A surface quality visual inspection system for printed packaging paper

Abstract

The application discloses a kind of surface quality visual inspection systems of packaging paper printed matter, it is related to printed matter detection technical field;The present application is triggered when quality traceability signaling, according to the defect index of current K group of unqualified printed matter, construct fault matching model, simultaneously extract historical data from database to construct fault history model, by calculating the area similarity value, shape similarity value of fault matching model and fault history model, and then get comprehensive similarity index, obtain the fault history model with the highest comprehensive similarity index, extract its fault reason, and K group fault reason is matched, counted and sorted, form fault reason set, as the estimated defect reason of printing equipment, this way combines historical data, can quickly locate the potential fault reason of printing equipment, compared with artificial investigation equipment component, greatly improve the traceability efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of printed matter detection, in particular to a surface quality visual detection system for packaging paper printed matter. Background Art

[0002] In the packaging paper printing and production process, the surface quality of the printed product is of vital importance. It not only affects the aesthetics and overall image of the product, but may also affect consumers' trust in the product, and thus is related to the market competitiveness of the product.

[0003] However, the current visual inspection system for the surface quality of printed packaging paper still has the following deficiencies in practical application:

[0004] In actual production, existing visual inspection systems only determine whether products are qualified, which can no longer meet the company's needs for refined product quality management. They cannot accurately quantify various defects in printed packaging paper, such as scratches, patterns, and ink, which is not conducive to in-depth analysis of the root causes of product quality problems.

[0005] When faced with a large number of unqualified products, existing detection methods are unable to quickly and accurately trace the cause of the failure of printing equipment by combining historical data. When batch printing defects occur, companies can only manually check the various components of the equipment. This method is time-consuming, labor-intensive and inefficient, and cannot solve production problems in a timely manner.

[0006] Therefore, a surface quality inspection system for printed packaging paper is introduced. Summary of the Invention

[0007] The purpose of the present invention is to solve the problems mentioned in the background technology and to provide a surface quality visual inspection system for packaging paper printed products.

[0008] The purpose of the present invention can be achieved by the following technical solution: A surface quality visual inspection system for printed packaging paper, comprising:

[0009] Defect recognition module: Analyzes the image data collected from the printed packaging paper product and determines various defect indices of the printed packaging paper product image data based on the analysis results. These defect indices include a physical defect index M1, a pattern defect index M2, and an ink defect index M3. Based on these defect indices, the print quality index Ger of the printed packaging paper product image data is determined.

[0010] Defect processing module: Sets the quality threshold index corresponding to the printing quality index Ger, and classifies each group of packaging printed products into qualified printed products and unqualified printed products based on the set quality threshold index. At the same time, it continuously monitors the classification results of each group of packaging paper printed products. If the classification results of each group of packaging paper printed products reach K groups as unqualified printed products during the continuous monitoring process, the quality traceability signaling is triggered and sent to the defect traceability module; where K>5;

[0011] Defect tracing module: When the quality tracing signal is triggered, the printing quality index Ger of K groups of unqualified printed products is extracted, and corresponding steps are executed to determine the estimated defect cause of the printing equipment.

[0012] As a preferred embodiment of the present invention, the physical defect index M1 of the packaging paper printed product image data is determined as follows:

[0013] Identify scratch defect features, wrinkle defect features, and void defect features from image data of packaging paper prints;

[0014] Dividing the image data of the printed wrapping paper into various image sub-regions, counting the total number of pixels of the scratch defect feature, the total number of pixels of the wrinkle defect feature, and the total number of pixels of the cavity defect feature in each image sub-region, and converting them into scratch feature area, wrinkle feature area, and cavity feature area based on the image resolution;

[0015] Set the weight coefficients corresponding to the scratch feature area, wrinkle feature area, and cavity feature area respectively, multiply the scratch feature area, wrinkle feature area, and cavity feature area of ​​each image sub-region by the corresponding set weight coefficients, and then sum them to obtain the defect sub-value of each image sub-region;

[0016] Set the weight coefficients corresponding to different graphic sub-regions, extract the defect sub-values ​​of each image sub-region, multiply them by the corresponding weight coefficients, and then sum them to obtain the comprehensive defect value of the packaging paper printed product;

[0017] The intervals of the comprehensive values ​​corresponding to the preset defect comprehensive values ​​are each corresponding to a physical defect score of a printed packaging paper product; the comprehensive defect values ​​of the printed packaging paper product are matched with the corresponding intervals of the comprehensive values ​​to obtain the physical defect score of the printed packaging paper product;

[0018] The obtained physical defect score is used as the physical defect index M1 of the packaging paper printed product image data.

[0019] As a preferred embodiment of the present invention, the pattern defect index M2 of the packaging paper printed matter image data is determined as follows:

[0020] Extract qualified image data corresponding to the printed wrapping paper image data, align the printed wrapping paper image data with the qualified image data, perform feature point detection and descriptor calculation on the two sets of image data to obtain a feature point set and corresponding descriptors; perform feature point matching on the two sets of image data to obtain a matching point set; select M matching point pairs from the matching point set to obtain a transformation matrix from the printed wrapping paper image data to the qualified image data;

[0021] The obtained transformation matrix is ​​used to transform the packaging paper printed product image so that the packaging paper printed product is spatially aligned with the qualified image data. The two aligned sets of image data are compared pixel by pixel to calculate the mean square error between the packaging paper printed product image data and the qualified image data.

[0022] A reference threshold corresponding to the mean square error is set. If the mean square error between the packaging paper printed product image data and the qualified image data is less than the reference threshold, a preset value is used as the pattern defect index M2 of the packaging paper printed product image data. If the mean square error between the packaging paper printed product image data and the qualified image data is greater than the reference threshold, the difference between the mean square error and the reference threshold is calculated and recorded as the deviation degree value.

[0023] The preset deviation degree value corresponds to an interval of degree values, and each group of degree value intervals corresponds to a pattern defect score of a packaging paper print; the deviation degree value of the packaging paper print is matched with the corresponding degree value interval to obtain the pattern defect score of the packaging paper print; and the obtained pattern defect score is used as the pattern defect index M2 of the packaging paper print image data.

[0024] As a preferred embodiment of the present invention, the ink defect index M3 of the packaging paper printed matter image data is determined as follows:

[0025] identifying ink dot defect features and ink spot defect features from image data of a packaging paper print;

[0026] Counting the total number of pixels of ink dot defect features and the total number of pixels of ink spot defect features in the packaging paper printed product image data, and converting them into ink dot feature areas and ink spot feature areas based on the resolution of the image;

[0027] Set weight coefficients corresponding to the characteristic areas of ink dots and ink spots, respectively. Multiply the characteristic areas of ink dots and ink spots of the packaging paper printed image data by the corresponding weight coefficients, and then sum them to obtain the ink defect value of each image sub-region, which is recorded as Q1.

[0028] Set the standard color of the printed wrapping paper, calculate the average color value of the printed wrapping paper in the Lab color space, and record it as L1, a1, and b1; extract the average color value of the standard color in the Lab color space, and record it as L2, a2, and b2;

[0029] According to the formula Calculate the color difference evaluation value Q2 of the packaging paper print;

[0030] Substitute the ink defect value Q1 and color difference evaluation value Q2 of the packaging paper print into the formula Perform weighted calculation to obtain the ink performance value Q3 of the packaging paper printing; Q1 允许 、Q2 允许 They represent the maximum allowable value of ink defects and the maximum allowable value of color difference evaluation respectively; α1 and α2 are the influencing weight factors of ink defect value Q1 and color difference evaluation value Q2 respectively;

[0031] The performance value interval corresponding to the ink performance value Q3 is preset, and each group of performance value intervals corresponds to an ink defect score of the packaging paper printed product; the ink performance value Q3 of the packaging paper printed product is matched with the corresponding performance value interval to obtain the ink defect score of the packaging paper printed product;

[0032] The obtained ink defect score is used as the ink defect index M3 of the packaging paper print image data.

[0033] As a preferred embodiment of the present invention, the printing quality index Ger of the packaging paper printed matter image data is determined as follows:

[0034] The physical defect index M1, pattern defect index M2 and ink defect index M3 of the packaging paper print are extracted; the weight coefficients corresponding to the physical defect index M1, pattern defect index M2 and ink defect index M3 are set respectively, the physical defect index M1, pattern defect index M2 and ink defect index M3 of the packaging paper print are multiplied by the corresponding set weight coefficients respectively, and then the sum is summed to obtain the printing quality index Ger of the packaging paper print image data.

[0035] As a preferred embodiment of the present invention, each group of packaged printed products is classified into qualified printed products and unqualified printed products according to a set quality threshold index, specifically:

[0036] The printing quality index Ger of each group of packaging paper printed products is analyzed and compared with the set quality threshold index. If the printing quality index Ger of a group of packaging paper printed products is higher than the set quality threshold index, it is classified as unqualified printed products, otherwise it is classified as qualified printed products.

[0037] As a preferred embodiment of the present invention, when the quality traceability signaling is triggered, the printing quality index Ger of K groups of unqualified printed products is extracted, and corresponding steps are performed, specifically:

[0038] S1: Pre-build a fault case database corresponding to the printing equipment, obtain the physical defect index, pattern defect index, and ink defect index of the printed packaging produced when each historical fault case corresponding to the printing equipment occurred, obtain the fault cause that caused each historical fault of the printing equipment, and combine the corresponding fault cause with the corresponding physical defect index, pattern defect index, and ink defect index and store them in the fault case database;

[0039] S2: From the printing quality index Ger of K groups of unqualified printed products, obtain the physical defect index M1, pattern defect index M2 and ink defect index M3 of the K groups of unqualified printed products, and draw three rays with the origin as the center point; the lengths of the three rays correspond to the values ​​of the physical defect index M1, pattern defect index M2 and ink defect index M3 respectively. With the end points of the three rays as marking points, connect the three groups of marking points in sequence to form a closed polygon, and use the formed polygon as the fault matching model of the unqualified printed products.

[0040] As a preferred embodiment of the present invention, when the quality traceability signaling is triggered, the printing quality index Ger of K groups of unqualified printed products is extracted and corresponding steps are executed, further comprising:

[0041] S3: Similarly to step S2, the physical defect index, pattern defect index, and ink defect index of the packaging printed products produced when each historical failure case occurred in the failure case database are extracted, and polygons are constructed. The constructed polygons are used as the failure history model corresponding to each historical failure case;

[0042] S4: Obtain the areas of the fault matching model and each group of fault history models, use the area of ​​the fault matching model as the numerator and the area of ​​the fault history model as the denominator, calculate the ratio between the two groups of areas, and obtain the area similarity value F1 between the fault matching model and each group of fault history models;

[0043] By calculating the Euclidean distance, the closest distance values ​​of the three groups of ray coordinates between the fault matching model and each group of fault history models are obtained, and the maximum value of the three groups of closest distance values ​​is selected as the shape similarity value F2 between the fault matching model and each group of fault history models;

[0044] After normalizing the area similarity value F1 and shape similarity value F2 of the fault matching model and each group of fault history models, they are put into the formula The calculation is performed to obtain a comprehensive similarity index F3 between the fault matching model and each group of fault history models; wherein η1 and η2 are influence weight factors of the area similarity value F1 and the shape similarity value F2 respectively.

[0045] As a preferred embodiment of the present application, the estimated defect cause of the printing equipment is determined, specifically:

[0046] S5: Select the fault history model with the highest comprehensive similarity index F3, and extract the fault cause corresponding to the fault history model; match the K groups of fault causes with each other, if the same fault cause appears, count the number of occurrences of the same fault cause, and sort the fault causes from high to low according to the number of occurrences, integrate the fault causes into a fault cause set after the sorting is completed, and take the fault cause set as the estimated defect cause of the printing equipment.

[0047] Compared with the prior art, the present application has the following advantages:

[0048] The present application processes the packaging paper printed matter image data, identifies scratch, wrinkle, hollow, ink dot and ink spot defect features, counts the total number of related pixels and converts it into area, matches the defect score through pre-set different intervals, and finally determines the physical defect index, pattern defect index, ink defect index and printing quality index. These quantitative indexes can accurately reflect the defect degree of the packaging paper printed matter, meet the needs of enterprises for fine management of product quality, and help enterprises to deeply analyze the root cause of product quality problems.

[0049] The present application constructs a fault matching model according to the defect indexes of the current K groups of unqualified printed matters when the quality traceability signaling is triggered, constructs a fault history model by extracting historical data from the database, calculates the area similarity value and the shape similarity value of the fault matching model and the fault history model, and then obtains the comprehensive similarity index, obtains the fault history model with the highest comprehensive similarity index, extracts its fault cause, and matches, counts and sorts the K groups of fault causes to form a fault cause set as the estimated defect cause of the printing equipment. This way combines historical data to quickly locate the potential fault cause of the printing equipment, greatly improving the traceability efficiency compared with manual inspection of equipment components. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to facilitate understanding of those skilled in the art, the present application will be further described below with reference to the accompanying drawings.

[0051] Figure 1 The present application is a schematic diagram of the principle. DETAILED DESCRIPTION

[0052] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0053] See also Figure 1 As shown, a surface quality visual inspection system for packaging paper printed products includes a defect recognition module, a defect processing module, and a defect tracing module;

[0054] The defect recognition module is used to analyze the image data collected from the packaging paper printed product and determine various defect indices of the packaging paper printed product image data based on the analysis results. The various defect indices include a physical defect index M1, a pattern defect index M2, and an ink defect index M3. Based on the various defect indices of the packaging paper printed product image data, a print quality index Ger of the packaging paper printed product image data is determined.

[0055] It should be noted that the image data is collected by installing a high-resolution industrial camera above the transmission path of the packaging paper print, which can meet the needs of clearly capturing the surface details of the packaging paper print. The collected image data is preprocessed before analysis, and the Gaussian filtering algorithm is used to reduce the noise of the image. The size of the Gaussian kernel is adjusted according to the noise situation of the image, and then the color image is converted into a grayscale image. Then, the histogram equalization algorithm is used to enhance the grayscale image. By redistributing the grayscale values ​​of the image, the grayscale histogram of the image is made more uniform, thereby enhancing the contrast between defects and background in the image.

[0056] Determine the physical defect index M1 of the packaging paper printed product image data, specifically:

[0057] Identify scratch defect features, wrinkle defect features, and void defect features from image data of packaging paper prints;

[0058] Based on the visual attention of the current printed wrapping paper, the image data of the printed wrapping paper is divided into various image sub-regions. The total number of pixels of the scratch defect feature, the total number of pixels of the wrinkle defect feature, and the total number of pixels of the cavity defect feature in each image sub-region are counted, and the total number of pixels of the scratch defect feature, the wrinkle defect feature, and the cavity defect feature are converted into the scratch feature area, the wrinkle feature area, and the cavity feature area based on the image resolution.

[0059] Set the weight coefficients corresponding to the scratch feature area, wrinkle feature area, and cavity feature area respectively, multiply the scratch feature area, wrinkle feature area, and cavity feature area of ​​each image sub-region by the corresponding set weight coefficients, and then sum them to obtain the defect sub-value of each image sub-region;

[0060] According to the visual attention of different image sub-regions, the corresponding weight coefficients are set. The defect sub-values ​​of each image sub-region are extracted and multiplied by the corresponding weight coefficients respectively. The sum is then used to obtain the comprehensive defect value of the packaging paper printed product.

[0061] The interval of the comprehensive value corresponding to the preset defect comprehensive value is set. Each interval of the comprehensive value corresponds to a physical defect score of the printed packaging paper. The physical defect score range is set to 1-10 and is a positive integer. The higher the defect comprehensive value, the higher the physical defect score obtained. The defect comprehensive value of the printed packaging paper is matched with the corresponding comprehensive value interval to obtain the physical defect score of the printed packaging paper.

[0062] The obtained physical defect score is used as the physical defect index M1 of the packaging paper printed product image data;

[0063] It should be noted that, for example:

[0064] The scratch recognition process is:

[0065] Using the Canny edge detection algorithm, we first perform Gaussian smoothing on the preprocessed image data to reduce the impact of noise. We then calculate the image's gradient amplitude and direction. Non-maximum suppression is then performed to eliminate spurious responses caused by edge detection. Finally, through double threshold processing and edge connection, we determine the true edge. Scratches usually appear as long, thin edges, and the detected edge information can be used to preliminarily locate the scratch.

[0066] Perform morphological operations on the image after edge detection, such as dilation and erosion. The dilation operation can expand the edges of the scratches and connect the broken scratches; the erosion operation can remove some small interfering edges. By reasonably selecting the size and shape of the structural elements of dilation and erosion, the complete shape of the scratch can be better extracted.

[0067] Extract scratch features, such as length, width, and area, and set appropriate thresholds to determine whether the extracted edge is a scratch. For example, if the edge length exceeds a certain threshold and the width is relatively narrow, it is considered a scratch. At the same time, information such as the position and direction of the scratch in the image can be combined to further improve the accuracy of scratch detection.

[0068] The wrinkle recognition process is as follows:

[0069] Wrinkles can cause changes in the texture of the wrapping paper surface, so texture analysis methods can be used to detect wrinkles. Common texture analysis methods include gray-level co-occurrence matrix (GLCM) and local binary pattern (LBP). GLCM describes the spatial distribution of grayscale levels in an image. By calculating its statistical characteristics, such as contrast, correlation, and energy, it can be used to determine whether wrinkles exist in the image. LBP is a simple and effective texture description operator that generates a binary pattern by comparing the grayscale values ​​of a central pixel with those of its neighbors, reflecting the image's local texture information. Region segmentation, based on the results of texture analysis, uses methods such as threshold segmentation and cluster analysis to separate wrinkle regions from the background. Threshold segmentation divides the image into different regions by setting a threshold based on grayscale values ​​or texture features. Cluster analysis classifies pixels in an image based on their characteristics, with pixels belonging to the same class considered to be the same region. Feature verification extracts wrinkle region features, such as area, shape, and texture complexity. The segmented regions are then compared with a pre-set wrinkle feature model to verify whether they are genuine wrinkles. For example, if the area of ​​a region is large and the texture complexity is high, it is determined to be a wrinkle region;

[0070] The hole identification process is:

[0071] The pre-processed image is binarized to convert it into black and white, highlighting the characteristics of the voids. A commonly used binarization method is the global threshold method, such as the Otsu algorithm, which can automatically calculate the optimal threshold to separate the image into foreground and background. Connected region analysis is performed on the binarized image to find all connected regions in the image, each of which represents a possible void. By calculating the area, perimeter, center of gravity and other features of the connected regions, regions that meet the void characteristics are screened out. For example, an area threshold is set to remove connected regions with too small an area, as they are considered to be noise or other interference factors.

[0072] Determine the pattern defect index M2 of the packaging paper printed product image data, specifically:

[0073] The image data of the qualified image corresponding to the printed image data of the packaging paper is extracted, and the printed image data of the packaging paper is aligned with the qualified image data; the qualified image data is stored in a database, and each printed image data of the packaging paper has a unique identifier (such as a product number, a batch number, etc.) corresponding thereto; the corresponding qualified image data is retrieved from the database through the identifier; the feature point extraction algorithm is used to detect and describe the feature points of the two groups of image data respectively, and the feature point set and the corresponding descriptor are obtained; the feature point matching algorithm is used to match the feature points of the two groups of image data, and the matching point set is obtained; a number of M matching points are selected from the matching point set; wherein M is initially set by a technician; and the random sample consensus algorithm is used to obtain the transformation matrix of the printed image data of the packaging paper to the qualified image data.

[0074] The transformation matrix obtained is used to transform the printed image data of the packaging paper, so that the printed image data of the packaging paper is aligned with the qualified image data in spatial position, and the two groups of image data after alignment are compared pixel by pixel to calculate the mean square error between the printed image data of the packaging paper and the qualified image data.

[0075] A reference threshold value corresponding to the mean square error is set, if the mean square error between the printed image data of the packaging paper and the qualified image data is less than the reference threshold value, a preset value is taken as the pattern defect index M2 of the printed image data of the packaging paper; if the mean square error between the two groups of image data is less than the reference threshold value, it means that the pattern positions of the two groups of image data are completely coincident, and the preset value can be 0 or 1; if the mean square error between the printed image data of the packaging paper and the qualified image data is greater than the reference threshold value, the difference between the mean square error and the reference threshold value is calculated, and is recorded as a deviation degree value.

[0076] The deviation degree value corresponds to an interval, and each interval corresponds to a pattern defect score of the packaging paper; the pattern defect score ranges from 1 to 10 and is a positive integer, and the higher the deviation degree value, the higher the pattern defect score obtained by matching; the deviation degree value of the packaging paper is matched with the corresponding interval to obtain the pattern defect score of the packaging paper.

[0077] The pattern defect score obtained is taken as the pattern defect index M2 of the printed image data of the packaging paper.

[0078] The ink defect index M3 of the printed image data of the packaging paper is determined, specifically as follows:

[0079] The ink dot defect features and the ink spot defect features are identified from the image data of the packaging paper.

[0080] The total number of pixels of the ink dot defect features and the total number of pixels of the ink spot defect features in the image data of the packaging paper are counted, and the ink dot feature area and the ink spot feature area are converted based on the resolution of the image.

[0081] The ink defect value of the packaging paper printed matter is calculated according to the formula Q1 = w1 * S1 + w2 * S2, wherein S1 and S2 respectively represent the dot feature area and the mottle feature area of the packaging paper printed matter image data, and w1 and w2 respectively represent the weight coefficients corresponding to the dot feature area and the mottle feature area.

[0082] The standard color of the packaging paper printed matter is set according to the standard color card, and the average color value of the packaging paper printed matter in the Lab color space is calculated, which is recorded as L1, a1 and b1; the average color value of the standard color in the Lab color space is extracted, which is recorded as L2, a2 and b2;

[0083] The color difference evaluation value Q2 of the packaging paper printed matter is calculated according to the formula

[0084] The ink defect value Q1 and the color difference evaluation value Q2 of the packaging paper printed matter are substituted into the formula The weighted calculation is performed, so as to obtain the ink performance value Q3 of the packaging paper printed matter; Q1 允许 , Q2 允许 respectively represent the highest allowable value of the ink defect and the highest allowable value of the color difference evaluation; the setting is performed according to the printing quality requirement; wherein a1 and a2 respectively represent the influence weight factors of the ink defect value Q1 and the color difference evaluation value Q2;

[0085] The performance value interval corresponding to the ink performance value Q3 is preset, and each group of performance value intervals corresponds to an ink defect score of the packaging paper printed matter; the ink defect score ranges from 1 to 10 and is a positive integer, and the higher the ink performance value Q3 is, the higher the ink defect score matched is; the ink performance value Q3 of the packaging paper printed matter is matched with the corresponding performance value interval, so as to obtain the ink defect score of the packaging paper printed matter.

[0086] The obtained ink defect score is taken as the ink defect index M3 of the packaging paper printed matter image data.

[0087] It should be noted that the following examples are provided for illustration:

[0088] Dot defect recognition process:

[0089] The preprocessed gray-scale image is binarized to convert the image into a black-and-white image and highlight the difference between the dot and the background. The Otsu algorithm can be used to automatically determine the optimal threshold to divide the image into foreground (dot) and background two parts;

[0090] ​The binary image is processed using morphological dilation and erosion operations. First, the dilation operation is performed to extend the edges of the ink dots using circular or square structural elements to connect any broken parts. Then, the erosion operation is performed to remove some isolated noise points, making the shape of the ink dots clearer and more accurate.

[0091] Through connected region analysis, each connected black region is regarded as an ink dot;

[0092] Ink spot defect recognition process:

[0093] The image is segmented using methods based on region growing or cluster analysis to separate the ink spot area from the background. Based on color features and spatial neighborhood relationships, pixels with similar colors and adjacent pixels are merged into one region to identify the ink spot area.

[0094] Extracting the physical defect index M1, pattern defect index M2, and ink defect index M3 of the printed wrapping paper; setting weight coefficients corresponding to the physical defect index M1, pattern defect index M2, and ink defect index M3, respectively; multiplying the physical defect index M1, pattern defect index M2, and ink defect index M3 of the printed wrapping paper by the corresponding weight coefficients; and then summing the results to obtain the print quality index Ger of the printed wrapping paper image data;

[0095] The defect processing module is used to set the quality threshold index corresponding to the printing quality index Ger, and classify each group of packaging printed products into qualified printed products and unqualified printed products based on the set quality threshold index. At the same time, it continuously monitors the classification results of each group of packaging paper printed products. If the classification results of the cumulative number of packaging paper printed products reaching K groups are unqualified during the continuous monitoring process, the quality traceability signaling is triggered and sent to the defect traceability module; where K>5, the specific value is set by the technical staff;

[0096] Specifically:

[0097] Analyze the printing quality index Ger of each group of packaging paper printed products and compare it with the set quality threshold index. If the printing quality index Ger of a group of packaging paper printed products is higher than the set quality threshold index, it is classified as unqualified printed products; otherwise, it is classified as qualified printed products;

[0098] It should be noted that if it is classified as an unqualified printed product, the printing quality index Ger corresponding to the unqualified printed product is extracted, and the difference is calculated with the quality threshold index, and the difference is recorded as the estimated difference. If the estimated difference is lower than the preset reference difference, the image data of the unqualified printed product is extracted, and the printing quality index Ger is analyzed again, and the re-analyzed printing quality index Ger is compared with the quality threshold index. If the re-analyzed printing quality index Ger is lower than the quality threshold index, the average of the two groups of printing quality indexes Ger is taken as the final evaluation value, and the result of the comparison and classification of the final evaluation value and the quality threshold index is taken as the final classification result of the corresponding unqualified printed product.

[0099] The defect tracing module is used to extract the printing quality index Ger of K groups of unqualified printed products when the quality tracing signal is triggered, and execute corresponding steps to determine the estimated defect cause of the printing equipment;

[0100] Specifically:

[0101] S1: Pre-build a fault case database corresponding to the printing equipment, obtain the physical defect index, pattern defect index, and ink defect index of the printed packaging produced when each historical fault case corresponding to the printing equipment occurred, obtain the fault cause that caused each historical fault of the printing equipment, and combine the corresponding fault cause with the corresponding physical defect index, pattern defect index, and ink defect index and store them in the fault case database;

[0102] S2: From the print quality index Ger of K groups of unqualified printed products, obtain the physical defect index M1, pattern defect index M2, and ink defect index M3 of the K groups of unqualified printed products, and draw three rays with the origin as the center point; the first ray is along the positive direction of the x-axis and its length corresponds to the value of the physical defect index M1, the second ray is at an angle of 120 degrees to the positive direction of the x-axis, and its length corresponds to the value of the pattern defect index M2, and the third ray is at an angle of 240 degrees to the positive direction of the x-axis, and its length corresponds to the value of the ink defect index M3; the lengths of the three rays correspond to the values ​​of the physical defect index M1, pattern defect index M2, and ink defect index M3, respectively. With the end points of the three rays as marking points, the three groups of marking points are connected in sequence to form a closed polygon, and the formed polygon is used as the fault matching model of the unqualified printed products;

[0103] It should be noted that, assuming that from the printing quality index Ger of the K group of unqualified printed products, the physical defect index is 8, the pattern defect index is 6, and the ink defect index is 5;

[0104] Determine the coordinates of the endpoints of the three rays:

[0105] The first ray: along the positive direction of the x-axis, with a length of 8 and an end point coordinate of (8,0);

[0106] The second ray: The angle with the positive direction of the x-axis is 120 degrees, and the length is 6. According to the formula for converting polar coordinates to rectangular coordinates, the coordinates of the end point of the second ray are (-3, 5.2):

[0107] The third ray: The angle with the positive direction of the x-axis is 240 degrees, and the length is 5; also calculated according to the above formula, the coordinates of the end point of the third ray are (-2.5, -4.3).

[0108] Connecting these three coordinates in sequence forms a closed polygon, which is the fault matching model constructed based on this set of defect indexes of unqualified printed products.

[0109] S3: Similarly to step S2, the physical defect index, pattern defect index, and ink defect index of the packaging printed products produced when each historical failure case occurred in the failure case database are extracted, and polygons are constructed. The constructed polygons are used as the failure history model corresponding to each historical failure case;

[0110] S4: Obtain the areas of the fault matching model and each group of fault history models, use the area of ​​the fault matching model as the numerator and the area of ​​the fault history model as the denominator, calculate the ratio between the two groups of areas, and obtain the area similarity value F1 between the fault matching model and each group of fault history models;

[0111] By calculating the Euclidean distance, the closest distance values ​​of the three groups of ray coordinates between the fault matching model and each group of fault history models are obtained, and the maximum value of the three groups of closest distance values ​​is selected as the shape similarity value F2 between the fault matching model and each group of fault history models;

[0112] It should be noted that the lower the closest distance value is, the closer the two groups of models are in spatial position.

[0113] After normalizing the area similarity value F1 and shape similarity value F2 of the fault matching model and each group of fault history models, they are put into the formula Calculation is performed to obtain the comprehensive similarity index F3 between the fault matching model and each group of fault history models; where η1 and η2 are the influence weight factors of the area similarity value F1 and the shape similarity value F2 respectively;

[0114] S5: Select the fault history model with the highest comprehensive similarity index F3 and extract the fault cause of the corresponding fault history model; match the K groups of fault causes with each other. If the same fault cause appears, count the number of occurrences of the same fault cause and sort the fault causes from high to low according to the number of occurrences. After sorting, integrate them into a set of fault causes, and use the set of fault causes as the estimated defect cause of the printing equipment;

[0115] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A surface quality visual inspection system for printed packaging paper, characterized in that: include: Defect recognition module: Analyzes the image data collected from the packaging paper printed product and determines various defect indices of the packaging paper printed product image data based on the analysis results; The various defect indices include physical defect index M1, pattern defect index M2 and ink defect index M3; Determining a printing quality index Ger of the packaging paper printed product image data based on various defect indices of the packaging paper printed product image data; Defect processing module: Sets the quality threshold index corresponding to the printing quality index Ger, and classifies each group of packaging printed products into qualified printed products and unqualified printed products based on the set quality threshold index. At the same time, it continuously monitors the classification results of each group of packaging paper printed products. If the classification results of each group of packaging paper printed products reach K groups as unqualified printed products during the continuous monitoring process, the quality traceability signaling is triggered and sent to the defect traceability module; where K>5; Defect tracing module: When the quality tracing signal is triggered, the printing quality index Ger of K groups of unqualified printed products is extracted and corresponding steps are executed to determine the estimated defect cause of the printing equipment; Specifically: S1: Pre-build a fault case database corresponding to the printing equipment, obtain the physical defect index, pattern defect index, and ink defect index of the printed packaging produced when each historical fault case corresponding to the printing equipment occurred, obtain the fault cause that caused each historical fault of the printing equipment, and combine the corresponding fault cause with the corresponding physical defect index, pattern defect index, and ink defect index and store them in the fault case database; S2: From the print quality index Ger of the K groups of unqualified printed products, obtain the physical defect index M1, pattern defect index M2, and ink defect index M3 of the K groups of unqualified printed products. Draw three rays with the origin as the center point; the lengths of the three rays correspond to the values ​​of the physical defect index M1, pattern defect index M2, and ink defect index M3, respectively. Using the end points of the three rays as marking points, connect the three groups of marking points in sequence to form a closed polygon. The formed polygon is used as the fault matching model of the unqualified printed products. S3: Similarly to step S2, the physical defect index, pattern defect index, and ink defect index of the packaging printed products produced when each historical failure case occurred in the failure case database are extracted, and polygons are constructed. The constructed polygons are used as the failure history model corresponding to each historical failure case; S4: Obtain the areas of the fault matching model and each group of fault history models, use the area of ​​the fault matching model as the numerator and the area of ​​the fault history model as the denominator, calculate the ratio between the two groups of areas, and obtain the area similarity value F1 between the fault matching model and each group of fault history models; By calculating the Euclidean distance, the closest distance values ​​of the three groups of ray coordinates between the fault matching model and each group of fault history models are obtained, and the maximum value of the three groups of closest distance values ​​is selected as the shape similarity value F2 between the fault matching model and each group of fault history models; After normalizing the area similarity value F1 and shape similarity value F2 of the fault matching model and each group of fault history models, they are put into the formula Calculate and obtain the comprehensive similarity index F3 between the fault matching model and each group of fault history models; in are the influence weight factors of area similarity value F1 and shape similarity value F2 respectively; S5: Select the fault history model with the highest comprehensive similarity index F3, and extract the fault cause of the corresponding fault history model; match the K groups of fault causes with each other. If the same fault cause appears, count the number of occurrences of the same fault cause, and sort the fault causes from high to low according to the number of occurrences. After sorting, integrate them into a fault cause set, and use the fault cause set as the estimated defect cause of the printing equipment.

2. The surface quality visual inspection system for packaging paper printed products according to claim 1, characterized in that: Determine the physical defect index M1 of the packaging paper printed product image data, specifically: Identify scratch defect features, wrinkle defect features, and void defect features from image data of packaging paper prints; Dividing the image data of the printed wrapping paper into various image sub-regions, counting the total number of pixels of the scratch defect feature, the total number of pixels of the wrinkle defect feature, and the total number of pixels of the cavity defect feature in each image sub-region, and converting them into scratch feature area, wrinkle feature area, and cavity feature area based on the image resolution; Set the weight coefficients corresponding to the scratch feature area, wrinkle feature area, and cavity feature area respectively, multiply the scratch feature area, wrinkle feature area, and cavity feature area of ​​each image sub-region by the corresponding set weight coefficients, and then sum them to obtain the defect sub-value of each image sub-region; Set the weight coefficients corresponding to different graphic sub-regions, extract the defect sub-values ​​of each image sub-region, multiply them by the corresponding weight coefficients, and then sum them to obtain the comprehensive defect value of the packaging paper printed product; The intervals of the comprehensive values ​​corresponding to the preset defect comprehensive values ​​are each corresponding to a physical defect score of a printed packaging paper product; the comprehensive defect values ​​of the printed packaging paper product are matched with the corresponding intervals of the comprehensive values ​​to obtain the physical defect score of the printed packaging paper product; The obtained physical defect score is used as the physical defect index M1 of the packaging paper printed product image data.

3. The surface quality visual inspection system for packaging paper printed products according to claim 2, characterized in that: Determine the pattern defect index M2 of the packaging paper printed product image data, specifically: Extracting qualified image data corresponding to the packaging paper printed product image data, aligning the packaging paper printed product image data with the qualified image data, performing feature point detection and descriptor calculation on the two sets of image data to obtain a feature point set and corresponding descriptors; performing feature point matching on the two sets of image data to obtain a matching point set; Selecting M matching point pairs from the matching point set to obtain a transformation matrix from the packaging paper printed matter image data to qualified image data; The obtained transformation matrix is ​​used to transform the packaging paper printed product image so that the packaging paper printed product is spatially aligned with the qualified image data. The two aligned sets of image data are compared pixel by pixel to calculate the mean square error between the packaging paper printed product image data and the qualified image data. A reference threshold corresponding to the mean square error is set. If the mean square error between the packaging paper printed product image data and the qualified image data is less than the reference threshold, a preset value is used as the pattern defect index M2 of the packaging paper printed product image data. If the mean square error between the packaging paper printed product image data and the qualified image data is greater than the reference threshold, the difference between the mean square error and the reference threshold is calculated and recorded as the deviation degree value. The preset deviation degree value corresponds to an interval of degree values, and each group of degree value intervals corresponds to a pattern defect score of a packaging paper print; the deviation degree value of the packaging paper print is matched with the corresponding degree value interval to obtain the pattern defect score of the packaging paper print; and the obtained pattern defect score is used as the pattern defect index M2 of the packaging paper print image data.

4. The surface quality visual inspection system for packaging paper printed products according to claim 3, characterized in that: Determine the ink defect index M3 of the packaging paper printed product image data, specifically: identifying ink dot defect features and ink spot defect features from image data of a packaging paper print; Counting the total number of pixels of ink dot defect features and the total number of pixels of ink spot defect features in the packaging paper printed product image data, and converting them into ink dot feature areas and ink spot feature areas based on the resolution of the image; Set weight coefficients corresponding to the characteristic areas of ink dots and ink spots, respectively. Multiply the characteristic areas of ink dots and ink spots of the packaging paper printed image data by the corresponding weight coefficients, and then sum them to obtain the ink defect value of each image sub-region, which is recorded as Q1. Set the standard color of the printed wrapping paper, calculate the average color value of the printed wrapping paper in the Lab color space, and record it as L1, a1, and b1; extract the average color value of the standard color in the Lab color space, and record it as L2, a2, and b2; According to the formula Calculate the color difference evaluation value Q2 of the packaging paper print; Substitute the ink defect value Q1 and color difference evaluation value Q2 of the packaging paper print into the formula Perform weighted calculation to obtain the ink performance value Q3 of the packaging paper printing product; Respectively represent the maximum allowable value of ink defects and the maximum allowable value of color difference evaluation; are the influencing weight factors of ink defect value Q1 and color difference evaluation value Q2 respectively; The performance value interval corresponding to the ink performance value Q3 is preset, and each group of performance value intervals corresponds to an ink defect score of the packaging paper printed product; the ink performance value Q3 of the packaging paper printed product is matched with the corresponding performance value interval to obtain the ink defect score of the packaging paper printed product; The obtained ink defect score is used as the ink defect index M3 of the packaging paper print image data.

5. The surface quality visual inspection system for packaging paper printed products according to claim 4, characterized in that: Determine the printing quality index Ger of the packaging paper printed product image data, specifically: The physical defect index M1, pattern defect index M2 and ink defect index M3 of the packaging paper print are extracted; the weight coefficients corresponding to the physical defect index M1, pattern defect index M2 and ink defect index M3 are set respectively, the physical defect index M1, pattern defect index M2 and ink defect index M3 of the packaging paper print are multiplied by the corresponding set weight coefficients respectively, and then the sum is summed to obtain the printing quality index Ger of the packaging paper print image data.

6. The surface quality visual inspection system for packaging paper printed products according to claim 5, characterized in that: Each group of packaged printed products is classified into qualified printed products and unqualified printed products according to the set quality threshold index, specifically: The printing quality index Ger of each group of packaging paper printed products is analyzed and compared with the set quality threshold index. If the printing quality index Ger of a group of packaging paper printed products is higher than the set quality threshold index, it is classified as unqualified printed products, otherwise it is classified as qualified printed products.

Images