A transfer-proof identification method based on a riding seam structure and surface random texture binding

Abstract

The application discloses a kind of anti-transfer identification methods based on riding seam structure and surface random texture binding, including preparation identification base material with riding seam structure, preparation random texture, build three kinds of quantitative model, collect parameters and substitute into model calculation and complete traceability evaluation etc. steps.This method realizes the collaborative binding of riding seam structure and surface texture and the quantitative evaluation of anti-transfer and traceability by building quantitative model, solves the problem of no quantitative basis in prior art, improves the reliability and traceability accuracy of anti-transfer identification, and is suitable for identification anti-counterfeiting technical field.

Description

A method for preventing transfer identification based on binding of seam structure and random surface texture. Technical Field

[0001] This invention relates to the field of anti-counterfeiting technology, specifically to an anti-transfer labeling method based on a seam structure and random surface texture binding. Background Technology

[0002] In existing anti-transfer tag technologies, the seam structure and random surface texture are mostly designed independently, lacking quantitative representation methods for their coordinated binding. In practical applications, it is impossible to objectively determine the tightness of the binding between the seam structure and surface texture, making it impossible to predict the anti-transfer performance in advance. When the tag is illegally transferred, it is difficult to accurately assess the feasibility of traceability after the transfer. This design approach without quantitative basis makes it impossible to guarantee the reliability of anti-transfer tags and fails to meet the precise requirements for tag anti-counterfeiting and traceability in high-security scenarios.

[0003] There is an urgent need for a technical solution that can bind the seam structure to the random surface texture, prevent transfer, and provide traceability and quantitative evaluation. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of existing technologies and proposes an anti-transfer marking method based on the binding of a seam structure and random surface texture, characterized by the following steps:

[0005] S1: Prepare a label substrate with a seam-swapping structure;

[0006] S2: Prepare a random texture on the surface of the marking substrate;

[0007] S3: Construct a co-binding quantization model of the seam structure and the random surface texture;

[0008] S4: Collect the structural parameters of the seam-riding structure and the feature parameters of the random texture, and substitute them into the collaborative binding quantization model to obtain the collaborative binding quantization calculation result;

[0009] S5: Construct a quantitative model for the probability of transfer failure;

[0010] S6: Collect the adhesion parameters between the seam structure and the marking substrate, the shear force parameters during illegal transfer, and the environmental temperature influence factor parameters, and substitute them into the anti-transfer failure probability quantification model to obtain the anti-transfer failure probability quantification calculation result;

[0011] S7: Construct a quantitative evaluation model for the effectiveness of traceability;

[0012] S8: Collect the effective texture feature quantity after the identifier transfer and the total original texture feature quantity of the random texture, and substitute them into the traceability effectiveness quantification evaluation model to complete the traceability effectiveness quantification evaluation.

[0013] Preferably, the process for preparing the marking substrate with the seam-like structure in S1 is a mold embossing process, which is used to form an interlocking seam-like structure at a preset position on the marking substrate.

[0014] More preferably, the process of preparing random textures on the surface of the marking substrate in S2 is a laser etching process. The laser etching process is used to form irregularly distributed concave and convex texture patterns on the surface of the marking substrate. The direction of the concave and convex texture patterns is intersected with the direction of the interlocking of the seam structure.

[0015] More preferably, in step S4, the device for acquiring the structural parameters of the seam-riding structure is an optical profilometer, which is used to acquire the interlocking contact area parameters and gap length parameters of the seam-riding structure; the device for acquiring the feature parameters of the random texture is an image acquisition device, which is used to acquire the feature point quantity parameters, feature width parameters, and matching logarithm parameters of the seam-riding structure edge and the random texture features of the random texture.

[0016] More preferably, the collaborative binding quantization model is used to quantify the binding tightness between the seam structure and the surface random texture. The collaborative binding quantization model is constructed based on the synergistic relationship between the seam structure parameters and the texture feature parameters. The collaborative binding quantization calculation result is used to characterize the binding correlation strength between the two.

[0017] More preferably, the anti-transfer failure probability quantification model is used to quantify the possibility of failure after the identifier is illegally transferred. The anti-transfer failure probability quantification model is constructed based on the coupling relationship between the collaborative binding strength and the external interference parameters. The anti-transfer failure probability quantification calculation result is used to predict the anti-transfer performance of the identifier.

[0018] More preferably, the traceability effectiveness quantitative evaluation model is used to quantify the traceability feasibility after the identifier is transferred. The traceability effectiveness quantitative evaluation model is constructed based on the correlation between the probability of transfer failure and the amount of texture feature retention. The result of the traceability effectiveness quantitative evaluation is used to determine the traceability value of the identifier.

[0019] More preferably, the parameters of the collaborative binding quantization model include a collaborative correction coefficient for the interlocking contact area and the number of texture feature points, a collaborative correction coefficient for the interlocking gap length and the texture feature width, and a weight correction coefficient for the feature matching logarithm. The values ​​of each collaborative correction coefficient and weight correction coefficient are determined through a set number of control experiments. The set number of control experiments is determined by the parameter range of the interlocking depth of the interlocking structure and the texture depth of the random texture.

[0020] More preferably, the parameters of the anti-transfer failure probability quantification model include the coupling correction coefficient of binding correlation and adhesion, and the coupling correction coefficient of shear force and ambient temperature influence factor. The values ​​of each coupling correction coefficient are determined by mechanical simulation experiments, and the simulation scenario of the mechanical simulation experiments is an illegal peeling operation of the label under a preset temperature gradient environment.

[0021] More preferably, the parameters of the traceability effectiveness quantification evaluation model include the effective texture feature quantity after the identifier transfer and the total original texture feature quantity of the random texture. The values ​​of the effective texture feature quantity and the total original texture feature quantity are determined by a preset type of image recognition algorithm. The recognition object of the preset type of image recognition algorithm is the pixel feature value of the texture image before and after the identifier transfer.

[0022] Technical Effects: This invention addresses the core issue of the lack of quantitative evaluation criteria for anti-transfer identifiers in the prior art by constructing a collaborative binding quantification model of the seam structure and random surface texture, a quantification model of anti-transfer failure probability, and a quantification evaluation model of traceability effectiveness. The core innovation lies in the collaborative construction of multiple models, which achieves full-link quantification of seam-to-texture binding, anti-transfer performance, and traceability effectiveness, ensuring the reliability and accuracy of anti-transfer identifiers and meeting the requirements of high-security scenarios. Attached Figure Description

[0023] Figure 1 is a flowchart of the anti-transfer marking method based on the binding of the seam structure and the random surface texture in this application. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0025] In existing anti-transfer marking technologies, the seam structure and random surface texture are mostly used independently, lacking a quantitative characterization of the synergistic binding relationship between the two. This makes it impossible to predict the anti-transfer performance or quantitatively assess the feasibility of traceability, resulting in designs that rely on experience and poor application reliability and economy.

[0026] Based on this, please refer to Figure 1. This embodiment provides an anti-transfer marking method based on the binding of a seam structure and a random surface texture. The implementation process includes the following steps: The first step is to prepare a marking substrate with a seam structure. This step is the foundation of the entire anti-transfer marking preparation and quantitative evaluation system. The selection of the substrate needs to comprehensively consider the difficulty of subsequent seam structure molding, the compatibility of random texture preparation, and the tolerance of the actual application environment. Usually, polymer composite materials or metal sheets are selected. These materials have both good formability and mechanical stability, which can ensure the interlocking strength of the seam structure and the retention durability of the random texture. The design of the seam structure needs to be combined with the preparation area of ​​the subsequent random texture to ensure that the two can form an effective synergy. Therefore, before preparation, the molding area of ​​the seam structure needs to be delineated on the substrate. This area needs to partially overlap with the coverage area of ​​the subsequent random texture. The area ratio of the overlapping area needs to be determined according to the substrate size and anti-transfer requirements to ensure that the seam structure can effectively constrain the random texture. During the preparation process, the stability of the molding process parameters needs to be controlled to avoid deviations in the size of the seam structure due to process fluctuations, which would affect the subsequent synergistic binding effect with the random texture.

[0027] The second step involves preparing a random texture on the surface of the marking substrate. This step must be based on the seam-crossing structure prepared in the first step, ensuring the random texture and the seam-crossing structure are compatible and adaptable. The texture preparation area must cover the overlapping area of ​​the seam-crossing structure defined in the first step, and extend to other key anti-transfer parts of the substrate, forming a comprehensive anti-transfer barrier. The preparation of the random texture must ensure the uniqueness and non-replicability of the texture, which is the core prerequisite for achieving anti-transfer and traceability functions. Therefore, a preparation process with random characteristics must be used to ensure that the texture of each marking is different, and that this difference can be stably collected and identified. The size parameters of the texture must match the size of the seam-crossing structure to avoid the inability to form an effective synergy due to the texture size being too large or too small. After preparation, a preliminary integrity test must be performed on the texture to ensure that there are no large areas of missing or damaged areas, providing a reliable texture foundation for subsequent parameter acquisition and model calculation.

[0028] The third step is to construct a quantitative model for the collaborative binding of the seam structure and the random surface texture. This model is the core of quantitatively representing the collaborative binding relationship between the two and is the first creative key point of the entire technical solution. Existing technologies lack such quantitative models, making it impossible to objectively judge the binding effect. The core idea of ​​this solution is to comprehensively consider the physical contact characteristics of the seam structure and the feature matching characteristics of the random texture, as these two characteristics jointly determine the strength of the collaborative binding. Before constructing the model, it is necessary to clarify the core factors affecting the collaborative binding. Through extensive preliminary experiments and theoretical analysis, the interlocking contact area of ​​the seam structure, the gap length, the number of feature points of the random texture, the feature width, the number of matching pairs between the seam structure edge and the random texture features, and the total number of feature points of the random texture are identified as core influencing factors. These factors can comprehensively reflect the collaborative relationship between the seam structure and the random texture. The model construction process needs to be based on these core factors, establishing mathematical relationships between the quantitative representation indicators and each factor to ensure that the model can accurately reflect the tightness of the binding between the two.

[0029] The fourth step involves collecting the structural parameters of the seam-seam structure and the feature parameters of the random texture, and then substituting them into the collaborative binding quantization model to obtain the collaborative binding quantization calculation results. The accuracy of parameter acquisition directly determines the accuracy of the model calculation results; therefore, high-precision dedicated acquisition equipment is required. The acquisition process must follow a preset acquisition procedure: first, the structural parameters of the seam-seam structure are acquired, followed by the feature parameters of the random texture. The acquisition area must precisely correspond to the formed areas of the first and second steps to ensure that the acquired parameters accurately reflect the collaborative binding state of the two. After acquisition, the parameters need to be preprocessed to remove outlier data and avoid data errors affecting the model calculation results. After preprocessing, the parameters are substituted into the collaborative binding quantization model according to the model's required format to obtain the collaborative binding quantization calculation results. These results will serve as the core input parameters for the subsequent anti-transfer failure probability quantization model, achieving effective connection between different models.

[0030] The fifth step is to construct a quantitative model for the probability of transfer failure. This model is crucial for predicting transfer performance and represents the second key creative aspect of the technical solution. Existing technologies cannot predict transfer performance, leading to blind spots in sign design. This model is based on the coupling relationship between cooperative bonding strength and external interference parameters. Whether a sign will fail to transfer in practical applications depends not only on its own cooperative bonding strength but also on external interference forces and environmental factors. Before constructing the model, it is necessary to identify the external interference parameters affecting transfer failure. By analyzing common illegal transfer methods and actual application environments, the adhesion between the seam structure and the sign substrate, the shear force during illegal transfer, and the influence of ambient temperature are identified as core external interference parameters. These parameters comprehensively reflect the transfer risks faced by the sign in practical applications. The model construction process requires establishing a mathematical relationship between the probability of transfer failure, cooperative bonding strength, and external interference parameters to ensure that the model can accurately quantify the possibility of failure after the sign is illegally transferred.

[0031] The sixth step involves collecting adhesion parameters between the seam-attached structure and the marking substrate, shear force parameters during illegal transfer, and environmental temperature influence factor parameters. These parameters are then input into the anti-transfer failure probability quantification model to obtain the quantified anti-transfer failure probability calculation results. Parameter collection must be tailored to the actual application scenario. Adhesion parameter collection must simulate the actual installation state of the marking to ensure the results reflect the true adhesion level. Shear force parameter collection must cover the range of forces applied by common illegal transfer methods to ensure the model can adapt to different transfer risk scenarios. Environmental temperature influence factor parameters must cover the temperature range the marking may face, considering the impact of temperature on the substrate's mechanical properties, adhesion, and co-bonding strength. After collection, the parameters are preprocessed to remove outliers and standardize them to ensure they meet the input requirements of the anti-transfer failure probability quantification model. After being input into the model, the anti-transfer failure probability quantification result is obtained. This result will be used for subsequent traceability effectiveness quantification evaluation, bridging the gap between anti-transfer performance prediction and traceability value assessment.

[0032] The seventh step is to construct a quantitative evaluation model for traceability effectiveness. This model is the core of quantifying the feasibility of traceability after identifier transfer and is also the third key creative point of the technical solution. Existing technologies cannot quantitatively evaluate traceability feasibility, making it impossible to determine the traceability value of the transferred identifier. The construction idea of ​​this model is based on the correlation between the probability of anti-transfer failure and the amount of texture feature retention. Because the traceability feasibility after identifier transfer mainly depends on the integrity of the identifier structure and the number of identifiable texture features, the probability of anti-transfer failure reflects the integrity of the identifier structure, and the amount of texture feature retention reflects the amount of information that can be used for traceability. Before constructing the model, the core parameter of texture feature retention needs to be clarified. The effective amount of texture features after identifier transfer and the total amount of original texture features of random textures are determined as core parameters. These two parameters can directly reflect the integrity of the traceability information retained by the transferred identifier. The model construction process needs to establish a mathematical correlation between traceability effectiveness, the probability of anti-transfer failure, and the amount of texture feature retention to ensure that the model can accurately quantify the feasibility of traceability after identifier transfer.

[0033] The eighth step involves collecting the effective texture features after the identifier transfer and the total original texture features of the random texture, and then substituting them into the traceability effectiveness quantification evaluation model to complete the traceability effectiveness quantification evaluation. The collection of the total original texture features must be performed immediately after the random texture is prepared to ensure that the collection results reflect the original state of the texture. The collection of effective texture features must be performed after simulating the identifier transfer. The simulated transfer process must be based on common illegal transfer methods to ensure the authenticity of the collection scenario. During the collection process, the same equipment and standards as those used for collecting random texture feature parameters must be used to ensure parameter consistency and comparability. After collection, the parameters are preprocessed to remove interfering data, ensuring that the parameters accurately reflect the retention of texture features. Substituting these into the model, the traceability effectiveness quantification evaluation result is obtained through calculation. This result can be directly used to determine the traceability value after identifier transfer, providing a reliable basis for subsequent traceability applications.

[0034] The entire technical solution, through the coordinated implementation of these eight steps, constructs a full-link quantitative evaluation system for the collaborative binding of the seam structure and random surface texture, as well as its subsequent performance. The core creative design lies in the construction of three progressive quantitative models. These three models are sequentially linked, from quantifying binding strength to predicting anti-transfer performance, and finally to assessing traceability value, forming a complete technical closed loop. This solves the problem of the lack of quantitative standards in existing technologies, ensuring the scientific nature of the label design and the reliability of its application. Each step is closely logically connected; the implementation effect of the previous step directly affects the progress of the next. Therefore, in actual implementation, it is necessary to strictly control the process parameters and data acquisition accuracy of each step to ensure the overall effectiveness of the technical solution.

[0035] Existing technologies lack a clear manufacturing process for the seam-attached structure, resulting in poor consistency in its formation and affecting the bonding stability with random textures. Therefore, the first step in preparing the marking substrate with the seam-attached structure employs a die-imprinting process. This process forms an interlocking seam-attached structure at predetermined locations on the marking substrate. The die-imprinting process is chosen for its high forming accuracy and good consistency in mass production, effectively solving the problem of poor forming consistency in existing technologies. The die design must strictly adhere to the predetermined dimensions of the seam-attached structure. The interlocking structure of the die must perfectly match the expected seam-attached structure. The die material must be high-strength and wear-resistant to ensure that the die dimensions do not deform during mass production, guaranteeing the forming accuracy of the seam-attached structure. During the imprinting process, three core parameters must be controlled: imprinting pressure, imprinting temperature, and imprinting time. The imprinting pressure must be determined based on the material properties of the substrate to ensure a clear interlocking structure while avoiding excessive pressure that could damage the substrate. The imprinting temperature must be determined based on the melting point or softening temperature of the substrate to ensure it is in a suitable forming state during the imprinting process, improving the integrity of the formed structure. Imprinting time must be matched with imprinting pressure and temperature to ensure the substrate can be fully formed and stably maintain the interlocking structure. Pre-defined positions must be achieved through pre-positioning marks on the substrate to ensure the seam structure accurately corresponds to the subsequently fabricated random texture. The interlocking structure design enhances its anti-transfer capability; the interlocking depth and width must be determined based on anti-transfer requirements. Too shallow an interlocking depth will cause the seam structure to easily detach, while too deep an interlocking depth will increase fabrication difficulty. The interlocking width must be compatible with the feature dimensions of the subsequent random texture to provide structural assurance for its co-bonding with the random texture.

[0036] Existing technologies lack a clear definition of the fabrication process and distribution of random textures, leading to unstable texture transfer prevention effects and difficulty in effectively synergizing with the seam structure. Therefore, the second step of fabricating random textures on the marking substrate surface employs laser etching. This process creates irregularly distributed raised and recessed texture patterns on the substrate surface, with the texture patterns' paths intersecting the seam structure's interlocking direction. Laser etching is chosen because it allows for precise control of texture depth and size, effectively addressing the instability of texture transfer prevention in existing technologies. The selection of laser etching equipment must be based on the substrate's material properties and texture size requirements, ensuring the equipment's etching precision meets the texture feature size requirements. During etching, three core parameters must be controlled: laser power, etching speed, and etching depth. Laser power must be determined based on the substrate's absorptivity to ensure the desired raised and recessed texture is formed on the substrate surface while avoiding excessive damage due to excessive power. The etching speed must match the laser power to guarantee texture edge clarity. The etching depth needs to be determined based on the anti-transfer requirements. Too shallow a depth will cause the texture to be easily worn away, while too deep a depth will affect the mechanical properties of the substrate. The irregularly distributed raised and recessed texture pattern is achieved through randomly generated etching paths. The random generation of these paths must be based on an encryption algorithm to ensure that the texture pattern of each identifier is unique and cannot be copied. The design of the intersecting texture direction is key to achieving anti-transfer cooperation with the seam structure. The intersection angle needs to be controlled at around 90 degrees. This angle allows the texture and the seam structure's interlocking directions to complement each other to the greatest extent. When the identifier faces illegal transfer, the seam structure and the intersecting texture can jointly resist the transfer force, further enhancing the tightness of their cooperative bonding and strengthening the overall anti-transfer performance.

[0037] Existing technologies lack clearly defined equipment for acquiring structural and feature parameters, resulting in insufficient parameter acquisition accuracy and affecting the accuracy of subsequent quantification model calculations. Therefore, in the fourth step, an optical profilometer is used to acquire the structural parameters of the seam structure. This device is used to acquire the interlocking contact area and gap length parameters of the seam structure. An image acquisition device is used to acquire the feature parameters of the random texture, including the number of feature points, feature width, and the matching logarithm of the seam structure edge and random texture features. The selection of the optical profilometer must be based on its high-precision geometric parameter measurement capabilities to ensure accurate acquisition of the microscopic geometric parameters of the seam structure. During acquisition, the optical profilometer must be calibrated using standard geometric blocks to ensure measurement accuracy meets requirements. During acquisition, the marker substrate must be fixed on the measurement platform, and the measurement range and resolution adjusted. The measurement range must cover the entire seam structure area, and the measurement resolution must be determined based on the dimensions of the seam structure to ensure clear capture of the details of the interlocking contact area and gap length. The interlocking contact area parameter is acquired by scanning the interlocking area of ​​the seam structure with the optical profilometer to obtain a two-dimensional image of the area, which is then calculated using image analysis software. The gap length parameter is acquired by scanning the gap area of ​​the seam structure, measuring the maximum and average lengths of the gap, and taking the average as the final gap length parameter. The image acquisition equipment selection must consider the size characteristics of the random texture, using a high-resolution industrial camera with a macro lens to ensure clear capture of texture details. A standardized lighting system must be set up during acquisition, employing uniform diffuse illumination to avoid shadows affecting texture feature recognition. During acquisition, the camera's focal length, aperture, and exposure time must be adjusted to ensure a clear texture image without overexposure or underexposure. The feature point count parameter is acquired by extracting features from the texture image using image analysis software, employing a corner detection algorithm to identify feature points in the texture, and counting the total number of feature points. The feature width parameter is acquired by measuring the texture width corresponding to each feature point and taking the average as the final feature width parameter. The matching logarithm parameter is acquired by overlaying and comparing the edge image of the seam structure with the texture image, identifying overlapping or complementary feature points, and counting the number of matching feature point pairs. By clearly defining these dedicated acquisition devices and acquisition parameters, the accuracy of parameter acquisition can be significantly improved, providing reliable parameter input for collaborative binding quantization models and ensuring the accuracy of model calculation results.

[0038] Existing technologies lack a clear definition of the function and construction basis of collaborative binding quantization models, resulting in directionless model design and an inability to accurately characterize the binding strength. Therefore, a collaborative binding quantization model is used to quantify the binding tightness between seam structures and random surface textures. This model is constructed based on the synergistic relationship between seam structure parameters and texture feature parameters, and the quantization results are used to characterize the binding strength between the two. In specific implementation, the collaborative binding quantization model adopts a quantification formula for the binding correlation of seam structure surface textures, the mathematical expression of which is:

[0039] ;

[0040] This formula is used to quantitatively calculate the bonding correlation between the seam structure and the random surface texture. The core design logic is to comprehensively consider the synergistic effect of the physical contact characteristics of the seam structure and the feature matching characteristics of the texture on the bonding strength. This comprehensive design approach can solve the problem of inaccurate quantification of bonding strength caused by considering only one type of characteristic in existing technologies. In the formula… This parameter represents the degree of binding between the seam structure and the random surface texture. It is a dimensionless quantity, and the larger the value, the tighter the binding between the two and the stronger the basic anti-transfer performance. This parameter is the core input of the subsequent anti-transfer failure probability quantification model and directly determines the accuracy of the anti-transfer performance prediction.

[0041] The co-correction coefficient, representing the interlocking contact area and the number of texture feature points, is a dimensionless parameter. Its function is to balance the contribution weights of the interlocking contact area and the number of feature points in the co-bonding process. Since the influence of the interlocking contact area and the number of feature points on the bonding strength varies under different substrates and processes—for example, the interlocking contact area has a greater impact on rigid substrates, while the number of feature points has a more significant impact on flexible substrates—it is necessary to experimentally determine the specific value of this coefficient. The experiment requires selecting different types of substrates and using different fabrication processes to prepare multiple sets of samples with different interlocking contact areas and the number of feature points. The bonding strength of each set of samples is tested, and then data fitting is used to determine the bonding strength under different scenarios. The optimal value.

[0042] The interlocking contact area of ​​the seam structure, measured in square meters (length squared), directly reflects the physical contact range between the seam structure and the substrate and textured areas. A larger contact area indicates a stronger physical bond between the seam structure and the substrate, as well as more contact points with the random texture, resulting in a more robust physical bond. The value of this parameter is determined by the design dimensions and manufacturing process of the seam structure. The precision of the manufacturing process directly affects the actual value of the interlocking contact area; therefore, measurement accuracy must be ensured when acquiring this parameter.

[0043] The number of feature points representing the random texture is a dimensionless parameter. The more feature points there are, the stronger the uniqueness and non-replicability of the texture, and the more binding nodes are formed with the seam structure. Each binding node can share a portion of the external force, thereby improving the overall binding strength. This parameter is determined by the fabrication process of the random texture, and the random path generation algorithm of the laser etching process directly affects the number of feature points.

[0044] The co-correction coefficient representing the gap length and texture feature width is a dimensionless parameter used to balance the negative impact of gap length and feature width on bonding strength. A larger gap results in poorer interlocking of the bonding structure, making it more prone to loosening; a wider feature width leads to poorer adaptation between the texture and the bonding structure, also causing loosening. The degree of negative impact of gap length and feature width varies in different scenarios, therefore experimental determination is necessary. The numerical values, experimental methods and Similarly, samples with different gap lengths and characteristic widths were selected, the bonding strength was tested, and then determined through data fitting. The value of .

[0045] The gap length represents the dimension of the seam joint, measured in meters. This parameter is crucial for the tightness of the seam joint. A larger gap length means the uneven parts of the seam joint cannot fully engage, weakening the physical bond and reducing the binding strength. This parameter is determined by the mold design of the seam joint, and the mold's machining accuracy directly affects the actual value of the gap length.

[0046] The feature width represents the random texture, measured in length in meters. This parameter directly affects the adaptability of the texture to the seam structure. If the feature width is too wide, the texture will not be able to effectively fit the uneven parts of the seam structure; if the feature width is too narrow, the texture will lack mechanical strength and be easily damaged. Therefore, it is necessary to design an appropriate feature width according to the size of the seam structure.

[0047] The weighting correction coefficient, representing the number of feature matching pairs, is a dimensionless parameter used to enhance the influence of feature matching degree on binding correlation. A higher number of feature matching pairs indicates better synergistic adaptation between the seam-like structure and the random texture, allowing them to form a mutually constraining structure and improve binding stability. Therefore, it is necessary to further refine the weighting coefficient. This factor is assigned a high weight, and its value is also determined experimentally. Samples with different matching logs are selected, the binding strength is tested, and the optimal weight is obtained by fitting.

[0048] The number of matching pairs represents the number of matching pairs between the edge of the seam structure and the random texture features. It is a dimensionless parameter. The number of matching pairs is determined by the relative position and size fit between the seam structure and the random texture. Precise control of the relative position between the two during the fabrication process can improve the number of matching pairs.

[0049] The total number of feature points representing the random texture is a dimensionless parameter used to normalize the matching logarithm, ensuring that the calculation results for this part are within a reasonable range. This avoids excessive deviations in the calculation results due to too many or too few total feature points, and ensures that the binding correlation between different samples is comparable.

[0050] The theoretical basis of this formula is that the binding affinity is positively correlated with the physical contact area, the number of feature points, and the number of matching pairs, and negatively correlated with the gap length and feature width. This correlation conforms to the principles of mechanics and the laws of structural synergy. The larger the physical contact area, the stronger the intermolecular forces and the stronger the binding; the more feature points, the more binding nodes, and the better the effect of dispersing the forces; the more matching pairs, the stronger the synergistic constraint. On the other hand, the larger the gap length, the less sufficient the physical contact; the wider the feature width, the worse the fit, all of which weaken the binding strength. Therefore, by combining various influencing factors in a linear combination, the synergistic binding strength can be accurately quantified.

[0051] The logical derivation of the formula is as follows: First, the core influencing factors of the cooperative bonding strength are identified. Through analysis of the cooperative mechanism between the seam structure and random texture, the core influencing factors are determined to be the interlocking contact area and gap length of the seam structure, and the number of feature points, feature width, matching pairs, and total number of feature points of the random texture. These factors comprehensively cover the two key dimensions of physical contact and feature matching. Second, the correlation between each factor and the bonding strength is analyzed. Based on mechanical experiments and structural analysis, it is determined that the interlocking contact area, the number of feature points, and the number of matching pairs are positively correlated with the bonding strength, while the gap length and feature width are negatively correlated with the bonding strength. Third, a cooperative correction coefficient and a weight correction coefficient are introduced. Since the dimensions of each factor are different and the degree of influence varies, direct combination will lead to inconsistent dimensions in the formula and meaningless calculation results. Therefore, a cooperative correction coefficient and a weight correction coefficient are introduced. , , Three dimensionless coefficients are used to balance the influence weights of each factor while achieving dimensional uniformity. Then, the basic form of the formula is constructed: for positively correlated factors, a product form is used to reflect the synergistic effect; for negatively correlated factors, a product form is used as the denominator to reflect the negative impact; for the matching logarithm, a ratio to the total number of feature points is used to achieve normalization. Finally, all parts are combined to form a complete formula, and the homogeneity of dimensions is verified to ensure the scientific validity of the formula.

[0052] The implementation process of this formula is as follows: First, an optical profilometer and an image acquisition device are used to obtain... , , , , , The specific values ​​of parameters are determined, and the parameters are preprocessed to remove outliers. Then, based on the substrate type and preparation process, parameters that have been pre-determined experimentally are selected. , , The coefficient values ​​are calculated by substituting the parameters and coefficients into the formula, starting with the first term. The contribution of physical contact characteristics to the binding affinity is obtained; then the second term is calculated. This yields the contribution of feature matching characteristics to the binding association degree; finally, the two results are added together to obtain the result. The final value will be used as the input parameter for the subsequent anti-transfer failure probability quantification model to achieve a quantitative characterization of the binding strength.

[0053] The core innovation of this formula lies in its first-ever integration of the physical contact characteristics of the seam structure and the feature matching characteristics of random textures into the same quantification model. Through multi-parameter collaborative correction and normalization, it achieves precise quantification of the binding correlation between the two, solving the problem of the inability to quantify and represent the collaborative binding relationship in existing technologies. Simultaneously, the formula's progressive design provides reliable basic parameters for subsequent prediction of anti-transfer performance and evaluation of traceability effectiveness, forming a full-link quantitative evaluation system and overcoming the limitation of existing technologies that rely on empirical judgment in anti-transfer identifier design.

[0054] Existing technologies lack a clear definition of the function and construction basis of the anti-transfer failure probability quantification model, making it impossible to predict the anti-transfer performance of the identifier. Therefore, the anti-transfer failure probability quantification model is used to quantify the probability of identifier failure after unauthorized transfer. This model is constructed based on the coupling relationship between cooperative binding strength and external interference parameters. The calculation results of the anti-transfer failure probability quantification are used to predict the anti-transfer performance of the identifier. In specific implementation, the anti-transfer failure probability quantification model adopts the anti-transfer failure probability calculation model, the mathematical formula of which is:

[0055] ;

[0056] This formula is used to quantitatively calculate the failure probability of a tag after it has been illegally transferred. Its core design logic is based on the coupling effect of the cooperative binding strength and external interference parameters, predicting the tag's anti-transfer reliability in practical applications. This consideration of coupling effect comprehensively reflects the stress state of the tag in actual applications, solving the problem of inaccurate anti-transfer performance prediction caused by considering only a single factor in existing technologies. Where... This represents the probability of the anti-transfer failure. It is a dimensionless quantity with a value between zero and one. The closer the value is to zero, the lower the possibility of the tag failing after being illegally transferred, and the stronger the anti-transfer performance. The closer the value is to one, the higher the risk of anti-transfer failure. This parameter can provide a direct basis for the design optimization of the tag and the selection of application scenarios.

[0057] The coupling correction coefficient, representing the bond affinity and adhesion, is a dimensionless parameter. Its function is to balance the synergistic contribution of bond affinity and adhesion to resist unauthorized transfer. Bond affinity reflects the synergistic bonding strength between the seam structure and the random texture, while adhesion reflects the bonding strength between the seam structure and the substrate. Together, they constitute the internal resistance of the marker to unauthorized transfer. The coupling effect varies under different substrates and application scenarios. For example, in high-temperature environments, adhesion decays faster than bond affinity; therefore, mechanical simulation experiments are needed to determine the coupling effect. The specific numerical values ​​were determined. During the experiment, different types of substrates were selected to simulate different application environments. The anti-transfer ability of the markers under different combinations of bonding affinity and adhesion was tested, and then determined through data fitting. The optimal value.

[0058] The binding correlation between the seam structure and the random surface texture is represented by a dimensionless parameter. This parameter is calculated by the cooperative binding quantification model mentioned above and directly reflects the basic strength of the cooperative binding between the two. It is the core internal factor affecting the anti-transfer performance. The larger the value, the stronger the internal resistance and the lower the probability of anti-transfer failure.

[0059] This parameter represents the adhesion between the seam-attached structure and the substrate. Its dimension is the negative square of mass multiplied by length multiplied by time, and its unit is Newtons. Adhesion is the fundamental mechanical property that fixes the seam-attached structure to the substrate. The greater the adhesion, the more difficult it is to peel the seam-attached structure from the substrate, and the greater the external force required for illegal transfer. The magnitude of this parameter is determined by the substrate type, the manufacturing process of the seam-attached structure, and the surface treatment method. For example, surface roughening treatment can improve adhesion.

[0060] The coupling correction coefficient, representing the influence factors of shear force and ambient temperature, is a dimensionless parameter used to balance the synergistic effects of shear force and ambient temperature on anti-transfer failure. Shear force is the main external interference force leading to label transfer failure, while ambient temperature indirectly affects the anti-transfer effect by influencing the mechanical properties and adhesion of the substrate. The effect of shear force varies at different temperatures; for example, at high temperatures, the substrate softens, making transfer more likely under the same shear force. Therefore, mechanical simulation experiments are needed to determine the effect. The numerical values, experimental methods and Similarly, by simulating different temperature environments and applying different shear forces, the failure conditions of the markers were tested, and the results were obtained through fitting. The optimal value.

[0061] This represents the shear force applied during illegal transfer, with dimensions of mass multiplied by length multiplied by time to the negative square, and units of Newtons. This parameter is the main external interference force causing the transfer of identification tags to fail. Its magnitude is determined by the tools and methods used in the illegal transfer; for example, the shear force applied when using a blade to peel is greater than that applied by hand.

[0062] This represents the influence of ambient temperature, a dimensionless parameter whose value is obtained through experimental fitting of the correlation between temperature and substrate properties. Temperature changes affect the mechanical properties and adhesion of the substrate, thus impacting the anti-transfer effect. For example, increased temperature leads to a decrease in the elastic modulus of the polymer substrate and a reduction in adhesion. The value increases with increasing temperature, reflecting the promoting effect of ambient temperature on the failure of the transfer prevention system.

[0063] The theoretical basis of this formula is that the failure probability of anti-transfer marking is positively correlated with external interference force and negatively correlated with internal binding strength and adhesion. It uses an exponential function to characterize the change in failure probability, which aligns with the relationship between failure probability and external force and material strength in materials mechanics. In materials mechanics, the failure probability of a component is usually characterized by an exponential distribution or a Weibull distribution. The exponential function can better reflect the trend of failure probability as the ratio of external force to strength increases. When the ratio of external force to strength increases, the failure probability increases exponentially, and this trend is consistent with the failure characteristics of anti-transfer marking.

[0064] The logical derivation of the formula is as follows: First, the core factors affecting anti-transfer failure are identified. Through mechanical analysis of the illegal transfer process of the marker, internal factors include binding affinity and adhesion, while external factors include shear force and ambient temperature. These factors jointly determine the probability of marker anti-transfer failure. Second, the correlation between failure probability and internal and external factors is constructed. Based on the exponential distribution failure probability model, it is assumed that the failure probability is related to the ratio of internal resistance to external interference; the greater the internal resistance and the smaller the external interference, the lower the failure probability. Third, a coupling correction coefficient is introduced. Because there is coupling between internal and external factors, directly using a simple ratio cannot accurately reflect the actual failure pattern. Therefore, a coupling correction coefficient is introduced. and Two coupling correction coefficients are used to balance the coupling effects of each factor. Then, the basic form of the formula is determined, using an exponential function. The negative correlation characterizing the failure probability, where This represents the coupling ratio of internal resistance to external disturbance force. Finally, through... Obtain the failure probability To ensure that the probability of failure is within the range of zero to one, and to verify the homogeneity of dimensions, the formula must be scientifically sound.

[0065] The implementation process of this formula is as follows: First, obtain the specific values ​​of each parameter. Calculated by the collaborative binding quantization model, Data were collected using adhesion testing equipment. Shear force values ​​under common illegal transfer methods are collected using mechanical sensors. The correlation between temperature and substrate properties was obtained through experimental fitting. and The parameters were determined through prior mechanical simulation experiments. Then, the collected parameters were preprocessed to remove outliers and standardized to ensure they fit the input requirements of the formula. Next, the numerator of the exponential part was calculated. and denominator To obtain the ratio of the two, calculate the negative value of the ratio, and substitute it into the exponential function to get... Finally, subtracting the result from the exponent yields the probability of anti-transfer failure. The final value will be used in the subsequent quantitative evaluation model of traceability effectiveness.

[0066] The core innovation of this formula lies in its first-ever inclusion of the coupling effect between internal synergistic bonding strength and adhesion, and external shear force and ambient temperature, into the quantitative calculation of the anti-transfer failure probability. It employs an exponential function to accurately characterize the changing pattern of the failure probability, solving the problem of existing technologies' inability to predict anti-transfer performance. Simultaneously, this formula effectively connects with the previously discussed synergistic bonding quantitative model, constructing a progressive quantitative system using bonding correlation parameters. This ensures that the prediction of anti-transfer performance is based on precise quantitative data, rather than empirical judgment, improving the scientific rigor and reliability of the marking design. Furthermore, the formula balances the influence weights of different factors through a coupling correction coefficient, adapting to the needs of different substrates and application scenarios, enhancing the versatility of the technical solution.

[0067] Existing technologies lack a clear definition of the function and construction basis of a quantitative evaluation model for traceability effectiveness, making it impossible to quantitatively assess the feasibility of traceability after identifier transfer. Therefore, a quantitative evaluation model for traceability effectiveness is used to quantify the feasibility of traceability after identifier transfer. This model is constructed based on the correlation between the probability of transfer failure and the amount of texture feature retention. The results of the quantitative evaluation of traceability effectiveness are used to determine the traceability value of the identifier. In specific implementation, the quantitative evaluation model for traceability effectiveness adopts the identifier traceability effectiveness evaluation formula, the mathematical formula of which is:

[0068] ;

[0069] This formula is used to quantitatively evaluate the traceability effectiveness after identifier transfer. Its core design logic combines the probability of anti-transfer failure with the amount of texture feature retention to comprehensively judge whether the identifier possesses traceability value. This comprehensive judgment approach can fully reflect the structural and informational integrity of the identifier after transfer, solving the problem of inaccurate traceability feasibility assessments caused by considering only one type of factor in existing technologies. In the formula… The value represents the traceability validity of the identifier. It is a dimensionless quantity expressed as a percentage. The higher the value, the higher the feasibility of traceability after the identifier is transferred, and the greater the traceability value. The lower the value, the lower the traceability feasibility. This parameter can be directly used to determine whether the identifier has traceability application value after the transfer.

[0070] The probability of transfer failure is represented by a dimensionless parameter, calculated using the transfer failure probability quantification model described above. Subtracting the transfer failure probability from the result indicates the degree of structural integrity preservation after the transfer. A larger value indicates less damage to the marker during the transfer process, higher structural integrity, and a more complete traceability foundation. For example, a transfer failure probability of 0.2 results in a structural integrity preservation of 0.8, meaning the marker maintains good structural integrity after the transfer.

[0071] The effective texture feature quantity represents the area covered by texture features that can still be clearly identified and used for traceability comparison after the transfer. It is the core information carrier for traceability. The magnitude of this parameter is determined by the severity of the transfer process and the wear resistance of the texture. The more severe the transfer process and the more serious the wear of the texture, the smaller the effective texture feature quantity; the stronger the wear resistance of the texture, the more effective texture feature quantity is retained.

[0072] This represents the total amount of original texture features of the random texture, with the dimension of length squared and the unit being square meters. It indicates the total coverage area of ​​the original texture after preparation. This parameter is obtained by image acquisition equipment and image analysis software after the random texture is prepared, and serves as a benchmark for measuring the proportion of effective texture features retained.

[0073] The ratio of effective texture features to the total number of original texture features represents the proportion of texture features retained. The larger the ratio, the more effective traceability information is retained after the transfer, and the more solid the traceability information foundation. For example, a ratio of 0.7 indicates that 70% of the effective texture features are still retained after the transfer, which can provide sufficient information for traceability comparison.

[0074] The theoretical basis of this formula is that the effectiveness of traceability is jointly determined by the structural integrity of the identifier and the amount of texture information retained, and the two synergistically affect the feasibility of traceability. Structural integrity is the foundation of traceability; only when the identifier maintains a certain level of structural integrity can texture features be preserved. The amount of texture information retained is the core of traceability; only when there are sufficient effective texture features can it be compared with the original texture to achieve traceability. Therefore, the product of the two can comprehensively reflect the effectiveness of traceability. This design conforms to the basic principles of traceability technology. The essence of traceability is to confirm the origin of the identifier by comparing the feature information of the transferred identifier with that of the original identifier, and the preservation of feature information depends on structural integrity and texture abrasion resistance.

[0075] The logical derivation of the formula is as follows: First, the core factors affecting the effectiveness of traceability are identified. Through analysis of the traceability process, the structural integrity of the identifier and the amount of texture feature retention are determined to be the core influencing factors. Structural integrity is reflected by the probability of anti-transfer failure, and the amount of texture feature retention is reflected by the ratio of the effective texture feature quantity to the total original texture feature quantity. Second, the correlation between these two factors and traceability effectiveness is analyzed. Higher structural integrity and a larger texture feature retention ratio result in stronger traceability effectiveness; both are positively correlated with traceability effectiveness. Third, the basic form of the formula is constructed. Since both are dimensionless parameters and positively correlated, a product form is used to combine their influences to obtain the basic value of traceability effectiveness. Finally, multiplying by 100% converts the result into a percentage form for easy intuitive judgment and verification of dimensional homogeneity, ensuring the scientific validity of the formula.

[0076] The implementation process of this formula is as follows: First, obtain the specific values ​​of each parameter. Calculated by the anti-transfer failure probability quantification model, After the simulated identifier transfer, texture images are acquired using image acquisition equipment, and then the area of ​​the effective texture feature region is calculated using image analysis software. The data was acquired and calculated immediately after the random texture was prepared. Then, the parameters were preprocessed to ensure… and The measurement standards are consistent to avoid ratio deviations caused by measurement errors. Next, calculate one minus... The results yield the degree of structural integrity preservation, and then the calculation is performed. and The ratio of these two values ​​is used to obtain the texture feature preservation ratio. Then, the two results are multiplied to obtain the base value for traceability effectiveness, and finally multiplied by 100% to obtain the traceability effectiveness expressed as a percentage. The result can be directly used to determine the traceability value of the transferred identifier. When the result is higher than the preset threshold, it indicates that the identifier has traceability value and can be used for subsequent traceability comparison; when the result is lower than the preset threshold, it indicates that the identifier has no traceability value.

[0077] The core innovation of this formula lies in its pioneering integration of the anti-transfer failure probability with texture feature retention, constructing a quantitative evaluation model for traceability effectiveness. This achieves precise quantification of traceability feasibility after identifier transfer, solving the problem of existing technologies' inability to quantitatively assess traceability feasibility. Simultaneously, this formula effectively connects with the aforementioned anti-transfer failure probability quantification model, utilizing the anti-transfer failure probability parameter to construct a complete end-to-end quantification system, forming a closed loop from binding strength quantification to anti-transfer performance prediction, and then to traceability effectiveness evaluation. Furthermore, the formula outputs results in percentage form, making it intuitive and easy to understand, facilitating judgment and decision-making in practical applications, and overcoming the limitation of existing technologies' reliance on subjective judgment in traceability feasibility assessment.

[0078] Existing technologies lack a clear method and basis for determining the correction coefficients in collaborative binding quantification models, resulting in a lack of standard values ​​for the correction coefficients and affecting the accuracy of model calculations. Therefore, the parameters of the collaborative binding quantification model include collaborative correction coefficients for the interlocking contact area and the number of texture feature points, collaborative correction coefficients for the interlocking gap length and texture feature width, and weighted correction coefficients for the feature matching logarithm. The values ​​of each collaborative correction coefficient and weighted correction coefficient are determined through a preset number of control experiments. The preset number of experiments is determined by the parameter range of the interlocking depth of the interlocking structure and the texture depth of the random texture. The preset number of experiments is based on the parameter range of the interlocking depth and texture depth because these two parameters directly affect the collaborative binding effect. The adaptability of the collaborative correction coefficients varies under different parameter ranges. For example, in the shallower interlocking depth range, the interlocking contact area has a smaller impact on the binding strength, and the corresponding collaborative correction coefficient needs to be adjusted. Therefore, a preset number of experiments covering the key parameter ranges is required to ensure that the correction coefficients can accurately balance the contribution weights of each parameter in different application scenarios.

[0079] The implementation process of the control experiment is as follows: First, the experimental and control variables were determined. The experimental variables were the interlocking depth and the texture depth of the random texture. The control variables included substrate type, preparation process parameters, and other structural and texture parameters. The control variables must be kept consistent to avoid affecting the experimental results. Second, parameter intervals were divided. Based on the common ranges of interlocking depth and texture depth in practical applications, multiple continuous parameter intervals were divided, and three representative values ​​were selected for each interval as experimental levels. Third, the number of preset groups was determined. Each parameter interval combination corresponds to one experimental group. The number of groups must cover all key parameter interval combinations to ensure the adaptability of the correction coefficients. Then, experimental samples were prepared. According to the parameter requirements of each experimental group, samples with interlocking structures and random textures were prepared. Five parallel samples were prepared for each group to ensure the reliability of the experimental results. Next, the bonding strength of the samples was tested. A universal tensile testing machine was used to test the peel strength of the samples at a preset tensile speed as the evaluation index of bonding strength. The average peel strength of each group of samples was recorded. Finally, data fitting and coefficient determination: the structural parameters, texture parameters and corresponding binding strength data of each group of samples are substituted into the co-binding quantization model, and the least squares method is used to fit the data to determine the co-correction coefficients and weight correction coefficients that minimize the error between the model calculation results and the actual test results. These coefficients are then associated with the corresponding parameter ranges to form a coefficient database, which facilitates the selection of the corresponding coefficient values ​​according to the specific parameter range in practical applications.

[0080] By determining the correction coefficient through a controlled experiment with a predetermined number of groups, a clear standard can be provided for the value of the correction coefficient, ensuring the accuracy of the calculation results of the collaborative binding quantitative model, avoiding model errors caused by arbitrary coefficient values, and improving the reliability of the entire quantitative evaluation system.

[0081] Existing technologies lack a clear definition of the measurement method and scenario for coupling correction coefficients in the anti-transfer failure probability quantification model, leading to inaccurate coefficient values ​​and affecting the accuracy of failure probability prediction. Therefore, the parameters of the anti-transfer failure probability quantification model include coupling correction coefficients for bonding affinity and adhesion, and coupling correction coefficients for shear force and ambient temperature influence factors. The values ​​of each coupling correction coefficient are determined through mechanical simulation experiments. The simulation scenario is an illegal tag removal operation under a preset temperature gradient. The preset temperature gradient environment covers the main temperature application scenarios that tags may face, such as -20 degrees Celsius to 60 degrees Celsius. This temperature range covers most indoor and outdoor application environments. Simulating illegal removal operations can reproduce the mechanical action during actual illegal transfer, ensuring that the measured coupling correction coefficients accurately reflect the coupling relationship between bonding affinity, adhesion, shear force, and ambient temperature in actual applications.

[0082] The implementation process of the mechanical simulation experiment is as follows: First, determine the experimental and control variables. The experimental variables are ambient temperature and shear force, while the control variables include substrate type, labeling structural parameters, texture parameters, bonding correlation, adhesion, etc. The control variables must be kept consistent to ensure the reliability of the experimental results. Second, set preset temperature gradients. Based on common application environment temperature ranges, set multiple temperature gradients, each spaced ten degrees Celsius apart, ranging from -20°C to 60°C. Third, set the shear force range. Based on common illegal transfer methods, set multiple shear force levels, ranging from 50 Newtons to 500 Newtons, covering the shear force range from hand peeling to tool peeling. Next, prepare experimental samples. Select typical substrates and structural parameters, and prepare multiple identical labeling samples to ensure sample consistency. Finally, build the experimental platform, which includes an environmental test chamber, a universal tensile testing machine, and mechanical sensors. The environmental test chamber is used to control the experimental temperature, the universal tensile testing machine is used to apply shear force, and the mechanical sensors are used to accurately measure the shear force values. Next, experimental tests were conducted. The experimental samples were first placed in an environmental test chamber, adjusted to a preset temperature, and maintained at that temperature for two hours to allow the samples to adapt to the ambient temperature. Then, the samples were fixed on a universal tensile testing machine, and a shear force was applied at a preset shear rate until the samples experienced transfer failure. The shear force value at failure and the corresponding ambient temperature were recorded. Simultaneously, the binding correlation and adhesion values ​​of the samples were recorded. Five parallel samples were prepared for each experimental condition, and the average failure data were tested and recorded. Finally, data fitting and coefficient determination were performed. The binding correlation, adhesion, shear force, ambient temperature, and corresponding failure results of each experimental group were substituted into the anti-transfer failure probability quantification model. Maximum likelihood estimation was used for data fitting to determine the coupling correction coefficient values ​​that minimized the error between the model's prediction and the actual failure results. These coefficients were then correlated with the corresponding temperature gradients to form a coefficient database, facilitating the selection of appropriate coefficient values ​​based on specific temperature scenarios in practical applications.

[0083] By measuring the coupling correction coefficient through this mechanical simulation experiment, the accuracy of the coefficient value can be improved, ensuring the predictive accuracy of the anti-transfer failure probability quantification model. This enables the model to accurately reflect the anti-transfer failure law in actual applications, providing a reliable basis for the design optimization of the sign and the selection of application scenarios.

[0084] Existing technologies lack a clear definition of the parameter measurement methods and identification objects in traceability effectiveness quantification evaluation models, leading to inaccurate parameter collection and affecting the evaluation results. Therefore, the parameters of the traceability effectiveness quantification evaluation model include the effective texture feature quantity after identifier transfer and the total original texture feature quantity of the random texture. The values ​​of the effective texture feature quantity and the total original texture feature quantity are determined using a preset type of image recognition algorithm. The recognition object of this preset type of image recognition algorithm is the pixel feature value of the texture image before and after identifier transfer. This preset type of image recognition algorithm can employ edge detection and feature matching algorithms. By identifying the pixel feature values ​​of the texture image, it can accurately distinguish between effective and invalid texture feature regions, thereby accurately calculating the effective texture feature quantity and the total original texture feature quantity, providing reliable parameter input for traceability effectiveness evaluation.

[0085] The implementation process of the image recognition algorithm is as follows: First, image acquisition and preprocessing. For determining the total amount of original texture features, after the random texture is prepared, a high-resolution image acquisition device is used to capture texture images. During shooting, uniform lighting and no shadow interference are ensured, and the image resolution is not less than 3,000 pixels per inch. For determining the effective amount of texture features, after simulating the transfer of identifiers, the same image acquisition device and shooting parameters are used to capture texture images, ensuring that the shooting conditions are consistent between the two shooting sessions. The preprocessing process includes image grayscale conversion, noise reduction, and enhancement. Grayscale conversion converts the color image into a grayscale image, reducing the amount of data; noise reduction uses a Gaussian filtering algorithm to remove noise interference in the image; enhancement uses a histogram equalization algorithm to improve the contrast between texture features and the background, facilitating subsequent feature recognition.

[0086] Secondly, edge detection is performed using the Canny edge detection algorithm to identify the edge features of the texture. This algorithm features high detection accuracy and strong noise resistance, and can accurately identify the edge contours of the texture. During implementation, a reasonable threshold range is first set, based on the image's grayscale histogram, to ensure accurate differentiation between edge and non-edge pixels. Then, edge detection is performed on the preprocessed image to obtain the texture edge image. In the edge image, white pixels represent texture edges, and black pixels represent the background.

[0087] Then, feature extraction and matching are performed. For the original texture image, texture feature points are extracted from the edge image. The SIFT algorithm is used to extract the position, scale, and orientation information of the feature points, and the total number of feature points is counted. At the same time, the total area of ​​the texture region in the edge image is calculated, which is the total amount of original texture features. For the transferred texture image, the same SIFT algorithm is used to extract feature points, and they are matched with the feature points of the original texture image. A matching threshold is set. When the Euclidean distance between two feature points is less than the matching threshold, they are considered as valid matching feature points. The number of valid matching feature points is counted, and the area of ​​the texture region corresponding to these valid feature points is calculated, which is the amount of valid texture features.

[0088] Finally, for parameter calculation and output, the total area of ​​the texture region obtained from edge detection is directly output for the total amount of original texture features; for the effective texture features, the area of ​​the texture region corresponding to the matched effective feature points is output, along with the number of matching feature point pairs, providing parameter support for the collaborative binding quantization model. This pre-defined type of image recognition algorithm can accurately measure the effective texture features and the total amount of original texture features, ensuring the accuracy of parameter acquisition, providing reliable parameter input for the traceability effectiveness quantification evaluation model, and guaranteeing the reliability of the evaluation results.

[0089] The core innovation of this image recognition algorithm lies in its combination of Canny edge detection and SIFT feature matching algorithms, achieving accurate identification and matching of texture features. It effectively distinguishes between valid and invalid regions of the transferred texture, solving the problem of inaccurate texture feature parameter acquisition in existing technologies. Simultaneously, the algorithm employs uniform shooting and processing parameters, ensuring consistent parameter acquisition standards between the original and transferred textures. This avoids errors caused by differences in acquisition conditions, improves parameter comparability and accuracy, and provides technical support for the accurate evaluation of traceability effectiveness.

[0090] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A method for preventing transfer identification based on binding of a seam structure and random surface texture, characterized in that, Includes the following steps: S1: Prepare a label substrate with a seam-like structure; S2: Prepare a random texture on the surface of the label substrate; S3: Construct a co-bonding quantization model of the seam-like structure and the random surface texture, wherein the mathematical formula used in the co-bonding quantization model is: In the formula, This represents the degree of binding correlation between the seam structure and the random surface texture. The coefficient representing the collaborative correction between the interlocking contact area and the number of texture feature points. This represents the interlocking contact area of ​​the straddle joint structure. The number of feature points representing the random texture. The coefficient representing the co-correction between the seam gap length and the texture feature width. Represents the gap length of the seam structure. The feature width representing the random texture. The weight correction coefficient represents the number of feature matching logs. The number of matching pairs between the edge of the seam structure and random texture features. Represents the total number of feature points in a random texture; S4 S5: Collect the structural parameters of the seam-seam structure and the feature parameters of the random texture, and substitute them into the collaborative binding quantization model to obtain the collaborative binding quantization calculation result; S6: Construct an anti-transfer failure probability quantization model, the mathematical formula of which is: In the formula, Represents the probability of anti-transfer failure. The coupling correction coefficient represents the degree of binding correlation and adhesion. This represents the degree of binding correlation between the seam structure and the random surface texture. This represents the adhesion between the seam structure and the signage substrate. This represents the coupling correction coefficient between shear force and the influence of ambient temperature. This represents the shear force applied during illegal transfer. Represents the factors affecting environmental temperature; S6: Collect the adhesion parameters between the seam-attached structure and the marking substrate, the shear force parameters during illegal transfer, and the environmental temperature influence factor parameters, and substitute them into the anti-transfer failure probability quantification model to obtain the anti-transfer failure probability quantification calculation result; S7: Construct a traceability effectiveness quantification evaluation model, the mathematical formula used in the traceability effectiveness quantification evaluation model is: In the formula, This indicates the validity of the traceability identifier. Represents the probability of anti-transfer failure. The effective texture feature quantity after the identifier is transferred. The total amount of original texture features representing the random texture; S8: Collect the effective texture feature quantity after the identifier transfer and the total original texture feature quantity of the random texture, and substitute them into the traceability effectiveness quantification evaluation model to complete the traceability effectiveness quantification evaluation.

2. The anti-transfer identification method based on the binding of a seam structure and random surface texture according to claim 1, characterized in that, The process of preparing the marking substrate with the seam structure in S1 is a mold embossing process, which is used to form a concave-convex interlocking seam structure at a preset position on the marking substrate.

3. The anti-transfer identification method based on the binding of a seam structure and random surface texture according to claim 1, characterized in that, The process for preparing random textures on the surface of the marking substrate in S2 is a laser etching process. The laser etching process is used to form irregularly distributed concave and convex texture patterns on the surface of the marking substrate. The direction of the concave and convex texture patterns is intersected with the direction of the interlocking of the seam structure.

4. The anti-transfer identification method based on the binding of a seam structure and random surface texture according to claim 1, characterized in that, In S4, the device for acquiring the structural parameters of the seam-riding structure is an optical profilometer, which is used to acquire the interlocking contact area parameters and gap length parameters of the seam-riding structure; the device for acquiring the feature parameters of the random texture is an image acquisition device, which is used to acquire the feature point quantity parameters, feature width parameters, and matching logarithm parameters of the seam-riding structure edge and the random texture features of the random texture.

5. The anti-transfer identification method based on the binding of a seam structure and random surface texture according to claim 1, characterized in that, The collaborative binding quantization model is used to quantify the binding tightness between the seam structure and the surface random texture. The collaborative binding quantization model is constructed based on the synergistic relationship between the seam structure parameters and the texture feature parameters. The collaborative binding quantization calculation results are used to characterize the binding correlation strength between the two.

6. The anti-transfer identification method based on the binding of a seam structure and random surface texture according to claim 1, characterized in that, The anti-transfer failure probability quantification model is used to quantify the possibility of failure after the identifier is illegally transferred. The anti-transfer failure probability quantification model is constructed based on the coupling relationship between the cooperative binding strength and the external interference parameters. The anti-transfer failure probability quantification calculation result is used to predict the anti-transfer performance of the identifier.

7. The anti-transfer identification method based on the binding of a seam structure and random surface texture according to claim 1, characterized in that, The traceability effectiveness quantitative evaluation model is used to quantify the feasibility of traceability after the transfer of the identifier. The model is constructed based on the correlation between the probability of failure to prevent transfer and the amount of texture feature retention. The results of the traceability effectiveness quantitative evaluation are used to determine the traceability value of the identifier.

8. The anti-transfer identification method based on the binding of a seam structure and random surface texture according to claim 5, characterized in that, The parameters of the collaborative binding quantization model include the collaborative correction coefficients for the interlocking contact area and the number of texture feature points, the collaborative correction coefficients for the interlocking gap length and the texture feature width, and the weight correction coefficients for the feature matching logs. The values ​​of each collaborative correction coefficient and weight correction coefficient are determined through a set number of control experiments. The set number of control experiments is determined by the parameter range of the interlocking depth of the interlocking structure and the texture depth of the random texture.

9. The anti-transfer identification method based on the binding of a seam structure and random surface texture according to claim 6, characterized in that, The parameters of the anti-transfer failure probability quantification model include the coupling correction coefficient of binding correlation and adhesion, and the coupling correction coefficient of shear force and ambient temperature influence factor. The values ​​of each coupling correction coefficient are determined by mechanical simulation experiments. The simulation scenario of the mechanical simulation experiments is an illegal peeling operation of the label under a preset temperature gradient environment.

10. The anti-transfer identification method based on the binding of a seam structure and random surface texture according to claim 7, characterized in that, The parameters of the traceability effectiveness quantification evaluation model include the effective texture feature quantity after identifier transfer and the total original texture feature quantity of the random texture. The values ​​of the effective texture feature quantity and the total original texture feature quantity are determined by a preset type of image recognition algorithm. The recognition object of the preset type of image recognition algorithm is the pixel feature value of the texture image before and after identifier transfer.

Images