Intelligent evaluation method, device and system for printhead status of digital printing machine

Abstract

The present invention discloses a method, device and system for intelligently evaluating the state of a digital printing machine nozzle, and relates to the field of image processing technology, including: obtaining a test image printed by a target digital printing machine; determining the ink uneven area according to the pixel value of each image area in the test image; determining the ink artifact annoyance coefficient of each ink uneven area according to the edge curve of each ink uneven area; determining the characteristic loss factor of each ink uneven area according to the ink artifact annoyance coefficient of each ink uneven area; performing image correction on the test image according to the characteristic loss factor of each ink uneven area, so as to evaluate the state of the nozzle according to the test image after image correction. The present invention can improve the clarity and accuracy of the image features of the test image, and thus can improve the accuracy of the nozzle state evaluation.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method, device and system for intelligently evaluating the nozzle status of a digital printing machine. Background Art

[0002] The working principle of industrial digital printing machine is to print the designed pattern on white paper, and then transfer the pattern of the paper to the cloth through high temperature transfer technology. One of the core components of digital printing machine is the print head, and its stability is directly related to the printing quality and production efficiency. Therefore, it is very important to reasonably evaluate the status of the print head of the digital printing machine.

[0003] In the existing methods, it is usually necessary to analyze the test image printed by the print head of the digital printing machine to detect image feature defects or grid leakage anomalies, so as to evaluate the state of the print head.

[0004] However, the wear and aging of the printheads may cause uneven inkjet, which makes the ink on the test image unevenly distributed and the image features blurred or distorted, resulting in poor accuracy in the evaluation of the printhead status. Summary of the invention

[0005] The embodiments of the present invention provide a method, device and system for intelligently evaluating the status of a printhead of a digital printing machine, which can improve the accuracy of the evaluation of the status of the printhead.

[0006] A first aspect of an embodiment of the present invention provides a method for intelligently evaluating the status of a printhead of a digital printing machine, comprising:

[0007] Obtain a test image printed by a target digital printing machine;

[0008] Determine the ink uneven area in the test image according to the pixel value of each image area in the test image;

[0009] Determine the ink artifact annoyance coefficient of each ink uneven region according to the edge curve in each ink uneven region, where the ink artifact annoyance coefficient is used to characterize the degree of interference of the ink uneven region by the artifact;

[0010] According to the ink artifact nuisance coefficient of each ink uneven area, the characteristic loss factor of each ink uneven area is determined respectively;

[0011] The test image is corrected according to the characteristic loss factor of each ink uneven area, so that the state of the nozzle can be evaluated according to the test image after the image correction.

[0012] A second aspect of an embodiment of the present invention provides an intelligent evaluation device for a printhead state of a digital printing machine, comprising:

[0013] An image acquisition module, used to acquire a test image printed by a target digital printing machine;

[0014] The region determination module is used to determine the ink uneven region in the test image according to the pixel value size of each image region in the test image;

[0015] A coefficient determination module, used to determine the ink artifact annoyance coefficient of each ink uneven area according to the edge curve in each ink uneven area, and the ink artifact annoyance coefficient is used to characterize the degree of interference of the ink uneven area by the artifact;

[0016] A loss determination module, for determining a characteristic loss factor of each ink uneven region according to an ink artifact nuisance coefficient of each ink uneven region;

[0017] The image correction module is used to perform image correction on the test image according to the characteristic loss factor of each ink uneven area, so as to evaluate the state of the nozzle according to the image-corrected test image.

[0018] A third aspect of an embodiment of the present invention provides an intelligent evaluation system for the nozzle status of a digital printing machine, comprising a data acquisition module, an image data processing platform, an intelligent evaluation module and a user interface;

[0019] A data acquisition module, used for acquiring a test image printed by a target digital printing machine;

[0020] An image data processing platform, used to execute the intelligent evaluation method for the printhead status of a digital printing machine provided in any one of the above aspects;

[0021] An intelligent evaluation module is used to evaluate the state of the printhead according to the test image processed by the image data processing platform to obtain a printhead evaluation result;

[0022] A user interface is provided for displaying the results of the sprinkler evaluation.

[0023] In the intelligent evaluation method for the nozzle status of a digital printing machine provided by an embodiment of the present invention, the uneven ink area in the pixel image caused by wear and aging is first determined based on the pixel value size of each image area in the test image. Then, based on the edge curve in the uneven ink area, the degree of influence of the artifacts in the uneven ink area on the regional features is analyzed to determine the characteristic loss factor of the uneven ink area. Finally, based on the characteristic loss factor of the uneven ink area, the test image is corrected to improve the clarity and accuracy of the image features of the test image. In this way, the embodiment of the present invention can improve the clarity and accuracy of the image features of the test image by identifying the uneven ink area in the test image and performing image correction on the test image based on the characteristic loss factor of the uneven ink area, thereby improving the accuracy of the nozzle status evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 A schematic flow chart of a first method for intelligently evaluating the status of a printhead of a digital printing machine provided by an embodiment of the present invention;

[0026] Figure 2 A schematic diagram of a test image provided by an embodiment of the present invention;

[0027] Figure 3 A schematic diagram of an edge curve of a test image provided by an embodiment of the present invention;

[0028] Figure 4 A schematic flow chart of a second method for intelligently evaluating the status of a printhead of a digital printing machine provided by an embodiment of the present invention;

[0029] Figure 5 A schematic flow chart of a third method for intelligently evaluating the status of a printhead of a digital printing machine provided by an embodiment of the present invention;

[0030] Figure 6 A schematic flow chart of a fourth method for intelligently evaluating the status of a printhead of a digital printing machine provided by an embodiment of the present invention;

[0031] Figure 7 A schematic diagram of the structure of an intelligent evaluation device for the nozzle status of a digital printing machine provided by one embodiment of the present invention;

[0032] Figure 8 A schematic diagram of the structure of an intelligent evaluation system for the printhead status of a digital printing machine provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the method, device and system for intelligent evaluation of the nozzle status of a digital printing machine proposed by the present invention, its specific implementation, structure, features and effects in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0034] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0035] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of the present invention are in compliance with the relevant provisions of laws and regulations.

[0036] It should be noted that in the embodiments of the present invention, certain software, components, models and other existing solutions in the industry may be mentioned, which should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present invention, but it does not mean that the applicant has or will necessarily use the solution.

[0037] In the existing methods, the printhead status is usually evaluated by analyzing the test image printed by the printhead of the digital printing machine to detect image feature defects or grid leakage anomalies. However, the wear and aging of the printhead may cause uneven inkjet, resulting in uneven ink distribution on the test image, blurring or distorting the image features, and thus resulting in poor accuracy in the printhead status evaluation.

[0038] The object of the present invention is to provide a method, device and system for intelligently evaluating the status of a nozzle of a digital printing machine. In the method for intelligently evaluating the status of a nozzle of a digital printing machine provided in an embodiment of the present invention, the uneven ink area caused by wear and aging in the pixel image is first determined based on the pixel value size of each image area in the test image. Then, based on the edge curve in the uneven ink area, the degree of influence of the artifacts in the uneven ink area on the regional features is analyzed, thereby determining the characteristic loss factor of the uneven ink area. Finally, based on the characteristic loss factor of the uneven ink area, the test image is corrected to improve the clarity and accuracy of the image features of the test image. In this way, the embodiment of the present invention can improve the clarity and accuracy of the image features of the test image by identifying the uneven ink area in the test image and correcting the test image based on the characteristic loss factor of the uneven ink area, thereby improving the accuracy of the nozzle status evaluation.

[0039] The following describes specific embodiments of a method, device and system for intelligently evaluating the status of a printhead of a digital printing machine provided by an embodiment of the present invention.

[0040] Figure 1 A flow chart of a method for intelligently evaluating the status of a printhead of a digital printing machine is provided. The method for intelligently evaluating the status of a printhead of a digital printing machine can be applied to an image data processing platform in an intelligent evaluation system for the status of a printhead of a digital printing machine. The method for intelligently evaluating the status of a printhead of a digital printing machine may include the following S101 to S105.

[0041] S101, obtaining a test image printed by a target digital printing machine.

[0042] In this embodiment, the test image is acquired by an image acquisition device, which may be a high-precision camera.

[0043] As an example, an industrial light source and a high-precision camera can be used to collect test images printed by a target digital printing machine at preset intervals, and then the image data processing platform receives the collected test images. Figure 2 As shown, a schematic diagram of a test image is provided.

[0044] Then, the image data processing platform can also perform pre-processing operations such as grayscale conversion, filtering, and data enhancement on the test image to remove interference from various unstable external noises that exist during the camera shooting process.

[0045] S102, determining the ink uneven area in the test image according to the pixel value of each image area in the test image.

[0046] In this embodiment, the uneven ink area is used to characterize an area in the test image where the ink droplets are unevenly distributed and the color saturation is significantly different from that of the surrounding area.

[0047] The pixel value size of the image area is used to represent the accumulated value of the pixel values ​​of each pixel point in the image area.

[0048] As an example, the image data processing platform traverses each pixel point in the test image, and then for each image area, accumulates the pixel values ​​of each pixel point in the image area to obtain the pixel value size of each image area in the test image.

[0049] Then, a pixel value difference threshold is set, and the pixel value size of each image area is compared with the pixel value size of the surrounding image areas. When the difference between the pixel value sizes of the surrounding image areas is greater than the pixel value difference threshold, the image area is marked as an uneven ink area.

[0050] S103, determining an ink artifact annoyance coefficient of each ink uneven region according to the edge curve in each ink uneven region, where the ink artifact annoyance coefficient is used to characterize the degree of interference of the ink uneven region by the artifact.

[0051] In this embodiment, the edge curve is used to represent the line describing the boundary or shape of the graphic. Figure 3 As shown, a schematic diagram of the edge curve of a test image is provided.

[0052] As an example, the image data processing platform uses an edge detection algorithm to extract edge curves of each ink uneven area in the test image. The edge detection algorithm may be a Canny edge detector.

[0053] Then, the interval distances between the edge curves in the uneven ink area are calculated, and the average of the interval distances between the edge curves is used as the density value of the uneven ink area. The larger the density value of the uneven ink area, the stronger the artifact phenomenon, that is, the higher the degree of loss of detail features in the uneven ink area.

[0054] Therefore, the image data processing platform presets the mapping relationship between the density value and the ink artifact annoyance coefficient. According to the density value of the ink uneven area and the preset mapping relationship, the ink artifact annoyance coefficient corresponding to the ink uneven area is obtained. For example, a linear or nonlinear function can be used for conversion to ensure that the denser the edge curve, the higher the ink artifact annoyance coefficient.

[0055] S104, determining the characteristic loss factor of each ink uneven region according to the ink artifact nuisance coefficient of each ink uneven region.

[0056] In this embodiment, the feature loss factor is used to characterize the degree of detail feature loss in a local area.

[0057] As an example, the image data processing platform presets a mapping relationship between the ink artifact nuisance coefficient and the characteristic loss factor. According to the value of the artifact nuisance coefficient and the preset mapping relationship, the artifact nuisance coefficient is converted into the characteristic loss factor. For example, a linear or nonlinear function can be used for conversion to ensure that severe artifacts correspond to higher loss factors.

[0058] S105, performing image correction on the test image according to the characteristic loss factor of each ink uneven area, so as to evaluate the state of the nozzle according to the image-corrected test image.

[0059] In this embodiment, the image data processing platform uses image restoration or enhancement technology to perform image correction on each uneven ink area according to the characteristic loss factor of each uneven ink area to improve the image quality, thereby evaluating the nozzle status based on the test image after image correction.

[0060] Specifically, for smaller areas of uneven ink, you can use interpolation or neighborhood pixel-based repair algorithms to fill them; for larger areas or global unevenness, you can try to adjust the image contrast, brightness or use filters to smooth the edges; at the same time, you can also use deep learning techniques, such as convolutional neural networks (CNN), to train models to automatically identify and correct different types of uneven ink problems.

[0061] In the intelligent evaluation method for the nozzle status of a digital printing machine provided in this embodiment, the uneven ink area in the pixel image caused by wear and aging is first determined based on the pixel value size of each image area in the test image. Then, based on the edge curve in the uneven ink area, the degree of influence of the artifacts in the uneven ink area on the regional features is analyzed to determine the characteristic loss factor of the uneven ink area. Finally, based on the characteristic loss factor of the uneven ink area, the test image is corrected to improve the clarity and accuracy of the image features of the test image. In this way, the embodiment of the present invention can improve the clarity and accuracy of the image features of the test image by identifying the uneven ink area in the test image and performing image correction on the test image based on the characteristic loss factor of the uneven ink area, thereby improving the accuracy of the nozzle status evaluation.

[0062] As an optional embodiment, Figure 4 As shown, S102 may specifically include the following S401-S403:

[0063] S401, dividing a test image into a plurality of image regions;

[0064] S402, determining the ink highlighting coefficient of each image area according to the pixel value of each image area;

[0065] S403: Determine the image region whose ink protrusion coefficient is greater than a preset ink threshold as an ink uneven region in the test image.

[0066] In this embodiment, the test image may be divided into images by using a fixed-size grid division method or an image segmentation algorithm. For example, the image segmentation algorithm may include a threshold-based segmentation algorithm, an edge-based segmentation algorithm, and a region-based segmentation algorithm.

[0067] The ink highlight coefficient is defined according to the pixel value statistics of the region and a preset rule. For example, the difference between the pixel value mean of the image region and the pixel value mean of the entire test image can be used as the ink highlight coefficient.

[0068] As an example, the image data processing platform uses superpixel segmentation technology to divide the test image into several image regions. Then, for each image region, the mean of the pixel values ​​of the image region is calculated according to the pixel values ​​of each pixel point in the image region; at the same time, for the entire test image, the mean of the pixel values ​​of the test image is calculated according to the pixel values ​​of each pixel point in the test image. Then, the mean of the pixel values ​​of the image region is subtracted from the mean of the pixel values ​​of the test image to obtain the ink protrusion coefficient of the image region.

[0069] Finally, the ink protrusion coefficient of each image area is compared with the preset ink threshold. If the ink protrusion coefficient of a certain image area is greater than the preset ink threshold, the image area is determined as an ink uneven area in the test image.

[0070] Through this embodiment, the ink protrusion coefficient of each image area is calculated according to the pixel value of each image area, so as to accurately determine whether the image area belongs to the ink uneven area according to the ink protrusion coefficient. In this way, this embodiment can accurately determine whether the image area belongs to the ink uneven area, which is helpful for the subsequent calculation of the characteristic loss factor of the ink uneven area, and perform image correction on the ink uneven area, thereby improving the accuracy of the nozzle status assessment.

[0071] As an optional embodiment, S402 may specifically include:

[0072] Acquire each second image region adjacent to the first image region, the first image region being any one of the image regions;

[0073] Calculating a pixel value difference between the first image area and the second image area according to a pixel value of the first image area and a pixel value of the second image area;

[0074] The average value of each pixel value difference is calculated to obtain the ink protrusion coefficient of the first image area.

[0075] In this embodiment, the ink protrusion coefficient can be determined by the following (1):

[0076] (1)

[0077] In the formula, To characterize the The ink protrusion coefficient of the first image area, M, is used to characterize the ink protrusion coefficient of the first image area. the number of second image regions adjacent to the first image regions, To characterize the The pixel value size of the first image area, For characterization and The pixel value size of the mth second image area adjacent to the mth first image area.

[0078] in, Indicates the difference between the first and second image regions and the The pixel value difference between the mth first image area and the mth second image area is accumulated. The pixel value difference between the first image regions. The larger the value, the The greater the difference in color saturation between the first image area and the surrounding adjacent second image areas, the greater the difference in color saturation between the first image area and the surrounding adjacent second image areas. The larger the ink prominence coefficient of the first image area is, the larger the ink prominence coefficient of the first image area is.

[0079] No. The ink highlight coefficient of the first image area The larger the value, the The more unnatural the color transition of the first image area is, the greater the possibility that it belongs to the uneven ink area.

[0080] Through this embodiment, by comparing the pixel value of the first image area with the pixel value of each adjacent second image area, the color saturation difference between the first image area and the surrounding adjacent second image areas can be accurately determined, so that the first image area can be accurately determined. The ink highlighting coefficient of the first image area is obtained, so as to help to accurately judge whether the image area belongs to the ink uneven area according to the ink highlighting coefficient.

[0081] As an optional embodiment, Figure 5 As shown, S103 may specifically include the following S501-S502:

[0082] S501, determining an artifact intensity coefficient of a target uneven region according to an edge curve in the target uneven region, where the target uneven region is any one of the ink uneven regions;

[0083] S502, determining an ink artifact nuisance coefficient of the target non-uniform region according to an artifact intensity coefficient of the target non-uniform region and an artifact intensity coefficient of a corresponding nuisance non-uniform region, wherein the nuisance non-uniform region is an ink artifact non-uniform region whose distance from the target non-uniform region meets a preset distance condition.

[0084] In this embodiment, the artifact intensity coefficient is a quantitative indicator for measuring the severity of artifacts in a region.

[0085] The disturbing uneven regions refer to other ink uneven regions whose distances from the target uneven regions meet a preset distance condition, and these ink uneven regions may cause artifact interference to the target uneven regions.

[0086] The ink artifact annoyance coefficient reflects the degree of interference of the target inhomogeneous area as a whole with the artifacts after the annoyance inhomogeneous area causes artifact interference to the target inhomogeneous area.

[0087] As an example, the image data processing platform selects a target uneven region from each ink uneven region, and then uses image processing technology (such as edge detection algorithm) to extract the edge curve of the selected target uneven region.

[0088] Then, based on the extracted edge curves, the artifact intensity coefficient of the target inhomogeneous area is calculated. Specifically, each edge curve of the target inhomogeneous area is differentiated to obtain its curvature change. The larger the curvature, the more discontinuous the edge and the more obvious the artifact. Then, the artifact intensity coefficient of the target inhomogeneous area is obtained by accumulating each curvature change.

[0089] Then, the image data processing platform sets a maximum distance threshold, and determines each ink uneven region whose distance from the target uneven region does not exceed the maximum distance threshold as a disturbing uneven region.

[0090] Finally, the artifact intensity coefficient of each disturbing non-uniform area is divided by the distance between the corresponding disturbing non-uniform area and the target non-uniform area, and then the average is calculated, and the artifact intensity coefficient of the target non-uniform area is multiplied by the average to obtain the ink artifact disturbance coefficient of the target non-uniform area.

[0091] Through this embodiment, the artifact intensity coefficient of the target uneven area is determined according to the edge curve in the target uneven area. Then, according to the artifact intensity coefficient of the target uneven area and the artifact intensity coefficient of the disturbing uneven area that will cause artifact interference to the target uneven area, the ink artifact disturbance coefficient of the target uneven area is determined. In this way, this embodiment can accurately determine the ink artifact disturbance coefficient of the ink uneven area, which is helpful for the subsequent determination of the characteristic loss factor of the ink uneven area according to the ink artifact disturbance coefficient, so that the test image can be accurately corrected, which can improve the accuracy of the nozzle status assessment.

[0092] As an optional embodiment, Figure 6 As shown, S501 may specifically include the following S601-S605:

[0093] S601, obtaining an edge curve in a target uneven area;

[0094] S602, performing linear fitting on each edge curve to obtain a fitting straight line corresponding to each edge curve;

[0095] S603, determining a slope prominence coefficient of each fitted straight line according to the straight line slope of each fitted straight line, where the slope prominence coefficient is used to characterize the prominence degree of the straight line slope in the target uneven area;

[0096] S604, determining each edge curve corresponding to the maximum slope protrusion coefficient as a target edge curve;

[0097] S605: Determine the artifact intensity coefficient of the target non-uniform area according to each target edge curve and the maximum slope protrusion coefficient.

[0098] In this embodiment, the target edge curve is an edge curve that can effectively reflect the artifact intensity of the target non-uniform area.

[0099] As an example, the image data processing platform uses an edge detection algorithm (such as the Canny edge detection algorithm or the Soble edge detection algorithm) to obtain edge curves of target uneven areas in the test image, and then uses the least squares method combined with linear fitting to obtain fitting straight lines corresponding to each edge curve in the target uneven area.

[0100] In a region, the artifact phenomenon usually manifests as multiple parallel edges with similar slopes. If the slope of a certain edge appears frequently, it means that there are many edge curves with the same slope in the region, and the curve is the target edge curve that can effectively reflect the artifact intensity of the target uneven region. Therefore, the image data processing platform further obtains the linear slope of each fitting straight line, and counts the frequency of occurrence of each linear slope, and determines the frequency of occurrence of each linear slope as the corresponding slope prominence coefficient.

[0101] Then, traverse each slope protrusion coefficient, and determine each edge curve corresponding to the maximum slope protrusion coefficient as the target edge curve. Finally, calculate the average distance between each target edge curve, divide the maximum slope protrusion coefficient by the average distance between each target edge curve, and you can get the artifact intensity coefficient of the target uneven area.

[0102] Through this embodiment, according to the linear slope of the fitting straight line corresponding to each edge curve in the target uneven area, the target edge curve that can effectively reflect the artifact intensity of the target uneven area is screened out. Therefore, according to the target edge curve and the slope protrusion coefficient corresponding to the target edge curve, the artifact intensity coefficient of the target uneven area can be accurately calculated. This helps to determine the characteristic loss factor of the ink uneven area according to the ink artifact nuisance coefficient, and then accurately correct the test image, which can improve the accuracy of the nozzle status assessment.

[0103] As an optional embodiment, S603 may specifically include:

[0104] The linear slopes of all the fitted lines except the target fitted line are averaged to determine the slope average, and the target fitted line is any one of the fitted lines;

[0105] The slope prominence coefficient of the target fitting straight line is determined according to the straight line slope and the slope mean of the target fitting straight line.

[0106] In this embodiment, the slope protrusion coefficient can be determined by the following (2):

[0107] (2)

[0108] In the formula, To characterize the The slope of the fitted straight line is the prominent coefficient, To characterize the The slope of the fitted straight line, v, is used to characterize the Each fitted straight line other than the fitted straight line, Used to characterize The mean slope of each fitted straight line other than the fitted straight line, Used to represent logarithmic operations.

[0109] Among them, The slope of the fitted line The larger the The mean slope of the fitted lines other than the fitted lines The smaller it is, the The more prominent the slope of the first fitting line is in the target uneven area, the more prominent the first fitting line is. The slope prominence coefficient of the fitted straight line The bigger.

[0110] No. The slope prominence coefficient of the fitted straight line The larger the slope, the more edge curves with the same slope exist in the target uneven area. The greater the probability that the edge curve corresponding to the fitted straight line belongs to the target edge curve.

[0111] Through this embodiment, the slope prominence coefficient of each fitted straight line can be accurately calculated according to the linear slope of each fitted straight line, which is helpful to subsequently screen out the target edge curve in the target inhomogeneous region that can effectively reflect the artifact intensity of the target inhomogeneous region according to the slope prominence coefficient, so as to accurately calculate the artifact intensity coefficient of the target inhomogeneous region.

[0112] As an optional embodiment, S605 may specifically include:

[0113] The distance between each target edge curve is averaged to obtain the edge density coefficient;

[0114] The variance of the lengths between each target edge curve is calculated to obtain the edge variation coefficient;

[0115] Divide the edge variation coefficient by the edge density coefficient to obtain a first calculated value;

[0116] The first calculated value is multiplied by the maximum slope prominence coefficient to obtain the artifact intensity coefficient of the target uneven area.

[0117] In this embodiment, the artifact intensity coefficient of the target non-uniform area can be determined by the following (3):

[0118] (3)

[0119] In the formula, The artifact intensity coefficient used to characterize the j-th target inhomogeneity area, It is used to characterize the maximum slope prominence coefficient in the jth target inhomogeneous region, The edge variation coefficient used to characterize the j-th target uneven area, The edge density coefficient used to characterize the j-th target uneven area.

[0120] Among them, the edge density coefficient of the jth target uneven area is It is the mean distance between the edge curves of each target in the j-th target uneven area. The smaller the edge density coefficient is, the denser the edge curves of each target in the target uneven area are, and the stronger the artifact phenomenon is. The edge variation coefficient of the j-th target uneven area is That is, it is the length variance between the target edge curves in the jth target inhomogeneous region. The larger the edge variation coefficient is, the more disordered the length data of the target edge curves in the target inhomogeneous region is, and the stronger the artifact phenomenon is.

[0121] Artifact intensity coefficient of the jth target inhomogeneous region The larger it is, the more serious the artifact phenomenon in the j-th target inhomogeneous area is, that is, the worse the image quality of the j-th target inhomogeneous area is.

[0122] Through this embodiment, the artifact intensity coefficient of the target inhomogeneous region can be accurately calculated according to the edge density coefficient, edge variation coefficient and maximum slope prominence coefficient of the target inhomogeneous region, so that the evaluation of the artifact intensity is more comprehensive and accurate, thereby accurately reflecting the artifact phenomenon and image quality of the target inhomogeneous region.

[0123] As an optional embodiment, S502 may specifically include:

[0124] Obtain the centroid coordinates of each ink uneven area;

[0125] Determine the interval distance between the target uneven area and each ink uneven area other than the target uneven area according to each centroid coordinate;

[0126] According to the order of the sizes of the interval distances, the N ink uneven areas with the smallest interval distances are determined as the disturbing uneven areas;

[0127] Divide the artifact intensity coefficient of each disturbing non-uniform area by the corresponding interval distance to obtain the influence coefficient of each disturbing non-uniform area;

[0128] Calculate the mean of each influence coefficient to obtain the average influence coefficient of the non-uniform disturbance area;

[0129] The influence average coefficient is multiplied by the artifact intensity coefficient of the target non-uniform area to obtain the ink artifact nuisance coefficient of the target non-uniform area.

[0130] In this embodiment, the image data processing platform first uses the space coordinate system to obtain the centroid coordinates of all the ink uneven areas in the test image, and then determines the interval distance between the target uneven area and each ink uneven area other than the target uneven area according to the centroid coordinates of each ink uneven area. And according to the order of the interval distance, the N ink uneven areas with the smallest interval distance from the target uneven area are determined as the disturbing uneven areas.

[0131] Then, the ink artifact nuisance coefficient of the target non-uniform area is determined by the following (4):

[0132] (4)

[0133] In the formula, To characterize the The ink artifact annoyance coefficient of the target non-uniform area, To characterize the The artifact intensity coefficient of the target inhomogeneous area, N is used to represent the number of disturbing inhomogeneous areas, To characterize the The artifact intensity coefficient of the disturbing non-uniform area, To characterize the The target uneven area and the The spacing distance between the disturbing uneven areas.

[0134] in, It is used to represent the ratio of the artifact intensity coefficient of each disturbing non-uniform area to the corresponding interval distance. The smaller the interval distance between the target non-uniform area and the disturbing non-uniform area, the closer the target non-uniform area is to the disturbing non-uniform area, and the greater the influence of the disturbing non-uniform area on the target non-uniform area, that is, the ink artifact disturbance coefficient of the target non-uniform area will increase accordingly.

[0135] No. The ink artifact annoyance coefficient of the target non-uniform area The larger the value, the The greater the overall interference degree of the jth target inhomogeneous region by the artifacts, that is, the worse the image quality of the jth target inhomogeneous region.

[0136] Through this embodiment, the ink artifact nuisance influence of the target uneven area itself and the ink artifact nuisance influence from the surrounding disturbing uneven areas are combined, and the real ink artifact nuisance influence degree of the target uneven area is effectively measured, thereby improving the accuracy of the ink artifact nuisance coefficient, so that the image quality of the target uneven area can be accurately evaluated.

[0137] As an optional embodiment, S104 may specifically include:

[0138] The ink artifact annoyance coefficient of each ink uneven area is multiplied by the corresponding ink protrusion coefficient to obtain the characteristic loss factor corresponding to each ink uneven area.

[0139] In this embodiment, the characteristic loss factor can be specifically determined by the following (5):

[0140] (5)

[0141] In the formula, The characteristic loss factor used to characterize the i-th ink uneven area, The ink protrusion coefficient used to characterize the i-th ink uneven area, The ink artifact nuisance coefficient used to characterize the i-th ink uneven area.

[0142] Among them, the larger the ink protrusion coefficient is, the more serious the artifact phenomenon in the uneven ink area is, that is, the corresponding feature loss factor will be larger; the larger the ink artifact annoyance coefficient is, the greater the impact on the details of the uneven ink area is, that is, the corresponding feature loss factor will also be larger.

[0143] Through this embodiment, the characteristic loss factor corresponding to each uneven ink area can be accurately calculated based on the ink artifact nuisance coefficient and the ink protrusion coefficient of the uneven ink area. Therefore, the test image can be accurately corrected based on the characteristic loss factor corresponding to the uneven ink area to improve the accuracy of the nozzle status assessment.

[0144] As an optional embodiment, S105 may specifically include:

[0145] Multiply the characteristic loss factor of the ink uneven area by the maximum standard deviation of the corresponding Gaussian filter to obtain the corrected standard deviation corresponding to the ink uneven area;

[0146] The test image is corrected according to the corrected standard deviation of each ink uneven area, so that the state of the nozzle can be evaluated according to the test image after the image correction.

[0147] In this embodiment, the image data processing platform multiplies the characteristic loss factor of each ink uneven area by the maximum standard deviation of the corresponding Gaussian filter, thereby obtaining the corrected standard deviation corresponding to each ink uneven area. In this way, a set of element weights that obey the corrected standard deviation can be generated according to the Gaussian filter, and the data can be processed by weighted average to obtain the test image after filtering adjustment.

[0148] Among them, the maximum standard deviation of the Gaussian filter can be determined by the following (6):

[0149] (6)

[0150] In the formula, represents the maximum standard deviation of the Gaussian filter, and L represents the area of ​​the Gaussian filter.

[0151] Among them, in Gaussian filtering, the sum of the weights of all elements is 1, so theoretically the maximum filtering strength of Gaussian filtering should be infinitely close to "the weight of the central element is 1, and the weights of the other elements are 0". That is, when the weight of the central element is 1, the square difference between the central weight and the weight mean is That is, it represents the sum of the squared differences between the remaining L-1 elements and the weight mean when their weights are 0, so It represents the variance of the weights of all elements in the Gaussian filter when the weight of the central element of the Gaussian filter is 1. The maximum standard deviation can be obtained by taking the square root of the variance.

[0152] Maximum standard deviation of Gaussian filtering The larger the value is, the larger the correction standard deviation of the corresponding ink uneven area will be, and thus the image adjustment strategy of the corresponding ink uneven area will also change accordingly.

[0153] Through this embodiment, the characteristic loss factor of the ink uneven area is multiplied by the maximum standard deviation of the corresponding Gaussian filter to obtain the corrected standard deviation corresponding to the ink uneven area, so as to adjust the test image using the corrected standard deviation corresponding to each ink uneven area. In this way, the image quality of the ink uneven image is improved according to the characteristic loss factor, and the improved test image is used to evaluate the nozzle status, which can improve the evaluation accuracy of the nozzle status.

[0154] A method for intelligently evaluating the state of a printhead of a digital printing machine. Accordingly, the present invention also provides a specific embodiment of an intelligent device for evaluating the state of a printhead of a digital printing machine.

[0155] Figure 7A structural schematic diagram of an intelligent evaluation device for the nozzle status of a digital printing machine is provided. The intelligent evaluation device 700 for the nozzle status of a digital printing machine may include an image acquisition module 710, an area determination module 720, a coefficient determination module 730, a loss determination module 740 and an image correction module 750.

[0156] The image acquisition module 710 is used to acquire a test image printed by a target digital printing machine.

[0157] The region determination module 720 is used to determine the ink uneven region in the test image according to the pixel value size of each image region in the test image.

[0158] The coefficient determination module 730 is used to determine the ink artifact annoyance coefficient of each ink uneven area according to the edge curve in each ink uneven area. The ink artifact annoyance coefficient is used to characterize the degree of interference of the ink uneven area by the artifact.

[0159] The loss determination module 740 is used to determine the characteristic loss factor of each ink uneven area according to the ink artifact nuisance coefficient of each ink uneven area.

[0160] The image correction module 750 is used to perform image correction on the test image according to the characteristic loss factor of each ink uneven area, so as to evaluate the state of the nozzle according to the image-corrected test image.

[0161] As an optional embodiment, the region determination module 720 specifically includes the following units:

[0162] A region division unit, used for dividing a test image into a plurality of image regions;

[0163] A coefficient determination unit, used to determine the ink highlight coefficient of each image area according to the pixel value of each image area;

[0164] The area determination unit is used to determine the image area whose ink protrusion coefficient is greater than a preset ink threshold as the ink uneven area in the test image.

[0165] As an optional embodiment, the coefficient determination unit specifically includes the following units:

[0166] A region acquisition subunit, used to acquire each second image region adjacent to the first image region, the first image region being any one of the image regions;

[0167] A difference calculation subunit, used to calculate the pixel value difference between the first image area and the second image area according to the pixel value size of the first image area and the pixel value size of the second image area;

[0168] The coefficient determination subunit is used to calculate the average of the differences in pixel values ​​to obtain the ink protrusion coefficient of the first image area.

[0169] As an optional embodiment, the coefficient determination module 730 specifically includes the following units:

[0170] An intensity coefficient determination unit, used for determining an artifact intensity coefficient of a target uneven region according to an edge curve in the target uneven region, wherein the target uneven region is any one of the ink uneven regions;

[0171] The disturbance coefficient determination unit is used to determine the ink artifact disturbance coefficient of the target uneven area according to the artifact intensity coefficient of the target uneven area and the artifact intensity coefficient of the corresponding disturbance uneven area, wherein the disturbance uneven area is an ink uneven area whose distance from the target uneven area meets a preset distance condition.

[0172] As an optional embodiment, the intensity coefficient determination unit specifically includes the following subunits:

[0173] A curve acquisition subunit, used for acquiring edge curves in the target uneven area;

[0174] A straight line fitting subunit is used to perform linear fitting on each edge curve to obtain a fitting straight line corresponding to each edge curve;

[0175] A protrusion coefficient determination subunit is used to determine the slope protrusion coefficient of each fitted straight line according to the straight line slope of each fitted straight line, and the slope protrusion coefficient is used to characterize the protrusion degree of the straight line slope in the target uneven area;

[0176] A curve determination subunit, used for determining each edge curve corresponding to the maximum slope protrusion coefficient as a target edge curve;

[0177] The intensity coefficient determination subunit is used to determine the artifact intensity coefficient of the target uneven area according to each target edge curve and the maximum slope protrusion coefficient.

[0178] As an optional embodiment, the protrusion coefficient determination subunit is specifically used for:

[0179] The linear slopes of all the fitted lines except the target fitted line are averaged to determine the slope average, and the target fitted line is any one of the fitted lines;

[0180] The slope prominence coefficient of the target fitting straight line is determined according to the straight line slope and the slope mean of the target fitting straight line.

[0181] As an optional embodiment, the intensity coefficient determination subunit is specifically used for:

[0182] The distance between each target edge curve is averaged to obtain the edge density coefficient;

[0183] The variance of the lengths between each target edge curve is calculated to obtain the edge variation coefficient;

[0184] Divide the edge variation coefficient by the edge density coefficient to obtain a first calculated value;

[0185] The first calculated value is multiplied by the maximum slope prominence coefficient to obtain the artifact intensity coefficient of the target uneven area.

[0186] As an optional embodiment, the nuisance coefficient determination unit specifically includes the following subunits:

[0187] A coordinate acquisition subunit, used to acquire the centroid coordinates of each ink uneven area;

[0188] A distance determination subunit, used to determine the interval distance between the target uneven area and each ink uneven area other than the target uneven area according to each centroid coordinate;

[0189] The area screening subunit is used to determine N ink uneven areas with the smallest interval distance as disturbing uneven areas according to the order of the size of each interval distance;

[0190] A coefficient calculation subunit, used for dividing the artifact intensity coefficient of each disturbing non-uniform area by the corresponding interval distance to obtain the influence coefficient of each disturbing non-uniform area;

[0191] The coefficient calculation subunit is also used to calculate the average of each influence coefficient to obtain the influence average coefficient of the disturbance non-uniform area;

[0192] The nuisance coefficient determination subunit is used to multiply the influence average coefficient by the artifact intensity coefficient of the target uneven area to obtain the ink artifact nuisance coefficient of the target uneven area.

[0193] A method for intelligently evaluating the state of a printhead of a digital printing machine. Accordingly, the present invention also provides a specific embodiment of an intelligent system for evaluating the state of a printhead of a digital printing machine.

[0194] like Figure 8 As shown, a structural schematic diagram of an intelligent evaluation system for the nozzle status of a digital printing machine is provided. The intelligent evaluation system for the nozzle status of a digital printing machine includes a data acquisition module, an image data processing platform, an intelligent evaluation module and a user interface.

[0195] A data acquisition module, used for acquiring a test image printed by a target digital printing machine;

[0196] An image data processing platform, used to execute the intelligent evaluation method for the printhead status of a digital printing machine provided in any of the above embodiments;

[0197] An intelligent evaluation module is used to evaluate the state of the printhead according to the test image processed by the image data processing platform to obtain a printhead evaluation result;

[0198] A user interface is provided for displaying the results of the sprinkler evaluation.

[0199] In this embodiment, the data acquisition module first acquires the test image printed by the target digital printing machine, and then pre-processes the image data of the acquired test image and sends it to the image data processing platform. After receiving the test image, the image data processing platform will extract the features of the test image, and then determine the feature loss factor of the test image based on the extracted features, perform data adaptive smoothing on the test image based on the feature loss factor, and send the processed test image to the intelligent evaluation module. The intelligent evaluation module evaluates the state of the nozzle based on the received image, obtains the nozzle evaluation result, and finally outputs it to the user interface for display.

[0200] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0201] It should also be noted that the exemplary embodiments mentioned in the present invention describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiments, or in a different order from the embodiments, or several steps can be performed simultaneously.

[0202] The above is only a specific implementation of the present invention. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the system, module and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be covered within the protection scope of the present invention.

Claims

1. A method for intelligently evaluating the status of a printhead of a digital printing machine, characterized in that: The method comprises: Obtain a test image printed by a target digital printing machine; Determining an ink uneven area in the test image according to the pixel value of each image area in the test image; Determine, according to the edge curves in each of the ink uneven regions, an ink artifact annoyance coefficient of each of the ink uneven regions, wherein the ink artifact annoyance coefficient is used to characterize the degree to which the ink uneven region is disturbed by artifacts; Determining the characteristic loss factor of each of the ink uneven regions according to the ink artifact nuisance coefficient of each of the ink uneven regions; According to the characteristic loss factor of each of the ink uneven areas, the test image is corrected so that the state of the nozzle can be evaluated according to the test image after the image correction; The step of determining the ink uneven area in the test image according to the pixel value of each image area in the test image comprises: Dividing the test image into a plurality of image regions; Determining the ink highlighting coefficient of each image area according to the pixel value of each image area; Determine the image region where the ink protrusion coefficient is greater than a preset ink threshold as an ink uneven region in the test image; Determining the ink artifact annoyance coefficient of each of the ink uneven regions according to the edge curves in each of the ink uneven regions includes: Determine an artifact intensity coefficient of a target uneven region according to an edge curve in the target uneven region, wherein the target uneven region is any one of the ink uneven regions; The ink artifact disturbance coefficient of the target uneven area is determined according to the artifact intensity coefficient of the target uneven area and the artifact intensity coefficient of the corresponding disturbance uneven area, wherein the disturbance uneven area is an ink uneven area whose distance from the target uneven area meets a preset distance condition.

2. The method for intelligently evaluating the status of a printhead of a digital printing machine according to claim 1, characterized in that: Determining the ink highlighting coefficient of each image area according to the pixel value of each image area includes: Acquire each second image region adjacent to the first image region, the first image region being any one of the image regions; Calculating a pixel value difference between the first image area and the second image area according to a pixel value of the first image area and a pixel value of the second image area; The average of the pixel value differences is calculated to obtain the ink protrusion coefficient of the first image area.

3. The method for intelligently evaluating the status of a printhead of a digital printing machine according to claim 1, characterized in that: Determining the artifact intensity coefficient of the target uneven region according to the edge curve in the target uneven region includes: Acquire an edge curve in the target uneven area; Performing linear fitting on each of the edge curves to obtain a fitting straight line corresponding to each of the edge curves; Determining a slope prominence coefficient of each of the fitting straight lines according to the straight line slopes of the fitting straight lines, wherein the slope prominence coefficient is used to characterize the prominence degree of the straight line slope in the target uneven area; Determine each edge curve corresponding to the largest slope protrusion coefficient as a target edge curve; The artifact intensity coefficient of the target non-uniform area is determined according to each of the target edge curves and the maximum slope protrusion coefficient.

4. The method for intelligently evaluating the status of a printhead of a digital printing machine according to claim 3, characterized in that: Determining the slope prominence coefficient of each of the fitting straight lines according to the straight line slopes of the fitting straight lines comprises: Calculating the average of the straight line slopes of the fitted straight lines except the target fitted straight line to determine the slope average, wherein the target fitted straight line is any one of the fitted straight lines; The slope prominence coefficient of the target fitting straight line is determined according to the straight line slope of the target fitting straight line and the slope mean.

5. The method for intelligently evaluating the status of a printhead of a digital printing machine according to claim 3, characterized in that: Determining the artifact intensity coefficient of the target uneven area according to each of the target edge curves and the maximum slope protrusion coefficient includes: Calculating the mean of the distances between the target edge curves to obtain an edge density coefficient; Calculating the variance of the lengths between the target edge curves to obtain edge variation coefficients; Dividing the edge variation coefficient by the edge density coefficient to obtain a first calculated value; The first calculated value is multiplied by the maximum slope prominence coefficient to obtain the artifact intensity coefficient of the target uneven area.

6. The method for intelligently evaluating the status of a printhead of a digital printing machine according to claim 1, characterized in that: The step of determining the ink artifact nuisance coefficient of the target non-uniform region according to the artifact intensity coefficient of the target non-uniform region and the artifact intensity coefficient of the corresponding nuisance non-uniform region comprises: Obtaining the centroid coordinates of each of the uneven ink regions; Determining the interval distance between the target uneven area and each of the ink uneven areas other than the target uneven area according to each of the centroid coordinates; According to the order of the size of each of the spacing distances, the N ink uneven areas with the smallest spacing distances are determined as disturbing uneven areas; N represents a positive integer; Dividing the artifact intensity coefficient of each of the disturbing non-uniform regions by the corresponding interval distance to obtain the influence coefficient of each of the disturbing non-uniform regions; Calculating the average of the influence coefficients to obtain the average influence coefficient of the non-uniform disturbance area; The influence average coefficient is multiplied by the artifact intensity coefficient of the target non-uniform area to obtain the ink artifact nuisance coefficient of the target non-uniform area.

7. The method for intelligently evaluating the status of a printhead of a digital printing machine according to claim 6, characterized in that: The calculation formula for determining the ink artifact nuisance coefficient of the target uneven area is: In the formula, To characterize the The ink artifact annoyance coefficient of the target non-uniform area, To characterize the The artifact intensity coefficient of the target inhomogeneous area, N is used to represent the number of disturbing inhomogeneous areas, To characterize the The artifact intensity coefficient of the disturbing non-uniform area, To characterize the The target uneven area and the The spacing distance between the disturbing uneven areas.

8. The method for intelligently evaluating the status of a printhead of a digital printing machine according to claim 1, characterized in that: The characteristic loss factor is calculated as: In the formula, The characteristic loss factor used to characterize the i-th ink uneven area, The ink protrusion coefficient used to characterize the i-th ink uneven area, The ink artifact nuisance coefficient used to characterize the i-th ink uneven area.

9. An intelligent evaluation device for the state of a printhead of a digital printing machine, used to execute the intelligent evaluation method for the state of a printhead of a digital printing machine according to any one of claims 1 to 8, characterized in that: The device comprises: An image acquisition module, used to acquire a test image printed by a target digital printing machine; A region determination module, used for determining the ink uneven region in the test image according to the pixel value size of each image region in the test image; A coefficient determination module, used for determining an ink artifact annoyance coefficient of each of the ink uneven regions according to the edge curves in each of the ink uneven regions, wherein the ink artifact annoyance coefficient is used for characterizing the degree of interference of the ink uneven region by the artifact; A loss determination module, used to determine the characteristic loss factor of each of the ink uneven areas according to the ink artifact nuisance coefficient of each of the ink uneven areas; The image correction module is used to perform image correction on the test image according to the characteristic loss factor of each of the ink uneven areas, so as to evaluate the state of the nozzle according to the test image after the image correction.

10. An intelligent evaluation system for the nozzle status of a digital printing machine, characterized in that: The system includes a data acquisition module, an image data processing platform, an intelligent evaluation module and a user interface; The data acquisition module is used to acquire the test image printed by the target digital printing machine; The image data processing platform is used to execute the intelligent evaluation method for the printhead status of a digital printing machine according to any one of claims 1 to 8 above; The intelligent evaluation module is used to evaluate the state of the printhead according to the test image processed by the image data processing platform to obtain a printhead evaluation result; The user interface is used to display the nozzle evaluation result.

Images