Cork anti-counterfeiting identification method, server and storage medium

Abstract

This invention provides a method, server, and storage medium for anti-counterfeiting identification of corks. First, a cork image is acquired. Then, character codes are extracted from the cork image, and the original texture image of the cork is retrieved from a database based on these character codes. Next, the cork outline in the cork image is identified to determine the compression state of the cork. Finally, the anti-counterfeiting identification result of the cork is determined based on the cork image, the original texture image, and the compression state. By matching the cork image taken by the user with the original texture image stored in the database, and combining this with the compression state of the cork after it has been opened, the matching process is completed, avoiding misidentification caused by cork deformation and effectively improving the accuracy of anti-counterfeiting identification of corks.

Description

Technical Field

[0001] This invention belongs to the field of image recognition technology, and in particular relates to a method for anti-counterfeiting identification of corks, a server, and a storage medium. Background Technology

[0002] In recent years, wine, as a healthy and fashionable beverage, has become a staple on most people's tables. However, this has also brought with it a problem of widespread counterfeiting. While professionals can distinguish genuine wine from fakes through tasting and observation, the average person lacks the necessary knowledge and struggles to easily identify genuine wines.

[0003] In existing technologies, anti-counterfeiting marks are usually printed on wine bottles or packaging boxes to verify authenticity. However, many counterfeit products are made using purchased empty wine bottles and boxes, so printing anti-counterfeiting marks is not secure. In view of this, a cork anti-counterfeiting method has also been proposed in existing technologies.

[0004] Natural cork, with its soft and elastic properties, seals bottle necks well without completely isolating them from air, making it widely used as stoppers for wine bottles. Natural cork is covered with natural pores and fissures, much like a fingerprint, making it irreplaceable and impossible to counterfeit. Furthermore, cork is damaged during opening, preventing counterfeiters from repeatedly using existing anti-counterfeiting technologies that rely on identifying anti-counterfeiting codes on the cork. While simple, this method suffers from lower accuracy due to the deformation of the cork after use, easily leading to misidentification of genuine products as counterfeits. Summary of the Invention

[0005] In view of this, the present invention provides a method, server and storage medium for anti-counterfeiting identification of corks, aiming to solve the problem of low accuracy of anti-counterfeiting identification of corks in the prior art.

[0006] A first aspect of this invention provides a method for anti-counterfeiting identification of corks, comprising:

[0007] Obtain cork image;

[0008] Extract character codes from the cork image and retrieve the original texture image of the cork from the database based on the character codes;

[0009] The cork outline in the cork image is identified to determine the compression state of the cork;

[0010] Based on the cork image, the original texture image, and the compression status, the anti-counterfeiting identification result of the cork is determined.

[0011] A second aspect of the present invention provides a wine cork anti-counterfeiting identification device, comprising:

[0012] The acquisition module is used to acquire cork images;

[0013] The extraction module is used to extract character codes from cork images and retrieve the original texture image of the cork from the database based on the character codes.

[0014] The recognition module is used to identify the cork outline in the cork image and determine the compression state of the cork.

[0015] The determination module is used to determine the anti-counterfeiting identification result of the cork based on the cork image, the original texture image, and the compression state.

[0016] A third aspect of the present invention provides a server, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the cork anti-counterfeiting identification method of the first aspect above.

[0017] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the cork anti-counterfeiting identification method of the first aspect above.

[0018] The cork anti-counterfeiting identification method, server, and storage medium provided in this invention first acquire a cork image; then, character codes are extracted from the cork image, and the original texture image of the cork is retrieved from the database based on the character codes; next, the cork outline in the cork image is identified to determine the compression state of the cork; finally, the anti-counterfeiting identification result of the cork is determined based on the cork image, the original texture image, and the compression state. By matching the cork image taken by the user with the original texture image stored in the database, and combining the compression state of the cork after it has been opened, the matching process is completed, avoiding misidentification caused by cork deformation, and effectively improving the accuracy of cork anti-counterfeiting identification. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is an application scenario diagram of the cork anti-counterfeiting identification method provided in the embodiments of the present invention;

[0021] Figure 2 This is a flowchart illustrating the implementation of the cork anti-counterfeiting identification method provided in this embodiment of the invention.

[0022] Figure 3 This is a schematic diagram of the structure of the anti-counterfeiting identification device for red wine corks provided in an embodiment of the present invention;

[0023] Figure 4 This is a schematic diagram of the server structure provided in an embodiment of the present invention. Detailed Implementation

[0024] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0025] Figure 1 This is an application scenario diagram of the cork anti-counterfeiting identification method provided in an embodiment of the present invention. For example... Figure 1 As shown, in some embodiments, the cork anti-counterfeiting identification method provided by the present invention can be applied to, but is not limited to, this application scenario. In this embodiment of the invention, the system includes: a user terminal 11 and a server 12.

[0026] The user terminal can be a mobile phone, tablet or other device, and the server 12 can be a physical server or a cloud server, which is not limited here.

[0027] The user sends a corresponding anti-counterfeiting identification request to the server 12 through the user terminal 11. After the server 12 responds to the anti-counterfeiting identification request, the user uses the user terminal 11 to take a picture of the cork at a specific shooting angle and then sends it to the server 12. The server 12 matches the cork image with the corresponding original image stored in the database to determine the anti-counterfeiting identification result and sends it to the user terminal 11 to complete the anti-counterfeiting identification.

[0028] Figure 2 This is a flowchart illustrating the implementation of the cork anti-counterfeiting identification method provided in this embodiment of the invention. Figure 2 As shown, in some embodiments, the cork anti-counterfeiting identification method is applied to... Figure 1 The server 12 shown includes:

[0029] S210, Obtain the cork image.

[0030] In this embodiment of the invention, the obtained cork images can be one or more, and generally the cork can be photographed from multiple different angles.

[0031] S220: Extract the character codes from the cork image and retrieve the original texture image of the cork from the database based on the character codes.

[0032] In this embodiment of the invention, the top or side of the cork is often printed with corresponding character codes, winery icons and other information. The character codes can be used to quickly perform a preliminary search in the database to determine the original texture images with the same codes, that is, the images taken from various angles before the cork was embedded in the wine bottle.

[0033] S230, Identify the cork outline in the cork image to determine the compression state of the cork.

[0034] The diameter of a cork is generally slightly larger than the inner diameter of the bottle neck. Therefore, after the cork is inserted into the bottle neck, it will be compressed by the neck. Although cork has good elasticity, it will still deform after compression. Typically, after being pulled out, a cork will return to 4 / 5 of its original volume, and it will take 24 hours to fully return to its original volume. Before the cork fully recovers, the deformation caused by compression will have a certain impact on anti-counterfeiting identification; therefore, the compression state of the cork needs to be considered.

[0035] In this embodiment of the invention, the contour curve of the cork image can be extracted and compared with the contour curve of the cork in the original texture image to determine the compression state of the cork.

[0036] S240, determine the anti-counterfeiting identification result of the cork based on the cork image, the original texture image, and the compression state.

[0037] In this embodiment of the invention, by matching the cork image taken by the user with the original texture image stored in the database, the matching process is completed by combining the compression state of the cork after it is opened, thus avoiding misidentification caused by cork deformation and effectively improving the accuracy of cork anti-counterfeiting identification.

[0038] In some embodiments, S230 may include: identifying the cork outline in the cork image to obtain the current outline size of the cork; and determining the compression state of the cork based on the current outline size.

[0039] In this embodiment of the invention, the current contour size can be the contour width. When the captured cork image is a side view, the contour is rectangular. The width of the rectangle (i.e., the shorter side of the rectangle) can be detected and compared with the contour width recorded in the database to determine the compression state of the cork. For example, if the contour width of the side view image captured by the user is 22mm, while the contour width recorded in the database is 24mm, and the bottle mouth diameter is generally 20mm (assuming 20mm represents 100% compression), then the compression state of the cork is (24-22) / (24-20) = 50%.

[0040] In this case, due to the varying shooting distances of users, it is difficult to directly identify the outline width of the cork without any reference object. While the width of the cork changes when it is embedded, its length generally remains constant. Therefore, the length of the cork can be used as a reference. The aspect ratio of the photographed cork is 2:1, and the outline length recorded in the database is 44mm. Using this as a length reference, the outline width of the photographed cork is considered to be 22mm.

[0041] In this embodiment of the invention, the current profile dimension can also be the profile diameter. When the captured image of the cork is an image of the top surface of the cork, the diameter of the cork can be identified and compared with the cork diameter recorded in the database to determine the compression state. Similarly, the cork length can be used as a reference when identifying the cork diameter.

[0042] In some embodiments, S230 may include: identifying the cork outline in the cork image to obtain the current outline size and current outline curvature of the cork; and determining the compression state of the cork based on the current outline size and current outline curvature.

[0043] In this embodiment of the invention, due to the change in force when the cork is pulled out, the profile of the cork's side is approximately rectangular after being pulled out. However, the compression state of each cross-section (i.e., the cross-section perpendicular to the cork's side) is not entirely the same; that is, the long side of the cork's profile does not completely appear as a straight line, but has a small curvature. A straight line can be drawn between the two vertices of the long side of the profile. The portion of the long side of the profile that is concave relative to the straight line needs to have its compression state increased according to the curvature (e.g., increased from 50% to 51%), while the compression state of the convex portion is decreased.

[0044] The comparison between the cork image and the original texture image mainly involves comparing the natural gas pores and fissures in the image. These natural gas pores and fissures are often distributed at different cross-sections. Therefore, by calculating the compression state of each cross-section, each texture in the captured cork image is individually assigned a corresponding compression state, thereby effectively avoiding the impact of cork deformation on anti-counterfeiting identification.

[0045] In some embodiments, S240 may include: extracting at least one first feature texture from the original texture image and recording the position of each first feature texture on the cork; finding the second feature texture corresponding to each first feature texture in the cork image based on the position of each first feature texture; and determining the anti-counterfeiting identification result of the cork based on each first feature texture, the second feature texture corresponding to each first feature texture, and the compression state.

[0046] In this embodiment of the invention, a three-dimensional coordinate system can be established for the cork. Then, the coordinates of the center point of each feature texture in the three-dimensional coordinate system are used as the position of the first feature texture. After taking images of the cork from various angles, the server builds a simple three-dimensional model of the cork based on the images from each angle (wherein, the three-dimensional model is a cylinder with the positions of pores and cracks marked on it, but does not include actual image details). Then, based on the coordinates stored in the database, the server searches for the existence of a feature texture in the three-dimensional model according to a certain neighborhood range. If it exists, it is considered to be the second feature texture corresponding to the first feature texture.

[0047] In some embodiments, determining the anti-counterfeiting identification result of the cork based on each first feature texture, the second feature texture corresponding to each first feature texture, and the compression state includes: determining the similarity threshold corresponding to each second feature texture based on the compression state of the location of each second feature texture; comparing each second feature texture with its corresponding first feature texture to obtain the similarity of each second feature texture; adding the similarities of each second feature texture to obtain the total similarity of the cork image, and using it as the anti-counterfeiting identification result of the cork.

[0048] In this embodiment of the invention, when the cork is completely restored to its original volume, i.e., the compression state is 0%, a conventional similarity threshold, such as 0.9, can be used when comparing feature textures. That is, when the similarity is greater than 0.9, the first feature texture is considered to match its corresponding second feature texture. However, when the cork is not completely restored, the impact of the compression state on feature texture comparison needs to be considered, specifically by adjusting the similarity threshold. For example, when the compression state is 50%, the similarity threshold can be appropriately reduced, and when the similarity is greater than 0.8, the first feature texture is considered to match its corresponding second feature texture.

[0049] Optionally, a maximum similarity threshold and a minimum similarity threshold can be set, where the maximum similarity threshold corresponds to a compression state of 0%, the minimum similarity threshold corresponds to a compression state of 100%, and other compression states correspond to the intermediate values ​​of the maximum and minimum similarity thresholds, respectively.

[0050] In some embodiments, determining the anti-counterfeiting recognition result of the cork based on each first feature texture, the second feature texture corresponding to each first feature texture, and the compression state includes: inputting the first feature texture and the compression state of the original texture image into a pre-trained neural network model to predict the compressed third feature texture; and comparing the third feature texture with the second feature texture in the cork image to determine the anti-counterfeiting recognition result of the cork.

[0051] In this embodiment of the invention, since the changes in texture during compression are highly random, the self-learning characteristics of neural networks can be utilized to solve the recognition problem. A neural network model is used to predict the changes in the first feature texture after compression, and then compared with the second feature texture, thereby reducing the impact of cork deformation and effectively improving the recognition performance. The neural network model can be a feedforward neural network model, a convolutional neural network model, etc., and is not limited thereto.

[0052] In some embodiments, before inputting the cork image, the original texture image, and the compressed state into a pre-trained neural network model to obtain the anti-counterfeiting recognition result of the cork, the method may further include: acquiring multiple original textures and compressed textures in each compressed state during the compression and release process of each original texture; using the original textures and compressed states as inputs, and the compressed textures corresponding to the compressed states as inputs, to form a training set to train the neural network model.

[0053] In this embodiment of the invention, a compression test of the cork can be performed in advance (the cork after the test is unusable), and the changes in the feature texture of the cork can be captured in real time to train the neural network. The neural network possesses certain learning characteristics; after a certain number of tests to obtain training samples and train the neural network, it can self-learn to predict changes in feature texture. To reduce testing costs, scraps from cork manufacturing can be used for the compression test.

[0054] In some embodiments, S210 may include: acquiring an original captured image; determining the shooting angle of the original captured image; and determining a cork image based on the shooting angle and the original captured image.

[0055] In this embodiment of the invention, when a user takes a picture, the picture is often taken from a certain angle. In order to obtain the side and top images completely, it is necessary to first identify the shooting angle, and then process the picture taken by the user according to the shooting angle, so as to obtain the side and top images that are completely facing each other.

[0056] In summary, the beneficial effects of the present invention are as follows:

[0057] By matching the cork image taken by the user with the original texture image stored in the database, and taking into account the compression state of the cork after it has been opened, the matching process is completed, avoiding misidentification caused by cork deformation and effectively improving the accuracy of cork anti-counterfeiting identification.

[0058] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0059] Figure 3 This is a schematic diagram of the structure of the anti-counterfeiting identification device for red wine corks provided in an embodiment of the present invention. Figure 3 As shown, in some embodiments, the wine cork anti-counterfeiting identification device 3 includes:

[0060] Module 310 is used to acquire cork images;

[0061] Extraction module 320 is used to extract character codes from the cork image and retrieve the original texture image of the cork from the database based on the character codes;

[0062] The recognition module 330 is used to recognize the cork outline in the cork image and determine the compression state of the cork.

[0063] The determination module 340 is used to determine the anti-counterfeiting identification result of the cork based on the cork image, the original texture image, and the compression state.

[0064] Optionally, the recognition module 330 is specifically used to recognize the cork outline in the cork image to obtain the current outline size of the cork; and to determine the compression state of the cork based on the current outline size.

[0065] Optionally, the recognition module 330 is specifically used to recognize the cork outline in the cork image, obtain the current outline size and current outline curvature of the cork, and determine the compression state of the cork based on the current outline size and current outline curvature.

[0066] Optionally, a determining module is specifically used to extract at least one first feature texture from the original texture image and record the position of each first feature texture on the cork; based on the position of each first feature texture, find the second feature texture corresponding to each first feature texture in the cork image; and determine the anti-counterfeiting recognition result of the cork based on each first feature texture, the second feature texture corresponding to each first feature texture, and the compression state.

[0067] Optionally, the determining module 340 is specifically used to determine the similarity threshold corresponding to each second feature texture based on the compression state of the location of each second feature texture; compare each second feature texture with its corresponding first feature texture to obtain the similarity of each second feature texture; add the similarities of each second feature texture to obtain the total similarity of the cork image, and use it as the anti-counterfeiting recognition result of the cork.

[0068] Optionally, the determining module 340 is specifically used to input the first feature texture and the compressed state of the original texture image into a pre-trained neural network model to predict the compressed third feature texture; and to compare the third feature texture with the second feature texture in the cork image to determine the anti-counterfeiting recognition result of the cork.

[0069] Optionally, the wine cork anti-counterfeiting identification device 3 also includes a training module, which is used to acquire multiple original textures and compressed textures in each compressed state during the compression and release process of each original texture; the original textures and compressed states are used as inputs, and the compressed textures corresponding to the compressed states are used as inputs to form a training set to train the neural network model.

[0070] Optionally, the acquisition module 310 is specifically used to acquire the original captured image; determine the shooting angle of the original captured image; and determine the cork image based on the shooting angle and the original captured image.

[0071] The anti-counterfeiting identification device for red wine corks provided in this embodiment can be used to execute the above method embodiment. Its implementation principle and technical effect are similar, and will not be described again in this embodiment.

[0072] Figure 4 This is a schematic diagram of the server structure provided in an embodiment of the present invention. Figure 4 As shown, an embodiment of the present invention provides a server 4, which includes a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, it implements the steps in the various cork anti-counterfeiting identification method embodiments described above, for example... Figure 2 Steps 210 to 240 are shown. Alternatively, when processor 40 executes computer program 42, it implements the functions of each module / unit in the above system embodiments, for example... Figure 3 The functions of modules 310 to 340 are shown.

[0073] For example, computer program 42 may be divided into one or more modules / units, one or more of which are stored in memory 41 and executed by processor 40 to complete the present invention. One or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 42 in server 4.

[0074] Server 4 can be a terminal or a server. The terminal can be a mobile phone, MCU, ECU, etc., without limitation. The server can be a physical server, cloud server, etc., without limitation. Server 4 may include, but is not limited to, processor 40 and memory 41. Those skilled in the art will understand that... Figure 4This is merely an example of server 4 and does not constitute a limitation on server 4. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the terminal may also include input / output devices, network access devices, buses, etc.

[0075] The processor 40 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0076] The memory 41 can be an internal storage unit of the server 4, such as the hard drive or memory of the server 4. The memory 41 can also be an external storage device of the server 4, such as a plug-in hard drive, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the server 4. Furthermore, the memory 41 can include both internal storage units and external storage devices of the server 4. The memory 41 is used to store computer programs and other programs and data required by the terminal. The memory 41 can also be used to temporarily store data that has been output or will be output.

[0077] This invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the above-described cork anti-counterfeiting identification method embodiment.

[0078] A computer-readable storage medium stores a computer program 42. The computer program 42 includes program instructions. When executed by the processor 40, the program instructions implement all or part of the processes in the methods described in the above embodiments. The computer program 42 can also instruct related hardware to complete the process. The computer program 42 can be stored in a computer-readable storage medium. When executed by the processor 40, the computer program 42 can implement the steps of the various method embodiments described above. The computer program 42 includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0079] The computer-readable storage medium can be an internal storage unit of the terminal in any of the foregoing embodiments, such as the terminal's hard disk or memory. The computer-readable storage medium can also be an external storage device of the terminal, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the terminal. Furthermore, the computer-readable storage medium can include both internal storage units and external storage devices of the terminal. The computer-readable storage medium is used to store computer programs and other programs and data required by the terminal. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0080] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0081] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0082] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0083] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0084] In the embodiments provided by this invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0085] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0086] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0087] If an integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0088] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for identifying counterfeit corks, characterized in that, include: Obtain cork image; Extract the character codes from the cork image, and retrieve the original texture image of the cork from the database based on the character codes; The cork outline in the cork image is identified to determine the compression state of the cork; Based on the cork image, the original texture image, and the compression state, the anti-counterfeiting identification result of the cork is determined; The step of identifying the cork outline in the cork image and determining the compression state of the cork includes: The cork outline in the cork image is identified to obtain the current outline size of the cork; Based on the current profile dimensions, determine the compression state of the cork; Alternatively, the cork outline in the cork image can be identified to obtain the current outline size and current outline curvature of the cork; based on the current outline size and the current outline curvature, the compression state of the cork can be determined.

2. The cork anti-counterfeiting identification method according to claim 1, characterized in that, The step of determining the anti-counterfeiting identification result of the cork based on the cork image, the original texture image, and the compression state includes: Extract at least one first feature texture from the original texture image and record the position of each first feature texture on the cork; Based on the position of each first feature texture, find the second feature texture corresponding to each first feature texture in the cork image; The anti-counterfeiting identification result of the cork is determined based on each first feature texture, the second feature texture corresponding to each first feature texture, and the compression state.

3. The cork anti-counterfeiting identification method according to claim 2, characterized in that, The step of determining the anti-counterfeiting identification result of the cork based on each first feature texture, the second feature texture corresponding to each first feature texture, and the compression state includes: Based on the compression state of each second feature texture, determine the similarity threshold corresponding to each second feature texture; Each second feature texture is compared with its corresponding first feature texture to obtain the similarity of each second feature texture; The similarity scores of each second feature texture are summed to obtain the total similarity score of the cork image, which is then used as the anti-counterfeiting recognition result of the cork.

4. The cork anti-counterfeiting identification method according to claim 2, characterized in that, Based on each first feature texture, the corresponding second feature texture, and the compression state, the anti-counterfeiting identification result of the cork is determined, including: The first feature texture of the original texture image and the compression state are input into a pre-trained neural network model to predict the compressed third feature texture. The third feature texture is compared with the second feature texture in the cork image to determine the anti-counterfeiting identification result of the cork.

5. The cork anti-counterfeiting identification method according to claim 4, characterized in that, Before inputting the cork image, the original texture image, and the compressed state into a pre-trained neural network model to obtain the anti-counterfeiting recognition result of the cork, the method further includes: Acquire multiple original textures and the compressed texture in each compressed state during the compression and release process of each original texture; The original texture and the compressed state are used as inputs, and the compressed texture corresponding to the compressed state is used as input to form a training set to train the neural network model.

6. The method for anti-counterfeiting identification of corks according to any one of claims 1-5, characterized in that, The acquisition of the cork image includes: Acquire the original captured image; Determine the shooting angle of the original captured image; The cork image is determined based on the shooting angle and the original captured image.

7. A server comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the cork anti-counterfeiting identification method as described in any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the cork anti-counterfeiting identification method as described in any one of claims 1 to 6.

Images