A color deviation correction method and system for packaging printing process

Abstract

The present invention relates to the technical field of image color processing, and is a method and system for color deviation correction in a packaging printing process, comprising: obtaining a design area image, scanning a printed package, obtaining a printed package image, recording the amount of printed ink, printing speed and printing pressure, mapping the printed package image according to the design area image, obtaining a printed area image, comparing the printed area image with the design area image, obtaining a deviation area group set and a normal area group set, repeatedly obtaining the deviation area group set and the normal area group set according to the total number of area groups of the deviation area group set and the normal area group set, constructing a color deviation correction model using the deviation area group set and the normal area group set, adjusting a printing press based on the color deviation correction model, and obtaining a corrected printing press. The present invention can improve the intelligent degree of color deviation correction in the packaging printing process, and reduce the excessive consumption of time and human resources.

Description

Technical Field

[0001] The present invention relates to the technical field of image color processing, and in particular to a color deviation correction method and system in a packaging printing process. Background Art

[0002] The color of product packaging is a key visual element in product packaging design. It affects consumers' first impression and purchasing decisions. However, in the process of printing product packaging, there is often a color deviation between the printed product packaging and the designed product packaging. This will affect the pass rate of product packaging printing. Therefore, it is particularly important to correct the color deviation in the packaging printing process.

[0003] The current method for correcting color deviation in the packaging printing process is to compare the printed packaging image with the designed packaging image, and achieve the purpose of color correction by manually adjusting the printing machine parameters. Although this method can achieve the purpose of color deviation correction, it requires a lot of human resources and time, and the degree of intelligence needs to be improved. Summary of the invention

[0004] The present invention provides a color deviation correction method and system in a packaging printing process, the main purpose of which is to improve the intelligence level of color deviation correction in the packaging printing process and reduce excessive consumption of time and human resources.

[0005] To achieve the above object, the present invention provides a method for correcting color deviation in a packaging printing process, comprising:

[0006] Acquire a packaging design picture, perform standard size calibration on the packaging design picture to obtain a calibrated design picture, and perform color area division on the calibrated design picture to obtain a design area picture;

[0007] Extracting design areas in the design area picture in sequence, identifying design color channel values ​​of the design areas, performing key-value pairing between the design color channel values ​​and the design areas to obtain design area groups, and summarizing the design area groups to obtain a design area group set;

[0008] Starting a pre-built printing press and using the printing press to print a packaging design picture to obtain a printed package, scanning the printed package to obtain a printed package picture, and recording the amount of printing ink, printing speed, and printing pressure when the printing press prints the picture;

[0009] Performing standard size calibration on the printed packaging image to obtain a calibrated printed image, and performing area mapping division on the calibrated printed image according to the design area image to obtain a printed area image;

[0010] According to the design area group set, the printing area image is compared for color deviation to obtain a color deviation value, and the color deviation is determined according to the color deviation value, the amount of printing ink, the printing speed and the printing pressure to obtain a determination result group, wherein the determination result group includes: a deviation area group and a normal area group;

[0011] The deviation region group and the normal region group are used to supplement the pre-constructed initial deviation set and the initial normal set respectively, to obtain the deviation region group set and the normal region group set, and to obtain the total number of region groups of the deviation region group set and the normal region group set;

[0012] Determining whether the total number of area groups is less than a preset standard number of area groups;

[0013] If the total number of area groups is less than the standard number of area groups, the initial deviation set and the initial normal set are updated respectively using the deviation area group set and the normal area group set, and the process returns to the step of starting the pre-built printer and using the printer to print the packaging design image;

[0014] If the total number of area groups is not less than the standard number of area groups, the deviation area group set and the normal area group set are used to construct a machine learning model to obtain a color deviation correction model. The ink printing of the printing press is adjusted based on the color deviation correction model to obtain a calibrated printing press, thereby completing the color deviation correction of the packaging printing process.

[0015] Optionally, the step of calibrating the packaging design image to a standard size to obtain a calibrated design image includes:

[0016] Identifying blank edges in the packaging design image, and cropping the blank edges to obtain a cropped packaging design image;

[0017] Based on a preset standard picture size, adjusting the cropped packaging design picture to obtain a standard packaging design picture;

[0018] The center point of the standard packaging design picture is determined, and the center point of the picture is recorded as the coordinate origin. According to the coordinate origin, a coordinate system is constructed for the standard packaging design picture to obtain a calibrated design picture.

[0019] Optionally, dividing the calibration design image into color regions to obtain a design region image includes:

[0020] Performing preliminary artificial division on the calibration design image to obtain a preliminary division area image;

[0021] Sequentially extracting preliminary divided areas from the preliminary divided area picture;

[0022] Sequentially extract the preliminary pixel points in the preliminary divided area, identify the preliminary color channel values ​​of the preliminary pixel points, wherein the preliminary color channel values ​​are Color channel values ​​in a color space, the preliminary color channel values ​​comprising: a preliminary cyan value, a preliminary magenta value, a preliminary yellow value, and a preliminary black value;

[0023] According to the preliminary color channel value, the preliminary color modulus is calculated using the following formula:

[0024] ;

[0025] in, represents the preliminary color modulus, represents the initial cyan value, represents the preliminary magenta value, Indicates the preliminary yellow value, Indicates the preliminary black value;

[0026] The preliminary color moduli are summarized to obtain a preliminary color modulus set, which is expressed as:

[0027] ;

[0028] in, represents the preliminary color modulus set, represents the first preliminary color modulus, represents the nth preliminary color modulus, where n represents the number of preliminary pixels in the preliminary divided area;

[0029] The preliminary modulus variance of the preliminary color modulus in the preliminary color modulus set is calculated using the following formula:

[0030] ;

[0031] in, represents the preliminary modulus variance, represents the f-th preliminary color modulus;

[0032] Determining whether the preliminary modulus variance is greater than a preset standard modulus variance;

[0033] If the preliminary modulus variance is greater than the standard modulus variance, the minimum pixel point and the maximum pixel point of the preliminary divided area are identified, the minimum pixel point and the maximum pixel point are connected to obtain a pixel point connection line, and the preliminary divided area is divided based on the pixel point connection line to obtain a target divided area;

[0034] Taking the target divided area as a preliminary divided area picture, and returning to the step of sequentially extracting preliminary divided areas in the preliminary divided area picture;

[0035] If the preliminary modulus variance is not greater than the standard modulus variance, the calibration design image is updated using the preliminary divided regions to obtain an original region image;

[0036] The original regions are randomly extracted in the original region picture in sequence, the current extraction number is recorded, and the current extraction number is recorded as the region identifier. Based on the region identifier, the original region is marked to obtain the design region, wherein the design region is represented as:

[0037] ;

[0038] in, represents the design area, represents the original area, Indicates the area identifier;

[0039] The original region picture is updated using the designed region to obtain a designed region picture.

[0040] Optionally, the key-value pairing of the design color channel value and the design area to obtain the design area group includes:

[0041] The design color channel values ​​include: a design cyan value, a design magenta value, a design yellow value and a design black value, and the design color channel values ​​are expressed as:

[0042] ;

[0043] in, Indicates the design color channel value, represents the design cyan value, represents the design magenta value, Indicates the design yellow value, Indicates the design black value;

[0044] The design color channel value and the design area are paired to obtain a design area group, wherein the design area group is represented as:

[0045] ;

[0046] in, represents the design area group, Indicates the design area.

[0047] Optionally, performing area mapping division on the calibration printing image according to the design area image to obtain the printing area image includes:

[0048] Setting a neighborhood window value, and sequentially extracting printing pixels in the calibration printing image;

[0049] The printed pixel is recorded as the central pixel, and the central color channel value of the central pixel is obtained, wherein the central color channel value includes: a central cyan value, a central magenta value, a central yellow value and a central black value, and the central color channel values ​​are respectively expressed as:

[0050] ;

[0051] in, Represents the center color channel value, represents the central cyan value, represents the center magenta value, Indicates the center yellow value, Indicates the center black value;

[0052] Determine the filter center coordinates of the central pixel point, perform neighborhood division in the calibration printed image based on the filter center coordinates and the neighborhood window value, and obtain a neighborhood coordinate set, wherein the filter center coordinates and the neighborhood coordinate set are respectively expressed as:

[0053] ;

[0054] ;

[0055] in, represents the filter center coordinates, The horizontal coordinate represents the filter center coordinate, The ordinate represents the filter center coordinate, represents the neighborhood coordinate set, represents the neighborhood coordinates, represents the neighborhood horizontal coordinate, represents the neighborhood ordinate, i represents the index in the horizontal direction, and j represents the index in the vertical direction. Represents the neighborhood window value;

[0056] Identify a neighborhood color channel value set corresponding to the neighborhood coordinate set, and obtain a median color channel value of the neighborhood color channel value set, wherein the median color channel value includes: a median cyan value, a central magenta value, a median yellow value, and a median black value;

[0057] Using the median color channel value to update the center color channel value, to obtain a denoised printing pixel point;

[0058] The calibrated printed image is updated using the denoised printed pixels to obtain a denoised printed image;

[0059] The design areas are sequentially extracted from the design area image, and the area identifiers corresponding to the design areas are obtained. According to the design areas, the original printing areas are determined in the denoised printing image, and the original printing areas are marked by the area identifiers to obtain the printing areas, wherein the printing areas are represented as:

[0060] ;

[0061] in, Indicates the printing area, Indicates the original printing area;

[0062] The denoised printed image is updated using the printed area to obtain a printed area image.

[0063] Optionally, performing color deviation comparison on the printing area image according to the design area group set to obtain a color deviation value includes:

[0064] Acquire the printing color channel value of the printing area, perform key value pairing on the printing color channel and the printing area to obtain a printing area group, and summarize the printing area groups to obtain a printing area group set;

[0065] Extracting design area groups from the design area group set in sequence, obtaining design identifiers in the design area groups, using the design identifiers to perform identifier query in the printing area group set to obtain same-family identifiers, and obtaining same-family printing area groups corresponding to the same-family identifiers;

[0066] Extracting design color channel values ​​and printing color channel values ​​from the design area group and the same family printing area group respectively, wherein the printing color channel values ​​include: printing cyan value, printing red value, printing yellow value and printing black value;

[0067] Based on the design color channel value and the printing color channel value, the difference color channel value is calculated, wherein the printing color channel value and the difference color channel value are respectively expressed as:

[0068] ;

[0069] ;

[0070] in, Indicates the printing color channel value, Indicates the printing cyan value, Indicates the printed red value, Indicates the printing yellow value, Indicates the printing black value, Represents the difference color channel value;

[0071] According to the difference color channel value, the preset cyan visual coefficient, magenta visual coefficient, yellow visual coefficient and black visual coefficient, the color deviation value is calculated using the following formula:

[0072] ;

[0073] ;

[0074] ;

[0075] in, Indicates the color deviation value, represents the cyan visual coefficient, Represents the magenta visual coefficient, Indicates the yellow visual coefficient, Represents the black visual coefficient, represents the cyan difference, represents the magenta difference, Indicates the yellow difference, Indicates the black difference value.

[0076] Optionally, the color deviation determination is performed according to the color deviation value, the printing ink amount, the printing speed and the printing pressure to obtain a determination result group, including:

[0077] Determining whether the color deviation value is less than a preset standard difference value;

[0078] If the color deviation value is less than the standard difference value, the same family printing area group is recorded as a printing deviation group, and the printing deviation group is key-paired according to the printing ink amount, printing speed and printing pressure to obtain a deviation area group;

[0079] If the color deviation value is not less than the standard difference value, the same family printing area group is recorded as a normal printing group, and key value pairing is performed on the normal printing group according to the printing ink volume, printing speed and printing pressure to obtain a normal area group.

[0080] Optionally, the color deviation determination is performed according to the color deviation value, the printing ink amount, the printing speed and the printing pressure to obtain a determination result group, including:

[0081] Determining whether the color deviation value is less than a preset standard difference value;

[0082] If the color deviation value is less than the standard difference value, the same family printing area group is recorded as a printing deviation group, and the printing deviation group is key-paired according to the printing ink amount, printing speed and printing pressure to obtain a deviation area group;

[0083] If the color deviation value is not less than the standard difference value, the same family printing area group is recorded as a normal printing group, and key value pairing is performed on the normal printing group according to the printing ink volume, printing speed and printing pressure to obtain a normal area group.

[0084] Optionally, the method of constructing a machine learning model using the deviation region set and the normal region set to obtain a color deviation correction model includes:

[0085] The deviation region set and the normal region set are combined to obtain a learning region set, and the learning region set is divided into groups based on a preset learning division ratio to obtain a training region set, a verification region set, and a test region set;

[0086] A convolutional neural network model is selected, and the convolutional neural network model is trained using the training area set to obtain a training correction model; the training correction model is verified using the verification area set to obtain a verification correction model; and the verification correction model is tested using the test area set to obtain a color deviation correction model.

[0087] Optionally, performing ink printing adjustment on a printing press based on a color deviation correction model to obtain a corrected printing press includes:

[0088] Before starting the printing press, obtain the original printing ink volume, original printing speed and original printing pressure of the printing press;

[0089] Inputting the original printing ink volume, original printing speed and original printing pressure into a color deviation correction model to obtain a corrected printing ink volume, a corrected printing speed and a corrected printing pressure;

[0090] According to the corrected printing ink volume, the corrected printing speed and the corrected printing pressure, the parameters of the printing press are updated to obtain a corrected printing press.

[0091] To achieve the above object, the present invention also provides a color deviation correction system for a packaging printing process, comprising:

[0092] A design picture division module is used to obtain a packaging design picture, perform standard size calibration on the packaging design picture to obtain a calibrated design picture, perform color area division on the calibrated design picture to obtain a design area picture, extract design areas in the design area picture in sequence, identify design color channel values ​​of the design areas, perform key value pairing on the design color channel values ​​and the design areas to obtain design area groups, and summarize the design area groups to obtain a design area group set;

[0093] A printing image processing module is used to start a pre-built printing press and use the printing press to print the packaging design image to obtain a printed package, scan the printed package to obtain a printed package image, record the amount of printing ink, printing speed and printing pressure when the printing press prints the image, perform standard size calibration on the printed package image to obtain a calibrated printed image, and perform area mapping and division of the calibrated printed image according to the design area image to obtain a printed area image;

[0094] A color deviation calculation module is used to compare the color deviation of the printing area image according to the design area group set to obtain a color deviation value, and to determine the color deviation according to the color deviation value, the amount of printing ink, the printing speed and the printing pressure to obtain a determination result group, wherein the determination result group includes: a deviation area group and a normal area group, and the deviation area group and the normal area group are used to supplement the pre-constructed initial deviation set and the initial normal set respectively to obtain a deviation area group set and a normal area group set, and obtain the total number of area groups of the deviation area group set and the normal area group set;

[0095] The color deviation correction module is used to determine whether the total number of area groups is less than the preset number of standard area groups. If the total number of area groups is less than the standard number of area groups, the deviation area group set and the normal area group set are used to update the initial deviation set and the initial normal set respectively, and return to the step of starting the pre-built printing press and using the printing press to print the packaging design picture. If the total number of area groups is not less than the standard number of area groups, the deviation area group set and the normal area group set are used to construct a machine learning model to obtain a color deviation correction model, and the ink printing of the printing press is adjusted based on the color deviation correction model to obtain a calibrated printing press.

[0096] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0097] a memory storing at least one instruction; and

[0098] The processor executes the instructions stored in the memory to implement the color deviation correction method in the packaging printing process described above.

[0099] In order to solve the above problem, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the color deviation correction method for the packaging printing process described above.

[0100] In order to solve the problems described in the background technology, the present invention first obtains a packaging design picture, calibrates the packaging design picture to a standard size, and obtains a calibrated design picture, thereby ensuring that color deviation can be quickly identified when comparing packaging pictures. Next, the calibrated design picture is divided into color areas to obtain a design area picture. This step divides the calibrated design picture more finely, and groups areas of similar colors together, further paving the way for subsequent picture comparison. Design areas are extracted in the design area picture in turn, and design color channel values ​​of the design areas are identified. The design color channel values ​​and design areas are key-value paired to obtain a design area group, and the design area groups are summarized to obtain a design area group set, thereby improving the colors in the design area pictures. The information is obtained so that the color information of the relevant area can be quickly retrieved when the image is compared later, which simplifies the image comparison process and reduces the time of color correction. The printing press is started and the packaging design image is printed by the printing press to obtain the printed packaging, and the printed packaging is scanned to obtain the printed packaging image. The printing ink volume, printing speed and printing pressure when the printing press prints the image are recorded. This step completes the data recording of the printing press, and then the printed packaging image is calibrated to a standard size to obtain a calibrated printed image. The calibrated printed image is divided into regions according to the design area image to obtain a printed area image, thereby realizing the processing of the printed packaging image, so that the printed area image has the same structural size as the design area image. The area group set is used to compare color deviations and obtain color deviation values. According to the color deviation values, the printing area group is judged for color deviation to obtain a judgment result group. This step completes the color deviation identification in the printing process, and repeating this step can obtain a large amount of color deviation information. At the same time, since the design area group and the printing area group contain a large amount of processed color information, image comparison and identification can be performed quickly, which improves the intelligence level of the entire color correction and reduces the consumption of human resources. The deviation area group set and the normal area group set are supplemented with the initial deviation set and the initial normal set respectively to obtain the deviation area group set and the normal area group set. The obtained color deviation data are integrated to provide a data set for subsequent machine learning and obtain the deviation. The total number of area groups in the area group set and the normal area group set is determined to determine whether the total number of area groups is less than the standard number of area groups. This can determine whether enough deviation area groups and normal area groups have been obtained. If the total number of area groups is less than the standard number of area groups, it means that not enough deviation area groups and normal area groups have been obtained. The deviation area group set and the normal area group set are used to update the initial deviation set and the initial normal set respectively, and the step of starting the printing press is returned to realize the cyclic acquisition of the deviation area group and the normal area group. If the total number of area groups is not less than the standard number of area groups, it means that enough deviation area groups and normal area groups have been obtained. Then, the deviation area group set and the normal area group set are used to construct a machine learning model to obtain a color deviation correction model.Finally, the ink printing of the printing press is adjusted based on the color deviation correction model to obtain a corrected printing press, which realizes the intelligent correction of color deviation and reduces the time for correcting color deviation. Therefore, the present invention can improve the intelligence level of color deviation correction in the packaging printing process and reduce the excessive consumption of time and human resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0101] Figure 1 A schematic flow chart of a method for correcting color deviation in a packaging printing process provided by an embodiment of the present invention;

[0102] Figure 2 A functional module diagram of a color deviation correction system for a packaging printing process provided by an embodiment of the present invention;

[0103] Figure 3 A schematic diagram of the structure of an electronic device for implementing the color deviation correction method in the packaging printing process provided by an embodiment of the present invention.

[0104] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0105] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0106] The embodiment of the present application provides a color deviation correction method for a packaging printing process. The execution subject of the color deviation correction method for the packaging printing process includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the color deviation correction method for the packaging printing process can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0107] Reference Figure 1 FIG. 1 is a flow chart of a color deviation correction method for a packaging printing process provided by an embodiment of the present invention. In this embodiment, the color deviation correction method for a packaging printing process includes:

[0108] S1. Obtain a packaging design picture, perform standard size calibration on the packaging design picture to obtain a calibrated design picture, and perform color area division on the calibrated design picture to obtain a design area picture.

[0109] It is clear that the packaging design picture refers to a picture used to show the appearance of the product packaging. It is designed by the packaging appearance designer and will be used as a template for packaging printing in the future. The calibration design picture refers to the packaging design picture after the size is adjusted. The design area picture refers to the calibration design picture after the area is divided.

[0110] It should be explained that since the printed packaging needs to be scanned later to obtain the printed packaging image, and the printed packaging image needs to be compared with the packaging design image, in order to simplify the comparison process, the packaging design image and the printed packaging image need to be converted into images of the same size, and the orientation of the packaging design image and the printed packaging image needs to be corrected so that they can be accurately identified.

[0111] In detail, the step of calibrating the packaging design image to a standard size to obtain a calibrated design image includes:

[0112] Identifying blank edges in the packaging design image, and cropping the blank edges to obtain a cropped packaging design image;

[0113] Based on a preset standard picture size, the cropped packaging design picture is adjusted to obtain a standard packaging design picture;

[0114] The center point of the standard packaging design picture is determined, and the center point of the picture is recorded as the coordinate origin. According to the coordinate origin, a coordinate system is constructed for the standard packaging design picture to obtain a calibrated design picture.

[0115] It can be understood that the cropped packaging design image refers to the packaging design image after the blank edges are cropped, the standard image size refers to the image size set manually, the standard packaging design image refers to the cropped packaging design image after size adjustment, the image center point refers to the center of the standard packaging design image, and the image center point can be quickly located in the image processing software, and the calibrated design image refers to the standard packaging design image with a coordinate system added.

[0116] It should be explained that adjusting the cropped packaging design image means adjusting the size of the cropped packaging design image to the standard image size, wherein the adjustment method may be: scaling, setting values, etc. A coordinate system is constructed for the standard packaging design image, so that the corresponding area can be quickly and accurately found in the calibration design image when comparing the packaging printing image later.

[0117] In detail, the color area division of the calibration design image to obtain the design area image includes:

[0118] Performing preliminary artificial division on the calibration design image to obtain a preliminary division area image;

[0119] Sequentially extracting preliminary divided areas from the preliminary divided area picture;

[0120] Sequentially extract the preliminary pixel points in the preliminary divided area, identify the preliminary color channel values ​​of the preliminary pixel points, wherein the preliminary color channel values ​​are Color channel values ​​in a color space, the preliminary color channel values ​​comprising: a preliminary cyan value, a preliminary magenta value, a preliminary yellow value, and a preliminary black value;

[0121] According to the preliminary color channel value, the preliminary color modulus is calculated using the following formula:

[0122] ;

[0123] in, represents the preliminary color modulus, represents the initial cyan value, represents the preliminary magenta value, Indicates the preliminary yellow value, Indicates the preliminary black value;

[0124] The preliminary color moduli are summarized to obtain a preliminary color modulus set, which is expressed as:

[0125] ;

[0126] in, represents the preliminary color modulus set, represents the first preliminary color modulus, represents the nth preliminary color modulus, where n represents the number of preliminary pixels in the preliminary divided area;

[0127] The preliminary modulus variance of the preliminary color modulus in the preliminary color modulus set is calculated using the following formula:

[0128] ;

[0129] in, represents the preliminary modulus variance, represents the f-th preliminary color modulus;

[0130] Determining whether the preliminary modulus variance is greater than a preset standard modulus variance;

[0131] If the preliminary modulus variance is greater than the standard modulus variance, the minimum pixel point and the maximum pixel point of the preliminary divided area are identified, the minimum pixel point and the maximum pixel point are connected to obtain a pixel point connection line, and the preliminary divided area is divided based on the pixel point connection line to obtain a target divided area;

[0132] Taking the target divided area as a preliminary divided area picture, and returning to the step of sequentially extracting preliminary divided areas in the preliminary divided area picture;

[0133] If the preliminary modulus variance is not greater than the standard modulus variance, the calibration design image is updated using the preliminary divided regions to obtain an original region image;

[0134] The original regions are randomly extracted in the original region picture in sequence, the current extraction number is recorded, and the current extraction number is recorded as the region identifier. Based on the region identifier, the original region is marked to obtain the design region, wherein the design region is represented as:

[0135] ;

[0136] in, represents the design area, represents the original area, Indicates the area identifier;

[0137] The original region picture is updated using the designed region to obtain a designed region picture.

[0138] It can be understood that the preliminary divided area image refers to the calibration design image after artificial division, the preliminary pixel points refer to the pixel points in the preliminary divided area, the preliminary color modulus refers to the data representing the pixel value size of the preliminary pixel points calculated by the preliminary color channel value, and the standard modulus variance refers to the artificially set variance, which is used to determine whether the preliminary divided area needs to be further divided.

[0139] Furthermore, the minimum pixel point refers to the pixel point with the smallest preliminary color modulus in the preliminary divided area. The maximum pixel point refers to the pixel point with the largest preliminary color modulus in the preliminary divided area. The target divided area refers to the divided preliminary divided area. The original area image refers to the calibration design image after color area division, but the original area image has not been marked with areas, and the information of each area it contains is incomplete. The design area refers to the original area marked with area identification.

[0140] It should be explained that when dividing the calibration design image into color areas, it is first necessary to manually make a rough division of the calibration design image according to the color to ensure that the color of each preliminary divided area after the division is very similar to the human eye observation, and then identify the preliminary color modulus of each pixel point in each preliminary divided area, and calculate the preliminary modulus variance between these preliminary color moduli. If the preliminary modulus variance is smaller than the standard modulus variance, the preliminary divided area will not be processed. If the preliminary modulus variance is larger than the standard modulus variance, the two pixel points with the largest and smallest preliminary color modulus in the preliminary divided area are determined, and the preliminary divided area is cut with the line connecting these two pixel points as the cutting line. The preliminary divided area after cutting is taken as a whole, and the preliminary modulus variance is calculated again until the preliminary modulus variance is smaller than the standard modulus variance.

[0141] It is understandable that since the design area in the design area image obtained by color division will not retain very regular position information, the design area needs to be re-identified. Using the current number of extraction times to identify the design area not only ensures the uniqueness of the design area, but also simplifies the process of identifying the design area.

[0142] S2. Extracting design areas in the design area picture in sequence, identifying design color channel values ​​of the design areas, performing key-value pairing between the design color channel values ​​and the design areas to obtain design area groups, and summarizing the design area groups to obtain a design area group set.

[0143] It can be understood that the design color channel value refers to the average value of the CMYK color channel components of all pixels in the design area, wherein the CMYK color channel components refer to the cyan value, magenta value, yellow value and black value of the pixel in the CMYK color space. The design area group refers to the combination of the design color channel value and the design area.

[0144] It should be explained that by pairing the design color channel value with the design area by key value, the color data of the design area can be queried quickly enough to facilitate subsequent color comparison of the design area.

[0145] Specifically, the key-value pairing of the design color channel value and the design area to obtain the design area group includes:

[0146] The design color channel values ​​include: a design cyan value, a design magenta value, a design yellow value and a design black value, and the design color channel values ​​are expressed as:

[0147] ;

[0148] in, Indicates the design color channel value, represents the design cyan value, represents the design magenta value, Indicates the design yellow value, Indicates the design black value;

[0149] The design color channel value and the design area are paired to obtain a design area group, wherein the design area group is represented as:

[0150] ;

[0151] in, represents the design area group, Indicates the design area.

[0152] S3, start the pre-built printing machine and use the printing machine to print the packaging design picture to obtain a printed package, scan the printed package to obtain a printed package picture, and record the printing ink volume, printing speed and printing pressure when the printing machine prints the picture.

[0153] It can be understood that the printed packaging refers to the actual packaging printed by a printing press, the printed packaging image refers to the two-dimensional image of the printed packaging, the amount of printing ink refers to the amount of ink used in the printing process of the printing press, the printing speed refers to the number of packages printed by the printing press per minute, and the printing pressure refers to the pressure applied by the printing press to the paper during the printing process.

[0154] It should be explained that if the printing press and printing carrier are not replaced in a short period of time, the amount of printing ink, printing speed and printing pressure during printing will have the greatest impact on the color of the printed packaging image. Therefore, the amount of printing ink, printing speed and printing pressure during printing should be recorded for subsequent correction and adjustment.

[0155] S4, calibrating the printed packaging image to a standard size to obtain a calibrated printed image, and performing area mapping and division of the calibrated printed image according to the design area image to obtain a printed area image.

[0156] It is understood that the calibration printing image refers to the printing packaging image after the size is adjusted, wherein the size of the printing packaging image is the same as the size of the design packaging image. The printing area image refers to the calibration printing image after area division, wherein the printing area in the printing area image corresponds to the design area in the design area image.

[0157] It should be explained that since the printed packaging image is obtained by scanning the printed packaging, and during the scanning process of the printed packaging, it will be disturbed by the outside world, which will cause the printed packaging image to generate noise. Therefore, the printed packaging image needs to be filtered to reduce the error of subsequent image comparison.

[0158] In detail, the step of performing area mapping division on the calibration printing image according to the design area image to obtain the printing area image includes:

[0159] Setting a neighborhood window value, and sequentially extracting printing pixels in the calibration printing image;

[0160] The printed pixel is recorded as the central pixel, and the central color channel value of the central pixel is obtained, wherein the central color channel value includes: a central cyan value, a central magenta value, a central yellow value and a central black value, and the central color channel values ​​are respectively expressed as:

[0161] ;

[0162] in, Represents the center color channel value, represents the central cyan value, represents the center magenta value, Indicates the center yellow value, Indicates the center black value;

[0163] Determine the filter center coordinates of the central pixel point, perform neighborhood division in the calibration printed image based on the filter center coordinates and the neighborhood window value, and obtain a neighborhood coordinate set, wherein the filter center coordinates and the neighborhood coordinate set are respectively expressed as:

[0164] ;

[0165] ;

[0166] in, represents the filter center coordinates, The horizontal coordinate represents the filter center coordinate, The ordinate represents the filter center coordinate, represents the neighborhood coordinate set, represents the neighborhood coordinates, represents the neighborhood horizontal coordinate, represents the neighborhood ordinate, i represents the index in the horizontal direction, and j represents the index in the vertical direction. Represents the neighborhood window value;

[0167] Identify a neighborhood color channel value set corresponding to the neighborhood coordinate set, and obtain a median color channel value of the neighborhood color channel value set, wherein the median color channel value includes: a median cyan value, a central magenta value, a median yellow value, and a median black value;

[0168] Using the median color channel value to update the center color channel value, to obtain a denoised printing pixel point;

[0169] The calibrated printed image is updated using the denoised printed pixels to obtain a denoised printed image;

[0170] The design areas are sequentially extracted from the design area image, and the area identifiers corresponding to the design areas are obtained. According to the design areas, the original printing areas are determined in the denoised printing image, and the original printing areas are marked by the area identifiers to obtain the printing areas, wherein the printing areas are represented as:

[0171] ;

[0172] in, Indicates the printing area, Indicates the original printing area;

[0173] The denoised printed image is updated using the printed area to obtain a printed area image.

[0174] It can be understood that the neighborhood window value refers to a manually set constant, which represents the number of other coordinate points around a coordinate point, the printed pixel point refers to the pixel point in the calibration printed image, and the center color channel value refers to the center pixel point in the The cyan value, magenta value, yellow value and black value in the color space, the filter center coordinates refer to the coordinates of the center pixel point in the calibration print image, the neighborhood coordinate set refers to the set of N coordinates of N pixel points around the center pixel point, where N represents the neighborhood window value, and the neighborhood color channel value refers to the pixel point corresponding to the neighborhood coordinate in Cyan, magenta, yellow, and black values ​​in color space.

[0175] It can be understood that the median color channel refers to the median cyan value, median magenta value, median yellow value and median black value in the neighborhood color channel set, the denoised printing pixel refers to the printing pixel updated by the median color channel value, the denoised printing image refers to the calibrated printing image updated by the denoised printing pixel, the original printing area refers to the area in the denoised printing image that is the same as the design area position, wherein the design area position refers to the position of the design area in the design area image, and the printing area refers to the original printing area after area marking.

[0176] It should be explained that since both the design area image and the printing area image have been standardized and the coordinate systems added to the two are the same, when a design area is determined in the design area image, the design area position of this design area in the design area image can be identified, and then the same printing area position can be found in the printing area image. The printing area where the printing area position is located is the original printing area.

[0177] Exemplarily, a neighborhood color channel value set is: {[20% 30% 40% 50%], [10% 20% 30% 40%], [30% 40% 50% 60%]}, wherein the cyan values ​​are 20%, 10% and 30%, the magenta values ​​are 30%, 20% and 40%, the yellow values ​​are 40%, 30% and 50%, and the black values ​​are 50%, 40% and 60%, so the median cyan value, the median magenta value, the median yellow value and the median black value are 20%, 30%, 40% and 50%, respectively, so the median color channel value is: [20% 30% 40% 50%].

[0178] S5. According to the design area group set, perform color deviation comparison on the printing area image to obtain a color deviation value, and perform color deviation judgment on the printing area group according to the color deviation value to obtain a judgment result group, wherein the judgment result group includes: a deviation area group and a normal area group.

[0179] It can be understood that the color deviation value refers to data used to represent the color difference between the design area and the printing area, the deviation area group refers to a combination of a printing area whose color deviates from the design area and the amount of printing ink, printing speed and printing pressure, and the normal area group refers to a combination of a printing area whose color does not deviate from the design area and the amount of printing ink, printing speed and printing pressure.

[0180] Specifically, the color deviation comparison of the printing area image according to the design area group set to obtain the color deviation value includes:

[0181] Acquire the printing color channel value of the printing area, perform key value pairing on the printing color channel and the printing area to obtain a printing area group, and summarize the printing area groups to obtain a printing area group set;

[0182] Extracting design area groups from the design area group set in sequence, obtaining design identifiers in the design area groups, using the design identifiers to perform identifier query in the printing area group set to obtain same-family identifiers, and obtaining same-family printing area groups corresponding to the same-family identifiers;

[0183] Extracting design color channel values ​​and printing color channel values ​​from the design area group and the same family printing area group respectively, wherein the printing color channel values ​​include: printing cyan value, printing red value, printing yellow value and printing black value;

[0184] Based on the design color channel value and the printing color channel value, the difference color channel value is calculated, wherein the printing color channel value and the difference color channel value are respectively expressed as:

[0185] ;

[0186] ;

[0187] in, Indicates the printing color channel value, Indicates the printing cyan value, Indicates the printed red value, Indicates the printing yellow value, Indicates the printing black value, Represents the difference color channel value;

[0188] According to the difference color channel value, the preset cyan visual coefficient, magenta visual coefficient, yellow visual coefficient and black visual coefficient, the color deviation value is calculated using the following formula:

[0189] ;

[0190] ;

[0191] ;

[0192] in, Indicates the color deviation value, represents the cyan visual coefficient, Represents the magenta visual coefficient, Indicates the yellow visual coefficient, Represents the black visual coefficient, represents the cyan difference, represents the magenta difference, Indicates the yellow difference, Indicates the black difference value.

[0193] It can be understood that the printing color channel value refers to the average color channel value of all pixels in the printing area, wherein the average color channel value includes: average cyan value, average magenta value, average yellow value and average black value; the printing area group refers to a combination of a printing area and a printing color channel value; the design identifier refers to an area identifier in a design area group; the same family identifier refers to an area identifier that is the same as the design identifier and appears in a printing area group set; the same family printing area group refers to a printing area group whose area identifier is a same family identifier in a printing area group set; the difference color channel refers to the difference between the design color channel value and the printing color channel value; the cyan visual coefficient, magenta visual coefficient, yellow visual coefficient and black visual coefficient respectively refer to constants artificially set to represent the sensitivity of the human eye to cyan, magenta, yellow and black.

[0194] It should be explained that since the human eye has different perceptions of cyan, magenta, yellow and black, the weights of different colors for color deviation values ​​must be considered when identifying color deviations. Therefore, the cyan visual coefficient, magenta visual coefficient, yellow visual coefficient and black visual coefficient are introduced to weight the different colors in the calculation formula so that the results are more in line with human eye observations.

[0195] In detail, the color deviation determination is performed according to the color deviation value, the printing ink amount, the printing speed and the printing pressure to obtain a determination result group, including:

[0196] Determining whether the color deviation value is less than a preset standard difference value;

[0197] If the color deviation value is less than the standard difference value, the same family printing area group is recorded as a printing deviation group, and the printing deviation group is key-paired according to the printing ink amount, printing speed and printing pressure to obtain a deviation area group;

[0198] If the color deviation value is not less than the standard difference value, the same family printing area group is recorded as a normal printing group, and key value pairing is performed on the normal printing group according to the printing ink volume, printing speed and printing pressure to obtain a normal area group.

[0199] It should be explained that, during the printing process, the amount of printing ink, printing speed and printing pressure of the printing press have a great influence on the color of the printed area, so the determination result group needs to include the amount of printing ink, printing speed and printing pressure.

[0200] S6. Supplement the pre-constructed initial deviation set and initial normal set with the deviation region group and the normal region group respectively to obtain a deviation region group set and a normal region group set, and obtain the total number of region groups of the deviation region group set and the normal region group set.

[0201] It can be understood that the initial deviation set refers to a set storing deviation area groups, and the initial normal set refers to a set storing normal area groups, wherein when the initial deviation set and the initial normal set are just constructed, the initial deviation set and the initial normal set are both empty sets. The deviation area group set refers to the initial deviation set filled with deviation area groups, and the normal area group set refers to the initial normal set filled with normal area groups. The total number of area groups refers to the total number of deviation area groups in the deviation area group set and the total number of normal area groups in the normal area group set.

[0202] S7. Determine whether the total number of area groups is less than a preset standard number of area groups.

[0203] It is clear that the standard area group number refers to the total number of deviation area groups and normal area groups set manually. Since a large number of deviation area groups and normal area groups are required for subsequent machine learning, it is necessary to repeatedly collect deviation area groups and normal area groups until the total area group number is not less than the standard area group number.

[0204] If the total number of area groups is less than the standard number of area groups, then S8 is executed to update the initial deviation set and the initial normal set respectively using the deviation area group set and the normal area group set, and then the process returns to the step of starting the pre-built printing press.

[0205] It should be explained that when the total number of region groups is less than the standard number of region groups, it means that the currently obtained deviation region group set and normal region group set cannot meet the data set required for the subsequent construction of the machine learning model, so the printing press is started again to obtain more deviation region groups and normal region groups.

[0206] If the total number of area groups is not less than the number of standard area groups, execute S9, use the deviation area group set and the normal area group set to build a machine learning model, obtain a color deviation correction model, adjust the ink printing of the printing press based on the color deviation correction model, obtain a calibrated printing press, and complete the color deviation correction of the packaging printing process.

[0207] It can be understood that the color deviation correction model refers to a model obtained by learning a large number of deviation area groups and normal area groups, which can adjust the printing ink amount, printing speed and printing pressure of the printing press, and the correction printing press refers to the printing press after adjustment, wherein the machine learning models that can be selected are: convolutional neural network model or random forest model, etc.

[0208] It should be explained that before starting the printing press, the original printing ink amount, original printing speed and original printing pressure of the printing press are input into the color deviation correction model, and the corrected printing ink amount, corrected printing speed and corrected printing pressure can be obtained, and the printing press is adjusted according to the corrected printing ink amount, corrected printing speed and corrected printing pressure.

[0209] In detail, the method of constructing a machine learning model using the deviation region set and the normal region set to obtain a color deviation correction model includes:

[0210] The deviation region set and the normal region set are combined to obtain a learning region set, and the learning region set is divided into groups based on a preset learning division ratio to obtain a training region set, a verification region set, and a test region set;

[0211] A convolutional neural network model is selected, and the convolutional neural network model is trained using the training area set to obtain a training correction model; the training correction model is verified using the verification area set to obtain a verification correction model; and the verification correction model is tested using the test area set to obtain a color deviation correction model.

[0212] It can be understood that the learning area group refers to the union of the deviation area group and the normal area group, the learning division ratio refers to an artificially set proportional constant used to perform set division on the learning area group, the training area group refers to the learning area group used to train the convolutional neural network model, the verification area group refers to the learning area group used to verify the training correction model, and the test area group refers to the learning area group used to test the verification correction model.

[0213] It should be explained that the convolutional neural network refers to a deep learning model, the training correction model refers to a convolutional neural network model trained by a training area set, and the verification correction model refers to a training correction model verified by a verification area set.

[0214] In detail, the ink printing adjustment of the printing press based on the color deviation correction model to obtain a corrected printing press includes:

[0215] Before starting the printing press, obtain the original printing ink volume, original printing speed and original printing pressure of the printing press;

[0216] Inputting the original printing ink volume, original printing speed and original printing pressure into a color deviation correction model to obtain a corrected printing ink volume, a corrected printing speed and a corrected printing pressure;

[0217] According to the corrected printing ink volume, the corrected printing speed and the corrected printing pressure, the parameters of the printing press are updated to obtain a corrected printing press.

[0218] It can be understood that the original printing ink amount, original printing speed and original printing pressure respectively refer to the printing ink amount, printing speed and printing pressure manually set before the printing machine prints the package, and the corrected printing ink amount, corrected printing speed and corrected printing pressure respectively refer to the printing ink amount, printing speed and printing pressure that the printing machine should set after calculation by the color deviation correction model.

[0219] In order to solve the problems described in the background technology, the present invention first obtains a packaging design picture, calibrates the packaging design picture to a standard size, and obtains a calibrated design picture, thereby ensuring that color deviation can be quickly identified when comparing packaging pictures. Next, the calibrated design picture is divided into color areas to obtain a design area picture. This step divides the calibrated design picture more finely, and groups areas of similar colors together, further paving the way for subsequent picture comparison. Design areas are extracted in the design area picture in turn, and design color channel values ​​of the design areas are identified. The design color channel values ​​and design areas are key-value paired to obtain a design area group, and the design area groups are summarized to obtain a design area group set, thereby improving the colors in the design area pictures. The information is obtained so that the color information of the relevant area can be quickly retrieved when the image is compared later, which simplifies the image comparison process and reduces the time of color correction. The printing press is started and the packaging design image is printed by the printing press to obtain the printed packaging, and the printed packaging is scanned to obtain the printed packaging image. The printing ink volume, printing speed and printing pressure when the printing press prints the image are recorded. This step completes the data recording of the printing press, and then the printed packaging image is calibrated to a standard size to obtain a calibrated printed image. The calibrated printed image is divided into regions according to the design area image to obtain a printed area image, thereby realizing the processing of the printed packaging image, so that the printed area image has the same structural size as the design area image. The area group set is used to compare color deviations and obtain color deviation values. According to the color deviation values, the printing area group is judged for color deviation to obtain a judgment result group. This step completes the color deviation identification in the printing process, and repeating this step can obtain a large amount of color deviation information. At the same time, since the design area group and the printing area group contain a large amount of processed color information, image comparison and identification can be performed quickly, which improves the intelligence level of the entire color correction and reduces the consumption of human resources. The deviation area group set and the normal area group set are supplemented with the initial deviation set and the initial normal set respectively to obtain the deviation area group set and the normal area group set. The obtained color deviation data are integrated to provide a data set for subsequent machine learning and obtain the deviation. The total number of area groups in the area group set and the normal area group set is determined to determine whether the total number of area groups is less than the standard number of area groups. This can determine whether enough deviation area groups and normal area groups have been obtained. If the total number of area groups is less than the standard number of area groups, it means that not enough deviation area groups and normal area groups have been obtained. The deviation area group set and the normal area group set are used to update the initial deviation set and the initial normal set respectively, and the step of starting the printing press is returned to realize the cyclic acquisition of the deviation area group and the normal area group. If the total number of area groups is not less than the standard number of area groups, it means that enough deviation area groups and normal area groups have been obtained. Then, the deviation area group set and the normal area group set are used to construct a machine learning model to obtain a color deviation correction model.Finally, the ink printing of the printing press is adjusted based on the color deviation correction model to obtain a corrected printing press, which realizes the intelligent correction of color deviation and reduces the time for correcting color deviation. Therefore, the present invention can improve the intelligence level of color deviation correction in the packaging printing process and reduce the excessive consumption of time and human resources.

[0220] like Figure 2 , which is a functional module diagram of a color deviation correction system for a packaging printing process provided by an embodiment of the present invention.

[0221] The color deviation correction system 100 for packaging printing process of the present invention can be installed in an electronic device. According to the functions to be implemented, the color deviation correction system 100 for packaging printing process can include a design image division module 101, a printing image processing module 102, a color deviation calculation module 103 and a color deviation correction module 104. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by a processor of an electronic device and can complete fixed functions, which are stored in the memory of the electronic device.

[0222] The design picture division module 101 is used to obtain a packaging design picture, perform standard size calibration on the packaging design picture to obtain a calibrated design picture, perform color area division on the calibrated design picture to obtain a design area picture, extract design areas in the design area picture in sequence, identify design color channel values ​​of the design areas, perform key value pairing on the design color channel values ​​and the design areas to obtain design area groups, and summarize the design area groups to obtain a design area group set;

[0223] The printed image processing module 102 is used to start a pre-built printing press and use the printing press to print the packaging design image to obtain a printed package, scan the printed package to obtain a printed package image, record the amount of printing ink, printing speed and printing pressure when the printing press prints the image, calibrate the printed package image to a standard size to obtain a calibrated printed image, and perform area mapping and division of the calibrated printed image according to the design area image to obtain a printed area image;

[0224] The color deviation calculation module 103 is used to compare the color deviation of the printing area image according to the design area group set to obtain the color deviation value, and to determine the color deviation according to the color deviation value, the amount of printing ink, the printing speed and the printing pressure to obtain a determination result group, wherein the determination result group includes: a deviation area group and a normal area group, and the deviation area group and the normal area group are used to supplement the pre-constructed initial deviation set and the initial normal set respectively to obtain a deviation area group set and a normal area group set, and obtain the total number of area groups of the deviation area group set and the normal area group set;

[0225] The color deviation correction module 104 is used to determine whether the total number of area groups is less than the preset number of standard area groups. If the total number of area groups is less than the standard number of area groups, the deviation area group set and the normal area group set are used to update the initial deviation set and the initial normal set respectively, and return to the step of starting the pre-built printing press and using the printing press to print the packaging design picture. If the total number of area groups is not less than the standard number of area groups, the deviation area group set and the normal area group set are used to construct a machine learning model to obtain a color deviation correction model, and the ink printing of the printing press is adjusted based on the color deviation correction model to obtain a calibrated printing press.

[0226] In detail, the modules in the color deviation correction system 100 for the packaging printing process in the embodiment of the present invention are used in the same manner as described above. Figure 1 The color deviation correction method for the packaging printing process described in the above is the same technical means and can produce the same technical effect, so it will not be repeated here.

[0227] like Figure 3 FIG. 1 is a schematic diagram of the structure of an electronic device for implementing a color deviation correction method in a packaging printing process provided by an embodiment of the present invention.

[0228] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a color deviation correction method program for a packaging printing process.

[0229] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 also includes an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the color deviation correction method program in the packaging printing process, but also can be used to temporarily store data that has been output or is to be output.

[0230] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (such as a color deviation correction method program for a packaging printing process, etc.), and calls data stored in the memory 11, so as to execute various functions of the electronic device 1 and process data.

[0231] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0232] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0233] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management system, so that the power management system can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0234] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0235] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0236] The color deviation correction method program for the packaging printing process stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve:

[0237] Acquire a packaging design picture, perform standard size calibration on the packaging design picture to obtain a calibrated design picture, and perform color area division on the calibrated design picture to obtain a design area picture;

[0238] Extracting design areas in the design area picture in sequence, identifying design color channel values ​​of the design areas, performing key-value pairing between the design color channel values ​​and the design areas to obtain design area groups, and summarizing the design area groups to obtain a design area group set;

[0239] Starting a pre-built printing press and using the printing press to print a packaging design picture to obtain a printed package, scanning the printed package to obtain a printed package picture, and recording the amount of printing ink, printing speed, and printing pressure when the printing press prints the picture;

[0240] Performing standard size calibration on the printed packaging image to obtain a calibrated printed image, and performing area mapping division on the calibrated printed image according to the design area image to obtain a printed area image;

[0241] According to the design area group set, the printing area image is compared for color deviation to obtain a color deviation value, and the color deviation is determined according to the color deviation value, the amount of printing ink, the printing speed and the printing pressure to obtain a determination result group, wherein the determination result group includes: a deviation area group and a normal area group;

[0242] The deviation region group and the normal region group are used to supplement the pre-constructed initial deviation set and the initial normal set respectively, to obtain the deviation region group set and the normal region group set, and to obtain the total number of region groups of the deviation region group set and the normal region group set;

[0243] Determining whether the total number of area groups is less than a preset standard number of area groups;

[0244] If the total number of area groups is less than the standard number of area groups, the initial deviation set and the initial normal set are updated respectively using the deviation area group set and the normal area group set, and the process returns to the step of starting the pre-built printer and using the printer to print the packaging design image;

[0245] If the total number of area groups is not less than the standard number of area groups, the deviation area group set and the normal area group set are used to construct a machine learning model to obtain a color deviation correction model. The ink printing of the printing press is adjusted based on the color deviation correction model to obtain a calibrated printing press, thereby completing the color deviation correction of the packaging printing process.

[0246] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0247] Furthermore, if the module / unit integrated in the electronic device 1 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. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or system that can carry the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0248] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0249] Acquire a packaging design picture, perform standard size calibration on the packaging design picture to obtain a calibrated design picture, and perform color area division on the calibrated design picture to obtain a design area picture;

[0250] Extracting design areas in the design area picture in sequence, identifying design color channel values ​​of the design areas, performing key-value pairing between the design color channel values ​​and the design areas to obtain design area groups, and summarizing the design area groups to obtain a design area group set;

[0251] Starting a pre-built printing press and using the printing press to print a packaging design picture to obtain a printed package, scanning the printed package to obtain a printed package picture, and recording the amount of printing ink, printing speed, and printing pressure when the printing press prints the picture;

[0252] Performing standard size calibration on the printed packaging image to obtain a calibrated printed image, and performing area mapping division on the calibrated printed image according to the design area image to obtain a printed area image;

[0253] According to the design area group set, the printing area image is compared for color deviation to obtain a color deviation value, and the color deviation is determined according to the color deviation value, the amount of printing ink, the printing speed and the printing pressure to obtain a determination result group, wherein the determination result group includes: a deviation area group and a normal area group;

[0254] The deviation region group and the normal region group are used to supplement the pre-constructed initial deviation set and the initial normal set respectively, to obtain the deviation region group set and the normal region group set, and to obtain the total number of region groups of the deviation region group set and the normal region group set;

[0255] Determining whether the total number of area groups is less than a preset standard number of area groups;

[0256] If the total number of area groups is less than the standard number of area groups, the initial deviation set and the initial normal set are updated respectively using the deviation area group set and the normal area group set, and the process returns to the step of starting the pre-built printer and using the printer to print the packaging design image;

[0257] If the total number of area groups is not less than the standard number of area groups, the deviation area group set and the normal area group set are used to construct a machine learning model to obtain a color deviation correction model. The ink printing of the printing press is adjusted based on the color deviation correction model to obtain a calibrated printing press, thereby completing the color deviation correction of the packaging printing process.

[0258] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, and actual implementation may have other division methods.

[0259] The modules described as separate components may or may not be physically separated, and the components shown as modules 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 modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0260] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0261] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0262] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A color deviation correction method for packaging printing process, characterized in that: The method comprises: Acquire a packaging design picture, perform standard size calibration on the packaging design picture to obtain a calibrated design picture, and perform color area division on the calibrated design picture to obtain a design area picture; Extracting design areas in the design area picture in sequence, identifying design color channel values ​​of the design areas, performing key-value pairing between the design color channel values ​​and the design areas to obtain design area groups, and summarizing the design area groups to obtain a design area group set; Starting a pre-built printing press and using the printing press to print a packaging design picture to obtain a printed package, scanning the printed package to obtain a printed package picture, and recording the amount of printing ink, printing speed, and printing pressure when the printing press prints the picture; Performing standard size calibration on the printed packaging image to obtain a calibrated printed image, and performing area mapping division on the calibrated printed image according to the design area image to obtain a printed area image; According to the design area group set, the printing area image is compared for color deviation to obtain a color deviation value, and the color deviation is determined according to the color deviation value, the amount of printing ink, the printing speed and the printing pressure to obtain a determination result group, wherein the determination result group includes: a deviation area group and a normal area group; The deviation region group and the normal region group are used to supplement the pre-constructed initial deviation set and the initial normal set respectively, to obtain the deviation region group set and the normal region group set, and to obtain the total number of region groups of the deviation region group set and the normal region group set; Determining whether the total number of area groups is less than a preset standard number of area groups; If the total number of area groups is less than the standard number of area groups, the initial deviation set and the initial normal set are updated respectively using the deviation area group set and the normal area group set, and the process returns to the step of starting the pre-built printer and using the printer to print the packaging design image; If the total number of area groups is not less than the number of standard area groups, the deviation area group set and the normal area group set are used to construct a machine learning model to obtain a color deviation correction model; The ink printing of the printing press is adjusted based on the color deviation correction model to obtain a corrected printing press, including: Before starting the printing press, obtain the original printing ink volume, original printing speed and original printing pressure of the printing press; Inputting the original printing ink volume, original printing speed and original printing pressure into a color deviation correction model to obtain a corrected printing ink volume, a corrected printing speed and a corrected printing pressure; According to the corrected printing ink volume, corrected printing speed and corrected printing pressure, the parameters of the printing press are updated to obtain a corrected printing press, thereby completing the color deviation correction in the packaging printing process.

2. The color deviation correction method in the packaging printing process according to claim 1, characterized in that: The step of calibrating the packaging design image to a standard size to obtain a calibrated design image includes: Identifying blank edges in the packaging design image, and cropping the blank edges to obtain a cropped packaging design image; Based on a preset standard picture size, adjusting the cropped packaging design picture to obtain a standard packaging design picture; The center point of the standard packaging design picture is determined, and the center point of the picture is recorded as the coordinate origin. According to the coordinate origin, a coordinate system is constructed for the standard packaging design picture to obtain a calibrated design picture.

3. The color deviation correction method in the packaging printing process according to claim 2, characterized in that: The step of dividing the calibration design image into color regions to obtain a design region image includes: Performing preliminary artificial division on the calibration design image to obtain a preliminary division area image; Sequentially extracting preliminary divided areas from the preliminary divided area picture; Sequentially extract the preliminary pixel points in the preliminary divided area, identify the preliminary color channel values ​​of the preliminary pixel points, wherein the preliminary color channel values ​​are Color channel values ​​in a color space, the preliminary color channel values ​​comprising: a preliminary cyan value, a preliminary magenta value, a preliminary yellow value, and a preliminary black value; According to the preliminary color channel value, the preliminary color modulus is calculated using the following formula: ； in, represents the preliminary color modulus, represents the initial cyan value, represents the preliminary magenta value, Indicates the preliminary yellow value, Indicates the preliminary black value; The preliminary color moduli are summarized to obtain a preliminary color modulus set, which is expressed as: ； in, represents the preliminary color modulus set, represents the first preliminary color modulus, represents the nth preliminary color modulus, where n represents the number of preliminary pixels in the preliminary divided area; The preliminary modulus variance of the preliminary color modulus in the preliminary color modulus set is calculated using the following formula: ； in, represents the preliminary modulus variance, represents the f-th preliminary color modulus; Determining whether the preliminary modulus variance is greater than a preset standard modulus variance; If the preliminary modulus variance is greater than the standard modulus variance, the minimum pixel point and the maximum pixel point of the preliminary divided area are identified, the minimum pixel point and the maximum pixel point are connected to obtain a pixel point connection line, and the preliminary divided area is divided based on the pixel point connection line to obtain a target divided area; Taking the target divided area as a preliminary divided area picture, and returning to the step of sequentially extracting preliminary divided areas in the preliminary divided area picture; If the preliminary modulus variance is not greater than the standard modulus variance, the calibration design image is updated using the preliminary divided regions to obtain an original region image; The original regions are randomly extracted in the original region picture in sequence, the current extraction number is recorded, and the current extraction number is recorded as the region identifier. Based on the region identifier, the original region is marked to obtain the design region, wherein the design region is represented as: ； in, represents the design area, represents the original area, Indicates the area identifier; The original region picture is updated using the designed region to obtain a designed region picture.

4. The color deviation correction method in the packaging printing process according to claim 3, characterized in that: The design color channel value and the design area are key-paired to obtain a design area group, include: The design color channel values ​​include: a design cyan value, a design magenta value, a design yellow value and a design black value, and the design color channel values ​​are expressed as: ； in, Indicates the design color channel value, represents the design cyan value, represents the design magenta value, Indicates the design yellow value, Indicates the design black value; The design color channel value and the design area are paired to obtain a design area group, wherein the design area group is represented as: ； in, represents the design area group, Indicates the design area.

5. The color deviation correction method in the packaging printing process according to claim 4, characterized in that: The step of performing area mapping division on the calibration printing image according to the design area image to obtain the printing area image includes: Setting a neighborhood window value, and sequentially extracting printing pixels in the calibration printing image; The printed pixel is recorded as the central pixel, and the central color channel value of the central pixel is obtained, wherein the central color channel value includes: a central cyan value, a central magenta value, a central yellow value and a central black value, and the central color channel values ​​are respectively expressed as: ； in, Represents the center color channel value, represents the central cyan value, represents the center magenta value, Indicates the center yellow value, Indicates the center black value; Determine the filter center coordinates of the central pixel point, perform neighborhood division in the calibration printed image based on the filter center coordinates and the neighborhood window value, and obtain a neighborhood coordinate set, wherein the filter center coordinates and the neighborhood coordinate set are respectively expressed as: ； ； in, represents the filter center coordinates, The horizontal coordinate represents the filter center coordinate, The ordinate represents the filter center coordinate, represents the neighborhood coordinate set, represents the neighborhood coordinates, represents the neighborhood horizontal coordinate, represents the neighborhood ordinate, i represents the index in the horizontal direction, and j represents the index in the vertical direction. Represents the neighborhood window value; Identify a neighborhood color channel value set corresponding to the neighborhood coordinate set, and obtain a median color channel value of the neighborhood color channel value set, wherein the median color channel value includes: a median cyan value, a central magenta value, a median yellow value, and a median black value; Using the median color channel value to update the center color channel value, to obtain a denoised printing pixel point; The calibrated printed image is updated using the denoised printed pixels to obtain a denoised printed image; The design areas are sequentially extracted from the design area image, and the area identifiers corresponding to the design areas are obtained. According to the design areas, the original printing areas are determined in the denoised printing image, and the original printing areas are marked by the area identifiers to obtain the printing areas, wherein the printing areas are represented as: ； in, Indicates the printing area, Indicates the original printing area; The denoised printed image is updated using the printed area to obtain a printed area image.

6. The color deviation correction method in the packaging printing process according to claim 5, characterized in that: The step of performing color deviation comparison on the printing area image according to the design area group set to obtain a color deviation value includes: Acquire the printing color channel value of the printing area, perform key value pairing on the printing color channel and the printing area to obtain a printing area group, and summarize the printing area groups to obtain a printing area group set; Extracting design area groups from the design area group set in sequence, obtaining design identifiers in the design area groups, using the design identifiers to perform identifier query in the printing area group set to obtain same-family identifiers, and obtaining same-family printing area groups corresponding to the same-family identifiers; Extracting design color channel values ​​and printing color channel values ​​from the design area group and the same family printing area group respectively, wherein the printing color channel values ​​include: printing cyan value, printing red value, printing yellow value and printing black value; Based on the design color channel value and the printing color channel value, the difference color channel value is calculated, wherein the printing color channel value and the difference color channel value are respectively expressed as: ； ； in, Indicates the printing color channel value, Indicates the printing cyan value, Indicates the printed red value, Indicates the printing yellow value, Indicates the printing black value, Represents the difference color channel value; According to the difference color channel value, the preset cyan visual coefficient, magenta visual coefficient, yellow visual coefficient and black visual coefficient, the color deviation value is calculated using the following formula: ； ； ； in, Indicates the color deviation value, represents the cyan visual coefficient, Represents the magenta visual coefficient, Indicates the yellow visual coefficient, Represents the black visual coefficient, represents the cyan difference, represents the magenta difference, Indicates the yellow difference, Indicates the black difference value.

7. The color deviation correction method in the packaging printing process according to claim 6, characterized in that: The color deviation is determined according to the color deviation value, the printing ink amount, the printing speed and the printing pressure to obtain a determination result group, including: Determining whether the color deviation value is less than a preset standard difference value; If the color deviation value is less than the standard difference value, the same family printing area group is recorded as a printing deviation group, and the printing deviation group is key-paired according to the printing ink amount, printing speed and printing pressure to obtain a deviation area group; If the color deviation value is not less than the standard difference value, the same family printing area group is recorded as a normal printing group, and key value pairing is performed on the normal printing group according to the printing ink volume, printing speed and printing pressure to obtain a normal area group.

8. The color deviation correction method in the packaging printing process according to claim 7, characterized in that: The method of constructing a machine learning model using the deviation region set and the normal region set to obtain a color deviation correction model includes: The deviation region set and the normal region set are combined to obtain a learning region set, and the learning region set is divided into groups based on a preset learning division ratio to obtain a training region set, a verification region set, and a test region set; A convolutional neural network model is selected, and the convolutional neural network model is trained using the training area set to obtain a training correction model; the training correction model is verified using the verification area set to obtain a verification correction model; and the verification correction model is tested using the test area set to obtain a color deviation correction model.

9. A color deviation correction system for packaging printing process, characterized in that: The system comprises: A design picture division module is used to obtain a packaging design picture, perform standard size calibration on the packaging design picture to obtain a calibrated design picture, perform color area division on the calibrated design picture to obtain a design area picture, extract design areas in the design area picture in sequence, identify design color channel values ​​of the design areas, perform key value pairing on the design color channel values ​​and the design areas to obtain design area groups, and summarize the design area groups to obtain a design area group set; A printing image processing module is used to start a pre-built printing press and use the printing press to print the packaging design image to obtain a printed package, scan the printed package to obtain a printed package image, record the amount of printing ink, printing speed and printing pressure when the printing press prints the image, perform standard size calibration on the printed package image to obtain a calibrated printed image, and perform area mapping and division of the calibrated printed image according to the design area image to obtain a printed area image; A color deviation calculation module is used to compare the color deviation of the printing area image according to the design area group set to obtain a color deviation value, and to determine the color deviation according to the color deviation value, the amount of printing ink, the printing speed and the printing pressure to obtain a determination result group, wherein the determination result group includes: a deviation area group and a normal area group, and the deviation area group and the normal area group are used to supplement the pre-constructed initial deviation set and the initial normal set respectively to obtain a deviation area group set and a normal area group set, and obtain the total number of area groups of the deviation area group set and the normal area group set; A color deviation correction module is used to determine whether the total number of area groups is less than a preset number of standard area groups. If the total number of area groups is less than the standard number of area groups, the initial deviation set and the initial normal set are updated respectively by using the deviation area group set and the normal area group set, and the process returns to the step of starting the pre-built printer and using the printer to print the packaging design image. If the total number of area groups is not less than the standard number of area groups, the deviation area group set and the normal area group set are used to construct a machine learning model to obtain a color deviation correction model, and the ink printing adjustment of the printer is performed based on the color deviation correction model to obtain a corrected printer, including: Before starting the printing press, obtain the original printing ink volume, original printing speed and original printing pressure of the printing press; Inputting the original printing ink volume, original printing speed and original printing pressure into a color deviation correction model to obtain a corrected printing ink volume, a corrected printing speed and a corrected printing pressure; According to the corrected printing ink volume, the corrected printing speed and the corrected printing pressure, the parameters of the printing press are updated to obtain a corrected printing press.

Images