Digital printing process regulation and control method and system based on image analysis

Abstract

The invention relates to the technical field of textile printing, in particular to a digital printing process regulation and control method and system based on image analysis, and the method comprises the following steps: carrying out near-infrared analysis on pre-constructed standard cloth by using a multispectral camera to obtain a standard ink absorption degree, carrying out light-transmitting pore test on the standard cloth by using a backlight plate and a high-definition camera to obtain a standard porosity, and carrying out light-transmitting pore test on the standard porosity. Carrying out image edge detection on the current printing image to obtain an edge diffusion index, carrying out difference identification on the current printing image to obtain an image difference index, calculating an image qualification degree according to the edge diffusion index and the image difference index, comparing the image qualification degree with a preset qualification threshold value, and if the image qualification degree is greater than or equal to the qualification threshold value, determining that the current printing image is not qualified; if yes, the target printed cloth serves as qualified printed cloth, the qualified printed cloth is collected, multiple pieces of qualified printed cloth are obtained, and regulation and control over the digital printing technology are completed. According to the invention, the automation degree of regulation and control of the printing process can be improved, and the quality of printed products is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of textile printing, and particularly relates to a digital printing process regulation method and system based on image analysis. BACKGROUND

[0002] As an important processing technology in the modern textile industry, digital printing has the advantages of flexibility, efficiency, environmental protection, etc., and is widely used in personalized customization, small-batch printing and complex pattern processing fields. However, due to the differences between different fabric materials, it often leads to quality problems such as edge diffusion, pattern distortion and color deviation of the printed image, which affects the quality of the final printed product.

[0003] Traditional digital printing processes often rely on manual experience to set the inkjet amount and printing speed during the printing process, and fixed printing process parameters are set for similar fabrics.

[0004] Although the prior art can regulate the printing process, it is difficult to fine-tune the printing process parameters according to the slight differences between fabrics when printing similar fabrics, and there is a lack of real-time feedback means for the printing process, making it difficult to achieve intelligent and closed-loop control. Therefore, there is an urgent need for a digital printing process regulation method that combines image analysis to improve the automation of printing process regulation and improve the quality of printed products. SUMMARY

[0005] The present application provides a digital printing process regulation method based on image analysis and a computer readable storage medium, which aims to improve the automation of printing process regulation and improve the quality of printed products.

[0006] To achieve the above purpose, the present application provides a digital printing process regulation method based on image analysis, which comprises:

[0007] A multispectral camera, a backlight plate and a high-definition camera are obtained, the backlight plate comprising a light-emitting surface;

[0008] The standard fabric is pre-constructed and near-infrared analysis is performed using the multispectral camera to obtain the standard ink absorption;

[0009] The standard fabric is tested for light transmission aperture using the backlight plate and high-definition camera to obtain the standard aperture;

[0010] An initial fabric set and a digital printing device are obtained, and the initial fabric set is evaluated for printing state to obtain a target fabric set, a test ink absorption and a test aperture;

[0011] The target fabric is extracted from the target fabric set, and the target fabric set after the target fabric is extracted is used as an updated fabric set, and the target fabric is pre-processed to obtain a fabric to be printed;

[0012] The digital printing device is set up according to the preset standard inkjet volume, preset standard printing speed, standard ink absorption, standard porosity, test ink absorption, and test porosity to obtain the target printing device.

[0013] The target printing device is used to digitally print on the fabric to be printed, and the target printed fabric is obtained. A high-definition camera is used to acquire the current printed image of the target printed fabric.

[0014] Image edge detection is performed on the current printed image to obtain the edge diffusion index, and difference recognition is performed on the current printed image to obtain the image difference index;

[0015] The image passability is calculated based on the edge diffusion index and the image difference index, and the image passability is compared with the preset passability threshold.

[0016] If the image qualification is greater than or equal to the qualification threshold, the target printed fabric is regarded as a qualified printed fabric; otherwise, the printing speed is optimized according to the edge diffusion index, the optimized printing speed is used as the standard printing speed, the updated fabric set is used as the target fabric set, the target printing device is used as the digital printing device, and the step of extracting the target fabric from the target fabric set is returned until the target fabric set no longer contains the target fabric.

[0017] By compiling qualified printed fabrics, multiple qualified printed fabrics are obtained, and the digital printing process is controlled.

[0018] Optionally, the step of using a multispectral camera to perform near-infrared analysis on a pre-constructed standard fabric to obtain standard ink absorbance includes:

[0019] Based on a preset set of near-infrared wavelengths and a multispectral camera, near-infrared images are taken of standard fabric to obtain multiple near-infrared images. The set of near-infrared wavelengths includes multiple near-infrared wavelengths, and each near-infrared wavelength corresponds one-to-one with a near-infrared image.

[0020] For each of the multiple near-infrared images, perform the following operation:

[0021] A grayscale operation is performed on a near-infrared image to obtain a grayscale image, wherein the grayscale image includes multiple grayscale pixels;

[0022] Identify the center pixel, top-left pixel, bottom-left pixel, top-right pixel, and bottom-right pixel in a grayscale image;

[0023] Multiple neighboring points were identified based on the center pixel. The neighboring points are grayscale pixels in the grayscale image that are adjacent to the center pixel.

[0024] Based on the top-left pixel, bottom-left pixel, top-right pixel, and bottom-right pixel, obtain multiple top-left neighboring points, multiple bottom-left neighboring points, multiple top-right neighboring points, and multiple bottom-right neighboring points respectively;

[0025] By summarizing the center pixel, top-left pixel, bottom-left pixel, top-right pixel, bottom-right pixel, center neighbor, top-left neighbor, bottom-left neighbor, top-right neighbor, and bottom-right neighbor, multiple evaluation pixels are obtained;

[0026] Multiple evaluation grayscale values ​​are determined based on multiple evaluation pixels, where each evaluation grayscale value corresponds one-to-one with an evaluation pixel, and the evaluation grayscale value is the grayscale value of the evaluation pixel.

[0027] The near-infrared pixel value is calculated based on multiple evaluation grayscale values, where the near-infrared pixel value is the average of the multiple evaluation grayscale values;

[0028] The near-infrared wavelength corresponding to the near-infrared image is combined with the near-infrared pixel value to obtain a near-infrared spectral group;

[0029] By summarizing the near-infrared spectral groups, multiple near-infrared spectral groups were obtained;

[0030] Curve fitting is performed on a pre-constructed spectral coordinate system based on multiple near-infrared spectral groups to obtain near-infrared spectral curves, where the horizontal axis of the spectral coordinate system represents the near-infrared wavelength and the vertical axis represents the near-infrared pixel value.

[0031] Characteristic peak analysis was performed on the near-infrared spectrum curves to obtain the standard ink absorption.

[0032] Optionally, the step of performing characteristic peak analysis on the near-infrared spectral curve to obtain the standard ink absorbance includes:

[0033] Based on the preset hydrophobic wavelength range, the hydrophobic feature region is identified in the infrared spectrum curve, and the hydrophobic feature area of ​​the hydrophobic feature region is identified.

[0034] The first water absorption characteristic area and the second water absorption characteristic area are obtained based on the preset first water absorption wavelength range and the preset second water absorption wavelength range, respectively.

[0035] The standard ink absorption is calculated based on the hydrophobic characteristic area, the first water-absorbing characteristic area, and the second water-absorbing characteristic area.

[0036] Optionally, the step of using a backlight panel and a high-definition camera to test the light transmittance porosity of a standard fabric to obtain standard porosity includes:

[0037] A standard fabric is laid flat and fixed on the light-emitting surface of the backlight panel to obtain a fixed fabric, wherein the plane on which the fixed fabric is located is parallel to the light-emitting surface;

[0038] A high-definition camera is used to photograph a fixed piece of fabric to obtain an image of the translucent fabric;

[0039] A grayscale operation is performed on the image of the translucent fabric to obtain a translucent grayscale image, which includes multiple translucent pixels.

[0040] Multiple light-transmitting grayscale values ​​are identified based on multiple light-transmitting pixels. Each light-transmitting grayscale value corresponds one-to-one with a light-transmitting pixel, and the light-transmitting grayscale value is the grayscale value of the light-transmitting pixel.

[0041] The average transmittance gray value is calculated based on multiple transmittance gray values, where the average transmittance gray value is the average of the multiple transmittance gray values;

[0042] Perform the following operation on each of the multiple light-transmitting pixels:

[0043] Compare the light-transmitting gray value corresponding to the light-transmitting pixel with the average light-transmitting gray value. If the light-transmitting gray value corresponding to the light-transmitting pixel is greater than or equal to the average light-transmitting gray value, then the light-transmitting pixel is recorded as a light-emitting pixel.

[0044] Summarize the luminous pixels to obtain multiple luminous pixels, confirm the number of luminous pixels, and confirm the original number of multiple light-transmitting pixels.

[0045] Standard porosity is calculated based on the amount of light emitted and the original amount.

[0046] Optionally, the step of evaluating the printing status of the initial fabric set to obtain the target fabric set, test ink absorption, and test porosity includes:

[0047] Extract the initial cloth from the initial cloth set, and use the initial cloth set after extraction as the target cloth set;

[0048] The ink absorption and porosity were measured using the initial fabric, a multispectral camera, a backlight, and a high-definition camera.

[0049] Optionally, the step of setting the digital printing device according to preset standard inkjet volume, preset standard printing speed, standard ink absorption, standard porosity, test ink absorption, and test porosity to obtain the target printing device includes:

[0050] Confirm the current operating humidity and current operating temperature of the digital printing device;

[0051] Calculate the target inkjet volume based on the current operating humidity, current operating temperature, and standard inkjet volume.

[0052] The target printing speed is calculated based on the standard inkjet volume, target inkjet volume, standard printing speed, standard ink absorption, standard porosity, test ink absorption, and test porosity.

[0053] The digital printing device is set using the target ink volume and target printing speed to obtain the target printing device.

[0054] Optionally, the step of performing image edge detection on the current printed image to obtain the edge diffusion index includes:

[0055] Perform a grayscale conversion operation on the current printed image to obtain a grayscale printed image;

[0056] A pre-constructed edge recognition algorithm is used to perform edge recognition on the grayscale image of the printed pattern to obtain the set of edge pixels.

[0057] Perform the following operation on each edge pixel in the edge pixel set:

[0058] Obtain multiple edge-near pixels based on edge pixels, and obtain multiple edge-near pixel values ​​based on multiple edge-near pixels;

[0059] Identify the edge pixel values ​​of edge pixels and calculate the edge diffusion based on the values ​​of multiple edge neighboring pixels and the edge pixel values;

[0060] The edge diffusion degree is summarized to obtain multiple edge diffusion degrees. The edge diffusion index is calculated based on the multiple edge diffusion degrees, where the edge diffusion index is the average value of the multiple edge diffusion degrees.

[0061] To achieve the above objectives, the present invention also provides a digital printing process control system based on image analysis, comprising:

[0062] The standard fabric testing module is used to acquire data from a multispectral camera, a backlight panel, and a high-definition camera. The backlight panel includes a light-emitting surface. The multispectral camera is used to perform near-infrared analysis on the pre-constructed standard fabric to obtain the standard ink absorption. The backlight panel and the high-definition camera are used to perform light transmission porosity testing on the standard fabric to obtain the standard porosity.

[0063] The initial fabric evaluation module is used to acquire the initial fabric set and digital printing device, evaluate the printing status of the initial fabric set, obtain the target fabric set, test the ink absorption and test the porosity, extract the target fabric from the target fabric set, and use the target fabric set after extracting the target fabric as the updated fabric set. The target fabric is pre-processed to obtain the fabric to be printed.

[0064] The printing device control module is used to set the digital printing device according to the preset standard ink jet volume, preset standard printing speed, standard ink absorption, standard porosity, test ink absorption, and test porosity to obtain the target printing device. The target printing device is used to perform digital printing on the fabric to be printed to obtain the target printed fabric. The current printed image of the target printed fabric is obtained using a high-definition camera.

[0065] The printed fabric feedback module is used to perform image edge detection on the current printed image to obtain an edge diffusion index, perform difference recognition on the current printed image to obtain an image difference index, calculate the image passability based on the edge diffusion index and the image difference index, compare the image passability with a preset passability threshold, and if the image passability is greater than or equal to the passability threshold, then the target printed fabric is considered a passable printed fabric; otherwise, the printing speed is optimized based on the edge diffusion index, the optimized printing speed is used as the standard printing speed, the updated fabric set is used as the target fabric set, the target printing device is used as the digital printing device, and the process returns to the step of extracting the target fabric from the target fabric set until no target fabric is found in the target fabric set. The passable printed fabrics are then aggregated to obtain multiple passable printed fabrics, thus completing the control of the digital printing process. To solve the above problems, the present invention also provides an electronic device, which includes:

[0066] Memory, storing at least one instruction;

[0067] The processor executes the instructions stored in the memory to implement the image analysis-based digital printing process control method described above.

[0068] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the image analysis-based digital printing process control method described above.

[0069] To address the problems described in the background section, this invention utilizes a multispectral camera, a backlight panel, and a high-definition camera. The backlight panel includes a light-emitting surface. This invention prepares for subsequent near-infrared analysis and light transmittance porosity testing by acquiring the multispectral camera, backlight panel, and high-definition camera. The multispectral camera is then used to perform near-infrared analysis on a pre-constructed standard fabric to obtain standard ink absorption. The backlight panel and high-definition camera are used to perform light transmittance porosity testing on the standard fabric to obtain standard porosity. Thus, this invention obtains standard ink absorption and standard porosity without damaging the fabric by performing near-infrared analysis and light transmittance porosity testing on the standard fabric. Subsequently, the difference between the standard fabric and the initial fabric is compared to adjust the inkjet volume and printing speed. The degree of automation in controlling the printing process is improved by adjusting the degree of control. Simultaneously, the differences between different fabrics are considered, and the printing process is adaptively adjusted according to these differences, thereby improving the quality of the printed products. An initial fabric set and digital printing device are obtained, and the printing status of the initial fabric set is evaluated to obtain the target fabric set, test ink absorption, and test porosity. It can be seen that this embodiment of the invention evaluates the ink absorption capacity and porosity of the initial fabric by obtaining the test ink absorption and test porosity of the initial fabric set, facilitating precise control of parameters in the subsequent printing process and improving the quality of the final printed products. The target fabric is extracted from the target fabric set, and the target fabric set after the extraction of the target fabric is used as the updated fabric set. The standard fabric is pre-processed to obtain the fabric to be printed. The digital printing device is set to print according to preset standard inkjet volume, preset standard printing speed, standard ink absorption, standard porosity, test ink absorption, and test porosity to obtain the target printing device. It can be seen that this embodiment of the invention calculates the ideal inkjet volume and printing speed in advance before printing by using standard printing speed, standard ink absorption, standard porosity, test ink absorption, and test porosity, and sets the printing device accordingly, thereby improving the quality of the printed product. The target printing device is used to digitally print on the fabric to be printed to obtain the target printed fabric. A high-definition camera is used to acquire the current printed image of the target printed fabric, and image edge detection is performed on the current printed image to obtain the edge diffusion index. The current printed image undergoes difference recognition to obtain an image difference index. Based on the edge diffusion index and the image difference index, the image passability is calculated. The image passability is then compared with a preset passability threshold. This embodiment of the invention uses a high-definition camera to acquire the current printed image of the target printed fabric and performs real-time analysis to calculate the image passability. This facilitates automated selection of qualified printed fabrics based on the image passability and the passability threshold, improving the automation level of printing process control. If the image passability is greater than or equal to the passability threshold, the target printed fabric is considered qualified; otherwise, the printing speed is optimized based on the edge diffusion index, and this optimized printing speed is used as the standard printing speed. The updated fabric set is then used as the target fabric set.Using the target printing device as a digital printing device, the process returns to the step of extracting the target fabric from the target fabric set until no target fabric remains in the set. Qualified printed fabrics are then collected, resulting in multiple qualified printed fabrics. This completes the control of the digital printing process. It is evident that this embodiment of the invention optimizes the printing speed by calculating the edge diffusion index and replaces the standard printing speed with the optimized speed, thereby optimizing the printing effect when the target fabric is extracted from the target fabric set for printing next time, thus improving the quality of the printed product. Therefore, this invention can improve the automation level of printing process control and enhance the quality of printed products. Attached Figure Description

[0070] Figure 1 A flowchart illustrating a digital printing process control method based on image analysis provided in an embodiment of the present invention;

[0071] Figure 2 A functional block diagram of a digital printing process control system based on image analysis provided in an embodiment of the present invention;

[0072] Figure 3 This is a schematic diagram of the structure of an electronic device that implements the image analysis-based digital printing process control method according to an embodiment of the present invention.

[0073] Explanation of reference numerals in the attached figures:

[0074] 1. Electronic equipment; 10. Processor; 11. Memory; 12. Bus; 100. Digital printing process control system based on image analysis; 101. Standard fabric testing module; 102. Initial fabric evaluation module; 103. Printing device control module; 104. Printed fabric feedback module.

[0075] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0076] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0077] This application provides a digital printing process control method based on image analysis. The executing entity of the image analysis-based digital printing process control method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the image analysis-based digital printing process control method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0078] Reference Figure 1 The diagram shown is a flowchart illustrating a digital printing process control method based on image analysis according to an embodiment of the present invention. In this embodiment, the digital printing process control method based on image analysis includes:

[0079] S1. Acquire a multispectral camera, a backlight panel, and a high-definition camera. The backlight panel includes an emitting surface.

[0080] It should be explained that a multispectral camera is a type of multispectral imager; optionally, the ColorSpectrum Technology FS-1A hyperspectral camera can be used as the multispectral camera. The side of the backlight that emits light is the light-emitting surface. A high-definition camera is a type of high-definition video camera.

[0081] S2. Near-infrared analysis of the pre-constructed standard fabric is performed using a multispectral camera to obtain the standard ink absorption.

[0082] In this embodiment of the invention, the fabric includes cotton, linen, silk, wool, or polyester fabrics.

[0083] It should be understood that, due to the different materials or properties of different fabrics, the amount of ink used and the printing speed will vary slightly for different fabrics during printing. Therefore, this embodiment of the invention pre-analyzes a standard fabric to obtain a standard ink absorption and a standard porosity, and then adjusts the amount of ink used and the printing speed by comparing the difference between the standard fabric and the initial fabric.

[0084] For example, if the printing factory previously printed a certain fabric at a preset inkjet volume and preset printing speed, and the printed product was deemed qualified by manual inspection, then that fabric can be used as the standard fabric, the preset inkjet volume as the standard inkjet volume, and the preset printing speed as the standard printing speed. The preset inkjet volume and the preset printing speed are related to the model of the digital printing machine and are manually set by the printing factory's staff.

[0085] It should be explained that standard fabric refers to the standard ink volume and preset standard printing speed historically used by the printing factory.

[0086] In detail, the near-infrared analysis of the pre-constructed standard fabric using a multispectral camera to obtain standard ink absorbance includes:

[0087] Based on a preset set of near-infrared wavelengths and a multispectral camera, near-infrared images are taken of standard fabric to obtain multiple near-infrared images. The set of near-infrared wavelengths includes multiple near-infrared wavelengths, and each near-infrared wavelength corresponds one-to-one with a near-infrared image.

[0088] For each of the multiple near-infrared images, perform the following operation:

[0089] A grayscale operation is performed on a near-infrared image to obtain a grayscale image, wherein the grayscale image includes multiple grayscale pixels;

[0090] Identify the center pixel, top-left pixel, bottom-left pixel, top-right pixel, and bottom-right pixel in a grayscale image;

[0091] Multiple neighboring points were identified based on the center pixel. The neighboring points are grayscale pixels in the grayscale image that are adjacent to the center pixel.

[0092] Based on the top-left pixel, bottom-left pixel, top-right pixel, and bottom-right pixel, obtain multiple top-left neighboring points, multiple bottom-left neighboring points, multiple top-right neighboring points, and multiple bottom-right neighboring points respectively;

[0093] By summarizing the center pixel, top-left pixel, bottom-left pixel, top-right pixel, bottom-right pixel, center neighbor, top-left neighbor, bottom-left neighbor, top-right neighbor, and bottom-right neighbor, multiple evaluation pixels are obtained;

[0094] Multiple evaluation grayscale values ​​are determined based on multiple evaluation pixels, where each evaluation grayscale value corresponds one-to-one with an evaluation pixel, and the evaluation grayscale value is the grayscale value of the evaluation pixel.

[0095] The near-infrared pixel value is calculated based on multiple evaluation grayscale values, where the near-infrared pixel value is the average of the multiple evaluation grayscale values;

[0096] The near-infrared wavelength corresponding to the near-infrared image is combined with the near-infrared pixel value to obtain a near-infrared spectral group;

[0097] By summarizing the near-infrared spectral groups, multiple near-infrared spectral groups were obtained;

[0098] Curve fitting is performed on a pre-constructed spectral coordinate system based on multiple near-infrared spectral groups to obtain near-infrared spectral curves, where the horizontal axis of the spectral coordinate system represents the near-infrared wavelength and the vertical axis represents the near-infrared pixel value.

[0099] Characteristic peak analysis was performed on the near-infrared spectrum curves to obtain the standard ink absorption.

[0100] For example, if the near-infrared wavelength set is {1400nm, 1420nm, 1440nm…2000nm}, a multispectral camera is used to take a picture of the standard fabric in the 1400nm infrared spectral band to obtain a near-infrared image. Then, the standard fabric is photographed again in the 1420nm infrared spectral band, and so on, until the standard fabric is photographed again in the 2000nm infrared spectral band. After that, all the near-infrared images are combined to obtain multiple near-infrared images.

[0101] It should be explained that performing grayscale operation on the near-infrared image means converting each pixel in the near-infrared image to grayscale. Furthermore, the technique for performing grayscale operation on the near-infrared image to obtain a grayscale image is existing technology and will not be elaborated upon here. The center pixel is the grayscale pixel located at the geometric center of the grayscale image; the top-left pixel is the grayscale pixel located at the top-left corner of the grayscale image; the bottom-left pixel is the grayscale pixel located at the bottom-left corner of the grayscale image; the top-right pixel is the grayscale pixel located at the top-right corner of the grayscale image; and the bottom-right pixel is the grayscale pixel located at the bottom-right corner of the grayscale image.

[0102] It should be understood that the methods for obtaining multiple top-left neighboring points based on the top-left pixel, the methods for obtaining multiple bottom-left neighboring points based on the bottom-left pixel, the methods for obtaining multiple top-right neighboring points based on the top-right pixel, and the methods for obtaining multiple bottom-right neighboring points based on the bottom-right pixel are all the same as the method for identifying multiple center neighboring points based on the center pixel, and will not be repeated here. The evaluation pixel is categorized as the center pixel, top-left pixel, bottom-left pixel, top-right pixel, bottom-right pixel, center neighboring point, top-left neighboring point, bottom-left neighboring point, top-right neighboring point, or bottom-right neighboring point.

[0103] For example, the near-infrared spectral group is [1400 nm, 150 nm].

[0104] It should be explained that the spectral coordinate system is a coordinate system with near-infrared wavelength as the horizontal axis and near-infrared pixel value as the vertical axis. The phrase "based on multiple near-infrared spectral groups to perform curve fitting on the pre-constructed spectral coordinate system to obtain a near-infrared spectral curve" means that multiple near-infrared spectral groups are mapped as multiple coordinate points on the spectral coordinate system, and multiple coordinate points are fitted into a curve using a polynomial fitting method. The curve and the spectral coordinate system together constitute the near-infrared spectral curve. The method of fitting multiple coordinate points into a curve using a polynomial fitting method is existing technology and will not be elaborated here.

[0105] In detail, the analysis of characteristic peaks in the near-infrared spectral curve to obtain the standard ink absorbance includes:

[0106] Based on the preset hydrophobic wavelength range, the hydrophobic feature region is identified in the infrared spectrum curve, and the hydrophobic feature area of ​​the hydrophobic feature region is identified.

[0107] The first water absorption characteristic area and the second water absorption characteristic area are obtained based on the preset first water absorption wavelength range and the preset second water absorption wavelength range, respectively.

[0108] The standard ink absorption is calculated based on the hydrophobic characteristic area, the first water-absorbing characteristic area, and the second water-absorbing characteristic area. The calculation formula is as follows:

[0109]

[0110] Where σ0 is the standard ink absorption, and S1, S2 and S... s These are the first water-absorbing characteristic area, the second water-absorbing characteristic area, and the hydrophobic characteristic area, respectively, where e is a natural constant.

[0111] It should be explained that the hydrophobic wavelength range refers to [1670nm, 1770nm], the first water-absorbing wavelength range is [1400nm, 1500nm], and the second water-absorbing wavelength range is [1900nm, 2000nm].

[0112] Understandably, since the hydrophobic wavelength range corresponds to the range of absorption peaks caused by the stretching vibration of CH bonds in the near-infrared spectrum, and CH bonds are usually closely related to the content of hydrophobic groups (such as alkyl groups, aromatic hydrocarbons, etc.) in a material, this embodiment of the invention obtains the hydrophobic characteristic area through the hydrophobic wavelength range, thereby identifying the content of hydrophobic fiber materials such as polyester and polypropylene that do not easily absorb ink in the standard fabric. The larger the hydrophobic characteristic area, the higher the content of hydrophobic fiber materials. Since the first water absorption wavelength range corresponds to the range of absorption peaks caused by the bending vibration of OH bonds in the near-infrared spectrum, and the second water absorption wavelength range corresponds to the range of absorption peaks caused by the symmetric stretching vibration of HOH bond configuration in the near-infrared spectrum, and the more groups corresponding to OH bonds in a material, the stronger the water absorption of the material, this embodiment of the invention obtains the first and second water absorption characteristic areas through the first and second water absorption wavelength ranges, thereby reflecting the water absorption of the standard fabric. The larger the first and second water absorption characteristic areas, the stronger the water absorption of the standard fabric. Standard ink absorption reflects the ability of a standard fabric to absorb ink during digital printing. The higher the standard ink absorption, the stronger the ability of the standard fabric to absorb ink during digital printing.

[0113] For example, if the hydrophobic wavelength range is [1670nm, 1770nm], then draw a first vertical line with x = 1670nm and a second vertical line with x = 1770nm in the infrared spectrum curve. The area enclosed by the first vertical line, the second vertical line, the curve in the infrared spectrum curve, and the horizontal axis of the infrared spectrum curve is taken as the hydrophobic feature region. The area of ​​the hydrophobic feature region is the area of ​​the hydrophobic feature region.

[0114] It is understandable that the method for obtaining the first water absorption characteristic area based on the preset first water absorption wavelength range and the method for obtaining the second water absorption characteristic area based on the preset second water absorption wavelength range are the same as the method for obtaining the hydrophobic characteristic area using the hydrophobic wavelength range, and will not be described again here.

[0115] S3. Use a backlight and a high-definition camera to test the light transmittance of the standard fabric and obtain the standard porosity.

[0116] In detail, the method of using a backlight panel and a high-definition camera to test the light transmittance porosity of a standard fabric to obtain the standard porosity includes:

[0117] A standard fabric is laid flat and fixed on the light-emitting surface of the backlight panel to obtain a fixed fabric, wherein the plane on which the fixed fabric is located is parallel to the light-emitting surface;

[0118] A high-definition camera is used to photograph a fixed piece of fabric to obtain an image of the translucent fabric;

[0119] A grayscale operation is performed on the image of the translucent fabric to obtain a translucent grayscale image, which includes multiple translucent pixels.

[0120] Multiple light-transmitting grayscale values ​​are identified based on multiple light-transmitting pixels. Each light-transmitting grayscale value corresponds one-to-one with a light-transmitting pixel, and the light-transmitting grayscale value is the grayscale value of the light-transmitting pixel.

[0121] The average transmittance gray value is calculated based on multiple transmittance gray values, where the average transmittance gray value is the average of the multiple transmittance gray values;

[0122] Perform the following operation on each of the multiple light-transmitting pixels:

[0123] Compare the light-transmitting gray value corresponding to the light-transmitting pixel with the average light-transmitting gray value. If the light-transmitting gray value corresponding to the light-transmitting pixel is greater than or equal to the average light-transmitting gray value, then the light-transmitting pixel is recorded as a light-emitting pixel.

[0124] Summarize the luminous pixels to obtain multiple luminous pixels, confirm the number of luminous pixels, and confirm the original number of multiple light-transmitting pixels.

[0125] The standard porosity is calculated based on the number of light emitted and the original number, using the following formula:

[0126]

[0127] Where ε0 is the standard porosity, N x and N c These represent the number of emitted light and the original number, respectively.

[0128] It should be explained that the phrase "laying and fixing the standard fabric flat on the emitting surface of the backlight" refers to using clamps to flatten and fix the standard fabric to the backlight, thus ensuring the standard fabric is laid flat on the emitting surface of the backlight. The translucent fabric image refers to an image of the fixed fabric captured by a high-definition camera. The method for performing a grayscale operation on the translucent fabric image to obtain a translucent grayscale image is the same as the method for performing a grayscale operation on the near-infrared image to obtain a grayscale image, and will not be repeated here.

[0129] Understandably, the number of light-emitting pixels refers to the number of light-emitting pixels among multiple light-emitting pixels, while the original number refers to the number of light-transmitting pixels among multiple light-transmitting pixels.

[0130] It should be understood that, since standard fabric itself has a certain porous structure, and in this embodiment of the invention, the standard fabric is laid flat on a backlight plate, so that the light emitted by the backlight plate can penetrate the porous areas of the fabric, thereby forming high grayscale luminous pixels in the captured light-transmitting fabric image. That is, the luminous pixels correspond to the points where the light passes through the pores of the standard fabric in reality. Therefore, the standard porosity reflects the distribution density and number of pores in the standard fabric. The greater the standard porosity, the greater the distribution density and the greater the number of pores in the standard fabric.

[0131] S4. Obtain the initial fabric set and digital printing device, evaluate the printing status of the initial fabric set, obtain the target fabric set, test the ink absorption and test the porosity.

[0132] For example, a printing factory now needs to digitally print on a batch of fabric, which is an initial fabric set, and the initial fabric set includes multiple initial fabrics. The digital printing device is a digital printing machine.

[0133] In detail, the step of evaluating the printing status of the initial fabric set to obtain the target fabric set, test ink absorption, and test porosity includes:

[0134] Extract the initial cloth from the initial cloth set, and use the initial cloth set after extraction as the target cloth set;

[0135] The ink absorption and porosity were measured using the initial fabric, a multispectral camera, a backlight, and a high-definition camera.

[0136] It is understood that the method for obtaining test ink absorption and test porosity based on initial fabric, multispectral camera, backlight and high-definition camera is the same as the method for obtaining standard ink absorption and standard porosity using standard fabric, multispectral camera, backlight and high-definition camera, and will not be described again here.

[0137] S5. Extract the target fabric from the target fabric set, and use the target fabric set after extraction as the updated fabric set. Preprocess the target fabric to obtain the fabric to be printed.

[0138] It should be understood that before digital printing, the updated fabric needs to undergo pretreatment steps such as sizing, auxiliary agent penetration, and drying to improve the adhesion of ink to the fabric during digital printing. The pretreatment of the target fabric is to sizing, auxiliary agent penetration, and drying the updated fabric. The specific steps of sizing, auxiliary agent penetration, and drying are determined by the production process of the printing factory, and will not be elaborated here.

[0139] It should be explained that the target cloth set includes multiple target cloths.

[0140] S6. Set the digital printing device according to the preset standard inkjet volume, preset standard printing speed, standard ink absorption, standard porosity, test ink absorption, and test porosity to obtain the target printing device.

[0141] In detail, the step of setting the digital printing device according to preset standard inkjet volume, preset standard printing speed, standard ink absorption, standard porosity, test ink absorption, and test porosity to obtain the target printing device includes:

[0142] Confirm the current operating humidity and current operating temperature of the digital printing device;

[0143] The target inkjet volume is calculated based on the current operating humidity, current operating temperature, and standard inkjet volume. The calculation formula is as follows:

[0144]

[0145] Among them, M K M0 represents the target inkjet volume, M0 represents the standard inkjet volume, and RH represents the target inkjet volume. x and RH c These represent the current operating humidity and the preset reference operating humidity, respectively, T. x and T c These are the current operating temperature and the preset reference operating temperature, respectively.

[0146] The target printing speed is calculated based on the standard inkjet volume, target inkjet volume, standard printing speed, standard ink absorption, standard porosity, test ink absorption, and test porosity. The calculation formula is as follows:

[0147]

[0148] Among them, v k Let σ0 be the target printing speed, ε0 be the standard ink absorption and standard porosity, v0 be the standard printing speed, and tanh be the hyperbolic tangent function.

[0149] The digital printing device is set using the target ink volume and target printing speed to obtain the target printing device.

[0150] It should be explained that the current operating humidity refers to the relative humidity of the air in the environment where the digital printing device is located at this time. Optionally, the current operating humidity can be collected by a humidity sensor. The current operating temperature refers to the air temperature of the environment where the digital printing device is located at this time.

[0151] Understandably, the target inkjet volume refers to the volume of ink droplets ejected in a single stroke during the digital printing process. When the indoor environment is too dry, the ink inside the digital printing machine will gradually dry out during operation, clogging the printhead. Therefore, when the humidity decreases, the target inkjet volume needs to be increased appropriately to prevent the printhead from drying out. When the indoor temperature is too high, the evaporation rate of the ink when printed onto the fabric will increase. Therefore, the target inkjet volume also needs to be increased appropriately to reduce the impact of the evaporation effect.

[0152] It should be understood that the target printing speed refers to the linear speed of the printhead relative to the fabric during the digital printing process. The stronger the fabric's ink absorption capacity and the more pores it has, the easier it is for ink to penetrate the fabric. If the printhead movement speed is too slow, the ink will remain in the unit area for too long, easily leading to over-penetration and causing printing quality problems such as pattern edge diffusion and blurred outlines. Therefore, this embodiment of the invention calculates the target printing speed by testing ink absorption and porosity, thereby inhibiting excessive ink penetration and maintaining pattern clarity.

[0153] Optionally, the reference operating temperature is 25°C and the reference operating humidity is 50%.

[0154] It is understood that setting the digital printing device using the target inkjet volume and target printing speed to obtain the target printing device means setting the inkjet volume of the digital printing device to the target inkjet volume and setting the printing speed of the digital printing device to the target printing speed to obtain the target printing device.

[0155] S7. Use the target printing device to digitally print the fabric to be printed to obtain the target printed fabric. Use a high-definition camera to acquire the current printed image of the target printed fabric. Perform image edge detection on the current printed image to obtain the edge diffusion index. Perform difference recognition on the current printed image to obtain the image difference index.

[0156] It should be explained that the current printed image refers to the image of the target printed fabric captured by a high-definition camera.

[0157] Specifically, the step of performing difference recognition on the current printed image to obtain an image difference index includes:

[0158] The pre-constructed qualified image and the current printed image are input into the pre-constructed image difference analysis model to obtain the target analysis model;

[0159] Image difference index is obtained using a target analysis model.

[0160] It should be explained that a qualified image refers to an image of the printed fabric that has been produced and is captured in advance by the workers of the printing factory using a high-definition camera. The image difference analysis model is built on the basis of a convolutional neural network, and the main operating principle of the image difference analysis model is as follows: First, the convolutional neural network in the image difference analysis model is used to process the qualified image and the current printed image through multiple layers of convolution, pooling, and activation functions to obtain two feature vectors. Then, the cosine similarity between the two feature vectors is calculated, and the absolute difference between the cosine similarity and 1 is calculated. This absolute difference is the image difference index. The above process is a publicly available technical solution, and the embodiments of this invention will not be described in detail here.

[0161] Specifically, the step of performing image edge detection on the current printed image to obtain the edge diffusion index includes:

[0162] Perform a grayscale conversion operation on the current printed image to obtain a grayscale printed image;

[0163] A pre-constructed edge recognition algorithm is used to perform edge recognition on the grayscale image of the printed pattern to obtain the set of edge pixels.

[0164] Perform the following operation on each edge pixel in the edge pixel set:

[0165] Obtain multiple edge-near pixels based on edge pixels, and obtain multiple edge-near pixel values ​​based on multiple edge-near pixels;

[0166] The edge pixel values ​​of edge pixels are identified, and the edge diffusion is calculated based on the values ​​of multiple neighboring edge pixels and the edge pixel values. The calculation formula is as follows:

[0167]

[0168] Where EP is the edge diffusion degree, and G i Let be the i-th edge-nearest pixel value among multiple edge-nearest pixel values, and n be the number of edge-nearest pixel values ​​among the multiple edge-nearest pixel values;

[0169] The edge diffusion degree is summarized to obtain multiple edge diffusion degrees. The edge diffusion index is calculated based on the multiple edge diffusion degrees, where the edge diffusion index is the average value of the multiple edge diffusion degrees.

[0170] It is understood that the method of performing a grayscale operation on the current printed image to obtain a grayscale printed image is the same as the method of performing a grayscale operation on the near-infrared image to obtain a grayscale image, and will not be described again here. The edge pixel set includes: multiple edge pixels.

[0171] Optionally, the edge recognition algorithm is the Canny operator, and the technique of using a pre-constructed edge recognition algorithm to perform edge recognition on the printed grayscale image to obtain the edge pixel set is existing technology and will not be described in detail here. The edge pixel set refers to a set of multiple pixels in the printed grayscale image that meet the detection conditions of the Canny operator and are located at positions with significant changes in grayscale gradient. These multiple pixels are usually located in the boundary region between the printed pattern and the fabric background.

[0172] It is understood that the method for obtaining multiple edge-near pixels based on edge pixels is the same as the method for identifying multiple center-near pixels based on center pixels, and will not be described again here. Similarly, the method for obtaining multiple edge-near pixel values ​​based on multiple edge-near pixels is the same as the method for identifying multiple evaluation grayscale values ​​based on multiple evaluation pixels, and will not be described again here.

[0173] It should be understood that edge diffusion reflects the degree to which ink at the edge of the printed pattern outline in the grayscale image diffuses into the non-printed area of ​​the target printed fabric. The greater the edge diffusion, the greater the degree to which ink at the edge of the printed pattern outline in the grayscale image diffuses into the non-printed area of ​​the target printed fabric.

[0174] S8. Calculate the image qualification rate based on the edge diffusion index and the image difference index, compare the image qualification rate with the preset qualification threshold. If the image qualification rate is greater than or equal to the qualification threshold, then the target printed fabric is regarded as a qualified printed fabric. Otherwise, calculate the optimized printing speed based on the edge diffusion index, use the optimized printing speed as the standard printing speed, use the updated fabric set as the target fabric set, use the target printing device as the digital printing device, and return to the step of extracting the target fabric from the target fabric set until there is no target fabric in the target fabric set.

[0175] It should be explained that the acceptable threshold is a value set manually by the staff of the printing factory.

[0176] For example, if the image qualification rate is greater than or equal to the qualification threshold, the target printed fabric is collected as a qualified printed fabric. If the image qualification rate is less than the qualification threshold, the target printed fabric is discarded, the optimized printing speed is recalculated, and the optimized printing speed is used as the standard printing speed. The updated fabric set is used as the target fabric set, and the step of extracting the target fabric from the target fabric set is returned. That is, a target fabric is extracted from the target fabric set again for digital printing, until all the target fabrics in the target fabric set have been extracted. Finally, the collected qualified printed fabrics are summarized to obtain multiple qualified printed fabrics.

[0177] In detail, the formula for calculating the image qualification is as follows:

[0178]

[0179] Where, δ k For image qualification, τ k is the image difference index, and ln is the natural logarithm.

[0180] It should be understood that the image qualification rate is a comprehensive indicator used to quantify the printing quality of the target printed fabric. The higher the image qualification rate, the better the printing quality of the target printed fabric.

[0181] In detail, the calculation formula for the optimized printing speed is as follows, including:

[0182]

[0183] Among them, v g To optimize printing speed, EPK X EPK0 is the edge diffusion index, and EPK0 is the preset edge diffusion threshold.

[0184] It should be explained that the edge diffusion threshold is a value set manually by the printing factory staff based on the printing factory's historical data. Optionally, the average edge diffusion index of multiple target printed fabrics produced by the printing factory in the past can be used as the edge diffusion threshold.

[0185] Understandably, since the edge diffusion index reflects the degree to which ink at the edge of the printed pattern outline in the grayscale image diffuses into the non-printed area of ​​the target fabric, when the edge diffusion index is too large, it means that the ink stays at the edge of the printed pattern for too long, thus causing the ink to diffuse and affecting the clarity of the pattern edge. Therefore, this embodiment of the invention optimizes the printing speed by calculating the edge diffusion index and replaces the standard printing speed with the optimized printing speed, thereby optimizing the printing effect when the target fabric is extracted from the target fabric set for printing next time.

[0186] S9. Compile qualified printed fabrics to obtain multiple qualified printed fabrics, and complete the control of the digital printing process.

[0187] For example, multiple qualified printed fabrics are multiple printed fabrics that meet the production goals of the printing factory. After further post-processing (drying, color fixing and shaping, etc.), the multiple qualified printed fabrics can be officially used for garments, bedding or other industrial applications.

[0188] To address the problems described in the background section, this invention utilizes a multispectral camera, a backlight panel, and a high-definition camera. The backlight panel includes a light-emitting surface. This invention prepares the material for subsequent near-infrared analysis and light transmittance porosity testing. The multispectral camera is then used to perform near-infrared analysis on a pre-constructed standard fabric to obtain standard ink absorption. The backlight panel and high-definition camera are used to perform light transmittance porosity testing on the standard fabric to obtain standard porosity. This invention provides standard ink absorption and standard porosity by comparing the differences between the standard fabric and the initial fabric, thereby improving the printing efficiency. The automation level of the printing process is controlled, while taking into account the differences between different fabrics. The printing process is adaptively adjusted according to these differences, thereby improving the quality of the printed products. The invention involves acquiring an initial fabric set and a digital printing device, evaluating the printing status of the initial fabric set, obtaining the target fabric set, testing ink absorption, and testing porosity. It is evident that this embodiment of the invention evaluates the ink absorption capacity and porosity of the initial fabric set by obtaining the tested ink absorption and porosity, facilitating precise control of parameters in the subsequent printing process and improving the quality of the final printed products. The target fabric is extracted from the target fabric set, and the target fabric set after extraction is used as the updated fabric set. The target fabric is then pre-processed to obtain the product to be printed. The digital printing device is configured to print on the fabric according to preset standard inkjet volume, standard printing speed, standard ink absorption, standard porosity, test ink absorption, and test porosity to obtain the target printing device. This embodiment of the invention calculates the ideal inkjet volume and printing speed in advance before printing by using standard printing speed, standard ink absorption, standard porosity, test ink absorption, and test porosity, and then configures the printing device accordingly, thereby improving the quality of the printed product. The target printing device is used to digitally print on the fabric to be printed, resulting in the target printed fabric. A high-definition camera is used to acquire the current printed image of the target printed fabric. Image edge detection is performed on the current printed image to obtain the edge diffusion index. Difference recognition is then performed on the current printed image to obtain... The image difference index is used to calculate the image qualification rate based on the edge diffusion index and the image difference index. The image qualification rate is then compared with a preset qualification threshold. This embodiment of the invention uses a high-definition camera to acquire the current printing image of the target printed fabric and performs real-time analysis to calculate the image qualification rate. This facilitates the automated selection of qualified printed fabrics based on the image qualification rate and the qualification threshold, improving the automation level of printing process control. If the image qualification rate is greater than or equal to the qualification threshold, the target printed fabric is considered qualified; otherwise, the printing speed is optimized based on the edge diffusion index, and this optimized printing speed is used as the standard printing speed. The updated fabric set is used as the target fabric set, and the target printing device is used as the digital printing device.The process returns to the step of extracting the target fabric from the target fabric set until no target fabric remains in the set. Qualified printed fabrics are then collected, resulting in multiple qualified printed fabrics. This completes the control of the digital printing process. It can be seen that this embodiment of the invention optimizes the printing speed by calculating the edge diffusion index and replaces the standard printing speed with the optimized speed, thereby optimizing the printing effect when the target fabric is extracted from the target fabric set for printing next time, and improving the quality of the printed product. Therefore, this invention can improve the automation level of printing process control and enhance the quality of printed products.

[0189] like Figure 2 The diagram shown is a functional block diagram of a digital printing process control system based on image analysis provided in an embodiment of the present invention.

[0190] The image analysis-based digital printing process control system 100 of this invention can be installed in an electronic device 1. Depending on the functions implemented, the image analysis-based digital printing process control system 100 may include a standard fabric testing module 101, an initial fabric evaluation module 102, a printing device control module 103, and a printed fabric feedback module 104. The module described in this invention can also be called a unit, referring to a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, stored in the memory of the electronic device.

[0191] The standard fabric testing module 101 is used to acquire a multispectral camera, a backlight panel, and a high-definition camera. The backlight panel includes a light-emitting surface. The multispectral camera is used to perform near-infrared analysis on the pre-constructed standard fabric to obtain the standard ink absorption. The backlight panel and the high-definition camera are used to perform light transmission porosity testing on the standard fabric to obtain the standard porosity.

[0192] The initial fabric evaluation module 102 is used to acquire an initial fabric set and a digital printing device, evaluate the printing status of the initial fabric set, obtain a target fabric set, test ink absorption and test porosity, extract the target fabric from the target fabric set, and use the target fabric set after extracting the target fabric as an updated fabric set, preprocess the target fabric to obtain the fabric to be printed.

[0193] The printing device control module 103 is used to set the digital printing device according to the preset standard ink jet volume, preset standard printing speed, standard ink absorption, standard porosity, test ink absorption, and test porosity to obtain the target printing device. The target printing device is used to perform digital printing on the fabric to be printed to obtain the target printed fabric. The current printed image of the target printed fabric is obtained using a high-definition camera.

[0194] The printed fabric feedback module 104 is used to perform image edge detection on the current printed image to obtain an edge diffusion index, perform difference recognition on the current printed image to obtain an image difference index, calculate the image qualification based on the edge diffusion index and the image difference index, compare the image qualification with a preset qualification threshold, and if the image qualification is greater than or equal to the qualification threshold, then the target printed fabric is regarded as a qualified printed fabric; otherwise, the printing speed is optimized based on the edge diffusion index, the optimized printing speed is used as the standard printing speed, the updated fabric set is used as the target fabric set, the target printing device is used as the digital printing device, and the step of extracting the target fabric from the target fabric set is returned until there is no target fabric in the target fabric set. The qualified printed fabrics are then summarized to obtain multiple qualified printed fabrics, thus completing the control of the digital printing process.

[0195] In detail, the modules in the image analysis-based digital printing process control system 100 described in this embodiment of the invention employ the same methods as described above. Figure 1 The method uses the same technical means as the image analysis-based digital printing process control method described in the article and can produce the same technical effect, so it will not be repeated here.

[0196] like Figure 3 The diagram shown is a schematic diagram of the structure of an electronic device 1 that implements a digital printing process control method based on image analysis, according to an embodiment of the present invention.

[0197] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a digital printing process control method program based on image analysis.

[0198] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of a digital printing process control method program based on image analysis, but also to temporarily store data that has been output or will be output.

[0199] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., a digital printing process control method program based on image analysis) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0200] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0201] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0202] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0203] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0204] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0205] The image analysis-based digital printing process control method program stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When run in the processor 10, it can achieve the following:

[0206] Acquire a multispectral camera, a backlight panel, and a high-definition camera. The backlight panel includes a light-emitting surface.

[0207] Near-infrared analysis of a pre-constructed standard fabric was performed using a multispectral camera to obtain the standard ink absorbance.

[0208] The standard porosity was obtained by testing the light transmittance of a standard fabric using a backlight panel and a high-definition camera.

[0209] Obtain an initial fabric set and digital printing device, evaluate the printing status of the initial fabric set, and obtain the target fabric set, test ink absorption and test porosity;

[0210] Extract the target fabric from the target fabric set, and use the extracted target fabric set as the updated fabric set. Preprocess the target fabric to obtain the fabric to be printed.

[0211] The digital printing device is set up according to the preset standard inkjet volume, preset standard printing speed, standard ink absorption, standard porosity, test ink absorption, and test porosity to obtain the target printing device.

[0212] The target printing device is used to digitally print on the fabric to be printed, and the target printed fabric is obtained. A high-definition camera is used to acquire the current printed image of the target printed fabric.

[0213] Image edge detection is performed on the current printed image to obtain the edge diffusion index, and difference recognition is performed on the current printed image to obtain the image difference index;

[0214] The image passability is calculated based on the edge diffusion index and the image difference index, and the image passability is compared with the preset passability threshold.

[0215] If the image qualification is greater than or equal to the qualification threshold, the target printed fabric is regarded as a qualified printed fabric; otherwise, the printing speed is optimized according to the edge diffusion index, the optimized printing speed is used as the standard printing speed, the updated fabric set is used as the target fabric set, the target printing device is used as the digital printing device, and the step of extracting the target fabric from the target fabric set is returned until the target fabric set no longer contains the target fabric.

[0216] By compiling qualified printed fabrics, multiple qualified printed fabrics are obtained, and the digital printing process is controlled.

[0217] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0218] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0219] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0220] Acquire a multispectral camera, a backlight panel, and a high-definition camera. The backlight panel includes a light-emitting surface.

[0221] Near-infrared analysis of a pre-constructed standard fabric was performed using a multispectral camera to obtain the standard ink absorbance.

[0222] The standard porosity was obtained by testing the light transmittance of a standard fabric using a backlight panel and a high-definition camera.

[0223] Obtain an initial fabric set and digital printing device, evaluate the printing status of the initial fabric set, and obtain the target fabric set, test ink absorption and test porosity;

[0224] Extract the target fabric from the target fabric set, and use the extracted target fabric set as the updated fabric set. Preprocess the target fabric to obtain the fabric to be printed.

[0225] The digital printing device is set up according to the preset standard inkjet volume, preset standard printing speed, standard ink absorption, standard porosity, test ink absorption, and test porosity to obtain the target printing device.

[0226] The target printing device is used to digitally print on the fabric to be printed, and the target printed fabric is obtained. A high-definition camera is used to acquire the current printed image of the target printed fabric.

[0227] Image edge detection is performed on the current printed image to obtain the edge diffusion index, and difference recognition is performed on the current printed image to obtain the image difference index;

[0228] The image passability is calculated based on the edge diffusion index and the image difference index, and the image passability is compared with the preset passability threshold.

[0229] If the image qualification is greater than or equal to the qualification threshold, the target printed fabric is regarded as a qualified printed fabric; otherwise, the printing speed is optimized according to the edge diffusion index, the optimized printing speed is used as the standard printing speed, the updated fabric set is used as the target fabric set, the target printing device is used as the digital printing device, and the step of extracting the target fabric from the target fabric set is returned until the target fabric set no longer contains the target fabric.

[0230] By compiling qualified printed fabrics, multiple qualified printed fabrics are obtained, and the digital printing process is controlled.

[0231] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0232] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0233] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0234] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0235] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A digital printing process control method based on image analysis, characterized in that, The method includes: Acquire a multispectral camera, a backlight panel, and a high-definition camera. The backlight panel includes a light-emitting surface. Near-infrared analysis of a pre-constructed standard fabric was performed using a multispectral camera to obtain the standard ink absorbance. The standard porosity was obtained by testing the light transmittance of a standard fabric using a backlight panel and a high-definition camera. Obtain an initial fabric set and digital printing device, evaluate the printing status of the initial fabric set, and obtain the target fabric set, test ink absorption and test porosity; Extract the target fabric from the target fabric set, and use the extracted target fabric set as the updated fabric set. Preprocess the target fabric to obtain the fabric to be printed. The digital printing device is set up according to the preset standard inkjet volume, preset standard printing speed, standard ink absorption, standard porosity, test ink absorption, and test porosity to obtain the target printing device. The target printing device is used to digitally print on the fabric to be printed, and the target printed fabric is obtained. A high-definition camera is used to acquire the current printed image of the target printed fabric. Image edge detection is performed on the current printed image to obtain the edge diffusion index, and difference recognition is performed on the current printed image to obtain the image difference index; The image passability is calculated based on the edge diffusion index and the image difference index, and the image passability is compared with the preset passability threshold. If the image qualification is greater than or equal to the qualification threshold, the target printed fabric is regarded as a qualified printed fabric; otherwise, the printing speed is optimized according to the edge diffusion index, the optimized printing speed is used as the standard printing speed, the updated fabric set is used as the target fabric set, the target printing device is used as the digital printing device, and the step of extracting the target fabric from the target fabric set is returned until there is no target fabric in the target fabric set. By compiling qualified printed fabrics, multiple qualified printed fabrics are obtained, and the digital printing process is controlled.

2. The digital printing process control method based on image analysis as described in claim 1, characterized in that, The step of using a multispectral camera to perform near-infrared analysis on a pre-constructed standard fabric to obtain standard ink absorbance includes: Based on a preset set of near-infrared wavelengths and a multispectral camera, near-infrared images are taken of standard fabric to obtain multiple near-infrared images. The set of near-infrared wavelengths includes multiple near-infrared wavelengths, and each near-infrared wavelength corresponds to a near-infrared image. For each of the multiple near-infrared images, perform the following operation: A grayscale operation is performed on a near-infrared image to obtain a grayscale image, wherein the grayscale image includes multiple grayscale pixels; Identify the center pixel, top-left pixel, bottom-left pixel, top-right pixel, and bottom-right pixel in a grayscale image; Multiple neighboring points were identified based on the center pixel. The neighboring points are grayscale pixels in the grayscale image that are adjacent to the center pixel. Based on the top-left pixel, bottom-left pixel, top-right pixel, and bottom-right pixel, obtain multiple top-left neighboring points, multiple bottom-left neighboring points, multiple top-right neighboring points, and multiple bottom-right neighboring points respectively; By summarizing the center pixel, top-left pixel, bottom-left pixel, top-right pixel, bottom-right pixel, center neighbor, top-left neighbor, bottom-left neighbor, top-right neighbor, and bottom-right neighbor, multiple evaluation pixels are obtained; Multiple evaluation grayscale values ​​are determined based on multiple evaluation pixels, where each evaluation grayscale value corresponds one-to-one with an evaluation pixel, and the evaluation grayscale value is the grayscale value of the evaluation pixel. The near-infrared pixel value is calculated based on multiple evaluation grayscale values, where the near-infrared pixel value is the average of the multiple evaluation grayscale values; The near-infrared wavelength corresponding to the near-infrared image is combined with the near-infrared pixel value to obtain a near-infrared spectral group; By summarizing the near-infrared spectral groups, multiple near-infrared spectral groups were obtained; Curve fitting is performed on a pre-constructed spectral coordinate system based on multiple near-infrared spectral groups to obtain near-infrared spectral curves, where the horizontal axis of the spectral coordinate system represents the near-infrared wavelength and the vertical axis represents the near-infrared pixel value. Characteristic peak analysis was performed on the near-infrared spectrum curves to obtain the standard ink absorption.

3. The digital printing process control method based on image analysis as described in claim 2, characterized in that, The analysis of characteristic peaks in the near-infrared spectral curve to obtain the standard ink absorbance includes: Based on the preset hydrophobic wavelength range, the hydrophobic feature region is identified in the infrared spectrum curve, and the hydrophobic feature area of ​​the hydrophobic feature region is identified. The first water absorption characteristic area and the second water absorption characteristic area are obtained based on the preset first water absorption wavelength range and the preset second water absorption wavelength range, respectively. The standard ink absorption is calculated based on the hydrophobic characteristic area, the first water-absorbing characteristic area, and the second water-absorbing characteristic area.

4. The digital printing process control method based on image analysis as described in claim 3, characterized in that, The method of using a backlight panel and a high-definition camera to test the light transmittance porosity of a standard fabric to obtain the standard porosity includes: A standard fabric is laid flat and fixed on the light-emitting surface of the backlight panel to obtain a fixed fabric, wherein the plane on which the fixed fabric is located is parallel to the light-emitting surface; A high-definition camera is used to photograph a fixed piece of fabric to obtain an image of the translucent fabric; A grayscale operation is performed on the image of the translucent fabric to obtain a translucent grayscale image, which includes multiple translucent pixels. Multiple light-transmitting grayscale values ​​are identified based on multiple light-transmitting pixels. Each light-transmitting grayscale value corresponds one-to-one with a light-transmitting pixel, and the light-transmitting grayscale value is the grayscale value of the light-transmitting pixel. The average transmittance gray value is calculated based on multiple transmittance gray values, where the average transmittance gray value is the average of the multiple transmittance gray values; Perform the following operation on each of the multiple light-transmitting pixels: Compare the light-transmitting gray value corresponding to the light-transmitting pixel with the average light-transmitting gray value. If the light-transmitting gray value corresponding to the light-transmitting pixel is greater than or equal to the average light-transmitting gray value, then the light-transmitting pixel is recorded as a light-emitting pixel. Summarize the luminous pixels to obtain multiple luminous pixels, confirm the number of luminous pixels, and confirm the original number of multiple light-transmitting pixels. Standard porosity is calculated based on the amount of light emitted and the original amount.

5. The digital printing process control method based on image analysis as described in claim 4, characterized in that, The process of evaluating the printing status of the initial fabric set to obtain the target fabric set, test ink absorption, and test porosity includes: Extract the initial cloth from the initial cloth set, and use the initial cloth set after extraction as the target cloth set; The ink absorption and porosity were measured using the initial fabric, a multispectral camera, a backlight, and a high-definition camera.

6. The digital printing process control method based on image analysis as described in claim 5, characterized in that, The process of setting up the digital printing device according to preset standard inkjet volume, preset standard printing speed, standard ink absorption, standard porosity, test ink absorption, and test porosity to obtain the target printing device includes: Confirm the current operating humidity and current operating temperature of the digital printing device; Calculate the target inkjet volume based on the current operating humidity, current operating temperature, and standard inkjet volume. The target printing speed is calculated based on the standard inkjet volume, target inkjet volume, standard printing speed, standard ink absorption, standard porosity, test ink absorption, and test porosity. The digital printing device is set using the target ink volume and target printing speed to obtain the target printing device.

7. The digital printing process control method based on image analysis as described in claim 6, characterized in that, The step of performing image edge detection on the current printed image to obtain the edge diffusion index includes: Perform a grayscale conversion operation on the current printed image to obtain a grayscale printed image; A pre-constructed edge recognition algorithm is used to perform edge recognition on the grayscale image of the printed pattern to obtain the edge pixel set. Perform the following operation on each edge pixel in the edge pixel set: Obtain multiple edge-near pixels based on edge pixels, and obtain multiple edge-near pixel values ​​based on multiple edge-near pixels; Identify the edge pixel values ​​of edge pixels and calculate the edge diffusion based on the values ​​of multiple edge neighboring pixels and the edge pixel values; The edge diffusion degree is summarized to obtain multiple edge diffusion degrees. The edge diffusion index is calculated based on the multiple edge diffusion degrees, where the edge diffusion index is the average value of the multiple edge diffusion degrees.

8. A digital printing process control system based on image analysis, characterized in that, The system includes: The standard fabric testing module is used to acquire data from a multispectral camera, a backlight panel, and a high-definition camera. The backlight panel includes a light-emitting surface. The multispectral camera is used to perform near-infrared analysis on the pre-constructed standard fabric to obtain the standard ink absorption. The backlight panel and the high-definition camera are used to perform light transmission porosity testing on the standard fabric to obtain the standard porosity. The initial fabric evaluation module is used to acquire the initial fabric set and digital printing device, evaluate the printing status of the initial fabric set, obtain the target fabric set, test the ink absorption and test the porosity, extract the target fabric from the target fabric set, and use the target fabric set after extracting the target fabric as the updated fabric set. The target fabric is pre-processed to obtain the fabric to be printed. The printing device control module is used to set the digital printing device according to the preset standard ink jet volume, preset standard printing speed, standard ink absorption, standard porosity, test ink absorption, and test porosity to obtain the target printing device. The target printing device is used to perform digital printing on the fabric to be printed to obtain the target printed fabric. The current printed image of the target printed fabric is obtained using a high-definition camera. The printed fabric feedback module is used to perform image edge detection on the current printed image to obtain an edge diffusion index, perform difference recognition on the current printed image to obtain an image difference index, calculate the image qualification rate based on the edge diffusion index and the image difference index, compare the image qualification rate with a preset qualification threshold, and if the image qualification rate is greater than or equal to the qualification threshold, the target printed fabric is regarded as a qualified printed fabric; otherwise, the printing speed is optimized based on the edge diffusion index, the optimized printing speed is used as the standard printing speed, the updated fabric set is used as the target fabric set, the target printing device is used as the digital printing device, and the step of extracting the target fabric from the target fabric set is returned until there is no target fabric in the target fabric set. The qualified printed fabrics are then summarized to obtain multiple qualified printed fabrics, thus completing the control of the digital printing process.

Images