A method and system for detecting color of printed images with visual assistance

Abstract

The present invention relates to the field of image processing technology, and in particular to a method for color detection of printed images under visual assistance, the method comprising: obtaining a first printed image of a printed product; determining an environmental impact factor of the first printed image; determining a regional distribution characteristic value of the first printed image according to a first number of regions in the first printed image, a second number of regions in a second printed image of other printed products in the same batch as the printed product, a maximum regional variation degree in the first printed image, and a maximum regional variation degree in the second printed image, wherein the regional variation degree represents the gradient fluctuation degree of pixel points in the region; determining the color quality of the first printed image according to the color characteristic values ​​of the first printed image and the second printed image, the regional distribution characteristic value of the first printed image, and the environmental impact factor; and detecting the color quality of the first printed image by a first threshold. In this way, the present invention improves the detection efficiency and accuracy of printed images.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method and system for detecting the color of a printed image under visual assistance. Background Art

[0002] With the rapid development of digitalization and automation technology, color detection technology is widely used in the printing industry to detect the color of printed images. In the printing industry, color consistency and accuracy are important indicators of product quality. Any color deviation will directly affect the appearance and market acceptance of the final product. In recent years, the technology of color detection equipment has made significant progress. These devices are usually equipped with high-precision spectrometers, color sensors, and image processing technology, which can quickly and accurately measure and analyze the color of printed products.

[0003] In some scenarios, due to changes in printing environment conditions, changes in temperature and humidity in the printing environment have a direct impact on the viscosity, drying speed of the ink, and the ink absorption of the paper, which may affect the color uniformity, resulting in uneven distribution of ink during the printing process. This uneven ink distribution may cause color deviation, excessive color difference, or uneven color blocks on the image of the printed product, seriously affecting the quality of the printed product. Traditionally, the quality inspection of printed products is mainly carried out by manually operating instruments and tools. This method not only wastes a lot of manpower and material resources, but also has low inspection efficiency and accuracy because the inspection results are easily affected by the operator's experience and subjective factors. Summary of the invention

[0004] In order to solve the technical problem of low detection efficiency and accuracy when detecting the quality of printed products, the purpose of the present invention is to provide a method and system for color detection of printed images under visual assistance. The technical solution adopted is as follows:

[0005] In a first aspect, an embodiment of the present invention provides a method for detecting color of a printed image with visual assistance, comprising: acquiring a first printed image of a printed product; determining an environmental impact factor of the first printed image according to a first pixel value of each pixel in the first printed image, a second pixel value of pixels in a neighborhood of each pixel, and environmental parameters in the environment in which the printed product is located; determining a regional distribution characteristic value of the first printed image according to a first number of regions in the first printed image, a second number of regions in a second printed image of other printed products from the same batch as the printed product, a maximum regional variation degree in the first printed image, and a maximum regional variation degree in the second printed image, wherein the region represents a region with similar pixel value distribution of pixels in the printed image, and the regional variation degree represents a gradient fluctuation degree of pixels in the region; determining the color quality of the first printed image according to the color characteristic values ​​of the first printed image and the second printed image, the regional distribution characteristic value of the first printed image, and the environmental impact factor; and detecting the color quality of the first printed image by a first threshold.

[0006] Optionally, determining the environmental impact factor of the first printed image based on the first pixel value of each pixel in the first printed image, the second pixel value of the pixels in the neighborhood of each pixel, and the environmental parameters of the environment in which the printed product is located includes: determining the pixel difference value of each pixel based on the first pixel value of each pixel in the first printed image and the second pixel value of the pixels in the neighborhood of each pixel; clustering each pixel in the first printed image based on the pixel difference value of each pixel to obtain multiple clusters, and dividing all the pixels in each cluster into a region in the first printed image; determining the degree of regional change of each region in the first printed image by using the gradient of the pixels in each region in the first printed image, the gradient of the pixels in the neighborhood of each pixel, and the pixel difference value of the pixels in each region; determining the environmental impact factor of the first printed image based on the environmental parameters of the environment in which the printed product is located, the first number of regions in the first printed image, and the maximum degree of regional change in the first printed image.

[0007] Optionally, determining the pixel difference value of each pixel point based on the first pixel value of each pixel point in the first printed image and the second pixel value of each pixel point in the neighborhood of each pixel point includes: for each pixel point in the first printed image, calculating the absolute value of the first difference between the first pixel value of the pixel point and the second pixel value of each pixel point in the neighborhood of the pixel point; and superimposing the absolute values ​​of each first difference to obtain the pixel difference value of the pixel point.

[0008] Optionally, the degree of regional change of each region in the first printed image is determined by using the gradient of the pixel points in each region in the first printed image, the gradient of the pixel points in the neighborhood of each pixel point, and the pixel difference value of the pixel points in each region, including: calculating the average gradient of the gradient of all pixel points in the neighborhood of each pixel point in each region, and the average difference value of the pixel difference values ​​of all pixel points in each region; calculating the second difference between the gradient of each pixel point in each region of the first printed image and the average gradient of the pixel points in its neighborhood; calculating the first product between the second difference and the average difference value, and superimposing the first products corresponding to each pixel point in the region to obtain the degree of regional change of the region.

[0009] Optionally, determining the environmental impact factor of the first printed image based on environmental parameters in the environment in which the printed product is located, the first number of regions in the first printed image, and the maximum degree of regional change in the first printed image includes: determining a third difference between the temperature of the environment in which the printed product is located when printing and the optimal printing temperature, and a fourth difference between the humidity of the environment in which the printed product is located when printing and the optimal printing humidity; calculating the second product among the third difference, the fourth difference, the first number, and the maximum degree of regional change in the first printed image; and normalizing the second product to obtain the environmental impact factor of the first printed image.

[0010] Optionally, determining the regional distribution characteristic value of the first printed image based on the first number of areas in the first printed image, the second number of areas in the second printed image of other printed products in the same batch as the printed products, the maximum degree of regional change in the first printed image, and the maximum degree of regional change in the second printed image includes: calculating the absolute value of the fifth difference between the first number and the second number, and the absolute value of the sixth difference between the maximum degree of regional change in the first printed image and the maximum degree of regional change in the second printed image; calculating the third product of the absolute value of the fifth difference, the absolute value of the sixth difference, and the distance, the distance being the distance between the first area corresponding to the maximum degree of regional change in the first printed image and the second area corresponding to the maximum degree of regional change in the second printed image; and superimposing each third product to obtain the regional distribution characteristic value of the first printed image.

[0011] Optionally, determining the color quality of the first printed image based on the color characteristic values ​​of the first printed image and the second printed image, the regional distribution characteristic values ​​of the first printed image, and the environmental impact factor includes: determining the color distribution law value of the first printed image based on the color characteristic values ​​of the first printed image and the second printed image, the regional distribution characteristic values ​​of the first printed image, and the regional distribution characteristic values ​​of the second printed image; and determining that the ratio between the color distribution law value of the first printed image and the environmental impact factor of the first printed image is the color quality of the first printed image.

[0012] Optionally, determining the color distribution law value of the first printed image based on the color characteristic values ​​of the first printed image and the second printed image, the regional distribution characteristic values ​​of the first printed image and the regional distribution characteristic values ​​of the second printed image includes: determining the color characteristic values ​​of the first printed image and the second printed image based on the histograms of the RGB channels in the first printed image and the second printed image, respectively; calculating the variance of the color characteristic values ​​of the first printed image and the second printed image; superimposing the regional distribution characteristic values ​​of the first printed image and the regional distribution characteristic values ​​of the second printed image to obtain a superimposed characteristic value; calculating the fourth product between the variance and the superimposed characteristic value; and performing inverse proportional normalization processing on the fourth product to obtain the color distribution law value of the first printed image.

[0013] Optionally, detecting the color quality of the first printed image through a first threshold includes: when the color quality of the first printed image is greater than the first threshold, determining that the color quality of the first printed image meets the requirements; when the color quality of the first printed image is not greater than the first threshold, determining that the color quality of the first printed image does not meet the requirements, adjusting the temperature and humidity of the environment in which the printed product is located, and readjusting the printing ink of the printed product.

[0014] In a second aspect, an embodiment of the present invention provides a system for color detection of printed images with visual assistance, comprising: a processor and a memory; wherein the memory is used to store computer programs that can be run on the processor; and the processor is used to execute the program stored in the memory to implement the steps of the method for color detection of printed images with visual assistance as mentioned in the first aspect.

[0015] The present invention has the following beneficial effects: firstly, a first printed image of a printed product is acquired; then, the environmental impact factor of the first printed image is determined according to the first pixel value of each pixel point in the first printed image, the second pixel value of the pixel points in the neighborhood of each pixel point, and the environmental parameters of the environment in which the printed product is located; then, the regional distribution characteristic value of the first printed image is determined according to the first number of regions in the first printed image, the second number of regions in the second printed images of other printed products in the same batch as the printed product, the maximum regional variation degree in the first printed image, and the maximum regional variation degree in the second printed image, wherein the region represents the region with similar pixel value distribution of the pixel points in the printed image, and the regional variation degree represents the gradient fluctuation degree of the pixel points in the region; and the color quality of the first printed image is determined according to the color characteristic values ​​of the first printed image and the second printed image, the regional distribution characteristic value of the first printed image, and the environmental impact factor; finally, the color quality of the first printed image is evaluated by a first threshold.

[0016] In this way, the embodiment of the present invention can identify the area of ​​uneven color for each printed image, and then analyze the environmental factors during printing according to the degree of regional change of the area, so as to obtain the environmental impact factor of the environment on the printed image. The color quality of the printed image is determined by combining the color characteristics, regional distribution characteristics and environmental sound impact factors in the printed image, and finally the color quality is evaluated based on the threshold. In this way, the embodiment of the present invention can evaluate the color quality of the printed product based on the printed image of the printed product. The detection result will not be affected by the operator's experience and subjective factors, which improves the detection efficiency and accuracy of the printed image. The environmental parameters of the printed product can be adjusted according to the detection results, thereby ensuring that the quality of the printed product can meet the standards, reducing the scrap rate and improving production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A flowchart of a method for detecting color of a printed image with visual assistance is provided in accordance with an embodiment of the present invention.

[0019] Figure 2 A schematic structural diagram of a visually assisted printed image color detection system provided by an embodiment of the present invention.

[0020] Figure 3 A schematic structural diagram of a visually assisted printed image color detection system provided in another embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation, structure, features and effects of a visually assisted printed image color detection method proposed by the present invention in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0022] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0023] A specific scheme of a method for detecting color of a printed image with visual assistance provided by the present invention is described in detail below with reference to the accompanying drawings.

[0024] Embodiment 1:

[0025] See also Figure 1 , which shows a flow chart of a method for color detection of printed images with visual assistance provided by an embodiment of the present invention, comprising:

[0026] S101, acquiring a first printed image of a printed product.

[0027] Specifically, a printed product refers to a product obtained by printing an image on digital paper using printing technology. A first printed image refers to an image obtained by photographing a printed product. In an embodiment of the present invention, a camera is installed above a placement rack, and each printed product is placed on the placement rack for photographing to obtain a first printed image of the printed product. In an embodiment of the present invention, the printed product includes multiple batches, and each batch includes multiple printed products. In an embodiment of the present invention, the color of the printed image on each printed product of each batch needs to be detected.

[0028] S102, determining an environmental impact factor of the first printed image according to a first pixel value of each pixel in the first printed image, second pixel values ​​of pixels in a neighborhood of each pixel, and environmental parameters of an environment where the printed product is located.

[0029] Specifically, during the printing process, under the same printing parameters, the environmental factors in the printing environment may cause uneven colors after printing, resulting in printing quality problems. Among them, too high or too low temperature and humidity may cause the state of the ink to change, thereby causing the printed color to change, affecting the color quality of the printed image. Therefore, the embodiment of the present invention combines the pixel values ​​of the pixels in the printed image and the environmental parameters of the environment to determine the influencing factors of the printed image affected by the environment.

[0030] Furthermore, when determining the environmental impact factor of the first printed image, as an optional embodiment of the present invention, first, according to the first pixel value of each pixel in the first printed image and the second pixel value of the pixel in the neighborhood of each pixel, the pixel difference value of each pixel is determined; then, according to the pixel difference value of each pixel in the first printed image, each pixel is clustered to obtain multiple clusters, and all the pixels in each cluster are divided into a region in the first printed image; then, the gradient of the pixel in each region in the first printed image, the gradient of the pixel in the neighborhood of each pixel, and the pixel difference value of the pixel in each region are used to determine the degree of regional change of each region in the first printed image; finally, according to the environmental parameters of the environment in which the printed product is located, the first number of regions in the first printed image, and the maximum degree of regional change in the first printed image, the environmental impact factor of the printed image is determined.

[0031] Specifically, firstly, the color-uneven region in each printed image is obtained. If the color change of each pixel point and the surrounding neighboring pixel points is different, the more likely it is the color-uneven region. Therefore, when determining the pixel difference value of the pixel point, firstly, for each pixel point in the first printed image, the absolute value of the first difference between the first pixel value of the pixel point and the second pixel value of each pixel point in the neighborhood of the pixel point is calculated; then, the absolute values ​​of the first differences are superimposed to obtain the pixel difference value of the pixel point.

[0032] Specifically, the embodiment of the present invention uses the following formula to calculate the pixel difference value of the pixel point:

[0033]

[0034] In the above formula, Represents the pixel difference value of the i-th pixel point of the t-th first printed image. Represents the first pixel value of the i-th pixel point of the t-th first printed image. represents the second pixel value of the jth pixel in the neighborhood of the ith pixel of the tth first printed image. n represents the number of pixels in the neighborhood. It represents the difference between the pixel values ​​of each pixel and the pixels in its neighborhood. The larger the difference, the greater the difference in color change between the pixel and the pixels in its surrounding neighborhood. The more likely it is that the area is uneven in color, and the larger the pixel difference value of the i-th pixel.

[0035] The neighborhood of a pixel point may be a 4*4 range around the pixel point. Of course, the neighborhood of each pixel point may also be other ranges according to actual conditions, and the embodiment of the present invention is not limited thereto.

[0036] Furthermore, the pixel difference values ​​of all pixels in the first printed image are clustered by dbscan to form several clusters, each of which represents pixels with similar pixel difference values, which are clustered together due to color unevenness. Therefore, after clustering, for the pixels at the same position affected by color unevenness, the pixels with similar pixel difference values ​​are distributed in the same area, and all the pixels in each cluster are divided into one area, thereby obtaining multiple areas in the first printed image.

[0037] Furthermore, the gradient change of pixels in the region can reflect the change of brightness and color depth of the entire region. A relatively uniform gradient change indicates that the brightness and color depth of the entire region are relatively uniform, indicating that the entire region is regularly arranged. The gradient change of the color-uneven region caused by other factors may be more scattered and irregular, so the specific change of each region is analyzed according to the gradient change of each region. Therefore, when determining the degree of regional change of each region in the first printed image, as an optional embodiment of the present invention, firstly calculate the average gradient of the gradient of all pixels in the neighborhood of each pixel in each region, and the average difference value of the pixel difference values ​​of all pixels in each region; then calculate the second difference between the gradient of each pixel in each region in the first printed image and the average gradient of the pixels in its neighborhood; finally calculate the first product between the second difference and the average difference value, and superimpose the first products corresponding to each pixel in the region to obtain the degree of regional change of the region.

[0038] Specifically, the embodiment of the present invention uses the following formula to calculate the regional change degree of the region:

[0039]

[0040] In the above formula, Indicates the degree of region change of the u-th region of the t-th first printed image. Represents the second difference between the gradient of the i-th pixel point in the u-th region of the t-th first printed image and the average gradient of the gradients of all pixels in the neighborhood. Represents the average difference value of the pixel difference values ​​of all pixels in the u-th area of ​​the t-th first printed image. represents the first region u in the first printed image The larger the gradient fluctuation between each pixel and its neighboring pixels, the more disordered the color change in the area may be, which may be the color change affected by other factors. The smaller the gradient fluctuation, the more likely the pixels are distributed according to a certain rule, which may be the original color information of the printed product.

[0041] Furthermore, the environmental parameters in the environment where the printed product is located include, but are not limited to, the temperature and humidity in the environment. In the printing environment, the environmental parameters also include the optimal printing temperature and the optimal printing humidity. Among them, temperature fluctuations can affect the fluidity of the ink. In a high temperature environment, the viscosity of the ink may decrease, causing the ink to flow too much and unable to be accurately maintained in the predetermined printing area, thereby causing an uneven ink layer and inconsistent color depth; while in a low temperature environment, the viscosity of the ink may increase, and the fluidity of the ink may decrease, resulting in the ink being unable to fully penetrate into the paper surface during the printing process, resulting in an unsaturated or blurred color effect. When the humidity is too high, the paper may absorb moisture and swell, causing the surface of the paper to become uneven, thereby affecting the adhesion of the ink, resulting in poor color permeability and uneven ink drying. In addition, excessive humidity may also cause incomplete evaporation of the water in the ink, prolong the drying time, and even cause the ink to overflow or drag during the printing process. On the contrary, when the humidity is too low, the paper may become too dry due to insufficient moisture absorption, causing the ink to be difficult to distribute evenly, and the printed image may show a phenomenon of discontinuity or color incoherence. Therefore, in an ideal printing environment, the reference temperature suitable for printing is 23±2°C and the relative humidity is 45% to 65%. This range can effectively ensure the adhesion of the ink, the drying speed and the stability of the final printing effect; the more colors there are, the greater the impact of temperature and humidity may be, and the richness of the colors in the printed image will also aggravate the impact of temperature and humidity on the printing quality. The more colors there are, the more complex the types and mixing ratios of the inks are, and the sensitivity to environmental changes is enhanced. Therefore, in the embodiment of the present invention, the optimal printing temperature is 24°C and the optimal printing humidity is 55%.

[0042] Furthermore, when determining the environmental impact factor of the first printed image, as an optional embodiment of the present invention, first determine the third difference between the temperature of the environment in which the printed product is printed and the optimal printing temperature, and the fourth difference between the humidity of the environment in which the printed product is printed and the optimal printing humidity; then calculate the second product of the third difference, the fourth difference, the first number and the maximum regional change degree in the first printed image; finally, normalize the second product to obtain the environmental impact factor of the first printed image.

[0043] Specifically, the embodiment of the present invention uses the following formula to calculate the environmental impact factor of the printed image:

[0044]

[0045] In the above formula, Indicates the current Environmental impact factors of the first printed image of a batch of printing. Indicates The third difference between the temperature of the environment during printing of each batch and the optimal printing temperature. Indicates The fourth difference between the humidity of the environment when a batch is printed and the optimal printing humidity. Indicates The first number of areas in the t-th first printed image when printing a batch. Indicates the maximum area variation degree of the t-th first printed image. Represents the normalization function, which is used to Perform normalization. Indicates the current The difference between the temperature and humidity during printing of a batch and the optimal printing temperature and humidity during normal printing. The greater the difference, the greater the possible environmental impact. The more areas there are, the more possible color types there are, the greater the impact may be, and the greater the environmental impact factor.

[0046] in, The maximum and minimum normalization functions can be specifically represented.

[0047] S103, determining the regional distribution characteristic value of the first printed image based on the first number of regions in the first printed image, the second number of regions in the second printed image of other printed products in the same batch as the printed products, the maximum degree of regional variation in the first printed image, and the maximum degree of regional variation in the second printed image.

[0048] The region represents a region in which the pixel values ​​of the pixels in the printed image are similarly distributed, and the regional variation degree represents the gradient fluctuation degree of the pixels in the region.

[0049] Specifically, the color unevenness caused by temperature and humidity in the above-mentioned embodiments of the present invention often manifests as random or local changes. For example, at different positions on the same sheet of paper, the drying speed of the ink may be different, resulting in different shades of color in some areas of the printed image, or even mottled or color difference. Since this change usually occurs in a short period of time and its impact range is relatively limited, its manifestation is relatively irregular. Too high a temperature in the printing workshop will cause important amine substances in the water to evaporate, so that the pH value is too low, resulting in poor ink transfer, causing bubbling, pinholes and overall lighter printing color problems. On the other hand, too high a pH may burn the pigments in the ink, for example, some oranges are not as durable as other pigments. The volatile components of these inks may disappear from the ink in small amounts, causing color loss. Among them, unlike the color unevenness caused by changes in temperature and humidity, the color unevenness of the printed image itself is inherent and pre-existing in the printed product. This color unevenness feature is usually determined by multiple factors such as the content of the printed product, shooting conditions, light distribution, and artistic creation techniques. Different from the color deviation caused by changes in the external environment, the color unevenness of printed images often presents a certain regularity and is a normal visual effect. Therefore, the regional distribution characteristics and color distribution rules of each printed image are analyzed.

[0050] Furthermore, when determining the regional distribution characteristic value of the first printed image, as an optional embodiment of the present invention, the absolute value of the fifth difference between the first quantity and the second quantity and the absolute value of the sixth difference between the maximum regional change degree in the first printed image and the maximum regional change degree in the second printed image are first calculated; then the third product of the absolute value of the fifth difference, the absolute value of the sixth difference and the distance is calculated, and the distance is the distance between the first area corresponding to the maximum regional change degree in the first printed image and the second area corresponding to the maximum regional change degree in the second printed image; finally, the third products are superimposed to obtain the regional distribution characteristic value of the first printed image.

[0051] Specifically, the embodiment of the present invention uses the following formula to calculate the regional distribution characteristic value of the first printed image:

[0052]

[0053] In the above formula, Indicates the current The regional distribution characteristic value of the tth first printed image when printing a batch. Indicates the current The first number of regions in the t-th first printed image when printing a batch. Indicates the current When printing a batch of A second number of regions in a second printed image. The maximum degree of regional variation of the t-th first printed image. No. The maximum degree of regional variation of the second printed image. The first area corresponding to the largest area change degree in the t-th first printed image is The distance between the second regions corresponding to the maximum region change degree in the second printed image. z represents the current The number of second printed images in a batch. It indicates the difference in the number of regions between the t-th first printed image and the other second printed images. The greater the difference in the number of regions, the more different the regions of color unevenness during printing are, which may not be caused by color changes in the printed product itself. It indicates the difference between the regional variation degree of color unevenness and its position in the t-th first printed image. In normal color variation of printed products, the difference between the regional variation degree of the same area and its position is small.

[0054] S104, determining the color quality of the first printed image according to the color characteristic values ​​of the first printed image and the second printed image, the regional distribution characteristic value of the first printed image, and the environmental impact factor.

[0055] Specifically, since printed products are made of a variety of colors modulated from a limited number of ink colors, the effects presented on each printed product are similar under normal circumstances. If they are not similar, it may be that the ink is affected. Therefore, the histogram of the RGB channels of the printed image of each printed product is obtained, and the maximum values ​​in the R channel, G channel, and B channel are taken respectively. The ratio of the maximum value of each channel in the order of RGB is used as the color feature value f of each printed image. That is, the initial ratio of the maximum value in the R channel to the maximum value in the G channel is calculated first, and then the final ratio of the initial ratio to the maximum value in the B channel is calculated. The final ratio is the color feature value f of each printed image.

[0056] Furthermore, when determining the color quality of the first printed image, as an optional embodiment of the present invention, the color distribution law value of the first printed image is first determined based on the color characteristic values ​​of the first printed image and the second printed image, the regional distribution characteristic value of the first printed image and the regional distribution characteristic value of the second printed image; and then the ratio between the color distribution law value of the first printed image and the environmental impact factor of the first printed image is determined as the color quality of the first printed image.

[0057] Specifically, first, the color characteristic values ​​of the first printed image and the second printed image can be determined according to the histograms of the RGB channels in the first printed image and the second printed image respectively; then, the variance of the color characteristic values ​​of the first printed image and the second printed image is calculated; secondly, the regional distribution characteristic value of the first printed image and the regional distribution characteristic value of the second printed image are superimposed to obtain the superimposed characteristic value; and the fourth product between the variance and the superimposed characteristic value is calculated; finally, the fourth product is inversely normalized to obtain the color distribution law value of the first printed image.

[0058] Specifically, the embodiment of the present invention specifically uses the following formula to calculate the color distribution law value of the first printed image:

[0059]

[0060] In the above formula, Indicates the current The color distribution law value of the first printed image of a batch of printing. Indicates the current The regional distribution characteristic value of the tth first printed image when printing a batch. Represents the variance of the color characteristic values ​​of all the first printed images and the second printed images. Indicates The total number of printed products in a batch. It means that the smaller the regional distribution characteristic value is, the smaller the variance of all color characteristic values ​​is, which means that the more regular the color distribution is, the less the color of the printed image is affected, and the larger the color distribution regularity value is. Represents the inverse normalization function, which is used to Perform inverse proportional normalization.

[0061] Furthermore, for the printed images of the current batch, the overall color quality of the printed products of this batch can be analyzed by the influence of temperature and humidity in the current printing environment and the color distribution law specifically reflected on multiple printed products. In the embodiment of the present invention, the color quality of the first printed image is calculated using the following formula:

[0062]

[0063] In the above formula, Indicates the current The color quality of the first printed image in a batch of printing. Indicates the current The color distribution law value of the first printed image of a batch of printing. Indicates the current The environmental impact factor of the first printed image of a batch of printing. The larger the environmental impact factor, the more unstable the ink may be, and the greater the possibility of affecting the printed color. At the same time, the more irregular the color distribution in each printed image, that is, the lower the color distribution regularity value, the lower the color quality, and the higher the color distribution regularity value of the printing, the higher the color quality of the current batch of printing.

[0064] S105, detecting the color quality of the first printed image by using a first threshold.

[0065] Specifically, the embodiment of the present invention evaluates the color quality of the first printed image by setting a first threshold. By comparing the calculated color quality of the printed image with the first threshold, color deviation or inconsistency can be discovered in time, and the environmental conditions of the printing workshop can be adjusted according to these data, and the temperature and humidity of the printing workshop or the ink used for modulation can be readjusted in time. The first threshold can be set according to actual printing requirements, and the embodiment of the present invention is not limited here. Therefore, when the color quality of the first printed image is evaluated by the first threshold, as an optional embodiment of the present invention, when the color quality of the first printed image is greater than the first threshold, it is determined that the color quality of the first printed image meets the requirements; when the color quality of the first printed image is not greater than the first threshold, it is determined that the color quality of the first printed image does not meet the requirements, and the temperature and humidity of the environment in which the printed product is located are adjusted, and the printing ink of the printed product is readjusted.

[0066] Specifically, when the color quality of the first printed image does not meet the requirements, use an air conditioning system or constant temperature equipment to keep the temperature in the printing workshop stable. And install a humidifier or dehumidifier to adjust the humidity in the printing workshop as needed. Regularly check the temperature and humidity in the printing workshop, use a digital hygrometer and thermometer for real-time monitoring, keep the workshop ventilated, avoid moisture accumulation or excessive temperature fluctuations, so as to ensure the stability of the printing process and the consistency of color. Furthermore, the modulation of ink is also a key factor. The formulation and use of ink may fluctuate with environmental changes, so it is necessary to readjust the composition of the ink according to the color quality data of the printed product. Specifically, a small batch of ink mixing experiments are carried out in the ink laboratory, and each formulation is tested using a colorimeter, and the ink ratio is gradually adjusted until the target color requirements are met. The concentration, ratio and type of the ink are adjusted as needed to ensure the stability of the color quality. By accurately controlling the hue, concentration and viscosity of the ink, the color deviation can be effectively corrected to ensure the color reproduction and saturation. And a balance is achieved between the spectrophotometer, ink, substrate, printing press and printing environment to ensure the color accuracy of the printed product.

[0067] The embodiment of the present invention can identify the area of ​​uneven color for each printed image, and then analyze the environmental factors during printing according to the degree of regional change of the area, so as to obtain the environmental impact factor of the environment on the printed image. The color quality of the printed image is determined by combining the color characteristics, regional distribution characteristics and environmental sound impact factors in the printed image, and finally the color quality is evaluated based on the threshold. In this way, the embodiment of the present invention can evaluate the color quality of the printed product based on the printed image of the printed product, and the detection result will not be affected by the operator's experience and subjective factors, thereby improving the detection efficiency and accuracy of the printed image. The environmental parameters of the printed product can be adjusted according to the detection results, thereby ensuring that the quality of the printed product can meet the standards, reducing the scrap rate and improving production efficiency.

[0068] Embodiment 2:

[0069] Based on the visually assisted printed image color detection method provided in the above embodiment, and based on the same technical concept, an embodiment of the present invention further provides a visually assisted printed image color detection system. Figure 2 A schematic diagram of a visually assisted printed image color detection system according to an embodiment of the present invention is shown in FIG. Figure 2 As shown. The visually assisted printed image color detection system 200 includes: an acquisition module 201, used to acquire a first printed image of a printed product; a determination module 202, used to determine the environmental impact factor of the first printed image according to the first pixel value of each pixel in the first printed image, the second pixel value of the pixel in the neighborhood of each pixel, and the environmental parameters of the environment in which the printed product is located; the determination module 202 is also used to determine the regional distribution characteristic value of the first printed image according to the first number of regions in the first printed image, the second number of regions in the second printed image of other printed products in the same batch as the printed product, the maximum regional change degree in the first printed image, and the maximum regional change degree in the second printed image, wherein the region represents the region with similar pixel value distribution of the pixels in the printed image, and the regional change degree represents the gradient fluctuation degree of the pixels in the region; the determination module 202 is also used to determine the color quality of the first printed image according to the color characteristic values ​​of the first printed image and the second printed image, the regional distribution characteristic value of the first printed image, and the environmental impact factor; the detection module 203 is used to detect the color quality of the first printed image through a first threshold.

[0070] The embodiment of the present invention can identify the area of ​​uneven color for each printed image, and then analyze the environmental factors during printing according to the degree of regional change of the area, so as to obtain the environmental impact factor of the environment on the printed image. The color quality of the printed image is determined by combining the color characteristics, regional distribution characteristics and environmental sound impact factors in the printed image, and finally the color quality is evaluated based on the threshold. In this way, the embodiment of the present invention can evaluate the color quality of the printed product based on the printed image of the printed product, and the detection result will not be affected by the operator's experience and subjective factors, thereby improving the detection efficiency and accuracy of the printed image. The environmental parameters of the printed product can be adjusted according to the detection results, thereby ensuring that the quality of the printed product can meet the standards, reducing the scrap rate and improving production efficiency.

[0071] Embodiment three:

[0072] Corresponding to the visually assisted printed image color detection method provided in the above embodiment, based on the same technical concept, an embodiment of the present invention further provides a visually assisted printed image color detection system, which is used to execute the visually assisted printed image color detection method. Figure 3 A schematic diagram of a visually assisted printed image color detection system is provided as another embodiment of the present invention. Figure 3 The visually assisted printed image color detection system may have relatively large differences due to different configurations or performances, and may include one or more processors 301 and memory 302, the memory 302 is used to store computer programs that can be run on the processor 301, and the processor 301 is used to execute the program stored in the memory 302 to achieve the above Figure 1 The memory 302 may be a temporary storage or a permanent storage. The application stored in the memory 302 may include one or more modules (not shown in the figure), each of which may include a series of computer executable instructions in the visually assisted printed image color detection system.

[0073] Furthermore, the processor 301 can be configured to communicate with the memory 302, and execute a series of computer executable instructions in the memory 302 on the visually assisted printed image color detection system. The visually assisted printed image color detection system can also include one or more power supplies 303, one or more wired or wireless network interfaces 304, one or more input and output interfaces 305, and one or more keyboards 306.

[0074] Specifically in this embodiment, the visually assisted printed image color detection system includes a processor, a communication interface, a memory and a communication bus; wherein the processor, the communication interface and the memory communicate with each other through the bus; the memory is used to store computer programs; the processor is used to execute the programs stored in the memory to achieve the above Figure 1 The various steps in the method embodiment are similar to those in the method embodiment, and have the beneficial effects of the above method embodiments. To avoid repetition, the embodiments of the present invention will not be described in detail here.

[0075] It should be noted that the visually assisted printed image color detection system provided in the embodiment of the present invention and the visually assisted printed image color detection method provided in the embodiment of the present invention are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned visually assisted printed image color detection method, and has the same or similar beneficial effects, and the repeated parts will not be repeated.

[0076] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0077] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for detecting the color of a printed image with visual assistance, characterized in that: The visually assisted printed image color detection method comprises: acquiring a first printed image of a printed product; determining an environmental impact factor of the first printed image according to a first pixel value of each pixel in the first printed image, second pixel values ​​of pixels in a neighborhood of each pixel, and environmental parameters of an environment in which the printed product is located; Determining a regional distribution characteristic value of the first printed image according to a first number of regions in the first printed image, a second number of regions in a second printed image of another printed product in the same batch as the printed product, a maximum regional variation degree in the first printed image, and a maximum regional variation degree in the second printed image, wherein the regions represent regions with similar pixel value distributions of pixels in the printed image, and the regional variation degree represents a gradient fluctuation degree of pixels in the region; determining the color quality of the first printed image according to the color characteristic values ​​of the first printed image and the second printed image, the regional distribution characteristic value of the first printed image, and the environmental influencing factor; The color quality of the first printed image is detected using a first threshold.

2. The visually assisted printed image color detection method according to claim 1, characterized in that: Determining the environmental impact factor of the first printed image according to the first pixel value of each pixel in the first printed image, the second pixel value of each pixel in the neighborhood of the pixel, and the environmental parameters of the environment in which the printed product is located includes: Determine a pixel difference value of each pixel point according to a first pixel value of each pixel point in the first printed image and a second pixel value of a pixel point in a neighborhood of each pixel point; Clustering each pixel point according to the pixel difference value of each pixel point in the first printed image to obtain a plurality of clusters, and dividing all the pixel points in each cluster into an area in the first printed image; Determine the degree of regional change of each of the regions in the first printed image by using the gradient of the pixels in each of the regions in the first printed image, the gradient of the pixels in the neighborhood of each of the pixels, and the pixel difference value of the pixels in each of the regions; An environmental impact factor of the first printed image is determined according to environmental parameters of the environment in which the printed product is located, a first number of regions in the first printed image, and a maximum degree of regional variation in the first printed image.

3. The visually assisted printed image color detection method according to claim 2, characterized in that: Determining the pixel difference value of each pixel point according to the first pixel value of each pixel point in the first printed image and the second pixel value of each pixel point in the neighborhood of the pixel point includes: For each pixel in the first printed image, calculating an absolute value of a first difference between a first pixel value of the pixel and a second pixel value of each pixel in a neighborhood of the pixel; The absolute values ​​of the first difference values ​​are superimposed to obtain the pixel difference value of the pixel point.

4. The visually assisted printed image color detection method according to claim 2, characterized in that: Determining the degree of regional change of each of the regions in the first printed image by using the gradient of the pixel points in each of the regions in the first printed image, the gradient of the pixel points in the neighborhood of each of the pixel points, and the pixel difference value of the pixel points in each of the regions includes: Calculating the average gradient of the gradients of all pixels in the neighborhood of each pixel in each of the regions, and the average difference value of the pixel difference values ​​of all pixels in each of the regions; Calculating a second difference between the gradient of each pixel point in each of the regions in the first printed image and the average gradient of the pixels points in its neighborhood; A first product between the second difference value and the average difference value is calculated, and the first products corresponding to the pixels in the area are superimposed to obtain the area change degree of the area.

5. The visually assisted printed image color detection method according to claim 2, characterized in that: Determining the environmental impact factor of the first printed image according to the environmental parameters of the environment in which the printed product is located, the first number of regions in the first printed image, and the maximum degree of regional change in the first printed image includes: Determining a third difference between the temperature of the environment in which the printed product is printed and the optimal printing temperature, and a fourth difference between the humidity of the environment in which the printed product is printed and the optimal printing humidity; calculating a second product of the third difference, the fourth difference, the first number, and the maximum regional variation degree in the first printed image; The second product is normalized to obtain the environmental impact factor of the first printed image.

6. The visually assisted printed image color detection method according to any one of claims 1 to 5, characterized in that: Determining the regional distribution characteristic value of the first printed image according to the first number of regions in the first printed image, the second number of regions in the second printed image of another printed product in the same batch as the printed product, the maximum regional variation degree in the first printed image, and the maximum regional variation degree in the second printed image includes: calculating an absolute value of a fifth difference between the first number and the second number, and an absolute value of a sixth difference between a maximum degree of regional variation in the first printed image and a maximum degree of regional variation in the second printed image; Calculating a third product of the absolute value of the fifth difference, the absolute value of the sixth difference, and the distance between a first region corresponding to the maximum regional change degree in the first printed image and a second region corresponding to the maximum regional change degree in the second printed image; The third products are superimposed to obtain the regional distribution characteristic value of the first printed image.

7. The visually assisted printed image color detection method according to claim 1, characterized in that: The determining the color quality of the first printed image according to the color characteristic values ​​of the first printed image and the second printed image, the regional distribution characteristic value of the first printed image and the environmental impact factor comprises: determining a color distribution regularity value of the first printed image according to the color characteristic values ​​of the first printed image and the second printed image, the regional distribution characteristic value of the first printed image, and the regional distribution characteristic value of the second printed image; The ratio between the color distribution law value of the first printed image and the environmental impact factor of the first printed image is determined as the color quality of the first printed image.

8. The method for detecting color of printed images with visual assistance according to claim 7, characterized in that: Determining the color distribution regularity value of the first printed image according to the color characteristic values ​​of the first printed image and the second printed image, the regional distribution characteristic value of the first printed image, and the regional distribution characteristic value of the second printed image comprises: Determining color characteristic values ​​of the first printed image and the second printed image according to histograms of RGB channels in the first printed image and the second printed image respectively; calculating a variance of color feature values ​​of the first printed image and the second printed image; superimposing the regional distribution characteristic value of the first printed image and the regional distribution characteristic value of the second printed image to obtain a superimposed characteristic value; calculating a fourth product between the variance and the superposition eigenvalue; The fourth product is subjected to inverse proportional normalization processing to obtain a color distribution law value of the first printed image.

9. The visually assisted printed image color detection method according to claim 1, characterized in that: The detecting the color quality of the first printed image by using a first threshold comprises: When the color quality of the first printed image is greater than a first threshold, determining that the color quality of the first printed image meets the requirement; When the color quality of the first printed image is not greater than the first threshold, it is determined that the color quality of the first printed image does not meet the requirements, and the temperature and humidity of the environment in which the printed product is located are adjusted and the printing ink of the printed product is readjusted.

10. A visually assisted printed image color detection system, characterized in that: include: A processor and a memory; wherein the memory is used to store a computer program that can be run on the processor; A processor is used to execute the program stored in the memory to implement the steps of the visually assisted printed image color detection method as described in any one of claims 1 to 9.

Images