Information processing device, information processing method, and computer program

Abstract

An information processing device 1 comprises: a transformation unit 11 that transforms biometric information to generate transformed biometric information; and an estimation unit 12 that uses the biometric information and the transformed biometric information as a basis for estimating the likelihood of other-person acceptance in which another person is accepted erroneously when said biometric information is used for biometric authentication.

Description

Information processing device, information processing method, and recording medium

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

[0002] Patent Literature 1 describes a wearable system that receives a first plurality of iris images from an iris imaging device, generates a first plurality of iris codes corresponding to the first plurality of iris images, generates a distribution metric corresponding to iris cell locations, generates a first composite iris code using the distribution metric, and generates a first matching value using the first composite iris code and a first stored iris code. Patent Literature 2 describes a technology that acquires biometric information to be registered, references a storage means that stores registered biometric information linked to groups, calculates a similarity between the biometric information to be registered and the registered biometric information, selects a group to be linked to the biometric information to be registered based on the calculated similarity, and links the selected group to the biometric information to be registered and registers it in the storage means. Patent Literature 3 describes a technology that authenticates biometric information identified from multiple captured images of a user's eyes with different gaze directions based on reference images of the user's eyes for each gaze direction, and combines the respective authentication results to improve the accuracy of authentication based on biometric information of the eyes. Patent Document 4 describes a technology in which biometric information is acquired from each of a pair of left and right biological parts on the body, matching feature data to be used for matching is generated from each of the left and right biometric information, similarity feature data to be used for calculating the similarity between the left and right biometric information is generated from each of the left and right biometric information, and similarity scores indicating the similarity between the left and right biometric information are calculated by comparing the left and right matching feature data and the similarity scores, and the left and right matching feature data and the similarity scores are associated and registered in a registration DB, the left and right matching feature data are compared with left and right matching feature data generated from the biometric information at the time of authentication to calculate matching scores for each of the left and right, and the success or failure of authentication is determined using the similarity scores obtained by comparing the left and right matching scores, the similarity scores in the registration DB, and the left and right similarity features at the time of authentication.Patent Literature 5 describes a technology in which a biometric information acquisition unit acquires biometric information, a registration information acquisition unit acquires first registration information and second registration information, an authentication unit generates a matching score from the first registration information and the biometric information, compares it with a threshold and outputs an authentication result, a matching evaluation unit generates a matching score for each combination of successfully authenticated biometric information and two of the first registration information and the second registration information, evaluates the matching score, generates an evaluation result, and if the biometric information can be good second registration information, a replacement unit replaces the biometric information as new second registration information, thereby improving authentication accuracy during the authentication process. Patent Literature 6 describes a technology in which multiple iris codes for each enrollee are registered in an iris database together with pupil diameter / iris diameter ratio, and during authentication, the iris code is obtained by feature extraction from a captured iris image, and the pupil diameter / iris diameter ratio is calculated and compared with the ratio at the time of registration to select an appropriate iris code from the iris database as a matching target, and authentication is performed.

[0003] Japanese Patent Application Laid-Open No. 2022-105185 Japanese Patent Application Laid-Open No. 2017-215894 International Publication No. 2016 / 088415 Japanese Patent Application Laid-Open No. 2016-099880 International Publication No. 2012 / 131899 Japanese Patent Application Laid-Open No. 2004-167227

[0004] An object of this disclosure is to provide an information processing device, an information processing method, and a recording medium that aim to improve upon the techniques described in prior art documents.

[0005] One aspect of the information processing device includes a transformation means for transforming biometric information to generate transformed biometric information, and an estimation means for estimating, based on the biometric information and the transformed biometric information, the possibility of false acceptance, that is, false acceptance, when the biometric information is used for biometric authentication.

[0006] One aspect of the information processing method is to deform biometric information to generate deformed biometric information, and based on the biometric information and the deformed biometric information, estimate the possibility of false acceptance, that is, false acceptance, when the biometric information is used for biometric authentication.

[0007] One aspect of the recording medium has recorded thereon a computer program for causing a computer to execute an information processing method that transforms biometric information to generate transformed biometric information, and, based on the biometric information and the transformed biometric information, estimates the possibility of false acceptance, which would result in false acceptance of a false person, when the biometric information is used for biometric authentication.

[0008] FIG. 1 is a block diagram showing the configuration of an information processing device in a first embodiment. FIG. 2 is a block diagram showing the configuration of an information processing device in a second embodiment. FIG. 3 is a flowchart showing the flow of information processing operation of the information processing device in the second embodiment. FIG. 4 is a block diagram showing the configuration of an information processing device in a third embodiment. FIG. 5 is a diagram showing an overview of information processing operation of the information processing device in the third embodiment. FIG. 6 is a block diagram showing the configuration of an information processing device in a fourth embodiment. FIG. 7 is a flowchart showing the flow of information processing operation of the information processing device in the fourth embodiment. FIG. 8 is a block diagram showing the configuration of an information processing device in a fifth embodiment. FIG. 9 is a block diagram showing the configuration of an information processing device in a sixth embodiment. FIG. 10 is a flowchart showing the flow of information processing operation of the information processing device in the sixth embodiment. FIG. 11 is a diagram illustrating a matching score distribution generated by the information processing device in the sixth embodiment. FIG. 12 is a block diagram showing the configuration of an information processing device in a seventh embodiment. FIG. 13 is a block diagram showing the configuration of an information processing device in an eighth embodiment.

[0009] Hereinafter, embodiments of an information processing device, an information processing method, and a recording medium will be described with reference to the drawings. [1: First Embodiment]

[0010] A first embodiment of an information processing device, an information processing method, and a recording medium will be described below. Hereinafter, the first embodiment of the information processing device, the information processing method, and the recording medium will be described using an information processing device 1 to which the first embodiment of the information processing device, the information processing method, and the recording medium is applied. [1-1: Configuration of Information Processing Device 1]

[0011] FIG. 1 is a block diagram showing the configuration of an information processing device 1 according to the first embodiment. As shown in FIG. 1, the information processing device 1 includes a transformation unit 11 and an estimation unit 12. The transformation unit 11 transforms biometric information to generate transformed biometric information. The estimation unit 12 estimates the possibility of false acceptance, that is, false acceptance, when the biometric information is used for biometric authentication, based on the biometric information and the transformed biometric information. [1-2: Technical Effects of the Information Processing Device 1]

[0012] The information processing device 1 according to the first embodiment can estimate the possibility of erroneously accepting a different person when biometric information is used for biometric authentication, from information that can be acquired based on the biometric information. [2: Second Embodiment]

[0013] Next, a second embodiment of the information processing device, the information processing method, and the recording medium will be described. Hereinafter, the second embodiment of the information processing device, the information processing method, and the recording medium will be described using an information processing device to which the second embodiment of the information processing device, the information processing method, and the recording medium is applied. [2-1: Configuration of Information Processing Device 2]

[0014] 2 is a block diagram showing the configuration of an information processing device 2 in the second embodiment. As shown in FIG. 2, the information processing device 2 includes a calculation device 21 and a storage device 22. The information processing device 2 may further include a communication device 23, an input device 24, and an output device 25. However, the information processing device 2 does not necessarily have to include at least one of the communication device 23, the input device 24, and the output device 25. The calculation device 21, the storage device 22, the communication device 23, the input device 24, and the output device 25 may be connected via a data bus 26.

[0015] The arithmetic device 21 includes, for example, at least one of a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), and an FPGA (Field Programmable Gate Array). The arithmetic device 21 reads a computer program. For example, the arithmetic device 21 may read a computer program stored in the storage device 22. For example, the arithmetic device 21 may read a computer program stored in a computer-readable, non-transitory recording medium using a recording medium reading device (e.g., an input device 24 described later) not shown in the drawings that is included in the information processing device 2. The arithmetic device 21 may acquire (i.e., download or read) the computer program from a device (not shown) located outside the information processing device 2 via the communication device 23 (or another communication device). The arithmetic device 21 executes the read computer program. As a result, logical functional blocks for executing the operations to be performed by the information processing device 2 are realized within the arithmetic device 21. In other words, the arithmetic device 21 can function as a controller for realizing logical functional blocks for executing the operations (in other words, processing) to be performed by the information processing device 2.

[0016] 2 shows an example of logical functional blocks implemented within the arithmetic device 21 to perform information processing operations. As shown in FIG. 2 , the arithmetic device 21 implements a transformation unit 211, which is a specific example of a "transformation means" described in the appendix below, an estimation unit 212, which is a specific example of an "estimation means" described in the appendix below, a feature extraction unit 213, a matching score calculation unit 214, a biometric information acquisition unit 215, a registration unit 216, and an authentication unit 217. However, any of the feature extraction unit 213, the matching score calculation unit 214, the biometric information acquisition unit 215, the registration unit 216, and the authentication unit 217 may not be implemented within the arithmetic device 21. Details of the operations of the transformation unit 211, the estimation unit 212, the feature extraction unit 213, the matching score calculation unit 214, the biometric information acquisition unit 215, the registration unit 216, and the authentication unit 217 will be described later with reference to FIG. 3.

[0017] The storage device 22 can store desired data. For example, the storage device 22 may temporarily store a computer program executed by the arithmetic device 21. The storage device 22 may temporarily store data that the arithmetic device 21 temporarily uses when the arithmetic device 21 is executing a computer program. The storage device 22 may store data that the information processing device 2 stores for a long period of time. The storage device 22 may include 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 a disk array device. In other words, the storage device 22 may include a non-temporary recording medium. A registered biometric information database 221 may be implemented within the storage device 22.

[0018] The communication device 23 is capable of communicating with devices external to the information processing device 2 via a communication network (not shown). The communication device 23 may be a communication interface based on standards such as Ethernet (registered trademark), Wi-Fi (registered trademark), Bluetooth (registered trademark), or USB (Universal Serial Bus).

[0019] The input device 24 is a device that accepts information input to the information processing device 2 from outside the information processing device 2. For example, the input device 24 may include an operation device (e.g., at least one of a keyboard, a mouse, and a touch panel) that can be operated by an operator of the information processing device 2. For example, the input device 24 may include a reading device that can read information recorded as data on a recording medium that can be externally attached to the information processing device 2.

[0020] The output device 25 is a device that outputs information to the outside of the information processing device 2. For example, the output device 25 may output information as an image. That is, the output device 25 may include a display device (a so-called display) that can display an image showing the information to be output. For example, the output device 25 may output information as sound. That is, the output device 25 may include an audio device (a so-called speaker) that can output sound. Furthermore, for example, the output device 25 may output information on paper. That is, the output device 25 may include a printing device (a so-called printer) that can print desired information on paper. [2-2: Information Processing Operation Performed by the Information Processing Device 2]

[0021] The information processing device 2 in this embodiment performs biometric authentication using biometric information. In this embodiment, the biometric information includes a biometric image to be used for biometric authentication. The biometric image may include a face image, an iris image, a fingerprint image, etc. Furthermore, in this embodiment, the biometric information includes feature amounts extracted from the biometric image to be used for biometric authentication. The information processing device 2 performs an operation by the registration unit 216 to register the biometric information acquired by the biometric information acquisition unit 215 into the registered biometric information database 221, and an operation by the authentication unit 217 to perform biometric authentication between the biometric information acquired by the biometric information acquisition unit 215 and the biometric information registered in the registered biometric information database 221.

[0022] In the biometric authentication operation, first, the feature extraction unit 213 extracts features from the biometric image acquired by the biometric information acquisition unit 215 or the deformed biometric image deformed by the deformation unit 211. Next, the matching score calculation unit 214 calculates an authentication score based on the features. The authentication unit 217 determines whether biometric authentication is successful by comparing the authentication score with an authentication score threshold. The authentication score threshold may be set depending on the characteristics of the feature extraction unit 213 and the matching score calculation unit 214, the purpose of biometric authentication, the environment in which biometric authentication is used, etc. Note that a score used for authentication, which is calculated from features extracted from an image and features registered in the registered biometric information database, is referred to as an authentication score. Furthermore, a score used for quality judgment, which is calculated from features extracted from an acquired image and features extracted from a deformed biometric image, is referred to as a matching score. Furthermore, a score forming a score distribution used for quality judgment, which will be described in another embodiment, is also referred to as a matching score. The authentication score and the matching score are calculated by the same authentication device.

[0023] The information processing device 2 in this embodiment evaluates whether the quality of the biometric information satisfies the standard for registration in the registered biometric information database 221 before registering the biometric information. Furthermore, the information processing device 2 in this embodiment evaluates whether the quality of the biometric information satisfies the standard for biometric authentication before performing a biometric authentication operation using the biometric information. That is, the information processing device 2 can perform biometric authentication using registered biometric information of a predetermined quality or higher and biometric information of a predetermined quality or higher. Specifically, biometric information of a predetermined quality or higher in this embodiment is biometric information that is unlikely to erroneously accept a false person when used for biometric authentication.

[0024] The information processing device 2 performs a false acceptability estimation operation to estimate the possibility of false acceptance, that is, false acceptance, when the biometric information acquired by the biometric information acquisition unit 215 is used for biometric authentication. The information processing device 2 performs the false acceptability estimation operation using the feature extraction unit 213 and the matching score calculation unit 214, which are used by the authentication unit 217 in the biometric authentication operation.

[0025] The flow of the stranger acceptability estimation operation performed by the information processing device 2 will be described with reference to Fig. 3. Fig. 3 is a flowchart showing the stranger acceptability estimation operation performed by the information processing device 2.

[0026] 3, the biometric information acquisition unit 215 acquires a captured image of a living body (step S20). The biometric information acquisition unit 215 may acquire an image of a living body captured by a camera. The biometric information may be an image of a living body captured for registration purposes. Alternatively, the biometric information may be an image of a living body captured for biometric authentication purposes.

[0027] The transformation unit 211 transforms the biometric information to generate transformed biometric information (step S21). The transformation unit 211 may transform the biometric image to generate a transformed biometric image. When the biometric information is transformed, the generated transformed biometric information changes the individual characteristics of the original biometric information before transformation. Therefore, when the biometric image is transformed, the generated transformed biometric image becomes an image of a biometric with characteristics different from those of the original biometric image before transformation. In other words, the transformation unit 211 generates a transformed biometric image with characteristics of another person that are different from the original. The transformation of the transformed biometric image will be described in other embodiments.

[0028] The feature extraction unit 213 extracts the feature of the biometric information from the biometric information and extracts the deformation feature of the deformed biometric information from the deformed biometric information (step S22). The feature extraction unit 213 may extract the feature of the biometric image and the deformation feature of the deformed biometric image.

[0029] The matching score calculation unit 214 calculates a matching score based on the feature amount and the deformation feature amount (step S23). The matching score calculation unit 214 calculates a matching score as a numerical value for determining whether the biometric information is that of the same person. The matching score increases when the possibility that the biometric information is that of the same person is high, and decreases when the possibility that the biometric information is that of the same person is low. However, when using a biometric authentication device with a characteristic that the matching score decreases when the possibility that the biometric information is that of the same person is high and increases when the possibility that the biometric information is that of the same person is low, the relationship between the possibility that the biometric information is that of the same person and the magnitude of the matching score becomes the opposite of the above. Hereinafter, an authentication device that increases the matching score when the possibility that the biometric information is that of the same person will be described as an example. The matching score calculation unit 214 may calculate the matching score in the same way as the authentication score calculated during authentication.

[0030] However, when the quality of biometric information is poor, the matching score often becomes high when the same type of poor-quality biometric information is used, even if the biometric information belongs to different people. In other words, when poor-quality biometric information is used, the possibility of false acceptance increases. Examples of poor quality include focus blur, motion blur, dilated pupils, low contrast, and sensor noise.

[0031] As described above, deformed biometric information is information that has lost the characteristics of the owner of the biometric information before deformation. Therefore, the extracted deformation feature also loses the characteristics of the owner. When the quality of the biometric information is good, the matching score calculated based on the feature and the deformation feature often becomes a numerical value indicating a low possibility that the biometric information is from the same person. In other words, the matching score often becomes small. On the other hand, when the quality of the biometric information is poor, the matching score calculated based on the feature and the deformation feature may become a numerical value indicating a high possibility that the biometric information is from the same person. In other words, the matching score may become large. Therefore, based on whether the matching score calculated from the biometric information and information from which the characteristics have been removed is a numerical value indicating a high possibility that the biometric information is from the same person, it is possible to estimate the possibility of false acceptance when biometric authentication is performed using the biometric information.

[0032] The estimation unit 212 estimates the possibility of false acceptance based on the matching score (step S24). If the matching score is a value indicating a low possibility that the biometric information is that of the same person, the estimation unit 212 can estimate that the possibility of false acceptance is low. In other words, since a value indicating a low possibility that the information is the biometric information of the person himself / herself is calculated for information that has lost its authenticity due to deformation, it can be estimated that the possibility of false acceptance is low in biometric authentication using the biometric information. On the other hand, if the matching score is a value indicating a high possibility that the information is the biometric information of the same person, the estimation unit 212 can estimate that the possibility of false acceptance is high. In other words, since a value indicating a high possibility that the information is the biometric information of the person himself / herself is calculated for information that has lost its authenticity due to deformation, it can be estimated that the possibility of false acceptance is high in biometric authentication using the biometric information. In other words, the estimation unit 212 determines whether the matching score is a value indicating a low possibility that the information is the biometric information of the same person or a value indicating a high possibility that the matching score is calculated based on the biometric information of the same person. The estimation unit 212 may set a threshold for the matching score and estimate the possibility of false acceptance by comparing the matching score with the threshold. In this way, the estimation unit 212 can estimate the possibility of false acceptance based on the biometric information and the deformed biometric information. The threshold value of the matching score may be set based on the distribution of the matching score calculated by the matching score calculation unit 214 based on the feature extracted by the feature extraction unit 213. The distribution of the matching score will be described in another embodiment.

[0033] If the possibility of false acceptance is low (step S24: Yes) and biometric information for registration has been acquired in step 20, the registration unit 216 registers the acquired biometric information in the registered biometric information database 221 (step S25-1). If the possibility of false acceptance is low (step S24: Yes) and biometric information for authentication has been acquired in step 20, the authentication unit 217 performs biometric authentication using the acquired biometric information and the biometric information registered in the registered biometric information database 221 (step S25-2).

[0034] If there is a high possibility of accepting a different person (step S24: No), the process may return to step S20, where an image may be captured again to acquire biometric information again.

[0035] The functions of the transformation unit 211, the estimation unit 212, the feature extraction unit 213, and the matching score calculation unit 214 in this embodiment may be referred to as quality evaluation functions. [2-3: Technical Effects of Information Processing Device 2]

[0036] If low-quality biometric information is mixed in the biometric information registered in the registration database and the biometric information to be authenticated, the possibility of mistakenly accepting a different person may increase. It may also increase the possibility of rejecting a person who is the correct person. Using low-quality biometric information for biometric authentication in this way reduces the accuracy, usability, and other performance aspects of the authentication system. Registering low-quality biometric information in the registration database is particularly problematic, as the owner of that biometric information will always be authenticated as having low-quality biometric information.

[0037] The information processing device 2 in the second embodiment uses a matching score based on an acquired biometric image and a deformed biometric image, thereby preventing false acceptance, which is the false acceptance caused by the quality of the biometric image. That is, the information processing device 2 can determine whether the quality of an image is sufficient for biometric authentication from a single image of a biometric body. For example, the information processing device 2 does not need to refer to information registered in a database or the like, and can therefore relatively easily estimate the possibility of false acceptance when a biometric image is used for biometric authentication. [3: Third Embodiment]

[0038] Next, a third embodiment of the information processing device, the information processing method, and the recording medium will be described. Hereinafter, the third embodiment of the information processing device, the information processing method, and the recording medium will be described using an information processing device 3 to which the third embodiment of the information processing device, the information processing method, and the recording medium is applied.

[0039] 4 is a block diagram showing the configuration of an information processing device 3 according to the third embodiment. The information processing device 3 according to the third embodiment differs from the information processing device 2 according to the second embodiment in the operations of a transformation unit 311, an estimation unit 312, a feature extraction unit 313, a matching score calculation unit 314, a biometric information acquisition unit 315, a registration unit 316, and an authentication unit 317. [3-1: Information Processing Operations Performed by Information Processing Device 3]

[0040] The flow of information processing operations performed by the information processing device 3 will be described with reference to Fig. 3. In the third embodiment, the biometric information includes an iris image.

[0041] 3, the biometric information acquisition unit 315 acquires a captured iris image (step S20). The iris image acquired by the biometric information acquisition unit 315 may be an iris image captured for registration purposes. Alternatively, the iris image acquired by the biometric information acquisition unit 315 may be an iris image captured for biometric authentication purposes.

[0042] The deformation unit 311 deforms the iris image to generate a deformed iris image (step S21). [Example of generation of a deformed iris image]

[0043] The deformation unit 311 may generate a deformed iris image by inverting the iris image. The approximately circular iris region of the iris image is called an iris circle. The deformation unit 311 may generate a deformed iris image by inverting the iris circle of the iris image in any direction. If the image shown in FIG. 5(a-L) is an original iris image that has not been deformed, the deformation unit 311 may invert the original iris image left and right to generate a deformed iris image shown in FIG. 5(a-R).

[0044] Furthermore, the deformation unit 311 may divide the iris circle of the iris image into partial regions by at least one of the radii of two or more iris circles and a circle that shares a center with the iris circle, and generate a deformed iris image by changing the position of the partial region. In other words, the deformation unit 311 may generate a deformed iris image by combining partial images.

[0045] The deformation unit 311 may divide the iris circle of the iris image by the diameter of the iris circle and change the positions of the divided partial regions to generate a deformed iris image. Assume that the image illustrated in FIG. 5(b-L) is an original, undeformed iris image. In this case, for example, as illustrated in FIG. 5(b-L), the deformation unit 311 may divide the iris circle into an upper region and a lower region by the diameter of the iris circle. The deformation unit 311 may generate the deformed iris image illustrated in FIG. 5(b-R) by changing the position of the upper region of the iris circle illustrated in FIG. 5(b-L) downward and changing the position of the lower region of the iris circle illustrated in FIG. 5(b-L) upward.

[0046] The deformation unit 311 may divide the iris circle of the iris image into an inner region and an outer region of a circle that shares a center with the iris circle, and generate a deformed iris image by changing the positions of the divided partial regions. Alternatively, the deformation unit 311 may divide the iris circle of the iris image into one side and the other side of the radius of the iris circle, and generate a deformed iris image by changing the positions of the divided partial regions. Assume that the image illustrated in FIG. 5(c-L) is an undeformed original iris image. In this case, for example, as illustrated in FIG. 5(c-L), the deformation unit 311 may divide the iris circle into an inner region and an outer region of the iris circle, using a circle that shares a center with the iris circle. The deformation unit 311 may generate a deformed iris image illustrated in FIG. 5(c-R) by changing the position of the inner region of the iris circle illustrated in FIG. 5(c-L) outward and changing the position of the outer region of the iris circle illustrated in FIG. 5(c-L) inward.

[0047] The feature extraction unit 313 extracts iris image feature amounts from the iris image and extracts deformation feature amounts of the deformed iris image from the deformed iris image (step S22). The matching score calculation unit 314 calculates a matching score based on the iris feature amounts and the deformed iris feature amounts (step S23). The estimation unit 312 estimates the possibility of false acceptance based on the matching score (step S24).

[0048] If the possibility of false acceptance is low (step S24: Yes) and an iris image for registration has been acquired in step 20, the registration unit 316 registers the acquired iris image in the registered biometric information database 321 (step S25-1). If the possibility of false acceptance is low (step S24: Yes) and an iris image for authentication has been acquired in step 20, the authentication unit 317 performs iris authentication using the acquired iris image and the iris image registered in the registered biometric information database 321 (step S25-2).

[0049] In the present embodiment, the biometric information is an iris image as an example. If the biometric information is a fingerprint image, the deformation unit 311 may perform the same deformation as that performed on the iris image described above. If the biometric information is a face image, the deformation unit 311 may deform the face image by exchanging parts included in the face area, such as exchanging the left and right eyes or the left and right ears. [3-2: Technical Effects of the Information Processing Device 3]

[0050] The information processing device 3 according to the third embodiment can estimate the possibility of false acceptance in iris authentication using an iris image when registering and authenticating the iris image. The information processing device 3 can ensure the quality of the iris image used for iris authentication.

[0051] Furthermore, the information processing device 3 can efficiently transform the iris image. The information processing device 3 can transform the iris information without losing the original information. [4: Fourth Embodiment]

[0052] Next, a fourth embodiment of the information processing device, the information processing method, and the recording medium will be described. Hereinafter, the fourth embodiment of the information processing device, the information processing method, and the recording medium will be described using an information processing device 4 to which the fourth embodiment of the information processing device, the information processing method, and the recording medium is applied.

[0053] 6 is a block diagram showing the configuration of an information processing device 4 according to the fourth embodiment. The information processing device 4 according to the fourth embodiment differs from the information processing device 2 according to the second embodiment and the information processing device 3 according to the third embodiment in the operations of a transformation unit 411, an estimation unit 412, a feature extraction unit 413, a matching score calculation unit 414, a biometric information acquisition unit 415, a registration unit 416, and an authentication unit 417. [4-1: Information Processing Operations Performed by Information Processing Device 4]

[0054] The flow of the information processing operation performed by the information processing device 4 will be described with reference to Fig. 7. Fig. 7 is a flowchart showing the information processing operation performed by the information processing device 4.

[0055] In the fourth embodiment, the biometric information includes features extracted from an image of a biometric person. As shown in Fig. 7, the biometric information acquisition unit 415 acquires a captured image of a biometric person (step S20). The biometric image may be an image that can be used for biometric authentication, such as a face image, an iris image, or a fingerprint image. The biometric image may be an image of a biometric person captured for registration purposes. Alternatively, the biometric image may be an image of a biometric person captured for biometric authentication purposes.

[0056] The feature extraction unit 413 extracts feature amounts of the biometric image from the biometric image (step S40). The feature amounts extracted from the biometric image by the feature extraction unit 413 may include a correspondence between coordinates in the image and information on the feature corresponding to the coordinates. The coordinates in the image may be polar coordinates.

[0057] The transformation unit 411 transforms the feature amount to generate a transformed feature amount (step S41). The transformation unit 411 may transform the feature amount so as to maintain the correspondence between coordinates in the image and feature information. The transformation of the feature amount will be described in another embodiment. When the feature amount is transformed, the generated transformed feature amount loses the authenticity possessed by the original feature amount before transformation. In other words, the transformation unit 411 generates a transformed feature amount having the features of another person different from the actual person.

[0058] The matching score calculation unit 414 calculates a matching score based on the feature amount and the deformation feature amount (step S42).

[0059] The estimation unit 412 estimates the possibility of false acceptance based on the matching score (step S43). If the matching score is a value that indicates a low possibility that the features are those of the same person, the estimation unit 412 can estimate that the possibility of false acceptance is low. On the other hand, if the matching score is a magnitude that indicates a high possibility that the features are those of the same person, the estimation unit 412 can estimate that the possibility of false acceptance is high. In other words, the estimation unit 412 determines whether the matching score is a magnitude that indicates a high possibility that the features are those of the same person, or a magnitude that indicates a low possibility that the matching score is those of the same person.

[0060] If the possibility of false acceptance is low (step S43: Yes) and if a biometric image for registration has been acquired in step S20, the registration unit 416 registers the acquired biometric image in the registered biometric information database 421 (step S25-1). The registration unit 416 may register feature amounts extracted from the acquired biometric image in the registered biometric information database 421.

[0061] If the possibility of false acceptance is low (step S43: Yes) and a biometric image for biometric authentication has been acquired in step S20, the authentication unit 417 performs biometric authentication using the acquired biometric image and a biometric image registered in the registered biometric information database 421 (step S25-2). If feature amounts extracted from the biometric image are registered in the registered biometric information database 421, the authentication unit 417 may perform biometric authentication using the feature amounts extracted from the acquired biometric image and the feature amounts registered in the registered biometric information database 421. [4-2: Technical Effects of Information Processing Device 4]

[0062] The information processing device 4 in the fourth embodiment can suppress false acceptance, which is a false acceptance caused by the quality of a biometric image, by using a matching score based on the feature amounts of an acquired biometric image and the deformed feature amounts. That is, the information processing device 4 can determine, from a single image of a biometric image, whether the image quality is sufficient for use in biometric authentication. Because the information processing device 4 does not need to refer to information registered in a database, for example, it can relatively easily estimate the possibility of false acceptance when a biometric image is used for biometric authentication.

[0063] In biometric authentication, the process of extracting features is a relatively heavy process. The information processing device 4 transforms the features extracted from a biometric image, so it performs the process of extracting features from one biometric image only once. Therefore, the information processing device 4 performs lighter processing than when it transforms a biometric image, extracts features from the biometric image, and then extracts features from the transformed biometric image. [5: Fifth Embodiment]

[0064] Next, a fifth embodiment of the information processing device, the information processing method, and the recording medium will be described. Hereinafter, the fifth embodiment of the information processing device, the information processing method, and the recording medium will be described using an information processing device 5 to which the fifth embodiment of the information processing device, the information processing method, and the recording medium is applied.

[0065] 8 is a block diagram showing the configuration of an information processing device 5 according to the fifth embodiment. The information processing device 5 according to the fifth embodiment differs from the information processing device 2 according to the second embodiment to the information processing device 4 according to the fourth embodiment in the operations of a transformation unit 511, an estimation unit 512, a feature extraction unit 513, and a matching score calculation unit 514. [5-1: Information Processing Operations Performed by Information Processing Device 5]

[0066] The flow of information processing operations performed by the information processing device 5 will be described with reference to Fig. 7. In the fifth embodiment, the biometric information includes iris feature amounts extracted from an iris image.

[0067] 7, the biometric information acquisition unit 515 acquires a captured iris image (step S20). The iris image may be an iris image captured for registration purposes. Alternatively, the iris image may be an iris image captured for iris authentication purposes.

[0068] The feature extraction unit 513 extracts iris feature amounts from the iris image (step S40). The feature extraction unit 513 detects an iris circle from the iris image and extracts iris feature amounts from the iris circle. The iris feature amounts may include information indicating changes in features along the circumferential direction of the iris circle. The deformation unit 511 deforms the iris feature amounts to generate deformed iris feature amounts (step S41). [Example of generation of deformed iris feature amounts]

[0069] The deformation unit 511 may generate a deformed iris feature amount by inverting an iris circle corresponding to the iris feature amount. The deformation unit 511 may generate a deformed iris feature amount by inverting an iris circle corresponding to the iris feature amount in an arbitrary direction.

[0070] Furthermore, the deformation unit 511 may divide the iris circle corresponding to the iris feature amount into partial regions by at least one of the radii of two or more iris circles and a circle sharing a center with the iris circle, and change the position of the partial regions to generate a deformed iris feature amount. In other words, the deformation unit 511 may generate a deformed iris feature amount by combining partial feature amounts.

[0071] The matching score calculation unit 514 calculates a matching score based on the iris feature amount and the deformed iris feature amount (step S42). The estimation unit 512 estimates the possibility of false acceptance based on the matching score (step S43). If the matching score is a numerical value indicating a low possibility that the iris feature amount belongs to the same person, the estimation unit 512 can estimate that the possibility of false acceptance is low. On the other hand, if the matching score is a numerical value indicating a high possibility that the iris feature amount belongs to the same person, the estimation unit 512 can estimate that the possibility of false acceptance is high. In other words, the estimation unit 512 determines whether the matching score is a numerical value indicating a low possibility that the iris feature amount belongs to the same person or a numerical value indicating a high possibility that the matching score is a numerical value calculated based on the iris feature amount belongs to the same person.

[0072] If the possibility of false acceptance is low (step S43: Yes) and an iris image for registration has been acquired in step S20, the registration unit 516 registers the acquired iris image in the registered biometric information database 521 (step S25-1). The registration unit 516 may also register iris feature amounts extracted from the acquired iris image in the registered biometric information database 521.

[0073] If the possibility of false acceptance is low (step S43: Yes) and an iris image for biometric authentication has been acquired in step S20, the authentication unit 517 performs biometric authentication using the acquired iris image and an iris image registered in the registered biometric information database 521 (step S25-2). If iris feature amounts extracted from the iris image are registered in the registered biometric information database 521, the authentication unit 517 may perform biometric authentication using the iris feature amounts extracted from the acquired iris image and the iris feature amounts registered in the registered biometric information database 521. [5-2: Technical Effects of Information Processing Device 5]

[0074] The information processing device 5 in the fifth embodiment can register an iris image and estimate the possibility of false acceptance when performing iris authentication. The information processing device 5 can ensure the quality of iris information used for iris authentication. Furthermore, the information processing device 5 can modify iris information without losing the original information. [6: Sixth Embodiment]

[0075] Next, a sixth embodiment of an information processing device, an information processing method, and a recording medium will be described. Hereinafter, the sixth embodiment of the information processing device, the information processing method, and the recording medium will be described using an information processing device 6 to which the sixth embodiment of the information processing device, the information processing method, and the recording medium is applied. [6-1: Configuration of Information Processing Device 6]

[0076] As shown in FIG. 9 , the information processing device 6 of the sixth embodiment includes a calculation device 21 and a storage device 22, similar to the information processing device 2 of the second embodiment to the information processing device 5 of the fifth embodiment. Furthermore, the information processing device 6 of the sixth embodiment may include a communication device 23, an input device 24, and an output device 25, similar to the information processing device 2 of the second embodiment to the information processing device 5 of the fifth embodiment. However, the information processing device 6 does not have to include at least one of the communication device 23, the input device 24, and the output device 25. The information processing device 6 of the sixth embodiment differs from the information processing device 2 of the second embodiment to the information processing device 5 of the fifth embodiment in that a matching score distribution generation unit 618 is further implemented in the calculation device 21 and a matching score distribution storage unit 622 is further implemented in the storage device 22. Other features of the information processing device 6 may be the same as at least one other feature of the information processing device 2 of the second embodiment to the information processing device 5 of the fifth embodiment. Therefore, in the following, only the differences from the embodiments already described will be described in detail, and the description of other overlapping parts will be omitted as appropriate. [6-2: Information Processing Operation Performed by Information Processing Device 6]

[0077] Registered biometric information is registered in the registered biometric information database 621. As shown in Fig. 10, the matching score distribution generation unit 618 selects any two pieces of registered biometric information registered in the registered biometric information database 621 (step S60).

[0078] The matching score distribution generation unit 618 acquires a matching score calculated based on any two pieces of registered biometric information (step S61). The matching score distribution generation unit 618 may acquire a matching score calculated by the matching score calculation unit 614 based on any two pieces of registered biometric information. When the registered biometric information registered in the registered biometric information database 621 is an image of a living body, the feature extraction unit 613 extracts features, and the matching score calculation unit 614 calculates a matching score based on the features extracted by the feature extraction unit 613.

[0079] The matching score distribution generation unit 618 determines whether a predetermined number of matching scores have been calculated (step S62). The predetermined number is a number sufficient to generate a matching score distribution. Alternatively, in step S62, it may determine whether matching scores have been calculated for all combinations of registered biometric information.

[0080] When multiple pieces of registered biometric information are registered for one person, the selection operation in step S60 may include a selection operation between other people's registered biometric information and a selection operation between the person's registered biometric information.

[0081] When the operation of calculating the matching scores is completed (step S62: Yes), the matching score distribution generation unit 618 generates a matching score distribution indicating the distribution of each of the calculated matching scores (step S63). That is, the matching score distribution generation unit 618 generates a matching score distribution indicating the distribution of each of the multiple matching scores calculated based on any two of the registered biometric information registered in the registered biometric information database 621. The matching score distribution generation unit 618 stores the generated matching score distribution in the matching score distribution storage unit 622 (step S64).

[0082] 11 illustrates an example of a matching score distribution generated by the matching score distribution generation unit 618. The horizontal axis illustrates the magnitude of the matching score, and the vertical axis illustrates the frequency of occurrence of the magnitude of the matching score. The solid line FS may be an example of a distribution of matching scores based on each piece of registered biometric information between different people, and the dotted line TS may be an example of a distribution of matching scores based on each piece of registered biometric information between the same person. In other words, this illustrates that the matching score based on each piece of registered biometric information between different people is smaller than the matching score based on each piece of registered biometric information between the same person.

[0083] Furthermore, when it is possible to calculate matching scores based on each piece of registered biometric information of the same person, even if no distinction is made between matching scores based on each piece of registered biometric information of different people and matching scores based on each piece of registered biometric information of the same person, it is possible to predict that two peaks will appear in the distribution. Therefore, it can be determined that the peak of a relatively small matching score is the peak of the distribution of matching scores based on each piece of registered biometric information n of different people, and the peak of a relatively large matching score is the peak of the distribution of matching scores based on each piece of registered biometric information of the same person.

[0084] For example, if the matching score calculated from the biometric information acquired by the biometric information acquisition unit 615 is smaller than the peak of the other person's matching score distribution, as illustrated by the dashed-dotted line QH, it can be assumed that the biometric information acquired by the biometric information acquisition unit 615 is of a quality that can be used for biometric authentication. The biometric information from which the matching score illustrated by the dashed-dotted line QH is calculated can be understood as biometric information that makes it easy to distinguish between the person himself / herself and other people. Alternatively, if the matching score calculated from the biometric information acquired by the biometric information acquisition unit 615 is of a magnitude that is included in the person's matching score distribution, as illustrated by the dashed-two-dot line QL, it can be assumed that the biometric information acquired by the biometric information acquisition unit 615 is of a quality that cannot be used for biometric authentication.

[0085] When there are two peaks in the distribution, it can be understood that the distribution is a distribution of matching scores based on each of the registered biometric information of different people and matching scores based on each of the registered biometric information of the same person. Furthermore, when the matching scores are distributed in an area smaller than a predetermined area, it can be understood that the matching scores are based on each of the registered biometric information of different people. Furthermore, when the matching scores are distributed in an area larger than a predetermined area, it can be understood that the matching scores are based on each of the registered biometric information of the same person. The matching score distribution generation unit 618 may generate at least one of a different person matching score distribution and an actual person matching score distribution. For example, when a matching score distribution based on each of the registered biometric information of different people cannot be obtained and only an actual person matching score distribution based on each of the registered biometric information of the same person can be obtained, the determination criterion may be whether or not the matching score calculated from the biometric information acquired by the biometric information acquisition unit 615 is smaller than the range of the actual person matching score distribution. [6-3: Technical Effects of the Information Processing Device 6]

[0086] When the corresponding authentication device is used, the information processing device 6 can know a numerical value that is likely to be obtained as a matching score when calculating a matching score from each piece of registered biometric information of different people. Also, when calculating a matching score from each piece of registered biometric information of the same person, the information processing device 6 can know a numerical value that is likely to be obtained as a matching score. [7: Seventh Embodiment]

[0087] Next, a seventh embodiment of an information processing device, an information processing method, and a recording medium will be described. Hereinafter, the seventh embodiment of the information processing device, the information processing method, and the recording medium will be described using an information processing device 7 to which the seventh embodiment of the information processing device, the information processing method, and the recording medium is applied. [7-1: Configuration of Information Processing Device 7]

[0088] As shown in FIG. 12 , the information processing device 7 of the seventh embodiment includes a calculation device 21 and a storage device 22, similar to the information processing device 6 of the sixth embodiment. Furthermore, the information processing device 7 of the seventh embodiment may include a communication device 23, an input device 24, and an output device 25, similar to the information processing device 6 of the sixth embodiment. However, the information processing device 7 does not necessarily include at least one of the communication device 23, the input device 24, and the output device 25. The information processing device 7 of the seventh embodiment differs from the information processing device 6 of the sixth embodiment in that an authentication score storage unit 723 is further implemented in the storage device 22 and in the operation of the matching score distribution generation unit 718. Other features of the information processing device 7 may be the same as at least one other feature of the information processing device 6 of the sixth embodiment. Therefore, the following will describe in detail the differences from the previously described embodiments, and will omit appropriate descriptions of other overlapping features. [7-2: Information Processing Operation Performed by Information Processing Device 7]

[0089] The authentication score storage unit 723 stores the authentication score calculated when biometric authentication is performed on the acquired biometric information. In other words, the authentication score storage unit 723 stores the authentication score calculated by the matching score calculation unit 714 in a biometric authentication operation previously performed on the information processing device 7. The authentication score storage unit 723 may store the authentication score calculated when biometric authentication is performed on registered biometric information registered in the registered biometric information database 721 and biometric information acquired for biometric authentication. The authentication score storage unit 723 may store the authentication score calculated by the matching score calculation unit 714 regardless of whether the biometric authentication is successful or not. For example, if the authentication score of only one specific person registered in the registration database exceeds the authentication score threshold, the authentication score with the feature amount exceeding the threshold can be considered the true person score, and the authentication score with the feature amount other than the above feature amount registered in the registration database can be considered the other person score. If it is possible to determine whether a person is the true person or a other person using a method other than the biometric authentication, such as an ID card, the true person score and the other person score can be determined and stored using the determination result.

[0090] The matching score distribution generation unit 718 generates a matching score distribution that indicates the distribution of each authentication score stored in the authentication score storage unit 723. The distribution of authentication scores when biometric authentication is successful can be considered to correspond to the distribution of matching scores based on each piece of registered biometric information of the same person. The distribution of authentication scores when biometric authentication is unsuccessful can be considered to correspond to the distribution of matching scores based on each piece of registered biometric information of different people. The matching score distribution generation unit 718 stores the generated matching score distribution in the matching score distribution storage unit 722.

[0091] Furthermore, the matching score distribution generation unit 718 may generate a matching score distribution indicating the distribution of each of the authentication scores stored in the authentication score storage unit 723 and the matching scores calculated by the matching score calculation unit 614 in the sixth embodiment based on any two pieces of registered biometric information. The matching score distribution is a distribution determined for each authentication device, and may be generated from samples of matching scores calculated by the same authentication device. [7-3: Technical Effects of the Information Processing Device 7]

[0092] The information processing device 7 can generate a matching score distribution by using a history of results of past biometric authentication operations that have actually been performed. [8: Eighth Embodiment]

[0093] Next, an eighth embodiment of an information processing device, an information processing method, and a recording medium will be described. Hereinafter, the eighth embodiment of the information processing device, the information processing method, and the recording medium will be described using an information processing device 8 to which the eighth embodiment of the information processing device, the information processing method, and the recording medium is applied.

[0094] 13 is a block diagram showing the configuration of an information processing device 8 according to the eighth embodiment. The information processing device 8 according to the eighth embodiment differs from the information processing device 2 according to the second embodiment to the information processing device 7 according to the seventh embodiment in the operation of an estimation unit 812.

[0095] The matching score distribution storage unit 822 stores at least one of the matching score distribution generated by the matching score distribution generation unit 618 in the sixth embodiment and the matching score distribution generated by the matching score distribution generation unit 718 in the seventh embodiment.

[0096] The estimation unit 812 estimates the possibility of false acceptance based on the matching score calculated by the matching score calculation unit 814 and the matching score distribution stored in the matching score distribution storage unit 822. The estimation unit 812 may compare the matching score calculated by the matching score calculation unit 814 with a matching score threshold determined from the matching score distribution stored in the matching score distribution storage unit 822 to determine whether to register the biometric information acquired by the biometric information acquisition unit 815 or whether to use it for biometric authentication. The estimation unit 812 may determine that the biometric information acquired by the biometric information acquisition unit 815 has a quality that allows registration or a quality that can be used for biometric authentication when the matching score is smaller than the matching score threshold determined from the matching score distribution. In this case, the estimation unit 812 may make a determination using different thresholds depending on whether the use of the biometric information acquired by the biometric information acquisition unit 815 is registration or biometric authentication. [8-2: Technical Effects of Information Processing Device 8]

[0097] The information processing device 8 in the eighth embodiment can suppress false acceptance, in which a false person is mistakenly accepted due to the quality of the biometric information, by using a matching score based on the acquired biometric information and the modified biometric information, and a matching score distribution generated in advance. [9: Supplementary Note]

[0098] The following supplementary notes are further disclosed with respect to the above-described embodiments. [Supplementary Note 1] An information processing device comprising: a transformation means for transforming biometric information to generate transformed biometric information; and an estimation means for estimating, based on the biometric information and the transformed biometric information, a possibility of false acceptance, resulting in erroneous acceptance of a false person when the biometric information is used for biometric authentication. [Supplementary Note 2] The information processing device according to Supplementary Note 1, wherein the biometric information includes an image of a biometric, and the estimation means estimates the possibility of false acceptance based on a matching score calculated based on features extracted from the image of a biometric and transformation features extracted from a transformed biometric image obtained by transforming the image of the biometric. [Supplementary Note 3] The information processing device according to Supplementary Note 1 or 2, wherein the biometric information includes an iris image, and the estimation means estimates the possibility of false acceptance based on a matching score calculated based on iris features extracted from the iris image and transformation features extracted from a transformed iris image obtained by transforming the iris image. [Supplementary Note 4] The information processing device according to Supplementary Note 1, wherein the biometric information includes features extracted from an image of the biometric, the transformation means transforms the features to generate transformed features, and the estimation means estimates the possibility of false acceptance based on the features and a matching score calculated based on the transformed features. [Supplementary Note 5] The information processing device according to Supplementary Note 1 or 4, wherein the biometric information includes iris features extracted from an iris image, the transformation means transforms the iris features to generate transformed iris features, and the estimation means estimates the possibility of false acceptance based on an authentication score calculated based on the iris features and the transformed iris features. [Supplementary Note 6] The information processing device according to Supplementary Note 3 or 5, wherein the biometric information includes iris information of an iris region, and the transformation means generates the transformed iris information by inverting the iris information, or by dividing the iris information into partial information by at least one of two or more radii of the iris regions and circles sharing a center with the iris regions, and changing the positions of the partial information.[Supplementary Note 7] The information processing device according to any one of Supplementary Notes 1 to 6, comprising a generating means for generating a matching score distribution indicating a distribution of each of a plurality of matching scores calculated based on any two pieces of registered biometric information registered in a registration database. [Supplementary Note 8] The information processing device according to any one of Supplementary Notes 1 to 7, comprising: an authentication score storage means for storing authentication scores calculated when biometric authentication is performed on acquired biometric information; and a generating means for generating a matching score distribution indicating a distribution of each of the authentication scores stored in the authentication score storage means. [Supplementary Note 9] The information processing device according to Supplementary Note 7 or 8, wherein the estimating means estimates the possibility of false acceptance based on the calculated matching score and the matching score distribution generated by the generating means. [Supplementary Note 10] An information processing method, comprising: transforming biometric information to generate transformed biometric information; and estimating a possibility of false acceptance, which is to erroneously accept a false person when the biometric information is used for biometric authentication, based on the biometric information and the transformed biometric information. [Supplementary Note 11] A recording medium having recorded thereon a computer program for causing a computer to execute an information processing method, which comprises: transforming biometric information to generate transformed biometric information; and estimating, based on the biometric information and the transformed biometric information, the possibility of false acceptance, which occurs when the biometric information is used for biometric authentication.

[0099] This disclosure may be modified as appropriate within the scope of the claims and the technical idea that can be read from the entire specification. Information processing devices, information processing methods, and recording media that involve such modifications are also included in the technical idea of ​​this disclosure.

[0100] 1, 2, 3, 4, 5, 6, 7, 8 Information processing device 11, 211, 311, 411, 511 Deformation unit 12, 212, 312, 412, 512, 812 Estimation unit 213, 313, 413, 513, 613 Feature extraction unit 214, 314, 414, 514, 614, 714, 814 Matching score calculation unit 215, 315, 415, 515, 615, 815 Biometric information acquisition unit 216, 316, 416, 516 Registration unit 217, 317, 417, 517 Authentication unit 221, 321, 421, 521, 621, 721, 821 Registered biometric information database 618, 718 Matching score distribution generation unit 622, 722, 822 Matching score distribution storage unit 723 Authentication score storage unit

Claims

1. a transformation means for transforming the biometric information to generate transformed biometric information; an estimation means for estimating a possibility of false acceptance, that is, false acceptance, in which a false person is mistakenly accepted when the biometric information is used for biometric authentication, based on the biometric information and the modified biometric information; An information processing device comprising:

2. the biometric information includes an image of the biometric body; The estimation means estimates the possibility of false acceptance based on a matching score calculated based on a feature extracted from the biometric image and a transformation feature extracted from a transformed biometric image obtained by transforming the biometric image. The information processing device according to claim 1 .

3. the biometric information includes an iris image; The estimation means estimates the possibility of false acceptance based on a matching score calculated based on an iris feature amount extracted from the iris image and a deformed iris feature amount extracted from a deformed iris image obtained by deforming the iris image.

3. The information processing device according to claim 1.

4. the biometric information includes features extracted from an image of the biometric subject; the transformation means transforms the feature quantity to generate a transformed feature quantity; The estimation means estimates the possibility of the false acceptance based on the feature amount and the matching score calculated based on the deformation feature amount. The information processing device according to claim 1 .

5. the biometric information includes iris features extracted from an iris image, the deformation means deforms the iris feature amount to generate a deformed iris feature amount, The estimation means estimates the possibility of false acceptance based on an authentication score calculated based on the iris feature amount and the deformed iris feature amount.

5. The information processing device according to claim 1.

6. the biometric information includes iris information of an iris region; The deformation means is by inversion of the iris information, or The iris information is divided into partial information by at least one of the radii of two or more of the iris regions and a circle having a center that is the same as the iris region, and the position of the partial information is changed, Generate deformed iris information 6. The information processing device according to claim 3 or 5.

7. A generating means is provided for generating a matching score distribution that indicates the distribution of each of a plurality of matching scores calculated based on any two pieces of registered biometric information registered in the registration database. The information processing device according to claim 2 .

8. an authentication score storage means for storing an authentication score calculated when the acquired biometric information is biometrically authenticated; a generating means for generating a matching score distribution indicating the distribution of each of the authentication scores stored in the authentication score storage means; The information processing device according to claim 2 .

9. Transforming the biometric information to generate transformed biometric information; Based on the biometric information and the modified biometric information, a possibility of false acceptance, that is, false acceptance, in which the biometric information is used for biometric authentication, is estimated. A computer-implemented information processing method.

10. On the computer, Transforming the biometric information to generate transformed biometric information; Based on the biometric information and the modified biometric information, a possibility of false acceptance, that is, false acceptance, in which the biometric information is used for biometric authentication, is estimated. A computer program for executing an information processing method.