Printing label quality detection method and system

Abstract

The invention relates to the technical field of printing label quality, and discloses a printing label quality detection method and system, and the method comprises the steps: obtaining a first label, and building a plurality of judgment standard sets based on the first label; obtaining a second label, and performing quality judgment on the second label according to the plurality of judgment standard sets in sequence; outputting a quality judgment result of the second label, and adjusting the printing machine according to the result. According to the invention, the quality of the printed label can be automatically, quickly and accurately judged, and the detection efficiency and accuracy are greatly improved. Through a preset judgment standard set, the system can comprehensively detect the position, the shape, the color and the definition of the label, and it is ensured that each detail meets the quality requirement. In addition, the printing machine is adjusted in real time according to the detection result, generation of unqualified products is effectively avoided, the production cost is reduced, and the overall production efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of printed label quality, and in particular to a printed label quality detection method and system. Background Art

[0002] With the development of automation and intelligent technology, printed labels have been widely used in production lines. However, the quality of printed labels has always been a problem that has troubled manufacturers and consumers. The traditional method of printed label quality inspection mainly relies on manual visual inspection, which is not only inefficient but also easily affected by human factors, resulting in inaccurate test results.

[0003] Although the existing automated printed label quality inspection equipment can improve the inspection efficiency, it often has the problem of insufficient inspection accuracy or high misjudgment rate. Especially on high-speed production lines, the quality inspection requirements for printed labels are higher, and it is necessary to be able to quickly and accurately identify labels with unqualified quality so that the printing machine can be adjusted in time to avoid the production of a large number of unqualified products.

[0004] In addition, existing automated printed label quality inspection equipment is often difficult to adapt to the inspection of irregular types of labels, resulting in poor inspection results. Summary of the invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a printed label quality detection method and system, which can solve the problems of insufficient accuracy, high misjudgment rate and difficulty in adapting to irregular type label detection in printed label quality detection.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a method for detecting the quality of a printed label, comprising:

[0009] Acquire a first tag, and establish several judgment standard sets based on the first tag;

[0010] The first label is a label that has passed the quality inspection, and the plurality of judgment standard sets include a first judgment standard, a second judgment standard, a third judgment standard and a fourth judgment standard;

[0011] Acquire a second label, and perform quality judgment on the second label according to a plurality of judgment standard sets in sequence;

[0012] The second label is a quality-to-be-detected label;

[0013] The first judgment criterion is the position judgment criterion, the second judgment criterion is the four-layer shape judgment criterion, the four-layer shape includes the overall shape of the label, the shape of the background color block inside the label, the shape of the perforation inside the label, and the shape of the characters inside the label, the third judgment criterion is the color judgment criterion, and the fourth judgment criterion is the clarity judgment criterion;

[0014] Output the result of the quality judgment of the second label, and adjust the printing machine according to the result.

[0015] As a preferred solution of the printing label quality detection method described in the present invention, wherein: the first judgment criterion includes:

[0016] Obtain a first label with qualified quality, and establish a rectangular coordinate system in which the first label is on the same horizontal plane;

[0017] Establish a first comparison library, the first comparison library includes a number of comparison data sets, and each data set includes a number of first comparison point coordinates for this type of data set;

[0018] The number of comparison data sets includes an overall shape comparison data set, a background color block comparison data set, a character class comparison data set, and a perforation comparison data set;

[0019] The character class comparison data set includes a text comparison data set, a letter comparison data set, and a number class comparison data set;

[0020] Configure the second label to be measured in the same coordinate system and at the same position, and obtain the second comparison point coordinates corresponding to the first comparison points in the second label;

[0021] Perform the first position quality judgment according to the deviation values of the first comparison point coordinates and the second comparison point coordinates.

[0022] As a preferred solution of the printing label quality detection method described in the present invention, wherein: the second judgment criterion includes a parallel three-layer shape judgment criterion corresponding to the overall shape of the label, the shape of the background color block inside the label, and the shape of the perforation inside the label, and a one-layer character shape judgment criterion inside the label connected in series with the parallel three-layer shape judgment criterion;

[0023] Based on the first label with qualified quality, establish a first shape feature template for the overall shape of the label, the shape of the background color block inside the label, and the shape of the perforation inside the label, and a second shape feature template for the character shape inside the label;

[0024] Perform the first shape feature extraction on the second label to obtain the overall shape feature, background color block shape feature, and perforation shape feature of the second label;

[0025] Compare the overall shape feature, background color block shape feature, and perforation shape feature of the second label with the first shape feature template;

[0026] If the matching degree is not higher than the first shape threshold, it is determined that the quality of the overall shape or / and background color block shape or / and inner perforation shape in the second label is unqualified.

[0027] As a preferred solution of the printing label quality detection method described in the present invention, wherein: the second judgment criterion further includes:

[0028] Extract the second shape feature of the character shape of the second label with a matching degree higher than the first shape threshold to obtain the character shape feature;

[0029] Compare the character shape feature with the second shape feature template;

[0030] If the matching degree is not higher than the third shape threshold, it is determined that the quality of the character shape of the second label is unqualified;

[0031] If the matching degree is not higher than the second shape threshold and higher than the third shape threshold, first determine that the quality of the character shape of the second label is qualified, and at the same time obtain the probability of unqualified character shape quality of the second label within the target period;

[0032] If the probability is greater than the first period threshold, starting from the next period, it is determined that the quality of the character shape of the second label with a matching degree not higher than the second shape threshold and higher than the third shape threshold is unqualified;

[0033] And within this period, perform the third judgment criterion judgment on the second label with a matching degree higher than the third shape threshold;

[0034] If the probability is not greater than the first period threshold, starting from the next period, it is determined that the quality of the character shape of the second label with a matching degree not higher than the second shape threshold and higher than the third shape threshold is qualified;

[0035] And within this period, perform the third judgment criterion judgment on the second label with a matching degree higher than the third shape threshold;

[0036] Probability judgment is required for each period.

[0037] As a preferred solution of the printing label quality detection method described in the present invention, wherein: the third judgment criterion includes:

[0038] Establish a first color feature distribution map based on the first label with qualified quality, mark the maximum value, minimum value in the first color feature distribution map, and the first fitting function of the first color feature distribution map;

[0039] Extract the color features of the second label to obtain the maximum value, minimum value in the second color feature distribution map of the second label, and the second fitting function of the second color feature distribution map;

[0040] If the differences between the maximum and minimum values of the second label to be measured and the first label are both within the first color threshold, and the difference between the first fitting function and the second fitting function is a constant, then the color quality of the second label is qualified;

[0041] If the differences between the maximum and minimum values of the second label to be measured and the first label are both within the first color threshold, and the difference between the first fitting function and the second fitting function is not a constant, then the color quality of the second label is unqualified;

[0042] If any of the differences between the maximum and minimum values of the second label to be measured and the first label is not within the first color threshold, then the color quality of the second label is unqualified;

[0043] Perform the fourth judgment criterion on the second label with qualified color quality.

[0044] As a preferred solution of the printing label quality detection method of the present invention, wherein: the fourth judgment criterion includes:

[0045] If there is no bar code symbol area in the first label, the fourth judgment criterion judgment operation is not performed;

[0046] If there is a bar code symbol area in the first label, the fourth judgment criterion judgment operation is performed;

[0047] Extract the clarity of the bar code symbol area of the second label to obtain the clarity characteristic value of the bar code symbol area;

[0048] Compare the clarity characteristic value with a preset clarity threshold;

[0049] If the clarity characteristic value is not higher than the clarity threshold, it is determined that the clarity of the bar code symbol area of the second label is qualified;

[0050] If the clarity characteristic value is higher than the clarity threshold, it is determined that the clarity of the bar code symbol area of the second label is unqualified.

[0051] As a preferred solution of the printing label quality detection method of the present invention, wherein: the performing of the first position quality judgment includes:

[0052] Preset deviation value thresholds corresponding to several comparison data sets, including a first deviation threshold and a second deviation threshold;

[0053] Each comparison data set includes a corresponding first deviation threshold and a second deviation threshold, and the first deviation threshold and the second deviation threshold of each comparison data set are not required to be the same;

[0054] If the coordinate deviation threshold of the comparison points under any comparison data set is not greater than its corresponding first deviation threshold, the quality of the second label position is qualified;

[0055] If there are less than two coordinate deviation thresholds of the comparison points under any comparison data set that are greater than its corresponding first deviation threshold and less than its corresponding second deviation threshold, and the coordinate deviation thresholds of the comparison points at other positions are not greater than their corresponding first deviation thresholds, the quality of the second label position is qualified;

[0056] If there are more than two coordinate deviation thresholds of the comparison points under any comparison data set that are greater than its corresponding first deviation threshold, the quality of the second label position is unqualified;

[0057] If there is one or more coordinate deviation thresholds of the comparison points under any comparison data set that are greater than its corresponding second deviation threshold, the quality of the second label position is unqualified.

[0058] In a second aspect, the present invention provides a printing label quality detection system, including:

[0059] A judgment criterion acquisition module, configured to acquire a first label and establish a plurality of judgment criterion sets based on the first label;

[0060] The first label is a label with qualified quality detection, and the plurality of judgment criterion sets include a first judgment criterion, a second judgment criterion, a third judgment criterion, and a fourth judgment criterion;

[0061] A judgment module, configured to acquire a second label and perform quality judgment on the second label according to the plurality of judgment criterion sets in sequence;

[0062] The second label is a label to be detected for quality;

[0063] The first judgment criterion is a position judgment criterion, the second judgment criterion is a four-layer shape judgment criterion, the four-layer shape includes the overall shape of the label, the shape of the background color block inside the label, the shape of the perforation inside the label, and the shape of the characters inside the label, the third judgment criterion is a color judgment criterion, and the fourth judgment criterion is a clarity judgment criterion;

[0064] An adjustment module, configured to output the result of the quality judgment of the second label and adjust the printing press according to the result.

[0065] In a third aspect, the present invention provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the method described above are implemented.

[0066] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described above are implemented.

[0067] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention proposes a method and system for detecting the quality of printed labels, obtains a first label, and establishes a number of judgment criterion sets based on the first label; obtains a second label, and judges the quality of the second label according to the number of judgment criterion sets in sequence; outputs the result of the quality judgment of the second label, and adjusts the printing machine according to the result. The present invention can automatically, quickly and accurately judge the quality of printed labels, greatly improving the detection efficiency and accuracy. Through the preset judgment criterion sets, the system can comprehensively detect the position, shape, color and clarity of the labels to ensure that every detail meets the quality requirements. In addition, adjusting the printing machine in real time according to the detection results effectively avoids the production of unqualified products, reduces the production cost, and improves the overall production efficiency. Description of the Drawings

[0068] In order to more clearly illustrate the technical solutions of 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.

[0069] Figure 1 It is a flowchart of a method for detecting the quality of printed labels provided by an embodiment of the present invention;

[0070] Figure 2 It is a schematic diagram of the coordinate deviation of comparison points in a rectangular coordinate system in the first judgment criterion of a method for detecting the quality of printed labels provided by an embodiment of the present invention;

[0071] Figure 3 It is a comparison diagram of features obtained from the first shape feature template, the second shape feature template and the second label of a method for detecting the quality of printed labels provided by an embodiment of the present invention;

[0072] Figure 4 It is an effect diagram generated when judging according to the third judgment criterion of a method for detecting the quality of printed labels provided by an embodiment of the present invention;

[0073] Figure 5Schematic diagram of the difference in the judgment process for the barcode symbol area and the non - barcode symbol area of a printing label quality detection method provided by an embodiment of the present invention;

[0074] Figure 6 Internal structure diagram of a computer device for a printing label quality detection method provided by an embodiment of the present invention. Specific embodiments

[0075] To make the above - mentioned objects, features, and advantages of the present invention more obvious and understandable, the following will describe the specific embodiments of the present invention in detail with reference to the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0076] Embodiment 1, referring to Figures 1-6 This is the first embodiment of the present invention, which provides a printing label quality detection method, including:

[0077] Before introducing the embodiments of the present application in detail, for clarity, some related concepts are first explained.

[0078] Label quality detection: Refers to a series of inspections and tests on the printed labels to ensure that they meet the preset quality standards.

[0079] Preset judgment criterion set: Refers to a series of judgment criteria preset according to the characteristics of qualified labels before label quality detection. These criteria are used to guide the quality detection process to ensure the accuracy and consistency of the detection results.

[0080] In the existing related technologies, there are some problems, such as insufficient precision, a relatively high misjudgment rate, especially poor detection effects for irregular - type labels. These problems not only affect production efficiency but also increase the risk of non - conforming products, thereby increasing production costs.

[0081] The present application provides a method that can effectively solve the above - mentioned problems. Next, multiple embodiments will be combined to elaborate in detail how to implement this printing label quality detection method;

[0082] Figure 1 Shows a printing label quality detection method, including:

[0083] S101, obtain a first label and establish a number of judgment criterion sets based on the first label;

[0084] It should be noted that the first label is the initial control label, which is the standard label for judgment, and its quality has been strictly inspected and confirmed to be qualified. Establishing a judgment standard set based on the first label is to provide a comparison benchmark for subsequent quality inspection of the second label (i.e., the label to be detected).

[0085] In an optional embodiment, the first label can be various types of labels, such as household appliance labels, electronic labels, industrial labels, logistics labels, medical labels, variable data, RFID labels, etc. These labels usually have specific features such as shapes, colors, characters, and barcode symbol areas, and these features will be used to establish the judgment standard set.

[0086] It should be noted that the direction emphasized in this application is irregular labels, but it does not mean that this application cannot be applied to other regular labels.

[0087] In the embodiment of this application, the first label is a consumer type label, such as food labels, condiment labels, wine labels, water labels, daily chemical labels, family planning labels, milk powder labels, clothing labels, etc.

[0088] In the embodiment of this application, the first label is a label with qualified quality inspection, and several judgment standard sets include the first judgment standard, the second judgment standard, the third judgment standard, and the fourth judgment standard.

[0089] In the embodiment of this application, the first judgment standard is the position judgment standard, the second judgment standard is the four-layer shape judgment standard, and the four-layer shape includes the overall shape of the label, the shape of the background color block inside the label, the shape of the perforation inside the label, and the shape of the characters inside the label. The third judgment standard is the color judgment standard, and the fourth judgment standard is the clarity judgment standard.

[0090] In an optional embodiment, after the several judgment standard sets of the first label are established, they can be stored and called by integrating them into a fixed model or forming a fixed judgment network, so as to be quickly obtained and used when subsequent quality inspection of the second label is carried out.

[0091] In an optional embodiment, when establishing the judgment standard set, machine learning algorithms can be used to learn the features of the first label, so as to generate judgment standards that can accurately reflect the features of the first label. These judgment standards will be used as the basis for subsequent quality inspection to ensure the accuracy and consistency of the inspection results.

[0092] In an optional embodiment, a neural network can also be used to continuously optimize and update the judgment standard set to meet the quality inspection requirements of different types and specifications of labels. The neural network can automatically extract the features of the label through training and learning, and generate corresponding judgment standards, thereby improving the inspection efficiency and accuracy.

[0093] It should be noted that the present application does not limit the establishment of models and networks. The present application pays more attention to the protection of the underlying logic.

[0094] It should also be noted that obtaining the first label and establishing a number of judgment criterion sets based on the first label can provide an accurate and comprehensive benchmark for subsequent quality inspection of the second label. By establishing judgment criterion sets covering multiple aspects such as position, four-layer shape, color, and clarity, a comprehensive evaluation of the label quality can be ensured, thereby improving the accuracy and reliability of the inspection. In addition, these judgment criterion sets can be flexibly adjusted and optimized according to actual needs to adapt to the quality inspection requirements of different types and specifications of labels, further enhancing the applicability and flexibility of the system.

[0095] S102, obtain the second label, and perform quality judgment on the second label according to a number of judgment criterion sets in sequence;

[0096] In the embodiment of the present application, the second label is a label whose quality is to be detected.

[0097] It should be noted that the type and kind of the second label must be the same as those of the first label. Since the judgment criteria established in the previous steps are for the labels of the type of the first label, when performing the quality inspection of the second label, it is necessary to ensure that the second label is consistent with the first label in terms of type and kind, so as to ensure the accuracy of the judgment.

[0098] It should also be noted that after obtaining the second label, the system will sequentially use each judgment criterion in the judgment criterion set to perform quality inspection on the second label according to the preset order. This process is automated, greatly improving the inspection efficiency and reducing the errors caused by human factors at the same time.

[0099] It should also be noted that there are various existing technologies for the judgment of labels, and these existing technologies often do not make in-depth and accurate judgments. The printing label quality inspection system provided by the present invention can make detailed and accurate judgments on multiple key features of the label.

[0100] In the embodiment of the present application, the first judgment criterion includes:

[0101] Obtain a first label with qualified quality, and establish a rectangular coordinate system in which the first label is on the same horizontal plane;

[0102] Establish a first comparison library. The first comparison library includes a number of comparison data sets, and each data set includes a number of first comparison point coordinates for this type of data set;

[0103] The number of comparison data sets includes an overall shape comparison data set, a background color block comparison data set, a character class comparison data set, and a perforation comparison data set;

[0104] The character class comparison dataset includes a text comparison dataset, an alphabet comparison dataset, and a numeric comparison dataset;

[0105] Configure the second tag to be measured in the same coordinate system and at the same position, and obtain the coordinates of the second comparison point corresponding to the first comparison point in the second tag;

[0106] Perform the first position quality judgment based on the deviation value between the first comparison point coordinates and the second comparison point coordinates.

[0107] It should be noted that generally, an arbitrary vertex of the first tag is used as the origin of the rectangular coordinate system, or the line segment where the axis of symmetry is located is used as the horizontal and vertical coordinate axes to establish the rectangular coordinate system.

[0108] It should be noted that the accuracy of the rectangular coordinate system is the target accuracy, and the target accuracy is adjusted according to the user's requirements. If the user requires high accuracy, the accuracy is increased; if the user requires low accuracy, the accuracy is decreased. For example, if the user requires high accuracy, the accuracy of the rectangular coordinate system can be set to 0.08 mm; if the user requires low accuracy, the accuracy of the rectangular coordinate system can be set to 0.2 mm. Generally, the accuracy range is between 0.01 mm and 1 mm.

[0109] It should be noted that the first comparison point coordinates and the second comparison point are obtained by converting the image into a digital signal. After establishing the rectangular coordinate system, the printed label image to be detected is obtained through an image acquisition device, the image is converted into a digital signal, and positioned in the rectangular coordinate system to obtain the coordinate information of each feature point on the label.

[0110] It should be noted that the comparison point coordinates for several such datasets generally include more than four coordinate points, and generally the vertex position coordinates are selected, which is more convenient for recognition. In this application, considering the accuracy, recognition rate, and subsequent integration into various machine learning or deep learning requirements, the comparison point coordinates in the overall shape comparison dataset are set to 4 - 6, the comparison point coordinates in the background color block comparison dataset are set to 4 - 6, the comparison point coordinates in the perforation comparison dataset are set to 3, namely the center of the circle and any two points on the circumference, the comparison point coordinates in the text comparison dataset are set to 3 - 6, the comparison point coordinates in the alphabet comparison dataset are set to 3 - 4, and the comparison point coordinates in the numeric comparison dataset are set to 2 - 3. These quantities have been determined when establishing several judgment standard sets, as Figure 2 shown, the red solid dots in the figure are the comparison points. The red solid dots in the figure are larger only for easy understanding and display, and they are not actually that large.

[0111] In an alternative embodiment, the first position quality judgment may include the following:

[0112] Preset deviation value thresholds corresponding to several comparison data sets, including a first deviation threshold and a second deviation threshold;

[0113] Each comparison data set includes a corresponding first deviation threshold and a second deviation threshold, and the first deviation threshold and the second deviation threshold of each comparison data set are not required to be the same;

[0114] If the coordinate deviation threshold of the comparison points under any comparison data set is not greater than its corresponding first deviation threshold, the quality of the second label position is qualified;

[0115] If there are less than two coordinate deviation thresholds of the comparison points under any comparison data set that are greater than its corresponding first deviation threshold and less than its corresponding second deviation threshold, and the coordinate deviation thresholds of the comparison points in other positions are not greater than their corresponding first deviation thresholds, the quality of the second label position is qualified;

[0116] If there are more than two coordinate deviation thresholds of the comparison points under any comparison data set that are greater than its corresponding first deviation threshold, the quality of the second label position is unqualified;

[0117] If there is one or more coordinate deviation thresholds of the comparison points under any comparison data set that are greater than its corresponding second deviation threshold, the quality of the second label position is unqualified.

[0118] In the embodiments of the present application, the corresponding first deviation threshold and second deviation threshold of each comparison data set are obtained through statistical analysis of actual detection data and historical qualified data to maximize the detection accuracy. After the position judgment criterion is completed, enter the second judgment criterion, that is, the four-layer shape judgment.

[0119] In an optional embodiment, the specific steps obtained through statistical analysis of actual detection data and historical qualified data can be as follows:

[0120] Obtain historical qualified data and unqualified data, and use the historical qualified data and unqualified data as sample data sets;

[0121] Furthermore, input the sample data set into a machine learning model for training to obtain a trained machine learning model;

[0122] Furthermore, input the data to be measured into the trained machine learning model to output the predicted deviation value threshold;

[0123] Furthermore, according to the actual detection results, continuously adjust the parameters of the machine learning model until the predicted deviation value threshold is consistent with the actual detection results, and obtain the final first deviation threshold and second deviation threshold.

[0124] In the embodiment of the present application, since the selected precision is 0.1 mm, the first deviation threshold and the second deviation threshold are specifically set to 0.01 mm and 0.02 mm.

[0125] It should be noted that by learning historical data through a machine learning model, key factors affecting the quality of label positions can be automatically extracted, and corresponding deviation value thresholds can be generated. This method is more accurate and reliable than the traditional manual threshold setting and can adapt to the label quality detection requirements of different types and specifications.

[0126] It should also be noted that the machine learning model includes but is not limited to support vector machine (SVM), decision tree, random forest, gradient boosting decision tree (GBDT), neural network, etc. These models can be selected and optimized according to actual needs to improve the detection efficiency and accuracy.

[0127] After obtaining the first deviation threshold and the second deviation threshold, the position quality judgment can be carried out. If the position quality of the second label is qualified, it enters the next judgment criterion, that is, the four-layer shape judgment. If it is unqualified, an unqualified result is output, and the printing machine is adjusted according to the result to avoid the same problem for subsequent labels.

[0128] It should be noted that in addition to using the above coordinate comparison method, the first judgment criterion can also use the distance comparison method, specifically as follows:

[0129] Obtain the distance between every two first comparison points according to the coordinates of the first comparison points;

[0130] Obtain the distance between every two second comparison points corresponding to the second label to be measured;

[0131] Set the distance difference threshold according to the precision requirement;

[0132] Judge the relationship between the difference between the distance between every two first comparison points and the distance between every two second comparison points corresponding to the second label and the distance difference threshold.

[0133] However, the above distance calculation amount is large and cannot be judged in real time, so the coordinate comparison method is preferably used.

[0134] It should be noted that the first judgment criterion mainly conducts quality detection on the position of the label to ensure that there are no problems such as position deviation or misalignment during the printing process. This is the basis of label quality detection and also a prerequisite for the subsequent judgment criterion to be accurately carried out.

[0135] In the embodiment of the present application, the second judgment criterion includes a three-layer shape judgment criterion corresponding to the overall shape of the label, the shape of the background color block inside the label, and the shape of the perforation inside the label in parallel, and a one-layer label inner character shape judgment criterion in series with the three-layer shape judgment criterion in parallel;

[0136] Establish a first shape feature template for the overall shape of the label, the shape of the background color block inside the label, and the shape of the perforation inside the label based on the first label with qualified quality, as well as a second shape feature template for the character shape inside the label;

[0137] Perform first shape feature extraction on the second label to obtain the overall shape feature, background color block shape feature, and perforation shape feature of the second label;

[0138] Compare the overall shape feature, background color block shape feature, and perforation shape feature of the second label with the first shape feature template;

[0139] If the matching degree is not higher than the first shape threshold, it is determined that the quality of the overall shape or / and background color block shape or / and inner perforation shape in the second label is unqualified.

[0140] In the embodiment of the present application, the second judgment criterion further includes:

[0141] Perform second shape feature extraction on the character shape of the second label with a matching degree higher than the first shape threshold to obtain the character shape feature;

[0142] Compare the character shape feature with the second shape feature template;

[0143] If the matching degree is not higher than the third shape threshold, it is determined that the quality of the character shape of the second label is unqualified;

[0144] If the matching degree is not higher than the second shape threshold and higher than the third shape threshold, first recognize that the quality of the character shape of the second label is qualified, and at the same time obtain the probability of the unqualified quality of the character shape of the second label within the target period;

[0145] If the probability is greater than the first period threshold, starting from the next period, it is recognized that the quality of the character shape of the second label with a matching degree not higher than the second shape threshold and higher than the third shape threshold is unqualified;

[0146] And perform the third judgment criterion judgment on the second label with a matching degree higher than the third shape threshold within this period;

[0147] If the probability is not greater than the first period threshold, starting from the next period, it is recognized that the quality of the character shape of the second label with a matching degree not higher than the second shape threshold and higher than the third shape threshold is qualified;

[0148] And perform the third judgment criterion judgment on the second label with a matching degree higher than the third shape threshold within this period;

[0149] Probability judgment needs to be performed in each period.

[0150] It should be noted that the first shape feature template is a template that aggregates key feature information such as the overall shape of the first label, the shape of the background color block, and the shape of the perforation, and is used to compare with the corresponding features of the second label. The second shape feature template is a more refined template specifically established for the character shape to ensure the accuracy of the character shape. Specifically, the first shape feature template includes the contour feature of the overall shape, the area feature of the background color block, and the contour feature information of the perforation. The second shape feature template includes the contour feature of the character, the font feature, and the character spacing and other feature information. These feature information are obtained by extracting and learning the features of the first label through deep learning algorithms, which can accurately reflect the key features of the label shape and provide strong support for subsequent label quality detection.

[0151] In the embodiment of the present application, as Figure 3 shown, the specific structures of the first shape feature template and the second shape feature template are shown, and the real template is not used, and the template is not clear in the text.

[0152] It should be noted that the first shape threshold, the second shape threshold, and the third shape threshold are determined by the shape coincidence degree. The higher the coincidence degree, the more the shape of the second label matches the first shape feature template, and the higher the quality.

[0153] In the embodiment of the present application, the first shape threshold is set to 99.5%, the second shape threshold is set to 99.5%, and the third shape threshold is set to 98.9%. The setting of these thresholds is based on the statistical analysis of historical data and the comprehensive consideration of label quality requirements to ensure the accuracy and reliability of detection.

[0154] It should be noted that the target period is a time period preset by the system and is used to count the probability that the character shape quality of the second label is unqualified. At the end of each target period, the system will automatically calculate the probability that the character shape quality of the second label is unqualified during this period and adjust the character shape quality judgment standard for the next period according to the probability value. This method can realize the dynamic monitoring and optimization of label quality and improve the accuracy and efficiency of detection. Generally, the target period is set to 1 hour or one day, and in this application, it is set to 3 hours.

[0155] It should also be noted that the threshold for the first cycle is set at 0.5%, which is determined comprehensively based on historical data and actual requirements. If the probability of unqualified character shape quality in a certain cycle exceeds 0.5%, it is considered that there are fluctuations in the character shape quality in that cycle, and the judgment criteria need to be improved to ensure the quality of subsequent labels. This method of dynamically adjusting the judgment criteria can flexibly respond according to the actual production situation, improving the overall detection efficiency and accuracy. After the shape judgment is completed, if the shape quality of the second label is qualified, it enters the next judgment criteria. If it is unqualified, an unqualified result is output, and the printing machine or relevant process parameters are adjusted according to the result to avoid the same problems in subsequent labels.

[0156] In this application, the extraction of the first shape feature and the second shape feature of the second label are both the same operations as the extraction of the first shape feature template and the second shape feature template;

[0157] In an optional embodiment, specifically, the shape coincidence degree can be determined by extracting the areas of each part. For example, the area of the overall shape, the area of the background color block, and the area of the perforation are extracted, etc., and then compared with the corresponding areas in the first shape feature template to determine the shape coincidence degree. This method of area comparison is simple and intuitive, and can quickly and effectively judge whether the label shape is qualified.

[0158] The extraction method adopted in this application is to quickly judge the overall shape and the perforation shape by extracting the lines and the coincidence degree of the lines, and the rest are determined by extracting the area.

[0159] It should be noted that the second judgment criteria can comprehensively detect the overall shape, the background color block shape, the perforation shape, and the character shape of the label to ensure that the shape quality of the label meets the preset standards. This detection method not only improves the detection accuracy but also effectively avoids label quality problems caused by unqualified shapes. In addition, by setting different shape thresholds and dynamically adjusting the judgment criteria, the method of this application can adapt to the label quality detection requirements of different types and specifications, and has a wide range of application prospects.

[0160] In the embodiment of this application, the third judgment criteria include:

[0161] Establish a first color feature distribution map based on the first label with qualified quality, mark the maximum value, the minimum value in the first color feature distribution map, and the first fitting function of the first color feature distribution map;

[0162] Extract the color features of the second label to obtain the maximum value, the minimum value in the second color feature distribution map of the second label, and the second fitting function of the second color feature distribution map;

[0163] If the differences between the second label to be measured and the maximum and minimum values of the first label are both within the first color threshold, and the difference between the first fitting function and the second fitting function is a constant, then the color quality of the second label is qualified;

[0164] If the differences between the second label to be measured and the maximum and minimum values of the first label are both within the first color threshold, and the difference between the first fitting function and the second fitting function is not a constant, then the color quality of the second label is unqualified;

[0165] If any one of the differences between the second label to be measured and the maximum and minimum values of the first label is not within the first color threshold, then the color quality of the second label is unqualified;

[0166] Judge the second label with qualified color quality according to the fourth judgment criterion.

[0167] It should be noted that as Figure 4 shown is the effect diagram generated when making the third judgment criterion judgment, which can be intuitively seen or easily recognized by the machine. The first color feature distribution diagram is drawn based on the color features of the first label, which reflects the overall distribution and change trend of the label color. By establishing the first color feature distribution diagram, the maximum value, minimum value and overall distribution of the label color can be clearly seen, providing a basis for subsequent color quality judgment. At the same time, the first fitting function is a fitting of the first color feature distribution diagram, which describes the change law of the color distribution. When judging the color quality of the second label, by comparing the differences between the second color feature distribution diagram of the second label and the first color feature distribution diagram, including the differences in the maximum and minimum values and the differences in the fitting functions, the color quality of the second label can be accurately judged whether it is qualified. If the color quality of the second label is qualified, then enter the next judgment criterion, that is, the fourth judgment criterion. If unqualified, an unqualified result is output, and the printing machine or relevant process parameters are adjusted according to the result to avoid color quality problems in subsequent labels.

[0168] In the embodiment of the present application, the first color threshold is set based on the statistical analysis of historical data and the comprehensive consideration of the label color quality requirements to ensure the accuracy and reliability of the detection. This method of color feature extraction and comparison can not only quickly and effectively judge the color quality of the label, but also adapt to the label quality detection requirements of different types and specifications, and has a wide application prospect. After completing the color judgment, if the color quality of the second label is qualified, then enter the next judgment criterion, that is, the fourth judgment criterion. If unqualified, an unqualified result is also output, and corresponding adjustments are made according to the result. In the present application, the first color threshold is set to one two-thousandth of the maximum and minimum values corresponding to the first label.

[0169] In the embodiment of the present application, the fourth judgment criterion includes:

[0170] If there is no bar code symbol area in the first label, the fourth judgment criterion judgment operation is not performed;

[0171] If there is a bar code symbol area in the first label, the fourth judgment criterion judgment operation is performed;

[0172] Extract the clarity of the bar code symbol area of the second label to obtain the clarity characteristic value of the bar code symbol area;

[0173] Compare the clarity characteristic value with a preset clarity threshold;

[0174] If the clarity characteristic value is not higher than the clarity threshold, it is determined that the clarity of the bar code symbol area of the second label is qualified;

[0175] If the clarity characteristic value is higher than the clarity threshold, it is determined that the clarity of the bar code symbol area of the second label is unqualified. As Figure 5 shown, it is a schematic diagram of the difference in the judgment process for the presence and absence of a bar code symbol area.

[0176] It should be noted that when extracting the clarity of the bar code symbol area of the second label to obtain the clarity characteristic value of the bar code symbol area, the specific clarity is represented by randomly selecting the number of pixels within a fixed shape. The more the number of pixels, the higher the clarity of the bar code symbol area. The clarity calculation is achieved by establishing a correspondence table between the number of pixels in the fixed area and the clarity, and the correspondence table can be established according to actual needs, which is not limited in this application.

[0177] In the embodiments of the present application, the preset clarity threshold is set based on the comprehensive consideration of the statistical analysis of historical data and the requirements for the clarity of the bar code symbol area. This setting method ensures the accuracy and reliability of the detection. When judging the clarity of the bar code symbol area, if the clarity of the bar code symbol area of the second label is qualified, the entire label quality inspection process ends and a qualified result is output. If it is unqualified, an unqualified result is output, and the printing machine or relevant process parameters are adjusted according to the result to avoid problems with the clarity of the bar code symbol area in subsequent labels. This method for judging the clarity of the bar code symbol area not only improves the accuracy of the detection but also effectively avoids label quality problems caused by unqualified clarity of the bar code symbol area.

[0178] In addition, by setting a clarity threshold, the method of the present application can adapt to the label quality inspection requirements of different types and specifications and has a wide range of application prospects.

[0179] It should be noted that obtaining the second label and judging the quality of the second label according to a number of judgment criterion sets in sequence can comprehensively and accurately evaluate the quality of the label, ensuring that each label meets the preset standards. First, detecting the position of the label through the first judgment criterion can effectively avoid problems such as position deviation or misalignment of the label during the printing process, which is the basis for label quality detection. Second, the second judgment criterion comprehensively detects the overall shape of the label, the shape of the background color block, the shape of the perforation, and the shape of the characters to ensure that the shape quality of the label meets the preset standards and avoid label quality problems caused by unqualified shapes. Third, the third judgment criterion can accurately judge whether the color quality of the label is qualified by comparing the color feature distribution map of the label, improving the accuracy and efficiency of color detection. Finally, the fourth judgment criterion performs clarity detection on the label with a bar code symbol area to ensure the readability of the bar code symbol area and avoid label quality problems caused by unqualified clarity of the bar code symbol area. This multi-criterion detection method carried out in sequence not only improves the accuracy and efficiency of detection, but also can adapt to the label quality detection requirements of different types and specifications, providing strong support for the comprehensive guarantee of label quality.

[0180] S103. Output the result of the quality judgment of the second label and adjust the printing machine according to the result.

[0181] It should be noted that each unqualified condition corresponds to different operations for adjusting the printing machine to ensure that the quality of the subsequent printed labels meets the requirements. For example, if the position quality is unqualified, it may be necessary to adjust the positioning device of the printing machine; if the shape quality is unqualified, it may be necessary to adjust the printing die or cutting device; if the color quality is unqualified, it may be necessary to adjust the ink formula or printing pressure; if the clarity of the bar code symbol area is unqualified, it may be necessary to adjust the bar code printing parameters or clean the bar code printing head. This targeted adjustment method can quickly locate the source of the problem and improve the adjustment efficiency and accuracy. In addition, the embodiments of the present application can also record each quality detection result and adjustment operation to form a quality database. By analyzing and mining the quality database, potential problems and improvement points in the printing process can be further discovered, providing more scientific guidance and support for subsequent printing production.

[0182] In an optional embodiment, several judgment criterion sets of the first label can be trained into a quality detection model. The second label to be detected is input into the quality detection model, and the quality judgment result and corresponding adjustment suggestions are directly output. The adjustment suggestions include adjusting the printing parameters of the printing press, replacing the printing components of the printing press, and resetting the judgment criterion set for quality detection. The quality detection model is a machine learning model or a deep learning model. The machine learning model includes a decision tree model, a support vector machine model, a K-nearest neighbor model, and a naive Bayes model. The deep learning model includes a convolutional neural network model, a recurrent neural network model, and a generative adversarial network model. By continuously inputting qualified first labels and the second labels to be detected to train the quality detection model, the judgment accuracy of the quality detection model is improved.

[0183] In summary, the present invention proposes a method for detecting the quality of printed labels, which includes obtaining a first label and establishing several judgment criterion sets based on the first label; obtaining a second label and performing quality judgment on the second label according to the several judgment criterion sets in sequence; outputting the result of the quality judgment of the second label and adjusting the printing press according to the result. The present invention can automatically, quickly, and accurately judge the quality of printed labels, greatly improving the detection efficiency and accuracy. Through the preset judgment criterion sets, the system can comprehensively detect the position, shape, color, and clarity of the labels to ensure that every detail meets the quality requirements. In addition, by adjusting the printing press in real time according to the detection results, the generation of unqualified products is effectively avoided, the production cost is reduced, and the overall production efficiency is improved.

[0184] Embodiment 3, in this embodiment, a system for detecting the quality of printed labels is further provided, including:

[0185] A judgment criterion acquisition module, configured to obtain a first label and establish several judgment criterion sets based on the first label;

[0186] The first label is a label with qualified quality detection. The several judgment criterion sets include a first judgment criterion, a second judgment criterion, a third judgment criterion, and a fourth judgment criterion;

[0187] A judgment module, configured to obtain a second label and perform quality judgment on the second label according to the several judgment criterion sets in sequence;

[0188] The second label is a label to be detected for quality;

[0189] The first judgment criterion is a position judgment criterion, the second judgment criterion is a four-layer shape judgment criterion. The four-layer shape includes the overall shape of the label, the shape of the background color block inside the label, the shape of the perforation inside the label, and the shape of the characters inside the label. The third judgment criterion is a color judgment criterion, and the fourth judgment criterion is a clarity judgment criterion;

[0190] An adjustment module is used to output the result of the quality judgment of the second label and adjust the printing press according to the result.

[0191] Each of the above unit modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0192] This embodiment also provides a computer device, which can be a terminal, and its internal structure diagram can be as Figure 6 shown. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it realizes a method for detecting the quality of printed labels. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad set on the shell of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0193] This embodiment also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by the processor, the following steps are realized:

[0194] Obtain a first label and establish a number of judgment criterion sets based on the first label;

[0195] The first label is a label with qualified quality inspection. The number of judgment criterion sets includes a first judgment criterion, a second judgment criterion, a third judgment criterion, and a fourth judgment criterion;

[0196] Obtain a second label and perform quality judgment on the second label according to the number of judgment criterion sets in sequence;

[0197] The second label is a label to be inspected for quality;

[0198] The first judgment criterion is a position judgment criterion, the second judgment criterion is a four-layer shape judgment criterion, the four-layer shape includes the overall shape of the label, the shape of the background color block inside the label, the shape of the perforation inside the label, and the shape of the characters inside the label. The third judgment criterion is a color judgment criterion, and the fourth judgment criterion is a clarity judgment criterion;

[0199] Output the result of the quality judgment of the second label, and adjust the printing press according to the result.

[0200] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

[0201] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an all-hardware embodiment, an all-software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present application can be implemented in various computer languages.

[0202] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0203] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0204] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide for implementing the functions specified in Figure 1 one or more flows and / or blocksFigure 1 Steps of the functions specified in one or more boxes.

[0205] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0206] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A method for detecting the quality of printed labels, characterized in that: include: Acquire a first tag, and establish several judgment standard sets based on the first tag; The first label is a label that has passed the quality inspection, and the plurality of judgment standard sets include a first judgment standard, a second judgment standard, a third judgment standard and a fourth judgment standard; Acquire a second label, and perform quality judgment on the second label according to a plurality of judgment standard sets in sequence; The second label is a quality-to-be-detected label; The first judgment standard is a position judgment standard, the second judgment standard is a four-layer shape judgment standard, the four-layer shape includes the overall shape of the label, the shape of the background color block in the label, the shape of the perforation in the label and the shape of the characters in the label, the third judgment standard is a color judgment standard, and the fourth judgment standard is a clarity judgment standard; The result of the quality judgment of the second label is outputted, and the printing press is adjusted according to the result.

2. The printed label quality inspection method according to claim 1, characterized in that: The first judgment criteria include: Acquire a first label of qualified quality, and establish a rectangular coordinate system in which the first label is on the same horizontal plane; Establishing a first comparison library, wherein the first comparison library includes a plurality of comparison data sets, each data set includes a plurality of first comparison point coordinates for the data set; The several comparison data sets include an overall shape comparison data set, a background color block comparison data set, a character comparison data set, and a perforation comparison data set; The character comparison dataset includes a text comparison dataset, a letter comparison dataset and a number comparison dataset; Arrange the second tag to be tested in the same coordinate system and the same position, and obtain the coordinates of the second comparison point in the second tag corresponding to the first comparison point; A first position quality judgment is performed according to a deviation value between the first comparison point coordinates and the second comparison point coordinates.

3. The printed label quality inspection method according to claim 2, characterized in that: The second judgment standard includes three layers of shape judgment standards in parallel corresponding to the overall shape of the label, the shape of the background color block in the label, and the shape of the perforation in the label, and one layer of shape judgment standards for characters in the label connected in series with the three layers of shape judgment standards in parallel; Based on the first label of qualified quality, a first shape feature template for the overall shape of the label, the shape of the background color block in the label, and the shape of the perforation in the label is established, as well as a second shape feature template for the character shape in the label; Performing a first shape feature extraction on the second label to obtain an overall shape feature, a background color block shape feature, and a perforation shape feature of the second label; comparing the overall shape feature, the background color block shape feature and the perforation shape feature of the second label with the first shape feature template; If the matching degree is not higher than the first shape threshold, it is determined that the overall shape and / or the background color block shape and / or the inner perforation shape in the second label are of unqualified quality.

4. The printed label quality inspection method according to claim 3, characterized in that: The second judgment criterion also includes: Performing second shape feature extraction on the character shape of the second label whose matching degree is higher than the first shape threshold to obtain the character shape feature; comparing the character shape feature with the second shape feature template; If the matching degree is not higher than the third shape threshold, the character shape quality of the second label is determined to be unqualified; If the matching degree is not higher than the second shape threshold and higher than the third shape threshold, the character shape quality of the second label is first determined to be qualified, and the probability of the character shape quality of the second label being unqualified within the target period is obtained; If the probability is greater than the first cycle threshold, the character shape quality of the second label whose matching degree is not higher than the second shape threshold and higher than the third shape threshold is considered unqualified starting from the next cycle; And within the period, the second tag whose matching degree is higher than the third shape threshold is judged by the third judgment standard; If the probability is not greater than the first cycle threshold, then starting from the next cycle, the character shape quality of the second label whose matching degree is not higher than the second shape threshold and higher than the third shape threshold is determined to be qualified; And within the period, the second tag whose matching degree is higher than the third shape threshold is judged by the third judgment standard; Probability judgment is required in each cycle.

5. The printed label quality inspection method according to claim 4, characterized in that: The third judgment criterion includes: Establishing a first color feature distribution map based on the first label of qualified quality, marking the maximum value, the minimum value and the first fitting function of the first color feature distribution map in the first color feature distribution map; Performing color feature extraction on the second label to obtain a maximum value, a minimum value in a second color feature distribution map of the second label, and a second fitting function of the second color feature distribution map; If the difference between the maximum value and the minimum value of the second label to be tested and the first label is within the first color threshold, and the difference between the first fitting function and the second fitting function is a constant, the color quality of the second label is qualified; If the difference between the maximum value and the minimum value of the second label to be tested and the first label is within the first color threshold, and the difference between the first fitting function and the second fitting function is not a constant, the color quality of the second label is unqualified; If any of the differences between the maximum value and the minimum value of the second label to be tested and the first label is not within the first color threshold, the color quality of the second label is unqualified; The second label with qualified color quality is judged by the fourth judgment standard.

6. The printed label quality inspection method according to claim 5, characterized in that: The fourth judgment criterion includes: If the barcode symbol area does not exist in the first label, the fourth judgment standard judgment operation is not performed; If the barcode symbol area exists in the first label, a fourth judgment standard judgment operation is performed; Performing barcode symbol area clarity extraction on the second label to obtain a clarity feature value of the barcode symbol area; Comparing the clarity feature value with a preset clarity threshold; If the clarity characteristic value is not higher than the clarity threshold, it is determined that the clarity of the barcode symbol area of ​​the second label is qualified; If the clarity characteristic value is higher than the clarity threshold, it is determined that the clarity of the barcode symbol area of ​​the second label is unqualified.

7. The printed label quality inspection method according to claim 6, characterized in that: The first position quality judgment comprises: Presetting several deviation value thresholds corresponding to the comparison data sets, including a first deviation threshold and a second deviation threshold; Each comparison data set includes a corresponding first deviation threshold and a second deviation threshold, and the first deviation threshold and the second deviation threshold of each comparison data set are not required to be the same; If the comparison point coordinate deviation threshold under any comparison data set is not greater than its corresponding first deviation threshold, the second tag position quality is qualified; If there are two or more comparison point coordinate deviation thresholds under any comparison data set that are greater than their corresponding first deviation thresholds and less than their corresponding second deviation thresholds, and the comparison point coordinate deviation thresholds at other positions are not greater than their corresponding first deviation thresholds, then the second tag position quality is qualified; If there are more than two comparison point coordinate deviation thresholds under any comparison data set that are greater than their corresponding first deviation thresholds, the second tag position quality is unqualified; If one or more of the comparison point coordinate deviation thresholds under any comparison data set is greater than its corresponding second deviation threshold, the second tag position quality is unqualified.

8. A printed label quality inspection system, using the method according to any one of claims 1 to 7, characterized in that: include: A judgment criterion acquisition module, used to acquire a first label and establish a plurality of judgment criterion sets based on the first label; The first label is a label that has passed the quality inspection, and the plurality of judgment standard sets include a first judgment standard, a second judgment standard, a third judgment standard and a fourth judgment standard; A judgment module, used for obtaining a second label and performing quality judgment on the second label according to a plurality of judgment standard sets in sequence; The second label is a quality-to-be-detected label; The first judgment standard is a position judgment standard, the second judgment standard is a four-layer shape judgment standard, the four-layer shape includes the overall shape of the label, the shape of the background color block in the label, the shape of the perforation in the label and the shape of the characters in the label, the third judgment standard is a color judgment standard, and the fourth judgment standard is a clarity judgment standard; The adjustment module is used to output the quality judgment result of the second label and adjust the printing machine according to the result.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images