CN108898127B - Anti-counterfeiting method and device based on three-dimensional model matching - Google Patents
Anti-counterfeiting method and device based on three-dimensional model matching Download PDFInfo
- Publication number
- CN108898127B CN108898127B CN201810760619.0A CN201810760619A CN108898127B CN 108898127 B CN108898127 B CN 108898127B CN 201810760619 A CN201810760619 A CN 201810760619A CN 108898127 B CN108898127 B CN 108898127B
- Authority
- CN
- China
- Prior art keywords
- dimensional model
- digital
- dimensional
- article
- verified
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
- G06V20/653—Three-dimensional objects by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Evolutionary Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an anti-counterfeiting method and anti-counterfeiting equipment based on three-dimensional model matching, which comprise the following steps: scanning to obtain a digital three-dimensional model of a genuine object, and storing the digital three-dimensional model in a digital three-dimensional model information database; acquiring a digital three-dimensional model of an article to be verified; retrieving a three-dimensional model which is most matched with the three-dimensional model of the article to be verified from the digital three-dimensional model information database, and calculating the matching degree of the three-dimensional model; and judging whether the article to be verified is a genuine article according to whether the matching degree exceeds a certain threshold value. The method has the advantages of simple and easy operation, high accuracy, strong stability, low cost and difficult falsification of anti-counterfeiting information.
Description
Technical Field
The invention belongs to the technical field of anti-counterfeiting verification, and particularly relates to a method and equipment for performing anti-counterfeiting verification by comparing a digital three-dimensional model and applying a computer vision technology based on three-dimensional scanning of an article.
Background
The anti-counterfeiting technology commonly used at present is to store the description information, the production date, the production place, the name of a manufacturer, the website thereof, the article number and other information of a protected article into a bar code or a two-dimensional code. The consumer obtains the article information through scanning the code and logs in the anti-counterfeiting database of the article to compare. The method has low cost and is easy for large-scale production, but the bar code and the two-dimensional code label image are easily copied by lawbreakers, thereby limiting the anti-counterfeiting effect. Recently developed electronic tags do not use a visual means, but use an electronic device to store information about an article. The information can be transmitted to the identification system by electronic communication means such as Radio Frequency Identification (RFID) or Near Field Communication (NFC) (refer to patent CN 104281954A; CN 107590663A). And the identification system compares the acquired article information with the anti-counterfeiting database for verification. The non-contact data transmission mode can contain more information, and the storage medium is not printed on the outside in an unobtrusive mode and is not abraded or copied by illegal molecules. However, the electronic tag is expensive and is mostly used for source tracing and anti-counterfeiting of high-end products.
Although the above mentioned anti-counterfeit methods play a role in protecting the rights of consumers and manufacturers, the fatal defect is that the storage medium of the anti-counterfeit information is separated from the article itself. Generally, bar codes, two-dimensional codes and electronic labels are packaged on outer packages of articles, an anti-counterfeiting database only records basic description information of the articles, so that lawless persons can enjoy the basic description information, and a common counterfeiting means is to place counterfeit articles into packaging boxes used by original genuine articles. Usually, a consumer reads bar codes, two-dimensional codes and electronic label information in a genuine product packaging box, and then queries a background database to obtain commodity information, but the consumer is difficult to distinguish high-level counterfeit products from genuine products by using the commodity information. To solve the problem of exchanging the outer package, manufacturers may disable the device by opening the package once. However, this approach not only increases the cost of the product, but also is not conducive to diversion of the product because a buyer of one hand of the product cannot prove the authenticity of the product to a potential buyer of a second hand or even a plurality of future hands. Some people also think of the way of code-spraying the anti-counterfeit code of the commodity and integrally connecting the anti-counterfeit code with the commodity (refer to patent CN 104732409 a), but this intrusive method obviously destroys the original shape of the object, and is impossible to realize in some applications such as anti-counterfeit of artworks.
A rapidly developed three-dimensional scanning technique obtains spatial coordinates and texture information of an object surface by scanning the space, shape, structure, and color of an actual object. The digital three-dimensional model obtained through three-dimensional scanning can convert the three-dimensional information of the real object into a digital signal which can be directly processed by a computer, and a convenient and fast means is provided for digitalizing the real object. In the three-dimensional scanning process, the distance measurement sampling point on the surface of the original object can be smaller than 0.1 mm, and the distance measurement error of each point can be smaller than 0.1 mm. Such highly accurate shape information can be considered as a unique attribute of an article that is difficult to reproduce. Any highly simulated article is almost impossible to achieve with the original article with a geometric error of less than 0.1 mm at millions of sampling points. The patent (CN 104035988B) proposes to acquire a three-dimensional model of a ceramic artwork as identity information thereof by a three-dimensional scanner. However, in the implementation method described in the patent, the three-dimensional data information of the ceramic artwork to be verified can be marked on the outer package of the ceramic artwork and can also be printed on a product certificate. Although the three-dimensional data of the article is stored in the database, the query method still depends on the description information on the outer package of the article, and the problem that the characteristic information of the article is physically separated from the anti-counterfeiting authentication information on the outer package is not fundamentally solved.
The patent (CN 107505340 a) proposes scanning a ceramic artwork by X-ray and generating a three-dimensional image thereof, in order to determine whether the ceramic artwork to be identified is consistent with the target ceramic artwork in the database by comparing the three-dimensional image. However, this method compares structural features in three-dimensional images, rather than precisely comparing geometric dimensions, and thus is deficient in precision. And X-ray scanner belongs to professional equipment, and the price is expensive, and is bulky, and is inconvenient to carry, and X-ray scanner's operator needs to go through special training in order to avoid the injury that X-ray caused to the human body as far as possible, therefore X-ray scanner hardly popularizes in ordinary consumption.
Disclosure of Invention
In order to fundamentally solve the problem that anti-counterfeiting verification information exists on a physical medium outside an article and is easy to copy and tamper in the existing anti-counterfeiting method, the invention provides a brand-new anti-counterfeiting method which completely depends on the physical property of the article in the processes of acquisition, storage and query of anti-counterfeiting data and does not need to depend on anti-counterfeiting information such as bar codes, two-dimensional codes, electronic tags (RFID) and the like stored on external media such as certificates or packaging boxes and the like.
According to one aspect of the invention, an anti-counterfeiting method based on three-dimensional model matching is provided, which comprises the following steps:
scanning to obtain a digital three-dimensional model of a genuine object, and storing the digital three-dimensional model in a digital three-dimensional model information database;
acquiring a digital three-dimensional model of an article to be verified;
retrieving a three-dimensional model which is most matched with the three-dimensional model of the article to be verified from the digital three-dimensional model information database, and calculating the matching degree of the three-dimensional model;
and judging whether the article to be verified is a genuine article according to whether the matching degree exceeds a certain threshold value.
Preferably, the digital three-dimensional scanning comprises three-dimensional scanning of the appearance and/or internal geometry of the genuine object.
Preferably, the method further comprises:
and establishing an article information base, and storing the accessory information of the genuine articles, wherein the accessory information corresponds to the three-dimensional models of the genuine articles stored in the digital three-dimensional model information base one by one.
Preferably, after the scanning to obtain the digital three-dimensional model of the genuine object, the method further comprises:
calculating the characteristic vectors corresponding to the digital three-dimensional models, storing the characteristic vectors in a characteristic vector database, and corresponding to the three-dimensional models stored in a digital three-dimensional model information database one by one through a database technology.
Preferably, the calculation method of the feature vector is one of the following:
(1) expressing the two three-dimensional models by using a Zernike matrix or a spherical wavelet, and taking the coefficient of the Zernike matrix or the spherical wavelet as a characteristic vector;
(2) and using a spectral decomposition method to take the spectral decomposition coefficients of the two models as the feature vector.
Preferably, the feature vector is a set of real vectors for describing the overall or local features of the digitized three-dimensional model.
Preferably, the method for obtaining the digital three-dimensional model of the article to be verified is one of the following methods:
(1) three-dimensional scanning is carried out on the article to be verified by utilizing a three-dimensional scanner;
(2) the method comprises the steps that a binocular depth camera is used for shooting an article to be verified, and a digital three-dimensional model can be generated by processing distance information;
(3) and continuously photographing or shooting a section of video on the to-be-verified object by using a common monocular camera, and reconstructing a digital three-dimensional model by using a photogrammetric algorithm according to the corresponding relation of the overlapped part of the plurality of pictures and the camera projection geometric relation of each picture.
Preferably, the step of retrieving the three-dimensional model most matched with the three-dimensional model of the article to be verified in the digital three-dimensional model information database and calculating the matching degree thereof comprises the following steps:
(1) initializing, namely transforming the three-dimensional model in the digital three-dimensional model information database and the digital three-dimensional model of the object to be verified to a common reference coordinate system or directly taking one of the three-dimensional models as the reference coordinate system, and then carrying out initial registration on the two models in the transformed coordinate system;
(2) model registration, namely alternately estimating the corresponding relation of points between the two models and the current optimal coordinate transformation relation by using an iterative algorithm until the iteration error is smaller than a given threshold value or the iteration times reach a preset value;
(3) and calculating the similarity of the registered models as the matching degree.
Preferably, before retrieving the digital three-dimensional model information library, the method further comprises:
and acquiring a two-dimensional projection of the digital three-dimensional model of the article to be verified, judging the category of the article contained in the two-dimensional projection by using an object recognition algorithm in the image based on deep learning, and further scanning an article information base to filter out the three-dimensional model which does not belong to the category.
Preferably, after obtaining the best-matching digitized three-dimensional model, the method further comprises:
presenting the most matched digitized three-dimensional model through a visualization process;
zooming, rotating and moving the three-dimensional model by touching a screen, a mouse or a keyboard with a finger, and observing the object to be verified in a multi-angle, omnibearing and high-resolution manner;
and overlaying labels with different colors on the three-dimensional model to inform the same part and different parts of the object to be verified on the subdivided area.
According to another aspect of the present invention, there is also provided an anti-counterfeiting device based on three-dimensional model matching, including an anti-counterfeiting authentication server, the anti-counterfeiting authentication server including:
the digital three-dimensional model information database is used for storing a digital three-dimensional model of a genuine object;
the characteristic vector calculation module is used for calculating the characteristic vector of the digital three-dimensional model;
the characteristic vector database is used for storing the characteristic vectors of the digital three-dimensional model;
and the retrieval verification module is used for retrieving the three-dimensional model which is most matched with the three-dimensional model of the article to be verified in the digital three-dimensional model information database and calculating the matching degree of the three-dimensional model.
Preferably, the anti-counterfeit authentication server further comprises:
and the article information base is used for storing the accessory information of the genuine articles, and the accessory information corresponds to the three-dimensional models of the genuine articles stored in the digital three-dimensional model information base one by one.
Preferably, the device further comprises an authentication terminal, and the authentication terminal comprises:
the digital three-dimensional model acquisition module is used for acquiring a digital three-dimensional model of an article to be verified;
the verification interface is used for sending the digital three-dimensional model of the article to be verified to the retrieval verification module and receiving the digital three-dimensional model which is most matched and the article information corresponding to the digital three-dimensional model output by the anti-counterfeiting verification server;
the result display module is used for displaying the most matched three-dimensional model through a visualization process, zooming, rotating and moving the three-dimensional model through a finger touch screen, a mouse or a keyboard, and observing the to-be-verified object in a multi-angle, all-around and high-resolution mode; and overlaying labels with different colors on the three-dimensional model to inform the same part and different parts of the object to be verified on the subdivided area.
Preferably, the verification interface is a mobile phone interface, an internet interface or a terminal device query interface.
The invention has the advantages that: the invention does not need professional anti-counterfeiting equipment in the verification process, has simple and easy operation, high accuracy and strong stability, and has the advantages of low cost and difficult falsification of anti-counterfeiting information.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a schematic diagram illustrating the principle of three-dimensional scanning and related information entry after the production and manufacture of genuine products according to the present invention;
fig. 2 shows a schematic diagram of the principle of the present invention when the anti-counterfeit authentication of an article is required.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The invention utilizes a three-dimensional scanner to scan an article to construct a digital three-dimensional model (3D model) thereof. The digitized three-dimensional model refers in particular to a way of describing the actual object faithfully, completely, stereoscopically and digitally. By three-dimensional model is meant any object that can be represented in a point cloud, triangular mesh, polygon, or other manner, as well as its inherent properties, including geometric and texture information. The digitalized three-dimensional model digitizes the solid geometric information of the real object and the color texture information of the surface, and faithfully and completely reflects the appearance of the object and the information in the internal hollow structure (if any). In the process of obtaining the three-dimensional model of the article through three-dimensional scanning, the distance measurement sampling point on the surface of the original object can be smaller than 0.1 mm, and the distance measurement error of each point can be smaller than 0.1 mm. Such high precision information can be considered as a unique attribute of an article that is difficult to reproduce. Any highly simulated article is almost impossible to achieve if the geometric error of the original article is less than 0.1 mm at millions of sampling points.
Based on the thought, the invention provides a method for accurately comparing whether the digital three-dimensional model of the article to be verified in the three-dimensional coordinate system is consistent with the target digital three-dimensional model stored in the information database, and further determining whether the article to be verified is a genuine article. The method has the advantages of high anti-counterfeiting precision, difficult anti-counterfeiting information tampering and low cost.
The method of the invention comprises two processes: (A) after the production and manufacture of the article are finished, three-dimensional scanning is carried out on the article and relevant information is input; (B) when the anti-counterfeiting authentication of the article is required. The following describes the details of the two processes.
(A) When the article manufacturing process is completed, as shown in fig. 1, the following steps are performed:
and A1, after each article is manufactured to form a finished product, scanning the finished product by using a high-precision three-dimensional scanner to obtain a digital three-dimensional model. Each article is stored in the information repository in digitized form as a three-dimensional model. The accuracy of the digitized three-dimensional model should be such that perturbations caused by minor process variations in manual, semi-manual or industrial manufacturing can be distinguished. Note that three-dimensional scanning is not limited to scanning the appearance of the article, but may also capture geometric configuration information of hollow structural portions (if any) inside the article, thereby forming a more complete description of the article.
A2, other accessory information corresponding to the article in A1, such as the category of the article, the manufacturer, the production time, the production place and the price, etc. are stored in the article information base. The article attribute information may be one-to-one correspondence with the digitized three-dimensional models stored in the digitized three-dimensional model information repository using database techniques.
A3, corresponding to the digital three-dimensional model of the article in A1, and the feature vector module calculates the corresponding feature vector of each digital three-dimensional model. Generally, in order to speed up the retrieval of the digitized three-dimensional model in the digitized three-dimensional model information database, the three-dimensional model may be mapped to a feature space, and then a feature vector (shape descriptor) is defined in the space. The feature vectors are a set of real number vectors used to describe the global or local features of the digitized three-dimensional model. The description of the good feature vectors to the digital three-dimensional model should have sufficiency and necessity, that is, different digital three-dimensional models are required to correspond to different feature vectors, and different feature vectors correspond to different digital three-dimensional models. The feature vectors are stored in a feature vector database and correspond to the digitized three-dimensional models stored in a digitized three-dimensional model information database one to one through a database technology.
A4, the digital three-dimensional model information database, the article information database and the feature vector database are all stored in the anti-counterfeiting verification server at the cloud end. And each time the three-dimensional model is uploaded to the cloud server, the feature vector calculation module on the server is triggered, the feature vector of the digital three-dimensional model is calculated and written into the feature vector database.
(B) When the anti-counterfeiting authentication of the article is required, as shown in fig. 2, the following steps are executed:
and B1, the article verification terminal obtains the digital three-dimensional model of the article to be verified through the digital three-dimensional model obtaining module.
The acquisition of the digitized three-dimensional model includes, but is not limited to, the following common forms:
(1) the object is scanned three-dimensionally using a dedicated three-dimensional scanner. The scanning light source may be a laser (1aser) or a structured light (structured light). The three-dimensional scanner may be a mobile handheld device or a fixed desktop device.
(2) The object is photographed using a binocular depth camera. The binocular camera not only has a function of taking a picture by a general camera, but also can capture depth (depth) information of an object. Besides red, green and blue three-dimensional color information, each pixel also has one more dimension to describe distance information to the camera. And the professional computing software can generate a digital three-dimensional model by processing the distance information.
(3) Continuously taking pictures or a video of the object by using a common monocular camera including a mobile phone camera, and reconstructing a digital three-dimensional model by using a photogrammetry algorithm (Photogrammertry) according to the corresponding relation of the overlapped part of a plurality of photos and the camera projection geometrical relation of each photo.
B2, the anti-counterfeiting authentication interface of the item authentication terminal uploads the digital three-dimensional model to an item authentication server. The anti-counterfeiting verification interface can be a mobile phone interface, an internet interface or a terminal equipment query interface.
B3, the retrieval verification module on the article verification server searches the digital three-dimensional model information database for the three-dimensional model which is most matched with the uploaded digital three-dimensional model and calculates the matching degree of the three-dimensional model and the uploaded digital three-dimensional model. If the retrieval verification module needs to scan the digitized three-dimensional model information database in a large range and match the uploaded digitized three-dimensional model, in order to accelerate retrieval speed, the retrieval verification module firstly obtains a two-dimensional projection of the uploaded three-dimensional model, then judges the category of an article contained in the two-dimensional projection by using an object recognition algorithm in an image based on deep learning, and further scans the article information database to filter the digitized three-dimensional model which does not belong to the category.
B4, if the retrieval verification module needs to further reduce the range of the digital three-dimensional model to be matched in the database, the system will match the feature vector corresponding to the digital three-dimensional model to quickly screen the digital three-dimensional model in the digital three-dimensional model information database.
The similarity of the digitized three-dimensional models can be expressed approximately as the distance between their feature vectors. For three-dimensional models a and B, a and B are considered to be the same object even if they differ in their data on the computer storage medium if a can be matched to B by rotation and translation within their coordinate systems. Therefore, the retrieval verification module firstly utilizes the feature vectors with rigid invariance to match the three-dimensional model. Such approaches are mainly to find feature vectors with translational and rotational invariance. Typically, translational invariance can be obtained by initially transforming the model. For example, the centroid of the model is taken as its new reference coordinate system. Rotational invariance may be achieved by some specific transformations. Typical methods include:
(1) the model is represented by a Zernike matrix or spherical wavelet. The feature vectors are the coefficients of these transforms.
(2) The spectral decomposition coefficient of the model is used as a feature vector by a spectral decomposition method (spectral decomposition).
Most of the digitized three-dimensional models can be screened out by comparing the feature vectors. The number of the rest digitalized three-dimensional models to be matched is reduced to a small range which can be compared one by one.
And B5, calculating the matching degree of the rest digital three-dimensional models to be matched with the uploaded digital three-dimensional models one by one. The comparison result includes the overall similarity and the matching degree of each local part. For convenience of description, the digitized three-dimensional model uploaded through the anti-counterfeiting verification interface is referred to as a, and each digitized three-dimensional model to be matched is referred to as B. The retrieval verification module contained in the verification server does the following operations:
(1) initialization
The models a and B are transformed to a common reference frame or directly to one of them. For example, a principal component analysis (principal component analysis) method or the like may be used to transform the models, and then the two models may be initially registered in the transformed coordinate system.
(2) Model registration
And carrying out model registration on the model A and the model B by utilizing an optimization algorithm.
(2.1) an objective function is defined, and the objective function can be expressed as a weighting function of various characteristics such as geometry, texture and the like. Such as euclidean distances between corresponding points on model a and model B, differences in curvature, differences in color, etc.
(2.2) given the coordinate transformation relationships of the models A to B (mainly including translation vectors and rotation matrices), finding correspondences (coreespondance) between points in the model A and the model B to minimize the objective function. For each point Pi in model a, the corresponding point in model B is Φ (Pi). The algorithm finds an optimal correspondence min Φ Σ (Pi ∈ a) D (Pi, Φ (Pi)) such that the objective function is minimized. D is a function of the distance between two corresponding points. The first time this step is performed, the coordinate transformation relationship of a to B may use the result of (1) initialization.
And (2.3) giving the corresponding relation between the model A and the midpoint of the model B in the previous step, and solving the optimal coordinate transformation relation from the model A to the model B by an algorithm. Let the rotation matrix contained in the model a to model B coordinate transformation be R and the translation vector be t. For each point Pi in model a, the transformed coordinates are RPi + t. Because the goal of registration is to make model a match B as much as possible by rotational translation, the algorithm minimizes the distance of a point in a after the coordinate transformation from its corresponding point in B, i.e., min Σ (Pi ∈ a) D' (RPi + t, Φ (Pi)). D' is a distance function between two corresponding points, and the definition of the distance function may be the same as or different from that of the previous step.
And (2.4) repeating the second step and the third step until the iteration error is smaller than a given threshold value or the iteration number reaches an upper limit set in advance.
(3) The similarity of the registered models is calculated. Under certain conditions, we can use the optimal objective function value in step (2) as the similarity of the two models. In addition, we can also calculate other similarities of the two models after registration. Such as histogram representation of curvature distribution, color distribution, etc., and then the similarity or distance between these distributions is calculated as the similarity between models.
B6, the output module on the item authentication server returns the matching result to the item authentication terminal. If the matching precision exceeds a certain threshold value, the system determines that the object has high enough confidence as a genuine object, and the output module returns the digital three-dimensional model which is most matched and the corresponding object information to the object verification terminal.
B7, the verification result display module of the verification terminal will issue a verification report. The report includes whether the article to be verified exists in the genuine article three-dimensional model database. If the result is yes, the result display module displays the digital three-dimensional model which is most matched on the article verification anti-counterfeiting terminal through a visualization process, a terminal user can zoom, rotate and move the three-dimensional model through a finger touch screen, a mouse or a keyboard, and the article can be observed in a multi-angle, all-directional and high-resolution mode. Meanwhile, labels with different colors are superposed on the digital three-dimensional model to inform the subdivided region of the same part and different parts of the real object to be verified.
In conclusion, the method has the advantages of simple and easy operation, high accuracy, strong stability, low cost and difficult falsification of anti-counterfeiting information.
The anti-counterfeiting method applying the inventive concept of the present invention can have a variety of implementation methods, 2 of which are specifically described below:
example 1
And S1, scanning the commodity by a three-dimensional scanner to obtain a digital three-dimensional model when the commodity is manufactured and delivered from a factory. The model is uploaded through the Internet or stored in an anti-counterfeiting database through local connection. Meanwhile, the anti-counterfeiting system generates a retrieval number of the three-dimensional model of the commodity, and the retrieval number is placed in a packing box of the commodity or pasted on the surface of the packing of the commodity and can be changed into a password which can be remembered by a purchaser.
And S2, when anti-counterfeiting verification is needed, a three-dimensional scanner scans the commodity to obtain a digital three-dimensional model and uploads the digital three-dimensional model to an anti-counterfeiting server. The three-dimensional model retrieval number is also transmitted to the anti-counterfeiting server through a mobile phone or a computer application program.
And S3, after the anti-counterfeiting server receives the verification request, retrieving the corresponding digital three-dimensional model through the retrieval number.
And S4, comparing the difference of the two three-dimensional models by the anti-counterfeiting server by using an algorithm to judge whether the commodity is completely the same as that of the commodity when the commodity leaves the factory.
And S5, the anti-counterfeiting server returns the verification result to the mobile phone.
Example 2
And S1, scanning the commodity by a three-dimensional scanner to obtain a digital three-dimensional model when the commodity is manufactured and delivered from a factory. The model is uploaded through the Internet or stored in an anti-counterfeiting database through local connection.
And S2, when anti-counterfeiting verification is needed, a three-dimensional scanner scans the commodity to obtain a digital three-dimensional model and uploads the digital three-dimensional model to an anti-counterfeiting server.
And S3, after receiving the verification request, the anti-counterfeiting server firstly identifies the commodity type by using an artificial intelligence method, and reduces the query range of the three-dimensional model by matching the special characteristics of the commodity.
S4, for each digitized three-dimensional model, step S4 of example 1 is performed.
And S5, the anti-counterfeiting server returns the verification result to the mobile phone.
It should be noted that:
the algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose devices may be used with the teachings herein. The required structure for constructing such a device will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the claimed invention requires more features than are expressly recited in each claim. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device of an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the creation apparatus of a virtual machine according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (11)
1. An anti-counterfeiting method based on three-dimensional model matching is characterized by comprising the following steps:
the method comprises the steps of scanning to obtain a digital three-dimensional model of a genuine article object, and storing the digital three-dimensional model in a digital three-dimensional model information database;
calculating the characteristic vectors corresponding to the digital three-dimensional models, storing the characteristic vectors in a characteristic vector database, and corresponding to the digital three-dimensional models stored in a digital three-dimensional model information database one by one through a database technology;
acquiring a digital three-dimensional model of an article to be verified;
the third step that a retrieval verification module on the article verification server searches a three-dimensional model which is most matched with the uploaded digital three-dimensional model in a digital three-dimensional model information database and calculates the matching degree of the three-dimensional models, comprises the following steps:
firstly, if a retrieval verification module needs to scan a digitalized three-dimensional model information database in a large range and match an uploaded digitalized three-dimensional model, the retrieval verification module firstly obtains a two-dimensional projection of the uploaded three-dimensional model, then judges the category of an article contained in the two-dimensional projection by using an object recognition algorithm in an image based on deep learning, and further scans the article information database to filter the digitalized three-dimensional model which does not belong to the category;
if the retrieval verification module needs to further reduce the range of the digital three-dimensional models to be matched in the database, the system can match the feature vectors corresponding to the digital three-dimensional models to quickly screen the digital three-dimensional models in the digital three-dimensional model information base, and screen the digital three-dimensional models by comparing the feature vectors so as to screen most of the digital three-dimensional models, and the quantity of the rest digital three-dimensional models to be matched is reduced to a small range which can be compared one by one;
thirdly, calculating the matching degree of the rest digital three-dimensional models to be matched with the uploaded digital three-dimensional models one by one, wherein the comparison result comprises the overall similarity and the matching degree of each part;
A. initializing, namely transforming the three-dimensional model in the digital three-dimensional model information database and the three-dimensional model of the object to be verified to a common reference coordinate system or directly taking one of the three-dimensional models as the reference coordinate system, and then carrying out initial registration on the two models in the transformed coordinate system;
B. model registration
Defining an objective function, wherein the objective function is expressed as a weighting function of geometry and texture, and the weighting function comprises Euclidean distance, curvature difference and color difference between corresponding points on the digital three-dimensional model to be matched and the three-dimensional model of the article to be verified;
giving a coordinate transformation relation from the to-be-matched digital three-dimensional model to the to-be-verified article three-dimensional model, and searching a corresponding relation between the to-be-matched digital three-dimensional model and a point in the to-be-verified article three-dimensional model to minimize a target function;
using an iterative algorithm to alternately estimate the corresponding relation of the points between the two models and the current optimal coordinate transformation relation until the iteration error is smaller than a given threshold value or the iteration times reach a preset value;
C. calculating the similarity of the registered model as the matching degree;
the calculating the similarity of the registered models comprises:
calculating the similarity of the curvature and the color of the two registered models, representing the curvature distribution and the color distribution by using a histogram, and calculating the similarity or the distance between the distributions;
and judging whether the article to be verified is a genuine article according to whether the matching degree exceeds a certain threshold value.
2. The method of claim 1,
the three-dimensional scanning includes three-dimensional scanning of the appearance of the genuine article and/or the geometry of the internal hollow structure.
3. The method of claim 1, further comprising:
and establishing an article information base, and storing the accessory information of the genuine articles, wherein the accessory information corresponds to the digital three-dimensional models of the genuine articles stored in the digital three-dimensional model information base one by one.
4. The calculation method of the feature vector is one of the following methods:
(1) expressing the two digital three-dimensional models by using a Zernike matrix or a spherical wavelet, and taking the coefficient of the Zernike matrix or the spherical wavelet as a characteristic vector;
(2) and using a spectral decomposition method to take the spectral decomposition coefficients of the two models as the feature vector.
5. The method of claim 1,
the feature vectors are a set of real number vectors and are used for describing overall or local features of the digital three-dimensional model.
6. The method of claim 1,
the method for acquiring the digital three-dimensional model of the to-be-verified article is one of the following methods:
(1) three-dimensional scanning is carried out on the article to be verified by utilizing a three-dimensional scanner;
(2) photographing the to-be-verified object by using a binocular depth camera, and generating a digital three-dimensional model by processing distance information;
(3) continuously taking pictures or a video of the object to be verified by using a common monocular camera, and simultaneously reconstructing a digital three-dimensional model by using a photogrammetric algorithm according to the corresponding relation of the overlapped part of a plurality of pictures and the camera projection geometric relation of each picture.
7. The method of claim 1, wherein after obtaining the best-fit digitized three-dimensional model and the degree of fit exceeds a threshold, the method further comprises:
presenting the most matched digitized three-dimensional model through a visualization process;
zooming, rotating and moving the three-dimensional model by touching a screen, a mouse or a keyboard with a finger, and observing the object to be verified in a multi-angle, omnibearing and high-resolution manner;
and overlaying labels with different colors on the digital three-dimensional model to inform the same part and different parts of the object to be verified on the subdivided area.
8. An anti-counterfeiting device based on three-dimensional model matching, comprising an anti-counterfeiting authentication server, wherein the anti-counterfeiting authentication server comprises:
the digital three-dimensional model information database is used for storing a digital three-dimensional model of a genuine object;
the characteristic vector calculation module is used for calculating the characteristic vector of the digital three-dimensional model;
the characteristic vector database is used for storing the characteristic vectors of the digital three-dimensional model;
and the retrieval verification module is used for retrieving the three-dimensional model which is most matched with the three-dimensional model of the article to be verified in the digital three-dimensional model information database and calculating the matching degree of the three-dimensional model.
9. The apparatus of claim 8, wherein the anti-counterfeiting validation server further comprises:
and the article information base is used for storing the accessory information of the genuine articles, and the accessory information corresponds to the digital three-dimensional models of the genuine articles stored in the digital three-dimensional model information base one by one.
10. The apparatus of claim 8 or 9, wherein the apparatus further comprises an authentication terminal, the authentication terminal comprising:
the digital three-dimensional model acquisition module is used for acquiring a digital three-dimensional model of an article to be verified;
the verification interface is used for sending the digital three-dimensional model of the article to be verified to the retrieval verification module and receiving the digital three-dimensional model which is most matched and the article information corresponding to the digital three-dimensional model output by the anti-counterfeiting verification server;
the result display module is used for displaying the digital three-dimensional model which is matched most through the visualization process, zooming, rotating and moving the three-dimensional model through a finger touch screen, a mouse or a keyboard, and observing the object to be verified in a multi-angle, all-around and high-resolution mode; and overlaying labels with different colors on the three-dimensional model to inform the same part and different parts of the object to be verified on the subdivided area.
11. The apparatus of claim 10,
the verification interface is a mobile phone interface, an internet interface or a terminal equipment query interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810760619.0A CN108898127B (en) | 2018-07-11 | 2018-07-11 | Anti-counterfeiting method and device based on three-dimensional model matching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810760619.0A CN108898127B (en) | 2018-07-11 | 2018-07-11 | Anti-counterfeiting method and device based on three-dimensional model matching |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108898127A CN108898127A (en) | 2018-11-27 |
| CN108898127B true CN108898127B (en) | 2022-03-01 |
Family
ID=64349210
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810760619.0A Active CN108898127B (en) | 2018-07-11 | 2018-07-11 | Anti-counterfeiting method and device based on three-dimensional model matching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108898127B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109766944B (en) * | 2019-01-10 | 2021-05-25 | 四川中新华搜信息技术有限公司 | Commodity appearance anti-counterfeiting method based on CNN image recognition |
| CN110245962A (en) * | 2019-06-14 | 2019-09-17 | 广州市中煌科技有限公司 | A kind of method for anti-counterfeit of product |
| CN111311290B (en) * | 2020-04-17 | 2023-08-08 | 广州信天翁信息科技有限公司 | Article digitizing and verifying method and related device |
| CN111861330A (en) * | 2020-07-22 | 2020-10-30 | 南京奥拓电子科技有限公司 | Contraband identification and security inspection method and express delivery cabinet device |
| US20220092609A1 (en) * | 2020-09-22 | 2022-03-24 | Lawrence Livermore National Security, Llc | Automated evaluation of anti-counterfeiting measures |
| CN112325793B (en) * | 2020-09-30 | 2022-02-18 | 张成林 | Anti-counterfeiting detection method and device and multi-view camera |
| CN112329587B (en) * | 2020-10-30 | 2024-05-24 | 苏州中科先进技术研究院有限公司 | Beverage bottle classification method and device and electronic equipment |
| GB2610438A (en) * | 2021-09-07 | 2023-03-08 | Adaptix Ltd | A device and method of authenticating a component against reference data |
| CN114003034A (en) * | 2021-10-26 | 2022-02-01 | 山东新一代信息产业技术研究院有限公司 | Method, equipment and storage medium for making routing inspection plan of routing inspection robot |
| CN114943705B (en) * | 2022-05-27 | 2024-02-02 | 宁波艾腾湃智能科技有限公司 | Image data acquisition method for planar work or product attached to deformed substrate |
| CN114943706B (en) * | 2022-05-27 | 2023-04-07 | 宁波艾腾湃智能科技有限公司 | Anti-counterfeiting authentication of planar works or products in absolute two-dimensional space state |
| CN116151917B (en) * | 2023-01-04 | 2024-02-13 | 上海铱维思智能科技有限公司 | Transaction right determining method and system based on three-dimensional model |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104035988A (en) * | 2014-06-06 | 2014-09-10 | 上海优尼客物联网有限公司 | Three dimension scanning technique based ceramic artwork identity information inquiry system and method |
| CN104239299A (en) * | 2013-06-06 | 2014-12-24 | 富士通株式会社 | Three-dimensional model retrieval method and apparatus |
| CN104463957A (en) * | 2014-11-24 | 2015-03-25 | 北京航空航天大学 | Three-dimensional scene generation tool integration method based on materials |
| CN107505340A (en) * | 2017-07-27 | 2017-12-22 | 中国科学院高能物理研究所 | A kind of ceramics authentication method |
| CN108109212A (en) * | 2016-11-25 | 2018-06-01 | 阿里巴巴集团控股有限公司 | A kind of historical relic restorative procedure, apparatus and system |
-
2018
- 2018-07-11 CN CN201810760619.0A patent/CN108898127B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104239299A (en) * | 2013-06-06 | 2014-12-24 | 富士通株式会社 | Three-dimensional model retrieval method and apparatus |
| CN104035988A (en) * | 2014-06-06 | 2014-09-10 | 上海优尼客物联网有限公司 | Three dimension scanning technique based ceramic artwork identity information inquiry system and method |
| CN104463957A (en) * | 2014-11-24 | 2015-03-25 | 北京航空航天大学 | Three-dimensional scene generation tool integration method based on materials |
| CN108109212A (en) * | 2016-11-25 | 2018-06-01 | 阿里巴巴集团控股有限公司 | A kind of historical relic restorative procedure, apparatus and system |
| CN107505340A (en) * | 2017-07-27 | 2017-12-22 | 中国科学院高能物理研究所 | A kind of ceramics authentication method |
Non-Patent Citations (2)
| Title |
|---|
| 三维模型检索实验引擎系统和算法的设计;王勇睿;《中国优秀博硕士学位论文全文数据库（硕士） 信息科技辑》;20070215;正文第2.2节，第3.1-3.3节，第3.5节 * |
| 面向数控加工的三维人像模型相似度评价技术研究及应用;王媛媛;《中国优秀硕士学位论文全文数据库 工程科技I辑》;20120215;正文第2章，第3.2-3.3节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108898127A (en) | 2018-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108898127B (en) | Anti-counterfeiting method and device based on three-dimensional model matching | |
| CN108898128B (en) | Anti-counterfeiting method and equipment by matching digital three-dimensional model with photos | |
| US10963735B2 (en) | Methods for object recognition and related arrangements | |
| US10650546B2 (en) | Method of providing a descriptor for at least one feature of an image and method of matching features | |
| CN109791554B (en) | System and method for automatically generating metadata for a media document | |
| Ulrich et al. | Combining scale-space and similarity-based aspect graphs for fast 3D object recognition | |
| Kiforenko et al. | A performance evaluation of point pair features | |
| GB2349493A (en) | Representing and searching for an object using shape | |
| US10977481B2 (en) | System and method for object matching using 3D imaging | |
| US11934450B2 (en) | System and method for object matching using 3D imaging | |
| CN110674817B (en) | License plate anti-counterfeiting method and device based on binocular camera | |
| CN108334873A (en) | A kind of 3D four-dimension hand data discrimination apparatus | |
| Altuntas | Pair-wise automatic registration of three-dimensional laser scanning data from historical building by created two-dimensional images | |
| Zhang et al. | Kinect-based universal range sensor for laboratory experiments | |
| Lu et al. | Simple and efficient improvement of spin image for three-dimensional object recognition | |
| US7761438B1 (en) | Method and apparatus for representing and searching for an object using shape | |
| EP4120195A1 (en) | A method, a computer program and a system for calibrating at least one camera | |
| US20240220534A1 (en) | System and Method for Object Matching Using 3D Imaging | |
| Weinmann et al. | A brief survey on 2D and 3D feature extraction | |
| CN117710419A (en) | Mapping processing method, training method, computer equipment and storage medium | |
| Lu et al. | Signature of position angles histograms for 3D object recognition | |
| Kang et al. | 3D reconstruction method based on time-division multiplexing using multiple depth cameras | |
| JP2023095609A (en) | Image processing device, image processing method, and program | |
| Price et al. | Point-cloud registration using 3D shape contexts | |
| Larsen et al. | 3D Reconstruction of Buildings From Images with Automatic Façade Refinement |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP02 | Change in the address of a patent holder | ||
| CP02 | Change in the address of a patent holder |
Address after: Room 101-69, Honghai Business Building, Ningbo Free Trade Zone, Zhejiang 315800 Patentee after: NINGBO AITENGPAI INTELLIGENT TECHNOLOGY Co.,Ltd. Address before: 315000 No. 777 Zhongguanxi Road, Zhuangshi Street, Zhenhai District, Ningbo City, Zhejiang Province Patentee before: NINGBO AITENGPAI INTELLIGENT TECHNOLOGY Co.,Ltd. |