Personal authentication system, personal authentication method, and personal authentication program

Abstract

Provided is an authentication system that determines whether or not a person using an avatar in a specified service is the same person as the actual person. 【Solution means】The authentication system includes a personal feature point information generation unit 2 that extracts a plurality of feature points on an image from a personal image and generates personal feature point information regarding the positional relationship between the feature points of the personal image, a target image input unit 12 that inputs a target image which is an image of a target person to be authenticated during the authentication process, a target feature point information generation unit 13 that extracts a plurality of feature points on the image from the target image and generates target feature point information regarding the positional relationship between the feature points of the target image, an image information comparison unit 15 that compares the target image information generated by a target image information generation unit 14 and the personal image information generated by a personal image information generation unit 3, an authentication processing unit 17 that performs an authentication process using the personal feature point information / target feature point information, and an authentication display instruction unit 18 that instructs to display an authentication display consisting of content corresponding to the authentication result of the authentication processing unit 17.

Description

Technical Field

[0001] The present invention relates to a technique for realizing highly accurate personal authentication processing with a small amount of information.

Background Art

[0002] In recent years, with the improvement of processing capabilities in electronic computers such as computers, two-dimensional and three-dimensional computer graphics have been widely used in IT services such as games and SNS (Social Networking Service). In these services, not only icons and avatars imitating fictional characters are used, but also avatars that abstractly represent real people such as users to some extent based on their characteristics are increasingly used. As a result, for example, in a game, when a protagonist consisting of an avatar representing the characteristics of a user battles an enemy character, an effect of improving the user's sense of immersion in the game world occurs. In SNS, by using an avatar that abstractly represents the user himself / herself as an icon indicating the user, it is expected that an effect of promoting communication between users in a virtual space in the same sense as the real world will occur.

[0003] Both Patent Documents 1 and 2 disclose technologies for using avatars that imitate the actual appearances of players themselves or co-players in computer games that express virtual spaces using head-mounted displays.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0005] These avatars are exclusively used online, and it is impossible to determine that the person using a specific avatar is identical to the person shown in the original image that is the basis of the avatar design. Therefore, an identity verification procedure is required for using online services. However, authentication using a password or the like cannot completely prevent impersonation by a third party due to information leakage or the like, and in the case of biometric authentication, there is a problem that it is not easy to obtain biometric information in advance.

[0006] On the other hand, even when identity verification is performed by image authentication, if the personal image for reference is stored in advance, there is a problem that the burden of data storage is large, especially when a high-definition image is used to improve the authentication accuracy. In addition, there is still a risk that the personal image for reference may be tampered with due to information leakage or the like, and from this perspective, identity verification by image authentication is not perfect. Furthermore, when identity verification is performed by image authentication, there is a problem that the authentication accuracy decreases, for example, when a long time has passed from the acquisition of the personal image for reference to the actual identity verification process, or when the identity is verified with an expression completely different from the reference image.

[0007] Also, if identity verification is always performed (for example, every minute), the burden on the system is large and not practical. On the other hand, if identity verification is performed periodically (that is, at regular time intervals), for at least other users who use online services such as those where avatars are used, it is difficult to recognize whether the person using the avatar has undergone no identity verification at all, was identity-verified immediately before, or how much time has passed since the identity verification was performed.

[0008] The present invention has been made in view of the above problems, and an object thereof is to provide a technology that realizes highly accurate identity verification processing with a small amount of information, effectively prevents forgery of materials used for the verification processing, and allows a third party to easily grasp the verification result.

Means for Solving the Problems

[0009] In order to achieve the above object, the personal authentication system according to claim 1 is a personal authentication system that determines whether a person who uses the avatar with which the correspondence relationship with the user is set is the same person as the user in a predetermined service. The personal authentication system extracts a plurality of feature points from a personal image that is an image of the user, and generates personal feature point information that is information regarding the positional relationship between the plurality of feature points. This a personal feature point information generation means; a target feature point information generation means that extracts a plurality of feature points from a target image that is an image of a target person who is a person to be authenticated, and generates target feature point information that is information regarding the positional relationship between the plurality of feature points; a comparison is made between the positional relationship between the plurality of feature points in the personal image included in the personal feature point information and the positional relationship between the plurality of feature points in the target image included in the target feature point information, and authentication processing regarding the presence or absence of identity between the target person and the user is performed based on the comparison result; and authentication display instruction means for instructing as follows in association with the display of the avatar in the predetermined service , when the result of the authentication process by the authentication processing means affirms the identity between the target person and the individual, it instructs to perform an authentication display corresponding to the fact that the individual has been authenticated, and changes the display content according to the passage of time from the completion of the authentication process for the authentication display is characterized by comprising.

[0011] Also, in order to achieve the above object, claim 2The personal authentication system according to the above invention includes at least one of personal shooting condition information including information related to at least one of the expression and health condition of the person at the time of shooting and information related to the shooting date and time of the personal image, and personal shooting device information which is information related to the shooting device used for shooting the personal image. It further includes personal image information generation means for generating personal image information, target image information generation means for generating target image information including at least one of target shooting condition information including information related to at least one of the expression and health condition of the target person at the time of shooting and information related to the shooting date and time of the target image, and information related to the shooting device used for shooting the target image, image information comparison means for comparing the personal image information and the target image information, and based on the comparison result by the image information comparison means, feature point information correction means for correcting the positional relationship between the feature points in at least one of the personal feature point information and the target feature point information according to the difference between the personal image information and the target image information. The authentication processing means performs authentication processing based on the personal feature point information and / or the target feature point information corrected by the feature point information correction means. It is characterized in that.

[0012] Also, in order to achieve the above object, claim 3 The personal authentication method according to the invention is a personal authentication method for determining whether a person using an avatar with which a correspondence relationship with a person is set is the same person as the person in a predetermined service. It extracts a plurality of feature points from a personal image which is an image of the person, and generates personal feature point information which is information related to the positional relationship between the plurality of feature points. This A personal feature point information generation step, a target feature point information generation step of extracting a plurality of feature points from a target image which is an image of a target person who is a person to be authenticated, and generating target feature point information which is information related to the positional relationship between the plurality of feature points, comparing the positional relationship between the plurality of feature points in the personal image included in the personal feature point information and the positional relationship between the plurality of feature points in the target image included in the target feature point information, and performing an authentication process regarding the identity of the target person and the person based on the comparison result, and accompanying the display of the avatar in the predetermined service, when the result of the authentication process in the authentication processing step affirms the identity between the target person and the individual, it instructs to perform an authentication display corresponding to the fact that the individual has been authenticated, and changes the display content according to the passage of time from the completion of the authentication process for the authentication display It is characterized by including an authentication display instruction step for instructing as such.

[0013] Also, to achieve the above object, in the personal authentication method according to claim 4 In the above invention, it further includes an encryption processing step for encrypting the personal feature point information, an output information generation step for generating output information including the encrypted personal feature point information regarding the person corresponding to the avatar, which is recorded in a distributed ledger on a distributed network corresponding to a non-replaceable token in a correspondence relationship with the avatar, an output instruction step for instructing to output the output information generated in the information generation step to the distributed network, an output information acquisition step for acquiring the output information from the information recorded in the distributed ledger on the distributed network, and a decryption processing step for decrypting the personal feature point information included in the output information acquired in the output information acquisition step, and in the authentication processing step, the personal feature point information decrypted in the decryption processing step is used for authentication processing.

[0014] Also, to achieve the above object, in the personal authentication program according to claim 5 It is a personal authentication program for causing a computer to determine whether a person using the avatar in a predetermined service is the same person as the person, for an avatar in which a correspondence relationship with the person is set. The computer extracts a plurality of feature points from a personal image that is an image of the person, and generates personal feature point information that is information regarding the positional relationship between the plurality of feature points. This A personal feature point information generation function for extracting a plurality of feature points from a target image that is an image of a target person who is a person to be authenticated, and generating target feature point information that is information regarding the positional relationship between the plurality of feature points, a comparison of the positional relationship between the plurality of feature points in the personal image included in the personal feature point information and the positional relationship between the plurality of feature points in the target image included in the target feature point information, and an authentication processing function for performing authentication processing regarding the presence or absence of identity between the target person and the person based on the comparison result, and accompanying the display of the avatar in the predetermined service , when the result of the authentication process by the authentication processing function affirms the identity between the target person and the individual, it instructs to perform an authentication display corresponding to the fact that the individual has been authenticated, and changes the display content according to the passage of time from the completion of the authentication process for the authentication displayIt is characterized by causing execution of an authentication display instruction function for instructing as such.

Advantages of the Invention

[0015] According to the present invention, it is possible to realize highly accurate personal authentication processing with a small amount of information, and there is an effect that a third party can easily grasp the authentication result.

Brief Description of the Drawings

[0016]

Figure 1

Figure 2

Modes for Carrying Out the Invention

[0017] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. In the following embodiments, examples considered to be the most appropriate as embodiments of the present invention are described. Of course, the content of the present invention should not be construed as being limited to the specific examples shown in this embodiment. Any configuration having the same operation and effect, even if it is other than the specific configuration shown in the embodiment, is of course included in the technical scope of the present invention.

[0018] (Embodiment 1) First, the personal authentication system according to Embodiment 1 will be described. As shown in FIG. 1, the personal authentication system according to Embodiment 1 includes a personal image input unit 1 for inputting a personal image used for generating personal feature point information, a personal feature point information generation unit 2 that extracts a plurality of feature points on the image from the personal image and generates personal feature point information, which is information on the positional relationship between the feature points of the personal image, a personal image information generation unit 3 that generates information regarding the personal image, an avatar generation unit 5 that generates an avatar used by the user on services such as games and SNSs, an avatar token generation unit 6 that generates an avatar token, which is a non-fungible token in a correspondence relationship with the avatar used by the user, a transaction generation unit 7 that generates a transaction stored in a block in a distributed ledger corresponding to the avatar token as output information including the personal feature point information (preferably, the encrypted information), an electronic signature generation unit 8 that generates an electronic signature, which is data for proving that the generation and output of the information included in the transaction follow the intention of the holder of the avatar token, an output unit 9 that outputs the transaction and the electronic signature to a distributed network associated with the avatar token, a transaction acquisition unit 10 that acquires the transaction recorded in the distributed ledger corresponding to the avatar token, a personal feature point information extraction unit 11 that extracts the personal feature point information from the transaction acquired by the transaction acquisition unit 10, a target image input unit 12 that inputs a target image, which is an image of a target person to be authenticated during the authentication process, a target feature point information generation unit 13 that extracts a plurality of feature points on the image from the target image and generates target feature point information, which is information on the positional relationship between the feature points of the target image, a target image information generation unit 14 that generates target image information, which is information regarding the target image, an image information comparison unit 15 that compares the target image information generated by the target image information generation unit 14 with the personal image information generated by the personal image information generation unit 3, a feature point information correction unit 16 that corrects the personal feature point information and / or the target feature point information based on the comparison result by the personal image information comparison unit 15, an authentication processing unit 17 that performs a personal authentication process using the personal feature point information / target feature point information corrected by the feature point information correction unit 16, and an authentication display instruction unit 18 that instructs to display an authentication display consisting of content corresponding to the authentication result of the authentication processing unit 17.An authentication display generation unit 19 that generates a specific authentication display based on an instruction, and an authentication display output unit 20 that outputs the authentication display generated by the authentication display generation unit 19 to the service where the avatar is used.

[0019] The personal image input unit 1 is for inputting a personal image, which is an image of the person to be authenticated and is used for generating personal feature point information. The form of the personal image may be either a still image or a moving image, and it may be composed not only of a single image data but also of a plurality of image data taken from different directions. Regardless of whether it is in color or black and white, it may be either a 2D image or a 3D image. As a specific configuration of the personal image input unit 1, it may be configured to directly input a personal image by having an imaging function such as a camera, or it may be configured to input a personal image taken by a portable terminal possessed by the person, for example.

[0020] The personal feature point information generation unit 2 extracts a plurality of predefined feature points corresponding to each part of the face such as eyes, nose, mouth, ears, etc. and characteristic parts such as connection points of the jaw bone structure in the human body from the personal image, and generates personal feature point information, which is information on the positional relationship between the plurality of extracted feature points. The personal feature point information generated by the personal feature point information generation unit 2 is used as reference information for the personal authentication process by the authentication processing unit 17 described later. Although the generated personal feature point information may be used as reference information as it is, preferably, the personal feature point information subjected to necessary correction processing by the feature point information correction unit 16 described later is used.

[0021] As a specific configuration of the personal feature point information generation unit 2, an image recognition technology realized by deep learning, machine learning, etc. may be used, or a combination of a plurality of image recognition technologies may be used. Further, the "feature points" in the first embodiment indicate the positions of the body surface or internal parts of the human body, and any part may be arbitrarily determined as to which part should be set as the feature point. For example, it may be handled that the feature points are set only for the visually recognizable parts (eyes, nose, mouth, ears, eyebrows, etc.) and points corresponding to the contours on the face surface, or the feature points may be determined corresponding to the facial expression muscles inside the face and the positions of the joints which are the internal structures. Further, for example, when setting feature points for the eyes, only the center position of the eyes may be set as the feature point, or feature points may be set in detail for each of the inner corner of the eye, the outer corner of the eye, the pupil, and the white part of the eye. Note that for each feature point extracted by the personal feature point information generation unit 2, information regarding the position of the feature point (which may be the position itself in the original image, but preferably the position in the normalized coordinate system for reasons such as convenience during the personal authentication process) and the meaning of the feature point (a point corresponding to the outer corner of the eye, a point corresponding to the jaw joint, etc.) is recorded as feature point information.

[0022] The personal image information generation unit 3 is for generating personal image information, which is information about the person who is the subject of the personal image input by the personal image input unit 1, the shooting time of the personal image, shooting conditions, etc. The specific content of the personal image information includes at least one of personal shooting condition information including information about at least one of the expression and health condition of the person at the time of shooting and information about the shooting date and time of the personal image, and personal shooting device information which is information about the shooting device used for shooting the personal image. More preferably, it includes personal attribute information such as the age (or date of birth) and gender of the person. The specific content of the personal image information includes, in addition to personal attribute information about the target person such as the age (or date of birth) and gender of the target person, information about the shooting device such as the focal length, f-number of the lens used for shooting as personal shooting device information, and the sensitivity of the light-receiving part (film, image sensor), and includes at least one piece of information such as the shooting date and time, the health condition and expression of the person at the time of shooting as personal shooting condition information. As a specific mode of the information generation process by the personal image information generation unit 3, it may be configured to input character information describing such information from the outside, or for information that can be estimated by image analysis processing on the personal image, such as the health condition, expression, age, and gender of the person at the time of shooting, it may be configured to obtain it by image analysis.

[0023] The avatar generation unit 5 is for generating an avatar used by a user in services such as games and SNS. Specifically, for example, based on a full-body photo of the user, the avatar generation unit 5 extracts feature points (such as the centroid position of the eyes, the outer corner of the eyes, the inner corner of the eyes, etc.) set according to surface features (eyes, eyebrows, nose, mouth, ears, hairstyle, etc.), internal features (joints, etc.), and the position and shape of external elements such as clothes, accessories, and items held, and has a function of generating a realistic avatar that reflects the physical characteristics of the user based on the position information of the feature points. As the configuration of the avatar, it preferably consists of skeleton information (bones), surface information (skin), and weight information that defines the relationship between the two, but a simpler configuration such as consisting only of surface information may also be used. Also, when generating an avatar, instead of using the user's full-body photo as a reference, it may be possible to use only the face photo and use general-purpose data for the part below the neck, or it may be a design unrelated to the user's characteristics. The design of the avatar is not limited to realistic ones, but may also be a painterly or animated design. Or only the hairstyle, clothes, accessories such as glasses, rings, and bracelets, and belongings such as bags and umbrellas may be in a form different from the user's real image. Note that the avatar generation process by the avatar generation unit 5 may be in a mode of taking a full-body photo of the user separately from the personal image and generating it based on the full-body photo or the like, or it may be generated using the personal image input through the personal image input unit 1 or / and information about the feature points extracted from the personal image by the personal feature point information generation unit 2.

[0024] The avatar token generation unit 6 is for generating an avatar token, which is a non-fungible token in a correspondence relationship with the avatar generated by the avatar generation unit 5. The "non-fungible token" means a so-called NFT (Non-Fungible Token), that is, a token having the property of being non-substitutable with other tokens by having unique data, and is issued based on, for example, the ERC721 standard of Ethereum (registered trademark). The avatar token in the first embodiment of the present invention is issued based on ERC721 or other predetermined standards, and information such as information about the user of the corresponding avatar and personal feature point information (preferably information obtained by encrypting the personal feature point information, as will be described later) is stored on the blockchain.

[0025] "Blockchain" is a technology that synchronizes data while utilizing cryptographic techniques among multiple computers that make up a distributed network. Specifically, each block is composed of a collection of information regarding tokens such as agreed-upon transaction records, etc., and information for connecting to other blocks (information of the previous block), and a blockchain is formed by connecting a plurality of these blocks. Even if data tampering occurs in some of the multiple computers, correct data is selected by a majority vote among the other computers, so it has the characteristic that it is extremely difficult to destroy or tamper with data.

[0026] As the correspondence relationship between the avatar token and the avatar, it shall be in a form that associates the identifier of the avatar token and the identification information of the avatar (identification information may be attached to each individual avatar, or identification information (such as name) regarding the person targeted by the avatar may be used). More directly, the identifier of the avatar token and the identification information of the avatar may be the same content, or there is no problem in setting the correspondence relationship for those composed of different character strings, etc. Also, it may be in a form that associates with the URL information on the Internet space where the data constituting the avatar is stored.

[0027] Also, in the first embodiment, in the blocks constituting the distributed ledger in correspondence with the generated avatar token, in addition to the transaction record regarding the transfer of the ownership name of the avatar token, personal feature point information regarding the person in correspondence with the avatar (more preferably, the encrypted personal feature point information) shall be recorded. Regarding these pieces of information, they are converted into transactions, which are the information output to the distributed network in correspondence with the avatar token by the transaction generation unit 7.

[0028] Regarding the generation of avatar tokens, the avatar token generation unit 6 may generate them by itself, or it may be in a mode where an external system directly or indirectly connected to the avatar token generation unit 6 generates them by issuing a predetermined command to the external system. Also, the specific form of the avatar token is not limited to one compliant with ERC721, which is the standard of Ethereum (registered trademark), and may be in any form as long as it has the property of non-fungibility and the transaction history is stored on the blockchain.

[0029] The transaction generation unit 7 has a function of generating a transaction to be stored in a block in the distributed ledger, and corresponds to an example of the output information generation means in the claims. Specifically, as the content of the transaction, the transaction generation unit 7 shall generate information including personal feature point information regarding the person corresponding to the corresponding avatar in addition to information regarding the change of the ownership name of the avatar token. Note that the transaction generation unit 7 may generate a transaction in a mode including the personal feature point information as it is, but in the first embodiment, a new encryption processing unit 21 for encrypting the personal feature point information is provided, and the transaction generation unit 7 shall generate a transaction including the personal feature point information encrypted by the encryption processing unit 21. Any mode of encryption by the encryption processing unit 21 can be used. For example, the personal feature point information may be encrypted using a private key described later.

[0030] The electronic signature generation unit 8 has a function of generating an electronic signature which is data for proving that the creation / output of the information included in the transaction follows the intention of the avatar token holder. Specifically, the electronic signature generation unit 8 has a function of generating a hash value of the transaction generated by the transaction generation unit 7 and encrypting the hash value with the private key held by the promaide token holder to generate an electronic signature. Note that the "hash value" is a fixed-length value obtained by performing a certain calculation procedure on the original data. Since the calculation procedure is irreversible, it is considered impossible to restore the original data from the hash value. Also, the "private key" is a sequence of numbers used for the encryption process, and it has a configuration that can be decrypted by the corresponding "public key". In the first embodiment, the transaction generation unit 7 and the electronic signature generation unit 8 are configured to perform the creation of the transaction and the electronic signature, which are one aspect of the ownership change information, by themselves, but it is not necessary to be limited to this. The transaction generation unit 7 and the electronic signature generation unit 8 may have only a function of instructing an external predetermined device to create the transaction and the electronic signature.

[0031] The output unit 9 is for instructing to output the transaction generated by the transaction generation unit 7 and the electronic signature generated by the electronic signature generation unit 8 to a distributed network associated with the avatar token. The output unit 9 functions as an aspect of the output instruction means (output instruction step in the invention of the method). In the present embodiment, it is configured to directly output the transaction and the electronic signature, but it may also be configured to only instruct other components (including those provided outside the personal authentication system according to Embodiment 1) to output. In the first embodiment, the output unit 9 is directly or indirectly connected to the distributed network and is configured in a manner capable of outputting predetermined data to the distributed network. The distributed network generates a hash value of the output transaction and compares it with the data obtained by decrypting the electronic signature with the public key (= the hash value of the transaction). If the two values are different, it is determined that the transaction is not by the owner of the tangible object and the registration is rejected. If the two values match, it is determined that the transaction is by the owner, and the information constituted by the transaction is stored in the block constituting the distributed ledger. The transaction output by the output unit 9 includes information related to the personal feature point information. When the transaction is output to the distributed network, this information is stored in the block constituting the distributed ledger provided on the distributed network.

[0032] The transaction acquisition unit 10 is for acquiring the transactions recorded in the distributed ledger, and corresponds to the output information generation means (or the output generation step in the invention of the method). Specifically, the transaction acquisition unit 10 has a function of accessing the distributed ledger corresponding to the avatar for which the personal authentication process for the user is to be performed, and acquiring the personal feature point information (or the information obtained by encrypting the personal feature point information by the encryption processing unit 20). As a mechanism for accessing the corresponding transaction, for example, it may include identification information common to the avatar corresponding to the transaction in the transaction, or information regarding the correspondence with the avatar may be added to the distributed ledger itself storing the transaction.

[0033] The personal feature point information extraction unit 11 is for extracting the personal feature point information corresponding to the avatar for which the personal authentication process is to be performed from the transaction acquired by the transaction acquisition unit 10. When the personal feature point information is included in the transaction in its original state, the personal feature point information is extracted by selecting the corresponding part from the transaction. On the other hand, in the first embodiment, since the personal feature point information is encrypted by the encryption processing unit 21 and then included in the transaction, the personal feature point information extraction unit 11 has a function of performing decryption processing on the encrypted part by the newly provided decryption processing unit 22 and then extracting the personal feature point information.

[0034] The target image input unit 12 is for inputting a target image, which is an image of a target person who is the person to be authenticated during the authentication process. The form of the target image may be either a still image or a moving image, and it may be composed not only of a single image data but also of a plurality of image data taken from different directions. Regardless of whether it is in color or black and white, it may be either a two-dimensional image or a three-dimensional image. However, from the perspective of avoiding complication of the authentication process, it is preferable that the format of the target image is the same as the format of the personal image input via the personal image input unit 1. As for the specific configuration of the target image input unit 12, it may be configured to input a target image taken by a portable terminal held by the target person. However, from the perspective of preventing forgery of the target image, etc., it is also preferable to configure it to input only the video taken by a photographing device incorporating an anti-fraud mechanism (including not only the case where it is provided within the system but also the case where it is provided outside the system) provided in the personal authentication system according to the first embodiment.

[0035] Similar to the personal feature point information generation unit 2, the target feature point information generation unit 13 has a function of extracting a plurality of predetermined feature points corresponding to characteristic parts such as eyes, nose, mouth, ears, etc. on the face and connection points of the jaw skeleton from the target image input via the target image input unit 12, and generating target feature point information, which is information on the positional relationship between the plurality of feature points. As for the specific configuration of the target feature point information generation unit 13, image recognition technology realized by deep learning, machine learning, etc. may be used, or a combination of a plurality of image recognition technologies may be used. Also, regarding the feature points extracted by the target feature point information generation unit 13, although it may be arbitrarily determined which parts should be set as feature points, preferably, for the parts that are the same or common as the feature points extracted by the personal feature point information generation unit 2, they are extracted as feature points.

[0036] The target image information generation unit 14 generates target image information including at least one of information regarding at least one of the expression and health condition of the target person at the time of shooting and information regarding the shooting date and time of the target image with respect to the target image input by the target image input unit 12, and information on the shooting device used for shooting the target image, i.e., target shooting device information. More preferably, it is for generating target image information including target attribute information such as the age (date of birth) and gender of the target person. As specific contents of the target image information, in addition to target attribute information regarding the target person such as the age (or date of birth) and gender of the target person, information regarding the shooting device such as the focal length of the lens used for shooting, f-value, and sensitivity of the light-receiving part (film, image sensor) as the target shooting device information, and at least one or more pieces of information among the shooting date and time, the health condition of the target person at the time of shooting, the expression, etc. as the target shooting condition information are included. Preferably, it includes the same items as the personal image information. As a specific mode of the information generation process by the target image information generation unit 14, it may be configured to input character information describing these information from the outside, or for information that can be estimated by image analysis processing on the target image, such as the age, gender, and expression at the time of shooting of the person himself, it may be configured to obtain it by image analysis.

[0037] The image information comparison unit 15 is for comparing the personal image information generated by the personal image information generation unit 3 and the target image information generated by the target image information generation unit 14, and outputting the comparison result to the feature point information correction unit 16. Specifically, the image information comparison unit 15 compares common items (such as the shooting date) for each of the personal image information and the target image information, and has a function of extracting differences when there are differences in content (or when the differences are greater than or equal to a predetermined threshold) and outputting them as the comparison result. As a specific extraction mode of the differences, for example, it may be to simply extract the difference value for numerical information, but more preferably, it has a function of extracting the content of the information in each of the personal image information and the target image information, and outputting, as the comparison result, a list of the values of both instead of the difference value between the two for, for example, the focal length of the lens as information regarding the shooting device. When there are no differences or the differences are less than a predetermined threshold in each item, it may be to output a comparison result of "no difference", or it may be not to output any comparison result at all.

[0038] The feature point information correction unit 16 is for correcting the positional relationship between feature points in at least one of the personal feature point information and the target feature point information according to the difference between the personal image information and the target image information based on the comparison result by the image information comparison unit 15. Specifically, the feature point information correction unit 16 has a function of estimating the positional relationship between feature points when one image is shot under the conditions of the other image information instead of the conditions of its own image information based on the comparison result for each of one or more pieces of information among the shooting device information, shooting condition information, and attribute information in the image information, and then correcting the feature point information regarding the image.

[0039] For example, the feature point information correction unit 16 compares the shooting date and time of the personal image included in the personal shooting condition information with the shooting date and time of the target image included in the target shooting condition information. For example, when the shooting date and time of the target image is 10 years after the shooting date and time of the personal image, for the personal image, it is inferred how the positional relationship between the feature points changes due to aging and other secular changes when shooting 10 years after the actual shooting date and time, and the content of the personal feature point information is corrected based on the inference result. (In this case, it is also preferable to calculate the specific age based on the attribute information and then infer the secular change.) Further, for example, when the expression of the person is recorded as a smiling face in the personal shooting condition information and the expression of the target person is recorded as an angry face in the target shooting condition information, the feature point information correction unit 16 infers how the positional relationship between the feature points changes when the target image is shot with a smiling face instead of an angry face, and corrects the content of the target feature point information based on the inference result. Similarly, when the health state differs as the appearance such as the shape of the face changes, for the personal image, the feature point information correction unit 16 infers how the positional relationship between the feature points on the personal image changes when the health state of the subject in the target image is used instead of the health state of the person at the time of shooting the personal image, and then changes the positional relationship between the feature points in the personal feature point information based on the inference result.

[0040] In addition, the feature point information correction unit 16 has a function of correcting the information regarding the positional relationship of the feature points included in the personal feature point information based on the comparison result between the personal photographing device information, which is information regarding the characteristics of the photographing device that captured the personal image, and the target photographing device information, which is information regarding the characteristics of the photographing device that captured the target image, so that the positional relationship is the one when the image is captured by the photographing device that captured the target image instead of the photographing device that captured the personal image. For example, when the personal image is captured with a so-called wide-angle lens having a short focal length, compared with the case of a telephoto lens, the captured image of the face has an inflated appearance, and accordingly, the positions of the feature points in the personal image and the target image also vary from the positions when captured with a telephoto lens. Similarly, since the depth of focus differs if the focal length and f-value of the lens are different, the positions of the feature points in the personal image and the target image vary according to these differences. In view of the fact that the positions of the feature points derived from the captured image vary according to the characteristics of the photographing device even for the same subject, the feature point information correction unit 16 infers how the positional relationship between the feature points on the personal image changes when the personal image is captured not under the conditions recorded in the personal photographing device information but under the conditions recorded in the target photographing device information, and then changes the positional relationship between the feature points in the personal feature point information based on the inference result.

[0041] Regarding the specific algorithm for inferring how the positional relationship between the feature points changes based on the differences in each information, it may be generated by, for example, machine learning, deep learning, or reinforcement learning. Alternatively, a large number of specific examples, such as changes in the captured image due to differences in the photographing device, may be collected, and when correcting the personal feature point information, the example of the image closest to the content of the comparison result to be referred to may be extracted from the collection examples, and the correction content may be determined according to this. Also, when there is no difference between the image information or when the difference is only a minor difference, the feature point information correction unit 16 outputs each feature point information as it is to the authentication processing unit 17 without performing any special correction.

[0042] The authentication processing unit 17 is for performing an authentication process which is a process of determining the presence or absence of identity between the target person in the target image and the person in the personal image by comparing the two feature point information using the personal feature point information and the target feature point information corrected by the feature point information correction unit 16 as necessary. Specifically, the authentication processing unit 17 compares the information regarding the positional relationship of the feature points included in each of the personal feature point information and the target feature point information (the original personal feature point information and target feature point information if no correction is made) corrected by the feature point information correction unit 16, and performs the authentication process by detecting the similarities and differences in the positional relationship between a plurality of feature points in a corresponding relationship. That is, when the positional relationship between the corresponding feature points is the same, or when the difference, although not the same, is considered to be within the identity range and less than a predetermined reference value, the authentication processing unit 17 has a function of determining that the target person who is the subject of the target image is the same person as the person who is the subject of the personal image. Further, when the difference in the positional relationship between the corresponding feature points is equal to or greater than a predetermined reference value, the authentication processing unit 17 has a function of making a determination to deny the identity. As a processing mode of the authentication processing unit 17, it may be to determine the similarities and differences in the positional relationship with the feature points of the target image for all the feature points included in the personal feature point information, or it may be to determine the similarities and differences only for the positional relationship regarding a predetermined part of important feature points. Also, when the determination results are different for each feature point, such as the difference in the positional relationship between some feature points being equal to or greater than the reference value and the positional relationship between other feature points being the same, it may be to perform the authentication process regarding the presence or absence of identity according to whether the total amount of the differences exceeds a predetermined threshold value, or according to the proportion of the pairs of feature points with differences equal to or greater than the reference value. Note that the determination result by the authentication processing unit 17 is output to the authentication display instruction unit 18 together with the information regarding the date and time when the determination process is performed. Note that the execution timing of the authentication process by the authentication processing unit 17 may be any timing, but preferably it may be performed during the interaction (message exchange, delivery of items or things with monetary value, delivery of money, etc.) with other users in the service where the avatar is used.

[0043] The authentication display instruction unit 18 is for instructing to display, in a state attached to the avatar, an authentication display consisting of content according to the authentication result by the authentication processing unit 17 when the avatar corresponding to the user is displayed in services such as SNS and games. As a more preferable aspect, the authentication display instruction unit 18 has a function of instructing to change the display content according to the display to that effect and the passage of time since the completion of the authentication processing when the target person is authenticated as being the same as the user by the authentication processing unit 17. Specifically, the authentication display instruction unit 18 has a function of instructing to generate, in services where avatars such as games and SNS are used, an authentication display that is visually displayed attached to the avatar when the avatar is displayed and that can be visually recognized by other users as indicating "authenticated as the user". Note that "attached to the display of the avatar" means being displayed in the vicinity of the avatar displayed during the service in which the avatar is used, but it may also be displayed in a state integrally attached to the avatar, or as a display that modifies part or all of the avatar itself (for example, putting a special hat on the head, giving the whole a glossy feeling, etc.). Further, the authentication display instruction unit 18 may simply instruct to display an indication that the authentication process has been performed as the authentication display, but more preferably, it notifies information regarding the date and time when the authentication process was completed at the time of instruction and instructs to perform a display that visually changes according to the passage of time since the date and time when the authentication process was completed. As an aspect of such a change, examples include a change in the hue, saturation, and lightness of the authentication display according to the passage of time (for example, the color of the authentication display becomes lighter and eventually disappears according to the passage of time), and a change in shape, but other change aspects may also be possible.

[0044] The authentication display generation unit 19 is for generating a specific authentication display based on the instruction of the authentication display instruction unit 18. The authentication display generation unit 19 determines the specific content of the authentication display that is visually displayed along with the avatar and generates image data. The authentication display as the generated image data is output toward the service where the avatar is used via the authentication video output unit 20. When the authentication display is simply a display indicating that the authentication process has been performed, the authentication display generation unit 19 only generates a single piece of image data. On the other hand, when the authentication display is in a form that changes according to the passage of time since the completion of the authentication process, a plurality of pieces of image data are prepared, and information regarding the display timing of the plurality of pieces of image data (from the completion of the authentication process until one month has passed, from one month after the authentication process until six months have passed since the completion of the authentication process, etc.) is also generated together.

[0045] The authentication display output unit 20 is for outputting information regarding the authentication display generated by the authentication display generation unit 19 toward external services such as games and SNS where the avatar is used. Specifically, the authentication display output unit 20 has a function of outputting the image data generated as information regarding the authentication display (when a plurality of pieces of image data are generated, the data describing the plurality of pieces of image data and the display timing of each piece of image data). The output image data, etc. are displayed along with the avatar in an external service, and other users can visually grasp information such as the fact that the person authentication has been performed for the avatar, the person authentication has been performed but a certain period of time has passed since the authentication process (= there is a certain possibility that the user has changed thereafter), and the person authentication process has not been performed. As a modification example, after omitting the authentication display generation unit 19, the authentication display output unit 20 directly outputs a display instruction regarding the authentication display generated by the authentication display instruction unit 18 toward an external service, and in the external service, a configuration may be adopted in which specific authentication display images, etc. are generated in the same manner as the authentication display generation unit 19.

[0046] Next, the advantages of the personal authentication system according to Embodiment 1 will be described. First, the personal authentication system according to Embodiment 1 adopts a configuration in which authentication processing is performed by comparing personal feature point information, which is information on the positional relationship between a plurality of feature points extracted from a personal image, as reference information used at the time of authentication, with target feature point information extracted from a target image. Such feature point information is composed of a very small amount of information as compared with the image data itself, while depicting in detail the features of a person's face. Therefore, the personal authentication system according to Embodiment 1 has the advantage that highly accurate personal authentication processing can be realized with a small amount of information.

[0047] In addition, the personal authentication system according to Embodiment 1 adopts a configuration in which personal image information and target image information are compared during the authentication process, and the personal authentication process is performed after appropriately correcting the personal feature point information and / or the target feature point information based on the differences. By adopting such a configuration, the personal authentication system according to Embodiment 1 can correct to an appropriate value when the information on the positional relationship between the feature points is different from the appropriate content at the time of authentication due to differences in imaging devices, expressions, ages, etc. at the time of imaging. By adopting such a configuration, there is an advantage that more highly accurate personal authentication processing can be realized.

[0048] Furthermore, the personal authentication system according to Embodiment 1 has a configuration in which personal feature point information used as reference information during authentication processing is stored in a distributed ledger. By using blockchain, it becomes extremely difficult to destroy or falsify the data constituting the personal feature point information. Therefore, the personal authentication system according to Embodiment 1 has the advantage of being able to effectively prevent the forgery of materials used in the authentication process. In addition, in Embodiment 1, since the personal feature point information is encrypted and then stored in a distributed ledger, even in a system accessible to an unspecified number of people such as a public blockchain, a third party cannot grasp the content of the personal feature point information in advance. For example, it is possible to prevent fraud such as tampering with a target image so that target feature point information that matches the personal feature point information in advance is generated by the target person. From this perspective as well, it has the advantage of being able to effectively prevent the forgery of materials used in the authentication process.

[0049] Also, the personal authentication system according to Embodiment 1 is configured to perform an authentication display according to the result of the authentication process in association with the display of the used avatar. By adopting such a configuration, for a third party other than the avatar user (for example, another avatar user using the same service), it is possible to determine whether the avatar has been authenticated (that is, whether there is evidence that the avatar is being used by the person himself / herself), and how much time has passed since the authentication was performed (while there is evidence that the person has used it in the past, whether there is a certain degree of risk of impersonation by others depending on the passage of time). It has the advantage that a third party can easily grasp the authentication result.

[0050] (Embodiment 2) Next, the personal authentication system according to Embodiment 2 will be described. In Embodiment 2, with respect to the components having the same name and the same reference numerals as those in Embodiment 1, unless otherwise specified, they shall exhibit the same functions as the components in Embodiment 1.

[0051] Figure 2 shows that the personal authentication system according to Embodiment 2 includes an object image storage unit 24 that stores object images determined to be personal images among the object images used in past authentication processes, and a variation mode detection unit 25 that detects the variation mode of the positions of common points in the object images and personal images stored in the object image storage unit 24. The feature point information correction unit 26 has a function of estimating the secular change in the positional relationship of feature points due to differences in shooting times based on the shooting condition information, based on the variation mode derived by the variation mode detection unit 25.

[0052] The object image storage unit 24 is for storing object images determined to be personal images by the authentication process (more precisely, object images in the case where it is determined that the person who is the subject of the personal image and the subject person who is the subject of the object image are the same person). Specifically, the object image storage unit 24 has a function of storing, for object images determined to be personal images by the authentication unit 17, the object image information including information regarding the shooting time of the object image, the shooting device, etc.

[0053] The variation mode detection unit 25 is for deriving variation mode information, which is information regarding how the positional relationship of feature points extracted from the personal image varies over time, using past object images stored in the object image storage unit 24 and determined to have the same subject person as the personal image. Specifically, the variation mode detection unit 25 first derives, based on the object image information associated with each object image, the positional relationship between the feature points on the object image when the object image is taken by the same shooting device as the personal image and has the same expression as the personal image of the personal image. Next, the variation mode detection unit 25 has a function of detecting how the positional relationship between the feature points under the same conditions and the same expression varies according to the shooting time of the personal image and the shooting times of the respective object images, and generating the detection result as variation mode information.

[0054] The feature point information correction unit 26 has the same function as the feature point information correction unit 16 in Embodiment 1, and based on the difference between the time of capturing the personal image and the time of capturing the target image in relation to the new target image input through the target image input unit 12, when changing the position of each feature point based on the personal image to a position considering fluctuations due to aging and other secular changes, the fluctuation mode information derived by the fluctuation mode detection unit 25 is used. By utilizing the fluctuation mode information, which is information regarding the fluctuation mode of the positional relationship between the actual feature points of the individual, the feature point information correction unit 26 can more accurately derive the positional relationship of the feature points of the personal image at the time of capturing the newly input target image.

[0055] As described above, the content of the present invention has been explained over Embodiments 1 and 2. However, of course, the technical scope of the present invention should not be construed as being limited to the specific configurations described in the embodiments. As long as the functions of the present invention can be realized, various modifications and application examples to the above embodiments also naturally belong to the technical scope of the present invention.

Industrial Applicability

[0056] The present invention can be used as a technology that realizes highly accurate personal authentication processing with a small amount of information, effectively prevents forgery of materials used in the authentication process, and enables a third party to easily understand the authentication result.

Explanation of Signs

[0057] 1 Personal image input unit 2 Personal feature point information generation unit 3 Personal image information generation unit 5 Avatar generation unit 6 Avatar token generation unit 7 Transaction generation unit 8 Electronic signature generation unit 9 Output unit 10 Transaction acquisition unit 11 Personal feature point information extraction unit 12 Target image input unit 13 Target feature point information generation unit 14 Target Image Information Generation Unit 15 Image Information Comparison Unit 16, 26 Feature Point Information Correction Unit 17 Authentication Processing Unit 18 Authentication Display Instruction Unit 19 Authentication Display Generation Unit 20 Authentication Display Output Unit 21 Encryption Processing Unit 22 Decryption Processing Unit 24 Target Image Storage Unit 25 Variation Pattern Detection Unit

Claims

1. An identity authentication system that determines whether a person using an avatar in a predetermined service is the same person as the person, for an avatar that has been set to correspond to the person, comprising: an identity feature information generating means for extracting a plurality of feature points from an identity image that is an image of the identity of the person, and generating identity feature information that is information regarding positional relationships between the plurality of feature points; a target feature point information generating means for extracting a plurality of feature points from a target image which is an image of a target person who is a person to be authenticated, and generating target feature point information which is information regarding positional relationships between the plurality of feature points; an authentication processing means for comparing a positional relationship between a plurality of feature points in the person's image included in the person's feature point information with a positional relationship between a plurality of feature points in the target image included in the target feature point information, and performing authentication processing regarding the presence or absence of identity between the target person and the person based on a comparison result; an authentication display instruction means for instructing, when a result of the authentication processing by the authentication processing means recognizes the identity between the target person and the person himself / herself, to display an authentication display corresponding to the fact that the person has been authenticated, in association with the display of the avatar in the specified service, and for instructing to change the display content of the authentication display according to the elapsed time from the completion of the authentication processing; An identity authentication system comprising:

2. a personal image information generating means for generating personal image information including at least one of personal image photographing condition information including information regarding at least one of the facial expression and health condition of the person at the time of photographing and information regarding the photographing date and time of the personal image, and personal image photographing device information which is information regarding the photographing device used to photograph the personal image; a target image information generating means for generating target image information including at least one of target photographing condition information including information regarding at least one of a facial expression and a health condition of a target person at the time of photographing and information regarding a photographing date and time of the target image, and target photographing device information which is information regarding a photographing device used to photograph the target image; an image information comparison means for comparing the principal image information with the target image information; a feature point information correcting means for correcting a positional relationship between feature points in at least one of the personal feature point information and the target feature point information according to a difference between the personal image information and the target image information based on a comparison result by the image information comparing means; Further equipped with 2. The personal authentication system according to claim 1, wherein said authentication processing means performs authentication processing based on said personal feature point information and / or said target feature point information corrected by said feature point information correction means.

3. 1. A method for authenticating an individual, comprising: determining whether or not a person using an avatar in a predetermined service is the same as the individual, the method comprising the steps of: a personal feature point information generating step of extracting a plurality of feature points from a personal image that is an image of the person, and generating personal feature point information that is information regarding positional relationships between the plurality of feature points; a target feature point information generating step of extracting a plurality of feature points from a target image which is an image of a target person who is a person to be authenticated, and generating target feature point information which is information regarding positional relationships between the plurality of feature points; an authentication processing step of comparing a positional relationship between a plurality of feature points in the person image included in the person feature point information with a positional relationship between a plurality of feature points in the target image included in the target feature point information, and performing authentication processing regarding the presence or absence of identity between the target person and the person based on a comparison result; an authentication display instruction step of instructing, when a result of the authentication process in the authentication process step recognizes the identity between the target person and the person himself / herself, to display an authentication display corresponding to the fact that the person has been authenticated, in association with the display of the avatar in the predetermined service, and instructing to change the display content of the authentication display according to the elapsed time from the completion of the authentication process; A method for authenticating an individual, comprising:

4. an encryption processing step of encrypting the personal feature information; an output information generating step of generating output information including encrypted personal feature information regarding the person in correspondence with the avatar, the output information being recorded in a distributed ledger on a distributed network corresponding to a non-fungible token in correspondence with the avatar; an output instruction step of instructing the distributed network to output the output information generated in the information generation step; An output information acquisition step of acquiring the output information from information recorded in a distributed ledger on the distributed network; a decoding process step of decoding the personal feature information included in the output information acquired in the output information acquisition step; 4. The method according to claim 3, further comprising: a step of: using the personal feature information decrypted in the decryption step for authentication processing in the authentication processing step.

5. An identity authentication program that causes a computer to determine whether a person using an avatar in a predetermined service is the same person as the person, the program comprising: The computer is an identity feature information generating function for extracting a plurality of feature points from an identity image, which is an image of the identity of the person, and generating identity feature information, which is information regarding positional relationships between the plurality of feature points; Extracting a plurality of feature points from a target image, which is an image of a target person that is a person to be authenticated; a target feature point information generating function for generating target feature point information which is information regarding positional relationships between the plurality of feature points; an authentication processing function for comparing a positional relationship between a plurality of feature points in the person's image included in the person's feature point information with a positional relationship between a plurality of feature points in the target image included in the target feature point information, and performing authentication processing regarding the presence or absence of identity between the target person and the person based on a comparison result; an authentication display instruction function which, when a result of the authentication processing by the authentication processing function recognizes the identity between the target person and the person himself / herself, instructs the display of the authentication display corresponding to the fact that the person has been authenticated to be displayed in association with the display of the avatar in the specified service, and instructs the display content of the authentication display to be changed according to the elapsed time from the completion of the authentication processing; A personal authentication program characterized by executing the above.

Images