DTG printing method and system based on line scanning camera visual deformation and rigid body positioning

Abstract

The invention discloses a DTG printing method and system based on line scanning camera visual deformation and rigid body positioning, and relates to the technical field of digital textile printing. Dynamic images are collected in real time through a line scanning camera, and image coordinates are mapped to a printing equipment world coordinate system through a coordinate calibration module in combination with a calibration matrix; real-time error compensation is used for dynamically eliminating coordinate offset, and a dual-mode positioning module intelligently switches a positioning strategy; rigid body positioning realizes accurate positioning of non-deformation materials through template matching; deformation positioning performs adaptive compensation based on feature point extraction and grid deformation analysis, an image mapping module inversely corrects target pattern deformation according to a positioning result to generate a high-precision TIF image, the high-precision TIF image is converted into a printing instruction through an RIP processing module, and an integrated control module performs one-key triggering and dynamic parameter configuration and performs printing on a target pattern. The collection efficiency is optimized through light source synchronization and self-adaptive triggering, the system stability is improved in combination with a template database and an exception handling module, and high-quality printing of complex deformation materials is achieved.

Description

Technical Field

[0001] The present invention relates to the field of digital textile printing technology, and more particularly to a DTG printing method and system based on line scan camera visual deformation and rigid body positioning. Background Art

[0002] In the field of DTG printing, the current mainstream visual positioning technology has obvious limitations. On the one hand, the operating procedures of existing DTG visual positioning tools are cumbersome and require operators to control multiple software programs at the same time. For example, when positioning a material, it is necessary to first use one software for image acquisition, then use another software for coordinate conversion and positioning calculation, and finally import the results into the printing software. This not only increases the number of operating steps and reduces production efficiency, but also requires a high level of skill for the operators. Workers need to be familiar with the operating procedures and parameter settings of multiple software programs and undergo a long period of training to master them proficiently. On the other hand, most DTG positioning technologies on the market are mainly used for the production of rigid materials with fixed shapes. When encountering materials that are prone to local deformation, such as embroidery and cloth, problems will become prominent. These materials are prone to local deformation such as wrinkles and stretching during the placement, movement or printing process. Existing printers are unable to make corresponding deformation adjustments to the printed pattern based on the local deformation of the material, resulting in the printed pattern being unable to accurately match the position of the deformed material, thereby affecting the print quality and making it difficult to meet the market demand for personalized, high-precision pattern printing.

[0003] Existing DTG visual positioning requires multiple software operations and complicated steps; it can only process rigid materials and cannot accurately position embroidery / cloth when local deformation occurs. Summary of the Invention

[0004] In order to overcome the above problems existing in the prior art, the present invention discloses a DTG printing method and system based on line scan camera visual deformation and rigid body positioning, which can effectively solve the above technical problems.

[0005] In order to solve the above technical problems, the technical solutions of the present invention are as follows:

[0006] A DTG printing system based on line scan camera visual deformation and rigid body positioning, comprising:

[0007] Line scan camera module, used to receive trigger signals from outside the machine and continuously collect image data of dynamic printing materials;

[0008] A coordinate calibration module, configured to map the image coordinate system of the image data to the world coordinate system of the printing device and compensate for platform movement errors through dynamic calibration;

[0009] A dual-mode positioning module, comprising a rigid body positioning unit and a deformation positioning unit. The rigid body positioning unit achieves rigid positioning of non-deformed materials through template matching, while the deformation positioning unit performs adaptive compensation positioning of locally deformed materials based on feature point extraction and grid deformation analysis.

[0010] The image mapping module is used to reversely deform the target pattern according to the positioning results and map it to the printing canvas to generate a high-precision TIF image;

[0011] A RIP processing module, configured to rasterize the TIF image into RIP instructions recognizable by a printer;

[0012] An integrated control module is used to trigger image acquisition, positioning processing, and printing processes with one click, and dynamically configure printing parameters. The system achieves high-precision printing of deformable materials such as fabrics and embroidery through the dynamic trigger synchronization of the line scan camera, dual-mode positioning switching, and deformation compensation algorithms.

[0013] Preferably, the coordinate calibration module includes:

[0014] A calibration matrix generation unit collects multiple sets of images and physical coordinate data based on a preset calibration plate and calculates the conversion matrix between pixel size and actual physical size;

[0015] The real-time error compensation unit dynamically adjusts the conversion matrix to eliminate coordinate offsets caused by mechanical vibration or material deformation by receiving differential motion signals from the platform.

[0016] Preferably, the deformation positioning unit includes:

[0017] The multi-scale feature extraction subunit uses Gaussian pyramid downsampling to construct multi-resolution images and extracts cross-scale stable feature points through the SIFT algorithm;

[0018] The deformation field modeling subunit uses the RANSAC algorithm to screen geometrically consistent matching points based on the extracted feature point pairs, and constructs the global deformation field through thin plate spline interpolation;

[0019] The reverse mapping subunit performs pre-distortion processing on the target pattern according to the deformation field, so that the printed pattern adapts to the deformed material surface.

[0020] Preferably, the integrated control module further includes:

[0021] Adaptive trigger unit generates the trigger frequency of the line scan camera according to the platform movement speed, ensuring dynamic acquisition of images without motion blur;

[0022] The light source synchronization unit adjusts the brightness and pulse frequency of the strip light source to synchronize it with the camera exposure time and platform movement to eliminate reflection interference.

[0023] Preferably, it further comprises:

[0024] The template database module stores the reference templates and historical positioning parameters of different materials. When a material is detected to match the historical template, the calibration step is automatically skipped.

[0025] The exception handling module identifies missing or occluded areas in the image and triggers local re-sampling or repair based on deformation prediction of adjacent feature points.

[0026] Preferably, a DTG printing method based on line scan camera visual deformation and rigid body positioning includes the following steps:

[0027] Install the line scan camera and light source, fix the camera vertically above the printing platen, and establish an external trigger signal connection with the printing device;

[0028] Generate the conversion matrix from image coordinates to printing device coordinates through the calibration module, and dynamically calibrate the platform movement error;

[0029] Trigger the line scan camera to capture material images and select rigid body positioning or deformation positioning mode according to the material deformation state;

[0030] If the rigid body positioning mode is selected, the material position information is obtained through template matching; if the deformation positioning mode is selected, the feature points are extracted and the local deformation compensation parameters are calculated;

[0031] Map the target pattern to the printing canvas based on the positioning result, generate a TIF image and convert it into printing instructions through RIP processing;

[0032] According to the printing parameter configuration and RIP image control printing equipment to perform multi-color ink jetting, complete the pattern printing of adaptive material deformation.

[0033] Preferably, the method for determining the deformation state of the material includes:

[0034] By calculating the Hausdorff distance between the edge contour of the material and the reference template, if the distance exceeds the threshold, it is judged as a deformed material; or analyzing the frequency domain energy distribution of the material surface texture, if the proportion of high-frequency components exceeds the preset value, it is determined that local wrinkles or stretching exist.

[0035] Preferably, the deformation positioning mode specifically includes:

[0036] Perform multi-scale downsampling on the material image and construct a Gaussian pyramid feature space;

[0037] FAST corner detection is used to extract candidate feature points at each scale layer, and the ORB descriptor is used to generate rotation-invariant feature vectors.

[0038] Use PROSAC algorithm to eliminate mismatched point pairs and retain the feature point set that meets the geometric constraints;

[0039] The global deformation field is calculated based on the TPS algorithm to generate the inverse deformation mapping function of the target pattern.

[0040] Preferably, the mapping process includes:

[0041] Based on the light transmittance characteristics of ink, a white base ink layer is superimposed on the dark area to enhance the color rendering;

[0042] Convert RGB values ​​into CMYK ink ratios based on the color gamut mapping table, and optimize inkjet timing according to the physical characteristics of the nozzle to reduce feathering.

[0043] A computer-readable storage medium stores a computer program, which implements the above-mentioned DTG printing method when executed by a processor.

[0044] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention discloses a DTG printing method and system based on line scan camera visual deformation and rigid body positioning, which solves the problems of complex operation and difficult positioning of deformed materials in the prior art, realizes one-key triggering of image acquisition, positioning processing and printing process through an integrated control module, and dynamically configures printing parameters, simplifies the operation process, and reduces the requirements for workers' skills; the dual-mode positioning module can automatically switch the positioning mode according to the deformation state of the material. For non-deformed materials, the rigid body positioning unit quickly determines the position through template matching; in the face of locally deformed materials, the deformation positioning unit performs adaptive compensation positioning through feature point extraction and grid deformation analysis, and the multi-scale feature extraction subunit of the deformation positioning unit uses Gaussian pyramid downsampling to construct multi-resolution images. Stable feature points are extracted across scales through the SIFT algorithm to ensure that the feature points have good stability and repeatability at different scales. The deformation field modeling subunit uses the RANSAC algorithm based on the extracted feature point pairs to screen out geometrically consistent matching points, and then uses thin plate spline interpolation to construct a global deformation field to accurately describe the deformation of the material; based on the constructed deformation field, the inverse mapping subunit pre-distorts the target pattern so that the printed pattern can perfectly adapt to the deformed material surface, thereby achieving high-precision printing; the present invention successfully achieves high-precision printing of deformed materials such as fabrics and embroidery through the collaborative work of dynamic trigger synchronization, dual-mode positioning switching and deformation compensation algorithm of the line scan camera, effectively overcoming the defects of the existing technology and improving printing quality and production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the implementation methods or the description of the prior art. Obviously, the drawings described below are merely exemplary. For ordinary technicians in this field, other implementation drawings can be derived based on the provided drawings without any creative work.

[0046] Figure 1 This is a system structure diagram of the present invention;

[0047] Figure 2 This is a schematic diagram of the hardware connection of the present invention;

[0048] Figure 3 This is a schematic diagram of the automatic printing process of the present invention;

[0049] Figure 4 This is a step diagram of the method of the present invention. DETAILED DESCRIPTION

[0050] The accompanying drawings are for illustrative purposes only and are not to be construed as limiting this patent;

[0051] In order to better illustrate this embodiment, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual product size;

[0052] It is understandable to those skilled in the art that some well-known structures and descriptions thereof may be omitted in the drawings.

[0053] The technical solution of the present invention is further described below with reference to the accompanying drawings and embodiments.

[0054] Example 1

[0055] A DTG printing system based on line scan camera visual deformation and rigid body positioning, comprising:

[0056] Line scan camera module, used to receive trigger signals from outside the machine and continuously collect image data of dynamic printing materials;

[0057] A coordinate calibration module, configured to map the image coordinate system of the image data to the world coordinate system of the printing device and compensate for platform movement errors through dynamic calibration;

[0058] A dual-mode positioning module, comprising a rigid body positioning unit and a deformation positioning unit. The rigid body positioning unit achieves rigid positioning of non-deformed materials through template matching, while the deformation positioning unit performs adaptive compensation positioning of locally deformed materials based on feature point extraction and grid deformation analysis.

[0059] The image mapping module is used to reversely deform the target pattern according to the positioning results and map it to the printing canvas to generate a high-precision TIF image;

[0060] A RIP processing module, configured to rasterize the TIF image into RIP instructions recognizable by a printer;

[0061] An integrated control module is used to trigger image acquisition, positioning processing, and printing processes with one click, and dynamically configure printing parameters. The system achieves high-precision printing of deformable materials such as fabrics and embroidery through the dynamic trigger synchronization of the line scan camera, dual-mode positioning switching, and deformation compensation algorithms.

[0062] The coordinate calibration module includes:

[0063] A calibration matrix generation unit collects multiple sets of images and physical coordinate data based on a preset calibration plate and calculates the conversion matrix between pixel size and actual physical size;

[0064] The real-time error compensation unit dynamically adjusts the conversion matrix to eliminate coordinate offsets caused by mechanical vibration or material deformation by receiving differential motion signals from the platform.

[0065] The deformation positioning unit includes:

[0066] The multi-scale feature extraction subunit uses Gaussian pyramid downsampling to construct multi-resolution images and extracts cross-scale stable feature points through the SIFT algorithm;

[0067] The deformation field modeling subunit uses the RANSAC algorithm to screen geometrically consistent matching points based on the extracted feature point pairs, and constructs the global deformation field through thin plate spline interpolation;

[0068] The reverse mapping subunit performs pre-distortion processing on the target pattern according to the deformation field, so that the printed pattern adapts to the deformed material surface.

[0069] The integrated control module further includes:

[0070] Adaptive trigger unit generates the trigger frequency of the line scan camera according to the platform movement speed, ensuring dynamic acquisition of images without motion blur;

[0071] The light source synchronization unit adjusts the brightness and pulse frequency of the strip light source to synchronize it with the camera exposure time and platform movement to eliminate reflection interference.

[0072] Further including:

[0073] The template database module stores the reference templates and historical positioning parameters of different materials. When a material is detected to match the historical template, the calibration step is automatically skipped.

[0074] The exception handling module identifies missing or occluded areas in the image and triggers local re-sampling or repair based on deformation prediction of adjacent feature points.

[0075] See also Figure 1-3 Taking DTG printing of clothing fabrics as an example, the line scan camera module vertically fixes the line scan camera 60 cm above the printing platen, the lens is connected to the camera, and the strip light source is installed 50 cm below the camera in the vertical direction and aligned with the platen. The line scan camera is fixed on the machine using sheet metal parts to ensure that the camera is installed perpendicular to the printing platen. It can receive external trigger signals from the machine and continuously collect image data of dynamic printing materials, such as moving clothing fabrics, to provide an image basis for positioning and printing.

[0076] The calibration matrix generation unit of the coordinate calibration module collects multiple sets of images and physical coordinate data based on a preset calibration plate, and calculates the conversion matrix between pixel size and actual physical size. For example, a calibration plate of known size is placed on the printing platen, and the line scan camera collects the calibration plate image. By calculating the pixel coordinates and actual physical coordinates of specific points on the calibration plate, the conversion matrix is ​​obtained to realize the mapping of the image coordinate system to the world coordinate system of the printing device. The real-time error compensation unit dynamically adjusts the conversion matrix by receiving the differential motion signal of the platform. When the platform moves due to mechanical vibration or material deformation causing coordinate offset, the differential motion signal can reflect this deviation. The real-time error compensation unit corrects the conversion matrix in real time based on this, compensates for the platform movement error, and ensures the accuracy of the coordinate mapping.

[0077] For rigid clothing fabrics without deformation, such as hard decorative panels, the dual-mode positioning module uses a rigid positioning unit to achieve rigid positioning through template matching. The corresponding template is pre-set. When the collected material image successfully matches the template, the position of the material on the printing platen can be determined. For clothing fabrics with local deformation, such as soft knitted fabrics, the deformation positioning unit starts working. Its multi-scale feature extraction subunit uses Gaussian pyramid downsampling to construct a multi-resolution image and extracts cross-scale stable feature points through the SIFT algorithm. These feature points can remain stable at different scales and have certain robustness to changes in lighting, viewing angle, etc. The deformation field modeling subunit uses the RANSAC algorithm based on the extracted feature point pairs to screen out geometrically consistent matching points, remove mismatched points, and then construct a global deformation field through thin plate spline interpolation to describe the deformation of the material. The inverse mapping subunit pre-distorts the target pattern according to the deformation field, so that the printed pattern can adapt to the deformed material surface and achieve adaptive compensation positioning.

[0078] After completing positioning, the image mapping module reversely deforms the target pattern based on the positioning results. For example, if a logo is to be printed on a wrinkled clothing fabric, the image mapping module will perform corresponding reverse deformation processing on the logo pattern based on the deformation calculated by the deformation positioning unit, so that the printed logo can accurately fit on the wrinkled fabric, and then map it to the printing canvas to generate a high-precision TIF image.

[0079] The RIP processing module obtains the TIF image generated by the image mapping module and rasterizes it into RIP instructions that the printer can recognize. This process decomposes the image into individual pixels and converts them into instructions that the printer can execute based on the printer's inkjet characteristics, so that the printer can print correctly.

[0080] The integrated control module has a one-touch trigger function. The operator can simultaneously start the image acquisition, positioning processing and printing processes by clicking a button. It can also dynamically configure printing parameters. For example, according to the different materials and thicknesses of clothing fabrics, it can automatically adjust parameters such as printing speed and ink usage to achieve the best printing effect.

[0081] The template database module stores the reference templates and historical positioning parameters of different clothing fabrics. When a new clothing fabric is placed on the printing platen, the system will first compare it with the template in the template database. If it is detected that the material matches the historical template, the calibration step will be automatically skipped and the historical positioning parameters will be directly called for printing, thereby improving work efficiency.

[0082] During the image acquisition and processing process, if the exception handling module identifies missing or blocked areas in the image, it will trigger local re-capturing. For example, when an object accidentally blocks part of the clothing fabric, resulting in incomplete image acquisition, the exception handling module will control the line scan camera to re-capture the missing or blocked areas. If re-capture is not possible, it will be repaired based on the deformation prediction of adjacent feature points. The surrounding feature point information and deformation rules are used to predict the deformation of the missing or blocked areas, thereby repairing the image and ensuring the integrity of the print.

[0083] Example 2

[0084] A DTG printing method based on line scan camera visual deformation and rigid body positioning includes the following steps:

[0085] Install the line scan camera and light source, fix the camera vertically above the printing platen, and establish an external trigger signal connection with the printing device;

[0086] Generate the conversion matrix from image coordinates to printing device coordinates through the calibration module, and dynamically calibrate the platform movement error;

[0087] Trigger the line scan camera to capture material images and select rigid body positioning or deformation positioning mode according to the material deformation state;

[0088] If the rigid body positioning mode is selected, the material position information is obtained through template matching; if the deformation positioning mode is selected, the feature points are extracted and the local deformation compensation parameters are calculated;

[0089] Map the target pattern to the printing canvas based on the positioning result, generate a TIF image and convert it into printing instructions through RIP processing;

[0090] According to the printing parameter configuration and RIP image control printing equipment to perform multi-color ink jetting, complete the pattern printing of adaptive material deformation.

[0091] The method for determining the deformation state of the material includes:

[0092] By calculating the Hausdorff distance between the edge contour of the material and the reference template, if the distance exceeds the threshold, it is judged as a deformed material; or analyzing the frequency domain energy distribution of the material surface texture, if the proportion of high-frequency components exceeds the preset value, it is determined that local wrinkles or stretching exist.

[0093] The deformation positioning mode specifically includes:

[0094] Perform multi-scale downsampling on the material image and construct a Gaussian pyramid feature space;

[0095] FAST corner detection is used to extract candidate feature points at each scale layer, and the ORB descriptor is used to generate rotation-invariant feature vectors.

[0096] Use PROSAC algorithm to eliminate mismatched point pairs and retain the feature point set that meets the geometric constraints;

[0097] The global deformation field is calculated based on the TPS algorithm to generate the inverse deformation mapping function of the target pattern.

[0098] The mapping process includes:

[0099] Based on the light transmittance characteristics of ink, a white base ink layer is superimposed on the dark area to enhance the color rendering;

[0100] Convert RGB values ​​into CMYK ink ratios based on the color gamut mapping table, and optimize inkjet timing according to the physical characteristics of the nozzle to reduce feathering.

[0101] A computer-readable storage medium stores a computer program, which implements the above-mentioned DTG printing method when executed by a processor.

[0102] The Hausdorff distance is a metric used to measure the similarity between two point sets. It is widely used in fields such as image processing, computer vision, and pattern recognition. It defines the distance between two point sets by calculating the maximum value of the closest distance from each point in one point set to the other point set. The Hausdorff distance is particularly suitable for describing shape similarity because it is sensitive to changes in the shape and position of the point sets.

[0103] The core idea of ​​the FAST corner detection algorithm is to determine whether there is a corner by detecting the brightness change in the neighborhood around the pixel. Specifically, the algorithm checks the brightness difference between a pixel and the 16 pixels around it (forming a 16-pixel arc). If the pixel is a corner, there should be a continuous segment of pixels in this arc that is significantly brighter than the center pixel, or a continuous segment of pixels that is significantly darker than the center pixel.

[0104] The PROSAC algorithm (Progressive Sample Consensus) is a robust algorithm for feature point matching, particularly suitable for handling situations with a large number of outliers (incorrectly matched point pairs). It searches for the optimal geometric model by gradually increasing the size of the sample set. It is widely used in computer vision fields such as feature matching, pose estimation, and 3D reconstruction.

[0105] The TPS (Thin Plate Spline) algorithm is an interpolation method for image registration and shape deformation, and is widely used in computer vision, image processing, pattern recognition and other fields. It can realize non-rigid deformation and smoothly map one shape to another while maintaining the continuity and smoothness of the shape. The core idea of ​​the TPS algorithm is to find a smooth mapping function by minimizing an energy function. This energy function takes into account both the smoothness of the mapping and the degree of fit to the input point pairs. For a given source point set and target point set, the TPS algorithm can calculate a mapping function so that the source point set is as close as possible to the target point set after being mapped by the function, while maintaining the smoothness of the mapping.

[0106] See also Figure 2-4 , applied to the above-mentioned DTG printing system based on line scan camera visual deformation and rigid body positioning to achieve high-precision pattern printing on fabrics. The specific steps are as follows:

[0107] Fix the line scan camera vertically 60 cm above the printing platen to ensure a stable connection between the lens and the camera. Install the strip light source 50 cm vertically below the camera and align it with the platen. Use sheet metal to firmly mount the line scan camera on the machine, keeping the camera perpendicular to the printing platen to ensure accurate image acquisition. At the same time, establish an external trigger signal connection between the line scan camera and the printing device to ensure that the two can work synchronously and coordinatedly.

[0108] Using the calibration matrix generation unit in the calibration module, a preset calibration plate is placed on the printing platen. The line scan camera collects multiple sets of calibration plate images and the corresponding physical coordinate data. Through calculation, the conversion matrix between the pixel size and the actual physical size is obtained, and the mapping relationship between the image coordinate system and the world coordinate system of the printing device is established. In terms of dynamic calibration, the real-time error compensation unit receives the differential motion signal of the platform and dynamically adjusts the conversion matrix according to the deviation reflected by the signal to eliminate the coordinate offset caused by factors such as mechanical vibration or material deformation, thereby ensuring the accuracy of coordinate mapping.

[0109] When the fabric is placed on the printing platen and starts to move, the line scan camera is triggered to capture the image of the fabric. At the same time, the system determines whether to use the rigid body positioning mode or the deformation positioning mode based on the material deformation state judgment method. For example, by calculating the Hausdorff distance between the edge contour of the fabric and the reference template, if the distance exceeds the preset threshold, it is judged as a deformed material and the deformation positioning mode is selected; conversely, if the distance is within the threshold range, the rigid body positioning mode is selected, or the frequency domain energy distribution of the fabric surface texture is analyzed. If the proportion of high-frequency components exceeds the preset value, it is determined that there are local wrinkles or stretching, and the deformation positioning mode is selected.

[0110] If the rigid body positioning mode is selected, the material position information is obtained through template matching. The system will match the collected fabric image with the pre-stored template. Once the match is successful, the specific position of the fabric on the printing platen can be determined. If the deformation positioning mode is selected, the fabric image is multi-scale down-sampled to construct a Gaussian pyramid feature space. FAST corner detection is used to extract candidate feature points in each scale layer, and rotation-invariant feature vectors are generated through the ORB descriptor. The PROSAC algorithm is then used to eliminate mismatched point pairs and retain the feature point set that meets the geometric constraints. The global deformation field is calculated based on the TPS algorithm to generate the inverse deformation mapping function of the target pattern, thereby achieving adaptive compensation positioning of the deformed fabric.

[0111] According to the positioning results, the target pattern is mapped to the printing canvas based on the positioning results. Taking into account the light transmittance characteristics of the ink, a white base ink layer is superimposed on the dark area to enhance the color rendering. At the same time, the RGB value is converted into a CMYK ink ratio based on the color gamut mapping table, and the inkjet timing is optimized according to the physical characteristics of the nozzle to reduce the feathering phenomenon. After the mapping process is completed, a TIF image is generated and converted into a printing instruction through RIP processing.

[0112] According to the printing parameter configuration and RIP image, the printing device is controlled to execute multi-color ink jetting. The printing device precisely sprays ink onto the fabric according to the received RIP instructions, completes the pattern printing that adapts to the material deformation, and obtains a fabric product with a high-precision pattern.

[0113] The same or similar reference numerals correspond to the same or similar components;

[0114] The terms used in the drawings to describe positional relationships are for illustrative purposes only and should not be construed as limiting this patent;

[0115] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not limitations on the implementation methods of the present invention. For ordinary technicians in the field, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to enumerate all the implementation methods here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the claims of the present invention.

Claims

1. A DTG printing system based on line scan camera visual deformation and rigid body positioning, characterized in that: include: Line scan camera module, used to receive trigger signals from outside the machine and continuously collect image data of dynamic printing materials; A coordinate calibration module, configured to map the image coordinate system of the image data to the world coordinate system of the printing device and compensate for platform movement errors through dynamic calibration; A dual-mode positioning module, comprising a rigid body positioning unit and a deformation positioning unit. The rigid body positioning unit achieves rigid positioning of non-deformed materials through template matching, while the deformation positioning unit performs adaptive compensation positioning of locally deformed materials based on feature point extraction and grid deformation analysis. The image mapping module is used to reversely deform the target pattern according to the positioning results and map it to the printing canvas to generate a high-precision TIF image; A RIP processing module, configured to rasterize the TIF image into RIP instructions recognizable by a printer; An integrated control module is used to trigger image acquisition, positioning processing, and printing processes with one click, and dynamically configure printing parameters. The system achieves high-precision printing of deformable materials such as fabrics and embroidery through the dynamic trigger synchronization of the line scan camera, dual-mode positioning switching, and deformation compensation algorithms.

2. The DTG printing system according to claim 1, characterized in that: The coordinate calibration module includes: A calibration matrix generation unit collects multiple sets of images and physical coordinate data based on a preset calibration plate and calculates the conversion matrix between pixel size and actual physical size; The real-time error compensation unit dynamically adjusts the conversion matrix to eliminate coordinate offsets caused by mechanical vibration or material deformation by receiving differential motion signals from the platform.

3. The DTG printing system according to claim 1, characterized in that: The deformation positioning unit includes: The multi-scale feature extraction subunit uses Gaussian pyramid downsampling to construct multi-resolution images and extracts cross-scale stable feature points through the SIFT algorithm; The deformation field modeling subunit uses the RANSAC algorithm to screen geometrically consistent matching points based on the extracted feature point pairs, and constructs the global deformation field through thin plate spline interpolation; The reverse mapping subunit performs pre-distortion processing on the target pattern according to the deformation field, so that the printed pattern adapts to the deformed material surface.

4. The DTG printing system according to claim 1, characterized in that: The integrated control module further includes: Adaptive trigger unit generates the trigger frequency of the line scan camera according to the platform movement speed, ensuring dynamic acquisition of images without motion blur; The light source synchronization unit adjusts the brightness and pulse frequency of the strip light source to synchronize it with the camera exposure time and platform movement to eliminate reflection interference.

5. The DTG printing system according to claim 1, characterized in that: Further including: The template database module stores the reference templates and historical positioning parameters of different materials. When a material is detected to match the historical template, the calibration step is automatically skipped. The exception handling module identifies missing or occluded areas in the image and triggers local re-sampling or repair based on deformation prediction of adjacent feature points.

6. A DTG printing method based on line scan camera visual deformation and rigid body positioning, used to implement the DTG printing system according to any one of claims 1 to 5, characterized in that: The following steps are involved: Install the line scan camera and light source, fix the camera vertically above the printing platen, and establish an external trigger signal connection with the printing device; Generate the conversion matrix from image coordinates to printing device coordinates through the calibration module, and dynamically calibrate the platform movement error; Trigger the line scan camera to capture material images and select rigid body positioning or deformation positioning mode according to the material deformation state; If the rigid body positioning mode is selected, the material position information is obtained through template matching; If the deformation positioning mode is selected, feature points are extracted and local deformation compensation parameters are calculated; Map the target pattern to the printing canvas based on the positioning result, generate a TIF image and convert it into printing instructions through RIP processing; According to the printing parameter configuration and RIP image control printing equipment to perform multi-color ink jetting, complete the pattern printing of adaptive material deformation.

7. The DTG printing method according to claim 6, wherein: The method for determining the deformation state of the material includes: By calculating the Hausdorff distance between the edge contour of the material and the reference template, if the distance exceeds the threshold, it is judged as a deformed material; or analyzing the frequency domain energy distribution of the material surface texture, if the proportion of high-frequency components exceeds the preset value, it is determined that local wrinkles or stretching exist.

8. The DTG printing method according to claim 6, wherein: The deformation positioning mode specifically includes: Perform multi-scale downsampling on the material image and construct a Gaussian pyramid feature space; FAST corner detection is used to extract candidate feature points at each scale layer, and the ORB descriptor is used to generate rotation-invariant feature vectors. Use PROSAC algorithm to eliminate mismatched point pairs and retain the feature point set that meets the geometric constraints; The global deformation field is calculated based on the TPS algorithm to generate the inverse deformation mapping function of the target pattern.

9. The DTG printing method according to claim 6, wherein: The mapping process includes: Based on the light transmittance characteristics of ink, a white base ink layer is superimposed on the dark area to enhance the color rendering; Convert RGB values ​​into CMYK ink ratios based on the color gamut mapping table, and optimize inkjet timing according to the physical characteristics of the nozzle to reduce feathering.

10. A computer-readable storage medium storing a computer program, characterized in that: When the program is executed by a processor, the DTG printing method according to any one of claims 6 to 9 is implemented.

Images