KR20180129612A - Method and apparatus for image authentication using fuzzy vault based for protection of the coffee latte print copyright - Google Patents

Abstract

According to an embodiment of the present invention, an image authentication method includes: a step of inputting an image to be registered and content authentication information related to the image; a step of registering content which includes encrypted content authentication information obtained by encrypting the content authentication information related to the image using a fuzzy vault key; a step of authenticating the registered content through a matching result of matching a new fuzzy vault template generated for a new image with a previously generated fuzzy vault template upon receiving the input of the new image; and a step of performing coffee latte printing upon completing the authentication of the content. It is possible to provide an image authentication technique for coffee latte printing with robustness even if the partial modulation of an image occurs.

Description

TECHNICAL FIELD [0001] The present invention relates to a fuzzy bolt-based image authentication method and apparatus for protecting copyright of a coffee latte. [0002] The present invention relates to a fuzzy-

The following description relates to a field of image processing and information protection for image image authentication, and relates to a fuzzy-bolt-based image authentication method and apparatus for protecting coffee latte print copyright.

Recently, the demand of customers using 3D food printing has been increasing. Especially, models using coffee latte printers are being developed in China, Taiwan, and others.

In Korea, products using coffee latte printing technology are being launched, and various commercial models are being developed accordingly. On the other hand, the prosumer service model has the advantage of expanding market formation by freeing individual participation in industrial ecosystem.

A system for protecting the copyright of the production of such an individual coffee latte printing image is indispensable, and a "watermark" is used as a method for digital image authentication, and a "cryptographic hash" technique is used in the field of information protection have. However, watermark has difficulty to be used in real field because it has recognition rate, and cryptographic hash has inconvenience that authentication can not be performed if the data of the image deviates even by one bit.

Therefore, coffee latte printing using food 3D printing needs to be robust against partial modulation of images.

Reference: Korean Patent Laid-Open No. 10-20120020419, Korean Patent Laid-Open No. 10-2009-0110026

An image authentication method and apparatus for coffee latte printing having robustness even when partial modulation of an image occurs can be provided.

An image authentication method includes: inputting a video to be registered and content authoring information related to the video; Registering content including encrypted content authoring information obtained by encrypting content authoring information related to the video using a fuzzy key; The first information about the new image generated for the new image and the second information about the new image are matched with the generated fuzzy vault template upon receiving the input of the new image, ; And performing coffee latte printing upon completion of the authentication of the content.

The image authentication method includes: generating an sebbase key using first information generated at random and second information generated from the image; And generating a fuzzy vault template based on the first information, the second information, and any feature information.

The step of registering the content may include registering the content including the encrypted content authoring information, the fuzzy vault template, and the first information.

Wherein the authenticating the registered content comprises generating first information for a new image based on at least one or more features extracted randomly and based on at least one feature extracted from the new image using the Harris corner Generating second information on a new image, and performing matching with a previously stored fuzzy vault template based on synthesis information obtained by synthesizing first information on the new image and second information on the new image .

Wherein the step of authenticating the registered content comprises the steps of restoring the fuzzy vault key through a matching result obtained by matching the synthetic information with a previously stored fuzzy vault template, And a step of reconstructing the image.

The generating the sebbase key using the randomly generated first information and the second information generated from the image may include generating first information based on at least one or more extracted features extracted at random, And generating second information based on at least one feature extracted from the image using the Harris corner, wherein the first information and the second information include respective x values, y values, and vault values can do.

The image authentication apparatus includes an input unit for inputting a video to be registered and content authoring information related to the video; A key generation unit for generating an sebbase key using the first information generated at random and the second information generated from the image; A template generating unit for generating a fuzzy vault template based on the first information, the second information, and any feature information; A registration unit for registering content including encrypted content authoring information obtained by encrypting content authoring information related to the image using the fuzzy vault key; The first information on the new image generated for the new image and the second information on the new image are matched with the previously stored fuzzy vault template upon receiving the input of the new image, An authentication unit for authenticating the user; And a printing unit for performing coffee latte printing upon completion of the authentication of the content.

The registering unit may register content including the encrypted content authoring information, the fuzzy vault template, and the first information.

Wherein the authentication unit generates first information on a new image based on at least one or more features extracted at random and generates second information on a new image based on at least one feature extracted using the Harris corner from the new image, And may perform matching with the previously stored fuzzy vault template based on the composite information obtained by synthesizing the first information on the new image and the second information on the new image.

The authentication unit may restore the fuzzy vault key through the matching result obtained by matching the composite information with the previously stored fuzzy vault template and restore the encrypted content authoring information using the restored fuzzy bolt key.

It is expected to contribute to the expansion of the market by freeing individual participation in the industrial ecosystem of coffee latte printing prosumer service model.

Also, copyright of the production of coffee latte printing image can be protected through image authentication technique for coffee latte printing which has robustness even if partial modulation of image occurs.

1 is a block diagram illustrating a configuration of a video authentication apparatus according to an embodiment.
2 is a diagram for explaining generation of first information and second information in the image authentication apparatus according to an embodiment.
3 is a diagram for explaining generation of a fuzzy vault key in the image authentication apparatus according to an embodiment.
4 is a diagram for explaining generation of a fuzzy vault template in the image authentication apparatus according to the embodiment.
5 is a diagram for explaining registration of contents in the image authentication apparatus according to the embodiment.
FIG. 6 is a diagram for explaining contents authentication in the image authentication apparatus according to an embodiment.
7 is a flowchart illustrating an image authentication method in an image authentication apparatus according to an exemplary embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings.

In the following embodiments, a fuzzy bolt-based image authentication method for coffee latte printing using a secret distribution technique having robustness even when partial modulation of an image occurs will be described.

1 is a block diagram illustrating a configuration of a video authentication apparatus according to an embodiment.

The image authentication apparatus 100 may include an input unit 110, a key generation unit 120, a template generation unit 130, a registration unit 140, an authentication unit 150, and a print execution unit 160.

The input unit 110 may receive content storage information related to images and images to be registered.

The key generation unit 120 may generate the fuzzy logic key using the first information generated at random and the second information generated from the image. The key generation unit 120 may generate first information based on at least one extracted feature extracted at random and generate second information based on at least one feature extracted from the image using the Harris corner have.

The template generating unit 130 may generate the fuzzy vault template based on the first information, the second information, and any feature information.

The registering unit 140 may register the content including the encrypted content authoring information obtained by encrypting the content authoring information related to the image using the fuzzy vault key. The registration unit 140 can register content including encrypted content authoring information, a fuzzy vault template, and first information.

Upon receiving the input of the new image, the authentication unit 150 generates first information on the new image generated for the new image, second information on the new image, and matching result obtained by matching the generated second information with the generated fuzzy vault template The registered content can be authenticated. Specifically, the authentication unit 150 generates first information on a new image based on at least one feature extracted randomly, and generates a new image based on at least one feature extracted from the new image using the Harris corner And may perform matching with the previously stored fuzzy vault template based on the composite information obtained by synthesizing the first information on the new image and the second information on the new image. The authentication unit 150 may restore the fuzzy vault key through the matching result obtained by matching the synthetic information with the previously stored fuzzy vault template, and may restore the encrypted content authoring information using the restored fuzzy vault key.

The print execution unit 160 may perform coffee latte printing upon completion of the authentication of the content.

2 is a diagram for explaining generation of first information and second information in the image authentication apparatus according to an embodiment.

At least one feature may be extracted at random from the server (for example, a video authentication apparatus). For example, at least one or more random coordinates can be extracted at random. At this time, the image can be registered in advance using the fuzzy-bolt-based image and the secret distribution of the server. In this way, the first information can be generated based on at least one feature extracted at random. The image authentication apparatus can generate the first information including n features through the coordinate information generated at random. The first information may mean that the server secret is generated by extracting a characteristic from the server.

Further, the image authentication apparatus can extract at least one feature from the image. The image authentication apparatus can generate second information including m features. In this case, the image may be a fuzzy-bolt-based image. In this manner, the second information can be generated based on the extracted at least one feature. In this case, the second information may mean that the image secret is generated by extracting the feature from the image. Specifically, the feature can be extracted from the image 200 using the Harris corner. The Harris corner method is a typical method for finding feature points of an image, and is a method of extracting feature points by creating and mapping a small window.

The image authentication apparatus randomly generates n pieces of first information (n is a natural number) and m pieces of second information (m is a natural number).

3 is a diagram for explaining generation of a fuzzy vault key in the image authentication apparatus according to an embodiment.

, 영상의 제2 정보:

,

,

를 갖는다. 이때, 다항식의 차수는 max(n, m)+1 이상의 차수, 즉, n 또는 m의 최대값에 1을 가산한 차수를 이용한다. The image authentication apparatus can generate a single fuzzy vault key 310 by combining the generated first information with n (n is a natural number) and m (m is a natural number) second information. At this time, each of the first information and the second information has three values (x value, y value, vault value). Here, the x value and the y value may mean x coordinate information and y coordinate information. For example, when a fuzzy vault key is generated using five pieces of first information, five pieces of second information, and six pieces of vault values, the first information of the server:

, Second information of the image:

,

,

. In this case, the order of the polynomial is the order of max (n, m) +1 or more, that is, the order obtained by adding 1 to the maximum value of n or m.

4 is a diagram for explaining generation of a fuzzy vault template in the image authentication apparatus according to the embodiment.

)를 생성하여 퍼지볼트 템플릿(400)을 생성할 수 있다. 이때, 임의의 특징 정보는 거짓 특징점으로서, 예를 들면, 사용자에 의하여 거짓 특징점이 입력될 수 있고, 랜덤으로 거짓 특징점이 생성될 수도 있다. 이외에도 다양한 방법으로, 거짓 특징점이 생성될 수 있다.The image authentication apparatus can generate a fuzzy vault template (400) based on the first information, the second information, and any feature information. For example, the image authentication apparatus may include first information (n) of the extracted server, second information (m) of the image, and arbitrary feature information

) To generate the fuzzy vault template 400. [ At this time, the arbitrary feature information may be a false feature point, for example, a false feature point may be input by a user, and a false feature point may be generated randomly. In addition, false feature points can be generated in various ways.

7 is a flowchart illustrating an image authentication method in an image authentication apparatus according to an exemplary embodiment.

The image authentication apparatus can perform the content registration process 710 and the content authentication process 720. The image authentication apparatus can perform image authentication for fuzzy bolt - based coffee latte printing using a secret distribution technique having robustness even if partial modulation of the image occurs.

The content registration process 710 will be described in more detail with reference to FIG. The content authoring information related to the image and the image to be registered from the author can be inputted (510). The image authentication apparatus may generate the first information based on at least one feature extracted at random, and may generate the second information based on at least one feature extracted from the image. For example, the second information can be generated by extracting features from an image using an ellipse corner.

The image authentication apparatus may generate the fuzzy logic key 520 based on the first information and the second information. The image authentication apparatus can generate the fuzzy vault template 530 based on the first information, the second information, and any feature information.

The image authentication apparatus can encrypt the content authoring information related to the image using the fuzzy vault key 520. For example, encryption can be performed using AES (Advanced Encryption Standard), which is a standard encryption technique. Accordingly, the encrypted value obtained by encrypting the content authoring information using the fuzzy bolt key 520 can be expressed as E (content authoring information, fuzzy bolt key).

The content including encrypted content authoring information may be registered (550). At this time, the image authentication apparatus may register the content authoring information, the first information, and the fuzzy vault template together for future verification (540).

The content authentication process 720 will be described in more detail with reference to FIG. The process of authenticating the content can be performed by verifying through the decryption process. For example, authentication of a new image may be requested from an individual user. As the new image is input, the image authentication apparatus can perform the operation of the first information on the new image and the second information on the new image to synthesize the first information on the new image and the second information on the new image . The image authentication apparatus can perform the matching of the composite information obtained by combining the first information on the new image and the second information on the new image with the previously stored fuzzy vault template.

The image authentication apparatus can restore the fuzzy vault key through the matching result obtained by matching the synthetic information with the previously stored fuzzy vault template. At this time, the decrypted decryption value can be represented by D (content authoring information, fuzzy bolt key). The image authentication apparatus can complete the authentication process by restoring and verifying the encrypted content authoring information. For example, when the matching result (i.e., m + n) is equal to or greater than max (m + n) +1, a fuzzy vault key may be generated to decrypt the encrypted value to perform content verification. In this case, the order of the polynomial should be a degree of max (n, m) +1 or more, and the first information and the second information can be independently polynomial solved, and the combination of the first information and the second information, When the matching result (i.e., m + n) of the template is max (n, m) +1 or more, the encrypted content authoring information can be decrypted by generating the fuzzy vault key.

The image authentication apparatus can perform coffee latte printing according to completion of authentication of the content (730). Accordingly, the image that has been authenticated can be coffee latte-printed, and the coffee latte-printed image can be output. The image authentication apparatus can perform coffee latte printing based on the image registered as a new image.

The apparatus described above may be implemented as a hardware component, a software component, and / or a combination of hardware components and software components. For example, the apparatus and components described in the embodiments may be implemented within a computer system, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA) , A programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For ease of understanding, the processing apparatus may be described as being used singly, but those skilled in the art will recognize that the processing apparatus may have a plurality of processing elements and / As shown in FIG. For example, the processing unit may comprise a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as a parallel processor.

The software may include a computer program, code, instructions, or a combination of one or more of the foregoing, and may be configured to configure the processing device to operate as desired or to process it collectively or collectively Device can be commanded. The software and / or data may be in the form of any type of machine, component, physical device, virtual equipment, computer storage media, or device As shown in FIG. The software may be distributed over a networked computer system and stored or executed in a distributed manner. The software and data may be stored on one or more computer readable recording media.

The method according to an embodiment may be implemented in the form of a program command that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions to be recorded on the medium may be those specially designed and configured for the embodiments or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments. For example, it is to be understood that the techniques described may be performed in a different order than the described methods, and / or that components of the described systems, structures, devices, circuits, Lt; / RTI > or equivalents, even if it is replaced or replaced.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (10)

In the image authentication method,
Receiving a video to be registered and content authoring information related to the video;
Registering content including encrypted content authoring information obtained by encrypting content authoring information related to the video using a fuzzy key;
The first information on the new image generated for the new image and the second information on the new image are matched with the fuzzy vault template included in the registered content upon receiving the input of the new image, Authenticating the content; And
Performing coffee latte printing upon completion of the authentication of the content
And an image authentication method. The method according to claim 1,
Generating an sebbase key using the first information generated at random and the second information generated from the image; And
Generating a fuzzy vault template based on the first information, the second information, and any feature information
Further comprising the steps of: The method according to claim 1,
Wherein the registering of the contents comprises:
A step of registering contents including the encrypted content authoring information, the fuzzy vault template and the first information
And an image authentication method. The method according to claim 1,
Wherein the step of authenticating the content comprises:
Generates first information on a new image based on at least one feature extracted randomly and generates second information on a new image based on at least one feature extracted using the Harris corner from the new image A step of performing matching with a previously stored fuzzy vault template based on synthesis information obtained by synthesizing first information on the new image and second information on the new image,
And an image authentication method. 5. The method of claim 4,
Wherein the step of authenticating the content comprises:
And restoring the encrypted content authoring information by using the restored fuzzy bolt key, and restoring the encrypted content authoring information using the restored fuzzy bolt key
And an image authentication method. 3. The method of claim 2,
Wherein the step of generating the sebbase key using the randomly generated first information and the second information generated from the image comprises:
Generating first information based on at least one extracted feature extracted at random and generating second information based on at least one feature extracted using the Harris corner from the image
Lt; / RTI >
Wherein the first information and the second information each include an x value, a y value, and a vault value. A video authentication apparatus comprising:
An input unit for inputting a video to be registered and content authoring information related to the video;
A key generation unit for generating an sebbase key using the first information generated at random and the second information generated from the image;
A template generating unit for generating a fuzzy vault template based on the first information, the second information, and any feature information;
A registration unit for registering content including encrypted content authoring information obtained by encrypting content authoring information related to the image using the fuzzy vault key;
The first information on the new image generated for the new image and the second information on the new image are matched with the fuzzy vault template included in the registered content upon receiving the input of the new image, An authentication unit for authenticating the content; And
A printing unit for performing coffee latte printing upon completion of the authentication of the content,
And an image authentication device. 8. The method of claim 7,
Wherein the registration unit comprises:
The contents including the encrypted content authoring information, the fuzzy vault template, and the first information are registered
And the image authentication device. 8. The method of claim 7,
Wherein,
Generates first information on a new image based on at least one feature extracted randomly and generates second information on a new image based on at least one feature extracted using the Harris corner from the new image , And performs matching with a previously stored fuzzy vault template based on synthesis information obtained by synthesizing first information on the new image and second information on the new image
And the image authentication device. 10. The method of claim 9,
Wherein,
Restores the fuzzy vault key through the matching result obtained by matching the synthetic information with the pre-stored fuzzy vault template, and restores the encrypted content authoring information using the restored fuzzy bolt key
And the image authentication device.

Images