Automatic pattern registration printing method for textile fabric

Abstract

The application belongs to the technical field of digital printing machines, and particularly discloses a pattern automatic registration printing method for textile fabrics. The method realizes real-time collection through a high-definition industrial scanning camera, and performs image preprocessing, feature recognition, position adjustment and other operations, effectively solves the problem of the current printing precision, can guarantee that no matter how the size of the equipment changes, how the size of the textile fabric to be printed changes, and how the printing parameter mode changes, the image can be adaptively collected, and the quality of the final product is guaranteed. Through calling of RIP software and board card printing software, the deformed image data is called to the RIP software for image RIP processing, PRT printing data is produced, and then the board card printing software is sent through a network port for real-time printing. The method realizes high integration and synchronous parallel operation of a multifunctional virtual assembly line station, and improves the printing precision and efficiency.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of digital printing machines, and in particular, relates to a pattern automatic registration printing method for textile fabrics. BACKGROUND

[0002] With the development of computer technology and inkjet printing technology, digital printing technology has begun to be applied to the textile industry. This technology allows designers to directly transfer patterns from computers to printers and then print them onto fabrics, allowing for quick processing of complex printing.

[0003] Currently, there are two types of textile fabric printing product demands. The first type requires digital printing on jacquard cloth to provide fabrics with three-dimensional color patterns. The second type requires double-sided printing on high-end cloth, with strict alignment of patterns on both sides, such as high-end silk fabrics. Obviously, for the above two printing product demands, the current textile fabric printing process still has the following shortcomings: 1. There is still a certain deficiency in printing accuracy. The current printing technology can cause position deviation of the printed pattern due to factors such as fabric stretching and deformation, affecting the quality of the final product, especially when double-sided printing is performed. The current image capture design still has certain limitations.

[0004] 2. There is still a certain deviation in printing adaptability. The current printing production line is usually composed of multiple independent devices, making it difficult to coordinate between the various links.

[0005] 3. The image processing process is relatively cumbersome. The current design does not optimize image collection, increasing the complexity of subsequent image processing. Additionally, the image processing in the current printing technology usually requires complex algorithms and a large amount of computing resources, resulting in low efficiency. SUMMARY

[0006] In view of this, to solve the problems raised in the background art, a pattern automatic registration printing method for textile fabrics is proposed.

[0007] The purpose of the present application can be achieved by the following technical solutions: The present application provides a pattern automatic registration printing method for textile fabrics, which comprises the following steps: Step 1, AI feature template construction: importing a design drawing to be printed, recording the resolution of the design drawing and setting a coordinate system, and establishing an AI feature template to identify the position information of each target pattern from the AI feature template.

[0008] Step 2, image collection and uploading: using a high-definition industrial scanning camera installed on the back of the corresponding trolley head of a digital printing guide tape machine to perform real-time image collection on the textile fabric entering the printing work area.

[0009] Step 3, image analysis and acquisition adjustment: Analyze the imaging status of the textile fabric image to obtain the imaging score of the image, and determine whether the imaging score reaches the set imaging score. If not, confirm and adjust the light source setting index, return to step 2, until the set imaging score is reached. If so, proceed to the next step.

[0010] Step 4: Image preprocessing: Perform spatial coordinate transformation on the image to make it consistent with the position information and resolution of the design drawing.

[0011] Step 5: Image feature recognition: Use AI feature recognition algorithm on the transformed image to find the AI ​​features and coordinate information of the pattern in the image.

[0012] Step 6: Pattern position adjustment: Based on AI features and coordinate information, combined with the set coordinate system of the printed design drawing, the position of the target pattern outline in the design drawing is adjusted through a position correction algorithm to generate the printed pattern of the current physical textile fabric.

[0013] Step 7: Pattern format processing: Perform RIP processing on the print pattern of the current physical textile fabric to generate PRT format data.

[0014] Step 8: Pattern printing execution: Send the PRT format data to the board printing software through the network port for real-time printing.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) The present invention effectively solves the problem of insufficient current printing accuracy by utilizing a high-definition industrial scanning camera for real-time acquisition and performing multiple operations such as image preprocessing, feature recognition, and position adjustment. It can ensure that no matter how the specifications and dimensions of the equipment change, how the dimensions of the textile fabric to be printed change, and how the printing parameter mode changes, images can be adaptively acquired and the quality of the final product can be guaranteed, breaking the limitations of the current image capture design.

[0016] (2) The present invention establishes an AI feature template and combines a high-definition industrial scanning camera and a printer to achieve the linkage and coordination of multiple devices in the front printing production line, avoiding the cumbersomeness of the current monotonic control, improving the adaptability of current fabric printing, and also ensuring the efficiency and accuracy of current fabric printing.

[0017] (3) This aspect effectively shortens the overall processing time of the fabric printing process by establishing AI feature templates, reduces errors caused by human misjudgment, can adapt to printing scenarios with high repeatability and high detail requirements, and can quickly identify target patterns.

[0018] (4) The application breaks the current image processing process which is relatively cumbersome by analyzing the imaging state of the image of the textile fabric and adjusting the light source, realizes the optimized design during image acquisition, reduces the cumbersome of subsequent image processing, reduces the demand for processing algorithm and computing resources, and thus guarantees the image processing efficiency.

[0019] (5) The application calls the RIP software and the board card printing software, calls the deformed image data to the RIP software for image RIP processing to produce PRT printing data, and then sends the board card printing software through the network port for real-time printing. Real-time image acquisition, real-time image recognition, real-time image correction, real-time image RIP are realized, and image acquisition, recognition, correction, RIP processing and printing are integrated, forming a high-efficiency virtual pipeline, all processes can be run synchronously and in parallel, greatly improving the production efficiency and the accuracy of pattern registration. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used for the embodiment description. Obviously, the drawings in the following description are only some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0021] Figure 1 The method embodiment step flowchart of the application.

[0022] Figure 2 The specific implementation flowchart of step 3 of the application. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only some embodiments of the application, not all embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the application.

[0024] Please refer to Figure 1 The application provides a pattern automatic registration printing method of textile fabric, which comprises the following steps: step 1, AI feature template construction: a design drawing to be printed is imported, the resolution of the design drawing is recorded, a coordinate system is set, an AI feature template is established, and the position information of each target pattern is identified from the AI feature template.

[0025] Step 2, image acquisition and upload: through the digital printing guide machine corresponding to the high-definition industrial scanning camera installed on the back of the trolley head, the real-time image of the textile fabric entering the printing work area is collected.

[0026] Please refer to Figure 2 As shown in step 3, image analysis and acquisition adjustment: the imaging state of the image of the textile fabric is analyzed to obtain an imaging score, and it is determined whether the imaging score meets the set imaging score. If not, confirm the adjustment of the light source setting index, return to step 2, until the set imaging score is reached, if reached, execute the next step.

[0027] Step 4, image preprocessing: spatial coordinate transformation is performed on the image to make it consistent with the position information and resolution of the design drawing.

[0028] Step 5, image feature recognition: AI feature recognition algorithm is used on the transformed image to find the AI features and coordinate information of the pattern in the image.

[0029] Step 6, pattern position adjustment: based on AI features and coordinate information, combined with the setting coordinate system of the printed design drawing, the position of the target pattern contour in the design drawing is adjusted through the position correction algorithm to generate the printed pattern of the current physical textile fabric.

[0030] Step 7, pattern format processing: RIP processing is performed on the printed pattern of the current physical textile fabric to generate PRT format data.

[0031] Step 8, pattern printing execution: send PRT format data to board card printing software through network port for real-time printing.

[0032] Understandably, the supplement to step 1 is that the high-definition industrial line array camera is fixedly installed on the back of the printing trolley head and moves synchronously with the printing trolley head. When the device produces and prints, the trolley head moves back and forth along the X beam, and the camera synchronously scans the image of the textile fabric to be printed along the X direction. The trolley head prints one PASS, and the device guide Y advances a set distance, and the camera synchronously collects the image of the Y advancement height.

[0033] Understandably, regarding the establishment of AI feature template in step 1, it includes: A1, using a high-definition industrial line array camera to scan a selected textile fabric sample to obtain a return map of the textile fabric.

[0034] A2, on the return map, the target pattern area is framed by image editing software, which is called AI feature recognition area.

[0035] It should be noted that the area framed by the image editing software is a common means, and the specific framing details are not repeated.

[0036] It should be added that the region of the target pattern framed can also be framed by a special AI tool, and the size and shape of the feature recognition region should be adjusted according to the characteristics of the target pattern to ensure that the key features of the target pattern can be accurately contained. If there is a repeated flower pattern on the fabric, the key feature points such as the center point of the flower and the edge of the petal need to be defined.

[0037] A3, standardize the position information of each AI feature recognition region on the back position map, including the horizontal coordinate, the vertical coordinate and the rotation angle.

[0038] A4, based on the labeled back position map and the AI feature recognition region, the AI model is preliminarily trained, after the preliminary training, the actual sample is tested, and the model parameters are adjusted according to the test result, and the AI model that passes the test is used as the AI feature template.

[0039] It should be added that the model training and test judgment are the basic consideration points and conventional means for the existing model, and will not be described.

[0040] In one specific embodiment, the test pass can be detected by the consistency of the printed pattern and the target pattern in the design drawing, wherein the consistency detection includes multiple features such as position, image shape, etc., wherein the multiple features such as position, image shape, etc. can be constituted as a feature set, and the calculation result is calculated by Jaccard similarity as the consistency detection result, and a pass threshold is set. For example, when the consistency detection result is greater than 0.98, it can be considered as test pass.

[0041] The embodiment of the application can effectively shorten the overall processing time of the fabric printing process by establishing an AI feature template, reduce errors caused by human judgment errors, and can adapt to high repeatability and high detail requirement printing scenes, and can quickly identify target patterns.

[0042] Understandably, the high-definition industrial scanning camera in step 2 has a plurality of LED linear light sources installed at the lower part, and the LED linear light sources move synchronously with the high-definition industrial scanning camera.

[0043] It should be added that the LED linear light source is also installed at the lower part of the high-definition industrial linear array camera and moves synchronously with the camera, which is used to supplement light for jacquard or printed patterns on the reverse side of the textile fabric to obtain clear and easy-to-identify AI features. When the imaging score does not reach the set imaging score, the LED linear light source can be adjusted.

[0044] The embodiment of the present application establishes an AI feature template, and combines a high-definition industrial scanning camera and a printer, thereby realizing linkage and coordination of multiple devices in a pre-printing production line, avoiding the complexity of current single control, improving the adaptability of current fabric printing, and guaranteeing the efficiency and accuracy of current fabric printing.

[0045] Understandably, the imaging state analysis of the image of the textile fabric in step 3 includes: B1, the image of the textile fabric is segmented by a sliding window to obtain each segmented image block, and each imaging evaluation index of the textile fabric is confirmed.

[0046] B2, each imaging evaluation index of the textile fabric is compared with each reference imaging evaluation index, if an imaging evaluation index is greater than the corresponding reference imaging evaluation index, the imaging evaluation index is marked as a matching index.

[0047] B3, the number of matching indexes and the number of imaging evaluation indexes are counted, and the ratio of the two is marked as an imaging matching ratio.

[0048] B4, if an imaging evaluation index is less than the corresponding reference imaging evaluation index, the imaging evaluation index and the corresponding reference imaging evaluation index are subtracted, the absolute value of the difference is taken as the deviation value of the imaging evaluation index, the imaging evaluation index is marked as a deviation index, a matching correction factor is set, and the imaging matching ratio is corrected to obtain a corrected imaging matching ratio.

[0049] In one specific embodiment, the reference imaging evaluation index includes a reference imaging quality compliance and a reference imaging quality uniformity, and the reference imaging quality compliance can be specifically 0.5, and the reference imaging quality uniformity can be specifically 0.2.

[0050] B5, the product of the corrected imaging matching ratio and the total imaging score set in advance is taken as the imaging score of the image.

[0051] Further, the confirmation of each imaging evaluation index of the textile fabric in B1 includes: B11, each segmented image block is detected by an edge detection algorithm to obtain the image definition of each segmented image block.

[0052] It should be noted that the detection of each segmented image block by the edge detection algorithm is one of the common tasks in image processing. The edge detection algorithm can help identify the boundaries and contours in the image. In one specific embodiment, the edge detection algorithm includes but is not limited to Canny edge detection and Sobel detection, and exemplarily, Canny edge detection can be used as the edge detection algorithm of the present application.

[0053] B12, generate a color histogram of each segmented image block, extract the minimum pixel intensity and the maximum pixel intensity corresponding to the non-zero frequency in the color histogram, and extract the pixel intensity and the total number of pixels of each channel.

[0054] It should be noted that generating a color histogram of each segmented image block can be achieved by using OpenCV and NumPy library, etc.

[0055] B13, calculate the standard deviation of the pixel intensity of each channel to obtain the pixel intensity standard deviation corresponding to each segmented image block.

[0056] B14, make a ratio of the maximum pixel intensity and the minimum pixel intensity to obtain the dynamic range corresponding to each segmented image block, set the weights of the pixel intensity standard deviation and the dynamic range, and obtain the contrast of each segmented image block by weighted summation.

[0057] It should be noted that the pixel intensity standard deviation reflects the change of the pixel gray value within the image block, the larger the standard deviation, the more intense the gray change within the image block, and the higher the contrast, the dynamic range is defined as the ratio of the maximum pixel intensity and the minimum pixel intensity of the image block, which reflects the range of gray value within the image block, the larger the dynamic range, the wider the range of gray change within the image block, and the higher the contrast, the pixel intensity standard deviation reflects the image contrast from the breadth, and is more comprehensive, therefore, the weight of the pixel intensity standard deviation is set to be greater than the weight of the dynamic range, for example, the weight of the pixel intensity standard deviation can be 0.7, and the weight of the dynamic range can be 0.3.

[0058] Understandably, the specific example statistical process of obtaining the contrast of each segmented image block by weighted summation is as follows: the weights of the pixel intensity standard deviation and the dynamic range are denoted as w1 and w2 respectively, and the pixel intensity standard deviation and the dynamic range corresponding to each segmented image block are denoted as σ j and DR j respectively, j represents the number of segmented image blocks, j = 1, 2, …, m.

[0059] The contrast of each segmented image block is denoted as (Co) j , (Co) j = w1*σ j + w2*log2(DR j ).

[0060] It should be explained that log2(DR j ) is used instead of DR j directly participating in the calculation because the value of the dynamic range may be very large, and taking the logarithm can compress it to a more reasonable range, avoiding the influence of too large value on the result.

[0061] B15、by using the gray level co-occurrence matrix to extract the energy value and the entropy value of each segmented image block, the texture coincidence degree of each segmented image block is calculated.

[0062] Wherein, the texture coincidence degree of each segmented image block is calculated, including: R1, comparing the energy value and the entropy value of each segmented image block with the energy value and the entropy value of the image reference respectively, the texture coincidence degree of the image block with the energy value lower than the energy value of the image reference and the entropy value higher than the entropy value of the image reference is recorded as 0.

[0063] R2, if the energy value of a certain segmented image block is higher than or equal to the energy value of the image reference and the entropy value is higher than the entropy value of the image reference, the energy value of the adjacent segmented image and the energy value of the image reference are recorded as ζ and ζ' respectively, and The texture coincidence degree of the image block is recorded as α, and ε is the set energy value coincidence compensation factor.

[0064] Understandably, the higher the energy value, the more uniform the gray level distribution in the image, and the better the consistency. The entropy value reflects the uncertainty of information. Lower entropy value usually indicates more consistent and more regular texture.

[0065] In one specific embodiment, the energy value is in the range of [0, 1], and specifically, 0.7 can be taken as the specific value of ζ'.

[0066] R3, if the energy value of a certain segmented image block is lower than the energy value of the image reference and the entropy value is lower than or equal to the entropy value of the image reference, the entropy value of the adjacent segmented image and the entropy value of the image reference are recorded as and The The texture coincidence degree of the image block is recorded as β, and ε' is the set entropy value coincidence compensation factor.

[0067] In one specific embodiment, the entropy value of the image is usually between 0 and 8, and specifically, 4 can be taken as the specific value of

[0068] ​It should be noted that in texture analysis, energy can be used to represent the uniformity of an image. If the pixel values in a region vary little, the energy value of the region will be relatively high, indicating that the texture of the region is relatively uniform. Conversely, if the pixel values in a region vary greatly, the energy value of the region is relatively low, indicating that the texture of the region is relatively complex, and entropy can be used to measure the complexity and diversity of the texture. High entropy value is usually associated with complex texture, while low entropy value may indicate simple and repetitive texture pattern. Therefore, energy describes the uniformity of the image more, and entropy focuses more on the complexity and diversity of the texture. When printing fabric, more attention is paid to the consistency of the print, therefore, the energy value fitting compensation factor is set to be greater than the entropy value fitting compensation factor, for example, the energy value fitting compensation factor can be 0.6, and the entropy value fitting compensation factor can be 0.4.

[0069] R4, if the energy value of a certain segmented image block is higher than or equal to the energy value of the image reference and the entropy value is lower than or equal to the entropy value of the image reference, as the texture consistency δ of the image block, so as to obtain the texture consistency of each segmented image block, wherein the value of the texture consistency of each segmented image block belongs to one of 0 or β or δ.

[0070] B16, calculate the mean value of the image clarity, image contrast and texture consistency corresponding to each image block respectively, set the weight of clarity, contrast and texture consistency, and obtain the imaging quality compliance degree through linear regression function statistics.

[0071] It should be noted that before the imaging quality compliance degree is obtained through linear regression function statistics, the mean value of the image clarity, image contrast and texture consistency corresponding to each image block is also normalized, specifically, the normalization method of minimum-maximum normalization or Z-score standardization can be used, wherein the minimum-maximum normalization is used as an example for specific process as follows: the mean value of the image clarity corresponding to each image block is denoted as The maximum clarity and minimum clarity are filtered out from the image clarity corresponding to each image block, and are denoted as Sh max and Sh min , as the normalization result of the image clarity.

[0072] It can be understood that the normalization processing of image contrast and texture consistency is the same as that of image clarity, which will not be shown here.

[0073] ​It should be further supplemented that in fabric printing, the weights of the clarity, contrast and texture coincidence need to be considered according to specific application requirements and targets, because the clarity directly determines the subsequent printing quality, therefore, the weight of the clarity is set to be the largest, for example, the weight of the clarity can be 0.5, the contrast determines the boundary and detail display of the pattern, therefore, the weight of the contrast is set to be the second, and the weight of the texture coincidence is set to be the smallest, for example, the weight of the contrast can be set to be 0.3, and the weight of the texture coincidence can be 0.2.

[0074] B17, respectively calculate the standard deviations of the clarity, contrast and texture coincidence of each image segmentation image, and statistically calculate the imaging quality uniformity according to the statistical mode of the imaging quality coincidence, and take the imaging quality coincidence and the imaging quality uniformity as the imaging evaluation indexes of the textile fabric.

[0075] Further, the coincidence correction factor is set in the B4 step, including: B41, the number of deviation indexes is counted, denoted as D0.

[0076] B42, a first reference deviation value and a second reference deviation value are set.

[0077] It should be supplemented that the specific values of the first reference deviation value and the second reference deviation value can be set comprehensively according to historical experience, that is, historical data including actual values and reference values of each imaging evaluation index can be collected, the deviation values of each imaging evaluation index are recorded, and statistical quantities such as the minimum value and the median value of the deviation values are calculated, if the minimum value is 0, a value slightly larger than 0 is taken as the first reference deviation value, such as 0.1, if the minimum value is not 0, the minimum value is taken as the first reference deviation value, and the median value is taken as the second reference deviation value.

[0078] B43, the deviation indexes with the deviation values less than or equal to the first reference deviation value are marked as class I deviation indexes.

[0079] B45, if the deviation value is greater than the first reference deviation value and less than or equal to the second reference deviation value, the deviation index is marked as a class II deviation index.

[0080] B46, the deviation indexes with the deviation values greater than the set second reference deviation value are marked as class III deviation indexes.

[0081] B47, the numbers of the class I deviation indexes, the class II deviation indexes and the class III deviation indexes are counted, and the ratios of the numbers to the number of deviation indexes are calculated, and the ratios are sequentially marked as the class I deviation ratio, the class II deviation ratio and the class III deviation ratio, respectively, denoted as k a , k b and k c .

[0082] B48, set the weights of the type I, type II and type III deviation ratios, respectively denoted as f1, f2 and f3, set the anastomosis correction factor ψ,

[0083] In one specific embodiment, the type I deviation ratio represents the proportion of the deviation indicators with small deviation values, the type II deviation ratio represents the proportion of the deviation indicators with deviation values in the middle echelon, and the type III deviation ratio represents the proportion of the deviation indicators with large deviation values. In terms of deviation degree, the deviation degree of the type III deviation ratio is higher than that of the type II deviation ratio, and the deviation degree of the type II deviation ratio is higher than that of the type I deviation ratio. Therefore, the weight of the type III deviation ratio > the weight of the type II deviation ratio > the weight of the type I deviation ratio. Exemplarily, the weight f3 of the type III deviation ratio can be 0.6, the weight f2 of the type II deviation ratio can be 0.3, and the weight f1 of the type I deviation ratio can be 0.1.

[0084] It should be noted that the corrected imaging anastomosis ratio = imaging anastomosis ratio × (1-anastomosis correction factor).

[0085] Understandably, the adjustment light source setting indicator confirmed in step 3 includes: T1, if the number of deviation indicators is 2 or the number of deviation indicators is 1 and is the imaging quality conformity, the overall adjustment is taken as the adjustment mode, and if the number of deviation indicators is 1 and is the imaging quality uniformity, the local adjustment is taken as the adjustment mode.

[0086] T2, when the adjustment mode is overall adjustment, the current setting light source intensity and the highest light source intensity of the LED linear light source corresponding to the high-definition industrial scanning camera are extracted, denoted as I0 and I max , set the overall light source adjustment factor I0+I as the adjusted light source intensity, and as the adjusted light source setting indicator.

[0087] Among them, the setting of the overall light source adjustment factor includes: if the number of deviation indicators is 2, the deviation compensation factor is denoted as φ0, and if the number of deviation indicators is 1, the deviation compensation factor is denoted as φ1, so as to obtain the deviation compensation factor η, η takes the value of φ0 or φ1, and φ0> φ1.

[0088] The imaging quality conformity and the imaging quality uniformity are denoted as FH and JY respectively, and the overall light source adjustment factor FH' and JY' are the set reference imaging quality conformity and reference imaging quality uniformity respectively.

[0089] T3, when the adjustment mode is local adjustment, the adjusted light source setting indicator of local adjustment is confirmed.

[0090] Among them, confirming the adjustment light source setting indicators for local adjustment includes: T31, extracting the setting irradiation area positions of each LED linear light source corresponding to the high-definition industrial scanning camera, and using each image block located at the setting irradiation area position corresponding to the LED linear light source as each associated image block of the corresponding LED linear light source.

[0091] T32. Calculate the imaging quality conformity of each LED linear light source corresponding to each associated image block, and record the LED linear light source of the associated image block with an imaging quality conformity less than the reference imaging quality conformity as an adjusted light source.

[0092] T33. Set the overall light source adjustment factor Then, the adjusted light source intensity of the adjusted light source is determined in the same way as the confirmation method of the adjusted light source setting index during overall adjustment, and is used as the adjusted light source setting index for local adjustment, where e is a natural constant.

[0093] It should be added that the imaging quality conformity of each associated image block is calculated in a similar way to FH. The imaging clarity and other indicators of each associated image block are imported into the calculation framework corresponding to FH to obtain the imaging quality conformity of each associated image block.

[0094] The embodiments of the present invention break the shortcomings of the current cumbersome image processing process by analyzing the imaging status of the image of the textile fabric and adjusting the light source, realize the optimized design during image acquisition, reduce the cumbersomeness of subsequent image processing, and reduce the demand for processing algorithms and computing resources, thereby ensuring image processing efficiency.

[0095] Understandably, what needs to be added about step 4 is that after the high-definition industrial linear array camera captures the return image, the image can be transformed into spatial coordinates through a pre-calibration algorithm to eliminate lens distortion and convert the image into a standard coordinate system so that the image is consistent with the coordinate system and resolution of the design drawing. The pre-calibration parameter algorithm refers to the camera calibration parameter algorithm, and the specific conversion example process for the spatial coordinate transformation of the image is as follows: 1) Extract the internal parameters of the high-definition industrial linear array camera, such as focal length, principal point offset, lens distortion coefficient, etc., and at the same time extract the external parameters of the high-definition industrial linear array camera, such as the position and direction of the camera relative to the world coordinate system, and correct it through the distortion correction formula. After the distortion correction is completed, the image needs to be converted from the camera coordinate system to the coordinate system of the design drawing.

[0096] 2) Obtain the internal and external parameters of the camera through the calibration algorithm, and use the internal and external parameters of the camera to dedistort the image.

[0097] In one embodiment, the calibration algorithm can be specifically as the cv2.calibrateCamera function in OpenCV, and the image is deformed using the camera internal and external parameters.

[0098] 3) Using the known rotation matrix and translation vector, the deformed image is converted from the camera coordinate system to the coordinate system of the design drawing, and the spatial coordinate transformation is completed.

[0099] In one embodiment, the conversion of the deformed image from the camera coordinate system to the coordinate system of the design drawing can be realized by affine transformation or perspective transformation.

[0100] The embodiment of the application effectively solves the problems of current printing precision by using high-definition industrial scanning cameras for real-time acquisition, and performing image preprocessing, feature recognition, position adjustment and other operations, which can ensure that the image can be adaptively acquired regardless of the size of the equipment, the size of the printed textile fabric, and the printing parameter mode, and the quality of the final product is guaranteed, breaking the limitations of current image capture design.

[0101] Understandably, the AI feature recognition algorithm in step 5 performs feature recognition, which is a relatively mature technology, and its specific recognition process is not described.

[0102] Understandably, the position correction algorithm in step 6 can use the IDW interpolation algorithm formula in one embodiment to realize image correction calculation.

[0103] In another embodiment, in order to cope with the large amount of calculation demand in high-speed production mode, GPU is used for image processing, which is much more efficient than ordinary CPU, ensuring that real-time processing can be realized even at a speed of 80 meters per hour.

[0104] The embodiment of the application calls the RIP software and the board card printing software, calls the deformed image data to the RIP software for image RIP processing to produce PRT printing data, and then sends the board card printing software through the network port for real-time printing. Real-time image acquisition, real-time image recognition, real-time image correction, real-time image RIP are realized, and image acquisition, recognition, correction, RIP processing and printing are integrated, forming a high-efficiency virtual pipeline, all processes can be synchronized and run in parallel, greatly improving the production efficiency and the accuracy of pattern registration.

[0105] The above merely illustrates and describes the concept of the present application, and those skilled in the art can make various modifications or supplements to the described specific embodiments or adopt similar ways to replace, as long as the modifications or supplements do not deviate from the concept of the present application or exceed the defined scope of the present application, and should belong to the protection scope of the present application.

Claims

1. A method for automatically overprinting a pattern on a textile fabric, characterized in that: include: Step 1: AI feature template construction: used to import the design drawing to be printed, record the resolution of the design drawing and set the coordinate system, and establish the AI ​​feature template to identify the position information of each target pattern from the AI ​​feature template; Step 2: Image acquisition and upload: The high-definition industrial scanning camera installed on the back of the corresponding carriage of the digital printing guide machine is used to capture real-time images of textile fabrics entering the printing work area; Step 3, image analysis and acquisition adjustment: perform imaging status analysis on the image of the textile fabric to obtain the imaging score of the image, and determine whether the imaging score reaches the set imaging score. If not, confirm and adjust the light source setting index, return to step 2, and continue until the set imaging score is reached. If so, proceed to the next step. Step 4: Image preprocessing: Perform spatial coordinate transformation on the image to make it consistent with the position information and resolution of the design drawing; Step 5: Image feature recognition: Use AI feature recognition algorithm on the transformed image to find the AI ​​features and coordinate information of the pattern in the image; Step 6: Pattern Position Adjustment: Based on AI features and coordinate information, combined with the set coordinate system of the printed design drawing, the position of the target pattern outline in the design drawing is adjusted through a position correction algorithm to generate the printed pattern of the current physical textile fabric; Step 7: Pattern format processing: Perform RIP processing on the printed pattern of the current physical textile fabric to generate PRT format data; Step 8: Pattern printing execution: Send the PRT format data to the board printing software through the network port for real-time printing.

2. The method for automatically overprinting a pattern on a textile fabric according to claim 1, wherein: The step of establishing an AI feature template includes: Use a high-definition industrial linear array camera to scan the selected textile fabric samples to obtain the textile fabric back-image; On the return image, use image editing software to select the area of ​​the target pattern and record it as the AI ​​feature recognition area; Mark the position information of each AI feature recognition area on the return map, including the horizontal coordinate, vertical coordinate and rotation angle; Based on the marked return position map and AI feature recognition area, the AI ​​model is preliminarily trained. After completing the preliminary training, it is tested with actual samples, and the model parameters are adjusted according to the test results. The AI ​​model that passes the test is used as the AI ​​feature template.

3. The method for automatically overprinting a pattern on a textile fabric according to claim 1, wherein: A plurality of LED linear light sources are installed at the lower part of the high-definition industrial scanning camera, and the LED linear light sources move synchronously with the high-definition industrial scanning camera.

4. The method for automatically overprinting a pattern on a textile fabric according to claim 1, wherein: The imaging state analysis of the textile fabric image includes: The image of the textile fabric is segmented by a sliding window to obtain segmented image blocks, and various imaging evaluation indicators of the textile fabric are determined; Compare each imaging evaluation index of the textile fabric with each set reference imaging evaluation index one by one. If a certain imaging evaluation index is greater than the corresponding reference imaging evaluation index, mark the imaging evaluation index as a matching index; The number of coincidence indices and the number of imaging evaluation indices were counted, and the ratio of the two was recorded as the imaging coincidence ratio; If a certain imaging evaluation index is less than the corresponding reference imaging evaluation index, the imaging evaluation index is subtracted from the corresponding reference imaging evaluation index, and the absolute value of the difference is taken as the deviation value of the imaging evaluation index. The imaging evaluation index is marked as the deviation index, and the matching correction factor is set. The imaging matching ratio is corrected to obtain the corrected imaging matching ratio; The product of the corrected imaging coincidence ratio and the preset total imaging score is taken as the imaging score of the image.

5. The method for automatically overprinting a pattern on a textile fabric according to claim 4, wherein: The imaging evaluation indicators for confirming the textile fabric include: Each segmented image block is detected by an edge detection algorithm to obtain the image clarity of each segmented image block; Generate a color histogram for each segmented image block, extract the minimum pixel intensity and the maximum pixel intensity corresponding to the non-zero frequency in the color histogram, and extract the pixel intensity and the total number of pixels of each channel; Calculate the standard deviation of the pixel intensity of each channel to obtain the standard deviation of the pixel intensity corresponding to each segmented image block; Comparing the maximum pixel intensity with the minimum pixel intensity to obtain the dynamic range corresponding to each segmented image block, setting weights for the pixel intensity standard deviation and the dynamic range, and obtaining the contrast of each segmented image block by weighted summation; The energy value and entropy value of each segmented image block are extracted by using the gray level co-occurrence matrix, and the texture consistency of each segmented image block is calculated; Calculate the mean of image clarity, image contrast and texture consistency for each image block, set the weights of clarity, contrast and texture consistency, and obtain the imaging quality consistency through linear regression function statistics; The standard deviation of image clarity, image contrast and texture consistency corresponding to each image segmentation block is calculated respectively. The imaging quality uniformity is statistically analyzed in the same way as the imaging quality conformity. The imaging quality conformity and imaging quality uniformity are used as the imaging evaluation indicators of textile fabrics.

6. The method for automatically overprinting a pattern on a textile fabric according to claim 5, wherein: The calculating of the texture consistency of each segmented image block includes: The energy value and entropy value of each segmented image block are compared with the energy value and entropy value of the image reference respectively, and the texture consistency of the image block with an energy value lower than the energy value of the image reference and an entropy value higher than the entropy value of the image reference is recorded as 0; If the energy value of a segmented image block is higher than or equal to the energy value of the image reference and the entropy value is higher than the entropy value of the image reference, the energy value of the adjacent segmented image and the energy value of the image reference are denoted as ζ and ζ′ respectively. As the texture matching degree of the image block, it is recorded as α, and ε is the set energy value matching compensation factor; If the energy value of a segmented image block is lower than the energy value of the image reference and the entropy value is lower than or equal to the entropy value of the image reference, the entropy value of the adjacent segmented image and the entropy value of the image reference are recorded as and Will As the texture matching degree of the image block, it is recorded as β, and ε′ is the set entropy matching compensation factor; If the energy value of a segmented image block is higher than or equal to the energy value of the image reference and the entropy value is lower than or equal to the entropy value of the image reference, As the texture consistency δ of the image block, the texture consistency of each segmented image block is obtained.

7. The method for automatically overprinting a pattern on a textile fabric according to claim 4, wherein: The setting of the matching correction factor includes: The number of statistical deviation indicators is denoted as D0; Setting a first reference deviation value and a second reference deviation value; The deviation index with a deviation value less than or equal to the first reference deviation value is marked as a Class I deviation index; If the deviation value is greater than the first reference deviation value and less than or equal to the second reference deviation value, the deviation index is marked as a Class II deviation index; The deviation index with a deviation value greater than the set second reference deviation value is marked as a Class III deviation index; The number of type I deviation index, type II deviation index, and type III deviation index is counted and compared with the number of deviation indexes respectively. The ratios are recorded as type I deviation ratio, type II deviation ratio, and type III deviation ratio, respectively, and are recorded as k a 、k b and k c ; Set the weights of the deviation ratios of Class I, Class II, and Class III, denoted as f1, f2, and f3 respectively, and set the coincidence correction factor ψ.

8. The method for automatically overprinting a pattern on a textile fabric according to claim 7, wherein: The step of confirming and adjusting the light source setting index includes: If the number of deviation indicators is 2 or the number of deviation indicators is 1 and it is imaging quality compliance, the overall adjustment is used as the adjustment method; if the number of deviation indicators is 1 and it is imaging quality uniformity, the local adjustment is used as the adjustment method; When the adjustment mode is overall adjustment, extract the current set light source intensity and the maximum light source intensity of the LED linear light source corresponding to the high-definition industrial scanning camera, which are recorded as I0 and I max , set the overall light source adjustment factor Will As an indicator for adjusting light source intensity and light source settings; When the adjustment mode is local adjustment, confirm the adjustment light source setting indicators of the local adjustment.

9. The method for automatically overprinting a pattern on a textile fabric according to claim 8, wherein: The setting of the overall light source adjustment factor includes: If the number of deviation indicators is 2, the deviation compensation factor is recorded as φ0. If the number of deviation indicators is 1, the deviation compensation factor is recorded as φ1. In this way, the deviation compensation factor η is obtained. The value of η is φ0 or φ1, φ0>φ1; The imaging quality conformity and imaging quality uniformity are recorded as FH and JY respectively, and the overall light source adjustment factor is set. FH′ and JY′ are the set reference imaging quality conformance and reference imaging quality uniformity, respectively, and e is a natural constant.

10. The method for automatically overprinting a pattern on a textile fabric according to claim 9, wherein: The adjustment light source setting index for confirming the local adjustment includes: Extract the set illumination area position of each LED linear light source carried by the high-definition industrial scanning camera, and use each image block located at the corresponding illumination area position of the LED linear light source as each associated image block of the corresponding LED linear light source; Calculate the imaging quality conformity of each LED linear light source corresponding to each associated image block, and record the LED linear light source of the associated image block with an imaging quality conformity less than the reference imaging quality conformity as an adjusted light source; Set the overall light source adjustment factor Then, the adjusted light source intensity of the adjusted light source is confirmed in the same way as the confirmation method of the adjusted light source setting index during the overall adjustment, and is used as the adjusted light source setting index for the local adjustment.

Images