Laser holographic anti-counterfeiting film makeup method for optimizing joint precision

Abstract

The invention provides a laser holographic anti-counterfeiting film makeup method for optimizing seam precision, which comprises the following steps: acquiring light wave phase distribution data of a seam area through a preset optical simulation model, and calculating light wave phase difference of adjacent holographic image edges by adopting a fast Fourier transform algorithm to obtain spatial distribution coordinates of phase discontinuous points; extracting optical characteristic parameters of a seam area from the optimized phase distribution data, and simulating a propagation path of light waves in the seam area by adopting a finite element analysis method to obtain boundary conditions of smooth transition of the light waves; and manufacturing parameters of a seam area are extracted from the final microstructure template data, a holographic pattern of the seam area is generated through light wave phase modulation and pixel dot matrix density control by adopting a laser direct writing technology, and the holographic anti-counterfeiting film makeup with optical fracture suppression is obtained. By accurately controlling phase distribution and bright spot design of the seam area, continuous transition of light waves and visual seamless connection are achieved.

Description

Technical Field

[0001] The invention relates to a laser holographic anti-counterfeiting film platemaking method for optimizing seam precision. Background Art

[0002] Laser holographic anti-counterfeiting technology occupies a key position in the modern anti-counterfeiting field. Through complex optical patterns and unique optical properties, it provides high security and aesthetics for products and is widely used to protect currency, documents and high-value goods. At present, the platemaking process of anti-counterfeiting films has significant limitations in achieving seamless connections. Traditional platemaking methods often achieve image splicing through mechanical alignment or simple overlap, but these methods have difficulty controlling the optical properties of the seam area with micron-level precision, resulting in visible marks at the seams, affecting the overall aesthetics and anti-counterfeiting effect. In addition, the visual abruptness of the seam area will also reduce the observer's trust in the anti-counterfeiting film. During the platemaking process, phase continuity in the seam area becomes the primary technical challenge. If the edges of adjacent holographic images cannot achieve a smooth transition of light wave phases, a significant optical break will occur at the seam, destroying the integrity of the image. This phase discontinuity directly affects the concealment of the seam, which leads to another key issue, namely how to design a reasonable distribution of bright spots in the seam area to cover up the marks.

[0003] Uneven or poorly targeted bright spot distribution makes the seam area more prominent visually, making it difficult to distract the viewer through the principles of visual psychology. These two factors are interrelated: phase discontinuity causes optical defects, while irrational bright spot distribution amplifies the visual perception of these defects. Therefore, how to achieve a continuous transition of light waves and a seamless visual connection by precisely controlling the phase distribution and bright spot design in the seam area during the laser holographic anti-counterfeiting film splicing process has become a key issue that needs to be addressed. Summary of the Invention

[0004] The present invention proposes a laser holographic anti-counterfeiting film splicing method with optimized seam accuracy, which realizes continuous transition of light waves and visually seamless connection by precisely controlling the phase distribution and bright spot design of the seam area.

[0005] The technical solution of the present invention is achieved as follows: A laser holographic anti-counterfeiting film splicing method for optimizing seam accuracy, the method comprising: S101, obtaining light wave phase distribution data of the seam area through an optical simulation model, calculating the light wave phase difference between adjacent holographic image edges using a fast Fourier transform algorithm, and obtaining the spatial distribution coordinates of the phase discontinuity points; S102, adjusting the lightwave phase distribution parameters in the seam region using an iterative optimization algorithm based on the spatial distribution coordinates of the phase discontinuity points. If the phase difference is less than a preset threshold of 0.01 radians, the phase continuity requirement is determined to be met, and optimized phase distribution data is obtained. S103, extracting optical characteristic parameters of the joint region from the optimized phase distribution data, simulating the propagation path of light waves in the joint region using a finite element analysis method, and obtaining boundary conditions for smooth transition of light waves; S104, using a visual psychology model and combining the boundary conditions of smooth light wave transition, obtaining an initial bright spot density distribution scheme in the seam area, optimizing the bright spot density distribution and position, adjusting the spatial frequency response and color contrast sensitivity, and obtaining a bright spot distribution scheme that is uniform and visually distracting; S105: Based on a uniform and visually distracting bright spot distribution scheme, a digital micromirror device is used to generate a microstructure template for the seam area. The microstructure resolution and template surface accuracy are controlled. If the microstructure resolution reaches the micron level and the template surface accuracy is less than 0.1 micron, the seam area design is determined to meet the optical property consistency requirements, and the final microstructure template data is obtained. S106, extracting manufacturing parameters of the seam area from the final microstructure template data, using laser direct writing technology, through light wave phase modulation and pixel array density control, to generate a holographic pattern of the seam area, thereby obtaining a holographic anti-counterfeiting film panel with optical fracture suppression; S107, using high-resolution optical inspection equipment, obtains image data of the holographic anti-counterfeiting film panel seam area, uses image processing algorithms to analyze the seam area masking effect, and combines edge blur tolerance and light intensity perception threshold. If the visual defect of the seam area is lower than the preset threshold, it is determined that the seamless connection effect is achieved, and the final anti-counterfeiting film panel data is obtained. Holographic anti-counterfeiting films are batch generated to obtain anti-counterfeiting film products that meet the requirements of seam area masking and visual attention distraction.

[0006] The present invention achieves the following beneficial effects: The phase distribution of the seam region is obtained through optical simulation and fast Fourier transform, phase parameters are adjusted to achieve continuity using an iterative optimization algorithm, bright spot distribution is optimized by combining visual psychology models and genetic algorithms, a microstructure template is generated using a digital micromirror device, and a holographic pattern is produced using laser direct writing technology, ultimately achieving optical fracture suppression in the seam region. By precisely controlling the phase distribution, bright spot density, and microstructure parameters, the present invention effectively conceals visual defects at the anti-counterfeiting film joint, ensuring that the seam region and the overall pattern have consistent optical properties. This also achieves visual distraction, significantly improving the anti-counterfeiting performance and aesthetics of the holographic anti-counterfeiting film. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0008] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0009] The following will clearly and completely describe the technical solutions of the present invention in conjunction with the embodiments of the present invention. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0010] Reference Figure 1 A laser holographic anti-counterfeiting film splicing method for optimizing seam accuracy, characterized in that the method comprises: S101, using an optical simulation model, obtains light wave phase distribution data of the seam area, uses a fast Fourier transform algorithm to calculate the light wave phase difference between adjacent holographic image edges, and obtains the spatial distribution coordinates of the phase discontinuity point.

[0011] The optical simulation model is used to obtain the light wave phase distribution data in the joint area, determine the light wave phase distribution matrix, and use the fast Fourier transform algorithm to perform frequency domain conversion on the light wave phase distribution matrix to obtain the frequency domain phase distribution. Based on the frequency domain phase distribution, the phase difference between the edges of adjacent holographic images is calculated to determine an edge phase difference value set. If a phase difference value in the edge phase difference value set exceeds a preset threshold, it is marked as a phase discontinuity point, thereby obtaining a phase discontinuity point set. According to the set of phase discontinuity points, their spatial coordinates in the seam area are mapped to generate a spatial coordinate distribution. Through the spatial coordinate distribution, a two-dimensional interpolation algorithm is used to reconstruct the continuous phase distribution of the phase discontinuity points to obtain the optimized phase distribution. For the optimized phase distribution, the inverse fast Fourier transform is used to convert it back to the time domain phase distribution to generate the final phase distribution data.

[0012] S102, based on the spatial distribution coordinates of the phase discontinuity points, an iterative optimization algorithm is used to adjust the light wave phase distribution parameters in the seam area. If the phase difference is less than a preset threshold of 0.01 radians, it is determined that the phase continuity meets the requirements, and the optimized phase distribution data is obtained.

[0013] Obtaining light wave phase data in the seam area to generate an initial phase distribution matrix. Using the initial phase distribution matrix, the phase distribution parameters are adjusted using a gradient descent algorithm. The phase differences between adjacent holographic image edges are calculated to obtain a phase difference value set. For the phase difference value set, if any phase difference is less than a preset threshold, it is marked as a phase continuous point, and a phase continuous point set is generated. According to the set of phase continuous points, their spatial coordinates in the seam area are mapped to generate spatial coordinate distribution data. The spatial coordinate distribution data are processed by the spline interpolation algorithm to generate smoothed phase distribution data. The phase distribution parameters of the seam area are adjusted by the inverse mapping method based on the smoothed phase distribution data to generate the final phase distribution data. For the final phase distribution data, the statistical characteristics of the phase distribution are calculated to generate a phase distribution feature data set.

[0014] S103, extracting optical characteristic parameters of the joint area from the optimized phase distribution data, simulating the propagation path of the light wave in the joint area using a finite element analysis method, and obtaining boundary conditions for smooth transition of the light wave.

[0015] Extracting optical characteristic parameters of the joint area from the optimized phase distribution data, calculating the distribution characteristics of the parameters using a statistical analysis method, generating an optical characteristic distribution data set, and dividing the grid structure of the joint area using a finite element analysis method based on the optical characteristic distribution data set to generate grid division data; By meshing the data, the propagation path of the light wave in the seam area is simulated, the phase change characteristics of the propagation path are calculated, and a phase change data set is generated. For the phase change data set, if the phase change value is less than a preset threshold, it is determined to be a smooth transition point, and a smooth transition point set is generated; According to the set of smooth transition points, the spline interpolation method is used to optimize the boundary conditions of the seam area to generate optimized boundary condition data. Based on the optimized boundary condition data, the inverse mapping method is used to adjust the optical characteristic parameters of the seam area to generate the final optical characteristic data set.

[0016] S104, using a visual psychology model and combining the boundary conditions of smooth light wave transition, obtain an initial bright spot density distribution scheme in the seam area, optimize the bright spot density distribution and position, adjust the spatial frequency response and color contrast sensitivity, and obtain a bright spot distribution scheme that is uniform and visually distracting.

[0017] Obtain the initial bright spot density distribution data of the seam area from the visual psychology model.

[0018] represents the bright spot density distribution function, represents the intensity of the i-th bright spot, represents the standard deviation of the Gaussian distribution, and represents the coordinate position of the i-th bright spot, M represents the total number of bright spots combined with the boundary condition of smooth transition of light waves; The initial bright spot distribution dataset is iteratively optimized using a genetic algorithm to adjust the bright spot density and position to generate an optimized bright spot distribution dataset. Based on the optimized bright spot distribution dataset, the spatial frequency response characteristics are calculated to generate a spatial frequency distribution dataset. For the spatial frequency distribution dataset, if the frequency response value exceeds a preset threshold, the bright spot position is adjusted using an interpolation method to generate an adjusted bright spot distribution dataset. The color contrast sensitivity feature is calculated through the adjusted bright spot distribution data set to generate a color contrast distribution data set. Based on the color contrast distribution data set, the mean filtering method is used to optimize the bright spot density distribution to generate the final bright spot distribution data set. Through the final highlight distribution dataset, verify the attention distraction feature and generate the attention distraction distribution dataset.

[0019] Indicates the degree of distraction. Indicates the total number of bright spots, represents the position coordinates of the i-th bright spot, Represents the average value of all bright spot positions. This formula is used to calculate the degree of dispersion of bright spot distribution.

[0020] S105, based on a bright spot distribution scheme that is uniform and visually distracting, a digital micromirror device is used to generate a microstructure template for the seam area, and the microstructure resolution and template surface accuracy are controlled. If the microstructure resolution reaches the micron level and the template surface accuracy is less than 0.1 micron, it is determined that the seam area design meets the optical property consistency requirements, and the final microstructure template data is obtained.

[0021] generating initial microstructure template data of the seam area using a digital micromirror device, controlling the microstructure resolution and surface accuracy using preset parameters to obtain initial template data; and obtaining optimized template data by optimizing the microstructure resolution by adjusting the pixel unit size of the digital micromirror device if the resolution of the initial template data does not reach the micron level; Based on the optimized template data, the accuracy characteristics of the template surface are calculated. If the surface accuracy is better than the preset threshold, it is determined that the template meets the surface accuracy requirements and the accuracy verification data is obtained. Based on the accuracy verification data, the optical characteristic distribution of the seam area is analyzed and the mean filtering method is used to smooth the optical characteristic differences to obtain the optical characteristic data; If the consistency of the optical characteristic data does not reach the preset threshold, the local features of the microstructure template are adjusted by interpolation to obtain the adjusted template data.

[0022] Indicates the consistency deviation value of the optical characteristic data, M indicates the number of sampling points, Represents the optical characteristic value of the current point, Indicates the target optical characteristic value; Based on the adjusted template data, the final microstructure template data of the seam area is generated, and its resolution and surface accuracy are verified to obtain the final template data. Based on the final template data, the support vector machine algorithm is used to classify the consistency of the optical properties of the seam area, determine whether the design meets the consistency requirements, and obtain the verification result data.

[0023] S106, extracting the manufacturing parameters of the seam area from the final microstructure template data, using laser direct writing technology, through light wave phase modulation and pixel array density control, to generate a holographic pattern of the seam area, thereby obtaining a holographic anti-counterfeiting film panel with optical fracture suppression.

[0024] Extract characteristic parameters of the seam area from the microstructure template data, decompose the template data using data segmentation method, and obtain the manufacturing parameter set of the seam area; The manufacturing parameter set is processed by laser direct writing technology, and the phase distribution of the laser beam is adjusted using a light wave phase modulation algorithm to generate phase modulation data. Based on the phase modulation data, the pixel lattice density of the laser direct writing device is controlled. A gridding algorithm is used to generate holographic pattern data of the seam area. If the resolution of the holographic pattern data does not reach a preset threshold, the pixel lattice density is optimized through interpolation to obtain optimized holographic pattern data. Edge features are extracted from the optimized holographic pattern data, and the edge feature differences are smoothed using the mean filtering method to obtain smoothed holographic pattern data. By smoothing the holographic pattern data, holographic anti-counterfeiting film imposition data is generated, and the optical breakage suppression characteristics of the imposition data are verified using the support vector machine algorithm to obtain verified imposition data. Based on the verified imposition data, the output parameters of the laser direct writing equipment are adjusted to generate the final holographic anti-counterfeiting film imposition data.

[0025] S107, using high-resolution optical inspection equipment, obtains image data of the holographic anti-counterfeiting film panel seam area, uses image processing algorithms to analyze the seam area masking effect, and combines edge blur tolerance and light intensity perception threshold. If the visual defect of the seam area is lower than the preset threshold, it is determined that the seamless connection effect is achieved, and the final anti-counterfeiting film panel data is obtained. Holographic anti-counterfeiting films are batch generated to obtain anti-counterfeiting film products that meet the requirements of seam area masking and visual attention distraction.

[0026] The original image data of the joint area of ​​the holographic anti-counterfeiting film is collected by a high-resolution optical detection device to generate a first image data set, and the first image data set is preprocessed by an image denoising algorithm to remove noise interference to generate a second image data set; The edge detection algorithm is used to analyze the seam area in the second image data set, extract the edge fuzzy features, and generate an edge feature data set. Based on the edge feature data set and combined with the light intensity perception threshold, the visual defect ratio of the seam area is calculated to generate defect ratio data.

[0027] represents the regional defect ratio, Represents the light intensity value of the k-th pixel, represents the brightness threshold, m represents the total number of pixels in the region, and W represents the normalized weight; If the defect ratio data falls below a preset threshold, the seam area is deemed seamless and qualified panel data is generated. This qualified panel data is then used to generate batch production parameters for the holographic anti-counterfeiting film, resulting in a production data set. This production data set is then used to drive automated equipment to mass-produce anti-counterfeiting film products that meet the requirements for seam concealment and visual distraction.

[0028] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A laser holographic anti-counterfeiting film splicing method for optimizing seam accuracy, characterized in that: The method comprises: S101, obtaining light wave phase distribution data of the seam area through an optical simulation model, calculating the light wave phase difference between adjacent holographic image edges using a fast Fourier transform algorithm, and obtaining the spatial distribution coordinates of the phase discontinuity points; S102, adjusting the lightwave phase distribution parameters in the seam region using an iterative optimization algorithm based on the spatial distribution coordinates of the phase discontinuity points. If the phase difference is less than a preset threshold of 0.01 radians, the phase continuity requirement is determined to be met, and optimized phase distribution data is obtained. S103, extracting optical characteristic parameters of the joint region from the optimized phase distribution data, simulating the propagation path of light waves in the joint region using a finite element analysis method, and obtaining boundary conditions for smooth transition of light waves; S104, using a visual psychology model and combining the boundary conditions of smooth light wave transition, obtaining an initial bright spot density distribution scheme in the seam area, optimizing the bright spot density distribution and position, adjusting the spatial frequency response and color contrast sensitivity, and obtaining a bright spot distribution scheme that is uniform and visually distracting; S105: Based on a uniform and visually distracting bright spot distribution scheme, a digital micromirror device is used to generate a microstructure template for the seam area. The microstructure resolution and template surface accuracy are controlled. If the microstructure resolution reaches the micron level and the template surface accuracy is less than 0.1 micron, the seam area design is determined to meet the optical property consistency requirements, and the final microstructure template data is obtained. S106, extracting manufacturing parameters of the seam area from the final microstructure template data, using laser direct writing technology, through light wave phase modulation and pixel array density control, to generate a holographic pattern of the seam area, thereby obtaining a holographic anti-counterfeiting film panel with optical fracture suppression; S107, using high-resolution optical inspection equipment, obtains image data of the holographic anti-counterfeiting film panel seam area, uses image processing algorithms to analyze the seam area masking effect, and combines edge blur tolerance and light intensity perception threshold. If the visual defect of the seam area is lower than the preset threshold, it is determined that the seamless connection effect is achieved, and the final anti-counterfeiting film panel data is obtained. Holographic anti-counterfeiting films are batch generated to obtain anti-counterfeiting film products that meet the requirements of seam area masking and visual attention distraction.

2. The method according to claim 1, wherein Step S101 specifically includes: The optical simulation model is used to obtain the light wave phase distribution data in the joint area, determine the light wave phase distribution matrix, and use the fast Fourier transform algorithm to perform frequency domain conversion on the light wave phase distribution matrix to obtain the frequency domain phase distribution. Based on the frequency domain phase distribution, the phase difference between the edges of adjacent holographic images is calculated to determine an edge phase difference value set. If a phase difference value in the edge phase difference value set exceeds a preset threshold, it is marked as a phase discontinuity point, thereby obtaining a phase discontinuity point set. According to the set of phase discontinuity points, their spatial coordinates in the seam area are mapped to generate a spatial coordinate distribution. Through the spatial coordinate distribution, a two-dimensional interpolation algorithm is used to reconstruct the continuous phase distribution of the phase discontinuity points to obtain the optimized phase distribution. For the optimized phase distribution, the inverse fast Fourier transform is used to convert it back to the time domain phase distribution to generate the final phase distribution data.

3. The method according to claim 1, wherein Step S102 specifically includes: Obtaining light wave phase data in the seam area to generate an initial phase distribution matrix. Using the initial phase distribution matrix, the phase distribution parameters are adjusted using a gradient descent algorithm. The phase differences between adjacent holographic image edges are calculated to obtain a phase difference value set. For the phase difference value set, if any phase difference is less than a preset threshold, it is marked as a phase continuous point, and a phase continuous point set is generated. According to the set of phase continuous points, their spatial coordinates in the seam area are mapped to generate spatial coordinate distribution data. The spatial coordinate distribution data are processed by the spline interpolation algorithm to generate smoothed phase distribution data. The phase distribution parameters of the seam area are adjusted by the inverse mapping method based on the smoothed phase distribution data to generate the final phase distribution data. For the final phase distribution data, the statistical characteristics of the phase distribution are calculated to generate a phase distribution feature data set.

4. The method according to claim 1, wherein Step S103 specifically includes: Extracting optical characteristic parameters of the joint area from the optimized phase distribution data, calculating the distribution characteristics of the parameters using a statistical analysis method, generating an optical characteristic distribution data set, and dividing the grid structure of the joint area using a finite element analysis method based on the optical characteristic distribution data set to generate grid division data; By meshing the data, the propagation path of the light wave in the seam area is simulated, the phase change characteristics of the propagation path are calculated, and a phase change data set is generated. For the phase change data set, if the phase change value is less than a preset threshold, it is determined to be a smooth transition point, and a smooth transition point set is generated; According to the set of smooth transition points, the spline interpolation method is used to optimize the boundary conditions of the seam area to generate optimized boundary condition data. Based on the optimized boundary condition data, the inverse mapping method is used to adjust the optical characteristic parameters of the seam area to generate the final optical characteristic data set.

5. The method according to claim 1, wherein Step S104 specifically includes: Obtain the initial bright spot density distribution data of the seam area from the visual psychology model. represents the bright spot density distribution function, represents the intensity of the i-th bright spot, represents the standard deviation of the Gaussian distribution, and represents the coordinate position of the i-th bright spot, M represents the total number of bright spots combined with the boundary condition of smooth transition of light waves; The initial bright spot distribution dataset is iteratively optimized using a genetic algorithm to adjust the bright spot density and position to generate an optimized bright spot distribution dataset. Based on the optimized bright spot distribution dataset, the spatial frequency response characteristics are calculated to generate a spatial frequency distribution dataset. For the spatial frequency distribution dataset, if the frequency response value exceeds a preset threshold, the bright spot position is adjusted using an interpolation method to generate an adjusted bright spot distribution dataset. The color contrast sensitivity feature is calculated through the adjusted bright spot distribution data set to generate a color contrast distribution data set. Based on the color contrast distribution data set, the mean filtering method is used to optimize the bright spot density distribution to generate the final bright spot distribution data set. Through the final highlight distribution dataset, verify the attention distraction feature and generate the attention distraction distribution dataset. Indicates the degree of distraction. Indicates the total number of bright spots, represents the position coordinates of the i-th bright spot, Represents the average value of all bright spot positions. This formula is used to calculate the degree of dispersion of bright spot distribution.

6. The method according to claim 1, wherein Step S105 specifically includes: generating initial microstructure template data of the seam area using a digital micromirror device, controlling the microstructure resolution and surface accuracy using preset parameters to obtain initial template data; and obtaining optimized template data by optimizing the microstructure resolution by adjusting the pixel unit size of the digital micromirror device if the resolution of the initial template data does not reach the micron level; Based on the optimized template data, the accuracy characteristics of the template surface are calculated. If the surface accuracy is better than the preset threshold, it is determined that the template meets the surface accuracy requirements and the accuracy verification data is obtained. Based on the accuracy verification data, the optical characteristic distribution of the seam area is analyzed and the mean filtering method is used to smooth the optical characteristic differences to obtain the optical characteristic data; If the consistency of the optical characteristic data does not reach the preset threshold, the local features of the microstructure template are adjusted by interpolation to obtain the adjusted template data. Indicates the consistency deviation value of the optical characteristic data, M indicates the number of sampling points, Represents the optical characteristic value of the current point, Indicates the target optical characteristic value; Based on the adjusted template data, the final microstructure template data of the seam area is generated, and its resolution and surface accuracy are verified to obtain the final template data. Based on the final template data, the support vector machine algorithm is used to classify the consistency of the optical properties of the seam area, determine whether the design meets the consistency requirements, and obtain the verification result data.

7. The method according to claim 1, wherein Step S106 specifically includes: Extract characteristic parameters of the seam area from the microstructure template data, decompose the template data using data segmentation method, and obtain the manufacturing parameter set of the seam area; The manufacturing parameter set is processed by laser direct writing technology, and the phase distribution of the laser beam is adjusted using a light wave phase modulation algorithm to generate phase modulation data. Based on the phase modulation data, the pixel lattice density of the laser direct writing device is controlled. A gridding algorithm is used to generate holographic pattern data of the seam area. If the resolution of the holographic pattern data does not reach a preset threshold, the pixel lattice density is optimized through interpolation to obtain optimized holographic pattern data. Edge features are extracted from the optimized holographic pattern data, and the edge feature differences are smoothed using the mean filtering method to obtain smoothed holographic pattern data. By smoothing the holographic pattern data, holographic anti-counterfeiting film imposition data is generated, and the optical breakage suppression characteristics of the imposition data are verified using the support vector machine algorithm to obtain verified imposition data. Based on the verified imposition data, the output parameters of the laser direct writing equipment are adjusted to generate the final holographic anti-counterfeiting film imposition data.

8. The method according to claim 1, wherein Step S107 specifically includes: The original image data of the joint area of ​​the holographic anti-counterfeiting film is collected by a high-resolution optical detection device to generate a first image data set, and the first image data set is preprocessed by an image denoising algorithm to remove noise interference to generate a second image data set; The edge detection algorithm is used to analyze the seam area in the second image data set, extract the edge fuzzy features, and generate an edge feature data set. Based on the edge feature data set and combined with the light intensity perception threshold, the visual defect ratio of the seam area is calculated to generate defect ratio data. represents the regional defect ratio, Represents the light intensity value of the k-th pixel, represents the brightness threshold, m represents the total number of pixels in the region, and W represents the normalized weight; If the defect ratio data falls below a preset threshold, the seam area is deemed seamless and qualified panel data is generated. This qualified panel data is then used to generate batch production parameters for the holographic anti-counterfeiting film, resulting in a production data set. This production data set is then used to drive automated equipment to mass-produce anti-counterfeiting film products that meet the requirements for seam concealment and visual distraction.

Images