Digital printing quality analysis system based on machine vision

Abstract

The invention relates to the technical field of digital printing, in particular to a digital printing quality analysis system based on machine vision, which comprises the steps of constructing an ink jet concentration model based on color features and historical ink jet concentration in a sample image of historical digital printing, inputting the color features of a real-time image into the ink jet concentration model, and analyzing the color features of the real-time image. Outputting the real-time ink jet concentration of each sub-region of the real-time image; according to the real-time ink jet concentration of the sub-region, judging whether the space ink jet of the ink jet concentration of the sub-region is uniform or not, and if not, identifying the non-uniform distribution degree of the space ink jet concentration; if the non-uniform degree of spatial ink jet is high, the ink jet concentrations of all the sub-regions are integrated into a sub-region ink jet concentration empty sequence according to spatial positions, the real-time ink jet concentrations of the sub-regions in the ink jet concentration empty sequence are analyzed, and a spatial ink jet power compensation value is determined. The problem of non-uniform ink jetting is solved, and the printing quality of digital printing objects is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of digital printing, and in particular to a digital printing quality analysis system based on machine vision. Background Art

[0002] Digital printing has been widely used in the printing industry due to its advantages such as no need for plate making and personalized printing. As a modern printing method, it has significant advantages in printing efficiency and flexibility.

[0003] However, in the actual production process, digital printing is prone to various quality problems, among which the influence of inkjet concentration on digital printing is particularly prominent. The existing technology has a single detection dimension in the detection of inkjet concentration in the digital printing process, and thus cannot evaluate the quality of digital printing. In the spatial dimension, it cannot accurately analyze the distribution and uniformity of inkjet concentration in each sub-area; in the temporal dimension, it ignores the stability change of inkjet concentration over time, which makes it impossible to timely discover and solve the problem of printing quality fluctuation caused by changes in inkjet concentration.

[0004] To this end, we propose a digital printing quality analysis system based on machine vision. Summary of the invention

[0005] The object of the present invention is to provide a digital printing quality analysis system based on machine vision to solve at least one of the above-mentioned problems in the prior art.

[0006] The present invention provides a digital printing quality analysis system based on machine vision, comprising:

[0007] Data acquisition module: Based on the color features of the sample images of historical digital printing and the historical inkjet concentration, an inkjet concentration model is constructed, the color features of the real-time image are input into the inkjet concentration model, and the real-time inkjet concentration of each sub-area of ​​the real-time image is output;

[0008] Inkjet uniformity judgment module: judge whether the inkjet density of the sub-area is uniform in space according to the real-time inkjet density of the sub-area. If it is not uniform, identify the degree of uneven distribution of the spatial inkjet density.

[0009] Spatial dimension power compensation module: If the spatial inkjet unevenness is high, the inkjet concentrations of all sub-areas are integrated into a sub-area inkjet concentration spatial sequence according to their spatial positions. The real-time inkjet concentrations of the sub-areas in the inkjet concentration spatial sequence are analyzed to determine the spatial inkjet power compensation value, and to regulate the inkjet power of the digital printing machine during inkjet.

[0010] As a further solution of the present invention: it also includes:

[0011] Inkjet stability analysis module: if the spatial inkjet non-uniformity is low, identify whether the inkjet concentration of the sub-area is stable within the analysis period;

[0012] Time dimension power compensation module: If it is unstable, the time inkjet power compensation value is determined according to the inkjet concentration of the sub-area within the analysis period, and the inkjet power of the digital printing machine is regulated during inkjet.

[0013] As a further solution of the present invention: the process of obtaining the real-time inkjet concentration of the sub-area is:

[0014] Obtain color features of sample images of historical digital printing and historical inkjet concentration, where the color features include saturation and brightness, and build a model;

[0015] The collected real-time image is divided into sub-areas, and all saturation and brightness in the sub-areas of the real-time image are obtained. The sum and average are respectively performed to obtain the average saturation and average brightness of the current sub-area, which are input into the model, and the real-time inkjet concentration of the sub-area is output.

[0016] As a further solution of the present invention: the specific process of judging whether the inkjet concentration space of the sub-area is uniform is as follows:

[0017] The inkjet concentration of all sub-areas in the real-time image is obtained, and the inkjet uniformity judgment value is calculated by the variance processing formula. If the inkjet uniformity judgment value ≥ the inkjet uniformity judgment threshold, an inkjet unevenness signal is generated.

[0018] As a further solution of the present invention: the specific process of identifying the degree of uneven distribution of spatial inkjet concentration is:

[0019] Analyze the inkjet concentration of the sub-region in the sub-region inkjet concentration empty sequence to obtain adjacent concentration change rates and reference concentration change rates, perform data processing on the adjacent concentration change rates and the reference concentration change rates to obtain concentration change rate deviation values ​​and asynchronous concentration change rates;

[0020] Calculate the proportion of asynchronous concentration change rates, extract the concentration change rate deviation values ​​corresponding to all asynchronous concentration change rates, sum and average them, and obtain the asynchronous concentration change rate deviation mean;

[0021] The spatial concentration distribution value is obtained by multiplying the mean value of the asynchronous concentration change rate deviation with the number proportion of the asynchronous concentration change rate; if the spatial concentration distribution value is less than the spatial concentration distribution threshold, it indicates that the spatial inkjet non-uniformity is low; otherwise, it indicates that the spatial inkjet non-uniformity is high.

[0022] As a further solution of the present invention: the process of obtaining the concentration change rate deviation value and the asynchronous concentration change rate is:

[0023] The adjacent concentration change rates are subtracted from the reference concentration change rates and their absolute values ​​are taken to obtain a concentration change rate deviation value. If the concentration change rate deviation value is ≥ the concentration change rate deviation threshold, the adjacent concentration change rate corresponding to the concentration change rate deviation value is recorded as an asynchronous concentration change rate.

[0024] As a further solution of the present invention: the process of obtaining the reference concentration change rate is:

[0025] Extract the inkjet concentration of the sub-region located first in the order and the inkjet concentration of the sub-region located first in the reverse order in the empty order of the sub-region inkjet concentration; take the absolute value after difference processing to obtain the peak-to-valley inkjet concentration change value, measure the distance between the sub-regions first in the order and first in the reverse order to obtain the peak-to-valley distance difference; calculate the ratio of the peak-to-valley inkjet concentration change value to the peak-to-valley distance difference to obtain the reference concentration change rate.

[0026] As a further solution of the present invention: the process of obtaining the adjacent concentration change rate is:

[0027] Extract the inkjet concentration of the sub-region located in the previous sequence and the inkjet concentration of the sub-region located in the next sequence in the empty sequence of sub-region inkjet concentration; take the absolute value after difference processing to obtain the adjacent inkjet concentration change value, measure the distance between the sub-regions of the previous sequence and the next sequence, and record it as the adjacent distance difference; calculate the ratio of the adjacent inkjet concentration change value to the adjacent distance difference to obtain the adjacent concentration change rate.

[0028] As a further solution of the present invention: the spatial inkjet power compensation value is obtained in the following manner:

[0029] The inkjet concentration of the sub-area in the inkjet concentration space sequence is extracted, and the difference is made with the standard value of the inkjet concentration of the sub-area, and then the absolute value is taken to obtain the spatial inkjet concentration deviation value, and a fitting relationship model between the inkjet power and the inkjet concentration is constructed. According to the fitting relationship model, the spatial inkjet power compensation value of the digital printing machine when inkjet is used is calculated.

[0030] As a further solution of the present invention: the process of identifying whether the inkjet concentration of the sub-area is stable within the analysis period is as follows;

[0031] The inkjet concentration at all time points in the sub-region analysis period is analyzed to obtain the inkjet concentration stability value; if the inkjet concentration stability value ≥ the inkjet concentration stability threshold, it means that the inkjet concentration of the inkjet space in the analysis period fluctuates in the time dimension.

[0032] As a further solution of the present invention: the process of obtaining the stable value of the inkjet concentration is:

[0033] The inkjet concentrations at all time points in the sub-region analysis period are obtained and integrated into an inkjet concentration time series, all inkjet concentrations in the inkjet concentration time series are extracted and variance is calculated to obtain the variance of the inkjet concentration of each sub-region;

[0034] The variances of inkjet concentrations in all sub-regions are summed and averaged to obtain a stable value of inkjet concentration.

[0035] As a further solution of the present invention: the process of obtaining the time inkjet power compensation value is:

[0036] Extract the inkjet concentration of the sub-area in the inkjet concentration time series, and make a difference with the standard value of the inkjet concentration of the sub-area, and then take the absolute value to obtain the temporal inkjet concentration deviation value, input the fitting relationship model between the inkjet power and the inkjet concentration, and calculate the temporal inkjet power compensation value when the digital printing machine is inkjetting.

[0037] Beneficial effects of the present invention:

[0038] 1. The present invention constructs an inkjet concentration model based on the color features and historical inkjet concentration in the sample images of historical digital printing, inputs the color features of the real-time image into the inkjet concentration model, and outputs the real-time inkjet concentration of each sub-region of the real-time image; according to the real-time inkjet concentration of the sub-region, it is judged whether the spatial inkjet of the inkjet concentration of the sub-region is uniform, and if it is not uniform, the degree of uneven distribution of the spatial inkjet concentration is identified; if the spatial inkjet unevenness is high, the inkjet concentrations of all sub-regions are integrated into a sub-region inkjet concentration empty sequence according to the spatial position, the real-time inkjet concentrations of the sub-regions in the inkjet concentration empty sequence are analyzed, the spatial inkjet power compensation value is determined, and the inkjet power of the digital printing machine is regulated during inkjet; the present invention uses the sub-region color features to determine the spatial inkjet power compensation value. The inkjet concentration is calculated by the mean value, and the inkjet concentration of the sub-area is output according to the image color characteristics, so as to judge whether the spatial inkjet concentration distribution is consistent. For the case of inconsistent concentration distribution, the linear change degree of the inkjet concentration of each sub-area with the spatial distance is evaluated, and the degree of inkjet unevenness in the spatial dimension is identified to provide a basis for compensation and regulation. In the case of high inkjet unevenness, by analyzing the inkjet concentration of the sub-area in the inkjet concentration space sequence, the pre-constructed inkjet power and inkjet concentration fitting relationship model is used to calculate the spatial inkjet power compensation value, and send it to the inkjet device for regulation. It can adjust the inkjet power of the digital printing machine in a targeted manner, improve the problem of inkjet unevenness, and improve the printing quality of digital printed items.

[0039] 2. If the spatial inkjet unevenness is low, the present invention identifies whether the inkjet concentration of the sub-region within the analysis period is stable. If it is not stable, the temporal inkjet power compensation value is determined according to the inkjet concentration of the sub-region within the analysis period, and the inkjet power of the digital printing machine during inkjet is regulated. The present invention can carry out stability analysis on the inkjet concentration of each sub-region within a specific analysis period when the spatial inkjet unevenness is low, measure the fluctuation of the inkjet concentration in the time dimension, and promptly warn of the inkjet inconsistency problem in the time series during the printing process, and compensate for the fluctuation of the inkjet concentration in the time dimension, so as to ensure that the inkjet concentration of the digital printing machine in the time series tends to be stable, further improve the printing quality of digital printed products, and reduce the printing quality problems caused by the inkjet concentration factor. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 This is a system block diagram of a digital printing quality analysis system based on machine vision according to an embodiment of the present invention;

[0042] Figure 2 The present invention is a flowchart of a method for analyzing digital printing quality based on machine vision. DETAILED DESCRIPTION

[0043] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0044] Embodiment 1

[0045] like Figure 1 As shown, a digital printing quality analysis system based on machine vision provided by an embodiment of the present invention specifically includes:

[0046] Data acquisition module: Based on the color features of the sample images of historical digital printing and the historical inkjet concentration, an inkjet concentration model is constructed, the color features of the real-time image are input into the inkjet concentration model, and the real-time inkjet concentration of each sub-area of ​​the real-time image is output;

[0047] In some embodiments, a machine vision system is used to obtain sample images printed at different inkjet densities in history and convert them into an HSV color space;

[0048] Extracting color features and historical inkjet density from sample images of historical digital printing, where the color features include saturation S and brightness V;

[0049] Use the least squares method to fit the linear regression model and construct the error function, specifically:

[0050]

[0051] in, is the inkjet concentration of the i-th sample, is the saturation of the i-th sample, is the brightness of the i-th sample, n is the number of samples;

[0052] The linear regression model is verified according to the error function. If the verification is qualified, the partial derivative of the error function after the verification is completed is calculated and set to zero, and the values ​​of coefficients a, b, and c are obtained, and then a linear regression model between inkjet concentration C and saturation S and brightness V is constructed, which is specifically:

[0053]

[0054] If the verification fails, other models are used to map the relationship between inkjet concentration C and saturation S and brightness V. Other models include but are not limited to random forest models and deep learning models.

[0055] Taking the initial inkjet position of the digital printing machine as the origin, the image is divided into a plurality of parallel sub-areas with the same volume along the inkjet direction;

[0056] Based on any sub-region, obtain all saturation and brightness in the sub-region, and sum and average them respectively to obtain the average saturation and average brightness of the current sub-region;

[0057] The average saturation and average brightness of the sub-region are input into the model, and the real-time inkjet density of the sub-region is output;

[0058] Inkjet uniformity judgment module: judge whether the inkjet density of the sub-area is uniform in space according to the real-time inkjet density of the sub-area. If it is not uniform, identify the degree of uneven distribution of the spatial inkjet density.

[0059] In some embodiments, the inkjet concentration of all sub-areas in the real-time image is extracted, and the inkjet concentration of all sub-areas in the real-time image is calculated through a variance processing formula to obtain an inkjet uniformity judgment value;

[0060] The inkjet uniformity judgment value is compared with the inkjet uniformity judgment threshold. The specific comparison process is as follows:

[0061] If the inkjet uniformity judgment value is greater than or equal to the inkjet uniformity judgment threshold, it means that the inkjet concentrations of each sub-area are inconsistent, which further indicates that the inkjet concentration distribution in the spatial dimension is inconsistent, and an inkjet unevenness signal is generated;

[0062] If the inkjet uniformity judgment value is less than the inkjet uniformity judgment threshold, it means that the inkjet concentrations of each sub-area are consistent, and further indicates that the inkjet concentration distribution in the spatial dimension is consistent, and an inkjet uniformity signal is generated;

[0063] It should be noted that the inkjet uniformity judgment value is used to characterize the consistency of the inkjet concentration of each sub-region in the real-time image. The generation of an inkjet unevenness signal indicates that the inkjet concentration of each sub-region is inconsistent in the spatial dimension; the generation of an inkjet uniformity signal indicates that the inkjet concentration of each sub-region is relatively consistent in the spatial dimension. The inkjet uniformity signal can reflect that the inkjet concentration of each sub-region will not affect the printing quality of digital printed objects in the spatial dimension.

[0064] Based on the inkjet unevenness signal, the inkjet densities of all sub-areas are integrated into a sub-area inkjet density spatial sequence according to the spatial position, wherein the spatial position is the distance between the center point of the sub-area and the digital printed object;

[0065] Extract the inkjet concentration of the first sub-region and the inkjet concentration of the first sub-region in the reverse order in the sub-region inkjet concentration empty sequence; perform difference processing on the inkjet concentration of the first sub-region and the inkjet concentration of the first sub-region in the reverse order, and take the absolute value to obtain the peak-valley inkjet concentration change value, measure the distance between the first sub-region and the first sub-region in the reverse order, and obtain the peak-valley distance difference; perform ratio calculation on the peak-valley inkjet concentration change value and the peak-valley distance difference to obtain the reference concentration change rate;

[0066] Extract the inkjet concentration of the sub-region located in the previous sequence and the inkjet concentration of the sub-region located in the next sequence in the empty sequence of sub-region inkjet concentration; perform difference processing on the inkjet concentration of the sub-region in the previous sequence and the inkjet concentration of the sub-region in the next sequence, and take the absolute value to obtain the adjacent inkjet concentration change value, measure the distance between the sub-regions in the previous sequence and the next sequence, and record it as the adjacent distance difference; calculate the ratio of the adjacent inkjet concentration change value to the adjacent distance difference to obtain the adjacent concentration change rate;

[0067] Based on any adjacent concentration change rate, the adjacent concentration change rate is subjected to difference processing with the reference concentration change rate, and the absolute value of the difference is taken to obtain the concentration change rate deviation value;

[0068] The concentration change rate deviation value is compared with the concentration change rate deviation threshold. The specific comparison process is:

[0069] If the concentration change rate deviation value is greater than or equal to the concentration change rate deviation threshold, it means that the inkjet concentration change trend of the adjacent area corresponding to the current adjacent concentration change rate is significantly different from the inkjet concentration change trend corresponding to the reference concentration change rate, and the adjacent concentration change rate corresponding to the concentration change rate deviation value is recorded as an asynchronous concentration change rate;

[0070] If the concentration change rate deviation value is less than the concentration change rate deviation threshold, it means that the inkjet concentration change trend of the adjacent area corresponding to the current adjacent concentration change rate is slightly different from the inkjet concentration change trend corresponding to the reference concentration change rate, and the adjacent concentration change rate corresponding to the concentration change rate deviation value is recorded as the synchronous concentration change rate;

[0071] Count the number of asynchronous concentration change rates, calculate the proportion of the number of asynchronous concentration change rates, extract the concentration change rate deviation values ​​corresponding to all asynchronous concentration change rates, sum and average them, and obtain the asynchronous concentration change rate deviation mean;

[0072] The spatial concentration distribution value is obtained by multiplying the mean deviation of the asynchronous concentration change rate with the number proportion of the asynchronous concentration change rate;

[0073] Compare the spatial concentration distribution value with the spatial concentration distribution threshold. The specific comparison process is:

[0074] If the spatial concentration distribution value is less than the spatial concentration distribution threshold, it means that the inkjet concentration of each sub-area changes linearly with the spatial distance to a high degree, and the spatial inkjet non-uniformity is low;

[0075] If the spatial concentration distribution value is greater than or equal to the spatial concentration distribution threshold, it means that the linear variation degree of the inkjet concentration in each sub-area with the change of spatial distance is low, and the spatial inkjet non-uniformity is high;

[0076] It should be noted that the spatial concentration distribution value is obtained by processing the mean value of the asynchronous concentration change rate deviation and the number ratio of the asynchronous concentration change rate. The larger the mean value of the asynchronous concentration change rate deviation, the lower the degree of linear change of the inkjet concentration in each sub-region with the change of distance in space. The larger the number ratio of the asynchronous concentration change rate, the lower the degree of linear change of the inkjet concentration in each sub-region with the change of distance in space. The smaller the number ratio of the asynchronous concentration change rate, the higher the degree of linear change of the inkjet concentration in each sub-region with the change of spatial distance, indicating that the inkjet concentration of digital printing is more uniform in the spatial dimension, and has less impact on the printing quality of digital printed items.

[0077] Spatial dimension power compensation module: If the spatial inkjet non-uniformity is high, the inkjet concentrations of all sub-areas are integrated into a sub-area inkjet concentration space sequence according to the spatial position, and the real-time inkjet concentration of the sub-area in the inkjet concentration space sequence is analyzed to determine the spatial inkjet power compensation value, and adjust the inkjet power of the digital printing machine when inkjet;

[0078] In some embodiments, the inkjet concentration of the sub-region in the inkjet concentration space sequence is extracted, and the difference is processed with the standard value of the inkjet concentration of the sub-region, and then the absolute value of the difference is taken to obtain the spatial inkjet concentration deviation value. , a fitting relationship model between inkjet power and inkjet concentration is constructed, and according to the fitting relationship model, the spatial inkjet power compensation value KP of the digital printing machine when inkjet is used is calculated. The specific formula is:

[0079]

[0080] Wherein, k is the proportional coefficient between the inkjet power and the inkjet concentration determined experimentally in the fitting relationship model;

[0081] It should be noted that the standard value of inkjet concentration of the sub-area is set by the staff in this field based on historical experience;

[0082] The spatial inkjet power compensation value is sent to the inkjet device of the digital printing press to adjust the inkjet power of the digital printing press when it is inkjetting;

[0083] The technical solution of the embodiment of the present invention is as follows: based on the color features and historical inkjet concentrations in the sample images of historical digital printing, an inkjet concentration model is constructed, the color features of the real-time image are input into the inkjet concentration model, and the real-time inkjet concentration of each sub-region of the real-time image is output; according to the real-time inkjet concentration of the sub-region, whether the spatial inkjet concentration of the sub-region is uniform is judged, if it is not uniform, the degree of uneven distribution of the spatial inkjet concentration is identified; if the spatial inkjet unevenness is high, the inkjet concentrations of all sub-regions are integrated into a sub-region inkjet concentration space sequence according to the spatial position, the real-time inkjet concentrations of the sub-regions in the inkjet concentration space sequence are analyzed, the spatial inkjet power compensation value is determined, and the inkjet power of the digital printing machine is regulated during inkjet; the present invention controls the inkjet power of the digital printing machine during inkjet by controlling the sub-region. The inkjet concentration is calculated by the mean value of color features, and the inkjet concentration of the sub-area is output according to the image color features, so as to determine whether the spatial inkjet concentration distribution is consistent. For the case of inconsistent concentration distribution, the linear change degree of the inkjet concentration of each sub-area with the spatial distance is evaluated, and the degree of inkjet unevenness in the spatial dimension is identified to provide a basis for compensation and regulation. In the case of high inkjet unevenness, by analyzing the inkjet concentration of the sub-area in the inkjet concentration space sequence, the pre-constructed inkjet power and inkjet concentration fitting relationship model is used to calculate the spatial inkjet power compensation value, and send it to the inkjet device for regulation. It can adjust the inkjet power of the digital printing machine in a targeted manner, improve the problem of inkjet unevenness, and improve the printing quality of digital printed items.

[0084] Embodiment 2

[0085] like Figure 1 As shown, a digital printing quality analysis system based on machine vision provided by an embodiment of the present invention specifically includes:

[0086] Inkjet stability analysis module: if the spatial inkjet non-uniformity is low, identify whether the inkjet concentration of the sub-area is stable within the analysis period;

[0087] In some implementation schemes, based on the fact that the inkjet concentration of each sub-region varies linearly with the spatial distance, an analysis period is preset, the duration of the analysis period is T, the current time is used as the end time of the analysis period, the current time is recorded as TE, and the time interval corresponding to the analysis period is [TE-T, TE];

[0088] It is understandable that the value of the duration T of the analysis period is preset by those skilled in the art;

[0089] The inkjet concentrations at all time points of the sub-region are obtained and integrated into an inkjet concentration time series, all inkjet concentrations in the inkjet concentration time series are extracted and variance is calculated to obtain the variance of the inkjet concentration of each sub-region;

[0090] It can be understood that the time intervals for continuously collecting digital printed images during the analysis period are the same, and the analysis period is divided into a number of time points with equal time intervals, and a digital printed image is collected once at each time point;

[0091] The variances of inkjet concentrations in all sub-regions are summed and averaged to obtain a stable value of inkjet concentration;

[0092] The inkjet concentration stability value is compared with the inkjet concentration stability threshold value, and the specific comparison process is as follows;

[0093] If the inkjet concentration stability value is greater than or equal to the inkjet concentration stability threshold, it means that the inkjet concentration of the inkjet space in the analysis period fluctuates in the time dimension;

[0094] If the inkjet concentration stability value is less than the inkjet concentration stability threshold, it means that the inkjet concentration of the inkjet space within the analysis period tends to be stable in the time dimension;

[0095] It should be noted that the inkjet concentration stability value is used to characterize the fluctuation of the inkjet concentration in the inkjet space in the time dimension when the inkjet unevenness is low. The fluctuation of the inkjet concentration in the inkjet space in the time dimension during the analysis period indicates that there is inkjet inconsistency in the time series during the printing process, which helps to judge the printing quality of digital printed items. The inkjet concentration in the inkjet space in the time dimension during the analysis period tends to be stable, indicating that the inkjet concentration in the time and space series during the printing process is stable, which further indicates that the inkjet concentration has little effect on the printing quality of digital printed items.

[0096] Time dimension power compensation module: if it is unstable, the time inkjet power compensation value is determined according to the inkjet concentration of the sub-area within the analysis period, and the inkjet power of the digital printing machine is regulated during inkjet;

[0097] In some embodiments, the inkjet concentration of the sub-region in the inkjet concentration time series is extracted, and the difference is processed with the standard value of the inkjet concentration of the sub-region, and then the absolute value of the difference is taken to obtain the time inkjet concentration deviation value. , input the fitting relationship model between inkjet power and inkjet concentration, and calculate the time inkjet power compensation value SP when the digital printing machine is inkjetting. The specific formula is:

[0098]

[0099] The time inkjet power compensation value is sent to the inkjet device of the digital printing machine to adjust the inkjet power of the digital printing machine when it is inkjetting;

[0100] The technical solution of this embodiment is: if the spatial inkjet unevenness is low, identify whether the inkjet concentration of the sub-area within the analysis period is stable; if it is not stable, determine the time inkjet power compensation value according to the inkjet concentration of the sub-area within the analysis period, and adjust the inkjet power of the digital printing machine during inkjet. The present invention can carry out stability analysis on the inkjet concentration of each sub-area within a specific analysis period when the spatial inkjet unevenness is low, measure the fluctuation of the inkjet concentration in the time dimension, and promptly warn of the inkjet inconsistency problem in the time series during the printing process, and compensate for the fluctuation of the inkjet concentration in the time dimension, so as to ensure that the inkjet concentration of the digital printing machine in the time series tends to be stable, further improve the printing quality of digital printed items, and reduce printing quality problems caused by inkjet concentration factors.

[0101] Embodiment 3

[0102] like Figure 2 As shown, a digital printing quality analysis method based on machine vision provided by an embodiment of the present invention specifically includes the following steps:

[0103] Step 1: Based on the color features in the sample images of historical digital printing and the historical inkjet concentration, an inkjet concentration model is constructed, the color features of the real-time image are input into the inkjet concentration model, and the real-time inkjet concentration of each sub-area of ​​the real-time image is output;

[0104] Step 2: judging whether the inkjet concentration of the sub-region is uniform in space according to the real-time inkjet concentration of the sub-region, and if not, identifying the degree of uneven distribution of the spatial inkjet concentration;

[0105] Step 3: If the spatial inkjet non-uniformity is high, the inkjet concentrations of all sub-areas are integrated into a sub-area inkjet concentration spatial sequence according to their spatial positions, the real-time inkjet concentrations of the sub-areas in the inkjet concentration spatial sequence are analyzed, the spatial inkjet power compensation value is determined, and the inkjet power of the digital printing machine is regulated during inkjet.

[0106] Step 4: If the spatial inkjet non-uniformity is low, identify whether the inkjet concentration of the sub-area is stable within the analysis period;

[0107] Step 5: If it is unstable, determine the time inkjet power compensation value according to the inkjet concentration of the sub-area within the analysis period, and adjust the inkjet power of the digital printing machine when it is inkjet.

[0108] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0109] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A digital printing quality analysis system based on machine vision, characterized in that: include: Data acquisition module: Based on the color features of the sample images of historical digital printing and the historical inkjet concentration, an inkjet concentration model is constructed, the color features of the real-time image are input into the inkjet concentration model, and the real-time inkjet concentration of each sub-area of ​​the real-time image is output; Inkjet uniformity judgment module: judge whether the inkjet density of the sub-area is uniform in space according to the real-time inkjet density of the sub-area. If it is not uniform, identify the degree of uneven distribution of the spatial inkjet density. Spatial dimension power compensation module: If the spatial inkjet unevenness is high, the inkjet concentrations of all sub-areas are integrated into a sub-area inkjet concentration spatial sequence according to their spatial positions. The real-time inkjet concentrations of the sub-areas in the inkjet concentration spatial sequence are analyzed to determine the spatial inkjet power compensation value, and to regulate the inkjet power of the digital printing machine during inkjet.

2. The digital printing quality analysis system based on machine vision according to claim 1, characterized in that: Also includes: Inkjet stability analysis module: if the spatial inkjet non-uniformity is low, identify whether the inkjet concentration of the sub-area is stable within the analysis period; Time dimension power compensation module: If it is unstable, the time inkjet power compensation value is determined according to the inkjet concentration of the sub-area within the analysis period, and the inkjet power of the digital printing machine is regulated during inkjet.

3. The digital printing quality analysis system based on machine vision according to claim 1, characterized in that: The process of acquiring the real-time inkjet concentration of the sub-area is as follows: Obtain color features of sample images of historical digital printing and historical inkjet concentration, where the color features include saturation and brightness, and build a model; The collected real-time image is divided into sub-areas, and all saturation and brightness in the sub-areas of the real-time image are obtained. The sum and average are respectively performed to obtain the average saturation and average brightness of the current sub-area, which are input into the model, and the real-time inkjet concentration of the sub-area is output.

4. The digital printing quality analysis system based on machine vision according to claim 3, characterized in that: The specific process of judging whether the inkjet concentration space of the sub-region is uniform is as follows: The inkjet concentration of all sub-areas in the real-time image is obtained, and the inkjet uniformity judgment value is calculated by the variance processing formula. If the inkjet uniformity judgment value ≥ the inkjet uniformity judgment threshold, an inkjet unevenness signal is generated.

5. The digital printing quality analysis system based on machine vision according to claim 1, characterized in that: The specific process of identifying the degree of uneven distribution of spatial inkjet concentration is as follows: Analyze the inkjet concentration of the sub-region in the sub-region inkjet concentration empty sequence to obtain adjacent concentration change rates and reference concentration change rates, perform data processing on the adjacent concentration change rates and the reference concentration change rates to obtain concentration change rate deviation values ​​and asynchronous concentration change rates; Calculate the proportion of asynchronous concentration change rates, extract the concentration change rate deviation values ​​corresponding to all asynchronous concentration change rates, sum and average them, and obtain the asynchronous concentration change rate deviation mean; The spatial concentration distribution value is obtained by multiplying the mean value of the asynchronous concentration change rate deviation with the number proportion of the asynchronous concentration change rate; if the spatial concentration distribution value is less than the spatial concentration distribution threshold, it indicates that the spatial inkjet non-uniformity is low; otherwise, it indicates that the spatial inkjet non-uniformity is high.

6. The digital printing quality analysis system based on machine vision according to claim 5, characterized in that: The process of obtaining the concentration change rate deviation value and the asynchronous concentration change rate is as follows: The adjacent concentration change rates are subtracted from the reference concentration change rates and their absolute values ​​are taken to obtain a concentration change rate deviation value. If the concentration change rate deviation value is ≥ the concentration change rate deviation threshold, the adjacent concentration change rate corresponding to the concentration change rate deviation value is recorded as an asynchronous concentration change rate.

7. The digital printing quality analysis system based on machine vision according to claim 5, characterized in that: The process of obtaining the reference concentration change rate is as follows: Extract the inkjet concentration of the sub-region located first in the order and the inkjet concentration of the sub-region located first in the reverse order in the empty order of the sub-region inkjet concentration; take the absolute value after difference processing to obtain the peak-to-valley inkjet concentration change value, measure the distance between the sub-regions first in the order and first in the reverse order to obtain the peak-to-valley distance difference; calculate the ratio of the peak-to-valley inkjet concentration change value to the peak-to-valley distance difference to obtain the reference concentration change rate.

8. The digital printing quality analysis system based on machine vision according to claim 5, characterized in that: The process of obtaining the adjacent concentration change rates is as follows: Extract the inkjet concentration of the sub-region located in the previous sequence and the inkjet concentration of the sub-region located in the next sequence in the empty sequence of sub-region inkjet concentration; take the absolute value after difference processing to obtain the adjacent inkjet concentration change value, measure the distance between the sub-regions of the previous sequence and the next sequence, and record it as the adjacent distance difference; calculate the ratio of the adjacent inkjet concentration change value to the adjacent distance difference to obtain the adjacent concentration change rate.

9. The digital printing quality analysis system based on machine vision according to claim 5, characterized in that: The spatial inkjet power compensation value is obtained in the following manner: The inkjet concentration of the sub-area in the inkjet concentration space sequence is extracted, and the difference is made with the standard value of the inkjet concentration of the sub-area, and then the absolute value is taken to obtain the spatial inkjet concentration deviation value, and a fitting relationship model between the inkjet power and the inkjet concentration is constructed. According to the fitting relationship model, the spatial inkjet power compensation value of the digital printing machine when inkjet is used is calculated.

10. The digital printing quality analysis system based on machine vision according to claim 2, characterized in that: The process of identifying whether the inkjet concentration of the sub-area is stable within the analysis period is as follows: The inkjet concentration at all time points in the sub-region analysis period is analyzed to obtain the inkjet concentration stability value; if the inkjet concentration stability value ≥ the inkjet concentration stability threshold, it means that the inkjet concentration of the inkjet space in the analysis period fluctuates in the time dimension.

11. The digital printing quality analysis system based on machine vision according to claim 10, characterized in that: The process of obtaining the stable value of inkjet concentration is as follows: The inkjet concentrations at all time points in the sub-region analysis period are obtained and integrated into an inkjet concentration time series, all inkjet concentrations in the inkjet concentration time series are extracted and variance is calculated to obtain the variance of the inkjet concentration of each sub-region; The variances of inkjet concentrations in all sub-regions are summed and averaged to obtain a stable value of inkjet concentration.

12. The digital printing quality analysis system based on machine vision according to claim 11, characterized in that: The process of obtaining the time inkjet power compensation value is as follows: Extract the inkjet concentration of the sub-area in the inkjet concentration time series, and make a difference with the standard value of the inkjet concentration of the sub-area, and then take the absolute value to obtain the temporal inkjet concentration deviation value, input the fitting relationship model between the inkjet power and the inkjet concentration, and calculate the temporal inkjet power compensation value when the digital printing machine is inkjetting.

Images