JP5895751B2 - Biometric authentication device, retry control program, and retry control method - Google Patents

Description

  The present invention relates to a biometric authentication device, a retry control program, and a retry control method.

  Biometric authentication using various types of biological information such as fingerprints, palm prints, vein patterns, irises, facial images, and voices is known. In such biometric authentication, personal authentication is performed by comparing biometric information input by a user with biometric information registered in advance.

  However, the biometric information collected at the time of registration and authentication varies in quality depending on the input method to the input device to which the biometric information is input, and the use environment such as dirt attached to the biometric device or the input device. Occurs. For this reason, even if it is the biometric information of the same person, the biometric information collected at the time of authentication is not necessarily authenticated as the same biometric information as the biometric information collected at the time of registration. As a result, the biometric information of the person may be authenticated with the biometric information of the other person, or the biometric information of the other person may be authenticated with the biometric information of the person.

  As an example of a technology that adjusts the balance between the rejection rate and the acceptance rate of others, the threshold value to be compared with the similarity of biometric information collected at the time of registration and at the time of verification of biometric information is dynamically adjusted according to the operational status. The method of doing is mentioned.

JP 2008-097248 A JP 2000-163574 A

  However, the above-described conventional technique has a problem in that the authentication retry cannot be appropriately executed as described below.

  That is, the principal rejection rate and the stranger acceptance rate are in a trade-off relationship. For this reason, even if the threshold value compared with the similarity degree of biometric information is adjusted like the above-mentioned prior art, either the person rejection rate or the other person acceptance rate is increased. For example, when the threshold is lowered, the false rejection rate can be lowered while the false acceptance rate is increased. Further, when the threshold value is increased, the false acceptance rate can be lowered while the false acceptance rate can be lowered. In both the former and latter cases, authentication is retried when authentication fails. At this time, if the number of retries is granted without limitation, not only the person himself but also a malicious person, for example, a third party who intends to accept others by brute force attack of different biological information will be admitted. However, when the number of authentication retries is limited, the authentication opportunity of the rejected person is deprived due to the difference in input method and usage environment.

  The disclosed technology has been made in view of the above, and an object thereof is to provide a biometric authentication device, a retry control program, and a retry control method that can appropriately execute an authentication retry.

  The biometric authentication device disclosed in the present application includes a storage unit that stores biometric feature information that has failed in biometric authentication among biometric feature information extracted from biometric information during biometric authentication. Furthermore, the biometric authentication device includes a calculation unit that calculates the similarity between the biometric feature information for each combination of biometric feature information stored in the storage unit. Furthermore, the biometric authentication device includes a grouping unit that groups biometric feature information stored in the storage unit using the similarity between the biometric feature information calculated by the calculation unit. Furthermore, the biometric authentication apparatus includes a determination unit that determines whether the number of groups in which the biometric feature information is grouped by the grouping unit is equal to or less than a predetermined threshold. Further, the biometric authentication device allows the biometric authentication to be retried when the determination unit determines that the number of groups is equal to or less than the threshold, and determines that the number of groups exceeds the threshold. It has a retry control unit that limits the retry of biometric authentication.

  According to one aspect of the biometric authentication device disclosed in the present application, there is an effect that an authentication retry can be appropriately executed.

FIG. 1 is a block diagram illustrating a functional configuration of the biometric authentication apparatus according to the first embodiment. FIG. 2 is a diagram illustrating an example of authentication NG information. FIG. 3 is a flowchart illustrating a procedure of biometric authentication processing according to the first embodiment. FIG. 4 is a flowchart of the retry control process according to the first embodiment. FIG. 5 is a block diagram illustrating a functional configuration of the biometric authentication apparatus according to the second embodiment. FIG. 6 is a diagram illustrating an example of a grouping result. FIG. 7 is a diagram illustrating an example of a grouping result. FIG. 8 is a diagram illustrating an example of a grouping result. FIG. 9 is a diagram illustrating an example of a grouping result. FIG. 10 is a diagram illustrating an example of a calculation result of similarity between biometric feature information. FIG. 11 is a flowchart illustrating the procedure of the grouping process according to the second embodiment. FIG. 12 is a flowchart illustrating a procedure of ID determination processing according to the application example. FIG. 13 is a schematic diagram illustrating an example of a computer that executes a retry control program according to the first to third embodiments.

  Embodiments of a biometric authentication device, a retry control program, and a retry control method disclosed in the present application will be described below in detail with reference to the drawings. Note that this embodiment does not limit the disclosed technology. Each embodiment can be appropriately combined within a range in which processing contents are not contradictory.

[Configuration of biometric authentication device]
FIG. 1 is a block diagram illustrating a functional configuration of the biometric authentication apparatus according to the first embodiment. A biometric authentication device 10 shown in FIG. 1 executes biometric authentication processing for performing personal authentication by comparing biometric information input by a user with biometric information registered in advance. In particular, the biometric authentication device 10 has one advantage in the retry control of authentication, groups biometric feature information that has failed in biometric authentication according to the similarity between the biometric feature information, and the number of groups is equal to or less than a predetermined threshold. Whether to retry the authentication is controlled depending on whether or not there is.

  As one aspect of the biometric authentication device 10, it can be implemented by installing or preinstalling a biometric authentication program for executing the above biometric authentication processing in an information processing apparatus such as a personal computer. In the present embodiment, the following description will be given on the assumption that fingerprint authentication is employed as login authentication to an information processing apparatus shared by a plurality of users.

  As illustrated in FIG. 1, the biometric authentication device 10 includes an ID (identification) receiving unit 11, a biometric sensor 12, a storage unit 13, and a control unit 15. The biometric authentication apparatus 10 includes various functional units included in known computers other than the functional units illustrated in FIG. 1, such as various input devices, audio output devices, and communication interfaces for communicating with external devices. It does not matter as having the functional part.

  Among these, the ID receiving unit 11 is a processing unit that receives a user ID assigned to a user who has an account of the information processing apparatus. As an aspect of the ID receiving unit 11, a user interface such as a keyboard equipped with a numeric keypad and alphabet keys can be employed. As another aspect, a reading device that reads information from a magnetic card in which a user ID is recorded or a contact type or non-contact type IC card may be employed. The user ID received by the ID receiving unit 11 is output to the verification unit 15b described later.

  The biological sensor 12 is a sensor that reads biological information. In the following, it is assumed that fingerprint authentication is performed as an example of biometric authentication. As an implementation example of such a biosensor 12, an embodiment in which the biosensor 12 is incorporated in the information processing apparatus can be adopted, and an aspect in which the biosensor 12 is externally connected to the information processing apparatus, for example, a USB (Universal Serial Bus) or the like Can be adopted. Further, as an example of the detection method of the biosensor 12, any detection method such as a capacitance method, an electric field detection method, an optical method, a heat sensitive method, and a pressure sensitive method can be adopted. Furthermore, as an example of a reading method of the biosensor 12, a finger type, that is, a slide type that slides the center part inside the fingertip, or a stamp type that places a finger bar may be used. Absent. Note that the biological image read by the biological sensor 12 is output to the later-described extraction unit 15a as input biological information.

  The storage unit 13 is a storage device that stores various programs such as an OS (Operating System) executed by the control unit 15 and a biometric authentication program. As one aspect of the storage unit 13, a storage device such as a semiconductor memory element such as a flash memory, a hard disk, or an optical disk is given. The storage unit 13 is not limited to the type of storage device described above, and may be a RAM (Random Access Memory) or a ROM (Read Only Memory).

  The storage unit 13 stores reference biometric information 13a and authentication NG information 13b as an example of data used in a program executed by the control unit 15. In addition to the reference biometric information 13a and the authentication NG information 13b, the storage unit 13 can also store data such as various threshold values used by the grouping unit 15e and the determination unit 15f described later.

  The reference biometric information 13a is biometric information for reference that is referred to when collating with input biometric information read by the biometric sensor 12. As one aspect of the reference biometric information 13a, data in which biometric feature information obtained by extracting a feature amount from the user ID and the biometric information is associated can be employed. Here, one user ID corresponds to a plurality of pieces of biometric feature information extracted from the biometric information of a plurality of fingers held by the same user, for example, a plurality of sets of pieces of biometric feature information such as an index finger and a middle finger or an index finger and a ring finger. You can register with it. In the present embodiment, the following description will be made assuming that a maximum of two pieces of biometric feature information are registered in association with one user ID as the reference biometric information 13a. It is also possible to register in association with each other. Here, the case where biometric feature information is registered as reference biometric information 13a will be described, but biometric information itself may be registered.

  The authentication NG information 13b is various information related to the input biometric information for which biometric authentication has failed. As an aspect of the authentication NG information 13b, data in which a user ID and biometric feature information are associated can be employed. Here, only one piece of biometric feature information is verified in one biometric authentication. Therefore, unlike the reference biometric information 13a, the authentication NG information 13b is registered with user IDs and biometric feature information in a one-to-one correspondence. FIG. 2 is a diagram illustrating an example of the authentication NG information 13b. In the example of FIG. 2, the biometric information is input together with ID = 0001 when the user is authenticated for the first time and the second time, and the biometric information is input together with ID = 0011 when the user is authenticated for the third time to the fifth time. It indicates that ID = 0001 and biometric information are input at the time of the second authentication. The authentication NG information of each record is a user ID and biometric feature information that have failed in biometric authentication.

  The control unit 15 has an internal memory for storing programs defining various processing procedures and control data, and executes various processes using these. As shown in FIG. 1, the control unit 15 includes an extraction unit 15a, a verification unit 15b, an authentication unit 15c, a calculation unit 15d, a grouping unit 15e, a determination unit 15f, and a retry control unit 15g.

  The extraction unit 15 a is a processing unit that extracts biometric feature information from input biometric information read by the biosensor 12. As one aspect, the extraction unit 15a performs the following process when a retry limit is not instructed by the retry control unit 15g described later. That is, the extraction unit 15a extracts biometric feature information from the biometric information read by the biosensor 12 in accordance with an arbitrary collation method such as a minutia method, a pattern matching method, or a frequency analysis method adopted by the collation unit 15b. . For example, when the minutia method is adopted by the collation unit 15b described later, the extraction unit 15a, the direction of the feature points such as the end points and branch points of the ridges included in the fingerprint image pattern, the positional relationship and the feature points The correlation between each other is extracted as biometric feature information. Further, when the pattern matching method is adopted by the collation unit 15b described later, the extraction unit 15a extracts an image in which the fingerprint image is binarized or thinned as biometric feature information. In addition, when the frequency analysis method is adopted by the collation unit 15b described later, the extraction unit 15a extracts a waveform spectrum series when a cross section obtained by slicing the pattern pattern of the fingerprint image is regarded as a waveform as biometric feature information. .

  The collation unit 15b is a processing unit that collates the biometric feature information associated with the user ID received by the ID receiving unit 11 in the reference biometric information 13a with the biometric feature information extracted by the extraction unit 15a. As one aspect, the collation unit 15b reads biometric feature information having the same user ID as the user ID accepted by the ID accepting unit 11 from the reference biometric information 13a stored in the storage unit 13. At this time, the collation part 15b reads all the biometric feature information matched with user ID, when the some biometric feature information is matched with one user ID. Then, the collation unit 15b calculates the similarity between the biometric feature information read from the storage unit 13 and the biometric feature information extracted by the extraction unit 15a. In addition, when a plurality of pieces of biometric feature information are read, the matching unit 15b performs matching with the biometric feature information extracted by the extraction unit 15a for each piece of biometric feature information read from the storage unit 13. To do. In addition, the collation part 15b can employ | adopt arbitrary collation systems, such as a minutia system, a pattern matching system, and a frequency analysis method.

  The authentication unit 15c is a processing unit that authenticates whether or not the input biometric information is that of the person himself / herself based on the collation result by the collation unit 15b. As one aspect, the authentication unit 15c determines whether or not the maximum similarity among the similarities between the biometric feature information calculated by the matching unit 15b is equal to or greater than a predetermined threshold. At this time, the authentication unit 15c determines that the biometric authentication is successful when the maximum similarity is equal to or greater than the threshold. As a result, login to the information processing apparatus is permitted by the OS executed by the control unit 15. In this case, even if the biometric authentication has failed so far, a user who inputs biometric information will try biometric authentication for the first time. Therefore, the authentication unit 15c deletes the authentication NG information 13b stored in the storage unit 13. On the other hand, if the maximum similarity is less than the threshold, the authentication unit 15c determines that biometric authentication has failed. Then, the authentication unit 15 c additionally registers in the storage unit 13 authentication NG information that associates the user ID received by the ID reception unit 11 with the biometric feature information extracted by the extraction unit 15 a. In this case, login to the information processing apparatus is not permitted by the OS executed by the control unit 15. In this example, the case where the authentication NG information 13b is deleted when the biometric authentication is successful is illustrated, but the authentication NG information 13b is deleted when a predetermined period, for example, 5 minutes elapses since the last biometric authentication was executed. It doesn't matter as you do.

  The calculation unit 15d is a processing unit that calculates the similarity between biometric information for each combination of biometric information included in the authentication NG information 13b. As an aspect, the calculation unit 15d activates the process when a record of the authentication NG information 13b is additionally registered in the storage unit 13. First, the calculation unit 15d determines whether or not the number of retries for which authentication retries have been executed by the authentication unit 15c is greater than or equal to a predetermined threshold value. As such a threshold value, a value obtained by adding a predetermined margin, for example, “0” or “1” to the number of parts where biometric feature information can be registered for one user can be set. This threshold setting is adopted when the biometric feature information of different parts is registered for the same type of biometric information, the number of groups of biometric feature information is even between the biometric feature information of the same person. This is because the number of parts that can be registered converges. For example, if a maximum of two pieces of biometric feature information are registered in association with one user ID, the user himself / herself who has an account must enter and use the authentication method unless the second or third authentication retries are allowed. This is because the probability of being rejected due to environmental differences increases. For this reason, when the number of retries is less than the threshold value, an authentication retry is permitted by a retry control unit 15g described later.

  On the other hand, the calculation unit 15d calculates the similarity between the biometric feature information when the number of retries is equal to or greater than a predetermined threshold. That is, the calculation unit 15d differs from the input biometric feature information that has failed in biometric authentication in the past, unlike the above-described matching unit 15b that calculates the similarity between the input biometric feature information and the reference biometric feature information. Calculate similarity. Such similarity can be calculated by the same verification method as that of the verification unit 15b, or can be calculated by a different verification method when biometric information is registered as the authentication NG information 13b.

  The grouping unit 15e is a processing unit that groups the biometric feature information stored as the authentication NG information 13b in the storage unit 13 using the similarity between the biometric feature information calculated by the calculation unit 15d. As one aspect, the grouping unit 15e classifies the biometric feature information whose similarity is greater than or equal to a predetermined threshold into the same group. At this time, the grouping unit 15e can classify all biometric feature information combinations into the same group only when the similarity is equal to or greater than a threshold value. In addition, the grouping unit 15e sets a combination of biometric feature information whose similarity is equal to or greater than the threshold value to the common biometric feature information even if the similarity of some biometric feature information combinations is less than the threshold value. Can also be classified.

  The determination unit 15f is a processing unit that determines whether the number of groups in which the biometric feature information is grouped by the grouping unit 15e is equal to or less than a predetermined threshold. As one aspect, the determination unit 15f is a threshold value to be compared with the number of groups, for example, a value obtained by adding a predetermined margin, for example, “0” or “1” to the number of parts where biometric feature information can be registered for one user. The number of groups can be determined with the fixed. As another aspect, the determination unit 15f can determine the number of groups by dynamically changing a threshold value to be compared with the number of groups. That is, when biometric information of the same person is continuously input, it can be estimated that the number of groups of biometric feature information converges to the number of parts that can be registered as the number of retries increases. Therefore, in the initial stage, a threshold value larger than the number of registerable parts is adopted, and the threshold value is updated so that the number of parts that can be registered converges as the number of retries increases. Can also be done.

  The retry control unit 15g is a processing unit that controls an authentication retry. As one aspect, the retry control unit 15g permits an authentication retry when the number of retries is less than a threshold value. In addition, the retry control unit 15g permits the authentication retry even when the determination unit 15f determines that the number of groups is equal to or less than the threshold value. On the other hand, when the determination unit 15f determines that the number of groups has exceeded the threshold, the retry control unit 15g limits biometric authentication retries. As an example of such a retry restriction, even if a user ID or biometric information is input for a predetermined prohibition period, for example, 10 minutes until the next biometric authentication is permitted, extraction of biometric feature information and subsequent processing are stopped. Or the account of the user ID included in the authentication NG information 13b can be disabled for a certain period.

[Process flow]
Subsequently, a flow of processing of the biometric authentication apparatus according to the present embodiment will be described. Here, after (1) biometric authentication processing executed by the biometric authentication device 10 is described, (2) retry control processing is described.

(1) Biometric Authentication Process FIG. 3 is a flowchart illustrating the procedure of the biometric authentication process according to the first embodiment. This biometric authentication process is a process that is repeatedly executed when the biometric authentication device 10 is powered on.

  As shown in FIG. 3, when a user ID and biometric information are received (step S101), the extraction unit 15a determines whether or not a retry limit is instructed by the retry control unit 15g (step S102). If the retry limit is instructed (Yes in step S102), the process is terminated as it is.

  On the other hand, when the retry limit is not instructed (No in step S102), the extraction unit 15a extracts biometric feature information from the biometric information read by the biosensor 12 (step S103).

  And the collation part 15b collates the biometric feature information matched with the user ID received by the ID reception part 11 among the reference biometric information 13a, and the biometric feature information extracted by the extraction part 15a, and both. Is calculated (step S104).

  Subsequently, the authentication unit 15c determines whether the maximum similarity among the similarities between the biometric feature information calculated by the matching unit 15b is equal to or greater than a predetermined threshold (step S105). At this time, if the maximum similarity is equal to or greater than the threshold (Yes in step S105), it is determined that the biometric authentication is successful. In this case, even if the biometric authentication has failed so far, a user who inputs biometric information will try biometric authentication for the first time. Therefore, the authentication unit 15c deletes the authentication NG information 13b stored in the storage unit 13 (step S106) and ends the process.

  On the other hand, when the maximum similarity is less than the threshold (No in step S105), it is determined that biometric authentication has failed. In this case, the authentication unit 15c additionally registers authentication NG information in which the user ID received by the ID reception unit 11 and the biometric feature information extracted by the extraction unit 15a are associated with each other in the storage unit 13 (Step S107). The process is terminated.

(2) Retry Control Process FIG. 4 is a flowchart illustrating the retry control process according to the first embodiment. This retry control process is started when a new record is added to the authentication NG information 13b.

  As illustrated in FIG. 4, the calculation unit 15d determines whether or not the number of retries for which authentication retries have been executed by the authentication unit 15c is equal to or greater than a predetermined number (step S301). At this time, if the number of retries is less than the predetermined number (No in step S301), the process proceeds to step S306, and the process is terminated after the retry of the authentication is permitted by the retry control unit 15g (step S306).

  On the other hand, when the number of retries is equal to or greater than the predetermined number (step S301 Yes), the calculation unit 15d reads the authentication NG information 13b stored in the storage unit 13 (step S302). Then, the calculation unit 15d calculates the similarity between the biometric feature information for each combination of the biometric feature information included in the authentication NG information 13b (step S303).

  Subsequently, the grouping unit 15e groups biometric feature information using the similarity between the biometric feature information calculated in step S303 (step S304). Thereafter, the determination unit 15f determines whether or not the number of groups grouped in step S304 is equal to or less than a predetermined threshold (step S305).

  Here, when the number of groups is equal to or less than the threshold value (Yes in step S305), the retry control unit 15g permits authentication retry (step S306), and ends the process. On the other hand, when the number of groups exceeds the threshold (No in step S305), the retry control unit 15g limits the biometric authentication retry (step S307) and ends the process.

[Effect of Example 1]
As described above, the biometric authentication device 10 according to the present embodiment groups biometric feature information that has failed biometric authentication according to the similarity between the biometric feature information, and whether the number of groups is equal to or less than a predetermined threshold value. Controls whether or not authentication retry is possible. For this reason, when the number of groups is small, it can be determined that the principal has been rejected due to differences in input method and usage environment. When the number of groups is large, it can be determined that a third party who wants to accept another person is rejected due to a brute force attack of different biological information. Therefore, in the biometric authentication device 10 according to the present embodiment, when it is presumed that the biometric information of the person is rejected, the retry of authentication is permitted, and it is presumed that the biometric information of another malicious person is rejected. In some cases, authentication retries can be restricted. Therefore, according to the biometric authentication apparatus 10 according to the present embodiment, it is possible to appropriately execute an authentication retry.

  In the first embodiment, the case where the grouping of the biometric feature information is executed using one threshold value is illustrated. However, the grouping of the biometric feature information is not necessarily performed using only one threshold value. Therefore, in this embodiment, a case will be described in which biometric feature information grouping is performed using a plurality of threshold values.

[Configuration of biometric authentication device]
FIG. 5 is a block diagram illustrating a functional configuration of the biometric authentication apparatus according to the second embodiment. As shown in FIG. 5, the biometric authentication device 20 is different from the biometric authentication device 10 shown in FIG. 1 in that the control unit 21 replaces the grouping unit 15 e with a grouping unit 22 that is partly different in processing content. In addition to the above, the threshold update unit 23 is further different. In the following, functional units that exhibit the same functions as those in the first embodiment are denoted by the same reference numerals, and description thereof is omitted.

  The grouping unit 22 is included in the authentication NG information 13b by using a first threshold value F that classifies a plurality of pieces of biometric feature information into the same group and a second threshold value f that classifies the pieces of biometric feature information into different groups. It is a processing unit for grouping biometric feature information.

  As one aspect, the grouping unit 22 activates the grouping process when the similarity between the biometric feature information is calculated for each combination of biometric feature information. That is, the grouping unit 22 includes biometric feature information of a combination in which similarity comparison is not yet performed between the first threshold value F and the second threshold value f among the biometric feature information included in the authentication NG information 13b. A predetermined number of biometric feature information is selected. Hereinafter, as an example, assuming that three pieces of biometric feature information are selected, the three pieces of biometric feature information may be labeled and described as A, B, and C. In addition, the grouping unit 22 uses the similarity of all combinations of the previously selected three pieces of biometric feature information A to C, the first threshold value F and the second threshold value held in the internal memory of the grouping unit 22 (not shown). It is determined whether or not the following classification conditions 1 to 3 are satisfied by comparing the threshold f. Note that, here, three pieces of biological feature information will be described, but four or more pieces of biological feature information can be selected.

  For example, as an example of the classification condition 1, there is a condition that all the similarities between the three biometric features A, B, and C are equal to or more than the first threshold value F. This is because the similarity between the biometric feature information A and the biometric feature information B, the similarity between the biometric feature information A and the biometric feature information C, and the similarity between the biometric feature information B and the biometric feature information C are both the first threshold F. This is equivalent to the above. Further, as an example of the classification condition 2, of the similarities between the three pieces of biometric feature information A, B, and C, two similarities are equal to or more than the first threshold F, and the remaining one similarity is the second The threshold f is less than the first threshold F. Further, as an example of the classification condition 3, one of the three biometric feature information of A, B, and C has a similarity equal to or higher than the first threshold F, and the remaining two similarities are the first. There is a condition that it is less than the threshold value F.

  When the classification condition 1 is satisfied, the grouping unit 22 groups all of the biometric feature information A, the biometric feature information B, and the biometric feature information C into the same group. Further, the grouping unit 22 groups all of the biometric feature information A, the biometric feature information B, and the biometric feature information C into the same group even when the classification condition 2 is satisfied without satisfying the classification condition 1. . In addition, the grouping unit 22 does not satisfy the above classification condition 1 and classification condition 2 but satisfies the above classification condition 3, the biometric feature information that constitutes a set that is equal to or greater than the first threshold F is included in the same group. And group the remaining biometric feature information into different groups. For example, the similarity between the biometric feature information A and the biometric feature information B is greater than or equal to the first threshold F, the similarity between the biometric feature information A and the biometric feature information C, and the similarity between the biometric feature information B and the biometric feature information C. Are both less than the first threshold F. In this case, since the classification condition 3 is satisfied, the biometric feature information A and the biometric feature information B are grouped into the same group, and the biometric feature information C is a group to which the biometric feature information A and the biometric feature information B belong. Group to a different group. The grouping unit 22 groups all of the three pieces of biometric feature information into different groups when none of the above classification conditions 1 to 3 is satisfied.

  Thereafter, the grouping unit 22 repeatedly executes the above grouping process until the comparison between the biometric feature information of all combinations and the first threshold value F and the second threshold value f is completed. Then, when the comparison between the biometric feature information of all combinations and the first threshold value F and the second threshold value f is finished, the grouping unit 22 counts the number of groups grouped by the above grouping process. To do.

  The threshold update unit 23 is a processing unit that updates the first threshold F and the second threshold f. It is assumed that the first threshold value F and the second threshold value f are held in the internal memory of the grouping unit 22. Hereinafter, as an example, “100” is held as the initial value of the first threshold value F and “0” is held as the initial value of the second threshold value f in the internal memory of the control unit 21. Note that the initial values of the first threshold value F and the second threshold value f are merely examples, and it is needless to say that any numerical value can be adopted as long as the first threshold value F is larger than the second threshold value f.

  As one aspect, the threshold update unit 23 updates the first threshold F when the above classification condition 2 is satisfied. For example, the threshold update unit 23 performs an update using the minimum similarity S_min among the similarities grouped in the same group according to the classification condition 2 as a new first threshold F. As a result, as a result of the first threshold F approaching the second threshold f, the gray zone having a numerical width that is greater than or equal to the second threshold f and less than the first threshold F is reduced. However, if 2 * S_min <F or S_min <f, the numerical widths of the first threshold value F and the second threshold value f may become excessively small, so the first threshold value F is updated. I won't let you.

  Moreover, the threshold value update part 23 performs the following processes, when none of said classification conditions 1-3 is satisfy | filled. That is, the threshold update unit 23 includes the biometric feature information that does not satisfy the classification conditions 1 to 3 in one side and the biometric feature information of the group grouped by the classification condition 1 or the classification condition 2 in the past in the other combination. A combination of biometric feature information whose similarity is less than the first threshold F is extracted. Then, the threshold update unit 23 performs an update using the maximum similarity s_max as the new second threshold f among the similarities between the biometric feature information of each combination extracted previously. As a result, as a result of the second threshold f approaching the first threshold F, the gray zone having a numerical width that is greater than or equal to the second threshold f and less than the first threshold F is reduced. However, if 2 * S_min> (F−f), the numerical value width of the first threshold value F and the second threshold value f may become excessively small, so the second threshold value f is updated. I won't let you.

  Note that the threshold update unit 23 initializes both the first threshold F and the second threshold f when the biometric authentication by the authentication unit 15c is successful.

[Specific examples of grouping]
A specific example of grouping will be described with reference to FIGS. 6 to 9 are diagrams illustrating examples of grouping results. FIG. 10 is a diagram illustrating an example of a calculation result of similarity between biometric feature information. These examples of FIGS. 6 to 9 show the grouping results when the biological information is rejected three times, four times, five times, and six times. 6 to 9 indicate the biometric feature information that has failed in authentication, and the subscript number of the English character I indicates how many times authentication has failed. In the examples of FIGS. 6 to 9, when the biometric feature information I is regarded as a node, links connecting the nodes represent the degree of similarity. When the link is a thick line, it indicates that the similarity is greater than or equal to the first threshold F, and when the link is a thin line, the similarity is greater than or equal to the second threshold f and less than the first threshold F. When there is no link, the similarity is less than the second threshold f. Moreover, the rectangle of the dotted line enclosure shown in FIGS. 6-9 shows the biometric feature information group grouped into the same group by grouping. FIG. 10 also shows the similarity for each combination of the biometric feature information I _{1 to} I ₆ . 6 to 10 also assumes a case where a maximum of two pieces of biometric feature information are registered in association with one user ID.

As shown in FIG. 6, when the number of authentication retries is ₃ , grouping of biometric feature information I _{1 to} I ₃ is started. At this stage, as shown in FIG. 10, the similarity "40" of the _{I 1} and _{I 2,} the similarity "0" of the _{I 1} and _{I 3,} the similarity of _{I 2} and _{I 3} "90" is calculated Yes. In this case, since the similarity of each combination of I _{1 to} I ₃ does not correspond to any of the above classification conditions 1 to 3, the biometric feature information I _{1 to} I ₃ are all in separate groups. being classified.

As shown in FIG. 7, when the number of authentication retries is ₄ , grouping of the biometric feature information I _{1 to} I ₄ is started. At this stage, as shown in FIG. 10, the similarity of the _{I 1} and _{I 4} "10", the similarity "120" of the _{I 2} and _{I 4,} it is further calculated similarity _{I 3} and _{I 4} "120" The In this case, the similarity of each combination of I _{1 to} I ₄ does not correspond to the above classification condition 1, but the similarity of each combination of I ₂ , I _3, and I ₄ corresponds to the above classification condition 2 Applicable. For this reason, I ₂ , I ₃ and I ₄ are grouped into the same group. On the other hand, since there is no other biometric feature information in I ₁ so as to satisfy the above classification conditions 1 to 3, it is grouped in a group different from the groups of I ₂ , I ₃ and I ₄ . At this time, the groups I ₂ , I _3, and I ₄ are groups grouped according to the classification condition 2 and the minimum similarity S_min is “90”, so the first threshold F is updated to “90”. Is done. Also, the similarity between I ₁ and I ₂ , I ₃ , and I ₄ is “40”, “0”, and “10”, respectively, and the maximum similarity s_max is “40”. Is updated to “40”.

As shown in FIG. 8, when the number of authentication retries reaches ₅ , grouping of the biometric feature information I _{1 to} I ₅ is started. At this stage, as shown in FIG. 10, the similarity of the _{I 1} and _{I 5} "80", the similarity of the _{I 2} and _{I 5} "0", the similarity "50" of the _{I 3} and _{I 5, I 4} and The degree of similarity “0” of I ₅ is further calculated. In this _case, since the similarity of each combination of I 2, _{I 3} and _{I 4} corresponds to the classification condition 1 _above, I 2, _{I 3} and _{I 4} are grouped into the same group. On the other hand, since I ₁ and I ₅ do not satisfy the above classification conditions 1 to 3 even if other biometric feature information is added, I ₁ and I ₅ are grouped as independent groups. At this time, among the similarities between I ₁ and I ₂ , I ₃ and I ₄ and the similarities between I ₅ and I ₂ , I ₃ and I ₄ , the similarity “50” between I ₃ and I ₅ is “50”. Since the minimum similarity S_min is obtained, which is larger than the second threshold f = 40, the second threshold f is updated to “50”.

As shown in FIG. 9, when the number of authentication retries is ₆ , grouping of the biometric feature information I _{1 to} I ₆ is started. At this stage, as shown in FIG. 10, the similarity "130" of the _{I 1} and _{I 6,} the similarity "30" of the _{I 2} and _{I 6,} the similarity "10" of the _{I 3} and _{I 6, I 4} and similarity I ₆ "40", the similarity of _{I 5} and _{I 6} are "150" is further calculated. In this case, as described with reference to FIG. 8, I ₂ , I _3, and I ₄ are grouped into the same group according to the classification condition 1. Furthermore, the similarity of each combination of I ₁ , I ₅ and I ₆ corresponds to the above classification condition 2. For this reason, I ₁ , I ₅ and I ₆ are grouped into the same group. At this time, the groups of I ₁ , I ₅ and I ₆ are groups grouped according to the classification condition 2 and the minimum similarity S_min is “80”, so the first threshold F is updated to “80”. Is done. Note that the grouping results of the six pieces of biometric feature information do not depend on the input order, and the same results can be obtained.

In this way, when the number of authentication retries is six, the biometric feature information I _{1 to} I ₆ is divided into the groups I ₂ , I ₃ and I _{4 and} the groups I ₁ , I ₅ and I ₆ . Can be grouped into two groups. In this example, since the number of groups of biometric feature information has converged to the number of registerable parts “2”, it can be determined that there is a high probability that the person is rejected due to a difference in input method and usage environment.

  Furthermore, the second threshold f increases as the number of retries increases, such as 100 for the number of authentication retries at 100, 50 at the 4th stage, 40 at the 5th stage, 30 at the 6th stage, and so on. As described above, the gray zone having a numerical width less than the first threshold value F can be reduced. For this reason, when there is a high possibility that the subject's biometric information is rejected due to differences in the input method and usage environment, the number of groups of biometric feature information is quickly set to the number of parts where biometric information for reference can be registered. It is possible to converge.

[Process flow]
FIG. 11 is a flowchart illustrating the procedure of the grouping process according to the second embodiment. This grouping process is a process corresponding to step S304 shown in FIG. 4, and is started when the calculation unit 15d calculates the similarity between the biometric feature information for each combination of biometric feature information.

  As shown in FIG. 11, the grouping unit 22 is a combination in which the similarity is not yet compared between the first threshold value F and the second threshold value f in the biometric feature information included in the authentication NG information 13b. The three biometric feature information items A to C including the biometric feature information are selected (step S501).

  Then, the grouping unit 22 compares the similarity of all combinations of the three pieces of biometric feature information A to C selected in step S501 with the first threshold value F stored in the internal memory of the grouping unit 22 ( Step S502).

  Subsequently, the grouping unit 22 further compares the degree of similarity between all combinations of the three pieces of biometric feature information A to C selected in step S501 and the second threshold f held in the internal memory of the grouping unit 22. (Step S503).

  Thereafter, the grouping unit 22 determines whether or not the similarity of each combination of the three biometric features A, B, and C satisfies the classification condition 1 (step S504). At this time, if the above classification condition 1 is satisfied (Yes in step S504), the grouping unit 22 groups all of the biometric feature information A, the biometric feature information B, and the biometric feature information C into the same group (step S505). .

  On the other hand, if the above classification condition 1 is not satisfied (No in step S504), the grouping unit 22 further determines whether the similarity of each combination of the three biometric features A, B, and C satisfies the classification condition 2. Determination is made (step S506).

  At this time, if the above classification condition 2 is satisfied (step S506 Yes), the threshold update unit 23 updates the first threshold F (step S507). For example, the threshold update unit 23 performs an update using the minimum similarity S_min among the similarities grouped in the same group according to the classification condition 2 as a new first threshold F. Then, the grouping unit 22 groups all of the biometric feature information A, the biometric feature information B, and the biometric feature information C into the same group (step S505).

  If the above classification condition 2 is not satisfied (No in step S506), the grouping unit 22 further determines whether or not the similarity of each combination of the three biometric features A, B, and C satisfies the classification condition 3. Determination is made (step S508).

  When the above classification condition 3 is satisfied (step S508 Yes), the grouping unit 22 executes the following process. That is, the grouping unit 22 groups the biometric feature information that configures the set that is equal to or greater than the first threshold F into the same group, and groups the remaining biometric feature information into different groups (step S509).

  On the other hand, when the above classification condition 3 is not satisfied (No at Step S508), the threshold update unit 23 updates the second threshold f (Step S510). For example, the threshold update unit 23 includes biometric feature information that does not satisfy the classification conditions 1 to 3 on one side, and the biometric feature information of a group grouped according to the classification condition 1 or the classification condition 2 in the past is included in the other combination. A combination of biometric feature information whose similarity is less than the first threshold F is extracted. After that, the threshold update unit 23 performs an update with the maximum similarity s_max as the new second threshold f among the similarities between the biometric feature information of each combination extracted previously.

  Thereafter, the grouping unit 22 groups the three pieces of biometric feature information A, B, and C into different groups (step S511).

  Thereafter, the processing from step S501 to step S511 is repeated until the comparison between the similarity between the biometric feature information of all the combinations and the first threshold value F and the second threshold value f is completed (No in step S512). Run.

  When the grouping unit 22 finishes comparing the similarity between the biometric feature information of all combinations with the first threshold value F and the second threshold value f (Yes in step S512), the grouping unit 22 performs the following operation. Perform appropriate processing. That is, the grouping unit 22 calculates the number of groups grouped by the process of step S505, step S509, or step S511 (step S513), and ends the process.

[Effect of Example 2]
As described above, in the biometric authentication device 20 according to the present embodiment, in the same manner as in the above-described first embodiment, when it is estimated that the biometric information of the person is rejected, the authentication retry is permitted, and the malicious information is malicious. If it is estimated that the other person's biometric information is rejected, the authentication retry can be limited. Therefore, according to the biometric authentication device 20 according to the present embodiment, it is possible to appropriately execute an authentication retry.

  In addition, the biometric authentication device 20 according to the present embodiment compares the biometric feature information by comparing the similarity between the biometric feature information included in the authentication NG information 13b with the first threshold value F and the second threshold value f. Group. For this reason, in the biometric authentication device 20 according to the present embodiment, the zone of the first threshold F or higher, the gray zone of the numerical range of the second threshold f or higher and lower than the first threshold F, or the zone of the second threshold lower than Biometric feature information can be grouped by dividing the similarity into three zones. Therefore, according to the biometric authentication device 20 according to the present embodiment, it is possible to improve the accuracy of grouping.

  Furthermore, the biometric authentication device 20 according to the present embodiment is based on the comparison result between the similarity between the biometric feature information included in the authentication NG information 13b and the first threshold F and the second threshold f. The first threshold value F, the second threshold value f, or both are updated so as to narrow the numerical value range of the first threshold value F and the second threshold value f. For this reason, in the biometric authentication device 20 according to the present embodiment, the gray zone of the second threshold value f and the numerical width of the first threshold value can be reduced as the number of retries increases. Therefore, according to the biometric authentication device 20 according to the present embodiment, when there is a high possibility that the subject's biometric information is rejected due to a difference in input method or usage environment, the number of groups of biometric feature information is used for reference. It becomes possible to quickly converge the number of parts where biometric information can be registered.

  Although the embodiments related to the disclosed apparatus have been described above, the present invention may be implemented in various different forms other than the above-described embodiments. Therefore, another embodiment included in the present invention will be described below.

[Application method of user ID]
The disclosed apparatus can also use a user ID as a condition for controlling the retry of authentication. That is, there is a case where a malicious other person uses the same biometric information while changing the user ID to attack another person. From the viewpoint of suppressing this, the disclosed apparatus can also limit authentication retries if a non-identical user ID is included in the user ID included in the authentication NG information 13b for a predetermined threshold or more. Note that “1” may be adopted as the threshold value in order to prevent the above-described attack, or “1 + α” may be set by taking a margin for the user to input a user ID and make a mistake.

  FIG. 12 is a flowchart illustrating a procedure of ID determination processing according to the application example. The process of step S701 shown in FIG. 12 corresponds to step S305 shown in FIG. 4, and the subsequent processes can be replaced with the processes of steps S702 to S706 shown in FIG.

  When the process of step S304 shown in FIG. 4 is executed, as shown in FIG. 12, the disclosed apparatus determines whether or not the number of groups grouped in step S304 is equal to or smaller than a predetermined threshold (step S304). S701). At this time, if the number of groups exceeds the threshold (No in step S701), the disclosed apparatus limits the authentication retry (step S702) and ends the process.

  On the other hand, when the number of groups is equal to or smaller than the threshold (Yes in step S701), the disclosed apparatus determines whether or not a non-identical user ID is included in the user ID included in the authentication NG information 13b. Determination is made (step S703).

  Here, if the user IDs included in the authentication NG information 13b include a user ID that is not the same or more than the threshold (Yes in step S703), the disclosed device restricts the retry of authentication (step S702), The process ends.

  On the other hand, if the user IDs included in the authentication NG information 13b do not include a user ID that is not the same or more than the threshold (No in step S703), the disclosed device executes the following process.

  That is, when the number of groups grouped in step S304 is “1” (Yes in step S704), the disclosed apparatus executes a notification that prompts the user to input biometric information of the same type and different parts ( Step S705). Then, the disclosed apparatus permits an authentication retry (step S706) and ends the process.

  On the other hand, if the number of groups grouped in step S304 is greater than “1” (No in step S704), authentication notification is permitted without executing the notification in step S705 (step S706), and the process ends.

  In this way, by executing the processing shown in FIG. 12, it is possible to suppress an attack in which a malicious person uses the same biometric information and attempts to accept another person while changing the user ID. Further, when the number of groups is “1”, the biometric information of the same type and the same part is used because the difference in the input method and the use environment is large compared with the registration of the biometric feature information for reference. Even if you continue to retry authentication, you may fall into a dead end. In such a case, it is possible to increase the possibility of getting out of the authentication retry by inputting biometric information of the same type and different parts.

[1: N authentication]
In the first and second embodiments described above, the case where the one-to-one authentication is employed has been illustrated, but the one-to-N authentication can also be employed. For example, when the one-to-N authentication is employed, the disclosed apparatus uses a predetermined number of user IDs having the highest similarity in the authentication failure of each record of the authentication NG information 13b, for example, first to fifth user ID groups. It can be associated with biometric feature information. As a result, instead of the user ID, when the same person is not included in the upper predetermined number every time an authentication retry is executed, a malicious person uses the same biometric information to accept another person. It can also be estimated that the targeted attack is being carried out.

[Type of biometric information]
In the first and second embodiments, the case where fingerprint authentication is executed as biometric authentication has been illustrated, but other biometric authentication such as vein authentication and iris authentication can also be used. For example, when vein authentication is adopted as biometric authentication, a left hand vein pattern and a right hand vein pattern can be associated with one user ID and registered. Further, when iris authentication is adopted as biometric authentication, the right eye iris and the left eye iris can be registered in association with one user ID.

[Distribution and integration]
In addition, each component of each illustrated apparatus does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured.

  For example, in the first and second embodiments, the case where the biometric authentication device 10 or the biometric authentication device 20 is operated in a stand-alone manner is illustrated. However, the functional units included in the biometric authentication device 10 or the biometric authentication device 20 are included in the client terminal and the server. It can also be dispersed in the device. As an example, from the viewpoint of transferring biometric feature information instead of biometric information itself between client servers, the ID receiving unit 11, the biometric sensor 12, and the extracting unit 15a among the functional units of the biometric authentication device 10 are mounted on the client terminal. To do. On the other hand, a collation unit 15b, an authentication unit 15c, a calculation unit 15d, a grouping unit 15e, a determination unit 15f, and a retry control unit 15g are mounted on the server device. Thereby, also in the client server system, the retry control process described in the first and second embodiments can be executed.

  Also, some of the functional units of the extraction unit 15a, the verification unit 15b, the authentication unit 15c, the calculation unit 15d, the grouping unit 15e, the determination unit 15f, or the retry control unit 15g may be used as the external device of the biometric authentication device 10 or the biometric authentication device 20. It is also possible to connect via a network. In addition, each of the extraction unit 15a, the collation unit 15b, the authentication unit 15c, the calculation unit 15d, the grouping unit 15e, the determination unit 15f, or the retry control unit 15g has another functional unit, which is connected to the network. You may make it implement | achieve the function of said biometric authentication apparatus 10 or biometric authentication apparatus 20 by cooperating. In addition, the biometric authentication device 10 or the biometric authentication described above can be performed by using all or a part of the reference biometric information 13a and the authentication NG information 13b stored in the storage unit 13 as a database server and cooperating with the database server through a network connection. The function of the device 20 may be realized.

[Retry control program]
The various processes described in the above embodiments can be realized by executing a prepared program on a computer such as a personal computer or a workstation. In the following, an example of a computer that executes a retry control program having the same function as that of the above-described embodiment will be described with reference to FIG.

  FIG. 13 is a schematic diagram illustrating an example of a computer that executes a retry control program according to the first to third embodiments. As illustrated in FIG. 13, the computer 100 includes an operation unit 110 a, a speaker 110 b, a camera 110 c, a display 120, and a communication unit 130. Further, the computer 100 includes a CPU 150, a ROM 160, an HDD 170, and a RAM 180. These units 110 to 180 are connected via a bus 140.

  As shown in FIG. 13, the HDD 170 stores in advance a retry control program 170a that exhibits the same functions as the calculation unit 15d, grouping unit 15e, determination unit 15f, and retry control unit 15g described in the first embodiment. The The retry control program 170a may be integrated or separated as appropriate, similar to the components of the calculation unit 15d, grouping unit 15e, determination unit 15f, and retry control unit 15g illustrated in FIG. Further, the retry control program 170a may be appropriately integrated or distributed in the same manner as each component of the calculation unit 15d, grouping unit 22, threshold update unit 23, determination unit 15f, and retry control unit 15g illustrated in FIG. . In other words, all data stored in the HDD 170 need not always be stored in the HDD 170, and only data necessary for processing may be stored in the HDD 170.

  Then, the CPU 150 reads the retry control program 170 a from the HDD 170 and expands it in the RAM 180. Thereby, as shown in FIG. 13, the retry control program 170a functions as a retry control process 180a. The retry control process 180a expands various data read from the HDD 170 in an area allocated to itself on the RAM 180, and executes various processes based on the expanded data. The retry control process 180a includes processing executed by the calculation unit 15d, grouping unit 15e, determination unit 15f, and retry control unit 15g shown in FIG. 1, for example, processing shown in FIG. The retry control process 180a includes processing executed by the calculation unit 15d, grouping unit 22, threshold update unit 23, determination unit 15f, and retry control unit 15g shown in FIG. 5, for example, processing shown in FIG. It should be noted that all the processing units virtually realized on the CPU 150 do not always have to operate on the CPU 150, and only the processing units necessary for the processing need only be virtually realized.

  Note that the retry control program 170a is not necessarily stored in the HDD 170 or the ROM 160 from the beginning. For example, each program is stored in a “portable physical medium” such as a flexible disk inserted into the computer 100, so-called FD, CD-ROM, DVD disk, magneto-optical disk, or IC card. Then, the computer 100 may acquire and execute each program from these portable physical media. In addition, each program is stored in another computer or server device connected to the computer 100 via a public line, the Internet, a LAN, a WAN, etc., and the computer 100 acquires and executes each program from these. It may be.

  The following supplementary notes are further disclosed with respect to the embodiments including the above examples.

(Additional remark 1) The memory | storage part which memorize | stores the biometric feature information which biometric authentication failed among the biometric feature information extracted from biometric information at the time of biometric authentication,
A calculation unit that calculates the similarity between biometric feature information for each combination of biometric feature information stored in the storage unit;
A grouping unit that groups the biometric feature information stored in the storage unit using the similarity between the biometric feature information calculated by the calculation unit;
A determination unit that determines whether the number of groups in which the biometric feature information is grouped by the grouping unit is equal to or less than a predetermined threshold;
Retry for permitting the biometric authentication retry when the determining unit determines that the number of groups is equal to or less than the threshold value, and limiting the biometric authentication retry when the group number is determined to exceed the threshold value A biometric authentication device comprising: a control unit.

(Additional remark 2) The said grouping part is a group from which the similarity between the biometric feature information calculated by the said calculation part, the 1st threshold value which classify | categorizes several biometric feature information into the same group, and several biometric feature information differ 2. The biometric authentication device according to appendix 1, wherein the biometric feature information stored in the storage unit is grouped by comparing with a second threshold value that is classified as follows.

(Additional remark 3) Based on the comparison result with the similarity between the biometric feature information calculated by the calculation unit, and the first threshold and the second threshold, the first threshold and the second threshold The biometric authentication device according to appendix 2, further comprising a threshold update unit that updates the threshold.

(Supplementary Note 4) The threshold update unit may reduce the first threshold and the second threshold or the first threshold and the second threshold so as to narrow a numerical range of the first threshold and the second threshold. The biometric authentication device according to appendix 3, wherein both of the threshold values are updated.

(Additional remark 5) The biometric feature information for reference referred at the time of execution of the biometric authentication is a plurality of biometric feature information of different parts registered for the same type of biometric feature information,
Whether the number of groups in which the biometric feature information is grouped by the grouping unit is equal to or less than a threshold set based on the number of parts where the reference biometric feature information can be registered for one user. The biometric authentication device according to any one of appendices 1 to 4, wherein it is determined whether or not.

(Additional remark 6) The said determination part uses the threshold value updated so that it may converge to the number of the parts which can be registered as the frequency | count of retry of the said biometric authentication increases, The threshold determination of the said number of groups The biometric authentication device according to appendix 5, wherein the biometric authentication device is executed.

(Supplementary Note 7) The biometric feature information for reference that is referred to when the biometric authentication is performed is a plurality of biometric feature information of different parts registered with respect to the same type of biometric feature information,
The calculation unit calculates the similarity when the number of times that the biometric authentication retry is performed is equal to or greater than the number of parts that can register the reference biometric feature information for one user. The biometric authentication device according to any one of appendices 1 to 6, characterized in that:

(Additional remark 8) The said memory | storage part further memorize | stores the identification information of the user input with the said biometric feature information in addition to the biometric feature information which failed in the said biometric authentication,
Appendices 1-7, wherein the retry control unit limits the retry of the biometric authentication when the number of nonidentical pieces of identification information among the pieces of identification information stored in the storage unit is equal to or greater than a predetermined threshold. The biometric authentication device according to any one of the above.

(Additional remark 9) When the said biometric authentication is successful, or when the predetermined period passes since the said biometric authentication was performed last, it has further the deletion part which erase | eliminates the biometric feature information memorize | stored in the said memory | storage part The biometric authentication device according to any one of appendices 1 to 8, characterized in that:

(Appendix 10)
With reference to a storage unit that stores biometric feature information that failed biometric authentication among biometric feature information extracted from biometric information at the time of biometric authentication, the similarity between the biometric feature information is calculated for each combination of biometric feature information,
Using the calculated similarity between biometric feature information, group biometric feature information stored in the storage unit,
Determining whether the number of groups in which each biometric feature information is grouped is equal to or less than a predetermined threshold;
When it is determined that the number of groups is equal to or less than the threshold, the biometric authentication is permitted to be retried, and when it is determined that the number of groups exceeds the threshold, the biometric authentication is restricted. A retry control program characterized by that.

(Appendix 11) The computer
With reference to a storage unit that stores biometric feature information that failed biometric authentication among biometric feature information extracted from biometric information at the time of biometric authentication, the similarity between the biometric feature information is calculated for each combination of biometric feature information,
Using the calculated similarity between biometric feature information, group biometric feature information stored in the storage unit,
Determining whether the number of groups in which each biometric feature information is grouped is equal to or less than a predetermined threshold;
The biometric authentication retry is permitted when it is determined that the number of groups is equal to or less than the threshold, and the biometric authentication retry is executed when the number of groups is determined to exceed the threshold. A retry control method characterized by the above.

DESCRIPTION OF SYMBOLS 10 Biometric authentication apparatus 11 ID reception part 12 Biosensor 13 Memory | storage part 13a Reference biometric information 13b Authentication NG information 15 Control part 15a Extraction part 15b Verification part 15c Authentication part 15d Calculation part 15e Grouping part 15f Determination part 15g Retry control part

Claims (8)

A storage unit that stores biometric feature information that failed biometric authentication among biometric feature information extracted from biometric information during biometric authentication;
A calculation unit that calculates the similarity between biometric feature information for each combination of biometric feature information stored in the storage unit;
A grouping unit that groups the biometric feature information stored in the storage unit using the similarity between the biometric feature information calculated by the calculation unit;
A determination unit that determines whether the number of groups in which the biometric feature information is grouped by the grouping unit is equal to or less than a predetermined threshold;
Retry for permitting the biometric authentication retry when the determining unit determines that the number of groups is equal to or less than the threshold value, and limiting the biometric authentication retry when the group number is determined to exceed the threshold value A biometric authentication device comprising: a control unit.   The grouping unit classifies the similarity between the biometric feature information calculated by the calculation unit, a first threshold for classifying the plurality of biometric feature information into the same group, and a plurality of biometric feature information into the different groups. The biometric authentication device according to claim 1, wherein biometric feature information stored in the storage unit is grouped by comparing with a threshold value of two.   The first threshold value and the second threshold value are updated based on a comparison result between the biometric feature information calculated by the calculation unit and the first threshold value and the second threshold value. The biometric authentication device according to claim 2, further comprising a threshold update unit.   The threshold update unit is configured to reduce the numerical value range of the first threshold and the second threshold, and the first threshold, the second threshold, or both the first threshold and the second threshold. The biometric authentication device according to claim 3, wherein the biometric authentication device is updated. The biometric feature information for reference that is referred to when the biometric authentication is executed is a plurality of biometric feature information of different parts registered for the same type of biometric feature information,
Whether the number of groups in which the biometric feature information is grouped by the grouping unit is equal to or less than a threshold set based on the number of parts where the reference biometric feature information can be registered for one user. The biometric authentication device according to any one of claims 1 to 4, wherein it is determined whether or not.   The determination unit performs the threshold determination of the number of groups using a threshold that is updated so as to converge to the number of parts that can be registered as the number of times that the biometric authentication retry is performed increases. The biometric authentication device according to claim 5. On the computer,
With reference to a storage unit that stores biometric feature information that failed biometric authentication among biometric feature information extracted from biometric information at the time of biometric authentication, the similarity between the biometric feature information is calculated for each combination of biometric feature information,
Using the calculated similarity between biometric feature information, group biometric feature information stored in the storage unit,
Determining whether the number of groups in which each biometric feature information is grouped is equal to or less than a predetermined threshold;
When it is determined that the number of groups is equal to or less than the threshold, the biometric authentication is permitted to be retried, and when it is determined that the number of groups exceeds the threshold, the biometric authentication is restricted. A retry control program characterized by that. Computer
With reference to a storage unit that stores biometric feature information that failed biometric authentication among biometric feature information extracted from biometric information at the time of biometric authentication, the similarity between the biometric feature information is calculated for each combination of biometric feature information,
Using the calculated similarity between biometric feature information, group biometric feature information stored in the storage unit,
Determining whether the number of groups in which each biometric feature information is grouped is equal to or less than a predetermined threshold;
The biometric authentication retry is permitted when it is determined that the number of groups is equal to or less than the threshold, and the biometric authentication retry is executed when the number of groups is determined to exceed the threshold. A retry control method characterized by the above.

Images