An intelligent defect recognition system for thermal sublimation transfer paper based on image analysis

Abstract

The present invention relates to the field of computer vision technology. Specifically, it relates to an intelligent defect recognition system for thermal sublimation transfer paper based on image analysis, including an image acquisition module, a pattern defect acquisition module, a pattern defect analysis module, a color defect acquisition module, a color defect analysis module, a paper defect detection module, a paper defect analysis module, a comprehensive analysis module for transfer finished products, and a management database. This system analyzes the pattern defect parameters of the transfer finished product image to obtain the pattern evaluation coefficient of the transfer finished product image, analyzes the color defect parameters of the transfer finished product image to obtain the color evaluation coefficient of the transfer finished product image, analyzes the paper defect parameters of the thermal sublimation transfer paper to obtain the paper evaluation coefficient of the thermal sublimation transfer paper, and then comprehensively evaluates to obtain the defect evaluation index of the thermal sublimation transfer paper, which helps to clarify the specific defect sources and influence degrees in the thermal sublimation transfer process, and quickly discover and solve problems.

Description

Technical Field

[0001] The present invention relates to the field of computer vision technology. Specifically, it is an intelligent recognition system for defects of thermal sublimation transfer paper based on image analysis. Background Art

[0002] Thermal sublimation transfer technology is a special printing technology. Its principle is mainly based on the fact that certain dyes can directly change from solid state to gaseous state at a specific temperature and penetrate into the receiving material to achieve printing. With the continuous development of material science and printing technology, thermal sublimation transfer technology has gradually matured and improved. Early thermal sublimation transfer was mainly applied to some specific fields, such as photo printing, etc. Now it has been widely used in many industries such as textiles, plastic products, ceramics, etc. With the progress of technology and the change of market demand, the requirements for transfer quality are becoming increasingly strict.

[0003] For example, the existing Chinese patent with the publication number CN116572636B discloses a detection method and system for a double-roller thermal transfer device. This solution can comprehensively evaluate the transfer quality of the thermal transfer device by detecting the defects of the film material before transfer, the transfer width of the film material, the defects of the finished product after transfer, and the remaining waste after transfer, master the conditions of each link in the thermal transfer process, and timely discover the problems existing in the film material itself and the defects occurring in the transfer process, ensuring a good effect of thermal transfer.

[0004] However, there are the following problems in the above patent: This solution mainly detects the damaged positions and defect positions on the finished product film for the defects of the finished product after transfer, and does not involve the defect detection of the transferred pattern, such as blurring, deformation, missing printing, etc. This may lead to an incomplete evaluation of the finished product quality, unable to timely discover problems in the transferred pattern, thus affecting the overall quality and aesthetics of the product, and may also not meet the standards in some application scenarios with high requirements for pattern quality. Summary of the Invention

[0005] In order to overcome the shortcomings in the background art, the embodiments of the present invention provide an intelligent recognition system for defects of thermal sublimation transfer paper based on image analysis, which can effectively solve the problems involved in the above background art.

[0006] The object of the present invention can be achieved by the following technical solutions: The present invention provides an intelligent recognition system for defects of thermal sublimation transfer paper based on image analysis, including: an image acquisition module for acquiring an image of the thermal sublimation transfer paper, denoted as the transferred finished product image.

[0007] A pattern defect acquisition module for detecting the pattern defect parameters of the transferred finished product image, where the pattern defect parameters include the pattern blurring degree, the pattern deformation degree, and the pattern missing printing degree.

[0008] A pattern defect analysis module, which is used to analyze the pattern evaluation coefficient α of the transferred finished product image based on the pattern defect parameters of the transferred finished product image.

[0009] A color defect acquisition module, which is used to detect the color defect parameters of the transferred finished product image. The color defect parameters include the proportion of color spots, the degree of color deviation, and the degree of color uniformity.

[0010] A color defect analysis module, which is used to analyze the color evaluation coefficient β of the transferred finished product image based on the color defect parameters of the transferred finished product image.

[0011] A paper defect detection module, which is used to detect the paper defect parameters of the thermal sublimation transfer paper. The paper defect parameters include the degree of ink accumulation and the degree of warping.

[0012] A paper defect analysis module, which is used to analyze the paper evaluation coefficient γ of the thermal sublimation transfer paper based on the paper defect parameters of the thermal sublimation transfer paper.

[0013] A comprehensive analysis module for the transferred finished product, which is used to analyze the defect evaluation index of the thermal sublimation transfer paper based on the pattern evaluation coefficient, color evaluation coefficient, and paper evaluation coefficient of the thermal sublimation transfer paper of the transferred finished product image, and provide feedback on it.

[0014] A management database, which is used to store the pixel point difference threshold, the transferred master image, and the flatness difference threshold.

[0015] Preferably, the specific analysis method of the image acquisition module is as follows: First step, obtain the thermally sublimated transfer paper after transfer.

[0016] Second step, use a high-definition camera to obtain an image of the thermally sublimated transfer paper after transfer.

[0017] Third step, record the obtained image of the thermally sublimated transfer paper as the transferred finished product image.

[0018] Preferably, the specific analysis method of the pattern defect acquisition module is as follows: First step, read the transferred finished product image, perform grayscale processing on the transferred finished product image, and divide it into several sub-regions with equal areas, which are recorded as each sub-region of the transferred finished product image. Detect the grayscale values of each pixel point in each sub-region of the transferred finished product image, and obtain the difference of each pixel point in each sub-region of the transferred finished product image by subtracting the grayscale value of each pixel point in each sub-region of the transferred finished product image from the grayscale value of its adjacent pixel point, which is recorded as Δσ im , where i represents the number of the i-th sub-region, i = 1, 2,..., n, m represents the number of the m-th pixel point, m = 1, 2,..., q. At the same time, read the preset pixel point difference threshold recorded as Δσ0 from the management database, and substitute it into the formula Obtain the pattern blurring degree ξ of the transferred finished product image, n represents the number of sub-regions, and q represents the number of pixel points.

[0019] In the second step, read the transferred master image from the management database, adjust its size to the same size as the transferred finished product image through size scaling, take a number of key points on the transferred master image at a set gap, and mark the set key points on the transferred finished product image in sequence. Make the key points correspond one by one, denoted as each group of key points of the transferred image. Overlap the transferred master image with the transferred finished product image, measure the distances of each group of key points of the transferred image respectively, and denote it as d j , j represents the number of the jth group of key points, j = 1, 2,..., k. Calculate the average value of the distances of each group of key points of the transferred image, and denote it as Substitute it into the formula Obtain the pattern deformation degree ζ of the transferred finished product image, and k represents the number of groups of key points.

[0020] In the third step, extract the transferred pattern parts in the transferred master image and the transferred finished product image respectively through edge contour extraction technology, denoted as the edge contour of the transferred master pattern and the edge contour of the transferred finished product pattern. Overlap the edge contour of the transferred master pattern and the edge contour of the transferred finished product pattern to obtain the number of overlapping pixel points, denoted as N. At the same time, extract the total number of pixel points of the transferred master image, denoted as N 总 , Substitute it into the formula Obtain the pattern missing printing degree ε of the transferred finished product image.

[0021] Preferably, the specific analysis method of the pattern defect analysis module is: read the pattern blurring degree ξ, pattern deformation degree pattern missing printing degree ε of the transferred finished product image respectively, and substitute them into the formula Obtain the pattern evaluation coefficient α of the transferred finished product image. φ1, φ2, and φ3 respectively represent the weight factors of the set pattern blurring degree, pattern deformation degree, and pattern missing printing degree, and e represents the natural constant.

[0022] Preferably, the specific analysis method of the color defect acquisition module is: in the first step, denote each pixel point in the transferred master image and the transferred finished product image as each transferred pixel point, detect the chromaticity values of each transferred pixel point in the red (R), green (G), and blue (B) color channels of the transferred master image and the transferred finished product image respectively, calculate the difference between the two to obtain the chromaticity value differences of each transferred pixel point in the R, G, and B channels of the transferred finished product image and the transferred master image, and compare them with the preset chromaticity value difference thresholds respectively to screen out each abnormal chromaticity pixel point, and count the number of each abnormal chromaticity pixel point, denoted as N 异常 , read the total number of pixel points N of the transferred master image 总 , through the formula Obtain the percentage ο of color spots in the transferred finished product image.

[0023] In the second step, read the chromaticity values of each transfer pixel point of the transfer master image. The chromaticity values of each transfer pixel point of the transferred finished product image. By calculating the average value of each of them respectively, obtain the average chromaticity values of the transfer master image and the transferred finished product image. Substitute it into the formula Obtain the color deviation degree ρ of the transferred finished product image.

[0024] In the third step, read the gray scale values σ of each pixel point in each sub-region of the transferred finished product image. im , through the formula Obtain the average gray scale value of each sub-region of the transferred finished product image. q represents the number of pixel points, and calculate the average value of the average gray scale values of each sub-region of the transferred finished product image, denoted as Substitute it into the formula Obtain the color uniformity degree λ of the transferred finished product image, where n represents the number of sub-regions.

[0025] Preferably, the specific analysis method of the color defect analysis module is: respectively read the percentage ο of color spots, the color deviation degree ρ, and the color uniformity degree λ of the transferred finished product image, and substitute them into the formula Obtain the color evaluation coefficient β of the transferred finished product image. respectively represent the weight factors of the set percentage of color spots, color deviation degree, and color uniformity degree, and e represents the natural constant.

[0026] Preferably, the specific analysis method of the paper defect detection module is: in the first step, place the thermal sublimation transfer paper stably on the detection platform, select detection points according to the set gap, and obtain the flatness of each detection point of the thermal sublimation transfer paper through a flatness measuring instrument, denoted as P f , f represents the number of the f-th detection point, f = 1, 2,..., g, calculate the average value of the flatness of each detection point of the thermal sublimation transfer paper, denoted as And read the preset flatness difference threshold from the management database, denoted as ΔP0, and substitute it into the formula Obtain the ink accumulation degree τ of the thermal sublimation transfer paper.

[0027] In the second step, place the thermal sublimation transfer paper on a flat horizontal plane, and measure the distance between each detection point of the thermal sublimation transfer paper and the horizontal plane using a vernier caliper, denoted as d' f , substitute it into the formula Obtain the warping degree of the thermal sublimation transfer paper. g represents the number of detection points.

[0028] Preferably, the specific analysis method of the paper defect analysis module is as follows: read the ink accumulation degree τ and warping degree of the thermal sublimation transfer paper Substitute them into the formula to obtain the paper evaluation coefficient γ of the thermal sublimation transfer paper, where η1 and η2 respectively represent the weight factors of the set ink accumulation degree and warping degree, and e represents the natural constant.

[0029] Preferably, the specific analysis method of the defect evaluation index of the thermal sublimation transfer paper is as follows: respectively read the pattern evaluation coefficient α, color evaluation coefficient β of the transferred finished product image, and the paper evaluation coefficient γ of the thermal sublimation transfer paper, and substitute them into the formula to obtain the defect evaluation index of the thermal sublimation transfer paper where w1, w2, and w3 respectively represent the weight factors of the set pattern evaluation coefficient, color evaluation coefficient, and paper evaluation coefficient of the transferred finished product image.

[0030] Preferably, the specific analysis method of the transferred finished product comprehensive analysis module is as follows: read the defect evaluation index of the thermal sublimation transfer paper, and compare it with the preset defect evaluation index threshold. If the defect evaluation index of the thermal sublimation transfer paper is greater than or equal to the preset defect evaluation index threshold, it means that the defect evaluation index of the thermal sublimation transfer paper is qualified. If the defect evaluation index of the thermal sublimation transfer paper is less than the preset defect evaluation index threshold, it means that the defect evaluation index of the thermal sublimation transfer paper is unqualified, and feedback is given to the system.

[0031] Compared with the prior art, the present invention has the following beneficial effects: First, the present invention analyzes the pattern evaluation coefficient of the transferred finished product image based on the pattern defect parameters of the transferred finished product image, which helps to timely discover and solve pattern defect problems, thereby improving the quality stability of the transferred finished product.

[0032] Second, the present invention analyzes the color evaluation coefficient of the transferred finished product image based on the color defect parameters of the transferred finished product image, which helps to ensure that the colors of the transferred finished products in mass production are consistent and improve the overall quality of the products.

[0033] Third, the present invention analyzes the paper evaluation coefficient of the thermal sublimation transfer paper based on the paper defect parameters of the thermal sublimation transfer paper. By understanding the paper defects, corresponding measures can be taken to avoid or reduce the poor transfer quality caused by paper problems.

[0034] Fourth, the present invention analyzes the defect evaluation index of the thermal sublimation transfer paper based on the pattern evaluation coefficient, color evaluation coefficient, and paper evaluation coefficient of the transferred finished product image, and gives feedback on it, which helps to clarify the specific defect sources and influence degrees in the thermal sublimation transfer process, quickly discover and solve problems, reduce unnecessary repetitive work and time waste, and improve production efficiency. Brief Description of the Drawings

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0036] Figure 1 It is a system module connection diagram of the present invention.

[0037] Figure 2 For Figure 1 it is a schematic flowchart of the method of the image acquisition and collection module in

[0038] Figure 3 For Figure 1 it is a flowchart judgment block diagram of the transfer finished product comprehensive analysis module. Detailed Embodiments

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0040] Please refer to Figure 1 As shown, an intelligent defect recognition system for heat sublimation transfer paper based on image analysis includes an image acquisition module, a pattern defect acquisition module, a pattern defect analysis module, a color defect acquisition module, a color defect analysis module, a paper defect detection module, a paper defect analysis module, a transfer finished product comprehensive analysis module, and a management database.

[0041] The management database is connected to the image acquisition module, the pattern defect analysis module, the color defect analysis module, the paper defect analysis module, and the transfer finished product comprehensive analysis module. The pattern defect acquisition module is connected to the pattern defect analysis module. The color defect acquisition module is connected to the color defect analysis module. The paper defect detection module is connected to the paper defect analysis module. The transfer finished product comprehensive analysis module is connected to the pattern defect analysis module, the color defect analysis module, and the paper defect analysis module.

[0042] The image acquisition module is used to obtain the image of the heat sublimation transfer paper, denoted as the transfer finished product image.

[0043] Please refer to Figure 2 As shown, the specific analysis method of the image acquisition module is as follows: First step, obtain the heat sublimation transfer paper after transfer.

[0044] In the second step, an image of the sublimation transfer paper after transfer is acquired through a high-definition camera.

[0045] In the third step, the obtained sublimation transfer paper image is recorded as the transferred finished product image; presenting the transferred state in the form of an image can more intuitively understand the situation and timely detect possible problems in the transfer process.

[0046] The pattern defect acquisition module is used to detect the pattern defect parameters of the transferred finished product image. The pattern defect parameters include the degree of pattern blurring, the degree of pattern deformation, and the degree of pattern missing printing.

[0047] The specific analysis method of the pattern defect acquisition module is as follows: In the first step, read the transferred finished product image, perform grayscale processing on the transferred finished product image, and divide it into several sub-regions with equal areas, denoted as each sub-region of the transferred finished product image. Detect the grayscale values of each pixel point in each sub-region of the transferred finished product image, and obtain the difference of each pixel point in each sub-region of the transferred finished product image by subtracting the grayscale value of each pixel point in each sub-region of the transferred finished product image from the grayscale value of its adjacent pixel point, denoted as Δσ im , where i represents the number of the i-th sub-region, i = 1, 2,..., n, m represents the number of the m-th pixel point, m = 1, 2,..., q. At the same time, read the preset pixel point difference threshold from the management database, denoted as Δσ0, and substitute it into the formula to obtain the pattern blurring degree ξ of the transferred finished product image. n represents the number of sub-regions, and q represents the number of pixel points. Through operations such as grayscale processing and region division, the characteristics of different parts of the transferred finished product image can be deeply understood, making the evaluation of the quality of the transferred finished product more accurate and objective, and timely detecting potential blurring problems.

[0048] It should be noted that the specific analysis method of the difference of each pixel point in each sub-region of the transferred finished product image is as follows: Read the grayscale values of each pixel point in each sub-region of the transferred finished product image. At the same time, obtain the grayscale values of the four adjacent upper, lower, left, and right pixel points of each pixel point in each sub-region of the transferred finished product image respectively. Obtain the difference between the grayscale value of each pixel point in each sub-region of the transferred finished product image and the grayscale values of the four adjacent upper, lower, left, and right pixel points, and obtain the difference of each pixel point in each sub-region of the transferred finished product image by taking the average value of them.

[0049] Second step: Read the transfer master image from the management database, resize it to the same size as the transferred finished product image, take several key points on the transfer master image at the set gap, and mark the set key points on the transferred finished product image in sequence. Make the key points correspond one by one, denoted as each group of key points of the transfer image. Overlap the transfer master image with the transferred finished product image, measure the distances of each group of key points of the transfer image respectively, and denote it as d j , where j represents the number of the j-th group of key points, j = 1, 2,..., k. Calculate the average value of the distances of each group of key points of the transfer image, and denote it as Substitute it into the formula to obtain the pattern deformation degree of the transferred finished product image k represents the number of groups of key points; it can promptly detect the pattern deformation problems caused during the transfer process, improve product quality, help maintain the consistency between the transferred finished products of different batches and the master, and reduce deviations.

[0050] Third step: Use the edge contour extraction technology to extract the transfer pattern parts in the transfer master image and the transferred finished product image respectively, denoted as the transfer master pattern edge contour and the transferred finished product pattern edge contour. Overlap the transfer master pattern edge contour and the transferred finished product pattern edge contour to obtain the number of overlapping pixel points, denoted as N. At the same time, extract the total number of pixel points of the transfer master image, denoted as N 总 , and substitute it into the formula to obtain the pattern missing printing degree ε of the transferred finished product image; it can accurately know the specific degree of pattern missing printing of the transferred finished product, facilitate timely problem discovery, effectively reduce the missing printing phenomenon, and ensure the integrity and quality of the transferred finished product.

[0051] Pattern defect analysis module, used to analyze and obtain the pattern evaluation coefficient α of the transferred finished product image according to the pattern defect parameters of the transferred finished product image.

[0052] The specific analysis method of the pattern defect analysis module is: Read the pattern blur degree ξ and pattern deformation degree pattern missing printing degree ε of the transferred finished product image respectively, and substitute them into the formula to obtain the pattern evaluation coefficient α of the transferred finished product image. φ1, φ2, and φ3 respectively represent the set weight factors of the pattern blur degree, pattern deformation degree, and pattern missing printing degree, and e represents the natural constant; it can more comprehensively and accurately reflect the overall quality status of the transferred finished product, rather than a single-dimensional consideration, making quality control more scientific and reasonable, and ensuring the stability of product quality.

[0053] It should be noted that in a specific embodiment, φ1 can be set to 0.3, φ2 can be set to 0.3, and φ3 can be set to 0.4. Pattern missing printing will directly result in an incomplete pattern, seriously affecting the overall effect. Therefore, the weight corresponding to pattern missing printing is relatively large.

[0054] A color defect acquisition module is used to detect the color defect parameters of the transferred finished product image. The color defect parameters include the proportion of color spots, the degree of color deviation, and the degree of color uniformity.

[0055] The specific analysis method of the color defect acquisition module is as follows: First step, record each pixel point in the transferred master image and the transferred finished product image as each transferred pixel point, and respectively detect the chromaticity values of each transferred pixel point in the transferred master image and the transferred finished product image on the three color channels of red (R), green (G), and blue (B). Take the difference between the two to obtain the chromaticity value difference of each transferred pixel point in the R, G, and B channels of the transferred finished product image compared with the transferred master image, and compare it with the preset chromaticity value difference threshold respectively to screen out each abnormal chromaticity pixel point, and count the number of each abnormal chromaticity pixel point, denoted as N 异常 , read the total number of pixel points N of the transferred master image 总 , through the formula Obtain the proportion of color spots ο of the transferred finished product image; it can accurately understand the color quality of the transferred finished product, timely discover problems such as color spots, effectively reduce defective products caused by color problems such as color spots, and save costs.

[0056] It should be noted that the specific analysis method for screening out each abnormal chromaticity pixel point is as follows: Read the chromaticity values of each transferred pixel point in the transferred master image and the transferred finished product image on the three color channels of red (R), green (G), and blue (B), and record the chromaticity values of each transferred pixel point in the R channel of the transferred master image and the transferred finished product image as x represents the number of the xth transferred pixel point, x = 1, 2,..., y. Through the formula Obtain the chromaticity value difference of each transferred pixel point in the R channel of the transferred finished product image compared with the transferred master image Denote it as the chromaticity value difference of each transferred pixel point in the R channel. Analyze the chromaticity value differences of each transferred pixel point in the G channel and the B channel in turn according to the method of analyzing the chromaticity value differences of each transferred pixel point in the R channel, and compare them with the set chromaticity value difference threshold respectively. If the chromaticity value difference of a certain transferred pixel point on any channel is greater than the set chromaticity value difference threshold, then determine that this transferred pixel point is an abnormal chromaticity pixel point. If the chromaticity value differences of a certain transferred pixel point on the R, G, and B channels are all less than or equal to the set chromaticity value difference threshold, then determine that the chromaticity value difference of this transferred pixel point is qualified.

[0057] It should be noted that in a specific embodiment, the chromaticity value difference thresholds set for the three color channels of red (R), green (G), and blue (B) are 5, 3, and 4 respectively. For a certain transfer pixel, the chromaticity value difference in the R channel is 6, the chromaticity value difference in the G channel is 2, and the chromaticity value difference in the B channel is 5. Since the chromaticity value differences of this transfer pixel in the R channel and the B channel both exceed their respective chromaticity value difference thresholds, it is determined that this transfer pixel is an abnormal chromaticity pixel.

[0058] Second step, read the chromaticity values of each transfer pixel of the transfer master image The chromaticity values of each transfer pixel of the transferred finished image By separately calculating their averages, the average chromaticity values of the transfer master image and the transferred finished image are obtained Substitute them into the formula The color deviation degree ρ of the transferred finished image is obtained; it can reduce color differences, ensure a high color consistency between the transferred finished product and the master, and maintain the stability and consistency of the color of the transferred product.

[0059] Third step, read the gray values σ of each pixel of each sub-region of the transferred finished image im , through the formula The average gray value of each sub-region of the transferred finished image is obtained q represents the number of pixels, and the average value of the average gray values of each sub-region of the transferred finished image is calculated and denoted as Substitute it into the formula The color uniformity degree λ of the transferred finished image is obtained, n represents the number of sub-regions; it can accurately understand the uniformity degree of the color distribution of the transferred finished image in each region, and helps to timely detect possible local color non-uniformity problems.

[0060] The color defect analysis module is used to analyze and obtain the color evaluation coefficient β of the transferred finished image according to the color defect parameters of the transferred finished image.

[0061] The specific analysis method of the color defect analysis module is: separately read the stain ratio ο, color deviation degree ρ, and color uniformity degree λ of the transferred finished image, and substitute them into the formula The color evaluation coefficient β of the transferred finished image is obtained, respectively represent the weight factors of the set stain ratio, color deviation degree, and color uniformity degree, and e represents the natural constant; by comprehensively considering the performance of the transferred finished image in multiple key color aspects, it helps to maintain the stability and consistency of the product in terms of color.

[0062] It should be noted that in a specific embodiment, can be set to 0.4, can be set to 0.4, It can be set to 0.2. The proportion of color spots is relatively more crucial. If the proportion of color spots is too large, it will have a very significant adverse impact on the overall color performance. The degree of color deviation is also important. It will cause the color to present a state inconsistent with the expectation and have a greater impact on the visual effect. Although the degree of color uniformity is also important, the impact may be relatively smaller compared. However, if the degree of color uniformity is very poor, it will also seriously reduce the quality of the transferred finished product. Therefore, the weights corresponding to the proportion of color spots and the degree of color deviation are relatively high.

[0063] The paper defect detection module is used to detect the paper defect parameters of the thermal sublimation transfer paper. The paper defect parameters include the degree of ink accumulation and the degree of warping.

[0064] The specific analysis method of the paper defect detection module is as follows: First step, place the thermal sublimation transfer paper stably on the detection platform, select detection points according to the set gap, and obtain the flatness of each detection point of the thermal sublimation transfer paper through a flatness measuring instrument, denoted as P f , where f represents the number of the f-th detection point, f = 1, 2,..., g. Calculate the average value of the flatness of each detection point of the thermal sublimation transfer paper, denoted as And read the preset flatness difference threshold from the management database, denoted as ΔP0, and substitute it into the formula to obtain the ink accumulation degree τ of the thermal sublimation transfer paper; ensuring the flatness of the paper helps to achieve a better transfer effect and avoid problems such as uneven ink distribution caused by unevenness. When the flatness of the paper is good, the distribution of ink on the paper surface will be relatively more uniform, and it is not easy to have the situation of excessive or insufficient local accumulation, which helps to achieve a good printing or transfer effect. If the paper is uneven, with raised or sunken areas, during the printing or transfer process, the ink may accumulate more in the raised areas and less in the sunken areas, resulting in uneven ink distribution, affecting the quality and clarity of the pattern or text, and even may have problems such as uneven ink color and ghosting. At the same time, the uneven paper may cause uneven pressure distribution during the printing or transfer process, further affecting the uniformity and stability of ink accumulation.

[0065] Second step, place the thermal sublimation transfer paper on a flat horizontal plane, and measure the distance between each detection point of the thermal sublimation transfer paper and the horizontal plane using a vernier caliper, denoted as d' f , and substitute it into the formula to obtain the warping degree of the thermal sublimation transfer paper where g represents the number of detection points; it can promptly detect whether there is a warping problem with the transfer paper, ensure the product quality, help understand the performance of the transfer paper under different conditions, and reduce the errors in subsequent processing or use caused by warping.

[0066] A paper defect analysis module, which is used to analyze the paper evaluation coefficient γ of the thermal sublimation transfer paper according to the paper defect parameters of the thermal sublimation transfer paper.

[0067] The specific analysis method of the paper defect analysis module is as follows: Read the ink accumulation degree τ and warping degree of the thermal sublimation transfer paper Substitute them into the formula to obtain the paper evaluation coefficient γ of the thermal sublimation transfer paper. η1 and η2 respectively represent the weight factors of the set ink accumulation degree and warping degree, and e represents the natural constant; it can accurately reflect the comprehensive situation of the paper in terms of ink accumulation and warping, rather than the consideration of a single index, which helps to strictly control the paper quality during the production process and timely discover problems.

[0068] It should be noted that in a specific embodiment, η1 can be set to 0.6 and η2 can be set to 0.4. Ink accumulation will directly affect the transfer effect and quality, and may cause problems such as unclear patterns and uneven colors. The influence of the warping degree may be relatively smaller, but if the warping is severe, it will also affect the use and transfer operation to a certain extent. Therefore, the weight corresponding to the ink accumulation degree is higher.

[0069] A transfer finished product comprehensive analysis module, which is used to analyze the defect evaluation index of the thermal sublimation transfer paper according to the pattern evaluation coefficient, color evaluation coefficient of the transfer finished product image, and the paper evaluation coefficient of the thermal sublimation transfer paper, and give feedback on it.

[0070] Please refer to Figure 3 As shown, the specific analysis method of the defect evaluation index of the thermal sublimation transfer paper is as follows: Read the pattern evaluation coefficient α, color evaluation coefficient β of the transfer finished product image, and the paper evaluation coefficient γ of the thermal sublimation transfer paper respectively, and substitute them into the formula to obtain the defect evaluation index of the thermal sublimation transfer paper where w1, w2, and w3 respectively represent the weight factors of the set pattern evaluation coefficient, color evaluation coefficient of the transfer finished product image, and paper evaluation coefficient of the thermal sublimation transfer paper; through the defect evaluation index, possible quality defects can be discovered and located more accurately, ensuring the stable quality of the produced transfer finished products and producing higher-quality transfer finished products.

[0071] It should be noted that in a specific embodiment, w1 can be set to 0.5, w2 can be set to 0.3, and w3 can be set to 0.2. The pattern evaluation coefficient may be relatively important because the integrity and clarity of the pattern directly affect the appearance and quality of the finished product. The color evaluation coefficient is also very crucial, as accurate color is essential for the quality of the finished product. The paper evaluation coefficient of the heat sublimation transfer paper is relatively less important, but still cannot be ignored. Therefore, the weight corresponding to the pattern evaluation coefficient of the transferred finished product image is higher, the weight corresponding to the color evaluation coefficient is the second, and the weight corresponding to the paper evaluation coefficient of the heat sublimation transfer paper is lower.

[0072] The specific analysis method of the transferred finished product comprehensive analysis module is as follows: Read the defect evaluation index of the heat sublimation transfer paper and compare it with the preset defect evaluation index threshold. If the defect evaluation index of the heat sublimation transfer paper is greater than or equal to the preset defect evaluation index threshold, it means that the defect evaluation index of the heat sublimation transfer paper is qualified. If the defect evaluation index of the heat sublimation transfer paper is less than the preset defect evaluation index threshold, it means that the defect evaluation index of the heat sublimation transfer paper is unqualified, and feedback to the system. It can effectively screen out qualified and unqualified products, ensure that the product quality reaches a certain standard, and optimize the production process according to the feedback information, improving the overall production efficiency and quality.

[0073] The management database is used to store the pixel point difference threshold, the transfer master image, and the flatness difference threshold.

[0074] The present invention analyzes the pattern evaluation coefficient of the transferred finished product image based on the pattern defect parameters of the transferred finished product image, analyzes the color evaluation coefficient of the transferred finished product image based on the color defect parameters of the transferred finished product image, analyzes the paper evaluation coefficient of the heat sublimation transfer paper based on the paper defect parameters of the heat sublimation transfer paper, and then comprehensively evaluates to obtain the defect evaluation index of the heat sublimation transfer paper and gives feedback on it, which helps to clarify the specific defect sources and influence degrees in the heat sublimation transfer process, quickly discover and solve problems, reduce unnecessary repetitive work and time waste, and improve production efficiency.

[0075] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be construed as limitations on the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention, and still be covered by the protection scope of the present invention.

Claims

1. An intelligent defect recognition system for heat sublimation transfer paper based on image analysis, characterized in that, The system specifically includes the following modules: An image acquisition module, which is used to obtain an image of the heat sublimation transfer paper, denoted as the transferred finished product image; A pattern defect acquisition module, which is used to detect the pattern defect parameters of the transferred finished product image. The pattern defect parameters include the degree of pattern blurring, the degree of pattern deformation, and the degree of pattern missing printing; A pattern defect analysis module, which is used to analyze and obtain the pattern evaluation coefficient of the transferred finished product image based on the pattern defect parameters of the transferred finished product image ; A color defect acquisition module, which is used to detect the color defect parameters of the transferred finished product image. The color defect parameters include the proportion of color spots, the degree of color deviation, and the degree of color uniformity; A color defect analysis module for analyzing and obtaining a color evaluation coefficient of a transferred finished product image based on color defect parameters of the transferred finished product image ; A paper defect detection module, which is used to detect the paper defect parameters of the heat sublimation transfer paper. The paper defect parameters include the degree of ink accumulation and the degree of warping; A paper defect analysis module, which is used to analyze the paper defect parameters of the thermal sublimation transfer paper to obtain the paper evaluation coefficient of the thermal sublimation transfer paper ; A transferred finished product comprehensive analysis module, which is used to analyze and obtain the defect evaluation index of the heat sublimation transfer paper based on the pattern evaluation coefficient, color evaluation coefficient of the transferred finished product image, and the paper evaluation coefficient of the heat sublimation transfer paper, compare it with the preset defect evaluation index threshold, and give feedback on it; A management database, which is used to store the pixel difference threshold, the transferred master image, and the flatness difference threshold.

2. The intelligent defect recognition system for heat sublimation transfer paper based on image analysis according to claim 1, wherein The image acquisition module is specifically used for: First step, obtain the heat sublimation transfer paper after transfer; Second step, use a high-definition camera to obtain an image of the heat sublimation transfer paper after transfer; Third step, record the obtained heat sublimation transfer paper image as the transferred finished product image.

3. The intelligent defect recognition system for heat sublimation transfer paper based on image analysis according to claim 2, characterized in that, The pattern defect acquisition module is specifically used for: First step, read the transferred finished product image, perform grayscale processing on the transferred finished product image, and divide it into several sub-regions with equal areas, denoted as each sub-region of the transferred finished product image. Detect the grayscale values of each pixel point in each sub-region of the transferred finished product image, and obtain the difference of each pixel point in each sub-region of the transferred finished product image by subtracting the grayscale value of each pixel point in each sub-region of the transferred finished product image from its adjacent pixel points, denoted as , where represents the number of the th sub-region, , represents the number of the th pixel point, . At the same time, read the preset pixel point difference threshold from the management database, denoted as , substitute it into the formula to obtain the pattern blur degree of the transferred finished product image, represents the number of sub-regions, represents the number of pixel points; Step 2: Read the transfer master image from the management database, adjust its size to the same size as the transfer finished product image through size scaling, take several key points on the transfer master image at the set gap, and mark the set key points on the transfer finished product image in sequence. Make the key points correspond one by one, and record them as the key point groups of the transfer image. Overlap the transfer master image with the transfer finished product image, measure the distances of the key point groups of the transfer image respectively, and record them as , indicating the number of the th key point group, , calculate the average value of the distances of the key point groups of the transfer image, and record it as , substitute it into the formula to obtain the pattern deformation degree of the transfer finished product image , indicating the number of key point groups; In the third step, the transfer pattern parts in the transfer master image and the transfer finished product image are respectively extracted through the edge contour extraction technology, denoted as the transfer master pattern edge contour and the transfer finished product pattern edge contour. The transfer master pattern edge contour and the transfer finished product pattern edge contour are overlapped to obtain the number of overlapping pixel points, denoted as , and at the same time, the total number of pixel points in the transfer master image is extracted, denoted as , and substitute it into the formula to obtain the pattern missing degree of the transfer finished product image .

4. The intelligent defect recognition system for heat sublimation transfer paper based on image analysis according to claim 3, characterized in that, The pattern defect analysis module is specifically used for: Read the pattern blurring degree, the pattern deformation degree, and the pattern missing printing degree of the transferred finished product image respectively , the pattern deformation degree , the pattern missing printing degree , substitute them into the formula to obtain the pattern evaluation coefficient of the transferred finished product image , respectively represent the weight factors of the set pattern blurring degree, the pattern deformation degree, and the pattern missing printing degree represents the natural constant 5. The intelligent defect recognition system for heat sublimation transfer paper based on image analysis according to claim 1, characterized in that, The color defect acquisition module is specifically used for: First step, mark each pixel point in the transfer master image and the transfer finished product image as each transfer pixel point, detect the chromaticity values of each transfer pixel point in the transfer master image and the transfer finished product image on the three color channels of red (R), green (G), and blue (B) respectively, subtract the two to obtain the chromaticity value differences of each transfer pixel point in the transfer finished product image and the transfer master image on the R, G, and B channels, and compare them with the preset chromaticity value difference thresholds respectively to screen out each abnormal chromaticity pixel point, count the number of each abnormal chromaticity pixel point, denoted as , read the total number of pixel points of the transfer master image , through the formula obtain the stain proportion of the transfer finished product image ; Step 2: Read the chromaticity values of each transfer pixel of the transfer master image , and the chromaticity values of each transfer pixel of the transfer finished product image . By calculating the average value of each respectively, obtain the average chromaticity values of the transfer master image and the transfer finished product image , substitute them into the formula to obtain the color deviation degree of the transfer finished product image , represents the number of each transfer pixel; Step 3: Read the grayscale values of each pixel point in each sub-region of the transferred finished product image , and obtain the grayscale mean value of each sub-region of the transferred finished product image through the formula , , where represents the number of pixel points, and calculate the average value of the grayscale mean values of each sub-region of the transferred finished product image, denoted as . Substitute it into the formula to obtain the color uniformity degree of the transferred finished product image , where represents the number of sub-regions, represents the number of the -th sub-region, represents the number of the -th pixel point, .

6. The intelligent defect recognition system for heat sublimation transfer paper based on image analysis according to claim 5, wherein The color defect analysis module is specifically used for: Read the proportion of color patches, color deviation degree, and color uniformity degree of the transferred finished image respectively , color deviation degree , color uniformity degree , substitute them into the formula to obtain the color evaluation coefficient of the transferred finished image , respectively represent the weight factors of the set proportion of color patches, color deviation degree, and color uniformity degree, represents the natural constant.

7. An intelligent defect recognition system for thermal sublimation transfer paper based on image analysis according to claim 1, characterized in that, The paper defect detection module is specifically used for: First step, place the thermal sublimation transfer paper steadily on the detection platform, select detection points according to the set gap, and obtain the flatness of each detection point of the thermal sublimation transfer paper through a flatness measuring instrument, denoted as , indicating the number of the th detection point, , calculate the average value of the flatness of each detection point of the thermal sublimation transfer paper, denoted as , and read the preset flatness difference threshold from the management database, denoted as , substitute it into the formula to obtain the ink accumulation degree of the thermal sublimation transfer paper ; Step 2: Place the heat sublimation transfer paper on a flat horizontal surface, and use a vernier caliper to measure the distance between each detection point of the heat sublimation transfer paper and the horizontal surface, denoted as , and substitute it into the formula to obtain the warping degree of the heat sublimation transfer paper , indicating the number of detection points.

8. An intelligent defect recognition system for heat sublimation transfer paper based on image analysis according to claim 7, characterized in that, The paper defect analysis module is specifically used for: Read the ink accumulation degree of the thermal sublimation transfer paper , warping degree , substitute them into the formula to obtain the paper evaluation coefficient of the thermal sublimation transfer paper , respectively represent the weight factors of the set ink accumulation degree and warping degree, represents the natural constant.

9. An intelligent defect recognition system for thermal sublimation transfer paper based on image analysis according to claim 1, characterized in that, The transferred finished product comprehensive analysis module is specifically used for: Read the pattern evaluation coefficient of the transferred finished product image respectively , color evaluation coefficient , paper evaluation coefficient of the heat sublimation transfer paper , substitute them into the formula to obtain the defect evaluation index of the heat sublimation transfer paper , where respectively represent the weight factors of the pattern evaluation coefficient, color evaluation coefficient, and paper evaluation coefficient of the set transferred finished product image 10. An intelligent defect recognition system for thermal sublimation transfer paper based on image analysis according to claim 9, characterized in that, The transferred finished product comprehensive analysis module is specifically used for: Read the defect evaluation index of the heat sublimation transfer paper, compare it with the preset defect evaluation index threshold. If the defect evaluation index of the heat sublimation transfer paper is greater than or equal to the preset defect evaluation index threshold, it means that the defect evaluation index of the heat sublimation transfer paper is qualified. If the defect evaluation index of the heat sublimation transfer paper is less than the preset defect evaluation index threshold, it means that the defect evaluation index of the heat sublimation transfer paper is unqualified, and give feedback to the system.

Images