Label printing defect on-line visual identification detection device

Abstract

The invention belongs to the field of printing defect identification, relates to a data analysis technology, and particularly relates to an online visual identification and detection device for label printing defects, which is used for solving the problem that defects except displacement defects cannot be identified and processed in the prior art. Comprising a printing defect recognition and analysis module, a batch quality analysis module, an optimization feedback processing module and a database, the printing defect recognition and analysis module, the batch quality analysis module and the optimization feedback processing module are sequentially in communication connection, and the database is in communication connection with the printing defect recognition and analysis module and the batch quality analysis module; according to the method, the printing offset degree, the printing color deviation degree, the surface reflectance and other parameters of the analysis object can be sequentially analyzed and comprehensively processed in combination with the processes of image processing, reflected light testing and the like to obtain the defect coefficient, and the overall printing quality of the analysis object is fed back through the defect coefficient; and data support is provided for overall quality analysis of the whole batch.

Description

Technical Field

[0001] The invention belongs to the field of printing defect recognition and relates to data analysis technology, and specifically is an online visual recognition and detection device for label printing defects. Background Art

[0002] Label printing is a process that uses paper, film, metal and other materials as the base material, and uses a printing press to print ink, coating and other printing media on the base material. Label printing is widely used in commerce, industry and daily life, and has a variety of application scenarios and advantages.

[0003] The invention patent with publication number CN115330761A discloses a method for identifying surface printing shift defects of electronic products. The defect identification method solves the technical problem of low accuracy in identifying surface printing shift defects of electronic products by performing image processing on the surface printing image, thereby improving the accuracy of identifying surface printing shift defects of electronic products. The method is mainly used for identifying surface printing shift defects of electronic products. However, the method can only identify shift defects, but cannot identify and process other defects of label printing, nor can it optimize and analyze the production end of label printing based on the identification results, resulting in the inability to guarantee the production quality of label printing.

[0004] In view of the above technical problems, this application proposes a solution. Summary of the invention

[0005] The purpose of the present invention is to provide an online visual recognition and detection device for label printing defects, which is used to solve the problem that the prior art cannot recognize and process defects other than displacement defects;

[0006] The technical problem to be solved by the present invention is: how to provide an online visual recognition and detection device for label printing defects that can identify and process defects other than displacement defects.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] An online visual recognition and detection device for label printing defects comprises a printing defect recognition and analysis module, a batch quality analysis module, an optimization feedback processing module and a database, wherein the printing defect recognition and analysis module, the batch quality analysis module and the optimization feedback processing module are sequentially connected in communication, and the database is connected in communication with the printing defect recognition and analysis module and the batch quality analysis module;

[0009] The printing defect recognition and analysis module is used to recognize and analyze label printing defects: the label to be analyzed is marked as an analysis object, image processing and reflected light test are performed on the analysis object to obtain a printing offset value YP, a printing color difference value YS and a reflection deviation value FP respectively; the defect coefficient QX of the analysis object is obtained by numerically calculating the printing offset value YP, the printing color difference value YS and the reflection deviation value FP; the analysis object is marked as a qualified object or a defective object according to the defect coefficient QX;

[0010] The batch quality analysis module is used to comprehensively analyze the results of defect recognition of label printing of the same batch: generate an analysis cycle, obtain the quality coefficient ZL of defect recognition of the label batch within the analysis cycle; send the quality coefficient ZL of the label batch to the database for storage;

[0011] The optimization feedback module is used to perform optimization feedback analysis on the production end of label printing according to the label printing defect identification result.

[0012] Furthermore, the specific process of image processing of the analysis object includes: photographing the analysis object and marking the photographed image as a detection image, enlarging the detection image into a pixel grid image and performing grayscale transformation, obtaining a standard image of the analysis object through a database, segmenting the detection image and the printed area in the standard image through a binary method, comparing the detection image with the printed area in the standard image and marking the number of overlapping pixel grids and the pixel grids of the printed area in the standard image as qualified.

[0013] Furthermore, the process of obtaining the printing offset value YP and the printing color difference value YS includes: marking the difference between the number of pixel grids in the printing area of ​​the standard image and the number of re-qualified ones as the printing offset value YP; marking the absolute value of the difference in grayscale values ​​between the detection image and the standard image as the gray difference value, and summing and averaging all the re-qualified gray difference values ​​to obtain the printing color difference value YS.

[0014] Furthermore, the specific process of conducting a reflected light test on the analysis object includes: irradiating a light source on the analysis object, measuring the intensity of the reflected light through a reflection photometer and marking it as the reflection value of the analysis object, retrieving the reflection standard value of the analysis object through a database, and marking the absolute value of the difference between the reflection value and the reflection standard value as a reflection deviation value FP.

[0015] Furthermore, the specific process of marking the analysis object as a qualified object or a defective object includes: obtaining the defect threshold QXmax through the database, and comparing the defect coefficient QX of the analysis object with the defect threshold QXmax: if the defect coefficient QX is less than the defect threshold QXmax, it is determined that the printing defect recognition result of the analysis object meets the requirements, and the corresponding analysis object is marked as a qualified object; if the defect coefficient QX is greater than or equal to the defect threshold QXmax, it is determined that the printing defect recognition result of the analysis object does not meet the requirements, and the corresponding analysis object is marked as a defective object.

[0016] Furthermore, the process of obtaining the quality coefficient ZL of the label batch includes: summing and averaging the defect coefficients QX of the entire batch of analysis objects that undergo defect identification within the analysis period to obtain the defect performance value QB of the label batch, performing variance calculation on the defect coefficients QX of the entire batch of analysis objects that undergo defect identification within the analysis period to obtain the stable performance value WB of the label batch, and obtaining the quality coefficient ZL of the label batch by numerically calculating the defect performance value QB and the stable performance value WB.

[0017] Furthermore, the specific process of the optimization feedback module performing optimization feedback analysis on the production end of label printing based on the label printing defect identification results includes: retrieving the quality coefficient ZL of all label batches at the end of the analysis cycle, marking L1 label batches with the smallest quality coefficient ZL value as optimized batches, retrieving the printing speed and printing pressure of the optimized batches in the production stage, forming a speed optimization range by the maximum printing speed and the minimum printing speed of all priority batches, forming a pressure optimization range by the maximum printing pressure and the minimum printing pressure of all priority batches, forming an optimization feedback data set by the speed optimization range and the pressure optimization range, sending the optimization feedback data set to the mobile phone terminal of the manager, and setting the printing speed and printing pressure of the label printing machine within the speed optimization range and the pressure optimization range of the optimization feedback data set in the subsequent label printing production process.

[0018] Furthermore, the working method of the label printing defect online visual recognition detection device comprises the following steps:

[0019] Step 1: Identify and analyze label printing defects: mark the label to be analyzed as the analysis object, perform image processing and reflected light test on the analysis object to obtain the printing offset value YP, printing color difference value YS and reflection deviation value FP respectively;

[0020] Step 2: numerically calculate the printing offset value YP, the printing color difference value YS and the reflection deviation value FP to obtain the defect coefficient QX of the analysis object, and mark the analysis object as a qualified object or a defective object according to the defect coefficient QX;

[0021] Step 3: Comprehensively analyze the identification results of label printing defects of the same batch: generate an analysis cycle and obtain the quality coefficient ZL of the label batch within the analysis cycle;

[0022] Step 4: Conduct optimization feedback analysis on the label printing production end based on the label printing defect identification results: retrieve the quality coefficient ZL of all label batches at the end of the analysis cycle, mark the L1 label batches with the smallest quality coefficient ZL value as the optimized batch, retrieve the printing speed and printing pressure of the optimized batches in the production stage, and generate an optimization feedback data set based on the printing speed and printing pressure of all optimized batches in the production stage.

[0023] The present invention has the following beneficial effects:

[0024] 1. The printing defect recognition and analysis module can identify and analyze label printing defects. By combining image processing and reflected light testing, the printing deviation, printing color deviation, surface reflectivity and other parameters of the analyzed object are analyzed and processed comprehensively to obtain the defect coefficient. The defect coefficient is used to provide feedback on the overall printing quality of the analyzed object. At the same time, the analyzed object is differentiated and marked according to the feedback results, providing data support for the overall quality analysis of the entire batch;

[0025] 2. The batch quality analysis module can be used to comprehensively analyze the identification results of label printing defects in the same batch, and the defect coefficients of the entire batch of analysis objects that have been identified within the analysis cycle can be numerically processed to obtain the quality coefficient, and the overall printing quality of the label batch can be evaluated through the quality coefficient;

[0026] 3. Through the optimization feedback module, the production end of label printing can be optimized and analyzed based on the results of label printing defect identification. The optimized batches can be screened by analyzing the quality coefficient of each label batch within the cycle. Then, the processing parameters of all optimized batches of labels at the production end are combined to generate an optimized feedback data set. The operating parameters of subsequent label printing machines are optimized and adjusted through the optimized feedback data set to improve the label printing effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 is a system block diagram of Embodiment 1 of the present invention;

[0029] Figure 2This is a flow chart of the method of Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0030] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] Embodiment 1: Figure 1 As shown, an online visual recognition and detection device for label printing defects includes a printing defect recognition and analysis module, a batch quality analysis module, an optimization feedback processing module and a database. The printing defect recognition and analysis module, the batch quality analysis module and the optimization feedback processing module are communicatively connected in sequence, and the database is communicatively connected to the printing defect recognition and analysis module and the batch quality analysis module.

[0032] The printing defect recognition and analysis module is used to recognize and analyze label printing defects: the label to be analyzed is marked as the analysis object, and the image processing and reflected light test are performed on the analysis object to obtain the printing offset value YP, the printing color difference value YS and the reflection deviation value FP respectively; the specific process of image processing on the analysis object includes: taking an image of the analysis object and marking the captured image as a detection image, enlarging the detection image into a pixel grid image and performing grayscale transformation, obtaining the standard image of the analysis object through the database, segmenting the detection image and the printing area in the standard image through the binary method, and comparing the detection image with the printing area in the standard image. The number of overlapping pixel grids and the pixel grids in the printing area of ​​the standard image are marked as re-qualified, and the difference between the number of pixel grids in the printing area of ​​the standard image and the number of re-qualified is marked as the printing offset value YP; the absolute value of the difference in grayscale value between the re-qualified image and the standard image is marked as the gray difference value, and all the re-qualified gray difference values ​​are summed and averaged to obtain the printing color difference value YS; the specific process of performing reflected light test on the analysis object includes: irradiating the light source on the analysis object, measuring the intensity of the reflected light through a reflection photometer and marking it as the reflection value of the analysis object, retrieving the reflection standard value of the analysis object through a database, and comparing the reflection value with the reflection standard value. The absolute value of the difference is marked as the reflection deviation value FP; the defect coefficient QX of the analyzed object is obtained by the formula QX=c1×YP+c2×YS+c3×FP, where c1, c2 and c3 are all proportional coefficients, and c1>c2>c3>1. The defect coefficient QX is a value that reflects the quality of the printing of the analyzed object. The larger the value of the defect coefficient QX, the worse the printing quality of the analyzed object. The defect threshold QXmax is obtained through the database, and the defect coefficient QX of the analyzed object is compared with the defect threshold QXmax: if the defect coefficient QX is less than the defect threshold QXmax, the printing defect recognition result of the analyzed object is determined to be If the result meets the requirements, the corresponding analysis object is marked as a qualified object; if the defect coefficient QX is greater than or equal to the defect threshold QXmax, it is determined that the printing defect recognition result of the analysis object does not meet the requirements, and the corresponding analysis object is marked as a defective object; the label printing defects are identified and analyzed, and the printing offset, printing color deviation, surface reflectivity and other parameters of the analysis object are analyzed and comprehensively processed in turn by combining image processing and reflected light testing to obtain the defect coefficient. The overall printing quality of the analysis object is fed back through the defect coefficient, and the analysis object is differentiated and marked according to the feedback results, providing data support for the overall quality analysis of the entire batch.

[0033] The batch quality analysis module is used to conduct a comprehensive analysis on the defect recognition results of label printing of the same batch: generate an analysis cycle, sum and average the defect coefficients QX of the entire batch of analysis objects that undergo defect recognition within the analysis cycle to obtain the defect performance value QB of the label batch, perform variance calculation on the defect coefficients QX of the entire batch of analysis objects that undergo defect recognition within the analysis cycle to obtain the stable performance value WB of the label batch, and obtain the quality coefficient ZL of the label batch through the formula ZL=w1×QB+w2×WB, where w1 and w2 are both proportional coefficients, and w1>w2>1, and the quality coefficient ZL is a value that reflects the overall printing quality of the label batch. The larger the value of the quality coefficient ZL, the worse the overall printing quality of the label batch; send the quality coefficient ZL of the label batch to the database for storage; conduct a comprehensive analysis on the defect recognition results of label printing of the same batch, perform numerical processing on the defect coefficients of the entire batch of analysis objects that undergo defect recognition within the analysis cycle to obtain the quality coefficient, and evaluate the overall printing quality of the label batch through the quality coefficient.

[0034] The optimization feedback module is used to perform optimization feedback analysis on the production side of label printing based on the results of label printing defect identification: at the end of the analysis cycle, the quality coefficient ZL of all label batches is retrieved, and the L1 label batches with the smallest quality coefficient ZL value are marked as optimized batches. L1 is a numerical constant, and the specific value of L1 is set by the management personnel; the printing speed and printing pressure of the optimized batch in the production stage are retrieved, and the speed optimization range is composed of the maximum printing speed and the minimum printing speed of all priority batches, and the pressure optimization range is composed of the maximum printing pressure and the minimum printing pressure of all priority batches. An optimized feedback data set is generated and sent to the mobile phone terminal of the manager. In the subsequent label printing production process, the printing speed and printing pressure of the label printing machine are respectively set within the speed optimization range and pressure optimization range of the optimized feedback data set; based on the label printing defect identification results, the production end of the label printing is optimized and feedback analysis is performed, and the optimized batches are screened by analyzing the quality coefficient of each label batch within the cycle, and then the processing parameters of all optimized batches of labels at the production end are combined to generate an optimized feedback data set, and the operating parameters of the subsequent label printing machines are optimized and adjusted through the optimized feedback data set to improve the label printing effect.

[0035] Embodiment 2: Figure 2 As shown, a method for online visual recognition and detection of label printing defects comprises the following steps:

[0036] Step 1: Identify and analyze label printing defects: mark the label to be analyzed as the analysis object, perform image processing and reflected light test on the analysis object to obtain the printing offset value YP, printing color difference value YS and reflection deviation value FP respectively;

[0037] Step 2: numerically calculate the printing offset value YP, the printing color difference value YS and the reflection deviation value FP to obtain the defect coefficient QX of the analysis object, and mark the analysis object as a qualified object or a defective object according to the defect coefficient QX;

[0038] Step 3: Comprehensively analyze the identification results of label printing defects of the same batch: generate an analysis cycle and obtain the quality coefficient ZL of the label batch within the analysis cycle;

[0039] Step 4: Conduct optimization feedback analysis on the label printing production end based on the label printing defect identification results: retrieve the quality coefficient ZL of all label batches at the end of the analysis cycle, mark the L1 label batches with the smallest quality coefficient ZL value as the optimized batch, retrieve the printing speed and printing pressure of the optimized batches in the production stage, and generate an optimization feedback data set based on the printing speed and printing pressure of all optimized batches in the production stage.

[0040] An online visual recognition and detection device for label printing defects, when working, marks a label to be analyzed as an analysis object, performs image processing and reflected light test on the analysis object to obtain a printing offset value YP, a printing color difference value YS and a reflection deviation value FP respectively; performs numerical calculation on the printing offset value YP, the printing color difference value YS and the reflection deviation value FP to obtain a defect coefficient QX of the analysis object, and marks the analysis object as a qualified object or a defective object according to the defect coefficient QX; generates an analysis cycle, and obtains a quality coefficient ZL of a label batch within the analysis cycle; retrieves the quality coefficient ZL of all label batches at the end of the analysis cycle, marks L1 label batches with the smallest quality coefficient ZL values ​​as optimized batches, retrieves the printing speed and printing pressure of the optimized batch in the production stage, and generates an optimized feedback data set according to the printing speed and printing pressure of all optimized batches in the production stage.

[0041] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

[0042] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula close to the real value. The coefficients in the formula are set by technicians in this field according to the actual situation; for example: formula QX = c1×YP+c2×YS+c3×FP; technicians in this field collect multiple groups of sample data and set corresponding defect coefficients for each group of sample data; substitute the set defect coefficients and the collected sample data into the formula, any three formulas constitute a three-variable linear equation group, screen the calculated coefficients and take the average, and obtain the values ​​of c1, c2 and c3 as 3.51, 2.68 and 2.24 respectively;

[0043] The size of the coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the coefficient depends on the amount of sample data and the preliminary setting of the corresponding defect coefficient for each set of sample data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantized value, such as the defect coefficient is proportional to the value of the printing offset value.

[0044] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0045] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An online visual recognition detection device for label printing defects, characterized in that: It includes a printing defect recognition and analysis module, a batch quality analysis module, an optimization feedback processing module and a database, wherein the printing defect recognition and analysis module, the batch quality analysis module and the optimization feedback processing module are sequentially connected in communication, and the database is connected in communication with the printing defect recognition and analysis module and the batch quality analysis module; The printing defect recognition and analysis module is used to recognize and analyze label printing defects: the label to be analyzed is marked as an analysis object, image processing and reflected light test are performed on the analysis object to obtain a printing offset value YP, a printing color difference value YS and a reflection deviation value FP respectively; the defect coefficient QX of the analysis object is obtained by numerically calculating the printing offset value YP, the printing color difference value YS and the reflection deviation value FP; The analysis object is marked as a qualified object or a defective object by the defect coefficient QX; The batch quality analysis module is used to comprehensively analyze the results of defect recognition of label printing of the same batch: generate an analysis cycle, obtain the quality coefficient ZL of defect recognition of the label batch within the analysis cycle; send the quality coefficient ZL of the label batch to the database for storage; The optimization feedback module is used to perform optimization feedback analysis on the production end of label printing according to the label printing defect identification result.

2. The device for online visual recognition and detection of label printing defects according to claim 1, characterized in that: The specific process of image processing on the analysis object includes: photographing the analysis object and marking the photographed image as a detection image, enlarging the detection image into a pixel grid image and performing grayscale transformation, obtaining a standard image of the analysis object through a database, segmenting the detection image and the printed area in the standard image through a binary method, comparing the detection image with the printed area in the standard image and marking the number of overlapping pixel grids and the pixel grids of the printed area in the standard image as qualified.

3. The on-line visual recognition detection device for label printing defects according to claim 2 is characterized in that: The process of obtaining the printing offset value YP and the printing color difference value YS includes: marking the difference between the number of pixels in the printing area of ​​the standard image and the number of re-qualified pixels as the printing offset value YP; marking the absolute value of the difference in grayscale values ​​between the detection image and the standard image as the gray difference value, and summing up and averaging all the re-qualified gray difference values ​​to obtain the printing color difference value YS.

4. The on-line visual recognition detection device for label printing defects according to claim 3 is characterized in that: The specific process of performing a reflected light test on the analysis object includes: irradiating the light source on the analysis object, measuring the intensity of the reflected light with a reflection photometer and marking it as the reflection value of the analysis object, retrieving the reflection standard value of the analysis object through a database, and marking the absolute value of the difference between the reflection value and the reflection standard value as the reflection deviation value FP.

5. The device for online visual recognition and detection of label printing defects according to claim 4, characterized in that: The specific process of marking the analysis object as a qualified object or a defective object includes: obtaining the defect threshold QXmax through the database, and comparing the defect coefficient QX of the analysis object with the defect threshold QXmax: if the defect coefficient QX is less than the defect threshold QXmax, it is determined that the printing defect recognition result of the analysis object meets the requirements, and the corresponding analysis object is marked as a qualified object; if the defect coefficient QX is greater than or equal to the defect threshold QXmax, it is determined that the printing defect recognition result of the analysis object does not meet the requirements, and the corresponding analysis object is marked as a defective object.

6. The device for online visual recognition and detection of label printing defects according to claim 5, characterized in that: The process of obtaining the quality coefficient ZL of the label batch includes: summing and averaging the defect coefficients QX of the entire batch of analysis objects that undergo defect identification within the analysis period to obtain the defect performance value QB of the label batch, performing variance calculation on the defect coefficients QX of the entire batch of analysis objects that undergo defect identification within the analysis period to obtain the stable performance value WB of the label batch, and obtaining the quality coefficient ZL of the label batch by numerically calculating the defect performance value QB and the stable performance value WB.

7. The device for online visual recognition and detection of label printing defects according to claim 6, characterized in that: The specific process of the optimization feedback module performing optimization feedback analysis on the production end of label printing based on the label printing defect identification results includes: retrieving the quality coefficient ZL of all label batches at the end of the analysis cycle, marking L1 label batches with the smallest quality coefficient ZL value as optimized batches, retrieving the printing speed and printing pressure of the optimized batches in the production stage, forming a speed optimization range by the maximum printing speed and the minimum printing speed of all priority batches, forming a pressure optimization range by the maximum printing pressure and the minimum printing pressure of all priority batches, forming an optimization feedback data set by the speed optimization range and the pressure optimization range, sending the optimization feedback data set to the mobile phone terminal of the manager, and setting the printing speed and printing pressure of the label printing machine within the speed optimization range and the pressure optimization range of the optimization feedback data set in the subsequent label printing production process.

Images