Printing quality evaluation monitoring system and method based on image analysis

Abstract

The invention discloses a printing quality evaluation monitoring system and method based on image analysis, and belongs to the technical field of digital printing quality detection.The method comprises the steps that an image of a printed product is collected, preprocessed and imported into an image segmentation model to be segmented; calculating Chinese character font similarity through a similarity calculation strategy, comparing the Chinese character font similarity with a font similarity threshold, and screening out an image corresponding to the Chinese character font similarity meeting the standard according to a comparison result; calculating the Chinese character printing standard degree according to the Chinese character printing standard degree calculation strategy; according to the method, before all the Chinese characters are comprehensively monitored, the similar Chinese characters are screened out, so that the data volume needing to be processed can be reduced, and the evaluation efficiency is improved; through the image segmentation model, Chinese characters in the image can be segmented more accurately, and high-precision printing quality detection is realized.

Description

Technical Field

[0001] The invention belongs to the technical field of digital printing quality detection, and in particular relates to a printing quality evaluation and monitoring system and method based on image analysis. Background Art

[0002] The Chinese character printing quality assessment standard mainly focuses on the Chinese character printing quality of printed materials, including the standardization of fonts, clarity, and consistency with the original manuscript. The Chinese character printing quality assessment standard aims to improve the viewing and usability of printed materials. It is also related to the reputation and market competitiveness of printing companies.

[0003] Most of the existing Chinese character printing quality assessments are to monitor the quality of each Chinese character through layer extraction and segmentation. Before comprehensively monitoring all Chinese characters, the existing technology cannot screen out similar Chinese characters that are easily confused, and thus cannot perform printing quality assessment on similar Chinese characters, resulting in low assessment efficiency. For example, a Chinese patent with authorization announcement number CN117495852B discloses a digital printing quality detection method based on image analysis. The method first obtains a digital printing image to be tested, uses an image layering algorithm to extract layers of the digital printing image to be tested, performs center segmentation on the extracted layers, and fuses pixel-similar regions to obtain a processed image to be tested; uses a matching model to perform geometric transformation matching on the processed image to be tested to obtain a position-matched image to be tested; obtains a grayscale image of the matched image to be tested, and performs pixel point quality detection by calculating grayscale difference values, thereby improving the accuracy and efficiency of digital printing quality detection and judgment.

[0004] In order to solve the above problems, the present invention designs a printing quality evaluation and monitoring system and method based on image analysis. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention proposes a printing quality evaluation and monitoring system and method based on image analysis. The present invention collects images of printed products, pre-processes the images and imports them into an image segmentation model for segmentation; calculates Chinese character glyph similarity through a similarity calculation strategy, compares the Chinese character glyph similarity with a glyph similarity threshold, and screens out images corresponding to Chinese character glyph similarities that meet the standards according to the comparison results; calculates Chinese character printing standards according to a Chinese character printing standard calculation strategy; and evaluates printing quality according to the calculated Chinese character printing standards. Before comprehensively monitoring all Chinese characters, the present invention first screens out similar Chinese characters, which can reduce the amount of data that needs to be processed and improve evaluation efficiency; and through the image segmentation model, the Chinese characters in the image can be more accurately segmented to achieve high-precision printing quality detection.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A printing quality assessment and monitoring method based on image analysis comprises the following specific steps:

[0008] Step 1: Collect images of printed products, pre-process the images, import the pre-processed images into the image segmentation model for segmentation, and store the images obtained after segmentation in a segmented image storage module;

[0009] Step 2: import the segmented image into the Chinese character glyph similarity calculation strategy to calculate the Chinese character glyph similarity, compare the calculated Chinese character glyph similarity with a preset glyph similarity threshold, and store the image corresponding to the Chinese character glyph similarity greater than the glyph similarity threshold in a similar image storage module;

[0010] Step 3, obtaining an image corresponding to a Chinese character with a similarity greater than a character similarity threshold, and importing the corresponding image into a Chinese character printing standard degree calculation strategy to calculate the Chinese character printing standard degree;

[0011] Step 4: Evaluate the printing quality based on the calculated Chinese character printing standard.

[0012] Specifically, the step 1 includes the following specific steps:

[0013] S11, collecting images of printed products and preprocessing the images, wherein the preprocessing is to convert the images into black and white images by a binarization method;

[0014] S12, importing the preprocessed image into an image segmentation model for segmentation, the image segmentation model segments the image into two parts: a target image area and a background image area, the image segmentation model includes an image segmentation formula, the image segmentation formula is:

[0015]

[0016] in, is the image segmentation result, k + is the grayscale average of the target image area, k - is the grayscale average value of the background image area, arctan is the inverse tangent function, ε is a constant, φ(x) is the signed distance function constructed according to the initial contour curve of the evolution curve S(x,y), and the evolution function S(x,y) is: S(x,y)=α1∫ targ(c) |Fk + | 2 dxdy+α2∫ back(c) |Fk - | 2 dxdy,

[0017] Where x is the horizontal coordinate of the evolution function, y is the vertical coordinate of the evolution function, α1 is the weight coefficient of the target image area, α2 is the weight coefficient of the background image area, targ(c) is the target image area of ​​the evolution curve, back(c) is the background image area of ​​the evolution curve, F is the gray value of the image, and dxdy is the curve integral of the coordinates;

[0018] S13, storing the plurality of images obtained after segmentation in a segmented image storage module.

[0019] Specifically, the step 2 includes the following specific steps:

[0020] S21, importing the segmented image into a Chinese character glyph similarity calculation strategy to calculate Chinese character glyph similarity, wherein the Chinese character glyph similarity calculation strategy includes a Chinese character glyph similarity calculation formula, and the Chinese character glyph similarity calculation formula is:

[0021]

[0022] Among them, Q zx (z1,z2) is the Chinese character shape similarity between Chinese characters z1 and z2, len max is the longest common substring length of Chinese characters z1 and z2, is the stroke order code of Chinese character z1, is the stroke order code of Chinese character z2, The Chinese character with the short stroke order code in Chinese characters z1 and z2, is the proportion of common substrings, is the stroke difference between Chinese characters z1 and z2, is the stroke difference ratio, ham is the Hamming distance between Chinese characters z1 and z2, is the Hamming distance ratio, β1 is the common substring ratio, β2 is the stroke difference ratio, β3 is the Hamming distance ratio, β1+β2+β3=1;

[0023] S22, comparing the calculated Chinese character glyph similarity with a preset glyph similarity threshold, and storing images corresponding to Chinese character glyph similarities greater than the glyph similarity threshold in a similar image storage module.

[0024] Specifically, the step three includes the following specific steps:

[0025] An image corresponding to a Chinese character with a glyph similarity greater than a glyph similarity threshold is obtained, and the corresponding image is introduced into a Chinese character printing standard degree calculation strategy to calculate the Chinese character printing standard degree, wherein the Chinese character printing standard degree calculation strategy includes a Chinese character printing standard degree calculation formula, and the Chinese character printing standard degree calculation formula is: Among them, i is the horizontal coordinate of the image, j is the vertical coordinate of the image, M(i,j) is the pixel value of the Chinese character template image coordinate (i,j), and C(i,j) is the pixel value of the Chinese character image to be tested with coordinate (i,j).

[0026] Specifically, the step 4 includes the following specific steps:

[0027] The average value of the Chinese character printing standard degree is calculated and compared with the preset average threshold value of the Chinese character printing standard degree. If the average value of the Chinese character printing standard degree is greater than or equal to the preset average threshold value of the Chinese character printing standard degree, the printed product is judged to be qualified; if the average value of the Chinese character printing standard degree is less than the preset average threshold value of the Chinese character printing standard degree, the printed product is judged to be unqualified.

[0028] Specifically, the method for selecting the values ​​of α1, α2, β1, β2, β3, glyph similarity threshold, Chinese character printing standard threshold and minimum Chinese character printing standard sum threshold is as follows: select 1500 printed products, import the images into the image segmentation model for segmentation, substitute them into the similarity calculation strategy to calculate the Chinese character glyph similarity, compare the Chinese character glyph similarity with the glyph similarity threshold, screen out images corresponding to the Chinese character glyph similarity that meets the standards according to the comparison results, substitute them into the Chinese character printing standard calculation strategy to calculate the Chinese character printing standard, compare the Chinese character printing standard with the Chinese character printing standard threshold, evaluate the printing quality according to the comparison results, invite 100 printing experts to screen out incorrectly printed Chinese characters from 1500 printed products and evaluate the printed products, import the printing quality evaluated by the system and the results of the expert evaluation into the fitting software, compare and output a set of α1, α2, β1, β2, β3, glyph similarity threshold, Chinese character printing standard threshold and minimum Chinese character printing standard sum threshold with the highest judgment accuracy.

[0029] A printing quality evaluation and monitoring system based on image analysis, which is implemented based on the above-mentioned printing quality evaluation and monitoring method based on image analysis, comprises an image acquisition module, an image preprocessing module, an image segmentation module, an image storage module, a Chinese character glyph similarity calculation module, a Chinese character printing standardization module, a printing evaluation module and a control module;

[0030] Specifically, the image acquisition module is used to acquire images of printed products, the image preprocessing module is used to preprocess the acquired images, the image segmentation module is used to import the preprocessed images into the image segmentation model for segmentation, the Chinese character glyph similarity calculation module is used to import the segmented images into the Chinese character glyph similarity calculation strategy to calculate the Chinese character glyph similarity, the image storage module is used to store the segmented images and images corresponding to the Chinese character glyph similarities greater than the glyph similarity threshold, the Chinese character printing standard degree module is used to obtain images corresponding to the Chinese character glyph similarities greater than the glyph similarity threshold, import the corresponding images into the Chinese character printing standard degree calculation strategy to calculate the Chinese character printing standard degree, and the printing evaluation module is used to evaluate the printing quality according to the calculated Chinese character printing standard degree;

[0031] Specifically, the control module is used to control the operation of the image acquisition module, the image preprocessing module, the image segmentation module, the image storage module, the Chinese character shape similarity calculation module, the Chinese character printing standardization module and the printing evaluation module.

[0032] An electronic device comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes the above-mentioned printing quality assessment and monitoring method based on image analysis by calling the computer program stored in the memory.

[0033] A computer-readable storage medium stores instructions. When the instructions are executed on a computer, the computer is enabled to execute the above-mentioned printing quality assessment and monitoring method based on image analysis.

[0034] The beneficial effects of the present invention are:

[0035] The present invention collects images of printed products, pre-processes the images and imports them into an image segmentation model for segmentation; calculates Chinese character glyph similarity through a similarity calculation strategy, compares the Chinese character glyph similarity with a glyph similarity threshold, and selects images corresponding to Chinese character glyph similarities that meet the standards according to the comparison results; calculates Chinese character printing standard degrees according to a Chinese character printing standard degree calculation strategy; and evaluates printing quality according to the calculated Chinese character printing standard degrees;

[0036] The present invention selects similar Chinese characters before comprehensively monitoring all Chinese characters, thereby reducing the amount of data to be processed and improving evaluation efficiency.

[0037] The present invention adopts image preprocessing technology to make the input image clearer, which helps to improve the accuracy of subsequent segmentation and recognition.

[0038] The present invention can more accurately segment Chinese characters in an image through an image segmentation model, and by performing pixel-level analysis and evaluation on each Chinese character, it reduces the situations of mis-segmentation and missed segmentation, and can achieve high-precision printing quality detection.

[0039] The present invention can timely discover problems and feed back to operators through real-time evaluation of printing quality, which is helpful to timely adjust and improve printing quality and improve the accuracy and real-time performance of printing quality control.

[0040] The present invention can adapt to different types and styles of printed materials by updating and upgrading the algorithm model and can be flexibly applied to different printing scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0042] Figure 1 A schematic diagram of a printing quality assessment and monitoring method based on image analysis according to the present invention;

[0043] Figure 2 The figure is a schematic diagram of the overall framework of a printing quality assessment and monitoring system based on image analysis according to the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions 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 part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0045] Example 1

[0046] See also Figure 1 The present invention provides an embodiment: a printing quality assessment and monitoring method based on image analysis, which comprises the following specific steps:

[0047] Step 1: Collect images of printed products, pre-process the images, import the pre-processed images into the image segmentation model for segmentation, and store the images obtained after segmentation in a segmented image storage module;

[0048] In this embodiment, step one includes the following specific steps:

[0049] S11, collecting images of printed products and preprocessing the images, wherein the preprocessing includes converting the images into black and white images by a binarization method;

[0050] It should be noted here that the process of converting an image into a black and white image by binarization method mainly includes the following steps:

[0051] Read the original image: First, you need to use an image processing library (such as PIL or OpenCV) to read the image to be processed;

[0052] Convert color images to grayscale images: Before binarization, it is usually necessary to convert color images to grayscale images, because grayscale images have only one channel and are easier to process later. You can use the convert('L') method of the PIL library to convert images to grayscale images.

[0053] Threshold processing of grayscale images: Select a suitable threshold to determine whether a pixel should be converted to black or white. Common threshold processing methods include global threshold and adaptive threshold.

[0054] Binarize the thresholded image: After thresholding, pixels with values ​​greater than the threshold can be set to white (255), and pixels with values ​​less than or equal to the threshold can be set to black (0), thereby obtaining a binary image. The image can be converted to a binary image using the convert('1') method of the PIL library.

[0055] Save the binarized image: Finally, save the binarized image.

[0056] It should be further explained here that this method uses image preprocessing technology to make the input image clearer, which helps to improve the accuracy of subsequent segmentation and recognition.

[0057] S12, importing the preprocessed image into the image segmentation model for segmentation, the image segmentation model divides the image into two parts: the target image area and the background image area, the image segmentation model includes an image segmentation formula, and the image segmentation formula is:

[0058]

[0059] in, is the image segmentation result, k + is the grayscale average of the target image area, k -is the grayscale average of the background image area, arctan is the inverse tangent function, ε is a constant, φ(x) is the signed distance function constructed based on the initial contour curve of the evolution curve S(x,y), and the evolution function S(x,y) is: S(x,y)=α1∫ targ(c) |Fk + | 2 dxdy+α2∫ back(c) |Fk - | 2 dxdy,

[0060] Where x is the horizontal coordinate of the evolution function, y is the vertical coordinate of the evolution function, α1 is the weight coefficient of the target image area, α2 is the weight coefficient of the background image area, generally, α1=α2=1, targ(c) is the target image area of ​​the evolution curve, back(c) is the background image area of ​​the evolution curve, F is the gray value of the image, and dxdy is the curve integral of the coordinates;

[0061] It should be noted here that importing the binarized image into the image segmentation model for segmentation usually includes the following specific steps:

[0062] Image loading: Use image processing libraries (such as OpenCV, MATLAB, ITK, etc.) to load binarized image files;

[0063] Model loading: Loading a trained image segmentation model, including loading pre-trained weight files and configuring the model structure;

[0064] Image input: Input the preprocessed image into the image segmentation model and convert the image data into the input format required by the model, such as into a floating-point tensor;

[0065] Model reasoning: Run the model for reasoning, and generate segmentation results based on the input image, which may include convolution operations, pooling operations, activation functions, etc.

[0066] Result analysis: Based on the segmentation results output by the model, the segmentation mask or segmentation category label is obtained through analysis, which is usually presented in the form of probability map, category label matrix or pixel-level label.

[0067] Post-processing: Post-process the segmentation results, such as applying morphological operations (dilation, erosion, etc.) to remove small holes or connect separated small areas.

[0068] Save results: Save the segmentation results in image format or directly in the database for subsequent analysis and use.

[0069] It should be further explained here that this method utilizes an efficient image segmentation model to more accurately segment the Chinese characters in the image. By performing pixel-level analysis and evaluation on each Chinese character, it reduces the chances of mis-segmentation and missed segmentation, and can achieve high-precision printing quality detection.

[0070] S13, storing the plurality of images obtained after segmentation in a segmented image storage module.

[0071] Step 2: import the segmented image into the Chinese character glyph similarity calculation strategy to calculate the Chinese character glyph similarity, compare the calculated Chinese character glyph similarity with a preset glyph similarity threshold, and store the image corresponding to the Chinese character glyph similarity greater than the glyph similarity threshold in a similar image storage module;

[0072] In this embodiment, step 2 includes the following specific steps:

[0073] S21, importing the segmented image into a Chinese character glyph similarity calculation strategy to calculate the Chinese character glyph similarity, the Chinese character glyph similarity calculation strategy includes a Chinese character glyph similarity calculation formula, and the Chinese character glyph similarity calculation formula is:

[0074]

[0075] Among them, Q zx (z1,z2) is the Chinese character shape similarity between Chinese characters z1 and z2, len max is the longest common substring length of Chinese characters z1 and z2, is the stroke order code of Chinese character z1, is the stroke order code of Chinese character z2, The Chinese character with the short stroke order code in Chinese characters z1 and z2, is the proportion of common substrings, is the stroke difference between Chinese characters z1 and z2, is the stroke difference ratio, ham is the Hamming distance between Chinese characters z1 and z2, is the Hamming distance ratio, β1 is the common substring ratio, β2 is the stroke difference ratio, β3 is the Hamming distance ratio, β1+β2+β3=1;

[0076] S22, comparing the calculated Chinese character glyph similarity with a preset glyph similarity threshold, and storing images corresponding to Chinese character glyph similarities greater than the glyph similarity threshold in a similar image storage module.

[0077] Step 3, obtaining an image corresponding to a Chinese character with a similarity greater than a character similarity threshold, and importing the corresponding image into a Chinese character printing standard degree calculation strategy to calculate the Chinese character printing standard degree;

[0078] In this embodiment, step three includes the following specific steps:

[0079] An image corresponding to a Chinese character glyph similarity greater than a glyph similarity threshold is obtained, and the corresponding image is imported into a Chinese character printing standard degree calculation strategy to calculate the Chinese character printing standard degree. The Chinese character printing standard degree calculation strategy includes a Chinese character printing standard degree calculation formula, and the Chinese character printing standard degree calculation formula is: Among them, i is the horizontal coordinate of the image, j is the vertical coordinate of the image, M(i,j) is the pixel value of the Chinese character template image coordinate (i,j), and C(i,j) is the pixel value of the Chinese character image to be tested with coordinate (i,j).

[0080] Step 4: Evaluate the printing quality based on the calculated Chinese character printing standard.

[0081] In this embodiment, step 4 includes the following specific steps:

[0082] The average value of the Chinese character printing standard degree is calculated and compared with the preset average threshold value of the Chinese character printing standard degree. If the average value of the Chinese character printing standard degree is greater than or equal to the preset average threshold value of the Chinese character printing standard degree, the printed product is judged to be qualified; if the average value of the Chinese character printing standard degree is less than the preset average threshold value of the Chinese character printing standard degree, the printed product is judged to be unqualified.

[0083] It should be noted here that the method for determining the values ​​of α1, α2, β1, β2, β3, the glyph similarity threshold and the average threshold of the Chinese character printing standard is as follows: 1500 printed products are selected, the images are imported into the image segmentation model for segmentation, the images are substituted into the similarity calculation strategy to calculate the Chinese character glyph similarity, the Chinese character glyph similarity is compared with the glyph similarity threshold, and the images corresponding to the Chinese character glyph similarity that meets the standards are screened out according to the comparison results, and the images are substituted into the Chinese character printing standard calculation strategy to calculate the Chinese character printing standard, the Chinese character printing standard is compared with the Chinese character printing standard threshold, the printing quality is evaluated according to the comparison results, 100 printing experts are invited to screen out incorrectly printed Chinese characters from the 1500 printed products and evaluate the printed products, the printing quality evaluated by the system and the results of the expert evaluation are imported into the fitting software, and a set of α1, α2, β1, β2, β3, the glyph similarity threshold and the average threshold of the Chinese character printing standard with the highest judgment accuracy is output.

[0084] It should be further explained here that by instantly evaluating the printing quality, timely discovering problems and feeding them back to the operators, it is helpful to adjust and improve the printing quality in a timely manner and improve the accuracy and real-time nature of printing quality control.

[0085] Example 2

[0086] See also Figure 2A printing quality assessment and monitoring system based on image analysis is implemented based on the above-mentioned printing quality assessment and monitoring method based on image analysis, and includes an image acquisition module, an image preprocessing module, an image segmentation module, an image storage module, a Chinese character glyph similarity calculation module, a Chinese character printing standardization module, a printing assessment module and a control module.

[0087] In this embodiment, the image acquisition module is used to acquire images of printed products, the image preprocessing module is used to preprocess the acquired images, the image segmentation module is used to import the preprocessed images into the image segmentation model for segmentation, the Chinese character glyph similarity calculation module is used to import the segmented images into the Chinese character glyph similarity calculation strategy to calculate the Chinese character glyph similarity, the image storage module is used to store the segmented images and the images corresponding to the Chinese character glyph similarities greater than the glyph similarity threshold, the Chinese character printing standard module is used to obtain the images corresponding to the Chinese character glyph similarities greater than the glyph similarity threshold, import the corresponding images into the Chinese character printing standard calculation strategy to calculate the Chinese character printing standard, and the printing evaluation module is used to evaluate the printing quality according to the calculated Chinese character printing standard.

[0088] In this embodiment, the control module is used to control the operation of the image acquisition module, the image preprocessing module, the image segmentation module, the image storage module, the Chinese character shape similarity calculation module, the Chinese character printing standardization module and the printing evaluation module.

[0089] Example 3

[0090] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes the above-mentioned printing quality assessment and monitoring method based on image analysis by calling the computer program stored in the memory.

[0091] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, and the computer program is loaded and executed by the processor to implement a printing quality assessment and monitoring method based on image analysis provided in the above method embodiment. The electronic device may also include other components for realizing the functions of the device. For example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface to input and output data, which will not be described in detail in this embodiment.

[0092] Example 4

[0093] This embodiment provides a computer-readable storage medium storing instructions, which, when a computer program is executed on a computer device, enables the computer device to execute the above-mentioned printing quality assessment and monitoring method based on image analysis;

[0094] For example, the computer readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0095] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function according to the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or / and a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available media may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0096] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the contents of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that technicians in the relevant technical field can well understand and use the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A printing quality assessment and monitoring method based on image analysis, characterized in that: The specific steps include: Step 1: Collect images of printed products, preprocess the images, and import the preprocessed images into the image segmentation model for segmentation; Step 2: import the segmented image into the Chinese character glyph similarity calculation strategy to calculate the Chinese character glyph similarity, compare the calculated Chinese character glyph similarity with a preset glyph similarity threshold, and select the image corresponding to the Chinese character glyph similarity that meets the preset standard according to the comparison result; Step 3, obtaining an image corresponding to a Chinese character with a similarity greater than a character similarity threshold, and importing the corresponding image into a Chinese character printing standard degree calculation strategy to calculate the Chinese character printing standard degree; Step 4: Evaluate the printing quality based on the calculated Chinese character printing standard.

2. A printing quality assessment and monitoring method based on image analysis as claimed in claim 1, characterized in that: The step 1 includes the following specific steps: S11, collecting images of printed products and preprocessing the images, wherein the preprocessing is to convert the images into black and white images by a binarization method; S12, importing the preprocessed image into an image segmentation model for segmentation, the image segmentation model segments the image into two parts: a target image area and a background image area, the image segmentation model includes an image segmentation formula, the image segmentation formula is: in, is the image segmentation result, k + is the grayscale average of the target image area, k - is the grayscale average value of the background image area, arctan is the inverse tangent function, ε is a constant, φ(x) is the signed distance function constructed according to the initial contour curve of the evolution curve S(x,y), and the evolution function S(x,y) is: S(x,y)=α1∫ targ(c) |Fk + | 2 dxdy+α2∫ back(c) |Fk - | 2 dxdy, Where x is the horizontal coordinate of the evolution function, y is the vertical coordinate of the evolution function, α1 is the weight coefficient of the target image area, α2 is the weight coefficient of the background image area, targ(c) is the target image area of ​​the evolution curve, back(c) is the background image area of ​​the evolution curve, F is the gray value of the image, and dxdy is the curve integral of the coordinates; S13, storing the plurality of images obtained after segmentation in a segmented image storage module.

3. A printing quality assessment and monitoring method based on image analysis as claimed in claim 2, characterized in that: The step 2 includes the following specific steps: S21, importing the segmented image into a Chinese character glyph similarity calculation strategy to calculate Chinese character glyph similarity, wherein the Chinese character glyph similarity calculation strategy includes a Chinese character glyph similarity calculation formula, and the Chinese character glyph similarity calculation formula is: Among them, Q zx (z1,z2) is the Chinese character shape similarity between Chinese characters z1 and z2, len max is the longest common substring length of Chinese characters z1 and z2, is the stroke order code of Chinese character z1, is the stroke order code of Chinese character z2, The Chinese character with the short stroke order code in Chinese characters z1 and z2, is the proportion of common substrings, is the stroke difference between Chinese characters z1 and z2, is the stroke difference ratio, ham is the Hamming distance between Chinese characters z1 and z2, is the Hamming distance ratio, β1 is the common substring ratio, β2 is the stroke difference ratio, β3 is the Hamming distance ratio, β1+β2+β3=1; S22, comparing the calculated Chinese character glyph similarity with a preset glyph similarity threshold, and storing images corresponding to Chinese character glyph similarities greater than the glyph similarity threshold in a similar image storage module.

4. A printing quality assessment and monitoring method based on image analysis as claimed in claim 3, characterized in that: The step three includes the following specific steps: An image corresponding to a Chinese character with a glyph similarity greater than a glyph similarity threshold is obtained, and the corresponding image is introduced into a Chinese character printing standard degree calculation strategy to calculate the Chinese character printing standard degree, wherein the Chinese character printing standard degree calculation strategy includes a Chinese character printing standard degree calculation formula, and the Chinese character printing standard degree calculation formula is: Among them, i is the horizontal coordinate of the image, j is the vertical coordinate of the image, M(i,j) is the pixel value of the Chinese character template image coordinate (i,j), and C(i,j) is the pixel value of the Chinese character image to be tested with coordinate (i,j).

5. A printing quality assessment and monitoring method based on image analysis as claimed in claim 4, characterized in that: The step 4 includes the following specific steps: The average value of the Chinese character printing standard degree is calculated and compared with the preset average threshold value of the Chinese character printing standard degree. If the average value of the Chinese character printing standard degree is greater than or equal to the preset average threshold value of the Chinese character printing standard degree, the printed product is judged to be qualified; if the average value of the Chinese character printing standard degree is less than the preset average threshold value of the Chinese character printing standard degree, the printed product is judged to be unqualified.

6. A printing quality assessment and monitoring system based on image analysis, which is implemented based on the printing quality assessment and monitoring method based on image analysis as claimed in any one of claims 1 to 5, characterized in that: The invention comprises an image acquisition module, an image preprocessing module, an image segmentation module, an image storage module, a Chinese character glyph similarity calculation module, a Chinese character printing standardization module, a printing evaluation module and a control module. The image acquisition module is used for acquiring images of printed products, the image preprocessing module is used for preprocessing the acquired images, the image segmentation module is used for importing the preprocessed images into an image segmentation model for segmentation, and the Chinese character glyph similarity calculation module is used for importing the segmented images into a Chinese character glyph similarity calculation strategy for calculating the Chinese character glyph similarity.

7. A printing quality assessment and monitoring system based on image analysis as claimed in claim 6, characterized in that: The image storage module is used to store the segmented images and images corresponding to the Chinese character glyph similarity greater than the glyph similarity threshold. The Chinese character printing standard module is used to obtain images corresponding to the Chinese character glyph similarity greater than the glyph similarity threshold, and import the corresponding images into the Chinese character printing standard calculation strategy to calculate the Chinese character printing standard. The printing evaluation module is used to evaluate the printing quality according to the calculated Chinese character printing standard.

8. A printing quality assessment and monitoring system based on image analysis as claimed in claim 7, characterized in that: The control module is used to control the operation of the picture acquisition module, the picture preprocessing module, the picture segmentation module, the picture storage module, the Chinese character shape similarity calculation module, the Chinese character printing standardization module and the printing evaluation module.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program that can be called by the processor, and the processor executes the printing quality assessment and monitoring method based on image analysis as described in any one of claims 1 to 5 by calling the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer is caused to execute a printing quality assessment and monitoring method based on image analysis as described in any one of claims 1 to 5.

Images