JP2012238256A - Biometric authentication device, biometric authentication method, and biometric authentication program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a biometric authentication device which provides improved security level in authentication process.SOLUTION: A biometric authentication device includes: a memory unit 13 for storing registered biometric information 32, a biometric information classification code 31, and sample biometric information 33; a biometric information classification code producing unit 15 which compares authentication format biometric information 51 with multiple pieces of sample biometric information 33 to calculate degree of similarity respectively and produces a biometric information classification code 31 on the basis of the similarity; an authentication priority information producing unit 16 which assigns a priority to the biometric information classification code 31 of each piece of sample biometric information 33 in descending order of similarity between the authentication format biometric information 51 and the sample biometric information 33 on the basis of the similarity, and produces authentication priority information such that the registered biometric information 32 belonging to a group of biometric information classification codes 31 having a lower priority is not used as an authentication subject, on the basis of a prescribed threshold value; and an authentication processing unit 17.

Description

  The present invention relates to a technique such as a biometric authentication device for the purpose of personal authentication.

As a system protection method in information security, there are “password authentication” for performing personal authentication by inputting a password by a user, “physical authentication” by using a key / ID card, and the like.
However, with password authentication, there is a risk that the password will be stolen by another person, and the user may forget the set password if the day when the password is not used continues. In the physical authentication, there is a possibility that the key / ID card may be lost, and there is a possibility that it may be illegally used by others.
In recent years, biometric authentication based on individual personal information such as fingerprints, finger veins, and palm veins has attracted attention as an authentication method for solving such problems. Since biometric authentication uses a part of the body as information, it is not forgotten like a complicated password, nor is it lost like a key. Furthermore, it is very difficult to impersonate other people as system users.

Biometric authentication methods include “one-to-one authentication” and “one-to-N authentication”.
One-to-one authentication is a method in which biometric information is acquired by a biometric sensor or the like, collated with biometric information registered in advance, and whether or not both match each other. In one-to-one authentication, a personal ID (IDentification) given to the person to be authenticated is input as primary authentication, biometric information associated with the personal ID is extracted, and the biometric information and biometric information input at the time of authentication are extracted. To see if they match. Primary authentication requires a means to input an ID card or a personal ID such as an ID number input by the person to be authenticated, but if the ID card is lost or the ID number is forgotten, the primary authentication is required. It becomes impossible to do.

  On the other hand, in the one-to-N authentication, biometric information is acquired by a biometric sensor or the like, and it is searched whether there is the same biometric information from a plurality of biometric information registered in advance, and the person to be authenticated is specified. It is a method. In the one-to-N authentication, since it is not necessary to perform primary authentication, it is not necessary to give an ID to the person to be authenticated, and the operation can be simplified. However, it is necessary to search for all the registered biometric information, which increases the processing time required for authentication.

  In order to shorten the processing time of 1-to-N authentication, a method of using a processing device capable of high-speed processing or improving an authentication processing method can be cited. As a processing time shortening method, a technique is known in which registered biometric information is grouped, authentication targets are narrowed down during authentication processing, and processing time is shortened (see, for example, Patent Document 1).

JP 2002-297549 A

  In the technique disclosed in Patent Document 1, the input biometric information is compared with reference data stored in the authentication device in advance, the similarity is calculated, and then classified according to the calculated similarity range. A code is assigned and the input biometric information is grouped. Further, in the one-to-N authentication process at the time of authentication, the authentication priority order of groups of biometric information registered in advance for one-to-N authentication depending on the similarity of the comparison result between the input biometric information and the reference data One-to-N authentication is performed according to the priority order.

  It is an object of the present invention to provide a biometric authentication device, a biometric authentication method, and a biometric authentication program that operate the generation of the priority order and improve the security level in authentication processing in the priority order determination mechanism.

  In order to solve the above problems, a biometric authentication device according to the present invention includes a biometric information input unit that inputs biometric information, and a biometric information that converts the input biometric information into authentication format biometric information that is information for authentication. The information conversion unit, the registered biometric information that is information for authentication of the biometric information registered in advance, the biometric information classification code that is information for identifying the group to which the registered biometric information belongs, and the group A storage unit that stores sample biometric information that is a sample of the biometric information, and compares the authentication form biometric information with the plurality of sample biometric information to calculate similarities, and based on the similarity, Based on the biometric information category code generation unit that generates the biometric information category code of the sample biometric information that is most similar to the authentication format biometric information, the authentication format biometric information is based on the similarity. Priorities are assigned to the biometric information category codes of each sample biometric information in the order similar to the biometric information, and the priorities belong to the group of biometric information category codes with lower priority based on a preset threshold value. An authentication priority information generation unit that generates authentication priority information and an authentication priority biometric information group and a group of biometric information classification codes in order of the priority of the authentication priority information so that registered biometric information is not subject to authentication. An authentication processing unit that performs authentication processing by collating with the registered biometric information to which it belongs.

  According to the present invention, the security level in authentication processing can be improved.

It is a block diagram which shows the structure of the hardware of the biometrics apparatus in embodiment of this invention. It is a block diagram which shows the functional structure of the biometrics apparatus in embodiment of this invention. It is a figure explaining the outline | summary of the process of the biometric information division code production | generation part in embodiment of this invention. It is a figure explaining the detail of the process of the biometric information classification code production | generation part in the embodiment of this invention, and the process of an authentication priority information generation part. It is a figure explaining the process in the authentication process part and memory | storage part in embodiment of this invention. It is a flowchart which shows the biometrics authentication operation | movement of the biometrics apparatus in embodiment of this invention.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
[Outline of Biometric Authentication Processing in Biometric Authentication Device 1]
First, an outline of biometric authentication processing in the biometric authentication device 1 of the present embodiment will be described.
The user registers biometric information in the biometric authentication device 1 in advance. The biometric authentication device 1 registers the biometric information by dividing it into groups according to characteristics. At the time of authentication, the biometric authentication device 1 first determines a group of biometric information input by the user at the time of authentication, and collates biometric information registered in advance with the biometric information input by the user at the time of authentication. And authenticate. In addition, the biometric authentication device 1 does not set all biometric information registered in advance as an authentication target, but sets a priority order for the group, and does not set a lower priority group as an authentication target.

In other words, when 1000 pieces of biometric information are registered, it takes time to return authentication results in order from 1 to 1000. Therefore, the biometric authentication device 1 groups and registers 1000 pieces of data. For example, the biometric authentication device 1 divides and registers 1000 pieces of data into 300 pieces (A group), 300 pieces (B group), and 400 pieces (C group). At this time, registration is performed by dividing into groups determined to be most similar to a sample representing the group.
At the time of authentication, the biometric authentication device 1 sets priorities for groups based on the similarity between the biometric information input by the user and the sample of each group. When it is determined that the biometric information input by the user is most similar to the sample of the A group, the biometric authentication device 1 first sets 300 pieces of data of the A group as authentication targets. Further, the biometric authentication device 1 prevents a group (for example, C group) in which the biometric information input by the user is relatively similar to the sample from being targeted for authentication.

[Configuration of Biometric Authentication Device 1]
FIG. 1 is a block diagram showing a hardware configuration of a biometric authentication device 1 according to an embodiment of the present invention.
The biometric authentication device 1 includes a biometric information input sensor 2 that inputs biometric information, a processor 3, a memory 4, a nonvolatile memory 5, and a control chip 6.
The processor 3 compares the biometric information input from the biometric information input sensor 2 with the biometric information stored in the non-volatile memory 5 according to the program developed in the memory 4 and determines the success or failure of the authentication. The processor 3, the memory 4, and the control chip 6 are generally integrated in the form of a microcomputer.
In the present embodiment, the host device 100 is connected to the biometric authentication device 1. The host device 100 is, for example, a personal computer.

FIG. 2 is a block diagram showing a functional configuration of the biometric authentication device 1 according to the embodiment of the present invention.
The biometric authentication device 1 includes a biometric information input unit 11, a biometric information conversion unit 12, a storage unit 13, a biometric information analysis unit 14, an authentication processing unit 17, a communication unit 18, and a registration processing unit 19. .

The biometric information input unit 11 inputs human biometric information 50 used for personal authentication. The biological information 50 is information such as fingerprints, veins, and irises, for example. The input biological information 50 is output to the biological information conversion unit 12.
The biometric information conversion unit 12 converts the biometric information 50 into authentication format biometric information 51 that is information for authentication. The authentication format biometric information 51 has various forms depending on the authentication method. For example, the authentication format biometric information 51 is information such as the type and position of a feature point of a fingerprint.

The storage unit 13 stores biometric information classification code 31, registered biometric information 32, and sample biometric information 33.
The biometric information classification code 31 is information for identifying a group when the biometric information 50 is grouped.
The registered biometric information 32 is information for authenticating biometric information registered in advance by the user. The registered biometric information 32 is an authentication target in the one-to-N authentication.
The sample biometric information 33 is a sample of biometric information 50 representing a group, and is used for determination when the biometric information 50 is grouped.
The storage unit 13 has a database in which the biometric information classification code 31 and the registered biometric information 32 are associated with each other.

The biological information analysis unit 14 includes a biological information classification code generation unit 15 and an authentication priority information generation unit 16.
The biometric information classification code generation unit 15 compares the authentication format biometric information 51 and the plurality of sample biometric information 33 to calculate the respective similarities, and based on the similarity, the sample with the most similar authentication format biometric information 51. The biometric information classification code 31 of the biometric information 33 is generated. The degree of similarity is an index indicating how much they are similar. There are various methods for obtaining the similarity according to the conventional technique. For example, there are a method for determining the match between the type and position of the feature point of the fingerprint, and a method for binarizing the captured image and calculating the pattern matching degree by comparing in pixel units.

  For example, as illustrated in FIG. 3, fingerprint authentication will be described as an example. The biometric information classification code generation unit 15 compares the input authentication format biometric information 51 with a plurality of sample biometric information 33. Here, the sample biometric information 33a, 33b, and 33c are representative types of fingerprints. The sample biometric information 33a is a “vortex pattern” (kajomon) in the shape of a vortex or a circle, and the sample biometric information 33b is a “hoof-shaped pattern” (sembroidery) in the shape of a horse hooves. The information 33c is a type of fingerprint called a “bow pattern” that draws a line like a mountain. The biometric information classification codes 31 of the sample biometric information 33a, 33b, and 33c are “A”, “B”, and “C”, respectively. Then, the biometric information classification code generation unit 15 calculates the similarity between the authentication format biometric information 51 and each sample biometric information 33, and the biometric information classification code “A” of the sample biometric information 33a that is most similar to each other. Is generated. A biometric information classification code “A” is assigned to the input authentication format biometric information 51. The authentication format biometric information 51 and the biometric information classification code “A” are output to the authentication processing unit 17 and the registration processing unit 19.

Based on the similarity calculated by the biometric information classification code generation unit 15, the authentication priority information generation unit 16 performs the biometric information classification code of each sample biometric information 33 in the order in which the authentication format biometric information 51 is similar to the sample biometric information 33. A priority is assigned to 31 and based on a preset threshold, authentication priority information 34 is generated so that registered biometric information 32 belonging to the group of biometric information classification code 31 with a lower priority is not subject to authentication. Is. The priority order is a priority order in which the authentication processing unit 17 described later extracts authentication targets.
The authentication priority information 34 is information in which a priority is assigned to the biometric information classification code 31. Further, the authentication priority information 34 is obtained by excluding the biometric information classification code 31 having a lower priority order based on a threshold set in advance by the user or by authenticating the biometric information classification code 31 having a lower priority order. It is generated with information indicating that it is not a target. As a result, the authentication processing unit 17 to be described later excludes the registered biometric information 32 belonging to the group of the biometric information classification code 31 having the lower priority from the authentication target.

This will be described with reference to FIG.
In FIG. 4, the biometric information classification code generation unit 15 calculates the similarity between the authentication format biometric information 51 and each sample biometric information 33a, 33b, and 33c. The mismatch rate is a form of similarity and its calculation method is omitted, but the smaller the value, the more similar.
The authentication priority information generation unit 16 acquires the similarity with each sample biometric information 33a, 33b, 33c, determines the magnitude relationship between these, generates the priority information 34 with priority. Here, since the mismatch rate is “1500” <“2300” <“2700”, it shows that the sample biometric information 33a, the sample biometric information 33b, and the sample biometric information 33c are similar in this order. Therefore, the authentication priority information generation unit 16 assigns priorities in the order of the biometric information classification codes “A”, “B”, and “C”.

Further, the authentication priority information generation unit 16 specifies the biometric information classification code “C” of the sample biometric information 33c having a mismatch rate equal to or higher than the threshold value “2500” preset by the user, and the group of the biometric information classification code “C”. Is excluded from the authentication priority information 34 so as not to be subject to authentication. Note that a user who is an authenticator or an administrator can arbitrarily set this threshold.
The authentication priority information 34 is output to the authentication processing unit 17.

  The authentication processing unit 17 performs authentication processing by collating the authentication format biometric information 51 and the registered biometric information 32 belonging to the group of the biometric information classification code 31 in the order of the priority of the authentication priority information 34. The authentication result is output to the communication unit 18.

Processing in the authentication processing unit 17 and the storage unit 13 will be described with reference to FIG.
First, the authentication processing unit 17 acquires the authentication format biometric information 51, the biometric information classification code 31, and the authentication priority information 34 from the biometric information analysis unit 14. Next, in order to extract the registered biometric information 32 to be authenticated, the authentication processing unit 17 refers to the authentication priority information 34, and the biometric information classification code 31 with a higher priority (according to the previous example, “ A ”) is used as a search key to search a database in which the biometric information classification code 31 and the registered biometric information 32 are associated, and the registered biometric information 32 that matches the biometric information classification code 31 is extracted as an authentication target. And the authentication process part 17 collates the extracted registration biometric information 32 and the authentication format biometric information 51, and performs an authentication process.

The authentication process is a process for verifying the user who has input the biometric information 50 as a registered user when the registered biometric information 32 and the authentication form biometric information 51 are collated and a predetermined precision is satisfied. is there. The predetermined matching rate is, for example, a mismatch rate of 500 or less.
Authentication is said to have been successful if the specified precision is met.
The authentication processing unit 17 collates the extracted registered biometric information 32 and the authentication format biometric information 51, and if there is nothing that satisfies the predetermined precision, the authentication priority information 34 is referred to, and the next priority is given. The registered biometric information 32 belonging to the group of the upper biometric information classification code 31 (“B” according to the previous example) is extracted, the extracted registered biometric information 32 and the authentication format biometric information 51 are collated, and the same Perform the authentication process.

Further, the authentication processing unit 17 refers to the authentication priority information 34, and if there is no next highest priority biometric information classification code 31, or the next highest priority biometric information classification code 31 is subject to authentication. If the information indicating not to be attached is attached, the authentication process is terminated.
The success or failure of authentication and the authorized registrant information are output to the communication unit 18 and notified to the host device 100.

The communication unit 18 transmits and receives information to and from the host device 100. The communication unit 18 is connected to the host device by any communication means (whether wired or wireless).
The registration processing unit 19 causes the storage unit 13 to store the biological information classification code 31 and the authentication format biological information 51 from the biological information analysis unit 14 or the biological information classification code 31 and the registered biological information 32 from the host device 100. It is. The user can register biometric information with the biometric authentication device 1.

  The biometric authentication device 1 operates according to a biometric authentication program that causes a computer to function as each functional unit described above.

[Operation of Biometric Authentication Device 1]
Next, an example of the operation of the biometric authentication device 1 will be described with reference to FIG. 6 (configuration is appropriately shown in FIG. 2).
Note that the user sets a threshold value used in step S15 in advance before the start of the biometric authentication process. In addition, it is assumed that the biometric information to be input is previously registered with biometric information classification code 31 and registered as biometric information 32.

As shown in the flowchart of FIG. 6, in step S <b> 11, the biological information input unit 11 acquires the input biological information 50.
In step S <b> 12, the biometric information conversion unit 12 converts the biometric information 50 into authentication format biometric information 51.
In step S <b> 13, the biometric information classification code generation unit 15 compares the authentication format biometric information 51 and the plurality of sample biometric information 33, and calculates the similarity.

In step S <b> 14, the biometric information classification code generation unit 15 generates the biometric information classification code 31 of the sample biometric information 33 with the most similar authentication type biometric information 51 based on the calculated similarity.
In step S15, the authentication priority information generation unit 16 determines the priority order of the biometric information classification code 31 of the sample biometric information 33 in the order in which the authentication format biometric information 51 is similar to the sample biometric information 33 based on the similarity. Based on the threshold set in advance, the authentication priority information 34 is generated so that the registered biometric information 32 belonging to the group of the biometric information classification code 31 with the lower priority is not subject to authentication.

In step S <b> 16, the authentication processing unit 17 refers to the authentication priority information 34 and extracts the registered biometric information 32 from the biometric information classification code 31 having a higher priority.
In step S <b> 17, the authentication processing unit 17 performs authentication processing by comparing the authentication form biometric information 51 with the extracted registered biometric information 32.
In step S18, the authentication processing unit 17 determines whether the authentication is successful.

If the authentication is successful (step S18 / Yes), the biometric authentication process ends.
On the other hand, if the authentication is not successful (No at Step S18), whether or not the authentication processing unit 17 has collated with all the registered biometric information 32 belonging to the group of the same biometric information classification code 31 at Step S19. Determine.
When not collating with all the registered biometric information 32 which belongs to the group of the same biometric information classification code 31 (step S19 * No), it returns to step S17 and the authentication process part 17 continues an authentication process.
On the other hand, if all of the registered biometric information 32 belonging to the group of the same biometric information classification code 31 are collated (step S19 / Yes), the authentication processing unit 17 gives priority to the authentication priority information 34 in step S20. It is determined whether or not there is a lower biological information classification code 31.

If it is determined that the authentication priority information 34 has the biometric information classification code 31 having a lower priority (step S20 / Yes), the process returns to step S16, and the authentication processing unit 17 refers to the authentication priority information 34. The registered biometric information 32 is extracted from the biometric information classification code 31 having the higher priority.
On the other hand, if it is determined that there is no biometric information classification code 31 with a lower priority in the authentication priority information 34 (No in step S20), the biometric authentication process ends. In this case, thereafter, the biometric authentication device 1 displays a message prompting the user to input biometric information again.

Through the above operation, the biometric authentication device 1 is based on the threshold set in advance by the user in determining the priority order of the groups to be authenticated when the one-to-N authentication is performed on the grouped registered biometric information 32. Thus, a group having a remarkably low degree of similarity with the sample biometric information 33 is excluded from the authentication target and 1-to-N authentication is performed.
Thereby, the user can arbitrarily operate the generation of the authentication priority information 34 according to the set value, and can improve the security level in the 1: N authentication.

  Further, even if there is a group whose priority order excluded from the authentication target matches the input biometric information, the user is prompted to input the biometric information again, thereby providing a highly accurate biometric information. Information can be obtained, reduction of rejection of the person can be realized, and reduction of acceptance of the other person can be realized.

<Modification>
As mentioned above, although one Embodiment of this invention was described, this invention is not limited to this, For example, it can change as follows in the range which does not deviate from the meaning of this invention.

  In the description of the embodiments, the fingerprint is used as the biological information. However, the present invention is not limited to this, and iris, retina, facial image, voice, blood vessel pattern of fingers and palms, etc. may be used as the biological information. .

  Further, the sample biometric information 33 may be created in advance, or the registered biometric information 32 may be used as the sample biometric information 33. For example, one of the registered biometric information 32 is selected, used as sample biometric information, and a new group D representative. Further, “D” may be newly created as the biometric information classification code.

  In addition, the biometric authentication device 1 can also display the success or failure of authentication and register the biometric information 50 in an environment where the biometric authentication device 1 is used alone without connecting the host device 100.

DESCRIPTION OF SYMBOLS 1 Biometric authentication apparatus 2 Biometric information input sensor 3 Processor 4 Memory 5 Non-volatile memory 6 Control chip 11 Biometric information input part 12 Biometric information conversion part 13 Memory | storage part 14 Biometric information analysis part 15 Biometric information division code generation part 16 Authentication priority information generation | occurrence | production Unit 17 authentication processing unit 18 communication unit 19 registration processing unit 31 biometric information classification code 32 registered biometric information 33 sample biometric information 33a sample biometric information 33b sample biometric information 33c sample biometric information 34 authentication priority information 50 biometric information 51 authentication format biometric information 100 Host device

Claims (4)

A biometric information input unit for inputting biometric information;
A biometric information conversion unit that converts the input biometric information into authentication format biometric information that is information for authentication;
Registered biometric information that is pre-registered information for authentication of the biometric information, biometric information classification code that is information for identifying a group to which the registered biometric information belongs, and biometric information that represents the group A storage unit for storing sample biometric information as a sample;
The authentication form biometric information and the plurality of sample biometric information are respectively compared to calculate a similarity, and based on the similarity, the biometric information classification code of the sample biometric information that is most similar to the authentication form biometric information A biometric information classification code generation unit for generating
Based on the similarity, the biometric information classification code of each sample biometric information is prioritized in the order in which the authentication format biometric information is similar to the sample biometric information, and the priority is set based on a preset threshold. An authentication priority information generating unit that generates authentication priority information so that the registered biometric information belonging to the group of the biometric information classification code having a lower rank is not subject to authentication;
An authentication processing unit that performs authentication processing by comparing the authentication format biometric information with the registered biometric information belonging to the group of the biometric information classification code in the order of the priorities of the authentication priority information;
A biometric authentication device comprising: The authentication processing unit, if the authentication is still successful even after performing the authentication process on the registered biometric information belonging to the group of the biometric information classification code that is to be authenticated in the authentication priority information, The biometric authentication device according to claim 1, further prompting the user to input the biometric information again. Registered biometric information that is information for authentication of biometric information registered in advance, biometric information classification code that is information for identifying a group to which the registered biometric information belongs, and a sample of the biometric information that represents the group A biometric authentication method in a biometric authentication device comprising a storage unit for storing sample biometric information,
A biometric information input step in which the biometric information input unit of the biometric authentication device inputs the biometric information;
A biometric information conversion step in which the biometric information conversion unit of the biometric authentication device converts the input biometric information into authentication format biometric information that is information for authentication;
The biometric information classification code generation unit of the biometric authentication device compares the authentication format biometric information and the plurality of sample biometric information to calculate the respective similarities, and the authentication format biometric information is based on the similarities. A biometric information segment code generating step for generating the biometric information segment code of the sample biometric information that is most similar;
The authentication priority information generation unit of the biometric authentication device assigns priorities to the biometric information classification codes of each sample biometric information in the order in which the authentication format biometric information is similar to the sample biometric information based on the similarity. An authentication priority information generating step for generating authentication priority information based on a preset threshold so as not to subject the registered biometric information belonging to the group of the biometric information classification code having a lower priority to be authenticated;
An authentication processing unit of the biometric authentication device performs authentication processing by collating the authentication form biometric information with the registered biometric information belonging to the group of the biometric information classification code in the order of the priority of the authentication priority information. An authentication process step;
A biometric authentication method comprising: A biometric authentication program for causing a computer to execute the biometric authentication method according to claim 3.

Images