Authentication device, authentication method, and program

Abstract

Provided is a technology relating to an authentication device that further enhances authentication accuracy. This authentication device is connected to a storage means which corresponds to an identifier of a class of first biological information subjected to class classification and which stores therein second biological information of a person corresponding to the first biological information. The authentication device specifies, among the first biological information and the second biological information of the person that is included in one image, the identifier of the class obtained by classification of the first biological information. The authentication device performs authentication using: second biological information of a plurality of persons that is stored by the storage means corresponding to the identifier of the class of the first biological information; and second biological information that is included in the image.

Description

[Technical Field]

[0001] The present invention relates to an authentication device, an authentication method, and a program. [Background technology]

[0002] Technologies for authenticating people in images are widely used. Patent Document 1 discloses a technology in which the iris patterns of the right and left eyes are registered in a database, and the iris patterns of the right and left eyes photographed by a camera are compared with the iris patterns of the right and left eyes registered in the database. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2017-142772 Summary of the Invention [Problem to be solved by the invention]

[0004] In the authentication technology described above, there is a demand for technology that can further improve authentication accuracy.

[0005] SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide an authentication device, an authentication method, and a program that solve the above-mentioned problems. [Means for solving the problem]

[0006] According to a first aspect of the present invention, an authentication device is provided with: a class identification means connected to a storage means that stores second biometric information of a person of classified first biometric information in a storage means corresponding to a class identifier of the first biometric information; a class identification means that identifies a class identifier of the first biometric information and the second biometric information of a person included in an image, based on the class classification of the first biometric information; and an authentication means that performs authentication using the second biometric information of a plurality of people stored in the storage means that corresponds to the class identifier of the first biometric information, and the second biometric information included in the image.

[0007] According to a second aspect of the present invention, an authentication method includes an authentication device connected to a storage means for storing second biometric information of a person of classified first biometric information in a storage means corresponding to a class identifier of the first biometric information, identifying a class identifier based on the class classification of the first biometric information from the first biometric information and the second biometric information of a person included in an image, and performing authentication using the second biometric information of multiple people stored in the storage means corresponding to the class identifier of the first biometric information and the second biometric information included in the image.

[0008] According to a third aspect of the present invention, a program causes a computer of an authentication device connected to a storage means that stores second biometric information of a person of classified first biometric information in a storage means that corresponds to a class identifier of the class of the first biometric information to function as: a class identification means that identifies a class identifier of the first biometric information and the second biometric information of a person included in an image, based on the class classification of the first biometric information; and an authentication means that performs authentication using second biometric information of a plurality of people stored in the storage means that corresponds to the class identifier of the first biometric information, and the second biometric information included in the image. [Effects of the Invention]

[0009] According to the present invention, it is possible to improve the accuracy of authentication using an image. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a diagram showing a schematic configuration of an authentication system including an authentication device according to an embodiment of the present invention. [Figure 2] FIG. 2 is a hardware configuration diagram of the authentication device according to the present embodiment. [Figure 3] FIG. 2 is a functional block diagram of the authentication device according to the present embodiment. [Figure 4] FIG. 10 is a diagram showing a processing flow of the authentication device in the registration processing according to the present embodiment. [Figure 5]FIG. 10 is a diagram showing a processing flow of the authentication device in the authentication process according to the present embodiment. [Figure 6] FIG. 10 is a first diagram showing a schematic configuration of an authentication system including an authentication device according to another embodiment. [Figure 7] FIG. 2 is a second diagram showing a schematic configuration of an authentication system including an authentication device according to another embodiment. [Figure 8] FIG. 10 is a third diagram showing a schematic configuration of an authentication system including an authentication device according to another embodiment. [Figure 9] FIG. 2 is a diagram showing a minimum configuration of an authentication device according to the present embodiment. [Figure 10] FIG. 10 is a diagram showing a processing flow of an authentication device with a minimum configuration according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] An authentication device according to an embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a diagram showing a schematic configuration of an authentication system including an authentication device according to this embodiment. The authentication device 1 is connected to and communicates with a mobile terminal 2 such as a smartphone, for example. The user takes a picture of their own face using a camera 3 provided on the mobile terminal 2. The authentication device 1 acquires the image generated by the photograph from the mobile terminal 2 and authenticates the user. The image shows the user's face. The authentication device 1 performs authentication using iris information and facial feature information in the image. In this embodiment, the iris information is the person's first biometric information, and the facial feature information is the person's second biometric information. The authentication device 1 performs authentication using these two pieces of biometric information captured in a single image. The biometric information is an example of feature information.

[0012] FIG. 2 is a hardware configuration diagram of the authentication device according to this embodiment. As shown in this diagram, the authentication device 1 is a computer equipped with various hardware components such as a CPU (Central Processing Unit) 101, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, a HDD (Hard Disk Drive) 104, a database 105, and a communication module 106. The mobile terminal 2 may also have a similar hardware configuration. The authentication device 1 is equipped with multiple databases 105. Note that the databases 105 may be configured as devices separate from the authentication device 1.

[0013] FIG. 3 is a functional block diagram of the authentication device according to this embodiment. When the CPU 101 starts the authentication program, the authentication device 1 performs the functions of an acquisition unit 11, a class identification unit 12, a registration unit 13, an authentication unit 14, and an output unit 15. The acquisition unit 11 acquires an image from the mobile terminal 2. The class identifying unit 12 identifies a class identifier based on the class classification of the iris information of the eye of a person included in an image (first biometric information) and facial feature information (second biometric information). The registration unit 13 registers the facial feature information of the person in a database corresponding to the class identifier of the iris information. The authentication unit 14 authenticates the person using facial feature information of a plurality of people stored in a database corresponding to the class identifier of the iris information and facial feature information of the person included in the image. The output unit 15 outputs the authentication result.

[0014] In this embodiment, the registration unit 13 classifies each piece of iris information for the left eye and the right eye included in the image acquired in the registration process, and registers facial feature information of the person appearing in the image in database 105 corresponding to the class ID of the iris information for the left eye and the class ID of the iris information for the right eye. The authentication unit 14 classifies each piece of iris information for the left eye and the right eye included in the image newly acquired for authentication, and performs authentication using the facial feature information of multiple people stored in database 105 that corresponds to each identifier of the class ID of the iris information for the left eye and the class ID of the iris information for the right eye, and the facial feature information of the person included in the image newly acquired for authentication.

[0015] The authentication device 1 of this embodiment has a plurality of databases 105 that can be uniquely identified by two identifiers: a class ID for the right eye and a class ID for the left eye. For example, if the class ID for the right eye is 10 and the class ID for the left eye is 10, the authentication device 1 has 10*10=100 databases 105 (where "*" indicates multiplication). If the class ID for the right eye E1 and the class ID for the left eye E2 are represented as (E1, E2), each database 105 can be identified as one of the 100 databases 105: (0,0), (0,1), (0,2), (0,9), (1,0), (1,1), (1,2), (1,9), (9,0), (9,1), (9,2), (9,9).

[0016] The authentication device 1 stores information about a classification model that outputs a class ID when information about the eye area of ​​a face captured in an image is input and the eye features are classified into classes. When an image is acquired, the class identification unit 12 of the authentication device 1 inputs information about the eye area contained in the image into a neural network or the like generated using the classification model, and outputs a class ID as a result. The classification model is information obtained by machine learning the relationship between a large number of eye images and correct data for the eye class IDs contained in the image, and includes, for example, information such as neural network weights. The class identification unit 12 uses this classification model to identify the class ID of the left eye and the class ID of the right eye. For example, the eye features are classified into classes based on features such as the radius of the eye pupil and color. The authentication device 1 may generate the classification model using a method other than machine learning when using a neural network.

[0017] FIG. 4 is a diagram showing a processing flow of the authentication device in the registration process. In the registration process, the user takes a picture of their own face using the portable terminal 2. The portable terminal 2 generates an image based on the image. The image shows the user's face. The more pixels the image has, the better. The user instructs the portable terminal 2 to start the registration process. The portable terminal 2 sends a registration request including the image to the authentication device 1.

[0018] The authentication device 1 receives a registration request. The acquisition unit 11 of the authentication device 1 acquires an image included in the registration request (step S101). The acquisition unit 11 determines whether a face can be detected from the image (step S102). If the acquisition unit 11 cannot detect a face, it ends the registration process. If the acquisition unit 11 detects a face, it generates facial feature information based on the facial area included in the image (step S103).

[0019] The acquisition unit 11 outputs the image to the class identification unit 12. The class identification unit 12 determines whether the iris of the left eye of the face shown in the image can be detected (step S104). If the iris of the left eye can be detected, the class identification unit 12 identifies the class ID of the left eye. Specifically, the class identification unit 12 inputs information about the left eye area into a neural network using a classification model, and as a result, outputs the class ID of the left eye (step S105).

[0020] The class identification unit 12 also determines whether the iris of the right eye of the face captured in the image can be detected (step S106). If the iris of the right eye can be detected, the class identification unit 12 identifies the class ID of the right eye. Specifically, the class identification unit 12 inputs information about the area of ​​the right eye into a neural network using a classification model, and outputs the class ID of the right eye as a result (step S107). If the iris of the left eye or right eye cannot be detected, the class identification unit 12 may output information indicating that the class ID of the left eye or right eye cannot be identified.

[0021] The class identification unit 12 outputs an output result indicating the left eye class ID, the right eye class ID, and information indicating that the left eye or right eye class ID is unspecifiable, and the image, to the registration unit 13. The registration unit 13 uses the left eye class ID, the right eye class ID, information indicating that the left eye class ID is unspecifiable, and information indicating that the right eye class ID is unspecifiable from the output result to identify the database 105 to which the facial feature information is to be registered (step S108). When the registration unit 13 has identified both the left eye class ID and the right eye class ID, it identifies only the database 105 corresponding to the left eye class ID and the right eye class ID as the database 105 to which the facial feature information is to be registered. For example, when the left eye class ID is "1" and the right eye class ID is "3", the registration unit 13 identifies the database 105 corresponding to the information of (1, 3) as the database to which the facial feature information is to be registered. The processing of the registration unit 13 is one aspect of processing in which each of the iris information of the left eye and the right eye, which is the first biometric information, is classified into classes, and the second biometric information (facial feature information) of the person of the first biometric information is registered in a storage means corresponding to the class identifier of the iris information of the left eye and the class identifier of the iris information of the right eye.

[0022] When only the class ID of the left eye has been identified, the registration unit 13 identifies multiple databases 105 corresponding to the class ID of the left eye as databases 105 to which facial feature information should be registered. Specifically, when the class ID of the left eye is "5" and the class ID of the right eye has not been identified, the registration unit 13 identifies ten databases 105, (5,0), (5,1)...(5,9), as databases to which facial feature information should be registered. The processing of the registration unit 13 is one aspect of processing to register the second biometric information (facial feature information) of the person of the first biometric information in all storage means identified by all identifiers of the class related to the left eye, when only the class identifier based on the class classification of the iris information of the left eye, which is the first biometric information, has been identified.

[0023] When only the class ID of the right eye has been identified, the registration unit 13 identifies multiple databases 105 corresponding to the class ID of the right eye as databases 105 to which facial feature information should be registered. Specifically, when the class ID of the right eye is "4" and the class ID of the left eye has not been identified, the registration unit 13 identifies ten databases 105, (4,0), (4,1)...(4,9), as databases to which facial feature information should be registered. The processing of the registration unit 13 is one aspect of processing to register the second biometric information (facial feature information) of the person of the first biometric information in all storage means identified by all identifiers of the class related to the right eye, when only the class identifier based on the class classification of the iris information of the first biometric information has been identified.

[0024] If neither the class ID of the left eye nor the class ID of the right eye can be identified, the registration unit 13 identifies all of the databases 105 as the databases 105 to which the facial feature information is to be registered. Specifically, if neither the class ID of the left eye nor the class ID of the right eye can be identified, the registration unit 13 identifies 100 databases 105 as the databases 105 to which the facial feature information is to be registered: (0,0), (0,1), (0,2), (0,9), (1,0), (1,1), (1,2), (1,9), (9,0), (9,1), (9,2), (9,9). The registration unit 13 registers the facial feature information in the databases 105 identified as the registration destinations (step S109). The authentication device 1 further includes a database 105 that indicates neither the left eye class ID nor the right eye class ID (null, null), and registers the facial feature information of all users who have requested registration in this database.

[0025] As a result, if the class ID of the eye classification class can be identified from the image, the user's facial feature information is registered in only one of all databases 105 in which the authentication device 1 registers facial feature information, or in only the databases 105 equal to the class ID of the left eye or right eye. Here, for example, twins have a high correlation in facial feature information. Therefore, if facial feature information for each twin is registered in a single database 105 and authentication processing is performed using the registered facial feature information, the calculation result for authenticating one twin may show a high degree of similarity with the facial feature information of the other twin, which may result in a recognition error. The eye feature information of twins is often different, which increases the likelihood that the facial feature information of each twin will be registered in different databases. Then, during authentication, the authentication device 1 performs authentication processing using only the facial feature information registered in that database 105 based on the eye class ID of one of the twins identified by the authentication device 1. This allows for more accurate authentication than performing authentication processing using a single database in which the facial feature information of both twins is registered. In other words, when authenticating one of the twins, the authentication process is performed using only database 105, which is presumed to contain the facial feature information of that person, so there is no need to determine whether the facial feature information of the other twin is similar, thereby improving authentication accuracy.

[0026] In the above process, it has been explained that the class identification unit 12 inputs information about the eye area of ​​a person's face included in an image into a neural network generated using a classification model and outputs a class ID. However, the neural network generated using the classification model may output a numerical value of the degree of relevance of the features of each of the 10 classes with class IDs = 0 to 9. In this case, the class identification unit 12 may input information about the eye area of ​​a person's face included in an image into the neural network generated using the classification model, output the degree of relevance with each of the 10 classes, and identify the class ID with the highest degree of relevance as a result.

[0027] Furthermore, in the above-described process, the portable terminal 2 transmits a registration request including an image to the authentication device 1. However, the portable terminal 2 may identify facial feature information and image information of the eye area from the image, and transmit a registration request including only the facial feature information and image information of the eye area to the authentication device 1. This may enable the authentication device 1 to omit the processes of generating facial feature information and identifying the eye area. The authentication device 1 may identify a class ID using the image information of the eye area included in the registration request, and register the facial feature information included in the registration request in the database 105 identified based on the class ID.

[0028] FIG. 5 is a diagram showing a processing flow of the authentication device in the authentication process. In the authentication process, the user takes a picture of their own face using the portable terminal 2. The portable terminal 2 generates an image based on the image. The image shows the user's face. The more pixels the image has, the better. The user instructs the portable terminal 2 to start the authentication process. The portable terminal 2 sends an authentication request including the image to the authentication device 1.

[0029] The authentication device 1 receives an authentication request. The acquisition unit 11 of the authentication device 1 acquires an image included in the authentication request (step S201). The acquisition unit 11 determines whether a face can be detected from the image (step S202). If the acquisition unit 11 cannot detect a face, it terminates the authentication process. If the acquisition unit 11 detects a face, it generates facial feature information based on the facial area included in the image (step S203).

[0030] The acquisition unit 11 outputs the image to the class identification unit 12. The class identification unit 12 determines whether the iris of the left eye of the face shown in the image can be detected (step S204). If the iris of the left eye can be detected, the class identification unit 12 identifies the class ID of the left eye. Specifically, the class identification unit 12 inputs information about the left eye area into a neural network using a classification model, and as a result, outputs the class ID of the left eye (step S205).

[0031] The class identification unit 12 also determines whether the iris of the right eye of the face captured in the image can be detected (step S206). If the iris of the right eye can be detected, the class identification unit 12 identifies the class ID of the right eye. Specifically, the class identification unit 12 inputs information about the area of ​​the right eye into a neural network using a classification model, and outputs the class ID of the right eye as a result (step S207). If the iris of the left eye or right eye cannot be detected, the class identification unit 12 may output information indicating that the class ID of the left eye or right eye cannot be identified.

[0032] The class identification unit 12 outputs an output result indicating the left eye class ID, the right eye class ID, and information indicating that the left eye or right eye class ID is unspecifiable, and the image, to the authentication unit 14. The authentication unit 14 uses the left eye class ID, the right eye class ID, information indicating that the left eye class ID is unspecifiable, and information indicating that the right eye class ID is unspecifiable from the output result to identify the database 105 from which the facial feature information is read (step S208). When the authentication unit 14 has identified both the left eye class ID and the right eye class ID, it identifies only the database 105 corresponding to the left eye class ID and the right eye class ID as the database 105 from which the facial feature information is read. For example, when the left eye class ID is "5" and the right eye class ID is "7," the registration unit 13 identifies the database 105 corresponding to the information of (5, 7) as the database 105 from which the facial feature information is read.

[0033] When only the class ID of the left eye can be identified, the authentication unit 14 identifies multiple databases 105 corresponding to the class ID of the left eye as databases 105 from which facial feature information is to be read. Specifically, when the class ID of the left eye is "3" and the class ID of the right eye cannot be identified, the authentication unit 14 identifies ten databases 105, (3,0), (3,1),...(3,9), as databases from which facial feature information is to be read. When neither the class ID of the left eye nor the class ID of the right eye can be identified, the authentication unit 14 identifies the database 105 corresponding to the information of (null, null) as database 105 from which facial feature information is to be read. If the authentication unit 14 cannot identify the class ID of either the left eye or the right eye, it may identify all of the 100 databases 105, namely (0,0), (0,1), (0,2), (0,9), (1,0), (1,1), (1,2), (1,9), (9,0), (9,1), (9,2), (9,9), as databases 105 from which to read facial feature information. In this case, it is not necessary to use the database 105 corresponding to the information of (null,null).

[0034] When the authentication unit 14 identifies the database 105 from which the data is to be read, it compares the facial feature information included in the identified database 105 with the feature information identified from the image included in the authentication request (step S209). As a result of the comparison, the authentication unit 14 determines that the similarity is equal to or greater than a predetermined threshold and identifies the user ID of the person whose facial feature information included in the database 105 is determined to have the highest similarity. The authentication unit 14 outputs the identified user ID to the output unit 15. It is assumed that the facial feature information and the person's user ID are linked and recorded in the database 105. If the similarity between the facial feature information included in the identified database 105 and the facial feature information of the image included in the authentication request is both less than the threshold, the authentication unit 14 outputs information indicating authentication failure to the output unit 15. If the similarity is equal to or greater than the threshold as a result of the comparison, the authentication unit 14 may output information indicating authentication success to the output unit 15. The output unit 15 transmits the output result, ie, the user ID or an authentication response indicating whether the authentication was unsuccessful or successful, to the mobile terminal 2 (step S210).

[0035] If the authentication response includes a user ID, the portable terminal 2 determines that the authentication is successful if the user ID matches the user ID stored in the device itself. The determination of whether the user IDs match and the determination of authentication success if they match may be performed by the authentication unit 14 of the authentication device 1. Furthermore, the portable terminal 2 may determine that the authentication is successful if the authentication response includes information indicating that the authentication is successful. The portable terminal 2 may determine that the authentication is unsuccessful if the authentication response includes information indicating that the authentication is unsuccessful. If the portable terminal 2 determines that the authentication is successful, it performs processing according to the authentication success. For example, if the portable terminal 2 determines that the authentication is successful, it may cancel the display of the login screen and change to a mode in which the portable terminal 2 can be used.

[0036] According to the above-described process, the authentication unit 14 of the authentication device 1 identifies the database 105 from which facial feature information for authentication is read based on the identification of the left eye class ID and the right eye class ID. In this process, the authentication unit 14 inputs information about the eye area of ​​the person's face included in the image into a neural network generated using a classification model and outputs the degree of association with each of the 10 classes. The authentication unit 14 may identify the database 105 from which facial feature information for authentication is read based on one or more class IDs with high degrees of association. For example, assume that the threshold for degree of association is 0.85, and the authentication unit 14 calculates that the degree of association with the class ID "3" for the left eye feature information is 0.88, the degree of association with the class ID "6" for the left eye feature information is 0.89, and the degree of association with the class ID "3" for the right eye feature information is 0.95. In this case, the authentication unit 14 may identify the two databases 105 (3,3) and (6,3) as the databases 105 from which facial feature information for authentication is read.

[0037] According to the above process, the authentication device 1 identifies a database 105 that is likely to contain facial feature information of the person to be authenticated, estimated based on the class classification of the person, and performs authentication processing by reading the facial feature information contained in the database 105. Therefore, it is possible to provide an authentication technology that increases the possibility of obtaining more accurate authentication results in a shorter time.

[0038] In the above process, the authentication device 1 performs authentication using an image containing at least two pieces of biometric information, i.e., iris information (first biometric information) and facial feature information (second biometric information). However, similar registration and authentication processes may be performed using an image containing at least two pieces of biometric information, i.e., biometric information other than iris information (first biometric information) and facial feature information (second biometric information). For example, assume that one image contains information on the vein shapes of left and right palms and a face. In this case, during the registration process, the authentication device 1 identifies each class ID into which the vein shape information of each palm is classified, and registers the facial feature information of the person contained in the image of the person in the database j105 corresponding to the two class IDs. Then, during authentication, the authentication unit 14 acquires an image containing the vein shape information of the left and right palms and a face, identifies the class IDs of the left and right palms based on the vein shape information of the left and right palms, and identifies the database from which the facial feature information is read, and performs authentication in the same manner.

[0039] (Another embodiment 1) In the above process, after the process of step S209, the authentication unit 14 of the authentication device 1 identifies the user ID of the person whose facial feature information included in the database 105 is determined to have the highest similarity, i.e., a similarity equal to or greater than a predetermined threshold. The authentication unit 14 of the authentication device 1 may change the threshold used in this process depending on the state in which the irises were detected. For example, the authentication unit 14 detects whether the irises of both eyes were detected in a first case, a second case in which the iris of only the left eye was detected, a third case in which the iris of only the right eye was detected, or a fourth case in which the irises of both eyes were not detected. The authentication unit 14 changes the threshold depending on whether the case is the first case, the second or third case, or the fourth case. Specifically, the threshold is changed so that it increases in the order of the first case < the second or third case < the fourth case. In other words, the first threshold for the first case is set to the lowest, the third threshold for the fourth case is set to the highest, and the second threshold for the second or third case is set between the first and third thresholds. In this way, when the irises of both eyes cannot be obtained, the authentication unit 14 sets the threshold to the highest value so that highly accurate authentication can be performed from among many people using only facial feature information. Also, when the irises of one eye are obtained, the threshold is set higher than when the irises of both eyes are obtained so that highly accurate authentication can be performed from among many people using facial feature information compared to when the irises of both eyes are obtained.

[0040] (Another embodiment 2) Fig. 6 is a first diagram showing a schematic configuration of an authentication system including an authentication device according to another embodiment. As shown in Fig. 6, the authentication device 1 may be communicatively connected to a gate device 4 equipped with a camera 3. In this case, the authentication device 1 acquires an authentication request from the gate device 4 and performs authentication processing in the same manner as in the above-described embodiment. Note that the registration processing in this case may be performed in the same manner as in the above-described embodiment by receiving a registration request from the authentication device 1 and the user's mobile terminal 2 or from the registration device 5. The gate device 4 is installed at a boarding gate at an airport, a ticket gate at a station, an entrance / exit of an office building, etc.

[0041] (Other embodiment 3) Fig. 7 is a second diagram showing the schematic configuration of an authentication system including an authentication device according to another embodiment. As shown in Fig. 7, the authentication device 1 may be communicatively connected to a payment terminal 6 equipped with a camera 3. In this case, the authentication device 1 acquires an authentication request from the payment terminal 6 and performs authentication processing in the same manner as in the above-described embodiment. Note that the registration processing in this case may also be performed in the same manner as in the above-described embodiment by receiving a registration request from the authentication device 1 and the user's mobile terminal 2 or from the registration device 5. The payment terminal 6 is installed in a store or the like.

[0042] (Other embodiment 4) FIG. 8 is a third diagram showing a schematic configuration of an authentication system including an authentication device according to another embodiment. In the above-described embodiments, an example has been described in which the authentication device is communicatively connected to a mobile terminal 2 equipped with a camera 3, a gate device 4, and a payment terminal 6 to perform the above-described registration and authentication processes. However, the functions of the authentication device 1 may be functions provided internally in the mobile terminal 2, the gate device 4, and the payment terminal 6. In this case, as an example, the authentication device 1 provided internally in the mobile terminal 2, the gate device 4, and the payment terminal 6 may not have the function of the database 105, but may be communicatively connected to an external database 105 to form an authentication system. In this case, the processing in the authentication device 1 is the same as in the other embodiments described above, except that it communicates with the external database 105 to register and read various information.

[0043] (Minimum Configuration Embodiment) FIG. 9 is a diagram showing the minimum configuration of an authentication device according to this embodiment. FIG. 10 is a diagram showing a processing flow by an authentication device with a minimum configuration according to this embodiment. The authentication device 1 performs at least the functions of a class identification unit 12 and an authentication unit 14 . The authentication device 1 is connected to a database 105 that stores second biometric information of a person of the first biometric information in a storage means corresponding to the class identifier of the classified first biometric information (step S301). The class identifying unit 12 identifies the class identifier of the first biometric information and the second biometric information of a person included in one image, based on the class classification of the first biometric information (step S302). The authentication unit 14 performs authentication using the second biometric information of a plurality of people stored in the database 105 corresponding to the class identifier of the first biometric information and the second biometric information included in the image (step S303).

[0044] In the above-described embodiments, an example is described in which a person's biometric information is captured in an image. However, the authentication device 1 according to the above-described embodiments may be used for authentication or matching when an image contains biometric information or characteristic information of an animal. Furthermore, the authentication device 1 according to the above-described embodiments may be used for authentication or matching when an image contains characteristic information of an object. In this case, the authentication device 1 connects a storage means corresponding to the class identifier of the classified first feature information to a storage means for storing second feature information of the target (animal or object) of the first feature information, and identifies the class identifier of the first feature information and second feature information of the target included in one image according to the class classification of the first feature information.The authentication device 1 then performs authentication and matching using the second feature information of the multiple targets stored in the storage means corresponding to the class identifier of the first feature information and the second feature information included in the image.

[0045] In this case, the authentication device 1 classifies the first feature information and registers the second feature information of the target of the first feature information in a storage means corresponding to the class identifier of the first feature information. The authentication device 1 classifies each of the first feature information of two different predetermined areas, which are the first feature information, and registers the second feature information of the target of the first feature information in a database 105 corresponding to the class identifiers of the two predetermined areas.

[0046] When the authentication device 1 is only able to identify a class ID based on the class classification of one of two specified areas of an object that is first feature information, it registers second feature information of the object having the first feature information in all databases 105 identified by all identifiers of the class related to the one specified area. When the authentication device 1 is only able to identify the class ID based on the other class classification of the two specified areas of the object that is the first feature information, it registers the second feature information of the object that has the first feature information in all databases 105 identified by all identifiers of the class related to the other specified area.

[0047] The above example illustrates a case in which the image contains iris information as the first feature information and facial feature information as the second feature information. However, the authentication device may display fingerprints, voice information, ear acoustics, etc. as the second feature information in the image. Ear acoustics is the detection of reflected sound emitted inside the ear. These fingerprints, voice audio information, and ear acoustics may be acquired using a sensor. Even if the image does not contain fingerprints, voice information, or ear acoustics, these information may be acquired separately from the image, and the authentication device 1 may perform the registration process or authentication process using the above-mentioned process. That is, the authentication device 1 may store second biometric information of the person of the first biometric information in a storage device corresponding to the class identifier of the classified first biometric information, identify the class identifier of the first biometric information from the first biometric information and the second biometric information of each acquired person based on the class classification of the first biometric information, and perform authentication using the acquired second biometric information and the second biometric information of multiple people stored in the storage device corresponding to the class identifier of the first biometric information.

[0048] Furthermore, in the above-described embodiments, examples have been described in which the first feature information is iris information, but the first feature information may be fingerprint, voice information, or acoustic information inside the ear, and the second feature information may be facial feature information or biometric information different from the first feature information (fingerprint, voice information, or acoustic information inside the ear). The first feature information and the second feature information do not have to be acquired using an image. In other words, the authentication device 1 may acquire the first feature information and the second feature information as separate data at the start of the registration process or authentication process as information not included in an image, and perform the registration process or authentication process in the same way.

[0049] The authentication device 1 described above has an internal computer system. The steps of each of the above-described processes are stored in the form of a program on a computer-readable recording medium, and the computer reads and executes this program to perform the above-described processes. Here, a computer-readable recording medium refers to a magnetic disk, a magneto-optical disk, a CD-ROM, a DVD-ROM, a semiconductor memory, etc. Alternatively, the computer program may be distributed to a computer via a communication line, and the computer that receives the program may execute the program.

[0050] The program may also be a program for realizing some of the functions described above, or may be a so-called differential file (differential program) that can realize the functions described above in combination with a program already recorded in the computer system.

[0051] Note that part or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes.

[0052] (Appendix 1) connecting a storage means corresponding to the class identifier of the classified first biometric information to a storage means for storing second biometric information of the person of the first biometric information; a class identification means for identifying a class identifier of the first biometric information and the second biometric information of a person included in one image, based on a class classification of the first biometric information; an authentication means for performing authentication using second biometric information of a plurality of persons stored in the storage means corresponding to a class identifier of the first biometric information and the second biometric information included in the image; An authentication device comprising:

[0053] (Appendix 2) connecting a storage means corresponding to the class identifier of the classified first biometric information to a storage means for storing second biometric information of the person of the first biometric information; a class identification means for identifying a class identifier of the acquired first biometric information and second biometric information of the person according to a class classification of the first biometric information; an authentication means for performing authentication using second biometric information of a plurality of persons stored in the storage means corresponding to a class identifier of the first biometric information and the acquired second biometric information; An authentication device comprising:

[0054] (Appendix 3) 3. The authentication device according to claim 1, wherein the first biometric information is iris information.

[0055] (Appendix 4) 4. The authentication device according to claim 1, wherein the first biometric information is iris information of each of the left eye and the right eye.

[0056] (Appendix 5) a registration means for classifying the first biometric information and registering the second biometric information of the person of the first biometric information in the storage means corresponding to the class identifier of the first biometric information; 5. The authentication device according to claim 1, further comprising:

[0057] (Appendix 6) The registration means classifies each of the iris information of the left eye and the right eye, which is the first biometric information, into classes, and registers the second biometric information of the person of the first biometric information in the storage means corresponding to the class identifier of the iris information of the left eye and the class identifier of the iris information of the right eye. 6. The authentication device according to claim 5.

[0058] (Appendix 7) When the registration means can only identify a class identifier based on the class classification of the iris information of the left eye, which is the first biometric information, the registration means registers the second biometric information of the person of the first biometric information in all of the storage means identified by all identifiers of the class related to the left eye. 10. The authentication device of claim 6.

[0059] (Appendix 8) When the registration means can only identify a class identifier based on the class classification of the iris information of the right eye, which is the first biometric information, the registration means registers the second biometric information of the person of the first biometric information in all of the storage means identified by all identifiers of the class related to the right eye. 8. An authentication device according to claim 6 or 7.

[0060] (Appendix 9) The second biometric information is characteristic information of a face shown in the image. 9. An authentication device according to any one of claims 1 to 8.

[0061] (Appendix 10) a storage means for storing second feature information of a target of the first feature information is connected to a storage means corresponding to a class identifier of the classified first feature information; a class identification means for identifying a class identifier based on a class classification of the first feature information from among the first feature information and the second feature information of an object included in one image; an authentication means for performing authentication using second feature information of a plurality of objects stored in the storage means corresponding to a class identifier of the first feature information and the second feature information included in the image; An authentication device comprising:

[0062] (Appendix 11) a storage means for storing second feature information of a target of the first feature information is connected to a storage means corresponding to a class identifier of the classified first feature information; a class identification means for identifying a class identifier of the acquired first feature information and the acquired second feature information of the target based on the class classification of the first feature information; an authentication means for performing authentication using second feature information of a plurality of targets stored in the storage means corresponding to a class identifier of the first feature information and the acquired second feature information; An authentication device comprising:

[0063] (Appendix 12) an authentication device connected to a storage means for storing second biometric information of a person of the first biometric information in a storage means corresponding to an identifier of a class of the classified first biometric information, Identifying a class identifier of the first biometric information and the second biometric information of a person included in one image according to a class classification of the first biometric information; Authentication is performed using second biometric information of a plurality of persons stored in the storage means corresponding to the class identifier of the first biometric information and the second biometric information included in the image. Authentication method.

[0064] (Appendix 13) an authentication device connected to a storage means for storing second biometric information of a person of the first biometric information in a storage means corresponding to an identifier of a class of the classified first biometric information, Identifying a class identifier of the first biometric information of the acquired person, based on a class classification of the first biometric information, from the first biometric information and the second biometric information of the acquired person; Authentication is performed using second biometric information of a plurality of persons stored in the storage means corresponding to the class identifier of the first biometric information and the acquired second biometric information. Authentication method.

[0065] (Appendix 14) an authentication device connected to a storage means for storing second feature information of a target of the first feature information in a storage means corresponding to a class identifier of the classified first feature information; Identifying a class identifier based on a class classification of the first feature information of the object included in one image, between the first feature information and the second feature information; Authentication is performed using second feature information of a plurality of objects stored in the storage means corresponding to the class identifier of the first feature information and second feature information included in the image. Authentication method.

[0066] (Appendix 15) an authentication device connected to a storage means for storing second feature information of a target of the first feature information in a storage means corresponding to a class identifier of the classified first feature information; Identifying a class identifier based on a class classification of the first feature information of the acquired target, from the first feature information and the second feature information of the target; Authentication is performed using second feature information of a plurality of targets stored in the storage means corresponding to a class identifier of the first feature information and the acquired second feature information. Authentication method.

[0067] (Appendix 16) a computer of an authentication device connected to a storage means for storing second biometric information of a person of the first biometric information in a storage means corresponding to an identifier of a class of the classified first biometric information; a class identification means for identifying a class identifier of the first biometric information and the second biometric information of a person included in one image, based on a class classification of the first biometric information; an authentication means for performing authentication using second biometric information of a plurality of persons stored in the storage means corresponding to a class identifier of the first biometric information and the second biometric information included in the image; A program that functions as a

[0068] (Appendix 17) a computer of an authentication device connected to a storage means for storing second biometric information of a person of the first biometric information in a storage means corresponding to an identifier of a class of the classified first biometric information; a class identification means for identifying a class identifier of the acquired first biometric information and the acquired second biometric information of the person according to a class classification of the first biometric information; an authentication means for performing authentication using second biometric information of a plurality of persons stored in the storage means corresponding to a class identifier of the first biometric information and the acquired second biometric information; A program that functions as a

[0069] (Appendix 18) a computer of an authentication device connected to a storage means for storing second feature information of a target of the first feature information in a storage means corresponding to a class identifier of the classified first feature information; a class identification means for identifying a class identifier based on a class classification of the first feature information, between the first feature information and the second feature information of an object included in one image; an authentication means for performing authentication using second feature information of a plurality of objects stored in the storage means corresponding to a class identifier of the first feature information and second feature information included in the image; A program that functions as a

[0070] (Appendix 19) a computer of an authentication device connected to a storage means for storing second feature information of a target of the first feature information in a storage means corresponding to a class identifier of the classified first feature information; a class identification means for identifying a class identifier based on the class classification of the first feature information of the acquired object, from the first feature information and the second feature information of the object; an authentication means for performing authentication using second feature information of a plurality of targets stored in the storage means corresponding to a class identifier of the first feature information and the acquired second feature information; A program that functions as a

[0071] (Appendix 20) A storage medium storing a program according to any one of claims 16 to 19. [Explanation of symbols]

[0072] 1. Authentication device 2. Mobile devices 3. Camera 11...Acquisition part 12. Class Identification Part 13. Registration Department 14. Authentication section 15. Output section 105···Database

Claims

1. a storage means for storing second biometric information of the person of the first biometric information, the storage means corresponding to the class identifiers of the iris information of each of the left and right eyes, being the classified first biometric information; a class identification means for identifying a class identifier of the first biometric information and the second biometric information of a person included in one image, based on a class classification of the first biometric information; an authentication means for performing authentication using second biometric information of a plurality of persons stored in the storage means corresponding to a class identifier of the first biometric information and the second biometric information included in the image; An authentication device comprising:

2. a registration means for classifying the first biometric information and registering the second biometric information of the person of the first biometric information in the storage means corresponding to the class identifier of the first biometric information; The authentication device according to claim 1 , comprising:

3. The registration means classifies each of the iris information of the left eye and the right eye, which is the first biometric information, into classes, and registers the second biometric information of the person of the first biometric information in the storage means corresponding to the class identifier of the iris information of the left eye and the class identifier of the iris information of the right eye. The authentication device according to claim 2 .

4. When the registration means can only identify a class identifier based on the class classification of the iris information of the left eye, which is the first biometric information, the registration means registers the second biometric information of the person of the first biometric information in all of the storage means identified by all identifiers of the class related to the left eye. The authentication device according to claim 3 .

5. When the registration means can only identify a class identifier based on the class classification of the iris information of the right eye, which is the first biometric information, the registration means registers the second biometric information of the person of the first biometric information in all of the storage means identified by all identifiers of the class related to the right eye.

5. The authentication device according to claim 3 or 4.

6. The second biometric information is characteristic information of a face shown in the image. The authentication device according to any one of claims 1 to 5.

7. an authentication device connected to a storage means for storing second biometric information of a person of the first biometric information in a storage means corresponding to a class identifier of the iris information of each of the left eye and the right eye, the first biometric information being classified into classes; Identifying a class identifier of the first biometric information and the second biometric information of a person included in one image according to a class classification of the first biometric information; Authentication is performed using second biometric information of a plurality of persons stored in the storage means corresponding to the class identifier of the first biometric information and the second biometric information included in the image. Authentication method.

8. a computer of an authentication device connected to a storage means for storing second biometric information of a person of the first biometric information in a storage means corresponding to a class identifier of the iris information of each of the left eye and the right eye, the first biometric information being classified into classes; a class identification means for identifying a class identifier of the first biometric information and the second biometric information of a person included in one image, based on a class classification of the first biometric information; an authentication means for performing authentication using second biometric information of a plurality of persons stored in the storage means corresponding to a class identifier of the first biometric information and the second biometric information included in the image; A program that functions as a

Images