Information processing device, information processing system, information processing method, and recording medium

Abstract

An information processing device according to the present invention comprises an acquisition means that acquires biological information for a subject and a control means that controls at least one of registration and updating of the biological information for the subject on the basis of at least one of the quality of the biological information, auxiliary information related to the biological information, and a comparison score calculated using the biological information.

Description

Information processing device, information processing system, information processing method, and recording medium

[0001] The present disclosure relates to the technical fields of an information processing device, an information processing system, an information processing method, and a recording medium.

[0002] One such device proposed is one that, when face authentication using a user's face image is successful, determines whether or not to prompt the user to update the registered image based on a score calculated by comparing the face image with face images of the user from previous successful face authentication attempts (see Patent Document 1).

[0003] WO 2023 / 166553

[0004] An object of this disclosure is to provide an information processing device, an information processing system, an information processing method, and a recording medium that aim to improve the technology related to the above-mentioned prior art documents.

[0005] One aspect of the information processing device comprises an acquisition means for acquiring biometric information of a target, and a control means for controlling at least one of registration and updating of the biometric information of the target based on at least one of the quality of the biometric information, auxiliary information related to the biometric information, and a matching score calculated using the biometric information.

[0006] One aspect of the information processing system includes an acquisition means for acquiring biometric information of a subject, and a control means for controlling at least one of registration and updating of the biometric information of the subject based on at least one of the quality of the biometric information, auxiliary information related to the biometric information, and a matching score calculated using the biometric information.

[0007] One aspect of the information processing method acquires biometric information of a target, and controls at least one of registration and updating of the target's biometric information based on at least one of the quality of the biometric information, auxiliary information related to the biometric information, and a matching score calculated using the biometric information.

[0008] One aspect of the recording medium has recorded thereon a computer program for causing a computer to execute an information processing method for acquiring biometric information of a subject and controlling at least one of registration and updating of the biometric information of the subject based on at least one of the quality of the biometric information, auxiliary information related to the biometric information, and a matching score calculated using the biometric information.

[0009] FIG. 1 is a block diagram showing an example of the configuration of an information processing device according to an embodiment. FIG. 2 is a flowchart showing an example of the operation of the information processing device according to an embodiment. FIG. 3 is a block diagram showing another example of the configuration of an information processing device according to an embodiment. FIG. 4 is a block diagram showing an example of the configuration of an information processing device according to an embodiment. FIG. 5 is a block diagram showing another example of the configuration of an authentication unit according to an embodiment. FIG. 6 is a diagram showing an example of a database. FIG. 7 is a block diagram showing another example of the configuration of an arithmetic device according to an embodiment. FIG. 8 is a block diagram showing another example of the configuration of an arithmetic device according to an embodiment. FIG. 9 is a block diagram showing another example of the configuration of an arithmetic device according to an embodiment.

[0010] First Embodiment A first embodiment of an information processing device, an information processing system, an information processing method, and a recording medium will be described with reference to Fig. 1 and Fig. 2. In the following, the first embodiment of the information processing device, the information processing system, the information processing method, and the recording medium will be described using an information processing device 10.

[0011] In FIG. 1 , the information processing device 10 includes an acquisition unit 11 and a control unit 12. Note that the information processing device 10 does not necessarily have to include either the acquisition unit 11 or the control unit 12. In this case, the information processing device 10 may include either the acquisition unit 11 or the control unit 12, and another device different from the information processing device 10 may include the other acquisition unit 11 or the control unit 12. In this case, the information processing device 10 and the other device may constitute an information processing system. The information processing system may include the information processing device 10 and the other device. In this case, it can be said that the information processing system includes the acquisition unit 11 and the control unit 12. Note that the information processing device 10 including the acquisition unit 11 and the control unit 12 may constitute a part of the information processing system. In this case, it can also be said that the information processing system includes the acquisition unit 11 and the control unit 12.

[0012] The acquisition unit 11 acquires biometric information of a target. The biometric information is information used for biometric authentication of the target. Examples of biometric authentication include at least one of face authentication, iris authentication, fingerprint authentication, palm print authentication, vein authentication, voiceprint authentication, and ear acoustic authentication, and multimodal biometric authentication. In the case of face authentication, the biometric information may be at least one of a face image including the target's face and features extracted from the face image. In the case of iris authentication, the biometric information may be at least one of an iris image including the target's iris and features extracted from the iris image. In the case of fingerprint authentication, the biometric information may be at least one of a fingerprint image including the target's fingerprint and features extracted from the fingerprint image. In the case of palm print authentication, the biometric information may be at least one of a palm print image including the target's palm print and features extracted from the palm print image. In the case of vein authentication, the biometric information may be at least one of a vein image including the target's vein pattern and features extracted from the vein image. In the case of voiceprint authentication, the biometric information may be at least one of audio information including the subject's voice and features extracted from the audio information. In the case of earacoustic authentication, the biometric information may be at least one of acoustic information including sound reflected from the subject's ear canal and features extracted from the acoustic information. In the case of multimodal biometric authentication, the biometric information may vary depending on the modality (in other words, the biometric authentication method) to be combined. For example, in the case of multimodal biometric authentication that combines face authentication and iris authentication, the biometric information may be at least one of a face image including the subject's face and features extracted from the face image, and an iris image including the subject's iris and features extracted from the iris image.

[0013] The control unit 12 controls at least one of registration and updating of the target biometric information based on at least one of the quality of the biometric information, auxiliary information related to the biometric information, and a matching score calculated using the biometric information. The quality of the biometric information may refer to an index indicating the state of the biometric information. The higher the quality of the biometric information, the more appropriately biometric authentication can be expected (e.g., without rejecting the actual person or misidentifying a different person as the actual person). For example, when the biometric information is at least one of a face image and an iris image, evaluation items for evaluating the quality may include at least one of brightness, blur, image resolution, lighting conditions, motion blur (i.e., subject movement), and frame-out (e.g., a part of the face or eye is outside the imaging range). When the biometric information is a face image, evaluation items for evaluating the quality may further include face orientation. When the biometric information is an iris image, evaluation items for evaluating the quality may further include at least one of eye orientation, colored contact lenses, eye opening degree, and blinking. For example, the quality of the face image and iris image can be appropriately evaluated using the evaluation items described above.

[0014] Auxiliary information related to biometric information may not be the biometric information itself, but may refer to information that supplements the biometric information. The auxiliary information may include, for example, at least one of date and time information, device information, and location information. For example, if the biometric information is at least one of a face image and an iris image, the date and time information may indicate the date and time when at least one of the subject's face and iris was captured. For example, if the biometric information is at least one of a fingerprint image, a palm print image, and a vein image, the date and time information may indicate the date and time when at least one of the subject's fingerprint, palm print, and vein pattern was read by a scanner. For example, if the biometric information is at least one of audio information including the subject's voice and acoustic information including sound reflected from the subject's ear canal, the date and time information may indicate the date and time when at least one of the audio information and acoustic information was recorded. The device information may be, for example, information (e.g., model number, serial number) for identifying at least one of the imaging device, scanner device, and sound recording device. The location information may indicate, for example, the location where at least one of the imaging device, scanner device, and sound recording device is installed.

[0015] The matching score may be an index indicating the degree of agreement between the feature amounts related to the target biometric information and the feature amounts of the comparison object, or may be an index indicating the degree of similarity between the feature amounts related to the target biometric information and the feature amounts of the comparison object. The "feature amounts of the comparison object" may be feature amounts related to pre-registered registered biometric information (e.g., biometric information of the registrant) or feature amounts related to other target biometric information. For example, when the acquisition unit 11 acquires a facial image as the target biometric information, the feature amounts extracted from the facial image correspond to the "feature amounts related to the target biometric information." When the acquisition unit 11 acquires feature amounts as the target biometric information, the feature amounts as the biometric information correspond to the "feature amounts related to the target biometric information." For example, when the registered biometric information is a facial image, the feature amounts extracted from the facial image correspond to the "feature amounts related to the registered biometric information." When the registered biometric information is feature amounts, the feature amounts as the registered biometric information correspond to the "feature amounts related to the registered biometric information."

[0016] For example, the control unit 12 may distinguish between high-quality biometric information and low-quality biometric information based on the quality of the biometric information. For example, the control unit 12 may determine the timing to update the biometric information based on date and time information as auxiliary information related to the biometric information. For example, the control unit 12 may estimate the quality of the biometric information based on device information as auxiliary information related to the biometric information. For example, the control unit 12 may determine whether or not to update the biometric information based on the matching score. "Controlling at least one of the registration and update of the target biometric information" may mean setting at least one of the registration status and update status of the target biometric information to an appropriate state. Note that "registration" is not limited to new registration and may be a concept that includes re-registration.

[0017] The operation of the information processing device 10 will be described with reference to the flowchart in Fig. 2. In Fig. 2, the acquisition unit 11 of the information processing device 10 acquires biometric information of a target (step S01). The control unit 12 of the information processing device 10 controls at least one of registration and updating of the biometric information of the target based on at least one of the quality of the biometric information, auxiliary information related to the biometric information, and a matching score calculated using the biometric information (step S102). In this way, the information processing device 10 performs an information processing method in which the information processing device acquires the biometric information of a target and controls at least one of registration and updating of the biometric information of the target based on at least one of the quality of the biometric information, auxiliary information related to the biometric information, and a matching score calculated using the biometric information.

[0018] The information processing device 10 may be realized by a computer reading a computer program recorded on a recording medium. In this case, the recording medium may have recorded thereon a computer program for causing the computer to execute an information processing method for acquiring biometric information of a target, and controlling at least one of registration and update of the target biometric information based on at least one of the quality of the biometric information, auxiliary information related to the biometric information, and a matching score calculated using the biometric information.

[0019] (Technical Effect) For example, payment using biometric authentication (hereinafter referred to as "biometric authentication payment") has been proposed. For example, if biometric authentication payment is applied to payments in physical stores, a user (corresponding to the above-mentioned "target") can shop empty-handed. Incidentally, biometric information may change with a user's age. For example, during a person's growth period, facial appearance and voice quality often change relatively significantly over a relatively short period of time. For example, as a user's lifestyle changes with age, facial appearance may change. If a user's actual biometric information differs from the user's registered biometric information, the authentication accuracy of biometric authentication may decrease. In response to this, the information processing device 10 controls at least one of the registration and update of a target's (e.g., a user's) biometric information based on at least one of the quality of the biometric information, auxiliary information related to the biometric information, and a matching score calculated using the biometric information. As a result, it is possible to prevent discrepancies between the user's actual biometric information and the user's registered biometric information. Therefore, the information processing device 10 according to the first embodiment can prevent a decrease in authentication accuracy of biometric authentication.

[0020] Second Embodiment A second embodiment of an information processing device, an information processing system, an information processing method, and a recording medium will be described with reference to Figures 3 and 4. Below, the second embodiment of an information processing device, an information processing system, an information processing method, and a recording medium will be described using an information processing device 100. Note that, for the second embodiment, descriptions that overlap with the description of the first embodiment will be omitted as appropriate.

[0021] 3 , the information processing device 100 includes a calculation device 110, a storage device 120, a communication device 130, an input device 140, and an output device 150. The calculation device 110, the storage device 120, the communication device 130, the input device 140, and the output device 150 may be connected via a data bus 160.

[0022] The arithmetic device 110 may include a processor 1101. The arithmetic device 110 may include other processors in addition to the processor 1101. That is, the arithmetic device 110 may include one or more processors. The processor 1101 may be a multi-core processor. When the arithmetic device 110 includes a single processor 1101 that is a multi-core processor, it can be said that the arithmetic device 110 logically includes multiple processors.

[0023] The processor 1101 may be, for example, at least one of a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field Programmable Gate Array), a TPU (Tensor Processing Unit), and a quantum processor.

[0024] The storage device 120 may include a memory 1201. The storage device 120 may include other memories in addition to the memory 1201. That is, the storage device 120 may include one or more memories. The memory 1201 may be, for example, at least one of a RAM (Random Access Memory), a ROM (Read Only Memory), a hard disk device, a magneto-optical disk device, an SSD (Solid State Drive), and an optical disk array. Therefore, the storage device 120 may include the memory 1201 as a non-transitory recording medium.

[0025] The storage device 120 can store desired data. A computer program 1201a to be executed by the arithmetic device 110 may be stored in the memory 1201 of the storage device 120. The storage device 120 may temporarily store data that is temporarily used by the arithmetic device 110 when the arithmetic device 110 is executing the computer program 1201a.

[0026] The computer program 1201a may be recorded on a computer-readable, non-transitory recording medium. In this case, the computer program 1201a may be stored in the memory 1201 by reading the recording medium using a recording medium reading device (not shown) included in the information processing device 100. The recording medium may be at least one of an optical disk, a magnetic medium, a magneto-optical disk, a semiconductor memory, and any other medium capable of storing a program. The computer program 1201a may be acquired (in other words, downloaded) from a device (not shown) external to the information processing device 100 via the communication device 130. The acquired computer program 1201a may be stored in the memory 1201.

[0027] The communication device 130 may be capable of communicating with devices external to the information processing device 100. The communication device 130 may perform wired communication or wireless communication.

[0028] The input device 140 is a device capable of accepting information input to the information processing device 100 from outside. The input device 140 may include an operation device (e.g., a keyboard, a mouse, a touch panel, etc.) that can be operated by a user of the information processing device 100. The input device 140 may include a recording medium reading device that can read information recorded on a recording medium that is detachable from the information processing device 100, such as a USB (Universal Serial Bus) memory. Note that when information is input to the information processing device 100 via the communication device 130 (in other words, when the information processing device 100 acquires information via the communication device 130), the communication device 130 may function as an input device.

[0029] The output device 150 is a device capable of outputting information to the outside of the information processing device 100. The output device 150 may output visual information such as text or images, auditory information such as sound, or tactile information such as vibration, as the information. The output device 150 may include, for example, at least one of a display, a speaker, a printer, and a vibration motor. The output device 150 may be capable of outputting information to a recording medium that is detachable from the information processing device 100, such as a USB memory. Note that when the information processing device 100 outputs information via the communication device 130, the communication device 130 may function as the output device.

[0030] The processor 1101 of the arithmetic device 110, together with the memory 1201 of the storage device 120 in which the computer program 1201a is stored (in other words, together with the memory 1201 and the computer program 1201a stored in the memory 1201), may execute the processing to be performed by the information processing device 100. For example, the processor 1101 may execute the computer program 1201a, thereby realizing a logical functional block in the arithmetic device 110 (for example, in the processor 1101) for executing the processing to be performed by the information processing device 100.

[0031] As shown in FIG. 4 , the arithmetic device 110 may include an acquisition unit 111 and a control unit 112 as logically realized functional blocks or as physically realized processing circuits. At least one of the acquisition unit 111 and the control unit 112 may be realized in a form that combines logical functional blocks and physical processing circuits (i.e., hardware). When the acquisition unit 111 and the control unit 112 are realized as functional blocks, the acquisition unit 111 and the control unit 112 may be realized by a single processor (e.g., processor 1101). Alternatively, the acquisition unit 111 and the control unit 112 may be realized by different processors. The "acquisition unit 111" and the "control unit 112" are components corresponding to the "acquisition unit 11" and the "control unit 12" in the first embodiment, respectively. The information processing device 100 may constitute a part of an information processing system. In this case, the information processing system can be said to include the acquisition unit 111 and the control unit 112.

[0032] The acquisition unit 111 acquires biometric information of a user (corresponding to the “subject” in the first embodiment). The control unit 112 controls at least one of registration and update of the user's biometric information based on at least one of the quality of the biometric information, auxiliary information related to the biometric information, and a matching score calculated using the biometric information.

[0033] (Technical Effect) According to the information processing device 100 of the second embodiment, similar to the information processing device 10 of the first embodiment, it is possible to suppress a decrease in authentication accuracy related to biometric authentication.

[0034] Third Embodiment A third embodiment of an information processing device, an information processing system, an information processing method, and a recording medium will be described with reference to FIGS. 5 to 7. Hereinafter, the third embodiment of the information processing device, the information processing system, the information processing method, and the recording medium will be described using an information processing device 100. In the third embodiment, a biometric image is used as an example of biometric information. However, the biometric information is not limited to a biometric image. Regarding the third embodiment, descriptions that overlap with those of the first and second embodiments will be omitted as appropriate.

[0035] The information processing device 100 according to the third embodiment may include a calculation device 110a instead of the calculation device 110. The calculation device 110a may have one or more processors, similar to the calculation device 110. As shown in Fig. 5 , the calculation device 110a may include a biometric image acquisition unit 111a, a quality evaluation unit 112a, a registration unit 112b, and an authentication unit 113 as logically realized functional blocks or as physically realized processing circuits. Note that at least one of the biometric image acquisition unit 111a, the quality evaluation unit 112a, the registration unit 112b, and the authentication unit 113 may be realized in a form in which a logical functional block and a physical processing circuit (i.e., hardware) are mixed.

[0036] When the biometric image acquisition unit 111a, the quality evaluation unit 112a, the registration unit 112b, and the authentication unit 113 are realized as functional blocks, the biometric image acquisition unit 111a, the quality evaluation unit 112a, the registration unit 112b, and the authentication unit 113 may be realized by a single processor (e.g., the processor 1101). Alternatively, the biometric image acquisition unit 111a, the quality evaluation unit 112a, the registration unit 112b, and the authentication unit 113 may each be realized by a different processor. Alternatively, parts of the biometric image acquisition unit 111a, the quality evaluation unit 112a, the registration unit 112b, and the authentication unit 113 may be realized by a single processor, and the remaining parts of the biometric image acquisition unit 111a, the quality evaluation unit 112a, the registration unit 112b, and the authentication unit 113 may be realized by one or more processors different from the single processor. The "biometric image acquisition unit 111a" corresponds to a specific example of the "acquisition unit 111" in the second embodiment. The "quality evaluation unit 112a" and the "registration unit 112b" correspond to a specific example of the "control unit 112" in the second embodiment.

[0037] The biometric image acquisition unit 111a may acquire a biometric image of the user. Note that the biometric image is not limited to an image generated by capturing at least a part of the user with a camera, but also includes, for example, an image generated by reading at least a part of the user with a scanner.

[0038] The authentication unit 113 may perform biometric authentication of the user using a biometric image. More specifically, the authentication unit 113 may perform biometric authentication of the user using the biometric image and a database (e.g., database 200 described later) in which registered biometric information is registered. Note that the database may be stored in, for example, the storage device 120, or may be stored in a device (e.g., a cloud server) different from the information processing device 100.

[0039] The authentication unit 113 will now be described with reference to FIG. 6 . As shown in FIG. 6 , the authentication unit 113 may include a feature extraction unit 1131 and a matching unit 1132. The feature extraction unit 1131 may extract features from a biometric image. For example, if the registered biometric information registered in the database described above is an image, the feature extraction unit 1131 may extract features from the image as the registered biometric information. The matching unit 1132 may calculate a matching score by matching the features extracted from the biometric image with the features extracted from the image as the registered biometric information. For example, if the registered biometric information registered in the database described above is a feature, the matching unit 1132 may calculate a matching score by matching the features extracted from the biometric image with the features as the registered biometric information.

[0040] If the user's biometric information is a feature amount and the registered biometric information registered in the database is a feature amount, the authentication unit 113 does not need to include the feature amount extraction unit 1131.

[0041] The authentication unit 113 may perform 1:1 authentication as biometric authentication. In this case, the authentication unit 113 may determine whether the matching score calculated by the matching unit 1132 is equal to or greater than a first threshold. If it is determined that the matching score is equal to or greater than the first threshold, the authentication unit 113 may identify the user as the person associated with the registered biometric information. On the other hand, if it is determined that the matching score is smaller than the first threshold, the authentication unit 113 may determine that a person corresponding to the user is not registered. Note that a determination that the matching score is equal to or greater than the first threshold may be referred to as "authentication success." A determination that the matching score is smaller than the first threshold may be referred to as "authentication failure."

[0042] The authentication unit 113 may perform 1:N authentication as biometric authentication. In this case, the authentication unit 113 may determine whether the maximum value of the matching scores calculated by the matching unit 1132 is equal to or greater than a first threshold. If it is determined that the maximum value of the matching scores is equal to or greater than the first threshold, the authentication unit 113 may identify the user as the person associated with the registered biometric information used to calculate the maximum matching score. On the other hand, if it is determined that the maximum value of the matching scores is smaller than the first threshold, the authentication unit 113 may determine that a person corresponding to the user is not registered. Note that a determination that the maximum value of the matching scores is equal to or greater than the first threshold may be referred to as "authentication success." A determination that the maximum value of the matching scores is smaller than the first threshold may be referred to as "authentication failure."

[0043] If the authentication is successful, the quality evaluation unit 112a may evaluate the quality of the biometric image acquired by the biometric image acquisition unit 111a. The quality evaluation unit 112a may calculate a quality score indicating the evaluation of the quality of the biometric image. The quality score may be, for example, at least one of the sum, simple average, and weighted average of the scores for each evaluation item for evaluating the quality of the biometric image. For example, if the biometric information is at least one of a face image and an iris image, the evaluation items may include at least one of brightness, blur, image resolution, lighting conditions, motion blur (i.e., subject blur), and frame-out (e.g., part of the face or eye is outside the imaging range). Note that if the authentication is unsuccessful, the quality evaluation unit 112a does not need to evaluate the quality of the biometric image acquired by the biometric image acquisition unit 111a.

[0044] The registration unit 112b may determine whether to register the biometric image based on the quality of the biometric image evaluated by the quality evaluation unit 112a. When the quality evaluation unit 112a calculates a quality score, the registration unit 112b may determine whether to register the biometric image based on the quality score. In this case, if the quality score is equal to or greater than a second threshold, the registration unit 112b may determine to register the biometric image. On the other hand, if the quality score is smaller than the second threshold, the registration unit 112b may determine not to register the biometric image.

[0045] If it is determined that the biometric image should be registered, the registration unit 112b may register the biometric image in the database as registered biometric information. Specifically, the registration unit 112b may register the biometric image in the database by linking the biometric image to identification information (e.g., a user ID) related to the person (i.e., the user) identified by the authentication unit 113.

[0046] Here, the database will be described with reference to FIG. 7 . Note that the database 200 shown in FIG. 7 is an example and is not limited to this. In the database 200, one user ID (in other words, one person) may be linked to multiple pieces of registered biometric information. For example, a person with user ID "0001" may be linked to multiple pieces of registered biometric information BI#1, BI#2, ..., BI#n. Note that only a single piece of registered biometric information may be linked to one user ID. Note that when multiple pieces of registered biometric information are linked to one user ID, the authentication unit 113 may perform biometric authentication using, for example, the registered biometric information whose acquisition date and time is closest to the current date and time (in other words, the latest) among the multiple pieces of registered biometric information.

[0047] For example, when a biometric image of a person with a user ID of "0001" is newly registered, the registration unit 112b may register the biometric image as registered biometric information BI#n+1. An upper limit may be set for the number of registered biometric information pieces that can be linked to a user ID. For example, when the number of registered biometric information pieces linked to a user ID is less than the upper limit, the registration unit 112b may register the new biometric image by linking the new biometric image to the user ID. For example, when the number of registered biometric information pieces linked to a user ID is equal to the upper limit, the registration unit 112b may delete the registered biometric information piece with the oldest acquisition date and time from among the registered biometric information pieces already linked to the user ID, and then register the new biometric image by linking the new biometric image to the user ID. This configuration can prevent the database from becoming bloated and reduce the processing load on the information processing device 100.

[0048] When only a single piece of registered biometric information is associated with a user ID and a new biometric image is to be registered, the registration unit 112b may delete the registered biometric information already associated with the user ID and then associate the new biometric image with the user ID, thereby registering the new biometric image. In other words, the registration unit 112b may replace the registered biometric information associated with the user ID with the new biometric image. When it is determined that a biometric image is to be registered, the registration unit 112b may extract features from the biometric image. Then, the registration unit 112b may register the extracted features in a database (e.g., database 200) as registered biometric information.

[0049] (Technical Effect) As described in the first embodiment, biometric information may change with the user's age. In other words, biometric information may change over time. Therefore, if the registered biometric information registered in the database is not updated, the user's actual biometric information may deviate from the registered biometric information. In response to this, if the biometric authentication is successful, it is possible to update the registered biometric information by registering the biometric information used in this biometric authentication (i.e., the user's actual biometric information) in the database.

[0050] As described above, in biometric authentication, authentication is successful if the matching score (or the maximum matching score) is equal to or greater than the first threshold. In other words, even if the quality of the biometric image acquired by the biometric image acquisition unit 111a is relatively low, authentication is successful as long as the matching score (or the maximum matching score) is equal to or greater than the first threshold. Therefore, if no countermeasures are taken, the quality of the registered biometric information may deteriorate. As a result, the actual person may be rejected or another person may be mistaken for the actual person in biometric authentication.

[0051] Therefore, in the information processing device 100 according to the third embodiment, whether or not to register a biometric image acquired by the acquisition unit 111 a as registered biometric information is determined based on the quality of the biometric image. Therefore, the information processing device 100 according to the third embodiment can suppress the influence of aging on biometric authentication and can maintain high quality of the registered biometric information.

[0052] The information processing device 100 may not have the authentication unit 113. In this case, biometric authentication may be performed by a device (e.g., a cloud server) different from the information processing device 100. In this case, the information processing device 100 may transmit the biometric image acquired by the biometric image acquisition unit 111a to a device different from the information processing device 100. Furthermore, the information processing device 100 may receive information indicating the result of biometric authentication from a device different from the information processing device 100.

[0053] Fourth Embodiment A fourth embodiment of an information processing device, an information processing system, an information processing method, and a recording medium will be described with reference to FIG. 8 . Hereinafter, the fourth embodiment of the information processing device, the information processing system, the information processing method, and the recording medium will be described using an information processing device 100. Note that in the fourth embodiment, a biometric image is given as an example of biometric information. However, biometric information is not limited to a biometric image. Note that, for the fourth embodiment, descriptions that overlap with the descriptions for the first to third embodiments will be omitted as appropriate.

[0054] The information processing device 100 according to the fourth embodiment may include a calculation device 110b instead of the calculation device 110. The calculation device 110b may have one or more processors, similar to the calculation device 110. As shown in Fig. 8 , the calculation device 110b may include a biometric image acquisition unit 111a, a registration unit 112b, an update proposal unit 112c, and an authentication unit 113 as logically realized functional blocks or as physically realized processing circuits. Note that at least one of the biometric image acquisition unit 111a, the registration unit 112b, the update proposal unit 112c, and the authentication unit 113 may be realized in a form in which a logical functional block and a physical processing circuit (i.e., hardware) are mixed.

[0055] Note that when the biometric image acquisition unit 111a, the registration unit 112b, the update proposal unit 112c, and the authentication unit 113 are realized as functional blocks, the biometric image acquisition unit 111a, the registration unit 112b, the update proposal unit 112c, and the authentication unit 113 may be realized by a single processor (e.g., the processor 1101). Alternatively, the biometric image acquisition unit 111a, the registration unit 112b, the update proposal unit 112c, and the authentication unit 113 may be realized by different processors. Alternatively, parts of the biometric image acquisition unit 111a, the registration unit 112b, the update proposal unit 112c, and the authentication unit 113 may be realized by a single processor, and the remaining parts of the biometric image acquisition unit 111a, the registration unit 112b, the update proposal unit 112c, and the authentication unit 113 may be realized by one or more processors different from the single processor. The "registration unit 112b" and the "update proposing unit 112c" correspond to a specific example of the "control unit 112" in the second embodiment.

[0056] The biometric image acquisition unit 111a may acquire a biometric image of the user. The authentication unit 113 may perform biometric authentication of the user using the biometric image. If the biometric authentication in the authentication unit 113 is successful, the update suggestion unit 112c may determine whether the matching score is equal to or less than a third threshold. As described in the third embodiment, the authentication unit 113 determines whether the matching score is equal to or greater than a first threshold. If the matching score is equal to or greater than the first threshold, the biometric authentication in the authentication unit 113 is successful. The third threshold is a value greater than the first threshold. Therefore, if the matching score is equal to or greater than the first threshold and equal to or less than the third threshold, the update suggestion unit 112c determines that the matching score is equal to or less than the third threshold. In other words, the range of the matching score for which the update suggestion unit 112c determines that the matching score is equal to or less than the third threshold is equal to or greater than the first threshold and equal to or less than the third threshold.

[0057] In biometric authentication, for example, a false acceptance rate (FAR) and a false rejection rate (FRR) are taken into consideration to achieve both authentication accuracy and user convenience. For this reason, the above-mentioned first threshold is often set to a value that, for example, allows an unregistered person (i.e., a stranger) to be mistaken for a registered person, but almost never causes a registered person to be rejected.

[0058] For example, when the possible range of the matching score is 0 or more and 1 or less, the matching score of the registrant is often close to 1. However, as the difference between the actual biometric information of the registrant (i.e., the user) and the registered biometric information of the registrant increases, for example, due to aging, the matching score of the registrant decreases. Therefore, the matching score can be used as an index indicating the difference between the actual biometric information of the registrant (i.e., the user) and the registered biometric information of the registrant. Therefore, the third threshold may be set as follows. For example, based on the relationship between the matching score and the false acceptance rate, a range of the matching score in which the false acceptance rate is small enough to be negligible may be determined. For example, the matching score fluctuates due to the physical condition of the registrant (i.e., the user). The third threshold may be set to a value that is smaller by a predetermined value than the lower limit of the range of the matching score in which the false acceptance rate is small enough to be negligible, taking into account the range of fluctuation in the matching score due to the physical condition of the registrant (i.e., the user).

[0059] If it is determined that the matching score is equal to or less than the third threshold, the update suggestion unit 112c may prompt the user to update the registered biometric information. For example, the update suggestion unit 112c may control the output device 150 to output at least one of text, an image, and a voice prompting the user to update the registered biometric information. If the user agrees to update the registered biometric information, the registration unit 112b may re-register the user's biometric information (e.g., a biometric image and / or feature amounts extracted from the biometric image) in the database. Note that the information processing device 100 may determine the biometric information to be re-registered by evaluating the quality of the biometric image, as in the third embodiment described above. Note that if it is determined that the matching score is greater than the third threshold, the update suggestion unit 112c may not prompt the user to update the registered biometric information.

[0060] (Technical Effect) According to the information processing apparatus 100 according to the fourth embodiment, it is possible to suppress the influence of changes over time in the user's actual biometric information on biometric authentication.

[0061] The information processing device 100 may not have the authentication unit 113. In this case, biometric authentication may be performed by a device (e.g., a cloud server) different from the information processing device 100. In this case, the information processing device 100 may transmit the biometric image acquired by the biometric image acquisition unit 111a to a device different from the information processing device 100. Furthermore, the information processing device 100 may receive information indicating the result of biometric authentication from a device different from the information processing device 100.

[0062] (First Modification) In addition to or instead of determining whether to prompt the user to update the registered biometric information based on auxiliary information related to the biometric image acquired by the biometric image acquisition unit 111a when the matching score is equal to or less than the third threshold, the update suggestion unit 112c may determine whether to prompt the user to update the registered biometric information based on auxiliary information related to the biometric image acquired by the biometric image acquisition unit 111a. For example, the auxiliary information may be location information (e.g., information indicating the location where at least one of the imaging device and the scanner device is installed). For example, the update suggestion unit 112c may prompt the user to update the registered biometric information when the location indicated by the location information as auxiliary information related to the registered biometric information differs from the location indicated by the location information as auxiliary information related to the biometric image acquired by the biometric image acquisition unit 111a. For example, the auxiliary information may be date and time information. For example, the update suggestion unit 112c may prompt the user to update the registered biometric information when the difference between the date and time indicated by the date and time information as auxiliary information related to the registered biometric information and the date and time indicated by the date and time information as auxiliary information related to the biometric image acquired by the biometric image acquisition unit 111a is equal to or greater than a predetermined time.

[0063] (Second Modification) For example, the update suggestion unit 112c may store the matching score of the user in the storage device 120 each time the biometric authentication of the user is successful. As a result, history information of the matching score of the user may be generated. When the time change of the matching score of the user based on the history information indicates a downward trend, the update suggestion unit 112c may prompt the user to update the registered biometric information. For example, the update suggestion unit 112c may determine whether the matching score of the user is equal to or less than a third threshold and whether the time change of the matching score of the user indicates a downward trend. For example, when it is determined that the matching score is equal to or less than the third threshold and that the time change of the matching score indicates a downward trend, the update suggestion unit 112c may prompt the user to update the registered biometric information. For example, even when it is determined that the matching score is equal to or less than the third threshold, if it is determined that the time change of the matching score does not indicate a downward trend, the update suggestion unit 112c may not prompt the user to update the registered biometric information. This is because the matching score may temporarily decrease due to an injury, etc. For example, even if it is determined that the time change in the matching score is on a downward trend, if it is determined that the matching score is greater than the third threshold, the update suggestion unit 112c does not need to prompt an update of the registered biometric information.

[0064] Fifth Embodiment A fifth embodiment of an information processing device, an information processing system, an information processing method, and a recording medium will be described with reference to FIG. Hereinafter, the fifth embodiment of the information processing device, the information processing system, the information processing method, and the recording medium will be described using an information processing device 100. In the fifth embodiment, a biometric image is used as an example of biometric information. However, the biometric information is not limited to a biometric image. In the fifth embodiment, descriptions that overlap with the descriptions of the first to fourth embodiments will be omitted as appropriate.

[0065] The information processing device 100 according to the fifth embodiment may include a calculation device 110c instead of the calculation device 110. The calculation device 110c may include one or more processors, similar to the calculation device 110. As shown in FIG. 9 , the calculation device 110c may include a biometric image acquisition unit 111a, a quality evaluation unit 112a, a registration unit 112b, a score calculation unit 112d, and an authentication unit 113, which may be logically implemented functional blocks or physically implemented processing circuits. Note that at least one of the biometric image acquisition unit 111a, the quality evaluation unit 112a, the registration unit 112b, the score calculation unit 112d, and the authentication unit 113 may be implemented in a form that combines logical functional blocks and physical processing circuits (i.e., hardware).

[0066] When the biometric image acquisition unit 111a, the quality evaluation unit 112a, the registration unit 112b, the score calculation unit 112d, and the authentication unit 113 are realized as functional blocks, the biometric image acquisition unit 111a, the quality evaluation unit 112a, the registration unit 112b, the score calculation unit 112d, and the authentication unit 113 may be realized by a single processor (e.g., the processor 1101). Alternatively, the biometric image acquisition unit 111a, the quality evaluation unit 112a, the registration unit 112b, the score calculation unit 112d, and the authentication unit 113 may be realized by different processors. Alternatively, the biometric image acquisition unit 111a, the quality evaluation unit 112a, the registration unit 112b, the score calculation unit 112d, and part of the authentication unit 113 may be realized by one processor, and the remaining parts of the biometric image acquisition unit 111a, the quality evaluation unit 112a, the registration unit 112b, the score calculation unit 112d, and the authentication unit 113 may be realized by one or more processors different from the one processor. Note that the "quality evaluation unit 112a," "registration unit 112b," and "score calculation unit 112d" correspond to specific examples of the "control unit 112" in the second embodiment.

[0067] The biometric image acquisition unit 111a may acquire a biometric image of a user. The authentication unit 113 may perform biometric authentication of the user using the biometric image. If the biometric authentication by the authentication unit 113 is successful, the quality evaluation unit 112a may evaluate the quality of the biometric image acquired by the biometric image acquisition unit 111a.

[0068] In the information processing device 100 according to the third embodiment, the registration unit 112b may determine whether to register a biometric image based on the quality of the biometric image evaluated by the quality evaluation unit 112a. In contrast, in the information processing device 100 according to the fifth embodiment, for example, the quality evaluation unit 112a may determine whether to temporarily store the biometric image in the storage device 120 based on the quality of the biometric image. For example, when the quality evaluation unit 112a calculates a quality score, the quality evaluation unit 112a may determine whether to temporarily store the biometric image in the storage device 120 based on the quality score. In this case, if the quality score is equal to or greater than a fourth threshold, the quality evaluation unit 112a may determine to temporarily store the biometric image in the storage device 120. On the other hand, if the quality score is less than the fourth threshold, the quality evaluation unit 112a may determine not to temporarily store the biometric image in the storage device 120. In other words, the quality evaluation unit 112a may temporarily store a biometric image of relatively high quality in the storage device 120. When the biometric image is temporarily stored in the storage device 120, the biometric image is stored for each user (for example, linked to a user ID). The fourth threshold value may be the same as or different from the second threshold value in the third embodiment.

[0069] The score calculation unit 112d may calculate a score using multiple biometric images stored in the storage device 120 for each user. Here, the operation of the score calculation unit 112d will be specifically described using multiple pieces of biometric information BI#1, BI#2, BI#3, and BI#4 of one user. The score calculation unit 112d may extract a feature quantity BQ#1 from the biometric information BI#1. The score calculation unit 112d may extract a feature quantity BQ#2 from the biometric information BI#2. The score calculation unit 112d may extract a feature quantity BQ#3 from the biometric information BI#3. The score calculation unit 112d may extract a feature quantity BQ#3 from the biometric information BI#3.

[0070] The score calculation unit 112d may calculate a score #1-2 indicating at least one of the degree of agreement between the feature BQ#1 and the feature BQ#2 and the degree of similarity between the feature BQ#1 and the feature BQ#2 by comparing the feature BQ#1 and the feature BQ#2. The score calculation unit 112d may calculate a score #1-3 indicating at least one of the degree of agreement between the feature BQ#1 and the feature BQ#3 and the degree of similarity between the feature BQ#1 and the feature BQ#3 by comparing the feature BQ#1 and the feature BQ#4. The score calculation unit 112d may calculate a score #1-4 indicating at least one of the degree of agreement between the feature BQ#1 and the feature BQ#4 and the degree of similarity between the feature BQ#1 and the feature BQ#4 by comparing the feature BQ#1 and the feature BQ#4. The score calculation unit 112d may calculate a score #2-3 indicating at least one of the degree of agreement between the feature BQ#2 and the feature BQ#3 and the degree of similarity between the feature BQ#2 and the feature BQ#3 by comparing the feature BQ#2 and the feature BQ#3. The score calculation unit 112d may calculate a score #2-4 indicating at least one of the degree of agreement between the feature BQ#2 and the feature BQ#4 and the degree of similarity between the feature BQ#2 and the feature BQ#4 by comparing the feature BQ#2 and the feature BQ#4. The score calculation unit 112d may calculate a score #3-4 indicating at least one of the degree of agreement between the feature BQ#3 and the feature BQ#4 and the degree of similarity between the feature BQ#3 and the feature BQ#4 by comparing the feature BQ#3 and the feature BQ#4.

[0071] The method by which the score calculation unit 112d calculates the score may be the same as the method by which the authentication unit 113 (specifically, the matching unit 1132) calculates the matching score. However, the authentication unit 113 calculates the matching score by matching feature amounts extracted from the biometric image acquired by the biometric image acquisition unit 111a with feature amounts related to the registered biometric information. In contrast, the score calculation unit 112d calculates the score by matching feature amounts extracted from the biometric images acquired by the biometric image acquisition unit 111a.

[0072] The score calculation unit 112d may, for example, take the average value of scores #1-2, #1-3, and #1-4 as the score of biometric image BI#1. The score calculation unit 112d may, for example, take the average value of scores #1-2, #2-3, and #2-4 as the score of biometric image BI#2. The score calculation unit 112d may, for example, take the average value of scores #1-3, #2-3, and #3-4 as the score of biometric image BI#3. The score calculation unit 112d may, for example, take the average value of scores #1-4, #2-4, and #3-4 as the score of biometric image BI#4. The score calculation unit 112d may calculate a score when a predetermined number of biometric images have been accumulated for one user. The score calculation unit 112b may calculate a score for one user when a predetermined period has elapsed since the previous score was calculated.

[0073] The registration unit 112b may, for example, register the biometric image with the highest score among the scores of biometric image BI#1, biometric image BI#2, biometric image BI#3, and biometric image BI#4, and at least one of the features extracted from the biometric image, as registered biometric information in a database (e.g., database 200).

[0074] (Technical Effect) When feature amounts extracted from biometric images acquired by the biometric image acquisition unit 111a are compared with each other, the following problem occurs. For example, the score calculated by comparing feature amounts extracted from a low-quality first biometric image with feature amounts extracted from a low-quality second biometric image may be greater than the score calculated by comparing feature amounts extracted from the low-quality first biometric image with feature amounts extracted from a high-quality third biometric image. As a result, the low-quality biometric image may be registered in the database as registered biometric information.

[0075] In contrast, in the information processing device 100 according to the fifth embodiment, the quality of the biometric image is evaluated by the quality evaluation unit 112a. Then, biometric images of relatively high quality are temporarily stored based on the quality of the biometric image. Therefore, in the information processing device 100, feature amounts extracted from biometric images of relatively high quality are compared with each other. Therefore, the information processing device 100 can solve the above-mentioned problem.

[0076] Furthermore, when a biometric image to be registered as registered biometric information is determined based on the matching score calculated by the authentication unit 113, the following problem arises. Due to the method of calculating the matching score, the more similar the biometric image is to the registered biometric information, the higher the matching score. For example, if there is a difference between the actual biometric information of the enrollee (i.e., the user) and the registered biometric information of the enrollee due to aging, the biometric image with the highest matching score may not adequately reflect the actual biometric information (in other words, biometric features) of the enrollee. In contrast, in the information processing device 100 according to the fifth embodiment, the registered biometric information is not used, and feature amounts extracted from the biometric images acquired by the biometric image acquisition unit 111a are matched. Therefore, it is expected that the biometric image registered by the registration unit 112b as registered biometric information adequately reflects the actual biometric information of the user.

[0077] From these facts, the information processing device 100 according to the fifth embodiment can suppress the influence of aging on biometric authentication, and can maintain high quality of registered biometric information.

[0078] The information processing device 100 may not have the authentication unit 113. In this case, biometric authentication may be performed by a device (e.g., a cloud server) different from the information processing device 100. In this case, the information processing device 100 may transmit the biometric image acquired by the biometric image acquisition unit 111a to a device different from the information processing device 100. Furthermore, the information processing device 100 may receive information indicating the result of biometric authentication from a device different from the information processing device 100.

[0079] Sixth Embodiment A sixth embodiment of an information processing device, an information processing system, an information processing method, and a recording medium will be described with reference to FIG. 10 . Hereinafter, the sixth embodiment of an information processing device, an information processing system, an information processing method, and a recording medium will be described using an information processing device 100. In the sixth embodiment, a biometric image is used as an example of biometric information. However, biometric information is not limited to a biometric image. In the sixth embodiment, descriptions that overlap with the descriptions of the first to fifth embodiments will be omitted as appropriate.

[0080] The information processing device 100 according to the sixth embodiment may include a calculation device 110d instead of the calculation device 110. The calculation device 110d may include one or more processors, similar to the calculation device 110. As shown in FIG. 10 , the calculation device 110d may include a biometric image acquisition unit 111a, a registration unit 112b, an update determination unit 112e, and authentication units 113a and 113b as logically realized functional blocks or as physically realized processing circuits. Note that at least one of the biometric image acquisition unit 111a, the registration unit 112b, the update determination unit 112e, and the authentication units 113a and 113b may be realized in a form in which logical functional blocks and physical processing circuits (i.e., hardware) are mixed.

[0081] Note that when the biometric image acquisition unit 111a, the registration unit 112b, the update determination unit 112e, and the authentication units 113a and 113b are realized as functional blocks, the biometric image acquisition unit 111a, the registration unit 112b, the update determination unit 112e, and the authentication units 113a and 113b may be realized by a single processor (e.g., the processor 1101). Alternatively, the biometric image acquisition unit 111a, the registration unit 112b, the update determination unit 112e, and the authentication units 113a and 113b may be realized by different processors. Alternatively, some of the biometric image acquisition unit 111a, the registration unit 112b, the update determination unit 112e, and the authentication units 113a and 113b may be realized by a single processor, and the remaining parts of the biometric image acquisition unit 111a, the registration unit 112b, the update determination unit 112e, and the authentication units 113a and 113b may be realized by one or more processors different from the single processor. The "registration unit 112b" and the "update determination unit 112e" correspond to a specific example of the "control unit 112" in the second embodiment.

[0082] The information processing device 100 according to the sixth embodiment may perform multimodal biometric authentication. The biometric image acquisition unit 111a may acquire a biometric image of a user according to a first modal and a biometric image of the user according to a second modal. The first and second modals may be combined in any manner. However, it is preferable that at least one of the first and second modals is a modal that is less susceptible to aging. For example, the first modal may be the user's face, and the second modal may be the user's iris. In this case, the information processing device 100 may perform face / iris multimodal biometric authentication. In the sixth embodiment, multimodal biometric authentication is performed using the first and second modals. However, multimodal biometric authentication using three or more modals may also be performed.

[0083] The authentication unit 113a may perform biometric authentication of a user using a biometric image related to a first modal. The authentication unit 113a may calculate a matching score related to the first modal by matching a feature extracted from the biometric image related to the first modal with a feature of registered biometric information related to the first modal. The authentication unit 113a may determine whether the matching score is equal to or greater than a fifth threshold. Note that the authentication unit 113a may perform 1:N authentication or 1:1 authentication.

[0084] The authentication unit 113b may perform biometric authentication of the user using a biometric image related to the second modal. The authentication unit 113b may calculate a matching score related to the second modal by matching a feature extracted from the biometric image related to the second modal with a feature of the registered biometric information related to the second modal. The authentication unit 113b may determine whether the matching score is equal to or greater than a sixth threshold. Note that the authentication unit 113b may perform 1:N authentication or 1:1 authentication.

[0085] For example, when the information processing device 100 is used for facility entrance / exit management, the user may be permitted to enter or exit if the authentication unit 113a determines that the matching score is equal to or greater than the fifth threshold and if the authentication unit 113b determines that the matching score is equal to or greater than the sixth threshold. On the other hand, the user may not be permitted to enter or exit if the authentication unit 113a determines that the matching score is smaller than the fifth threshold or if the authentication unit 113b determines that the matching score is smaller than the sixth threshold.

[0086] For example, when the information processing device 100 is used for payment, if the authentication unit 113a determines that the matching score is equal to or greater than the fifth threshold and if the authentication unit 113b determines that the matching score is equal to or greater than the sixth threshold, the payment may be performed. On the other hand, if the authentication unit 113a determines that the matching score is smaller than the fifth threshold and / or if the authentication unit 113b determines that the matching score is smaller than the sixth threshold, the payment may not be performed.

[0087] The update determination unit 112e may determine whether to update the registered biometric information based on the authentication results of the authentication units 113a and 113b. For example, if the authentication unit 113a determines that the matching score is equal to or greater than a fifth threshold and the authentication unit 113b determines that the matching score is equal to or greater than a sixth threshold, the update determination unit 112e may determine not to update the registered biometric information. For example, if the authentication unit 113a determines that the matching score is smaller than the fifth threshold and the authentication unit 113b determines that the matching score is smaller than the sixth threshold, the update determination unit 112e may determine not to update the registered biometric information. This is because in this case, the user cannot be identified.

[0088] For example, the update determination unit 112e may determine to update the registered biometric information when the authentication unit 113a determines that the matching score is equal to or greater than a fifth threshold and the authentication unit 113b determines that the matching score is smaller than a sixth threshold. In this case, the registration unit 112b may update the registered biometric information related to the second modal by registering at least one of the biometric image related to the second modal acquired by the biometric image acquisition unit 111a and the feature amount extracted from the biometric information in the database (database 200) as registered biometric information related to the second modal.

[0089] The registration unit 112b may determine whether to register the biometric image of the second modality as registered biometric information of the second modality based on auxiliary information related to the biometric image of the second modality. For example, the auxiliary information may be date and time information. For example, the registration unit 112b may determine to register the biometric image of the second modality as registered biometric information of the second modality when the difference between the date and time indicated by the date and time information as auxiliary information related to the registered biometric information of the second modality and the date and time indicated by the date and time information as auxiliary information related to the biometric image of the second modality is equal to or greater than a predetermined time. This configuration can prevent the registered biometric information from being repeatedly registered within a relatively short period of time. Even if the matching score related to the first modality is equal to or greater than the fifth threshold, the update determination unit 112e may determine not to update the registered biometric information if the matching score related to the first modality is relatively small and there is a possibility that a different person (i.e., a person not registered) may be mistaken for the registered person.

[0090] For example, when the authentication unit 113a determines that the matching score is smaller than the fifth threshold and the authentication unit 113b determines that the matching score is equal to or larger than the sixth threshold, the update determination unit 112e may determine to update the registered biometric information. In this case, the registration unit 112b may update the registered biometric information related to the first modal by registering at least one of the biometric image related to the first modal acquired by the biometric image acquisition unit 111a and the feature amount extracted from the biometric information in the database (database 200) as registered biometric information related to the first modal.

[0091] The registration unit 112b may determine whether to register the biometric image of the first modality as registered biometric information of the first modality based on auxiliary information related to the biometric image of the first modality. For example, the auxiliary information may be date and time information. For example, the registration unit 112b may determine to register the biometric image of the first modality as registered biometric information of the first modality when the difference between the date and time indicated by the date and time information as auxiliary information related to the registered biometric information of the first modality and the date and time indicated by the date and time information as auxiliary information related to the biometric image of the first modality is equal to or greater than a predetermined time. Even if the matching score related to the second modality is equal to or greater than a sixth threshold, the update determination unit 112e may determine not to update the registered biometric information when the matching score related to the second modality is relatively small and there is a possibility that a different person may be mistaken for the enrolled person.

[0092] (Technical Effect) According to the information processing device 100 according to the sixth embodiment, it is possible to update registered biometric information without the user being aware of it. One of the first modal and the second modal may be a modal that is not easily affected by aging, such as the iris. With this configuration, for example, even if a user performs biometric authentication for the first time in several years and authentication fails in the other of the first modal and the second modal, it is possible to update the registered biometric information related to the other of the first modal and the second modal.

[0093] Note that the information processing device 100 may not have at least one of the authentication units 113a and 113b. In this case, biometric authentication related to at least one of the first modal and the second modal may be performed by a device (e.g., a cloud server) different from the information processing device 100. In this case, the information processing device 100 may transmit a biometric image related to at least one of the first modal and the second modal, acquired by the biometric image acquisition unit 111a, to a device different from the information processing device 100. Furthermore, the information processing device 100 may receive information indicating a result of biometric authentication related to at least one of the first modal and the second modal from a device different from the information processing device 100.

[0094] (First Modification) The arithmetic device 110d may include a quality evaluation unit 112a. For example, if the authentication unit 113a determines that the matching score is equal to or greater than the fifth threshold and the authentication unit 113b determines that the matching score is less than the sixth threshold, the quality evaluation unit 112a may evaluate the quality of the biometric image related to the second modal acquired by the biometric image acquisition unit 111a. If the quality satisfies a predetermined quality, the registration unit 112b may register at least one of the biometric image related to the second modal acquired by the biometric image acquisition unit 111a and the feature amount extracted from the biometric information in the database (database 200) as registered biometric information related to the second modal. For example, if the authentication unit 113a determines that the matching score is less than the fifth threshold and the authentication unit 113b determines that the matching score is equal to or greater than the sixth threshold, the quality evaluation unit 112a may evaluate the quality of the biometric image related to the first modal acquired by the biometric image acquisition unit 111a. If the quality satisfies a predetermined quality, the registration unit 112b may register at least one of the biometric image related to the first modal acquired by the biometric image acquisition unit 111a and the feature amount extracted from the biometric information in the database (database 200) as registered biometric information related to the first modal. With this configuration, the quality of the registered biometric information can be maintained at a high level.

[0095] (Second Modification) For example, the calculation device 110d may calculate a weighted average of the matching score calculated by the authentication unit 113a and the matching score calculated by the authentication unit 113b as the fusion score. For example, when the information processing device 100 is used for facility entrance / exit management, a user may be permitted to enter or exit if the fusion score is equal to or greater than a predetermined threshold. For example, when the information processing device 100 is used for payment, payment may be made if the fusion score is equal to or greater than a predetermined threshold.

[0096] When the registered biometric information related to one of the first modal and the second modal is updated, the arithmetic device 110d may, for a predetermined period after the update, make the weight related to one of the first modal and the second modal smaller than the weight related to the other of the first modal and the second modal when calculating the fusion score. With this configuration, it is possible to suppress the influence on multimodal biometric authentication of, for example, temporary changes in biometric information due to injury or illness, and changes in biometric information due to fraudulent means (e.g., spoofing).

[0097] <Modification> A modification common to the third, fifth, and sixth embodiments will be described. Note that descriptions overlapping with those of the third, fifth, and sixth embodiments will be omitted as appropriate. In each of the third, fifth, and sixth embodiments, registered biometric information is automatically registered or updated. In contrast, the information processing device 100 according to this modification may notify the user that the registered biometric information will be registered or updated when the registered biometric information is to be registered or updated. For example, the output device 150 may display an image that prompts the user to select whether or not to register or update the registered biometric information. If the user selects, via the input device 140, to register or update the registered biometric information, the information processing device 100 may register or update the registered biometric information. On the other hand, if the user selects, via the input device 140, not to register or update the registered biometric information, the information processing device 100 need not register or update the registered biometric information.

[0098] <Supplementary Notes> A part or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes.

[0099] (Supplementary Note 1) An information processing device comprising: an acquisition means for acquiring biometric information of a target; and a control means for controlling at least one of registration and update of the biometric information of the target based on at least one of the quality of the biometric information, auxiliary information related to the biometric information, and a matching score calculated using the biometric information.

[0100] (Supplementary Note 2) The information processing device according to Supplementary Note 1, wherein the control means determines whether or not to register the biometric information acquired by the acquisition means, based on the quality and the matching score.

[0101] (Supplementary Note 3) The information processing device described in Supplementary Note 2, wherein the acquisition means acquires multiple pieces of biometric information of the target, and the control means extracts two or more pieces of biometric information having a predetermined quality from the multiple pieces of biometric information based on the quality of each piece of the multiple pieces of biometric information, and determines whether or not to register the extracted two or more pieces of biometric information based on a matching score calculated using the extracted two or more pieces of biometric information.

[0102] (Supplementary Note 4) The information processing device described in Supplementary Note 1, wherein the acquisition means acquires first biometric information of the target and second biometric information different from the first biometric information, and the control means determines whether to update the biometric information of the target based on the auxiliary information when the target is identified by biometric authentication using the first biometric information and is not identified by biometric authentication using the second biometric information.

[0103] (Supplementary Note 5) The information processing device according to Supplementary Note 1, wherein the control means suggests to the subject that the biometric information of the subject be updated when the matching score is within a predetermined range.

[0104] (Supplementary Note 6) The information processing device according to Supplementary Note 1, wherein the control means determines whether or not to register the biometric information acquired by the acquisition means based on the quality.

[0105] (Supplementary Note 7) The information processing device according to Supplementary Note 4, wherein the auxiliary information includes an elapsed time since the previous biometric authentication, and the control means determines to update the target biometric information when the elapsed time included in the auxiliary information is equal to or greater than a predetermined time.

[0106] (Supplementary Note 8) The information processing device according to Supplementary Note 1, wherein the biometric information includes information relating to an iris of the subject, and the quality of the biometric information includes an imaging condition relating to light.

[0107] (Appendix 9) The information processing device described in Appendix 6, wherein a plurality of pieces of biometric information of the subject are registered in the database, and when registering new biometric information of the subject in the database, the control means deletes one or more of the plurality of pieces of biometric information of the subject that are already registered in the database.

[0108] (Supplementary Note 10) An information processing system comprising: an acquisition means for acquiring biometric information of a target; and a control means for controlling at least one of registration and update of the biometric information of the target based on at least one of the quality of the biometric information, auxiliary information related to the biometric information, and a matching score calculated using the biometric information.

[0109] (Supplementary Note 11) An information processing method for acquiring biometric information of a target, and controlling at least one of registration and update of the biometric information of the target based on at least one of quality of the biometric information, auxiliary information related to the biometric information, and a matching score calculated using the biometric information.

[0110] (Supplementary Note 12) A recording medium having recorded thereon a computer program for causing a computer to execute an information processing method for acquiring biometric information of a subject, and controlling at least one of registration and updating of the biometric information of the subject based on at least one of the quality of the biometric information, auxiliary information related to the biometric information, and a matching score calculated using the biometric information.

[0111] Furthermore, some or all of the configurations described in Supplementary Notes 2 to 9 that are dependent on Supplementary Note 1 above may also be dependent on Supplementary Notes 10, 11, and 12 in the same dependent relationship as Supplementary Notes 2 to 9. Furthermore, not limited to Supplementary Notes 1, 10, 11, and 12, some or all of the configurations described as Supplements may be made dependent on various hardware, software, various recording means for recording software, or systems, within the scope of each of the above-mentioned embodiments.

[0112] This disclosure may be modified as appropriate within the scope that does not contradict the gist or idea of ​​the invention that can be read from the claims and the entire specification, and information processing devices, information processing systems, information processing methods, and recording media that involve such modifications are also included in the technical idea of ​​this disclosure.

[0113] 10, 100 Information processing device 11, 111 Acquisition unit 12, 112 Control unit

Claims

1. An information processing device comprising: an acquisition means for acquiring biometric information of a target; and a control means for controlling at least one of registration and updating of the biometric information of the target based on at least one of the quality of the biometric information, auxiliary information related to the biometric information, and a matching score calculated using the biometric information.

2. The information processing device according to claim 1, wherein the control means determines whether or not to register the biometric information acquired by the acquisition means based on the quality and the matching score.

3. The information processing device according to claim 2, wherein the acquisition means acquires multiple pieces of biometric information of the subject, and the control means extracts two or more pieces of biometric information having a predetermined quality from the multiple pieces of biometric information based on the quality of each piece of biometric information, and determines whether or not to register the extracted two or more pieces of biometric information based on a matching score calculated using the extracted two or more pieces of biometric information.

4. The information processing device described in claim 1, wherein the acquisition means acquires first biometric information of the target and second biometric information different from the first biometric information, and the control means determines whether to update the biometric information of the target based on the auxiliary information when the target is identified by biometric authentication using the first biometric information and is not identified by biometric authentication using the second biometric information.

5. The information processing device according to claim 1, wherein the control means suggests to the subject that the biometric information of the subject be updated if the matching score is within a predetermined range.

6. The information processing device according to claim 1, wherein the control means determines whether or not to register the biometric information acquired by the acquisition means based on the quality.

7. The information processing device according to claim 4, wherein the auxiliary information includes the time elapsed since the previous biometric authentication, and the control means determines to update the target biometric information if the elapsed time included in the auxiliary information is equal to or greater than a predetermined time.

8. The information processing device according to claim 1, wherein the biometric information includes information relating to the subject's iris, and the quality of the biometric information includes imaging conditions relating to light.

9. An information processing device as described in claim 6, wherein a plurality of pieces of biometric information of the subject are registered in the database, and when registering new biometric information of the subject in the database, the control means deletes one or more of the pieces of biometric information of the subject that are already registered in the database.

10. An information processing system comprising: an acquisition means for acquiring biometric information of a subject; and a control means for controlling at least one of registration and updating of the biometric information of the subject based on at least one of the quality of the biometric information, auxiliary information related to the biometric information, and a matching score calculated using the biometric information.

11. An information processing method for acquiring biometric information of a target, and controlling at least one of registration and updating of the biometric information of the target based on at least one of the quality of the biometric information, auxiliary information related to the biometric information, and a matching score calculated using the biometric information.

12. A recording medium having recorded thereon a computer program for causing a computer to execute an information processing method that acquires biometric information of a subject, and controls at least one of registration and updating of the biometric information of the subject based on at least one of the quality of the biometric information, auxiliary information related to the biometric information, and a matching score calculated using the biometric information.

Images