Anti-counterfeiting identification monitoring system and method based on machine vision shrink film form

Abstract

The invention relates to the technical field of machine vision and image processing, in particular to an anti-counterfeiting identification monitoring system and method based on a machine vision shrink film form. Comprising the following parts: a reference feature acquisition module used for acquiring three morphological features of the shrink film after product packaging, namely a watermark pattern, a closing seam and a hole; photographing and recording based on the three morphological characteristics, and taking the three morphological characteristics as standard references of a reference image; and the transportation damage simulation module is used for acquiring a product transportation route of the product from the production line to the consumer and recording key nodes in the product transportation route process. According to the invention, through advanced information technology and image identification technology, the accuracy and reliability of anti-counterfeiting verification are improved; supply chain environment parameters are dynamically monitored, and the misjudgment rate is reduced; image recognition captures subtle changes of packages, and accuracy is improved; the transparency and traceability are enhanced through whole-process data monitoring, the consumer trust is improved, and the product quality safety is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of machine vision and image processing, and particularly to an anti-counterfeiting identification and monitoring system and method based on the morphology of shrink film in machine vision. Background Art

[0002] With the development of global trade and the increasing attention of consumers to product safety, it has become crucial to ensure the transparency and authenticity of goods throughout the production and delivery process. In the field of fast-moving consumer goods, traditional anti-counterfeiting measures are insufficient due to the complexity of logistics and the susceptibility of packaging materials to environmental influences. Physical damage during transportation, differences in light intensity in different regions, and other factors can cause changes in the packaging appearance, making traditional anti-counterfeiting methods based on static templates prone to misjudgment or missed detection. When the shrink film wraps the product, the attachment position of the watermark pattern, the shape of the closing seam, and the position and size of the ventilation holes all show non-replicable randomness.

[0003] To address these challenges, there is an urgent need for a new monitoring mechanism that can dynamically adapt to changes in the actual application scenario. By leveraging advanced information technology, integrating sensors and data analysis algorithms, real-time collection and analysis of the movement of goods and the surrounding environmental parameters in the supply chain are carried out to achieve more accurate and reliable anti-counterfeiting verification. At the same time, the progress of image recognition technology has also provided new solutions for capturing changes in subtle structural features, facilitating the development of efficient anti-counterfeiting tools. Summary of the Invention

[0004] In order to overcome the drawbacks of backward anti-counterfeiting means and easy misjudgment, the present invention provides an anti-counterfeiting identification and monitoring system and method based on the morphology of shrink film in machine vision.

[0005] The technical solution is as follows: An anti-counterfeiting identification and monitoring system based on the morphology of shrink film in machine vision, comprising: A reference feature acquisition module: obtaining three morphological features of the shrink film after the product is packaged, namely a watermark pattern, a closing seam, and a hole; based on the three morphological features, taking a photo record, and using the three morphological features as the standard reference of the reference image; A transportation damage simulation module: obtaining the product transportation route from the production line to the hands of consumers, recording the key nodes in the product transportation route process, where the key nodes include the transportation route condition and the duration of the product being exposed outside; based on the transportation route condition and the duration of the product being exposed outside, calculating the first change image of the watermark pattern using the watermark pattern change formula; the first change image refers to the change in the watermark pattern compared with the factory state due to the loss caused by handling bumps or exposure during the product transportation process; Environmental damage modeling module: Based on the first changed image, obtain the local solar radiation intensity parameters based on the final geographical location of the product, and calculate the second changed image of the watermark pattern using the ghost overlay formula; the second changed image is used for product anti-counterfeiting identification and verification. Anti-counterfeiting verification decision module: Based on the reference image, the first changed image, and the second changed image, and combining the morphological changes of the closing seam and the morphological changes of the hole, obtain the anti-counterfeiting identification result.

[0006] Preferably, the reference feature acquisition module includes: Obtain the grayscale image matrix data of the original watermark pattern before printing and the grayscale image matrix data of the watermark pattern after printing; calculate the reference ghosting coefficient of the watermark pattern using the reference ghosting coefficient formula.

[0007] Preferably, calculating the reference ghosting coefficient of the watermark pattern using the reference ghosting coefficient formula includes: The reference ghosting coefficient formula is as follows, where, is the reference ghosting coefficient, is the grayscale image matrix of the original watermark pattern; is the ghosting convolution kernel; is the convolution operation; is the total number of image pixels; is the pixel point.

[0008] Preferably, the transportation damage simulation module includes: Based on the reference ghosting coefficient, obtain the transportation route conditions, and the transportation route conditions are specifically the road smoothness, the driving level of the driver, and the types of transportation route accidents; At the same time, obtain the duration of the product's external exposure, and the exposure duration is specifically the duration of the product's watermark pattern being exposed to natural light; Based on the reference ghosting coefficient, the transportation route conditions, and the duration of the product's external exposure, calculate the first changed image of the watermark pattern using the watermark pattern change formula.

[0009] Preferably, calculating the first changed image of the watermark pattern using the watermark pattern change formula based on the reference ghosting coefficient, the transportation route conditions, and the duration of the product's external exposure includes: The watermark pattern change formula is as follows, where, is the watermark grayscale value after transportation; is the original watermark grayscale value; is the material photosensitivity coefficient; is the exposure duration; is the solar radiation intensity; is the reference ghosting coefficient; is the transportation shock sensitivity coefficient; is the road evenness; is the driving level score; is the accident impact equivalent; is the random noise term .

[0010] Preferably, the environmental damage modeling module includes: Based on the sunlight irradiation situation in the region where the consumer is located, extract the ultraviolet irradiation data and the day-night temperature difference data; based on the ultraviolet irradiation data and the day-night temperature difference data, use the double-image superposition formula to calculate the second changed image of the watermark pattern.

[0011] Preferably, the calculating the second changed image of the watermark pattern by using the double-image superposition formula includes: the double-image superposition formula is as follows, wherein, is the total environmental damage value of the th product; , is the ultraviolet dose and temperature difference data of the th sampled product within the batch, = 1, 2, ……, , wherein, ≪N1, is the number of sampled products within the batch, and N1 is the total batch quantity; is the position weight of the th product; is the local environment correction amount of the th product.

[0012] Preferably, the anti-counterfeiting verification decision module includes: Taking the watermark pattern features in the reference image, the first changed image, and the second changed image as the first comparison feature sequence; Taking the closing seam features in the reference image and the closing seam shape changed image as the second comparison feature sequence; Taking the hole features in the reference image and the hole shape changed image as the third comparison feature sequence; Extracting the images with similarity lower than the preset threshold in the three comparison feature sequences as the final comparison images for anti-counterfeiting verification at the consumer side.

[0013] Preferably, the extracting the images with similarity lower than the preset threshold in the three comparison feature sequences as the final comparison images for anti-counterfeiting verification at the consumer side includes: The similarity threshold is a quantization index of the image difference degree calculated by the feature extraction algorithm. When the similarity is lower than the preset threshold, it is determined as a valid comparison image.

[0014] An anti-counterfeiting identification and monitoring method based on the morphology of shrink film using machine vision, comprising: S1: Use a high-resolution industrial camera to take multi-angle pictures of the original morphology of the shrink film watermark pattern, the closing seam, and the hole, and align the feature areas through an image registration algorithm; extract the watermark grayscale matrix, construct a Gaussian difference convolution kernel, calculate the reference ghosting coefficient after performing convolution operations, and realize the quantification of printing process errors; S2: Integrate GPS and Internet of Things sensors to collect transportation parameters; establish a multi-factor damage model, and dynamically generate a degraded watermark image after transportation through the photosensitivity coefficient and impact sensitivity; S3: Access the meteorological database to obtain the ultraviolet intensity and daily temperature difference at the target location; use a spatial interpolation algorithm to deduce the stacking position weight, execute the ghosting superposition formula, and generate an environmental aging feature map; S4: Deploy a multi-scale feature comparison engine to jointly analyze the watermark pattern, the closing seam, and the hole; set a dynamic threshold to trigger an anti-counterfeiting alarm, and support mobile terminal image hash value comparison and verification.

[0015] Beneficial effects: By introducing advanced information technology and image recognition technology, the present invention significantly improves the accuracy and reliability of anti-counterfeiting verification. First, the ability to dynamically monitor the flow of goods in the supply chain and their environmental parameters ensures that the anti-counterfeiting mechanism can adapt to changes in actual application scenarios, reducing the misjudgment rate caused by logistics complexity and environmental factors. Second, the progress of image recognition technology makes it possible to capture subtle structural feature changes in product packaging, further improving the accuracy of anti-counterfeiting verification. By monitoring and analyzing data throughout all links of the supply chain, not only is the misjudgment caused by physical damage or environmental factors reduced, but also the transparency and traceability of the product throughout the process from production to delivery are enhanced. Ultimately, this will enhance consumer trust, ensure product quality and safety, and provide more reliable anti-counterfeiting protection for the brand. In addition, the real-time data feedback mechanism can help enterprises quickly respond to potential problems, optimize supply chain management, and improve operational efficiency. Overall, the present invention not only solves the limitations of traditional anti-counterfeiting means, but also brings a more secure, transparent, and efficient supply chain experience to enterprises and consumers. Description of the Drawings

[0016] Figure 1 It is a schematic structural diagram of the anti-counterfeiting identification and monitoring system based on the morphology of shrink film using machine vision according to the present invention; Figure 2 It is a flowchart of the anti-counterfeiting identification and monitoring method based on the morphology of shrink film using machine vision according to the present invention. Detailed Embodiments

[0017] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0018] Embodiment 1: An anti-counterfeiting identification and monitoring system based on the morphology of shrink film by machine vision, as Figure 1 shown, includes: Reference feature acquisition module: Obtain three morphological features of the shrink film after the product is packaged, namely watermark pattern, closing seam, and hole; based on the three morphological features, take a photo record and use the three morphological features as the standard reference of the reference image. Transport damage simulation module: Obtain the product transport route of the product from the production line to the hands of consumers, record the key nodes in the product transport route process, and the key nodes include the transport route condition and the product's exposure time outside; based on the transport route condition and the product's exposure time outside, use the watermark pattern change formula to calculate the first change image of the watermark pattern; the first change image refers to the change in the watermark pattern compared with the factory state due to the loss caused by handling collisions or exposure during the product transport process. Environmental damage modeling module: Based on the first change image, obtain the local solar radiation intensity parameter based on the final geographical location of the product, and use the ghost overlay formula to calculate the second change image of the watermark pattern; the second change image is used for anti-counterfeiting identification and verification of the product. Anti-counterfeiting verification decision module: Based on the reference image, the first change image, and the second change image, and combined with the morphological changes of the closing seam and the morphological changes of the hole, obtain the anti-counterfeiting identification result.

[0019] The reference feature acquisition module includes: Obtain the grayscale image matrix data of the original watermark pattern before printing and the grayscale image matrix data of the watermark pattern after printing; use the reference ghost coefficient formula to calculate the reference ghost coefficient of the watermark pattern.

[0020] For further explanation, grayscale images of the pre - printed design draft and the post - printed shrink film are collected by a high - resolution industrial camera under standardized lighting conditions. After alignment by an image registration algorithm, pixel - level spatial consistency is ensured. The reference ghosting coefficient B normalizes the process error to a scalar in the range of [0, 1] through the mean of pixel absolute differences, providing an initial state reference for subsequent transportation / environmental damage modeling; eliminating the interference of inherent equipment errors, so that the damage simulation only focuses on the effects of external factors. When collecting the watermark pattern, closing seam, and hole features after shrink film packaging, attention is paid to the randomness of the watermark pattern, closing seam, and hole features. During shrinkage, the shape of the closing seam, the attachment position of the watermark, and the size of the stretching and punching positions are all random. A high - resolution camera is used to capture the random differences, and when calculating the reference ghosting coefficient, the random changes of the post - printed watermark are included to comprehensively reflect the randomness of the initial state of the shrink film.

[0021] The reference ghosting coefficient of the watermark pattern is calculated using the reference ghosting coefficient formula, including: The reference ghosting coefficient formula is as follows. Where, is the reference ghosting coefficient, is the grayscale image matrix of the original watermark pattern; is the ghosting convolution kernel; is the convolution operation; is the total number of image pixels; is the pixel point.

[0022] For further explanation, the formula for normalizing the grayscale image matrix of the original watermark pattern to [0, 1] is, , and the normalization formula is a well - known technology to those skilled in the art, so the following normalization formula will not be separately explained; The normalized grayscale matrix of the original watermark pattern (range 0, 1) represents the pixel values in the ideal printing state. is the Difference of Gaussian convolution kernel (DoG kernel), defined as , where is the Gaussian kernel with standard deviation < ; Simulating ink diffusion (wide Gaussian kernel ) and edge blurring caused by equipment mechanical vibration (narrow Gaussian kernel ) during the printing process, comprehensively characterizing the material properties and process errors. Performing a convolution operation on the original watermark image to generate a theoretically "post - process - damaged" watermark image, reflecting the inherent defects of the printing process. is used for the sum of normalized absolute differences to ensure that the reference ghosting coefficient is a dimensionless scalar (range 0, 1). By calculating , Quantify the combined effects of material properties (such as ink penetration) and equipment errors (such as overprint offset) during the printing process to provide a benchmark for subsequent transportation / environmental damage modeling. Compress the image difference into a single scalar to facilitate linkage with dynamic damage models (such as photochemical fading, mechanical shock), and avoid multi-factor coupling interference. Gaussian difference kernel The parameters of ( , ) can be adapted to different printing equipment through calibration experiments.

[0023] Transport damage simulation module, including: Based on the reference ghosting coefficient, obtain the transportation route conditions, and the transportation route conditions are specifically the road flatness, the driver's driving level, and the types of accidents on the transportation route; At the same time, obtain the duration of the product's external exposure, and the exposure duration is specifically the duration of the product's watermark pattern exposed to natural light; Based on the reference ghosting coefficient, the transportation route conditions, and the duration of the product's external exposure, use the watermark pattern change formula to calculate the first change image of the watermark pattern.

[0024] For further explanation, the road flatness (R, vibration spectrum energy normalization), driving level (D, rapid acceleration and deceleration frequency score), and accident type (A, sudden stop / collision event classification) are collected in real time through in-vehicle IoT sensors (triaxial accelerometer + GPS), and the data is normalized to the [0,1] interval. Based on the spatio-temporal matching of the photosensitive sensor and the transportation trajectory, the light exposure period of the watermark area is located, and the cumulative effective radiation duration T (hours) is calculated. After separating the process error by the reference ghosting coefficient B, R, D, and A quantify mechanical shock, and T×S (solar radiation intensity) quantifies photochemical damage, realizing multi-factor independent modeling; through a logical function ( ) dynamically adjusts the contribution of the ghosting coefficient B to match the non-linear superposition characteristics of actual damage. The randomness of shrink film wrapping makes transportation damage more complex. Different products have different initial forms, and under the same transportation conditions, the watermarks are differently affected by mechanical shock and photochemical damage. When collecting parameters and calculating the change image, combined with the random characteristics of the shrink film, the ghosting coefficient is adjusted through a logical function to make the result more in line with the actual situation.

[0025] Based on the reference ghosting coefficient, the transportation route conditions, and the duration of the product's external exposure, use the watermark pattern change formula to calculate the first change image of the watermark pattern, including: The watermark pattern change formula is as follows, Among them, is the watermark gray value after transportation; is the original watermark gray value; is the material photosensitive coefficient; is the exposure duration; is the solar radiation intensity; is the reference ghosting coefficient; is the transportation shock sensitivity coefficient; is the road surface evenness; is the driving level score; is the accident shock equivalent; is the random noise term .

[0026] For further explanation, : the gray value of the original watermark pixel, and the gray value of the original watermark pixel is normalized to represent the ideal state. : the photosensitivity coefficient of the material (m² / kW·h), and the light sensitivity is measured experimentally. T and S are the exposure duration (hours) and solar radiation intensity (kW / m²), respectively, to quantify the light exposure. B: the reference ghosting coefficient, and the reference ghosting coefficient is normalized to separate the inherent errors of the printing process. : calibrate the mechanical damage weight. 、 、 : normalize the transportation parameters, corresponding to the road surface evenness, driving level score, and accident shock equivalent respectively. : random noise, simulating environmental disturbances. The exponential term describes the light fading, and the logical function term correlates the shock and process errors, simulating edge blurring. Through 、 calibrate to adapt to different materials and transportation scenarios. The reference coefficient excludes the interference of printing defects and improves the accuracy of damage determination. After a certain packaging film (λ = 0.05, k = 2.0) is transported: Parameters: T = 8h, S = 1.2kW / m2, R = 0.6, D = 0.3, A = 0.1, B = 0.2. Calculation: The light damage retention rate is 62%, and the mechanical damage contribution is 0.18 (logical function term). Result: The original gray level drops from 0.8 to 0.67, and a deviation > 5% triggers an alarm.

[0027] The environmental damage modeling module includes: Based on the sunlight irradiation situation in the region where the consumer is located, extract the ultraviolet irradiation data and the day-night temperature difference data; based on the ultraviolet irradiation data and the day-night temperature difference data, calculate the second change image of the watermark pattern using the ghosting superposition formula.

[0028] For further explanation, extract the annual average ultraviolet intensity (UVI) and the daily average temperature difference (ΔT) of the target region through the meteorological database API, combine the Internet of Things temperature and humidity sensors to locate the product stacking position, and obtain the local microenvironment correction amount ( , ). The synergistic effect of ultraviolet light (photooxidation) and temperature difference (thermal expansion and contraction) leads to non-linear aging of the watermark material, and it is necessary to quantify its cumulative damage; the ghosting superposition formula ( ), which fuses batch sampling data ( , ), and geographical location interpolation ( ), solves the problems of regional climate differences and uneven local exposure. Predict the fading / cracking pattern of the watermark to support anti-counterfeiting verification across climate zones. The random shape of the shrink film causes different parts of the product to be affected differently by ultraviolet light and temperature difference. When extracting environmental data and calculating the change image, consider the local differences brought by the randomness of wrapping. When determining the position weight, take into account the random distribution of shrink film characteristics to make the environmental damage modeling more accurate.

[0029] Calculate the second change image of the watermark pattern using the ghosting superposition formula, including: the ghosting superposition formula is as follows, where, is the total environmental damage value of the th product; , is the ultraviolet dose and temperature difference data of the th sampled product within the batch, = 1, 2,..., , where, ≪N1, is the number of sampled products within the batch, and N1 is the total batch quantity; is the position weight of the th product; is the local environment correction amount of the th product.

[0030] For further explanation, , : The ultraviolet dose (UVI·h) and daily average temperature difference (°C) of the th sampled product within the batch. The data acquisition cost is reduced by sparse sampling (M≪N). : The position weight of the nth product, and the position weight is normalized, which is determined by the transportation stacking position (such as the outer layer exposure weight is 0.9 and the inner layer is 0.3). , : The local ultraviolet intensity and temperature difference correction amount calculated based on the interpolation of the final geographical location of the product, which solves the regional climate difference. The batch sampling term (∑ ) uses the statistical law of batch data to reduce the full-scale monitoring cost; the local correction term ( ) refines the individual exposure difference through spatial interpolation to improve the model accuracy. Environmental damage quantification: The formula outputs as the environmental damage value and inputs it into the watermark pattern change formula ( ), the co-evolution of the driving photochemical aging term ( ), and the mechanical damage term. The reference ghosting coefficient After separating the printing defects, Focus on quantifying the effects of the external environment and avoid cross-interference. Example: Randomly sample M = 50 products from a batch (N = 1000), and measure the average = 12. The nth product is located on the outer layer ( = 0.9), and by interpolation, = 15, = 10°C. Calculate: = 12 + 0.9×15×10 = 147. Application: Input it into the watermark change formula, which drives the gray value of this product to decrease by an additional 10%. After superimposing with the reference ghosting coefficient = 0.1, the total damage reaches 20%, exceeding the threshold to trigger an alarm.

[0031] The anti-counterfeiting verification decision module includes: Using the watermark pattern features in the reference image, the first change image, and the second change image as the first comparison feature sequence; Using the closing seam features in the reference image and the closing seam shape change image as the second comparison feature sequence; Using the hole features in the reference image and the hole shape change image as the third comparison feature sequence; Extract the images with similarity lower than the preset threshold in the three comparison feature sequences as the final comparison images for anti-counterfeiting verification at the consumer end.

[0032] For further illustration, a multi-dimensional anti-counterfeiting verification system is constructed through independent comparison sequences of three groups of features (multi-modal), namely watermark pattern, closing seam, and holes. The variation laws of each type of feature are driven by different physical mechanisms (photo-chemical aging, mechanical deformation, material cracking), making it difficult for counterfeiters to synchronously reproduce the true degradation trajectories of all features. The joint analysis of multiple features significantly increases the cost of counterfeiting, and single-feature imitation cannot pass the verification; dynamic threshold determination: a preset similarity threshold (such as SSIM < 0.85) adapts to different environmental damage intensities, reducing the false positive rate; only significant difference images are shown to consumers, simplifying the verification logic and supporting fast comparison on mobile devices. Example, anti-counterfeiting verification of a liquor package: watermark pattern sequence: the reference watermark is clear, and it fades due to light exposure after transportation (similarity 0.72), while the counterfeit has no fading (similarity 0.95); closing seam sequence: the closing seam of the genuine product is deformed due to vibration (similarity 0.68), while the counterfeit has a perfect shape (similarity 0.98); hole sequence: the edges of the holes of the genuine product are cracked (similarity 0.65), while the counterfeit has no cracking (similarity 0.99). Judgment: Only when the similarities of the three groups of the genuine product are all lower than the threshold (0.85), the "genuine product" is confirmed. When constructing the anti-counterfeiting verification system, the randomness of shrink film wrapping is the key to distinguishing authenticity. It is difficult for counterfeiters to replicate random features and their variation laws. When setting the threshold and extracting comparison images, the random morphology and changes are emphasized. Images that cannot reflect the changes of this characteristic are more likely to be counterfeits.

[0033] Extract the images with similarities lower than the preset threshold in the three comparison feature sequences as the final comparison images for anti-counterfeiting verification at the consumer end, including: The similarity threshold refers to a quantitative index of image difference calculated by a feature extraction algorithm. When the similarity is lower than the preset threshold, it is determined as a valid comparison image.

[0034] For further illustration, the similarity threshold calculates the structural and texture differences of the key regions of the image based on feature extraction algorithms (such as SIFT, CNN), and commonly uses SSIM (structural similarity index) or cosine distance of feature vectors for quantification. The preset threshold is calibrated through experiments: collect genuine damage samples and counterfeit samples, and select the best cut-off point (such as the optimal point of the ROC curve) after statistically analyzing the data distributions of the two types. When the similarity is lower than the threshold (such as SSIM < 0.8), it indicates that the damage conforms to the expected physical degradation law and is determined as valid; higher than the threshold is regarded as abnormal (such as no damage or artificial counterfeiting).

[0035] Example 2: On the basis of Example 1, as Figure 2 shown, an anti-counterfeiting identification and monitoring method based on the morphology of shrink film by machine vision includes: S1: Use a high-resolution industrial camera to shoot the original form of the shrink film watermark pattern, seam, and hole at multiple angles, and align the feature areas through the image registration algorithm; extract the watermark grayscale matrix, construct the Gaussian difference convolution kernel, perform the convolution operation, and calculate the reference ghosting coefficient to achieve the quantification of printing process errors; S2: Integrate GPS and IoT sensors to collect transportation parameters; establish a multi-factor damage model, and dynamically generate watermark degradation images after transportation through photosensitivity coefficient and impact sensitivity; S3: Access the meteorological database to obtain the target area's ultraviolet intensity and daily temperature difference; use the spatial interpolation algorithm to calculate the stacking position weight, execute the ghost superposition formula, and generate an environmental aging characteristic map; S4: Deploy a multi-scale feature comparison engine to conduct joint analysis of watermark patterns, seams, and holes; set dynamic thresholds to trigger anti-counterfeiting alarms, and support mobile image hash value comparison and verification.

[0036] The above is a detailed introduction to the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An anti-counterfeiting identification and monitoring system based on machine vision shrink film morphology, characterized in that: include: Benchmark feature acquisition module: obtains three morphological features of the shrink film after product packaging, namely watermark pattern, closing seam, and hole; Based on the three morphological features, taking photos and recording, and using the three morphological features as standard references for the benchmark image; Transportation damage simulation module: obtains the product transportation route from the production line to the hands of consumers, and records the key nodes in the product transportation route, including the transportation route status and the length of time the product is exposed outside; Based on the transportation route conditions and the time the product is exposed outside, a first change image of the watermark pattern is calculated using a watermark pattern change formula; the first change image refers to the change of the watermark pattern compared with the factory state due to the loss caused by handling bumps or exposure of the product during transportation; Environmental damage modeling module: based on the first change image, local solar radiation intensity parameters are obtained based on the final geographical location of the product, and a second change image of the watermark pattern is calculated using a ghosting superposition formula; the second change image is used for product anti-counterfeiting identification and verification; Anti-counterfeiting verification decision module: based on the reference image, the first change image, the second change image, combined with the shape change of the closing seam and the shape change of the hole, the anti-counterfeiting identification result is obtained.

2. The anti-counterfeiting identification and monitoring system based on machine vision shrink film morphology according to claim 1 is characterized in that: The reference feature acquisition module comprises: Obtain grayscale image matrix data of the original watermark pattern before printing and grayscale image matrix data of the watermark pattern after printing; calculate the reference ghosting coefficient of the watermark pattern using the reference ghosting coefficient formula.

3. The anti-counterfeiting identification and monitoring system based on machine vision shrink film morphology according to claim 2 is characterized in that: The method of calculating the reference ghosting coefficient of the watermark pattern by using the reference ghosting coefficient formula includes: the reference ghosting coefficient formula is as follows: in, is the reference ghosting coefficient, is the grayscale image matrix of the original watermark pattern; is the ghost convolution kernel; is the convolution operation; is the total number of image pixels; For pixels.

4. The anti-counterfeiting identification and monitoring system based on machine vision shrink film morphology according to claim 1 is characterized in that: The transport damage simulation module includes: Based on the reference ghosting coefficient, the transportation route condition is obtained, and the transportation route condition specifically includes road flatness, driving level of the driver, and the type of accident on the transportation route; At the same time, the exposure time of the product is obtained, and the exposure time is specifically the time when the watermark pattern of the product is exposed to natural light; Based on the reference ghosting coefficient, the transportation route conditions, and the length of time the product is exposed outdoors, a watermark pattern variation formula is used to calculate a first variation image of the watermark pattern.

5. The anti-counterfeiting identification and monitoring system based on machine vision shrink film morphology according to claim 4 is characterized in that: The first change image of the watermark pattern is calculated based on the reference ghosting coefficient, the transportation route conditions, and the exposure time of the product, using the watermark pattern change formula, including: the watermark pattern change formula is as follows, in, is the gray value of the watermark after transportation; is the original watermark grayscale value; is the photosensitivity coefficient of the material; The duration of nudity; is the solar radiation intensity; is the base ghosting coefficient; is the transport shock sensitivity coefficient; The road smoothness; Score driving proficiency; is the accident impact equivalent; is the random noise term .

6. The anti-counterfeiting identification and monitoring system based on machine vision shrink film morphology according to claim 1 is characterized in that: The environmental damage modeling module comprises: Based on the sunlight exposure conditions in the area where the consumer is located, ultraviolet radiation data and day and night temperature difference data are extracted; based on the ultraviolet radiation data and day and night temperature difference data, a second change image of the watermark pattern is calculated using a ghosting superposition formula.

7. The anti-counterfeiting identification and monitoring system based on machine vision shrink film morphology according to claim 6 is characterized in that: The method of calculating the second changed image of the watermark pattern by using the ghost superposition formula includes: the ghost superposition formula is as follows: in, For the Total environmental damage value of a product; , For the batch UV dose and temperature difference data of sampled products, =1,2,……, ,in, ≪N1, is the number of sampled products in the batch, and N1 is the total amount of the batch; For the The position weight of each product; For the The local environmental correction for a product.

8. The anti-counterfeiting identification and monitoring system based on machine vision shrink film morphology according to claim 1 is characterized in that: The anti-counterfeiting verification decision module includes: Using the watermark pattern features in the reference image, the first changed image, and the second changed image as a first comparison feature sequence; Using the seam features in the reference image and the seam morphology change image as a second comparison feature sequence; Using hole features in the reference image and the hole morphology change image as a third comparison feature sequence; The images with similarity lower than the preset threshold in the three comparison feature sequences are extracted as the final comparison images for anti-counterfeiting verification on the consumer side.

9. The anti-counterfeiting identification and monitoring system based on machine vision shrink film morphology according to claim 8 is characterized in that: The step of extracting an image whose similarity is lower than a preset threshold value from three comparison feature sequences as a final comparison image for anti-counterfeiting verification at the consumer end includes: The similarity threshold refers to a quantitative index of image difference calculated by a feature extraction algorithm. When the similarity is lower than a preset threshold, it is determined to be a valid comparison image.

10. An anti-counterfeiting identification and monitoring method based on machine vision shrink film morphology, used in an anti-counterfeiting identification and monitoring system based on machine vision shrink film morphology according to any one of claims 1 to 9, characterized in that: include: S1: Use a high-resolution industrial camera to shoot the original forms of shrink film watermark patterns, seams, and holes at multiple angles, and align feature areas through image registration algorithms; Extract the watermark grayscale matrix, construct the Gaussian difference convolution kernel, calculate the reference ghosting coefficient after performing the convolution operation, and realize the quantification of printing process errors; S2: Integrate GPS and IoT sensors to collect transportation parameters; establish a multi-factor damage model, and dynamically generate watermark degradation images after transportation through photosensitivity coefficient and impact sensitivity; S3: Access the meteorological database to obtain the target area's ultraviolet intensity and daily temperature difference; use the spatial interpolation algorithm to calculate the stacking position weight, execute the ghost superposition formula, and generate an environmental aging characteristic map; S4: Deploy a multi-scale feature comparison engine to conduct joint analysis of watermark patterns, seams, and holes; set dynamic thresholds to trigger anti-counterfeiting alarms, and support mobile image hash value comparison and verification.

Images