A high-precision printing quality detection method and system

Abstract

The present invention discloses a high-precision printing quality detection method and system, relating to the technical field of image processing. The method includes: configuring an image sensor for the printing quality inspection area, and performing sensing acquisition on a target printed product to obtain a printed image; transmitting the printed image back, performing image segmentation and grayscale processing based on the boundary of the printed product to determine a grayscale printed image; obtaining a standard printing template, and constructing a pixel stack space to supervise and train a printing registration module; transmitting the grayscale printed image to the printing registration module, and determining defect pixel features by performing pixel transition sampling registration and pixel skip point sampling registration; traversing the defect pixel features, performing defect type matching based on a defect matcher, and outputting printing quality data. It solves the technical problem of low printing quality detection accuracy and efficiency in the prior art, and achieves the technical effect of improving the printing quality detection accuracy and efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a high-precision printing quality detection method and system. Background Art

[0002] With the continuous development of modern industrial manufacturing, especially the continuous upgrading and expansion of the printing industry, printing quality detection has become a vital part of the production process. Traditional printing quality detection methods mainly rely on manual visual inspection or simple mechanical detection equipment. These methods have certain limitations in accuracy and efficiency, especially when facing large-scale, high-precision printing needs, they often cannot meet the requirements of fast, accurate, and error-free. In addition, the existing automated detection systems also face the problems of low detection accuracy and insufficient defect recognition capabilities, especially when dealing with complex printed images or minor defects, which are prone to missed detections and false detections. Therefore, how to improve the accuracy and efficiency of printing quality detection, especially in high-speed, large-scale production, to achieve automated and intelligent quality detection, has become a key issue that needs to be urgently solved in the current printing industry. Summary of the invention

[0003] The present application provides a high-precision printing quality detection method and system, which solves the technical problems of low printing quality detection accuracy and efficiency in the prior art.

[0004] In view of the above problems, the present application provides a high-precision printing quality detection method and system.

[0005] In a first aspect of the present application, a high-precision printing quality detection method is provided, the method comprising:

[0006] An image sensor is configured in the printing quality inspection area, and the target printing product is sensed and collected to obtain a printing image; the printing image is transmitted back, and image segmentation and grayscale processing are performed based on the printed product boundary to determine the grayscale printing image; a standard printing template is obtained, and a pixel stack space is constructed to supervise the training of a printing registration module, wherein the printing registration module includes a first pixel registration unit and a second pixel registration unit, and a first acquisition registration is performed based on pixel transition sampling, and a second acquisition registration is performed based on pixel interval sampling; the grayscale printing image is transmitted to the printing registration module, and defective pixel features are determined by performing pixel transition sampling registration and pixel interval sampling registration; the defective pixel features are traversed, defect type matching is performed based on a defect matcher, and printing quality data is output.

[0007] A second aspect of the present application provides a high-precision printing quality detection system, the system comprising:

[0008] Image acquisition unit: Configure an image sensor for the printing quality inspection area, and perform sensing acquisition on the target printed product to obtain a printed image; Image processing unit: Transmit the printed image, perform image segmentation and grayscale processing based on the boundary of the printed product to determine a grayscale printed image; Training unit: Obtain a standard printing template, construct a pixel stack space, and supervise the training of the printing registration module. Among them, the printing registration module includes a first pixel registration unit and a second pixel registration unit, and performs the first acquisition registration by pixel transition sampling and the second acquisition registration by pixel skip sampling; Registration unit: Transmit the grayscale printed image to the printing registration module, and determine the defective pixel features by performing pixel transition sampling registration and pixel skip sampling registration; Defect matching unit: Traverse the defective pixel features, perform defect type matching based on a defect matcher, and output printing quality data.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] First, configure an image sensor for the printing quality inspection area, and perform sensing acquisition on the target printed product to obtain a printed image. Next, transmit the printed image, perform image segmentation and grayscale processing based on the boundary of the printed product to determine a grayscale printed image. Further, obtain a standard printing template, construct a pixel stack space, and supervise the training of the printing registration module. Among them, the printing registration module includes a first pixel registration unit and a second pixel registration unit, and performs the first acquisition registration by pixel transition sampling and the second acquisition registration by pixel skip sampling. Then, transmit the grayscale printed image to the printing registration module, and determine the defective pixel features by performing pixel transition sampling registration and pixel skip sampling registration. Finally, traverse the defective pixel features, perform defect type matching based on a defect matcher, and output printing quality data. This solves the technical problem of low accuracy and efficiency in printing quality detection in the prior art, and achieves the technical effect of improving the accuracy and efficiency of printing quality detection. Description of the Drawings

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0012] Figure 1 It is a schematic flowchart of a high-precision printing quality detection method provided by an embodiment of this application;

[0013] Figure 2 It is a schematic structural diagram of a high-precision printing quality detection system provided by an embodiment of this application.

[0014] Description of the drawing reference numerals: Image acquisition unit 11, image processing unit 12, training unit 13, registration unit 14, defect matching unit 15. Detailed implementation manners

[0015] By providing a high-precision printing quality detection method and system, the present application solves the technical problems of low detection accuracy and efficiency in the prior art for printing quality detection.

[0016] Next, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0017] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server including a series of steps or units is not necessarily limited to those clearly listed steps or units, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices.

[0018] Embodiment 1, as Figure 1 shown, the present application provides a high-precision printing quality detection method, wherein the method includes:

[0019] Configure an image sensor for the printing quality inspection area, and perform sensing acquisition on the target printed product to obtain a printed image.

[0020] In the printing quality inspection area (the quality inspection position on the printing production line), according to the size, material and transmission speed of the printed product, reasonably configure a high-resolution and high-sensitivity image sensor, such as an industrial camera or a high-resolution camera, to ensure coverage of the entire detection area of the printed product. When the target printed product passes through the printing quality inspection area, the image sensor will be triggered to perform image acquisition to obtain a printed image.

[0021] Transmit back the printed image, perform image segmentation and grayscale processing based on the boundary of the printed product to determine a grayscale printed image.

[0022] Transfer the printed images captured by the image sensor to the processing system, and perform image segmentation and grayscale processing on these images. Specifically, use edge detection algorithms (such as Canny algorithm or Sobel algorithm) to extract the edge contour information of the printed product, and combine morphological processing (such as dilation and erosion operations) to optimize the edge results and remove the noise in the image; then use the contour extraction algorithm to identify the closed boundary regions, and crop the image regions related to the printed product according to the size and position of the boundary regions, removing the irrelevant background parts. After completing the boundary segmentation, perform grayscale processing on the extracted printed image regions, and use the pixel weighted average method to convert each pixel value of the RGB color image into a grayscale value. The calculation formula is: grayscale value = 0.299×R + 0.587×G + 0.114×B, where R, G, and B are the pixel values of the red, green, and blue channels respectively, and finally obtain the grayscale printed image.

[0023] Obtain a standard printing template, and construct a pixel stack space, and supervise and train the printing registration module. The printing registration module includes a first pixel registration unit and a second pixel registration unit, and performs the first acquisition registration by pixel jump sampling and the second acquisition registration by pixel skip sampling.

[0024] Load the preset standard printing template from the system, use the standard printing template as the ideal benchmark for the target printed product, and use the pixel information of the standard printing template to construct a pixel stack space. The pixel stack space is a multi-dimensional array structure used to store the pixel points and their mapping relationships of the standard printing template and the target printed image, supporting subsequent registration and defect detection operations. During the process of constructing the pixel stack space, supervise and train the printing registration module through the labeled standard template data to ensure that it can accurately perform image registration. The printing registration module includes two main units: the first pixel registration unit and the second pixel registration unit; the first pixel registration unit uses the pixel jump sampling method, and by setting a fixed sampling step (such as sampling every 5 pixels), quickly extracts the large-scale features of the template image and the target image to complete the preliminary rough registration; the second pixel registration unit finely optimizes the preliminary registration result generated by the first pixel registration unit, and uses the pixel skip sampling method (such as sampling every 2 pixels) to perform higher-precision alignment on the key pixel regions within a smaller range.

[0025] Transfer the grayscale printed image to the printing registration module, and determine the defective pixel features by performing pixel jump sampling registration and pixel skip sampling registration.

[0026] Transfer the grayscale printed image that has completed grayscale processing to the printing registration module for registration processing. The printing registration module performs pixel transition sampling registration and pixel skip-point sampling registration through the first pixel registration unit and the second pixel registration unit. Specifically, in the printing registration module, start the first pixel registration unit and adopt the pixel transition sampling method, that is, perform a jumping analysis on the pixels of the grayscale printed image according to the set sampling step (for example, sampling every 5 pixel points), and perform a preliminary match with the large-range pixel features of the standard printing template; for the preliminary registration result generated by the transition sampling registration, start the second pixel registration unit for refinement processing, and through the pixel skip-point sampling method (for example, sampling every 2 pixel points), perform further point-by-point alignment on the key areas and edge details in the grayscale image; after completing the two-stage registration, perform a difference analysis on the registration result, extract the abnormal pixel points by calculating the difference in grayscale values or the deviation of template matching, and mark them as defective pixel features.

[0027] Furthermore, the performing pixel transition sampling registration includes:

[0028] Transfer the grayscale printed image to the first pixel registration unit, perform image pixel scanning and pixel transition recognition according to the preset pixel scanning method, and locate the pixel transition coordinates; according to the preset window scale, collect the window pixel vectors of the pixel transition coordinates, add them to the pixel stack space, and determine the first pixel matrix; according to the standard printing template, determine the first standard pixel matrix, and perform registration verification on the first standard pixel matrix and the first pixel matrix to locate the abnormal pixel area, where the abnormal pixel area is the area framed by the unregistered window.

[0029] Specifically, transfer the grayscale printed image to the first pixel registration unit. After the first pixel registration unit is started, according to the preset pixel scanning method (such as linear scanning or serpentine scanning), scan the entire grayscale printed image line by line. During the scanning process, identify the pixel points whose grayscale value change exceeds the preset threshold by calculating the difference in grayscale values between adjacent pixels, and record their position coordinates. These coordinates are the pixel transition coordinates. Then, centered on each pixel transition coordinate, according to the preset window scale (such as 3×3, 5×5, etc.), collect the pixel grayscale vectors around this coordinate to form window pixel vectors, which are used to represent the feature distribution of the local area. These window pixel vectors are stored one by one into the pre-constructed pixel stack space, and finally the first pixel matrix of the target image is generated. Subsequently, extract the corresponding window pixel vectors from the standard printing template according to the same pixel transition sampling method and window scale, and construct the first standard pixel matrix to ensure the consistency of the structures of the two matrices; perform registration verification on the window vectors of the first standard pixel matrix and the first pixel matrix one by one, and use the error calculation method (such as Euclidean distance) to evaluate the matching situation. The formula is Among them, and are respectively the k-th pixel values of the corresponding window vectors of the target image and the standard template, and D is the matching error; for the window where the registration error D exceeds the preset threshold, it is marked as an abnormal pixel area, and the specific coordinates and window range of the abnormal area are recorded and saved in the abnormal data list.

[0030] Furthermore, the registration verification takes the pixel position as the first registration target and the gray vector as the second registration target. Among them, the gray vector includes the gray value of the pixel transition coordinate and the window gray gradient feature, and the window gray gradient feature includes the gradient direction and the gradient value; if the abnormal pixel area is empty, a qualified quality result is output; if the abnormal pixel area is not empty, the abnormal pixel area is transferred to the second pixel registration unit.

[0031] Preferably, after the grayscale printed image is input into the first pixel registration unit, the registration verification process first takes the pixel position as the first registration target and aligns the pixel transition coordinates in the target image and the standard template one by one; the system detects the position offset of the pixel transition point according to the preset tolerance range. If the difference between the actual coordinate of a certain transition point and the corresponding coordinate of the standard template exceeds the tolerance range, then this point is marked as a potential abnormal pixel. Subsequently, taking the gray vector as the second registration target, the gray value of each pixel transition coordinate and the window gray gradient feature are compared. The gray vector consists of two parts: the gray value of the transition coordinate and the window gray gradient feature. First, calculate the gray value difference between the transition points in the target image and the standard template. If the gray value difference exceeds the preset threshold, it is marked as abnormal; then calculate the direction and value of the gray gradient within the window, extract the gradient direction and the gradient value, and compare them with the gradient direction and value of the corresponding window of the standard template. If the deviation exceeds the set threshold, then this point is further marked as abnormal. After completing the double registration verification of the position and the gray vector, the system generates the detection result of the abnormal pixel area: if the abnormal pixel area is empty, indicating that all transition coordinates are successfully registered and no abnormality is detected, then the system directly outputs a qualified quality result and records the detection status as qualified; if the abnormal pixel area is not empty, then the marked abnormal area data, including the coordinates of the abnormal points, the gray value difference, the gradient feature, and the window range, are packed into transfer data and passed to the second pixel registration unit for further analysis, and at the same time, the processing status of the abnormal area is recorded.

[0032] Furthermore, pixel-by-pixel sampling registration is performed, including:

[0033] Transfer the abnormal pixel region to the second pixel registration unit, perform alternate pixel acquisition and add it to the pixel stack space to generate a second pixel matrix; determine a second standard pixel matrix according to the standard printing template; proofread the second pixel matrix and the second standard pixel matrix to determine pixel defect features, where the defect pixel features include geometric features and gray-scale distribution features.

[0034] After the first pixel registration unit completes preliminary registration and generates an abnormal pixel region, transfer the marked abnormal pixel region to the second pixel registration unit. After the second pixel registration unit is started, perform more refined pixel acquisition on the abnormal region based on the alternate sampling method. Specifically, within each abnormal pixel region, according to a preset alternate sampling strategy (such as sampling every other or every two pixels), extract the pixel point information with higher resolution in the abnormal region, and add the collected data to the pixel stack space to construct a second pixel matrix representing the characteristics of the abnormal region; extract the template data corresponding to the abnormal region from the standard printing template, and generate a second standard pixel matrix in the same alternate sampling method to ensure that the two matrices are consistent in sampling method and structure; proofread the second pixel matrix and the second standard pixel matrix point by point. First, compare the differences in their geometric features, including the integrity of the contour, the matching degree of the edge shape, and the angle offset situation, and determine whether there is a geometric abnormality by calculating the contour matching rate and the geometric deviation value; secondly, perform a detailed analysis of the gray-scale distribution features, and identify the color difference, texture unevenness or gray-scale abnormal points in the abnormal region by comparing the gray-scale value change trend, gradient direction and gray-scale distribution uniformity of each pixel point; the matching of the gray-scale distribution features is quantified by calculating the gray-scale difference (such as Euclidean distance or correlation coefficient) and the deviation angle of the gradient direction. If points exceeding the preset threshold are found, they are recorded as defect pixel features. After the proofreading is completed, the system generates a detailed description of the defect pixel features, including the specific data of its geometric feature abnormalities (such as shape distortion, edge breakage) and gray-scale distribution feature abnormalities (such as color deviation, texture unevenness).

[0035] Traverse the defect pixel features, perform defect type matching based on a defect matcher, and output printing quality data.

[0036] The system traverses and analyzes the marked defect pixel features, and uses a defect matcher (such as based on a feature template or a machine learning algorithm) to classify these defects into specific defect types (such as color deviation, stain, missing, etc.). Finally, the system outputs a set of printing quality data, including the detection results and detailed information about the defect types, for production quality assessment and improvement.

[0037] Furthermore, perform defect type matching based on a defect matcher and output printing quality data, including:

[0038] Construct a defect matcher, which includes a first matching layer based on defect status and a second matching layer based on printing defect types; based on the first matching layer, identify the defect pixel features and perform the matching of the geometric features to determine the first defect status; according to the inter-layer mapping, based on the second matching layer, perform the matching of the gray-scale distribution features to determine the defect type; combine the defect pixel features and the defect type to determine the printing quality data.

[0039] After the extraction of defect pixel features is completed, the system starts the defect matcher to perform type matching on the defects and generate printing quality data. The defect matcher adopts a hierarchical structure, including a first matching layer based on defect status and a second matching layer based on printing defect types. First, input each defect pixel feature into the first matching layer to extract its geometric feature information, such as contour shape, edge integrity, and position offset degree. Calculate the geometric deviation between this area and the standard template through a contour matching algorithm (such as Hu moment feature matching or shape context matching), and output the first defect status according to the matching score, such as edge breakage, shape deformation, or position offset. Then, according to the inter-layer mapping rule, input the defect status generated by the first matching layer into the second matching layer, and refine the analysis of the gray-scale distribution features of the defect pixel area in combination with this status. In the second matching layer, the system extracts the gray-scale value difference, gradient direction, and distribution uniformity, and determines the specific defect type through methods such as gray-scale histogram matching, correlation calculation, or gradient direction deviation analysis. For example, when the gray-scale distribution shows local unevenness, it is marked as a stain defect; if the gradient direction is disordered, it is determined as a blur defect; if the gray-scale value deviates significantly from the template, it is marked as a color difference defect. After the two-layer matching is completed, the system combines each defect pixel feature with the corresponding defect type to generate detailed record data including defect location, geometric features, gray-scale features, and defect type, and summarizes all defect data to generate printing quality data.

[0040] Furthermore, the construction of the defect matcher includes:

[0041] Divide M types of defect statuses, where M is a positive integer greater than 1, and the defect statuses at least include blocky, linear, and discrete dot-like; interact with the printing detection records, mine the printing defect types, and determine the attribution relationship between the printing defect types and the M types of defect statuses, where each type of defect status corresponds to at least one printing defect type; construct a first matching layer based on the M types of defect statuses, construct a second matching layer based on the printing defect types, and establish an inter-layer mapping between the first matching layer and the second matching layer based on the attribution relationship to generate a defect matcher.

[0042] When constructing a defect matcher, the system first classifies the status of printing defects into M types of defect statuses, where M is a positive integer greater than 1. The defect statuses at least include blocky, linear, and discrete dot-like. Blocky defects usually show large-area grayscale unevenness, such as stains or coating missing; linear defects include breaks or blurs of printing lines; discrete dot-like defects refer to scattered abnormal pixel points, such as tiny impurities or color spots. Next, the system loads and interacts with historical printing detection records, deeply mines the recorded defect data, and automatically extracts potential printing defect types through data clustering and pattern analysis algorithms (such as K-means clustering or DBSCAN), such as color difference, stain, blur, offset, etc. At the same time, the system determines the attribution of each printing defect type according to the corresponding relationship between the defect type and the M types of defect statuses. For example, "stain" belongs to blocky defects, "line blur" belongs to linear defects, and "impurity" belongs to discrete dot-like defects.

[0043] After clarifying the attribution relationship between the defect status and the printing defect type, the system starts to construct a defect matcher. First, a first matching layer is constructed based on the M types of defect statuses, and each status defines a matching model for detecting and classifying the geometric feature status of the input data. The blocky defect model focuses on large-area contour features; the linear defect model focuses on line continuity and curvature changes; the discrete dot-like defect model analyzes the sparse distribution features of pixel points. Subsequently, the system constructs a second matching layer based on the extracted printing defect types, and each defect type is represented by an independent classification model. The model inputs include grayscale value distribution, gradient direction, and texture features. The output of the second matching layer is a specific defect type determination.

[0044] To achieve the linkage of the two-layer matching, the system establishes an inter-layer mapping rule between the first matching layer and the second matching layer according to the aforementioned attribution relationship. The mapping rule stipulates that the matching result of each defect status can trigger a specific defect type classification module. For example, when the first matching layer identifies as "linear defect", the system inputs the corresponding grayscale distribution and gradient features into the second matching layer for further subdivision into types such as "line break" or "line blur". Finally, the system integrates the two-layer matching relationship to generate a complete defect matcher for subsequent defect type matching and quality data generation.

[0045] Furthermore, after outputting the printing quality data, it includes:

[0046] According to the periodic printing quality data of a preset period, filter out high-frequency printing defects that meet the preset defect frequency; conduct printing control traceability for the high-frequency printing defects, determine the feedback control strategy, and guide the printing control of the target printed product.

[0047] After outputting the printed quality data, the system enters the periodic data analysis and feedback control stage. First, the system performs statistical analysis on the stored printed quality data according to a preset period (such as daily, weekly, or monthly), and filters out the high-frequency printing defects that meet the preset defect frequency. The determination basis of the high-frequency printing defects is whether their occurrence frequency in multiple periods exceeds the set threshold. For example, the occurrence times of the "stain defect" in a month exceed 10% of the total detection times. Through the frequency statistics of the defect types, the system generates a list of high-frequency defects, which is arranged from high to low according to the occurrence frequency, highlighting the defect problems that need to be focused on. For the screened high-frequency printing defects, the system further performs a printing control traceability analysis. The traceability analysis determines the possible causes by correlating the time points of defect occurrence, detection positions, and relevant process parameters (such as ink concentration, printing speed, temperature, or pressure). The system can call historical process data records and use correlation analysis algorithms (such as Pearson correlation coefficient or multivariate regression analysis) to identify the significant relationships between printing parameters and defect frequencies. For example, through analysis, it is found that the "color difference defect" is closely related to the ink concentration fluctuation, or the "blurred line" is related to the unstable pressure of the print head.

[0048] After completing the traceability analysis, the system automatically generates feedback control strategies (such as adjusting the upper and lower limits of the ink concentration, improving the alignment accuracy of the print head, adding temperature or pressure sensors, etc.) according to the defect causes, and guides the adjustment of the printing process of the target printed product. For example, the system can automatically send the adjusted ink concentration parameters to the ink control unit of the printing equipment, or trigger the update of the alarm threshold of the pressure sensor module to ensure a significant reduction in the defect rate during the subsequent printing process.

[0049] In summary, the embodiments of the present application at least have the following technical effects:

[0050] First, an image sensor is configured in the printed quality inspection area, and the target printed product is sensed and collected to obtain a printed image. Then, the printed image is transmitted back, and image segmentation and grayscale processing are performed based on the boundary of the printed product to determine the grayscale printed image. Further, a standard printing template is obtained, and a pixel stack space is constructed to supervise and train the printing registration module. The printing registration module includes a first pixel registration unit and a second pixel registration unit, and performs the first acquisition registration by pixel transition sampling and the second acquisition registration by pixel alternate sampling. Then, the grayscale printed image is transmitted to the printing registration module, and the defect pixel features are determined by performing pixel transition sampling registration and pixel alternate sampling registration. Finally, the defect pixel features are traversed, and defect type matching is performed based on the defect matcher to output the printed quality data. This solves the technical problems of low printing quality detection accuracy and efficiency in the prior art, and achieves the technical effect of improving the printing quality detection accuracy and efficiency.

[0051] Embodiment 2. Based on the same inventive concept as a high-precision printing quality detection method in the foregoing embodiment, as Figure 2 shown, the present application provides a high-precision printing quality detection system, wherein the system includes:

[0052] An image acquisition unit 11: Configure an image sensor for the printing quality inspection area, and perform sensing acquisition on the target printed product to obtain a printed image; An image processing unit 12: Transmit the printed image, perform image segmentation and grayscale processing based on the boundary of the printed product to determine a grayscale printed image; A training unit 13: Obtain a standard printing template, and construct a pixel stack space, and supervise and train a printing registration module, wherein the printing registration module includes a first pixel registration unit and a second pixel registration unit, perform first acquisition registration by pixel transition sampling, and perform second acquisition registration by pixel skip sampling; A registration unit 14: Transmit the grayscale printed image to the printing registration module, and determine defect pixel features by performing pixel transition sampling registration and pixel skip sampling registration; A defect matching unit 15: Traverse the defect pixel features, perform defect type matching based on a defect matcher, and output printing quality data.

[0053] Further, the registration unit 14 is used to execute the following method:

[0054] Transmit the grayscale printed image to the first pixel registration unit, perform image pixel scanning and pixel transition recognition according to a preset pixel scanning method, and locate the pixel transition coordinates; According to a preset window scale, perform window pixel vector acquisition on the pixel transition coordinates, add them to the pixel stack space, and determine a first pixel matrix; According to the standard printing template, determine a first standard pixel matrix, perform registration and calibration on the first standard pixel matrix and the first pixel matrix, and locate an abnormal pixel area, wherein the abnormal pixel area is an area framed by an unregistered window.

[0055] Further, the registration unit 14 is used to execute the following method:

[0056] The registration and calibration takes the pixel position as the first registration target and the grayscale vector as the second registration target, wherein the grayscale vector includes the grayscale value of the pixel transition coordinate and the window grayscale gradient feature, and the window grayscale gradient feature includes a gradient direction and a gradient value; If the abnormal pixel area is empty, output a quality qualified result; If the abnormal pixel area is not empty, transfer the abnormal pixel area to the second pixel registration unit.

[0057] Further, the registration unit 14 is used to execute the following method:

[0058] Transfer the abnormal pixel region to the second pixel registration unit, perform skip-point pixel acquisition and add it to the pixel stack space to generate a second pixel matrix; determine a second standard pixel matrix according to the standard printing template; proofread the second pixel matrix and the second standard pixel matrix to determine pixel defect features, where the defect pixel features include geometric features and gray-scale distribution features.

[0059] Further, the defect matching unit 15 is used to execute the following method:

[0060] Construct a defect matcher, which includes a first matching layer based on the defect state and a second matching layer based on the printing defect type; based on the first matching layer, identify the defect pixel features and perform the matching of the geometric features to determine the first defect state; according to the inter-layer mapping, based on the second matching layer, perform the matching of the gray-scale distribution features to determine the defect type; combine the defect pixel features and the defect type to determine the printing quality data.

[0061] Further, the defect matching unit 15 is used to execute the following method:

[0062] Divide M types of defect states, where M is a positive integer greater than 1, and the defect states at least include blocky, linear, and discrete dot-like; interact with the printing detection records, mine the printing defect types, and determine the attribution relationship between the printing defect types and the M types of defect states, where each type of defect state corresponds to at least one printing defect type; construct a first matching layer based on the M types of defect states, construct a second matching layer based on the printing defect types, and establish an inter-layer mapping between the first matching layer and the second matching layer based on the attribution relationship to generate a defect matcher.

[0063] Further, the defect matching unit 15 is used to execute the following method:

[0064] According to the periodic printing quality data of a preset period, screen out the high-frequency printing defects that meet the preset defect frequency; perform printing control traceability for the high-frequency printing defects to determine a feedback control strategy to guide the printing control of the target printed product.

[0065] It should be noted that the above sequence of embodiments of the present application is only for description and does not represent the advantages or disadvantages of the embodiments. And the above describes specific embodiments of this specification. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0066] The foregoing are only the preferred embodiments of the present application, and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

[0067] This specification and the drawings are merely exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A high-precision printing quality detection method, characterized in that, The method includes: Configuring an image sensor for the printing quality inspection area, and performing sensing acquisition on the target printed product to obtain a printed image; Transmitting the printed image back, performing image segmentation and grayscale processing based on the boundaries of the printed product to determine a grayscale printed image; Obtaining a standard printing template, constructing a pixel stack space, and supervising and training a printing registration module, where the printing registration module includes a first pixel registration unit and a second pixel registration unit, performing first acquisition registration by pixel transition sampling, and performing second acquisition registration by pixel skip sampling; Transmitting the grayscale printed image to the printing registration module, and determining defective pixel features by performing pixel transition sampling registration and pixel skip sampling registration; Traversing the defective pixel features, performing defect type matching based on a defect matcher, and outputting printing quality data; Among them, the performing pixel transition sampling registration includes: Transmitting the grayscale printed image to the first pixel registration unit, performing image pixel scanning and pixel transition identification according to a preset pixel scanning method, and locating pixel transition coordinates; According to a preset window scale, performing window pixel vector acquisition on the pixel transition coordinates, adding them into the pixel stack space, and determining a first pixel matrix; According to the standard printing template, determining a first standard pixel matrix, performing registration and calibration on the first standard pixel matrix and the first pixel matrix, and locating an abnormal pixel area, where the abnormal pixel area is an area framed by an unregistered window; Among them, the registration and calibration takes the pixel position as the first registration target and the grayscale vector as the second registration target, where the grayscale vector includes the grayscale value of the pixel transition coordinates and the window grayscale gradient feature, and the window grayscale gradient feature includes a gradient direction and a gradient value; If the abnormal pixel area is empty, output a qualified quality result; If the abnormal pixel area is non-empty, transfer the abnormal pixel area to the second pixel registration unit; Among them, the performing pixel skip sampling registration includes: Transferring the abnormal pixel area to the second pixel registration unit, performing skip pixel acquisition and adding them into the pixel stack space to generate a second pixel matrix; According to the standard printing template, determining a second standard pixel matrix; Calibrating the second pixel matrix and the second standard pixel matrix to determine pixel defect features, where the defective pixel features include geometric features and grayscale distribution features.

2. The high-precision printing quality detection method according to claim 1, characterized in that Performing defect type matching based on a defect matcher and outputting printing quality data, including: Constructing a defect matcher, which includes a first matching layer based on defect status and a second matching layer based on printing defect types; Based on the first matching layer, identifying the defective pixel features and performing matching of the geometric features to determine a first defect status; According to the inter-layer mapping, based on the second matching layer, performing matching of the grayscale distribution features to determine the defect type; Combining the defective pixel features and the defect type to determine the printing quality data.

3. The high-precision printing quality detection method according to claim 2, characterized in that The constructing the defect matcher includes: Dividing M types of defect statuses, where M is a positive integer greater than 1, and the defect statuses at least include blocky, linear, and discrete dot-like; Interactive printing detection records are used to identify types of printing defects and determine the attribution relationship between the types of printing defects and M types of defect statuses, where each type of defect status corresponds to at least one type of printing defect; Based on the M types of defect statuses, a first matching layer is constructed, based on the types of printing defects, a second matching layer is constructed, and an inter-layer mapping between the first matching layer and the second matching layer is established based on the attribution relationship to generate a defect matcher.

4. A high-precision printing quality detection method according to claim 1, characterized in that, After outputting the printing quality data, it includes: According to the periodic printing quality data in a preset period, high-frequency printing defects that meet the preset defect frequency are screened; For the high-frequency printing defects, printing control traceability is performed to determine a feedback control strategy to guide the printing control of the target printed product.

5. A high-precision printing quality detection system, characterized in that, For implementing a high-precision printing quality detection method according to any one of claims 1-4, the system includes: Image acquisition unit: An image sensor is configured for the printing quality inspection area, and the target printed product is sensed and acquired to obtain a printing image; Image processing unit: The printing image is transmitted back, and image segmentation and grayscale processing are performed based on the boundary of the printed product to determine a grayscale printing image; Training unit: Obtain a standard printing template and construct a pixel stack space to supervise and train a printing registration module, where the printing registration module includes a first pixel registration unit and a second pixel registration unit, and first acquisition registration is performed by pixel transition sampling, and second acquisition registration is performed by pixel skip sampling; Registration unit: Transmit the grayscale printing image to the printing registration module, and determine the defective pixel features by performing pixel transition sampling registration and pixel skip sampling registration; Defect matching unit: Traverse the defective pixel features, perform defect type matching based on the defect matcher, and output the printing quality data.

Images