A method for color compensation of a coated printed sheet and a computer readable storage medium

Abstract

This invention discloses a method and storage medium for color compensation of laminated printed sheets. The method acquires the target color data and printing material combination of the document to be printed, inputs them into a pre-established color compensation model, and outputs the corresponding dot compensation value. Then, based on this compensation value, reverse dot compensation is performed on the document to be printed to generate the final printed document. The color compensation model is trained based on paired color data before and after lamination and corresponding material information, and can accurately characterize the color change patterns caused by the lamination process. This invention also includes a self-learning mechanism, which continuously optimizes the model parameters by detecting the color of the finished laminated sheet and comparing it with the target value. This solution achieves accurate and efficient pre-compensation for lamination color, effectively solving the problems of large color difference and low efficiency caused by traditional reliance on manual experience, and can be widely applied in printing proofing and production processes.

Description

Technical Field

[0001] This invention relates to the field of printing technology, and in particular to a method for accurately compensating for the color of printed sheets in a lamination process, and a computer-readable storage medium. Background Technology

[0002] In the production of high-end printed materials (such as brochures, packaging, and advertising posters), lamination is a common post-processing technique used to enhance the gloss, abrasion resistance, and durability of the printed materials. However, lamination can alter the visual appearance of the printed sheets, primarily because glossy lamination increases surface specular reflection, making colors appear more vibrant and saturated; while matte lamination increases diffuse reflection, resulting in darker, duller colors and reduced saturation. Furthermore, the film itself may have a subtle undertone (such as a slight yellow tint), which can also be superimposed on the printed material, causing color deviation.

[0003] Currently, a common pain point in the industry is that customers typically provide laminated samples as color standards (color samples). When printing plants are tracking samples, they first adjust the color on unlaminated printed sheets until the color is close to the laminated sample provided by the customer, and then proceed with lamination. However, because the color changes caused by lamination are difficult to predict accurately, the finished product after lamination often has a visible color difference (ΔE) from the customer's color sample.

[0004] In existing technologies, compensation estimates primarily rely on the operator's experience, lacking scientific and quantitative methods, leading to unstable and unreliable compensation results. Furthermore, some technical solutions attempting to address this problem are documented in published patent literature. For example:

[0005] Option 1 (Based on Optical Model Prediction): Chinese Patent CN111240001A, "A Method for Predicting the Color Effect of Coating," discloses a method that simulates the color effect after coating by establishing an optical model of the thin film and combining it with the reflective characteristics of the printing substrate, using a ray tracing algorithm. While this method is theoretically sound, it faces challenges in practical applications: First, accurately measuring the optical parameters of the thin film (such as refractive index and scattering coefficient) is difficult; second, the model calculation is complex and requires significant computational resources; finally, the interaction between ink and thin film in actual production is highly complex, making it difficult for a purely theoretical model to fully simulate, resulting in limited prediction accuracy.

[0006] Option 2 (Simple Compensation Based on an Empirical Database): Chinese Patent CN110244502A, "A Method and System for Color Compensation After Lamination," discloses a method that establishes an empirical database of color differences before and after lamination. When a target color is input, historical color difference data of similar colors are searched from the database and compensation is performed. This method is an improvement over pure experience, but its compensation accuracy heavily depends on the initial data density of the database. For colors not included in the database, simple linear interpolation is required, resulting in insufficient compensation accuracy. Furthermore, this option does not fully consider the systematic impact of different material combinations (paper, film) on color changes, leading to poor universality.

[0007] Option 3 (Online Detection and Feedback): Chinese Patent CN112883594A, "An Automatic Color Correction System for Lamination Based on Visual Detection," discloses a method that uses a camera to capture images after lamination and compares them with standard color samples to control the ink supply of the printing press. This method is a post-processing correction. While it can reduce color differences in mass production to some extent, it cannot be applied to precise pre-compensation in the pre-press stage, and it cannot recover defective products that have already been laminated, still resulting in material waste.

[0008] In summary, existing patented solutions either lack practicality due to model complexity, insufficient compensation accuracy and universality, or fail to fundamentally solve the problem due to being post-processing corrections. All of these fail to adequately meet the demands of high-precision, high-efficiency printing production. Therefore, there is an urgent need in this field for a technical solution that can achieve accurate, efficient, and universal digital compensation for lamination colors in the pre-press stage. Summary of the Invention

[0009] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art, which relies on human experience, has inaccurate compensation and low efficiency, and provides a color compensation method for laminated printed sheets based on data-driven and color science models.

[0010] To solve the above-mentioned technical problems, the present invention adopts the following technical solution:

[0011] In a first aspect, the present invention provides a method for color compensation of laminated printed sheets, comprising the following steps:

[0012] Obtain the target color data of the document to be printed, as well as the printing material information for the current order;

[0013] The target color data and the printing material information are input into a pre-established color compensation model, and the color compensation model outputs the dot compensation value corresponding to the target color data. The color compensation model is trained based on the paired color data before and after lamination of historical printed sheets and the corresponding material information. It is used to characterize the mapping relationship between the color before lamination and the dot compensation value required to achieve the target color after lamination under specific material information.

[0014] Based on the dot compensation value, reverse dot compensation is performed on the document to be printed to generate a compensated printed document.

[0015] In one implementation, the color compensation model is a lookup table model or a machine learning regression model.

[0016] In one implementation, the paired color data of the historical print sheets before and after lamination are obtained by measuring a standard color table, which contains multiple color patches covering the CMYK color gamut.

[0017] In one implementation, the target color data is a CIE Lab chromaticity value.

[0018] In one embodiment, the combination of printing materials includes paper type and film type.

[0019] In one embodiment, the printing material combination further includes an ink type.

[0020] In one implementation, the color compensation model is also trained and predicted with reference to printing equipment parameters and / or printing environment parameters.

[0021] In one embodiment, the method further includes the step of:

[0022] The compensated printed document is then printed and laminated to obtain the laminated finished product;

[0023] Measure the color data of the coated finished product and compare it with the target color data;

[0024] Based on the comparison results, the color compensation model is updated.

[0025] In one implementation, the method is performed during digital proofing or the printing production process.

[0026] In a second aspect, the present invention provides a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements any of the methods described in the first aspect above.

[0027] The beneficial effects of this invention are as follows:

[0028] Accuracy: By establishing a scientific color compensation model, qualitative compensation that relies on human experience is transformed into data-driven quantitative prediction, which significantly improves the consistency between the color after lamination and the target color sample and effectively reduces color difference (ΔE).

[0029] High efficiency: Automatic compensation of electronic files can be completed in the prepress stage, avoiding repeated trial and error and rework in the production process, greatly shortening the production cycle and reducing production costs.

[0030] Universality: By constructing a database and model containing different material combinations, this solution can adapt to various common paper, film and ink combinations, and has strong versatility.

[0031] Self-learning capability: Through a closed-loop feedback mechanism, the system can continuously optimize the model using production data, adapt to minor drifts in the production process, and maintain long-term accuracy.

[0032] Standardization: Extending color management from the printing process to the post-processing process has promoted the digitalization and standardization of the entire printing production process. Attached Figure Description

[0033] Figure 1 This is an overall flowchart of the color compensation method for laminated printed sheets provided in an embodiment of the present invention;

[0034] Figure 2 This is a flowchart of the color compensation model construction process in an embodiment of the present invention;

[0035] Figure 3 This is a flowchart illustrating the application process of the color compensation model in an embodiment of the present invention.

[0036] Figure 4 This is a flowchart illustrating the application and updating process of the color compensation model in this embodiment of the invention.

[0037] Figure 5 This is a schematic diagram of the hardware structure of a non-volatile computer-readable storage medium storing a computer program, provided as an embodiment of the present invention. Detailed Implementation

[0038] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Many specific details are set forth in the following description to provide a thorough understanding of the present invention. However, the present invention can be practiced in many other ways different from those described herein, and those skilled in the art can make similar modifications without departing from the spirit of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0039] It should be noted that when an element is referred to as being "fixed to" another element, it can be directly attached to the other element or there may be an intervening element. When an element is considered to be "connected" or "connected" to another element, it can be directly connected to the other element or there may be an intervening element. The terms "upper," "lower," "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only and do not represent the only possible implementation.

[0040] The core of this invention provides a method for color compensation in laminated printed sheets. The core concept of this method lies in establishing a data-driven color compensation model that can accurately learn the systematic color change patterns brought about by the lamination process under specific production materials. Furthermore, in the pre-press stage, this model is used to perform precise, reverse dot compensation on the documents to be printed, ensuring that the final laminated product color is highly consistent with the lamination color sample (i.e., the target color) provided by the customer.

[0041] For specific implementation details, please refer to [link / reference]. Figure 1 The method includes the following steps performed sequentially:

[0042] Step S10: Obtain the target color data of the document to be printed, as well as the printing material combination of the current order.

[0043] This step aims to prepare the necessary input data for subsequent model calculations. Two key types of information need to be obtained:

[0044] (1) Target color data of the document to be printed: This is the final standard for color matching. It can be obtained by measuring the color value of a physical color sample after lamination provided by the customer using a spectrophotometer; or it can be the color value specified in the design document that is expected to appear after lamination. To ensure that the accuracy of the color description is independent of the device, preferably, the target color data uses CIE Lab colorimetric values. For the entire document to be printed, the target color data corresponds to the expected color after lamination for each pixel or color area in the document.

[0045] (2) The combination of printing materials in the current order: This is a key factor affecting the color change of the lamination. The material combination must include at least the paper type (e.g., coated paper, matte paper, white cardstock, grey cardstock, etc.) and the film type (e.g., glossy film, matte film, etc.). This is because the surface properties of different papers (e.g., gloss, ink absorption) and the optical properties of different films (e.g., gloss, transparency, background color) will interact differently with the ink, resulting in drastically different color effects after lamination. Clearly defining the material combination is a prerequisite for the model to make accurate predictions.

[0046] Step S20: Input the target color data and printing material information into the pre-established color compensation model, and the color compensation model outputs the dot compensation value corresponding to the target color data.

[0047] This step is the core of the technical solution of this invention. The target color data and printing material combination obtained in step S10 are used as input and transmitted to a pre-established color compensation model.

[0048] The color compensation model is not based on theoretical optical formulas, but rather on an empirical model trained using statistical analysis or machine learning methods based on a large amount of historical production data. The training data for this model, namely "paired color data of historical printed sheets before and after lamination and corresponding material information," was constructed by systematically measuring the color values ​​of a large number of standard color charts before and after lamination under standardized conditions and correlating them with the material information at that time.

[0049] The model's internal mapping is constructed as follows: given specific material information, to obtain a certain target post-coating color, the color needs to be adjusted to a certain state before coating, and this state is directly output in the form of dot compensation values. In short, the model learns a complex nonlinear relationship: "To achieve A (target post-coating color), under condition B (material combination), C (dot compensation value) needs to be applied."

[0050] The specific implementation of the model may be, but is not limited to:

[0051] Lookup table model: a discrete data mapping table implemented using a high-precision interpolation algorithm.

[0052] Machine learning regression model: a continuous mathematical function learned through algorithms, such as a model built on multinomial regression or neural networks.

[0053] After receiving the input, the model quickly performs calculations and outputs the dot compensation value corresponding to each target color data point. This compensation value is usually expressed as the percentage adjustment of the dot count in each CMYK channel (such as ΔC, ΔM, ΔY, ΔK).

[0054] Step S30: Based on the dot compensation value, perform reverse dot compensation on the document to be printed to generate the compensated printed document.

[0055] This step puts the model's predictions into practice. Based on the dot compensation values ​​output by the color compensation model in step two, the original print file is modified during prepress processing.

[0056] This process is both inverse and pre-compensation. "Inverse" means that the direction of compensation is opposite to the direction of color change caused by lamination. For example, if the model predicts that matte lamination will darken the color (reduce brightness L), the compensation operation will appropriately brighten that color in pre-press (increasing the dot combination corresponding to brightness L). "Pre-compensation" means that all adjustments are made to the electronic file before printing.

[0057] The specific technical approach can be achieved through a dedicated software module or RIP plugin integrated into the prepress workflow. This module reads the compensation data output from the model and makes a global and precise adjustment to the CMYK dot percentage of each pixel or color block in the file. After the adjustment is completed, the final compensated printing file is generated. This file is sent to the printing press for output, and after lamination, the finished color can be as close as possible to the target color.

[0058] By organically combining the above three core steps, this invention achieves a leap from "experience-based color matching" to "predictive compensation," fundamentally solving the problem of color difference in lamination.

[0059] Example 1: Implementation of the basic method

[0060] This embodiment details the core implementation process of a color compensation method for laminated printed sheets. The method mainly consists of two macro-level stages: an offline model construction stage and an online compensation application stage.

[0061] (I) Offline Model Building Stage

[0062] This stage forms the foundation of the invention, aiming to establish an accurate and reliable color compensation model. Its core process is as follows: Figure 2 As shown, the specific steps are as follows:

[0063] S201: Prepare standard test documents.

[0064] First, a standard test file in electronic format needs to be created. This file should contain a standard color table that comprehensively covers and characterizes the color reproduction capabilities of printing equipment. Preferably, the internationally recognized IT8.7 / 4 color table is used, which contains over 1600 color patches systematically distributed throughout the entire CMYK (cyan, magenta, yellow, black) color space, including channel scales, gray balance scales, and numerous overlay color patches. Furthermore, based on actual production needs, some common spot colors (Pantone colors) or customer-specific color patches can be added to this color table to enhance the model's usability.

[0065] S202: Determine the combination of printing materials and perform standardized printing.

[0066] Systematically plan the combinations of printing materials to be tested. This is crucial for the model to differentiate the effects of different materials. The most basic combination should include different paper types (e.g., 157g coated paper, 200g matte paper, 250g white cardstock, etc.) and different film types (e.g., 25μm glossy film, 25μm matte film, etc.). To ensure the stability and comparability of printing data, all test prints must be performed under standardized printing conditions. Specifically, international printing standards such as ISO 12647-2 should be followed, and key parameters during the printing process should be strictly controlled and recorded, including but not limited to: solid density of each ink, dot gain (which can be monitored using UGRA / FOGRA control strips), relative contrast, and gray balance data. The type and series of inks used in printing must also be clearly recorded.

[0067] S203: Measure color data before lamination.

[0068] After the printed test print is completely dry, a high-precision spectrophotometer (such as X-Rite i1Pro3, eXact, etc.) is used to measure the CIE Lab color value of each color patch on the standard color chart. Before measurement, the instrument must be calibrated and measurement conditions must be standardized, such as using a D50 standard light source, a 2° standard viewing angle, and including specular reflection (SCI) to minimize the influence of paper surface texture and gloss on the measurement results. The measured pre-lamination color data (Lab_before) is then associated and stored with the corresponding color patch identifier (such as CMYK dot percentage).

[0069] S204: Apply a film and measure the color data after applying the film.

[0070] Apply a lamination process to the same test plate that has just been measured. The lamination process parameters (such as temperature, pressure, and speed) should be set to the recommended standard parameters for this type of film and kept stable. After lamination, allow it to cool and set completely. Subsequently, using the same spectrophotometer, under identical measurement settings and environmental conditions, measure the CIE Lab color value of each color patch on the color chart again to obtain the color data after lamination (Lab_after).

[0071] S205: Construct a color change database.

[0072] The data obtained in steps S203 and S204 are paired and organized to form complete color data records. Each record should contain at least the following information:

[0073] Unique Identifier ID

[0074] Printing material combination (paper type, film type)

[0075] Standard printing condition parameters (solid density, etc.)

[0076] CMYK values ​​of the original color blocks

[0077] Lab value measured before lamination (Lab_before)

[0078] Lab value measured after lamination (Lab_after)

[0079] The calculated color difference value (ΔE, preferably ΔE00)

[0080] By aggregating all such records, a large, multidimensional database of color variations is constructed. This database forms the foundation for subsequent model training.

[0081] S206: Training the color compensation model.

[0082] Based on the database constructed in step S205, a color compensation model is built and trained by computer. The essence of this model is to learn a complex mapping function from "target post-coating color" to "required pre-coating color (or directly to dot compensation value)".

[0083] The model input should include at least the target color data (Lab_target) and the combination of printing materials.

[0084] The model output is: the dot compensation values ​​(ΔC, ΔM, ΔY, ΔK) or the compensated Lab values ​​(Lab_compensated) required before lamination to achieve the desired color after lamination.

[0085] In this invention, the model can be implemented in two main forms:

[0086] (1) Lookup table model: A high-resolution multidimensional lookup table is constructed by performing high-precision interpolation calculations on the database (such as trilinear interpolation and tetrahedral interpolation). Given a target Lab value and material combination, the best matching dot compensation value can be directly output through lookup and interpolation.

[0087] (2) Machine learning regression model: Training is performed using machine learning algorithms. For example, multinomial regression can be used to fit the nonlinear relationship of color changes; or artificial neural networks, especially multilayer perceptrons, can be used to establish complex mappings between inputs and outputs with their powerful nonlinear fitting capabilities. The training process involves continuously adjusting the internal parameters of the model through optimization algorithms (such as gradient descent) to minimize the error (such as mean square error) between the model's predicted output and the real data in the database.

[0088] (II) Online Compensation Application Phase

[0089] Once the model has been trained and validated, it can be used for actual production orders. The process is as follows: Figure 3 As shown, the specific steps are as follows:

[0090] S301: Get input parameters.

[0091] For a new printing order, first obtain two key inputs:

[0092] Target color data: This is usually the CIE Lab value obtained by measuring the laminated sample (color swatch) provided by the customer. For the entire printed file, the target color is the desired laminated color of each pixel or area in the file, usually indexed by its standard CMYK value and internally converted to Lab value for processing.

[0093] Printing material combination for the current order: specify the type of paper and film to be used in this production.

[0094] S302: Model Calculation and Network Compensation.

[0095] The target color data and material combination obtained from S301 are input into the pre-loaded color compensation model. The model quickly calculates a set of corresponding dot compensation values ​​for each target color. For example, for a neutral gray (C50 M40 Y40 K10), the model may determine that under the "coated paper + matte lamination" combination, the dot percentage needs to be adjusted to (C51 M41 Y41 K9) to offset the darkening effect caused by the matte lamination. Subsequently, in the prepress processing stage, using specialized color management software or a plugin integrated into the RIP, the original electronic file to be printed (such as PDF or TIFF format) is adjusted globally and at the pixel level according to the compensation values ​​output by the model, thereby generating the final compensated printed file.

[0096] S303: Output and production.

[0097] The compensated print file is sent to a digital proofing machine for verification, or directly used for plate making for formal production. The paper, ink, and film types used in production must match the material combination of the input model. After printing, lamination is performed according to standard processes.

[0098] Example 2: Optimized Example with Self-Learning Function

[0099] Please see Figure 4 Based on Example 1, this example introduces a closed-loop control and self-learning mechanism to enable the system to continuously optimize.

[0100] S304: Quality Inspection and Data Feedback.

[0101] Sampling inspection is performed on the finished coated products produced by S303. The actual color data (Lab_actual) of key color blocks or areas on the finished product is measured using a spectrophotometer. This measured data is compared with the initially input target color data (Lab_target), and the color difference ΔE00 is calculated.

[0102] S305: Decision Making and Model Updates.

[0103] Set a color difference tolerance (e.g., ΔE00 < 2.5). If the color difference of the vast majority of samples is within the tolerance, the process ends and the finished product is qualified. If a systematic deviation or color difference that consistently exceeds the tolerance is found, it indicates that the current model has a prediction error under this specific production condition. In this case, the paired data of "compensated file color -> measured color after lamination" from this production is added to the original color change database as a new, valuable training sample.

[0104] Subsequently, the system can periodically (e.g., weekly) or triggered model update processes to retrain the original color compensation model using the expanded new database. This mechanism enables the model to dynamically adapt to the effects of ink batch changes, minute variations in film properties, and fluctuations in ambient temperature and humidity in the production environment, thereby achieving self-evolution and maintaining high prediction accuracy over the long term.

[0105] Example 3: Storage Medium Implementation Example

[0106] Please see Figure 5 This embodiment provides a non-volatile computer-readable storage medium 404 storing a computer program 403 to implement the above-described method. This medium may be, for example, a hard disk, a solid-state drive (SSD), a USB flash drive, flash memory, an optical disc (such as a CD-ROM, DVD), or a network storage device. When the computer program 403 in this storage medium is loaded and executed by one or more processors 402 (e.g., a CPU deployed in a prepress workstation, server, or cloud computing node), the processors 402 are controlled to implement the method described in any of the above embodiments.

[0107] The computer system typically includes the following hardware environment to execute the program:

[0108] One or more processors 402 (CPU);

[0109] The non-volatile storage device is used to persistently store the computer program 403, the color change database, and the trained color compensation model.

[0110] RAM is used to temporarily load program instructions and data during runtime for high-speed access by the processor 402.

[0111] Input / output interface for connecting to a spectrophotometer, receiving user commands, and communicating with prepress network nodes and printing production systems (such as RIP);

[0112] Communication bus 401 connects the above components.

[0113] When the computer program 403 stored on the non-volatile storage device is executed by the processor 402, it specifically implements the following functional modules:

[0114] Database management module: responsible for receiving, storing, indexing, and querying massive amounts of data in the color change database.

[0115] Model training engine: It has built-in multiple machine learning algorithms (such as neural networks and multinomial regression) and can call database data to perform model training, validation and update tasks.

[0116] Color Compensation Processing Module: This is the core application module of the program. It provides a user interface, receives target color and material combination parameters, calls the deployed color compensation model to perform prediction calculations, and generates a work ticket containing dot compensation instructions or directly modifies the data stream of the printing file.

[0117] System control and integration interface module: responsible for scheduling the entire process flow and providing standard interfaces (such as JDF / JMF based) with existing prepress workflows (such as Adobe Creative Suite plugins), RIP (raster image processor) systems and MIS (management information systems), ensuring that the compensation process is seamlessly embedded into the existing production chain.

[0118] The storage medium provided in this embodiment allows the lamination color compensation method of the present invention to be deployed and distributed as a software product, enabling printing companies to achieve accurate and efficient lamination color pre-compensation function by installing and running this software without modifying core hardware equipment.

[0119] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A method for color compensation in laminated printed sheets, characterized in that, Includes the following steps: Obtain the target color data of the document to be printed, as well as the printing material combination of the current order; The target color data and the printing material information are input into a pre-established color compensation model, and the color compensation model outputs the dot compensation value corresponding to the target color data. The color compensation model is trained based on the paired color data before and after lamination of historical printed sheets and the corresponding material information. It is used to characterize the mapping relationship between the color before lamination and the dot compensation value required to achieve the target color after lamination under specific material information. Based on the dot compensation value, reverse dot compensation is performed on the document to be printed to generate a compensated printed document.

2. The method according to claim 1, characterized in that, The color compensation model is either a lookup table model or a machine learning regression model.

3. The method according to claim 2, characterized in that, The paired color data of the historical printed sheets before and after lamination were obtained by measuring a standard color table, which contains multiple color patches covering the CMYK color gamut.

4. The method according to claim 1, characterized in that, The target color data is the CIE Lab chromaticity value.

5. The method according to claim 1, characterized in that, The combination of printing materials includes paper types and film types.

6. The method according to claim 5, characterized in that, The printing material combination also includes ink types.

7. The method according to claim 1, characterized in that, The color compensation model is also trained and predicted with reference to printing equipment parameters and / or printing environment parameters.

8. The method according to claim 1, characterized in that, The method further includes the following steps: The compensated printed document is then printed and laminated to obtain the laminated finished product; Measure the color data of the coated finished product and compare it with the target color data; Based on the comparison results, the color compensation model is updated.

9. The method according to any one of claims 1-8, characterized in that, The method is performed in digital proofing or printing production processes.

10. A non-volatile computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-9.

Images