Same-version multi-code digital label printing management system based on machine vision

Abstract

The invention relates to the technical field of image recognition, and discloses a same-version multi-code digital label printing management system based on machine vision, an image acquisition module is used for capturing a printed matter from a printing production line in real time to obtain a target image; the image detection module is used for detecting the quality of the target image, processing the shape and surface defect of each independent bar code unit image of the target image to obtain a surface feature value of the target image, and identifying the printing state of the printed matter based on the surface feature value of the target image; the multi-image analysis module is used for sampling multi-target images on a printing production line, constructing a checking printed matter group, and identifying the state of printing equipment based on a printing checking value of the checking printed matter group; and the collaborative adjustment module is used for comparing the printing parameters of the printing equipment with the standard parameters based on the printing regulation and control signal of the printing equipment so as to optimize the printing process of the same-version multi-code digital label.

Description

Technical Field

[0001] The present invention relates to the technical field of image recognition, and in particular to a same-version multi-code digital label printing management system based on machine vision. Background Art

[0002] Digital printing technology is a printing technology that prints images directly onto paper or other media in a digital way.

[0003] The same version of multi-code digital label printing management is developed based on these advantages of digital printing technology. It uses advanced digital printing equipment and software in the printing process to print multiple different barcodes on the same label. These barcodes can contain different product information, batch numbers, production dates, etc. to meet the diverse needs of enterprises.

[0004] In the printing production line, due to the fast production speed and large quantity, the quality inspection of printed products through visual inspection by staff has certain limitations. During the sampling process, it is particularly important to identify the barcode quality more comprehensively and effectively.

[0005] Based on this, the present invention proposes a same-version multi-code digital label printing management system based on machine vision. Summary of the invention

[0006] The purpose of the present invention is to provide a same-version multi-code digital label printing management system based on machine vision, which can obtain the target image of the printed product by capturing the image data of the printed product in real time during the same-version multi-code digital label printing process, that is, by segmenting the multiple barcodes corresponding to the target image of the printed product, and processing each independent barcode unit image in terms of shape, to obtain the non-standard deviation ratio and defect area ratio of the barcode unit image, and then by integrating the non-standard deviation ratio and defect area ratio corresponding to all the barcode unit images on the target image with the arrangement position of the barcode on the target image, it is possible to complete the identification of the printing quality from the quality of a single barcode unit image and the arrangement status of multiple barcode unit images.

[0007] The purpose of the present invention can be achieved through the following technical solutions: The same version multi-code digital label printing management system based on machine vision includes: The image acquisition module is used to capture the image data of the printed product from the printing production line in real time and pre-process the acquired image data to obtain the target image; The image detection module is used to detect the quality of the target image, segment the target image to obtain a number of barcode unit images, process the shape and surface defects of each independent barcode unit image to obtain the surface feature value of the target image, and complete the printing status recognition of the printed matter based on the surface feature value of the target image; The printing status of the printed product includes a normal printing signal and an abnormal printing signal; The multi-image analysis module is used to sample and process multiple target images on the printing production line, construct a verification print group, and complete the recognition of the printing equipment status based on the printing verification value of the verification print group; The collaborative adjustment module compares the printing parameters of the printing equipment with the standard parameters based on the printing control signal of the printing equipment, and optimizes the printing process of multi-code digital labels on the same version.

[0008] As a further solution of the present invention: the process of obtaining the surface feature value of the target image is: The non-standard deviation of the barcode unit image is obtained by processing the shape of the barcode unit image; The non-standard deviation ratios of all barcode unit images are calculated by the mean method to obtain the total non-standard deviation value of the target image, which is recorded as Mp; The defect abnormality ratio of the barcode unit image is obtained by processing the surface defects of the barcode unit image; The defect anomaly ratios of all barcode unit images are calculated by the mean value method to obtain the total defect anomaly value of the target image, which is recorded as Mx; The boundary and position of the barcode in the target image are processed to obtain the spacing variance value of the target image, which is recorded as Mc; By formula The surface feature value Mi of the target image is calculated, where d1, d2, and d3 are all preset proportional coefficients.

[0009] As a further solution of the present invention: the surface feature value Mi of the target image is compared with the surface feature threshold My of the target image: When the surface feature value Mi of the target image is less than the surface feature threshold My of the target image, a printing normal signal is generated; When the surface feature value Mi of the target image is greater than or equal to the surface feature threshold My of the target image, a printing abnormality signal is generated.

[0010] As a further solution of the present invention: the process of obtaining the non-standard deviation ratio of the barcode unit image is as follows: Overlapping the barcode unit image with the barcode standard image to obtain a barcode overlap image; Color the non-overlapping parts of the barcode overlap image; Count the number of colored pixel grids in the non-overlapping part of the barcode overlap image and the number of non-colored pixel grids in the overlapping part of the barcode overlap image; The non-standard deviation ratio of the barcode unit image is obtained by calculating the ratio of the number of colored pixel grids in the non-overlapping part of the barcode overlap image to the number of non-colored pixel grids in the overlapping part of the barcode overlap image.

[0011] As a further solution of the present invention: the process of obtaining the defect anomaly ratio of the barcode unit image is as follows: Obtaining a defective area in the barcode unit image, calculating the ratio of the area of ​​the defective area to the area of ​​the barcode unit image, and obtaining a defective area ratio of the barcode unit image; Obtaining the number of abnormal bars corresponding to the columns in the barcode unit image, calculating the ratio of the number of abnormal bars to the number of all bars in the barcode unit image, and obtaining the ratio of the number of abnormal bars in the barcode unit image; The abnormal number ratio of the barcode unit image and the defect area ratio of the barcode unit image are processed to obtain the defect abnormality ratio of the barcode unit image.

[0012] As a further solution of the present invention: the process of obtaining the abnormal bar number ratio of the barcode unit image is as follows: The barcode unit image is converted into a binary image by using an image binarization processing method; Scan each binarized barcode unit image column by column from left to right, count the number of black dots in each column, and divide the column into bars and spaces; In the vertical projection of a bar, if the number of black dot pixels of a bar is less than or equal to the threshold number of black dot pixels of the bar, the bar is marked as an abnormal bar; If the number of black dot pixels of a bar is greater than the threshold number of black dot pixels of the bar, the bar is recorded as a normal bar; The ratio of the number of abnormal bars to the number of all bars in the barcode unit image is calculated to obtain the abnormal bar ratio of the barcode unit image.

[0013] As a further solution of the present invention: the process of obtaining the defect area ratio of the barcode unit image is as follows: During the scanning process, if the number of empty black dot pixels is greater than or equal to the empty black dot pixel number threshold, the index of the column is recorded as L1, and the scanning is continued until the number of empty black dot pixels is less than the empty black dot pixel number threshold, then the index of the column is recorded as L2; Obtain the position of the defect point in the barcode unit image based on L1 and L2 in the barcode unit image and mark it; Connect all defect points in the barcode unit image end to end in a clockwise order to obtain the defect area in the barcode unit image; The ratio of the area of ​​the defective region to the area of ​​the barcode unit image is calculated to obtain the defective area ratio of the barcode unit image.

[0014] As a further solution of the present invention: the verification print set is processed: The surface characteristic values ​​of the printed products in the verification printed product group are processed according to the variance calculation formula to obtain the variance value of the verification printed product group, which is recorded as the verification variance value; Obtain the number of printed products whose surface characteristic values ​​in the verification printed product group are greater than or equal to the surface characteristic threshold value, and record it as the number of abnormal prints; The abnormal printing quantity is calculated by ratioing the total quantity of printed products in the verification printed product group to obtain the abnormal printing ratio; The verification variance value is multiplied by the abnormal printing ratio to obtain the printing verification value.

[0015] As a further solution of the present invention: if the printing verification value is less than the printing verification threshold, it means that the verification print obtained by random sampling is an accidental event, and a normal printing signal is obtained; If the printing verification value is greater than or equal to the printing verification threshold, it means that the verification print obtained by random sampling is a fault event, and a printing control signal is obtained.

[0016] As a further solution of the present invention: based on the printing control signal, the printing pressure, printing speed and printing drying temperature of the printing equipment are regulated to achieve the control of the printing quality of the printed product.

[0017] Beneficial effects of the present invention: In the present invention, during the printing process of the same-plate multi-code digital label, the image data of the printed product is captured in real time to obtain the target image of the printed product, that is, by segmenting the multiple barcodes corresponding to the target image of the printed product, each independent barcode unit image is processed in shape to obtain the non-standard deviation ratio of the barcode unit image, and then the independent barcode unit image is processed in surface defects to obtain the defect area ratio of the barcode unit image, and then the non-standard deviation ratio and defect area ratio corresponding to all the barcode unit images on the target image are integrated with the arrangement position of the barcode on the target image to obtain the surface feature value of the target image, thereby realizing the recognition of the printing quality from the quality of a single barcode unit image and the arrangement state of multiple barcode unit images; When random sampling is performed in the printing production process, when there are verification prints, images of the prints obtained before and after the verification prints are collected to construct a verification print group, and a printing verification value is obtained by processing the verification variance value and the abnormal printing ratio of the verification print group, thereby realizing the identification of the operating status of the printing equipment from the quality qualification rate of the prints and the degree of fluctuation of the printing quality, and completing the adjustment and optimization of the behavior parameters of the printing equipment based on the operating status of the printing equipment, thereby realizing the optimized management of the same-version multi-code digital label printing process. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The present invention will be further described below in conjunction with the accompanying drawings.

[0019] Figure 1It is a flowchart of a same-version multi-code digital label printing management system based on machine vision according to an embodiment of the present invention; Figure 2 This is a workflow diagram of a same-version multi-code digital label printing management system based on machine vision according to an embodiment of the present invention; Figure 3 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not 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. Example 1

[0021] See also Figure 1-Figure 2 As shown, the present invention is a same-version multi-code digital label printing management system based on machine vision, comprising: The image acquisition module is used to capture the image data of the printed product from the printing production line in real time and pre-process the acquired image data to obtain the target image; An image detection module is used to detect the quality of a target image, obtain a surface feature value of the target image, and recognize the printing state of a printed product based on the surface feature value of the target image; The printing status of the printed product includes a normal printing signal and an abnormal printing signal; The multi-image analysis module is used to sample and process multiple target images on the printing production line, construct a verification print group, and complete the recognition of the printing equipment status based on the printing verification value of the verification print group; The collaborative adjustment module compares the printing parameters of the printing equipment with the standard parameters based on the printing control signal of the printing equipment, and optimizes the printing process of multi-code digital labels on the same version. Example 2

[0022] The image data of printed products is collected in real time from printed products on the printing production line through devices such as cameras or scanners; Since the collected printed images may have problems such as noise and uneven lighting, the collected image data needs to be preprocessed; The preprocessing of image data includes noise removal, brightness adjustment, grayscale and contrast enhancement.

[0023] During the quality inspection of the target image, the Canny edge detection algorithm is used to determine the boundary and position of the barcode in the target image; Wherein, barcode includes but is not limited to barcode or QR code; According to the detected edge information, the barcode in the target image is divided into regions so that each independent barcode forms an independent barcode unit image; Obtain the barcode standard image corresponding to each barcode unit image, and compare the barcode unit image with the barcode standard image. Specifically: Overlapping the barcode unit image with the barcode standard image to obtain a barcode overlap image; Place the barcode overlap image on the white background image and color the non-overlapping parts of the barcode overlap image; The barcode overlap image is magnified several times to form a pixel grid overlap photo, and the number of pixel grids colored in the non-overlapping part of the barcode overlap image is counted; Obtain the number of non-colored pixels in the overlapping part of the statistical barcode overlapping map; The number of colored pixel grids in the non-overlapping part of the barcode overlap image is calculated by ratio with the number of non-colored pixel grids in the overlapping part of the barcode overlap image to obtain the non-standard deviation ratio of the barcode unit image; The non-standard deviation ratios of all barcode unit images are calculated by the mean value method to obtain the total non-standard deviation value of the target image; Among them, the barcode standard image is the barcode image with the best quality obtained in the barcode printing process, and the barcode standard image is set by the staff.

[0024] It should be noted that the non-standard deviation ratio of the barcode unit image reflects the printing defects of the single barcode body and reflects the printing quality of the single barcode.

[0025] Identify the surface defects of each barcode unit image, including dirty spots, missing prints and plate scratches; Specific: The barcode unit image is converted into a binary image by using an image binarization processing method; Among them, black represents the bars of the barcode, and white represents the spaces of the barcode; Scan each binarized barcode unit image column by column from left to right and count the number of black dots in each column; Count all the columns with black dots and calculate the average number of black dot pixels in each column; When the number of black pixel in any column is greater than 75% NA, the column is judged as a stripe, and all pixel values ​​in the column are set to 1; When the number of black pixel in any column is less than or equal to 75% NA, the column is considered empty and all pixel values ​​in the column are set to 0; Among them, NA represents the theoretical maximum number of black dot pixels in a column of the barcode; In the vertical projection of the bar, the number of black dot pixels of the bar is identified; If the number of black dot pixels of a bar is less than or equal to the threshold number of black dot pixels of the bar, it means that there is ink loss in the bar, and the bar is recorded as an abnormal bar; If the number of black dot pixels of the bar is greater than the black dot pixel number threshold of the bar, it means that the ink state of the bar is normal, and the bar is recorded as a normal bar; The number of abnormal bars is obtained, and the ratio of the number of abnormal bars to the number of all bars of the barcode unit image is calculated to obtain the ratio of the number of abnormal bars of the barcode unit image; Exemplarily, the black dot pixel number threshold of the bar is set to 95%NA. Generally, when the resolution of the barcode image is 300ppi, the human eye can perceive the defect when the number of defective pixels is greater than or equal to 5%NA.

[0026] In the vertical projection of the empty space, the number of empty black dot pixels is identified; During the scanning process, if the number of empty black dot pixels is greater than or equal to the empty black dot pixel number threshold, the index of the column is recorded as L1. After recording L1, continue to scan to the right until the number of empty black dot pixels is less than the empty black dot pixel number threshold, then record the index of the column as L2; Obtain the position of the defect point in the barcode unit image based on L1 and L2 in the barcode unit image and mark it; Connect all defect points in the barcode unit image end to end in a clockwise order to obtain the defect area in the barcode unit image; Obtaining the area of ​​the defective region in the barcode unit image, calculating the ratio of the area of ​​the defective region to the area of ​​the barcode unit image, and obtaining the defective area ratio of the barcode unit image; Among them, the threshold of the number of empty black dot pixels is set by the staff based on experience.

[0027] The ratio of the number of abnormal bars in the barcode unit image is recorded as Ts, and the ratio of the defective area in the barcode unit image is recorded as Tx. By formula The defect anomaly ratio Ti of the barcode unit image is calculated, where: is the preset proportional coefficient; in, The acquisition process is: there are m groups of historical data, each set of historical data includes the number of abnormal bar code unit image ratio Ts, the defect area ratio Tx and the bar code unit image defect abnormality ratio Ti; Use a linear model to fit m groups of historical data, bring the prepared historical data into the selected fitting model for fitting, and get the mean of the fitting coefficients as the preset proportional coefficient .

[0028] The defect anomaly ratios of all barcode unit images are calculated using the mean method to obtain the total defect anomaly value of the target image.

[0029] Identify the boundaries and positions of the barcode in the target image, specifically: Get the spacing behavior value of adjacent barcodes in each target image; The obtained spacing behavior value is calculated by difference with the spacing standard value to obtain the spacing deviation value; The standard spacing value is a preset spacing value of the barcode in the target image during the typesetting process.

[0030] All spacing deviation values ​​in the target image are processed according to the variance calculation formula to obtain the spacing variance value of the target image.

[0031] Processing the total value of non-standard deviation of the target image, the total value of defect anomaly of the target image and the distance variance value of the target image; The total value of the non-standard deviation of the target image is recorded as Mp, the total value of the defect anomaly of the target image is recorded as Mx, and the spacing variance value of the target image is recorded as Mc; By formula The surface feature value Mi of the target image is calculated, where d1, d2, and d3 are all preset proportional coefficients, d1 is 0.37, d2 is 0.35, and d3 is 0.28.

[0032] Preset a surface feature threshold My of the target image, and compare the surface feature value Mi of the target image with the surface feature threshold My of the target image; When the surface feature value Mi of the target image is less than the surface feature threshold My of the target image, it indicates that the printing quality of the printed matter corresponding to the target image is good, and a normal printing signal is generated; When the surface feature value Mi of the target image is greater than or equal to the surface feature threshold My of the target image, it indicates that the printing quality of the printed matter corresponding to the target image is poor, and a printing abnormality signal is generated.

[0033] Based on the surface feature values ​​of the target image, the quality of the printed product on the printing production line can be effectively identified. Example 3

[0034] During the production process on the printing production line, the printed product is randomly sampled, and if there is a surface feature value Mi of the sampled target image that is greater than or equal to the surface feature threshold My of the target image, the printed product corresponding to the target image is verified; Recording the target image corresponding to the verification print as the verification image; In chronological order, with the verification printed product as the center, image sampling is performed on the printed products located before the verification printed product, and the number of samples is not less than 3; at the same time, image sampling is performed on the printed products located after the verification printed product, and the number of samples is not less than 3, which together constitute the verification printed product group; Among them, the time interval adopted is set by the staff based on experience; Arranging the surface feature values ​​of the images corresponding to each printed product in the verification printed product group; The surface characteristic values ​​of the printed products in the verification printed product group are processed according to the variance calculation formula to obtain the variance value of the verification printed product group, which is recorded as the verification variance value; Obtain the number of printed products whose surface characteristic values ​​in the verification printed product group are greater than or equal to the surface characteristic threshold value, and record it as the number of abnormal prints; The abnormal printing quantity is calculated by ratioing the total quantity of printed products in the verification printed product group to obtain the abnormal printing ratio; The verification variance value is multiplied by the abnormal printing ratio to obtain the printing verification value; If the printing verification value is less than the printing verification threshold, it means that the verification print obtained by random sampling is an accidental event, and a normal printing signal is obtained, and the printing device maintains the normal printing procedure for printing; If the printing verification value is greater than or equal to the printing verification threshold, it means that the randomly sampled verification print product is a fault event, and a printing control signal is obtained to control the printing process of the printing equipment. Example 4

[0035] Based on the printing control signal, the printing pressure, printing speed and printing drying temperature of the printing equipment are regulated to complete the control of the printing quality of the printed product; Obtaining the standard printing pressure, standard printing speed and standard printing drying temperature corresponding to the printing of the standard image by the printing device; The standard printing pressure of the printing equipment is recorded as Y1, the standard printing speed is recorded as Y2, and the standard printing drying temperature is recorded as Y3; The surface feature value corresponding to the printed standard image is recorded as Yi; Construct a function model, that is, through Obtain the printing standard surface characteristic value function Yi, where Y1 is greater than 0; Display the printing standard surface characteristic value function in an image form through a character string, and record the curve as a printing standard curve; Obtaining the surface characteristic value corresponding to the printed product of the printing device at the current time, and the real-time printing pressure, real-time printing speed and real-time printing drying temperature corresponding to the surface characteristic value of the printed product; The real-time printing pressure of the printing device is recorded as y1, the real-time printing speed is recorded as y2, and the real-time printing drying temperature is recorded as y3; The surface feature value corresponding to the current time print is recorded as yi; Build a functional model, The actual printed surface characteristic value function yi is obtained, where y1 is greater than 0; The actual printed surface characteristic value function is displayed in an image form through a character string, and the curve is recorded as a printing control curve; In the process of regulating the printing equipment, with the printing standard curve as a reference, the opening size, horizontal position and vertical position of the printing control curve are brought closer to the printing standard curve to achieve the coincidence of the printing control curve and the printing standard curve in projection, thereby completing the printing pressure, printing speed and printing drying temperature heating regulation of the printing equipment.

[0036] The printing standard image is the printing standard image with the best quality obtained in the barcode printing process, and the printing standard image is set by the staff. Example 5

[0037] Reference Figure 3 The embodiment of the present invention further provides a computer device 3, comprising: a memory 302 and a processor 301 and a computer program 303 stored in the memory 302. When the computer program 303 is executed on the processor 301, a same-version multi-code digital label printing management system based on machine vision as described in any one of the above methods is implemented.

[0038] The computer device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that Figure 3 It is only an example of computer device 3 and does not constitute a limitation on computer device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0039] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0040] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 3. Further, the memory 302 may also include both an internal storage unit of the computer device 3 and an external storage device. The memory 302 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 302 may also be used to temporarily store data that has been output or is to be output. Example 6

[0041] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the same-version multi-code digital label printing management system based on machine vision as described in any of the above methods is implemented.

[0042] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, USB flash drive, mobile hard disk, disk or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0043] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0044] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0045] In the embodiments disclosed in the present application, it should be understood that the disclosed apparatus / terminal equipment and method can be implemented in other ways. For example, the apparatus / terminal equipment embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. One point, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, which may be electrical, mechanical or other forms.

[0046] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0047] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0048] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. The same version multi-code digital label printing management system based on machine vision is characterized by: include: The image acquisition module is used to capture the image data of the printed product from the printing production line in real time and pre-process the acquired image data to obtain the target image; The image detection module is used to detect the quality of the target image, segment the target image to obtain a number of barcode unit images, process the shape and surface defects of each independent barcode unit image to obtain the surface feature value of the target image, and complete the printing status recognition of the printed matter based on the surface feature value of the target image; The printing status of the printed product includes a normal printing signal and an abnormal printing signal; The multi-image analysis module is used to sample and process multiple target images on the printing production line, construct a verification print group, and complete the recognition of the printing equipment status based on the printing verification value of the verification print group; The collaborative adjustment module compares the printing parameters of the printing equipment with the standard parameters based on the printing control signal of the printing equipment, and optimizes the printing process of multi-code digital labels on the same version.

2. The same version multi-code digital label printing management system based on machine vision according to claim 1 is characterized in that: The process of obtaining the surface eigenvalues ​​of the target image is as follows: The non-standard deviation of the barcode unit image is obtained by processing the shape of the barcode unit image; The non-standard deviation ratios of all barcode unit images are calculated by the mean method to obtain the total non-standard deviation value of the target image, which is recorded as Mp; The defect abnormality ratio of the barcode unit image is obtained by processing the surface defects of the barcode unit image; The defect anomaly ratios of all barcode unit images are calculated by the mean value method to obtain the total defect anomaly value of the target image, which is recorded as Mx; The boundary and position of the barcode in the target image are processed to obtain the spacing variance value of the target image, which is recorded as Mc; By formula The surface feature value Mi of the target image is calculated, where d1, d2, and d3 are all preset proportional coefficients.

3. The same version multi-code digital label printing management system based on machine vision according to claim 2 is characterized in that: Compare the surface feature value Mi of the target image with the surface feature threshold My of the target image: When the surface feature value Mi of the target image is less than the surface feature threshold My of the target image, a printing normal signal is generated; When the surface feature value Mi of the target image is greater than or equal to the surface feature threshold My of the target image, a printing abnormality signal is generated.

4. The same version multi-code digital label printing management system based on machine vision according to claim 2 is characterized in that: The process of obtaining the non-standard deviation ratio of the barcode unit image is as follows: Overlapping the barcode unit image with the barcode standard image to obtain a barcode overlap image; Color the non-overlapping parts of the barcode overlap image; Count the number of colored pixel grids in the non-overlapping part of the barcode overlap image and the number of non-colored pixel grids in the overlapping part of the barcode overlap image; The non-standard deviation ratio of the barcode unit image is obtained by calculating the ratio of the number of colored pixel grids in the non-overlapping part of the barcode overlap image to the number of non-colored pixel grids in the overlapping part of the barcode overlap image.

5. The same version multi-code digital label printing management system based on machine vision according to claim 2 is characterized in that: The process of obtaining the defect anomaly ratio of the barcode unit image is as follows: Obtaining a defective area in the barcode unit image, calculating the ratio of the area of ​​the defective area to the area of ​​the barcode unit image, and obtaining a defective area ratio of the barcode unit image; Obtaining the number of abnormal bars corresponding to the columns in the barcode unit image, calculating the ratio of the number of abnormal bars to the number of all bars in the barcode unit image, and obtaining the ratio of the number of abnormal bars in the barcode unit image; The abnormal number ratio of the barcode unit image and the defect area ratio of the barcode unit image are processed to obtain the defect abnormality ratio of the barcode unit image.

6. The same version multi-code digital label printing management system based on machine vision according to claim 5 is characterized in that: The process of obtaining the abnormal bar number ratio of the barcode unit image is as follows: The barcode unit image is converted into a binary image by using an image binarization processing method; Scan each binarized barcode unit image column by column from left to right, count the number of black dots in each column, and divide the column into bars and spaces; In the vertical projection of a bar, if the number of black dot pixels of a bar is less than or equal to the threshold number of black dot pixels of the bar, the bar is marked as an abnormal bar; If the number of black dot pixels of a bar is greater than the threshold number of black dot pixels of the bar, the bar is recorded as a normal bar; The ratio of the number of abnormal bars to the number of all bars in the barcode unit image is calculated to obtain the abnormal bar ratio of the barcode unit image.

7. The same version multi-code digital label printing management system based on machine vision according to claim 6 is characterized in that: The process of obtaining the defect area ratio of the barcode unit image is as follows: During the scanning process, if the number of empty black dot pixels is greater than or equal to the empty black dot pixel number threshold, the index of the column is recorded as L1, and the scanning is continued until the number of empty black dot pixels is less than the empty black dot pixel number threshold, then the index of the column is recorded as L2; Obtain the position of the defect point in the barcode unit image based on L1 and L2 in the barcode unit image and mark it; Connect all defect points in the barcode unit image end to end in a clockwise order to obtain the defect area in the barcode unit image; The ratio of the area of ​​the defective region to the area of ​​the barcode unit image is calculated to obtain the defective area ratio of the barcode unit image.

8. The same version multi-code digital label printing management system based on machine vision according to claim 3 is characterized in that: Processing of the verification print set: The surface characteristic values ​​of the printed products in the verification printed product group are processed according to the variance calculation formula to obtain the variance value of the verification printed product group, which is recorded as the verification variance value; Obtain the number of printed products whose surface characteristic values ​​in the verification printed product group are greater than or equal to the surface characteristic threshold value, and record it as the number of abnormal prints; The abnormal printing quantity is calculated by ratioing the total quantity of printed products in the verification printed product group to obtain the abnormal printing ratio; The verification variance value is multiplied by the abnormal printing ratio to obtain the printing verification value.

9. The same version multi-code digital label printing management system based on machine vision according to claim 8, characterized in that: If the print verification value is less than the print verification threshold, it means that the verification print obtained by random sampling is an accidental event, and a normal printing signal is obtained; If the printing verification value is greater than or equal to the printing verification threshold, it means that the verification print obtained by random sampling is a fault event, and a printing control signal is obtained.

10. The same version multi-code digital label printing management system based on machine vision according to claim 9, characterized in that: Based on the printing control signal, the printing pressure, printing speed and printing drying temperature of the printing equipment are regulated to complete the control of the printing quality of the printed product.

Images