KR102289817B1 - System and method for providing authenticity verification and management for artwork - Google Patents

Abstract

According to one embodiment of the present invention, a server, which is a server configured to be connected with a first user terminal and a second user terminal in a genuine artwork verification and management service providing system to provide a genuine artwork verification and management service, includes: a communication module configured to communicate with the first and second user terminals through a network; a genuine artwork management module managing an image of a genuine artwork, size information of the genuine artwork and position information of the genuine artwork received from the second terminal; a genuine artwork verification module determining whether a verification target artwork is genuine based on an image of the verification target artwork and position information of the verification target artwork provided from the first user terminal, and then, providing a result of the determination as to whether the verification target artwork is genuine to the first user terminal through the communication module; and a database configured to store data received from the first and second user terminals for the data processing of the genuine artwork management module and the genuine artwork verification module. The genuine artwork verification module determines whether the verification target artwork is genuine based on a similarity determination between the image of the verification target artwork and the image of the genuine artwork, while determining whether the verification target artwork is genuine by additionally performing at least one among a comparison in size between the verification target artwork and the genuine artwork and a comparison between the position information of the verification target artwork and the position information of the genuine artwork.

Description

System and method for providing authenticity verification and management for artwork

The present invention relates to systems and methods for providing authenticity verification and management of works. Specifically, the present invention relates to a system and method for verifying the authenticity of a work based on a photographed image of the work of art and location information of the work, and providing a comprehensive management service for the work.

The content described in this section merely provides background information for the present embodiment and does not constitute the prior art.

In recent years, as works of art have become very popular as investment targets, offline and online trading of works of art is also increasing. Art works that have artistic and aesthetic elements, such as paintings, calligraphy, paintings, sculptures, crafts, sculptures, musical instruments, etc., often have different economic and preservation values depending on the creator of the art work. Since works of art produced by famous or unique creators have high economic value due to their workmanship and rarity, imitations of such works of art are difficult to distinguish from the real ones.

It is virtually impossible for a buyer who wants to buy a work of art to directly identify the authenticity of the work, and the buyer has no choice but to entrust the verification of the work to a professional verification agency. Verification of works through such a professional verification agency incurs additional cost and time. In particular, when purchasing a work through an offline market, it is even more difficult for the buyer to determine the authenticity of the work on the spot.

A system that can support the growth and revitalization of the art trade market by providing information and authenticity verification services on the works to be purchased to buyers in an easy way, and providing management services for verified works to artists and galleries and methods are in demand.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a system and method capable of verifying the authenticity of a corresponding work photographed in the field and providing the verification result to a user.

In addition, an object of the present invention is to promote convenience of artists and galleries by managing basic information of works verified as genuine, images of works, state information of works, location information of works, and transaction information of works, and It is to provide a system and method that can support the growth and activation of the art trading market by providing necessary information to users.

The objects of the present invention are not limited to the above-mentioned objects, and other objects and advantages of the present invention not mentioned may be understood by the following description, and will be more clearly understood by the examples of the present invention. Moreover, it will be readily apparent that the objects and advantages of the present invention may be realized by the means and combinations thereof indicated in the claims.

A server according to an embodiment of the present invention is a server configured to provide authenticity verification and management services of works in connection with a first user terminal and a second user terminal in a system for providing authenticity verification and management of works, wherein the first user a communication module configured to be able to communicate with a terminal and the second user terminal through a network; an authenticity management module for managing the image of the genuine work received from the second user terminal, size information of the genuine work, and location information of the genuine work; The authenticity of the verification target work is determined based on the image of the verification target work provided from the first user terminal and the location information of the verification target work, and the determined authenticity result of the verification target work is transmitted to the first through the communication module. Authenticity verification module provided to the user terminal; and a database configured to store data received from the first user terminal and the second user terminal for each user account for data processing of the authenticity management module and the authenticity verification module, wherein the authenticity verification module includes the verification target work Determine whether the verification target work is genuine based on the image similarity determination between the image of At least one of the comparison of the location information of the work is further performed to determine whether the work to be verified is genuine.

The authenticity verification and management providing method of a work according to another embodiment of the present invention is a method of providing authenticity verification and management of a work performed in a server linked to a first user terminal and a second user terminal, and the authenticity from the second user terminal receiving an image of the work, size information of the genuine work, and location information of the genuine work; Receiving an image of the verification target work and location information of the verification target work from the first user terminal; determining whether the image of the verification target work and the verification target work are genuine, and determining whether the verification target work is genuine based on the image similarity between the verification target work image and the image of the genuine work, determining whether the verification target work is genuine by further performing at least one of comparing the size of the verification target work with the size of the genuine work and comparing the location information of the verification target work with the location information of the genuine work; and providing, to the first user terminal, a result of the determined authenticity of the work to be verified.

A computer program according to another embodiment of the present invention is stored in a medium in combination with hardware to execute the method of verifying the authenticity of the work and providing management.

The system and method for verifying and managing the authenticity of a work according to an embodiment of the present invention determines whether the work to be verified is genuine based on the image similarity of the work to be verified photographed in the field, but the size of the work to be verified and the authenticity At least one of comparing the size of the work and the location information of the verification target work and the location information of the genuine work may be further performed to verify the authenticity of the work, and the verification result may be provided to the user.

In addition, the authenticity verification and management providing system and method of the work according to the embodiment manages the basic information of the verified work, the image of the work, the status information of the work, and the location information of the work to promote the convenience of artists and galleries, and , it is possible to support the growth and revitalization of the art trading market by providing users with necessary information related to works.

The specific effects of the present invention in addition to the above will be described together while describing specific details for carrying out the invention below.

1 is a schematic diagram illustrating a system for verifying the authenticity of a work and providing management according to an embodiment of the present invention.
2 is a block diagram illustrating a main configuration of a server according to an embodiment of the present invention.
3 is a flowchart schematically illustrating a process of performing a management service of a genuine work performed in a genuine product management module.
4 is a flowchart schematically illustrating a process of performing a verification service of a verification target work performed in the authenticity verification module.
5 is an exemplary diagram for explaining a network model structure (VGG16) used for image analysis in the present invention.
6 is an exemplary diagram for explaining a comparison process of location information performed in the present invention.
7 is a flowchart schematically illustrating a process of performing a search target work information providing service performed in a work search module.
8 is a flowchart illustrating a process of updating location information of a genuine work performed in the genuine product management module.
9 is a flowchart of a method of verifying the authenticity of a work and providing management according to another embodiment of the present invention.
10 is a flowchart illustrating detailed steps of determining whether a work to be verified is genuine.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be implemented in a variety of different forms, and only these embodiments allow the disclosure of the present invention to be complete, and common knowledge in the technical field to which the present invention belongs It is provided to fully inform the possessor of the scope of the invention, and the present invention is only defined by the scope of the claims. Like reference numerals refer to like elements throughout.

Unless otherwise defined, all terms (including technical and scientific terms) used herein may be used with the meaning commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless specifically defined explicitly.

In addition, in implementing the present invention, components may be subdivided for convenience of description, but these components may be implemented in one device or module, or one component may include a plurality of devices or modules. It may be implemented by being divided into .

1 is a schematic diagram illustrating a system for verifying the authenticity of a work and providing management according to an embodiment of the present invention.

Referring to FIG. 1 , the system 10 for providing authenticity verification and management of works includes a server 100 , a first consumer terminal 110 , and a second consumer terminal 120 .

The server 100 is a performing entity that is linked with the first user terminal 110 and the second user terminal 120, respectively, and provides a genuine verification service and a management service of the work.

The server 100 is a computer system that provides information or services to the first user terminal 110 or the second user terminal 120 through a network, and may refer to a computer program or device. Here, in the network, the server 100 provides an access path through which the first user terminal 110 and the second user terminal 120 can transmit and receive data after they are connected to each other. The network includes, for example, wired networks such as LANs (Local Area Networks), WANs (Wide Area Networks), MANs (Metropolitan Area Networks), and ISDNs (Integrated Service Digital Networks), or wireless networks such as wireless LANs, CDMA, Bluetooth, and satellite communication. However, the scope of the present invention is not limited thereto.

The server 100 may provide information on the work corresponding to the work image provided by the first user terminal 110 to the first user terminal 110 . In addition, the server 100 compares the work image provided from the first user terminal 110 with the genuine image, and based on the location information of the work, verifies the authenticity of the work image, and returns the verification result to the first user terminal (110) can be provided.

The first user terminal 110 corresponds to a terminal of the first user who intends to use the above-described service provided by the server 100 . The first user may be a user who needs to check information related to the specific work (A) and the authenticity of the specific work (A). For example, the first user may be a buyer who wants to purchase a specific work (A), but is not limited thereto.

The second user terminal 120 may be a terminal of a second user who registers a genuine image and work information of the work in the server 100 and wants to use the management service provided by the server 100 . The second user may be a user related to the specific work (B), for example, an artist who created the specific work (B) or an owner who owns the specific work (B), but is not limited thereto. The server 100 may receive a genuine image of the work, information about the work, and location information of the work from the second user terminal 120 , and may provide a management service for the work of the second user corresponding to the genuine article. In addition, the server 100 may provide a verification service and a work information providing service for the first user terminal 110 based on the work image, location information, work information, etc. provided from the second user terminal 120 .

In FIG. 1 , the first user terminal 110 and the second user terminal 120 are each shown as one, but this is only an example, and the plurality of first users and the plurality of second users are connected to the server 100 through their respective terminals. ) can be provided.

The server 100 may provide an application environment or a web environment implemented to provide the authenticity verification and management service of the above-described works.

In an embodiment, the service provided by the server 100 may be provided through application programs installed in the first user terminal 110 and the second user terminal 120 . Here, the application means an application, and may include, for example, an application executed in a mobile terminal (smart phone).

Also, in another embodiment, the server 100 may exchange data with the first user terminal 110 and the second user terminal 120 in a data transmission method through a web document. In this case, the web document refers to any data that is transmitted through a web site having a predetermined network address without limiting its type or format, and provided so that it can be viewed and/or modified. In this case, the server 100 may be a web server that provides a web page having a predetermined Uniform Resource Locator (URL), and in the first user terminal 110 and the second user terminal 120 , the web The service provided by the server 100 may be used by accessing the corresponding web page using a web browser. The format of the web document may be a format based on Hyper Text Markup Language (HTML), Extensible Markup Language (XML), JavaScript Object Notation (JSON), or another language, but is not limited to a specific format.

The first user and the second user may use the service provided by the server 100 by accessing the application or web environment through the first user terminal 110 and the second user terminal 120, respectively. That is, the first user is provided with verification of the authenticity of the work through the application (App) or web environment, and uses a service for receiving work information, and the second user is the second user through the application (App) or web environment You can receive management service (inventory service) for your works.

The first user terminal 110 and the second user terminal 120 may refer to various electronic devices such as a personal computer (PC), a notebook computer, a tablet, a mobile phone, a smart phone, and a wearable device (eg, a watch-type terminal). can In addition, the first user terminal 110 and the second user terminal 120 are an input unit (not shown) for receiving a user's input, a display unit (not shown) for displaying a service environment, and transmitting and receiving signals with the outside. A communication unit (not shown) and a control unit (not shown) for processing data, controlling each unit inside the first user terminal 110 and the second user terminal 120, and controlling data transmission/reception between the units can

Here, the first user terminal 110 may include an image generator (not shown) that can generate an image of the work and a location generator (not shown) that records the GPS location of the first user terminal 100 . there is. The image generator (not shown) may be a camera device. Here, the work image may be an image generated by the first user photographing the displayed work using the image generating unit, and the work image may be in a state of being photographed to include the work and the surrounding environment of the work. That is, the work image may be an image generated by photographing the exhibited work with a mobile phone camera, rather than professional equipment. The image of the work generated by the first user terminal 110 may be an image of the work to be verified or the image of the work to be searched. That is, it corresponds to an image generated by photographing a work for which it is not determined whether the work is genuine. The location generator may be a GPS recording device attached to the terminal device, and may generate location information based on latitude and longitude information of the terminal received from the GPS satellite.

The second user may create an image of the genuine work, location information of the genuine work, and size information of the genuine work, and through the second user terminal 120 , the real work image, location information of the genuine work, and size information of the genuine work may be provided to the server 100 . The genuine image may be an image generated by scanning or photographing a genuine work verified as genuine by the second user, and the second user terminal 120 may be configured to include a camera device or a scanning device for generating a genuine image. can The genuine image may be an image generated to include only the genuine work, and unlike the work image, may be an image that does not include other surrounding environments. The size information of the genuine work may be information obtained by measuring the size of the actual work. That is, the size information of the genuine work may include a horizontal length and a vertical length of the genuine work. In addition, when the genuine work is a sculpture having a three-dimensional shape rather than a painting, the width and height of the genuine work may also be included in the size information of the genuine work.

The second user may obtain information about a place and location where the genuine article is stored or displayed and provide the location information of the real article to the server 100 through the second user terminal 120 . Here, the location information of the genuine article may be GPS information corresponding to the place and location where the real article is stored, or GPS information corresponding to the place and location where the real article is displayed.

In addition, the second user provides basic information about the genuine work necessary for the management of the genuine work, for example, the title of the genuine work, the name of the artist, the author's history, the material of the work, the current status (owner, whether it is available for auction), etc. 2 may be provided to the server 100 through the user terminal 120 . In addition, the second user may provide the transaction information of the genuine work to the server 100 through the second user terminal 120 . Here, the transaction information may be information recording a transaction history of a genuine work, and may include information such as a transaction party and a transaction amount.

Hereinafter, with reference to FIGS. 2 to 8 , the main configuration of the server 100 and detailed processes of main services provided by the server 100 will be described in more detail.

2 is a block diagram illustrating a main configuration of a server according to an embodiment of the present invention. 3 is a flowchart schematically illustrating a process of performing a management service of a genuine work performed in a genuine product management module. 4 is a flowchart schematically illustrating a process of performing a verification service of a verification target work performed in the authenticity verification module. 5 is an exemplary diagram for explaining a network model structure (VGG16) used for image analysis in the present invention. 6 is an exemplary diagram for explaining a comparison process of location information performed in the present invention. 7 is a flowchart schematically illustrating a process of performing a search target work information providing service performed in a work search module. 8 is a flowchart illustrating a process of updating location information of a genuine work performed in the genuine product management module.

Referring to FIG. 2 , the server 100 includes a communication module 1010 , a genuineness management module 1020 , a genuineness verification module 1030 , a work search module 1040 , and a database 1050 .

The server 100 according to embodiments may be entirely hardware, or may have aspects that are partly hardware and partly software. For example, the server 100 of the present specification and each module and unit included therein may collectively refer to a device for exchanging data in a specific format and content in an electronic communication method and software related thereto. As used herein, terms such as “unit”, “module”, “server”, “system”, “device” or “terminal” refer to a combination of hardware and software driven by the hardware. it is intended to be For example, the hardware herein may be a data processing device including a CPU or other processor. In addition, software driven by hardware may refer to a running process, an object, an executable file, a thread of execution, a program, and the like.

The communication module 1010 is configured to be able to communicate with at least the first user terminal 110 and the second user terminal 120 through a network. The network provides an access path so that the server 100 , the first user terminal 110 , and the second user terminal 120 can transmit and receive packet data after accessing each other.

The authenticity management module 1020 is configured to collect, manage, and update genuine work-related information provided from the second user terminal 120 .

Referring to FIG. 3 , the authenticity management module 1020 includes the image of the genuine work received from the second user terminal 120 through the communication module 1010 , size information of the genuine work, location information of the genuine work, and transaction of the work. Information and basic information of the genuine work (the title of the genuine work, the name of the artist, the author's history, the material of the work, the current state (owner, whether it is available for auction), etc. may be received (S21).

The authenticity management module 1020 may store and manage the image of the genuine work received for each account of the second user in the database 1050, size information of the genuine work, location information of the genuine work, and basic information of the genuine work ( S22).

The authenticity management module 1020 updates and manages the stored genuine work-related information (S23). The second user may notify the user terminal ( 120), it is provided to the genuine product management module 1020, and information related to the genuine work can be maintained in the latest state in the server 100. In addition, the authenticity management module 1020 inquires to the second user terminal 120 whether the information of the genuine work is changed according to a predetermined cycle, and according to the information returned from the second user terminal 120, the information of the work is updated to the latest state. can also be maintained as

The image of the genuine work, size information of the genuine work, location information of the genuine work, and basic information of the genuine work collected from the second user terminal 120 are stored in the database 1050, and the verification target work requested by the first user It can be used as a basic data to verify the authenticity of the work and to provide search information related to the work to be searched. The database 1050 is configured to store data received from the first user terminal 110 and the second user terminal 120 for each user account for data processing of the authenticity management module 1020 and the authenticity verification module 1030 . .

The authenticity verification module 1030 determines the authenticity of the verification target work based on the image of the verification target work received from the first user terminal 110 through the communication module 1010, but size information and verification of the verification target work and determine whether the verification target work is genuine by further considering at least one of the location information of the target work.

Referring to FIG. 4 , the first user may request verification of a specific work through an authenticity verification service environment accessible through the first user terminal 110 ( S30 ). The first user may provide the server 100 with an image of the verification target work and location information of the verification target work together with the title and artist name of the verification target work.

The authenticity verification module 1030 determines whether the verification target work is genuine based on the image of the verification target work received from the first user terminal 110 through the communication module 1010 ( S31 ).

The authenticity verification module 1030 may read the title of the verification target work, the image of the genuine work corresponding to the author's name, location information of the genuine work, and size information of the genuine work from the database 1050 .

The authenticity verification module 1030 determines the image similarity between the image of the verification target work and the image of the genuine work. The authenticity verification module 1030 extracts a feature map from an image, performs maxpooling on the extracted feature map, and repeatedly performs the process of converting it into a feature map of a smaller size to output probabilities for a plurality of labels, It may include a deep learning-based image similarity analysis model 1031 trained to determine image similarity based on the probability values for a plurality of output labels, and use the image similarity analysis model 1031 to determine the verification target of the work. It judges the image similarity between the image and the image of the original work.

In an embodiment, the image similarity analysis model 1031 may be constructed using a neural network structure of VGG16 as shown in FIG. 5 . That is, the image similarity analysis model extracts a feature map using a convolutional layer and ReLU function using an input image having a size of 224×224, and performs maxpooling on the extracted feature map to obtain a smaller size. The process of transforming into a feature map may be repeatedly performed, and finally, probabilities for 1000 labels may be output through a fully connected layer and a softmax function.

The authenticity verification module 1030 extracts the first feature map of the image of the verification target work through the image similarity analysis model 1031, and repeats maxpooling on the extracted first feature map for a plurality of labels. You can print probabilities. In addition, the authenticity verification module 1030 extracts the second feature map of the image of the genuine work through the image similarity analysis model 1031, and repeatedly performs maxpooling on the extracted second feature map to obtain a plurality of labels. We can print the probability for The authenticity verification module 1030 compares the probability of the label output from the first feature map and the probability of the label output from the second feature map to determine the image similarity between the image of the work to be verified and the image of the genuine work. there is.

The authenticity verification module 1030 may determine whether the work to be verified is genuine according to the image similarity determination result. When the image similarity is less than the reference similarity, the authenticity verification module 1030 may determine that the verification target work is not genuine.

Here, since it is possible to create a counterfeit product with a similar image through various equipment and technologies, additional verification of the work to be verified may be required. The authenticity verification module 1030 determines the authenticity of the verification target work based on the image similarity determination, but further considers at least one of the size information of the verification target work and the location information of the verification target work to determine the authenticity of the verification target work can judge

The authenticity verification module 1030 may compare the size of the verification target work with the size of the genuine work, and further determine whether the verification target work is genuine according to the size comparison result. The authenticity verification module 1030 may determine that the verification target work is not genuine when the difference between the size of the verification target work and the size of the genuine work exceeds a reference value. The authenticity verification module 1030 may determine the size difference by comparing the horizontal and vertical lengths of the verification target work and the horizontal and vertical lengths of the genuine work.

The authenticity verification module 1030 may utilize the size information of the genuine work read from the database 1050 in the size comparison process. However, since it is difficult for the first user to acquire the actual size of the verification target work at the site where the verification target work is displayed, the size of the verification target work can be estimated from the image of the verification target work, and the estimated value is It can be used in the comparison process.

The authenticity verification module 1030 includes an image size analysis model 1032 , and the size of the verification target artwork may be estimated from the verification target artwork image through the image size analysis model 1032 . That is, the image size analysis model 1032 may estimate the horizontal length and vertical length of the verification target work within the verification target artwork image based on the distance between the first user terminal 110 and the verification target work. The authenticity verification module 1030 may determine whether the verification target work is genuine or not based on the horizontal and vertical lengths of the verification target artwork estimated from the image size analysis model 1032 , and the horizontal and vertical lengths of the genuine artwork.

와 같이 산출할 수 있다. 또한, 진품 검증 모듈(1030)은 진품 작품의 가로 길이(CH), 검증 대상 작품의 가로 길이(IH)를 비교하여 제2 정확도(accuracy2)를

와 같이 산출할 수 있다. 진품 검증 모듈(1030)은 제1 정확도(accuracy1)와 제2 정확도(accuracy2)의 평균 값과 기준 수치를 비교하여 검증 대상 작품의 진품 여부를 판단할 수 있다.For example, the authenticity verification module 1030 compares the horizontal length (CW) of the genuine work and the horizontal length (IW) of the verification target work to obtain a first accuracy (accuracy1).

can be calculated as In addition, the authenticity verification module 1030 compares the horizontal length (CH) of the genuine work and the horizontal length (IH) of the verification target work to obtain a second accuracy (accuracy2).

can be calculated as The authenticity verification module 1030 may compare the average value of the first accuracy (accuracy1) and the second accuracy (accuracy2) with a reference value to determine whether the verification target work is genuine.

The authenticity verification module 1030 may compare the location information of the verification target work with the location information of the genuine work, and further determine whether the verification target work is genuine or not based on the comparison result of the location information.

Specifically, the authenticity verification module 1030 sets a reference area based on the location information of the genuine work, determines whether the location information of the work to be verified is located in the reference area, and determines whether the location information of the work to be verified is When it is located within the reference area, it may be determined that the verification target work is genuine. The authenticity verification module 1030 may include a work location comparison model 1033 , and a comparison process to be described later may be performed through the work location comparison model 1033 .

Referring to FIG. 6 , a reference area having a radius R may be set based on the location C of the genuine work. Here, the line segment distance (D) between the position of the verification target work and the position of the genuine work may be defined.

)는 하기와 같은 수학식 1을 통해 계산될 수 있다. In one embodiment, the line segment distance (D,

) can be calculated through Equation 1 as follows.

[Equation 1]

은 진품 작품의 위도 좌표(

)와 검증 대상 작품의 위도 좌표(

)의 거리로,

와 같이 산출되며,

은 진품 작품의 경도 좌표(

)와 검증 대상 작품의 경도 좌표(

)의 거리로,

와 같이 산출된다.)(here,

is the latitude coordinate of the original work (

) and the latitude coordinates of the work to be verified (

) with a distance of

is calculated as

is the longitude coordinate of the original work (

) and the longitude coordinates of the work to be verified (

) with a distance of

is calculated as

)는 하기와 같은 구형 삼각법 공식인 수학식 2를 통해 계산될 수 있다.In another embodiment, the line segment distance (D,

) can be calculated through Equation 2, which is a spherical trigonometric formula as follows.

[Equation 2]

은 진품 작품의 위도 좌표,

은 검증 대상 작품의 위도 좌표,

은 진품 작품의 경도 좌표,

은 검증 대상 작품의 경도 좌표이다.)(here,

is the latitude coordinates of the original work,

is the latitude coordinates of the work to be verified,

is the longitude coordinate of the original work,

is the longitude coordinate of the work to be verified.)

The authenticity verification module 1030 may compare the calculated length of the line segment distance D and the radius R to determine whether the location information of the verification target work is located within a reference area of the genuine work. In the example of FIG. 6 , works G1 and G4 to be verified whose line segment distances D1 and D4 are smaller than the radius R can be determined to be genuine, but the segment distances D2 and D3 are larger than the radius R Works subject to verification (G2, G3) may be judged to be counterfeit products.

The authenticity verification module 1030 determines the image similarity between the image of the verification target work and the image of the genuine work, compares the size of the verification target work with the size of the genuine work, and compares the location of the verification target work and the genuine work It is possible to determine whether the verification target is genuine or not by using at least one of them.

In an embodiment, the authenticity verification module 1030 may determine whether the verification target is genuine by sequentially performing image similarity determination, size comparison, and location comparison. Determine the image similarity between the image of the verification target work and the image of the genuine work, determine the difference between the size of the verification target work and the size of the genuine work according to the image similarity determination result, and determine the size difference according to the size difference determination result Accordingly, it is possible to determine whether the verification target work is genuine or not based on the location information of the verification target work and the location information of the genuine work. That is, the image similarity between the image of the work subject to verification and the image of the original work is determined, the size difference is determined for the work to be verified that meets the preset image similarity, and the size difference is determined for the work to be verified that meets the preset size difference. Determination of authenticity based on location information may be performed. In addition, it is possible to verify the authenticity of the work subject to verification once more according to the location information of the genuine work, so that it may be possible to distinguish imitations made with similar images and work sizes. In other words, authenticity verification of the verification target work can be performed more accurately.

The authenticity verification module 1030 provides the determined authenticity result of the verification target work to the first user terminal (S32).

The first user may use the service of the server 100 according to the embodiment of the present invention not only to determine the authenticity of the specific target work, but also to obtain information about the specific target work.

The work search module 1040 receives basic information of the search target work from the first user terminal 110 through the communication module 1010 (S40), and based on the basic information of the search target work image and Information may be read from the database 1050 ( S41 ), and the image and information of the searched work to be searched for may be provided to the first user terminal 110 ( S42 ). Here, the basic information of the search target work includes at least one of an image of the search target work and a title of the search target work.

The first user may generate an image of a work to be searched by photographing a specific work to obtain information on the specific work through the first user terminal 110 . The first user may provide the image of the search target work to the server 100 through the first user terminal 110 and request information on the search target work included in the image of the search target work.

The work search module 1040 of the server 100 receives a search target work image through the communication module 1010, and may search for at least one similar image similar to the search target work image through the similar image search model. . The similar image search model extracts a feature map from the image, performs maxpooling on the extracted feature map, and repeatedly performs the process of converting it into a feature map of a smaller size to output probabilities for a plurality of labels, It may be a deep learning-based learning model trained to derive the at least one similar image based on the probability of the plurality of labels. That is, the work search module 1040 may determine a similarity range of probabilities for a plurality of labels output from the search target image, and determine images outputting probability values belonging to the determined similarity range as similar images similar to the search target image. there is.

The work search module 1040 may generate a similar image and information about the similar image and provide it to the first user. Here, the information about the similar image and the similar image may be information stored in the database 1050 as a genuine work image and related information of the genuine work image provided from second users, and may be generated based thereon.

In addition, the first user may provide the title of the work to be searched for to the server 100 through the first user terminal 110 , and may request an image with the title of the work and detailed information. The work search module 1040 searches the database 1050 for the title of the provided work, reads out the corresponding image and detailed information of the work from the database 1050, and stores it in the first user terminal 110 . can provide

While the verification service for the work of the above-described server 100 is continuously provided, location information on the work to be verified provided from the plurality of first user terminals 110 may be continuously provided, and the location information is the verification service of the work to be verified. It may be accumulated and stored in the database 1050 based on the title (S50).

Here, the location information about the work to be verified stored in the database 1050 may be location information that matches the current location information of the real work of the corresponding title, but location information that does not match the location information of the genuine work may also be included. there is. That is, when the verification target work is genuine, the location information may match, but when the verification target work is a counterfeit product, the location information may not match. Here, the matching of the location information means that the location information of the work to be verified is located within the reference area of the location information of the genuine work.

The authenticity management module 1020 may update the location information of the genuine work of the corresponding title based on the location information of the verification target work collected in the database 1050 ( S51 ).

The authenticity management module 1020 may update the current location information of the genuine work by comparing the location information of the verification target work collected in the database 1050 with the current location information of the genuine work of the corresponding title. The authenticity management module 1020 may update the current location information of the genuine work according to a ratio of information matching the current location information of the genuine work among the location information of the verification target work collected in the database 1050 .

When it is not necessary to update the location information of the genuine work, the authenticity management module 1020 maintains the current location information (S52-1). For example, the authenticity management module 1020 maintains the location information of the genuine work as the current location information when the ratio of the information matching the current location information of the genuine work among the collected location information of the verification target work is greater than or equal to the reference value. can That is, although some incorrect location information on the verification target work is collected, most of the information corresponds to the current location information of the genuine work, so the current location information of the genuine work is maintained as it is.

The authenticity management module 1020 requests confirmation of the second user when it is necessary to update the location information of the genuine work (S52-2). For example, the authenticity management module 1020 determines to change the location information of the genuine work when the ratio of the information matching the current location information of the genuine work among the collected location information of the work to be verified is less than the reference value. do. In a situation in which a large number of first users request verification of the verification target work at a different location than the current location information of the genuine work, the location of the genuine work may be moved to the location of the verification target. The authenticity management module 1020 may check whether the location information of the genuine work is changed to the second user.

The authenticity management module 1020 may update the current location information of the genuine work based on the location change information provided from the second user terminal 120 (S53).

The authenticity management module 1020 updates the current location information on the genuine work based on the location information of the verification target work collected from the first users even if the second user does not provide a change of the location information of the genuine work at all times. and management functions.

Hereinafter, a method of verifying the authenticity of a work and providing management according to another embodiment of the present invention will be described. The authenticity verification and management providing method of the work according to an embodiment of the present invention is a method of supporting the authenticity verification and management service of the work between the first user terminal 110 and the second user terminal 120 is performed, the server (100) may be performed as a subject. For the description of the present embodiment, reference may be made to FIGS. 1 to 8 and related descriptions described above.

9 is a flowchart of a method of verifying the authenticity of a work and providing management according to another embodiment of the present invention. 10 is a flowchart illustrating detailed steps of determining whether a work to be verified is genuine.

9 and 10 , a method of providing authenticity verification and management of a work according to another embodiment of the present invention is a method of providing authenticity verification and management of a work performed in a server linked to a first user terminal and a second user terminal , receiving an image of the genuine work, size information of the genuine work, and location information of the genuine work from the second user terminal (S100); Receiving the image of the verification target work from the first user terminal and the location information of the verification target work (S110); determining whether the verification target work is genuine (S120); and providing (S130) a result of whether or not the determined authenticity of the work to be verified is provided to the first user terminal.

The step of determining whether the verification target work is genuine (S120) is to determine the authenticity of the verification target work based on the image similarity between the verification target work image and the image of the genuine work, but the size of the verification target work and the By further comparing the size of the genuine work and the location information of the verification target work and the location information of the genuine work, it is possible to determine whether the verification target work is genuine.

In an embodiment, the above-described comparison process may be performed according to a series of sequences, and the step of determining whether the verification target work is genuine ( S120 ) includes the image similarity between the image of the verification target work and the image of the genuine work. Determining (S121), if the preset image similarity is satisfied, determining the difference between the size of the verification target work and the size of the genuine work (S122), If the preset size difference is satisfied, the verification The method may include comparing the location information of the target work with the location information of the genuine work to determine whether the verification target work is genuine (S123).

In step S121 , when the preset image similarity is not satisfied, the verification target work may be determined as a similar work. In step S122 , if the preset size difference is not satisfied, the verification target work may be determined as a similar work. In addition, when the location information of the verification target work is located within a reference region of the location information of the genuine work in step S123, the verification target work may be determined to be genuine. Also, when the location information of the verification target work is located outside the reference area of the location information of the genuine work in step S123, the verification target work may be determined to be a similar work.

In one embodiment, the step of determining the image similarity between the image of the verification target work and the image of the genuine work (S121) is to extract a feature map from the image, and perform maxpooling on the extracted feature map to have a smaller size By repeatedly performing the process of converting into a feature map of can be performed. Here, the step (S121) of determining the image similarity between the image of the work to be verified and the image of the genuine work is performed for a plurality of labels in the image of the work to be verified and the image of the genuine work through the image similarity analysis model. Each of the probability values may be output, and the image similarity may be determined by comparing the output probability values.

In one embodiment, the size information of the genuine work includes a horizontal length and a vertical length of the genuine work, and the step of determining the difference between the size of the verification target work and the size of the genuine work (S122) is an image size analysis model to estimate the horizontal length and vertical length of the verification target artwork from the image of the verification target artwork through Based on the comparison, the size of the verification target work and the size of the genuine work may be compared.

In one embodiment, the method includes the steps of: receiving basic information of a search target work from the first user terminal; reading images and information of a search target work of the search target work from the database based on the basic information of the search target work The method may further include the step of shipping, and providing the read image and information of the work to be searched for to the first user terminal. Here, the basic information of the search target work includes an image of the search target work by photographing the specific work to obtain information on the specific work, and the work search module compares at least one similar image similar to the search target work image. The database is searched through an image search model, and the similar image search model extracts a feature map from the image, performs maxpooling on the extracted feature map, and repeats the process of converting it into a feature map of a smaller size. It may be a deep learning-based learning model that is performed to output probabilities for a plurality of labels, and is trained to derive the at least one similar image based on the probabilities for the plurality of labels.

In one embodiment, the method may further include updating the location information of the original work of the corresponding title based on the location information of the work to be verified collected in the database.

The operation according to the method for verifying the authenticity of a work and providing management according to the embodiments described above may be at least partially implemented as a computer program and recorded in a computer-readable recording medium. A program for implementing the operation according to the method for authenticating and managing the work according to the embodiments is recorded and the computer-readable recording medium includes all kinds of recording devices in which computer-readable data is stored. . Examples of the computer-readable recording medium include a flash memory type, a hard disk type, a multimedia card micro type, and a card type memory (eg, SD or XD). memory, etc.), RAM, and ROM. In addition, the computer-readable recording medium may be distributed in a network-connected computer system, and the computer-readable code may be stored and executed in a distributed manner. In addition, functional programs, codes, and code segments for implementing the present embodiment may be easily understood by those skilled in the art to which the present embodiment belongs. The computer program is composed of a set of instructions that can be executed by the above-described computer, and the name may be different depending on the type of the computer. For example, when the form of the computer is a smart phone, the computer program may be referred to as an app.

The above description is merely illustrative of the technical idea of this embodiment, and various modifications and variations will be possible by those skilled in the art to which this embodiment belongs without departing from the essential characteristics of the present embodiment. Accordingly, the present embodiments are intended to explain rather than limit the technical spirit of the present embodiment, and the scope of the technical spirit of the present embodiment is not limited by these embodiments. The protection scope of this embodiment should be interpreted by the following claims, and all technical ideas within the equivalent range should be interpreted as being included in the scope of the present embodiment.

10: Authenticity verification and management provision system of works
100: server
110: first user terminal
120: second user terminal

Claims (12)

A server configured to provide authenticity verification and management services of works in connection with a first user terminal and a second user terminal, the server comprising:
a communication module configured to communicate with the first user terminal and the second user terminal through a network;
an authenticity management module for managing the image of the genuine work received from the second user terminal, size information of the genuine work, and location information of the genuine work;
The authenticity of the verification target work is determined based on the image of the verification target work provided from the first user terminal and the location information of the verification target work, and the determined authenticity result of the verification target work is transmitted to the first through the communication module. Authenticity verification module provided to the user terminal; and
A database configured to store data received from the first user terminal and the second user terminal for each user account for data processing of the authenticity management module and the authenticity verification module,
The authenticity verification module determines whether the verification target work is genuine based on the image similarity between the verification target work image and the image of the genuine work piece, and compares the size of the verification target work with the size of the genuine work, and determining whether the verification target work is genuine by further performing at least one of comparing the location information of the verification target work and the location information of the genuine work;
The authenticity verification module includes a trained deep learning-based image similarity analysis model for determining image similarity, and performs the image similarity determination through the image similarity analysis model,
The authenticity verification module includes an image size analysis model for estimating the size of the verification target work from the image of the verification target work, and the size with the genuine work through the size of the verification target work estimated through the image size analysis model make a comparison,
The database collects location information of the work to be verified from a plurality of first user terminals, and the authenticity management module includes location information of a genuine work of a corresponding title based on the location information of the work to be verified collected in the database. Perform the update to
The authenticity management module checks whether the location information of the genuine work is changed in the second user terminal when the ratio of the information matching the current location information of the genuine work among the collected location information of the work to be verified is less than the reference value, , Server, characterized in that for updating the current location information of the genuine work based on the location change information provided from the second user terminal. According to claim 1,
The authenticity verification module is
determining the image similarity between the image of the verification target work and the image of the genuine work,
determining the difference between the size of the verification target work and the size of the genuine work according to the image similarity determination result;
Server, characterized in that, based on the location information of the verification target work and the location information of the genuine work, according to the size difference determination result, determining whether the verification target work is genuine or not, and determining whether the verification target work is genuine . According to claim 1,
The image similarity analysis model outputs probabilities for a plurality of labels by repeatedly performing the process of extracting a feature map from an image, performing maxpooling on the extracted feature map to convert it into a feature map of a smaller size, and output The server, characterized in that it has been trained to determine the image similarity based on the probability values for the plurality of labels. 4. The method of claim 3,
The authenticity verification module is
Outputting probability values for a plurality of labels in the image of the verification target work and the image of the genuine work through the image similarity analysis model, respectively,
A server, characterized in that the image similarity is determined by comparing the output probability values. According to claim 1,
The image size analysis model estimates the horizontal length and vertical length of the verification target work from the image of the verification target work,
The size information of the genuine work includes a horizontal length and a vertical length of the genuine work,
The authenticity verification module compares the size of the verification target artwork with the size of the verification target artwork based on the horizontal length and vertical length of the verification target artwork estimated from the image size analysis model and the horizontal length and vertical length of the genuine artwork Server, characterized in that. According to claim 1,
The authenticity verification module is
When a reference area is set based on the location information of the genuine work, it is determined whether the location information of the work to be verified is located in the reference area, and the location information of the work to be verified is located in the reference area , the server, characterized in that it is determined that the verification target work is genuine. According to claim 1,
Server further comprising a work search module that reads the image and information of the search target work of the search target work from the database based on the basic information of the search target work received from the first user terminal and provides it to the first user terminal . 8. The method of claim 7,
The basic information of the search target work includes an image of the search target work in which a specific work is photographed to obtain information on the specific work,
The work search module searches the database for at least one similar image similar to the image of the work to be searched through the similar image search model,
The similar image search model outputs probabilities for a plurality of labels by repeatedly performing a process of extracting a feature map from the image, performing maxpooling on the extracted feature map, and converting it into a feature map of a smaller size, , a server, characterized in that it is a deep learning-based learning model trained to derive the at least one similar image based on the probability of the plurality of labels. delete A method of providing authenticity verification and management of works performed in a server linked to a first user terminal and a second user terminal,
Receiving an image of a genuine work, size information of the genuine work, and location information of the genuine work from the second user terminal;
Receiving an image of the verification target work and location information of the verification target work from the first user terminal;
Determining whether the verification target work is genuine or not, determining whether the verification target work is genuine or not, based on the image similarity between the verification target work image and the image of the genuine work piece, the size of the verification target work and the determining whether the verification target work is genuine by further performing at least one of comparing the size of the genuine work and comparing the location information of the verification target work with the location information of the genuine work;
providing a result of the determined authenticity of the work to be verified to the first user terminal; and
A step of updating the location information of a genuine work of a corresponding title based on the location information of the work to be verified collected from a plurality of first user terminals, When the ratio of the information matching the current location information is less than the reference value, it is checked whether the location information of the genuine work is changed in the second user terminal, and based on the location change information provided from the second user terminal, the real work is displayed. updating current location information;
In the step of determining the authenticity of the verification target work, the image similarity determination is performed through a trained deep learning-based image similarity analysis model,
In the step of judging whether the verification target work is genuine or not, the size comparison is performed by estimating the size of the verification target work from the image of the verification target work, and comparing the size of the verification target work estimated through the image size analysis model and the genuine work. A method comprising performing a size comparison of 11. The method of claim 10,
The step of determining whether the work to be verified is genuine,
determining an image similarity between the image of the verification target work and the image of the genuine work;
determining a difference between a size of the verification target work and a size of the genuine work when the image similarity is equal to or greater than a reference similarity level; and
If the difference in size is less than or equal to a reference size, determining whether the verification target work is genuine by comparing the location information of the verification target work with the location information of the genuine work. 12. A computer program stored in a recording medium in combination with hardware to execute the method for verifying and managing the authenticity of a work according to any one of claims 10 to 11.

Images