and contain key information such as the defective block's pixel coordinate range and defect type, allowing operators to quickly locate and address the problem.

[0067] The detection system first assigns a unique identifier to each object that is judged to be a defective block, and records its pixel coordinate range in detail in the defective block record list within the system, and determines the specific location by calculating the pixel coordinates of the upper left and lower right corners of the block. At the same time, the detection system will analyze the characteristics of the defective block based on the pre-set defect judgment rules and determine its defect type, such as by comparing the color distribution of the standard image and the finished product image to determine whether there is color distortion. Finally, the detection system integrates the pixel coordinate range and defect type of the defective block to generate an alarm signal, and sends it to the operator or relevant quality control personnel through various methods such as display screen prompts, SMS notifications, and production management system pop-up windows, so that the printed products corresponding to the defective block can be processed in time.

[0068] S320: When the comprehensive similarity is greater than or equal to a preset comprehensive similarity threshold, it is determined that the printing quality of the current printed product is qualified.

[0069] By adopting the above technical solution, the present application provides a printing quality detection method, which can ensure that the resolution, contrast and brightness distribution of the image data meet the detection requirements from the source by performing shooting quality evaluation on the image data of the printed product, and avoid distortion of the detection results caused by low-quality data; through edge detection and feature correction of standard image data, the deviation problem caused by shooting angle or size difference is solved, so that the image data of the printed product is consistent with the standard image in scale and geometric characteristics, laying an accurate foundation for subsequent comparison; further, the regional similarity is adjusted by the area influence factor and shape influence factor of the block, and the influence of each block on the overall quality evaluation is accurately quantified to improve the detection accuracy; by locating the defective block and generating an alarm signal, the location and type of the printing defect can be quickly marked, which is convenient for timely feedback and correction. This method effectively solves the detection deviation problem caused by insufficient data quality, image correction and detection accuracy in related technologies, and achieves high reliability, refinement and efficiency of printing quality detection for complex printed content.

[0070] The following describes the printing quality inspection system in the embodiment of the present invention from the perspective of hardware processing. Figure 4 , is a schematic diagram of the physical device structure of the printing quality inspection system in an embodiment of the present application.

[0071] It should be noted that Figure 4 The structure of the printing quality inspection system shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0072] like Figure 4 As shown, the electronic device includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes, such as the methods described in the above embodiments, based on programs stored in a read-only memory (ROM) 402 or programs loaded from a storage unit 408 into a random access memory (RAM) 403. RAM 403 also stores various programs and data required for system operation. CPU 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to bus 404.

[0073] The following components are connected to the input / output (I / O) interface 405: an input section 406 including an audio input device, push button switches, and the like; an output section 407 including a display, an audio output device, indicator lights, and the like; a storage section 408 including a hard disk and the like; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the input / output (I / O) interface 405 as needed. Removable media 411, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 410 as needed, so that computer programs read from the media can be installed in the storage section 408 as needed.

[0074] In particular, according to embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for executing the method illustrated in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication portion 409 and / or installed from removable media 411. When executed by central processing unit (CPU) 401, the computer program performs the various functions defined in this application. It should be noted that specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0075] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings.

[0076] Specifically, the printing quality inspection system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the printing quality inspection method provided in the above embodiment is implemented.

[0077] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the print quality inspection system described in the above embodiments, or may exist independently and not incorporated into the print quality inspection system. The storage medium carries one or more computer programs, which, when executed by a processor of the print quality inspection system, enable the print quality inspection system to implement the print quality inspection method provided in the above embodiments.

[0078] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0079] As used in the above embodiments, the term “when” may be interpreted to mean “if” or “after” or “in response to determining that” or “in response to detecting that”, depending on the context. Similarly, the phrases “upon determining that” or “if (stated condition or event) is detected” may be interpreted to mean “if determining that” or “in response to determining that” or “upon detecting (stated condition or event)” or “in response to detecting (stated condition or event)”, depending on the context.

[0080] Those skilled in the art will appreciate that all or part of the process steps in the above-described method embodiments can be implemented by a computer program instructing the relevant hardware. The program can be stored in a computer-readable storage medium, and when executed, the program can include the process steps in the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A printing quality detection method, characterized in that: include: Obtaining standard image data and printed product image data corresponding to the current printed product, wherein the standard image data is the target printing result of the current printed product, and the printed product image data is the actual printing result of the current printed product; Inputting the standard image data into a preset region recognition model to obtain a first region division result, wherein the first region division result includes a first key region and a first non-key region, wherein the first key region includes text, complex patterns, and color transition content, and the first non-key region includes solid color, background, and blank content; Inputting the printed product image data into the region recognition model to obtain a second region division result, wherein the second region division result includes a second key region and a second non-key region, and a pixel coordinate range of the second region division result maintains a one-to-one correspondence with the pixel coordinate range of the first region division result; Inputting the first region division result and the second region division result into a preset printing similarity matching model to obtain key region similarity and non-key region similarity; Performing weighted calculation on the key area similarity and the non-key area similarity to obtain a comprehensive similarity; When the comprehensive similarity is greater than or equal to a preset comprehensive similarity threshold, it is determined that the printing quality of the current printed product is qualified.

2. The method according to claim 1, characterized in that The key area and the non-key area each include a plurality of image blocks, and the weighted calculation of the key area similarity and the non-key area similarity to obtain a comprehensive similarity specifically includes: Determine the area impact factor corresponding to each block according to the block area of ​​each block in the key area and the non-key area; Adjusting the key area similarity or the non-key area similarity corresponding to each of the image blocks according to the area influence factor; The adjusted key area similarity and the non-key area similarity are weightedly calculated to obtain a comprehensive similarity.

3. The method according to claim 2, characterized in that The adjusting the key area similarity or the non-key area similarity corresponding to each of the image blocks according to the area impact factor specifically includes: determining a shape influence factor corresponding to each of the blocks according to the shape regularity of each of the blocks; The key area similarity or the non-key area similarity corresponding to each of the image blocks is adjusted according to the shape influence factor and the area influence factor.

4. The method according to claim 2, characterized in that After performing weighted calculation on the adjusted key area similarity and the non-key area similarity to obtain a comprehensive similarity, the method further includes: When the comprehensive similarity is less than a preset comprehensive similarity threshold, determining that the printing quality of the current printed product is unqualified; Comparing each of the image blocks of the current printed product one by one, and determining whether the key area similarity or the non-key area similarity corresponding to each image block is lower than the average image block similarity, where the average image block similarity is the ratio of the sum of the key area similarity and the non-key area similarity to the number of images blocks; If so, the corresponding image block is determined to be a defective image block and an alarm signal is generated. The alarm signal includes the pixel coordinate range and defect type of the defective image block.

5. The method according to claim 1, characterized in that: After obtaining the standard image data and the printed product image data corresponding to the current printed product, the method further includes: performing a shooting quality assessment on the image data of the printed product according to the standard image data to obtain a quality assessment value, wherein the shooting quality assessment includes detecting the resolution, contrast, and brightness distribution of the image data of the printed product; If the quality evaluation value is lower than a preset quality evaluation threshold, the printed product image data is determined to be unqualified, and a request is immediately made to reshoot.

6. The method according to claim 1, characterized in that After obtaining the standard image data and the printed product image data corresponding to the current printed product, the method further includes: Performing edge detection on the standard image data to obtain image edge features; According to the image edge features, feature correction is performed on the printed product image data to generate corrected printed product image data, wherein the feature correction includes rotation correction and scale normalization of the image.

7. The method according to claim 6, characterized in that After performing feature correction on the printed product image data according to the image edge features to generate corrected printed product image data, the method further includes: Acquire a standard resolution of the standard image data and a finished product resolution of the corrected printed product image data; Determining whether the standard resolution is consistent with the finished product resolution; If they are inconsistent, the standard resolution and / or the finished product resolution are adjusted to make the standard resolution equal to the finished product resolution.

8. A printing quality inspection system, characterized in that: The printing quality inspection system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the printing quality inspection system to execute the method described in any one of claims 1 to 7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on a printing quality inspection system, the printing quality inspection system is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a printing quality inspection system, the printing quality inspection system is enabled to perform the method according to any one of claims 1 to 7.

Images