JP2016081410A - Biometrics authentication method system, biometrics authentication program, and biometrics authentication method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a biometrics authentication system, biometrics authentication program, and biometrics authentication method capable of achieving high-speed processing.SOLUTION: A biometrics authentication system 100 includes: a registration unit 400 for registering biometrics data BD as biometrics data TBD in accordance with first index data and second index data having a plurality of hierarchies (n+1); and a collation device 600 for collating the biometrics data BD with the registered biometrics data TBD in accordance with the first index data and second index data.SELECTED DRAWING: Figure 2

Description

  The present invention relates to a biometric authentication method system, a biometric authentication program, and a biometric authentication method.

Conventionally, various research and development have been conducted on biometrics authentication method systems. For example, in biometric authentication, fingerprints, voiceprints, irises, veins, and the like are used.
For example, for fingerprints, a “pattern (image) matching method”, a “feature point (minutia) method”, a “feature point and relation method”, a “frequency analysis method”, and the like are currently used.

For example, the “pattern matching method” is a method in which a specific area of a fingerprint is limited and collation is performed while overlapping ridge patterns in the area.
In addition, the “feature point method” extracts and registers information from 20 to 30 points of the end points where the ridges are broken or the branch points where the ridges branch when the fingerprint image is collected. It is a technique to do.

The “feature point and relation method” is a technique that does not consider the same fingerprint unless both the feature point and the relation information are the same.
Furthermore, the “frequency analysis method” is a method of performing collation by obtaining a maximum correlation by using a cross section obtained by slicing a fingerprint pattern as a waveform and using a waveform spectrum series as feature information.

  In addition, for example, Patent Document 1 (Japanese Patent Laid-Open No. 2011-86130) discloses speeding up of an authentication process in a fingerprint authentication system used by a large number of users. The speed-up of the authentication process in the fingerprint authentication system described in Patent Document 1 is a fingerprint authentication system having a plurality of fingerprint sensors. When fingerprint data is input, depending on the fingerprint sensor to which the fingerprint data is input, A group specifying means for specifying a group to which the fingerprint data belongs; in the case of registration of fingerprint data, a registration means for registering the input fingerprint data in the storage device in association with the group specified by the group specifying means; In the case of data authentication, it comprises collation means for collating input fingerprint data with fingerprint data associated with the same group as the input fingerprint data among the fingerprint data registered in the storage device It is.

  Patent Document 2 (Japanese Patent Application Laid-Open No. 2009-164680) discloses a wireless communication terminal and a terminal use having a high security function that allows only a plurality of specific terminal users registered in advance to use the wireless communication terminal. A person identification method is disclosed.

  In a wireless communication terminal and a terminal user identification method described in Patent Document 2, in a wireless communication terminal including a PTT switch, a fingerprint reading unit provided in the PTT switch, fingerprint data of a plurality of terminal users, and fingerprint data thereof are used. A storage unit that can register ID number information including at least a use ID number set for each registered terminal user, and a fingerprint authentication unit that collates fingerprint data read by the fingerprint reading unit with registered fingerprint data in the storage unit And means for operating the wireless communication terminal based on the collation result of the fingerprint authentication unit, and means for acquiring one ID number information from the storage unit based on the collation result of the fingerprint authentication unit. is there.

  Further, Patent Document 3 (Japanese Patent Application Laid-Open No. 2006-277415) discloses a registration apparatus for a fingerprint authentication system suitable for users having different physical characteristics. The registration device described in Patent Literature 3 includes an input unit that inputs biometric information to be registered, a pre-extraction unit that extracts first feature data from the biometric information according to a predetermined feature extraction method, and the first feature data. And classifying the biometric information into any one of a plurality of groups, and a second feature data from the biometric information by a feature extraction method corresponding to each of the plurality of groups. A feature extraction unit for extraction, and a registration unit for associating the first feature data, the second feature data, and the classification data and registering them as reference biometric information are provided.

  Patent Document 4 (Japanese Patent Application Laid-Open No. 2006-277341) discloses a plurality of simultaneous biometric input devices capable of simultaneously acquiring a plurality of biometrics by an operation equivalent to positioning of a single biometric, and such a plurality of simultaneous simultaneous metrics. It is disclosed to provide a multiple simultaneous biometric authentication device that can perform high-speed authentication using a biometric input device.

  The multiple simultaneous biometrics authentication device described in Patent Document 4 is arranged in accordance with a standard relative position of a plurality of body parts within which a variation in a positional relationship between a plurality of body parts from which biometrics are acquired is within a predetermined range, Sensors corresponding to each biometric that simultaneously acquire types of biometrics corresponding to a plurality of body parts and dictionaries corresponding to the plurality of types of biometrics are feature points related to the person to be authenticated registered in each dictionary. Based on each of the biometrics obtained by the integrated dictionary, which is classified and integrated into a plurality of clusters corresponding to each biometric by performing cluster analysis on each, and a sensor corresponding to each biometric The feature points of the person from whom the plurality of types of biometrics are acquired are classified The identification means for determining the cluster of the integrated dictionary, and by comparing each of the plurality of biometrics and each element of the cluster indicated by the determination result by the determination means, the person from whom the plurality of types of biometrics have been acquired Authentication means for authenticating, and in the cluster classification in the integrated dictionary, the cluster classification is performed for the different types of biometrics, thereby generating subdivided clusters.

  Patent Document 5 (Japanese Patent Application Laid-Open No. 2008-40874) discloses a collation apparatus that can accurately perform collation score correction corresponding to fluctuations included in input data even when registered data is small. It is disclosed.

  The collation device described in Patent Document 5 is a collation device that determines whether or not input data matches registration data based on a collation score that represents the degree of similarity between input data and registration data. Score distribution storage means for storing the first collation score distribution examined in advance using data, registration data storage means for storing a plurality of registration data, data input means for receiving input of data, input data, A score calculating means for calculating a matching score by comparing with registered data to be checked, input data and a plurality of registered data stored in the registered data storage means to compare the second matching score distribution. A registration in which the score distribution calculating means for calculating, the first matching score distribution and the second matching score distribution are registered in the registered data storage means Correcting means for calculating a third matching score distribution by combining with weighting according to the number of data, and correcting the matching score calculated by the score calculating means based on the third matching score distribution; And a determination unit that determines whether or not the input data matches the registered data to be verified by comparing the verification score corrected by the correction unit with a predetermined threshold value.

JP 2011-86130 A JP 2009-164680 A JP 2006-277415 A JP 2006-277341 A JP 2008-40874 A

However, although the techniques of Patent Documents 1 to 5 can perform biometric authentication for a predetermined number of people, there is a problem that processing time is required when the number of registered biometric authentication data increases. Therefore, there is a problem that the user has to input information such as the group information of the technology of Patent Document 1 or the ID number of the technology of Patent Document 2 even in one fingerprint information. Further, in the technique of Patent Document 1 or Patent Document 2, when the group information or ID number is forgotten, there is a problem that fingerprint authentication does not function.
Furthermore, in Patent Documents 4 and 5, it is only possible to collate from a part of biometric authentication data, and it is difficult to perform biometric authentication on the scale of tens of thousands.

An object of the present invention is to provide a biometric authentication method system, a biometric authentication program, and a biometric authentication method that can realize high-speed processing.
Another object of the present invention is to provide a biometrics authentication method system, a biometrics authentication program, and a biometrics authentication method capable of high-speed collation of several tens of seconds or less regardless of the parameter.

(1)
A biometric authentication system according to one aspect performs registration using a first index having a plurality of layers according to a finger or hand vein pattern and a second index having a plurality of layers according to finger fingerprint data. Includes a registration unit.

  In this case, since registration is performed using the first index having a plurality of hierarchies and the second index having a plurality of hierarchies, the biometric data registered in the registration unit can be registered with an index (index).

(2)
A biometrics authentication system according to another invention performs registration using a first index having a plurality of layers according to a finger or hand vein pattern and a second index having a plurality of layers according to fingerprint data of the finger. Collation for collating the registration data of the registration unit of the first index and the second index with the biometric data to be collated according to the first index and the second index of the biometric data to be collated Part.

In this case, since registration is performed using the first index having a plurality of hierarchies and the second index having a plurality of hierarchies, the biometric data registered in the registration unit can be registered with an index (index).
Moreover, the collation result can be obtained only by collating the biometric data to be collated with the biometric data registered according to the first index and the second index.
As a result, since it is not necessary to collate with all registered biometric data, high-speed processing can be achieved.

(3)
The biometrics authentication system according to still another invention uses a first index having one layer according to a finger or hand vein pattern and a second index having a plurality of layers according to finger fingerprint data, or Using the first index having a plurality of hierarchies according to the finger or hand vein pattern and the second index having one hierarchy according to the fingerprint data of the finger, the registration unit to be registered and the biometric data to be collated Depending on the first index and the second index, the registration data of the registration unit of the first index and the second index and a collation unit that collates biometric data may be included.

In this case, in order to perform registration using the first index having one hierarchy and the second index having a plurality of hierarchies, or the first index having a plurality of hierarchies and the second index having one hierarchy, It is possible to register biometric data registered in the registration unit with an index.
Moreover, the collation result can be obtained only by collating the biometric data to be collated with the biometric data registered according to the first index and the second index.
As a result, since it is not necessary to collate with all registered biometric data, high-speed processing can be achieved.

(4)
The biometrics authentication system according to a fourth aspect of the present invention is the biometrics authentication system according to one aspect, another aspect, or still another aspect, wherein the registration unit places the other one below the first index and the second index. The determination may be made using the index data having a hierarchical structure and registered.

In this case, since either index data in which the second index is arranged below the first index or index data in which the first index is arranged below the second index is used, biometric data is easily classified. And can register.
Moreover, since the number of divisions can be increased also in collation, collation can be performed easily.

(5)
The biometrics authentication system according to the fifth invention is the biometrics authentication system according to the fourth invention from one aspect, wherein the registration unit includes at least one of a plurality of hierarchy levels of the first index and a plurality of hierarchy levels of the second index. One may include a registration adjustment unit that is adjusted according to at least one of the registered population and the number of registrations of each registration unit.

  In this case, since the registration unit includes a registration adjustment unit, the number of registrations can be adjusted according to the registered population and the number of registrations after the hierarchy. As a result, the verification time can be shortened regardless of whether the parameter is large or small.

(6)
The biometric authentication system according to a sixth aspect of the present invention is the biometric authentication system according to the fifth aspect of the present invention from the one aspect, wherein the first index is at least one of the number, angle, and branching point of the blood vessel axis of a part of the vein May be included.

In this case, since the first index includes at least one of the number, angle, and branching point of the blood vessel axis of a part of the vein, the vein can be easily classified.
The first index may optionally include vein thickness, vein depth, and the like. In addition, since the thickness of the vein may change, the axis of the vein of the vein may be extracted to determine the vein axis.

(7)
The biometrics authentication system according to a seventh aspect of the present invention is the biometrics authentication system according to the sixth aspect of the present invention from the one aspect, wherein the second index may include at least one of a fingerprint pattern, a feature, and a characteristic.

  In this case, since the second index includes at least one of a fingerprint pattern, a feature, and a characteristic, the fingerprint can be easily classified.

(8)
The biometrics authentication system according to an eighth aspect of the present invention is the biometrics authentication system according to the seventh aspect of the present invention from another aspect, wherein the collating unit has a hierarchical structure under one of the first index and the second index. The determination may be made using the index data and collated with registered data corresponding to the index data.

  In this case, since either index data in which the second index is arranged below the first index or index data in which the first index is arranged below the second index is used, biometric data is easily classified. In addition, since the number of divisions can be increased at the time of collation, the collation can be easily performed.

(9)
A biometrics authentication program according to still another invention uses a first index having a plurality of hierarchies according to a finger or hand vein pattern and a second index having a plurality of hierarchies according to finger fingerprint data. Registration processing to be registered.

  In this case, since registration is performed using the first index having a plurality of hierarchies and the second index having a plurality of hierarchies, the biometric data registered by the registration process can be registered with an index (index).

(10)
A biometrics authentication program according to still another invention is registered using a first index having a plurality of layers according to a finger or hand vein pattern and a second index having a plurality of layers according to fingerprint data of the finger. According to the first index and the second index of the vein pattern and fingerprint data to be verified, the registration data in the registration process of the first index and the second index, the vein pattern and fingerprint data to be verified, And a collation process for performing the collation.

In this case, since registration is performed using the first index having a plurality of hierarchies and the second index having a plurality of hierarchies, the biometric data registered by the registration process can be registered with an index (index).
Further, the collation result can be obtained only by collating the biometric data to be collated with the biometric data registered according to the first index and the second index.
As a result, since it is not necessary to perform collation processing with all biometric data that has been registered, high-speed processing can be achieved.

(11)
A biometrics authentication method according to still another invention uses a first index having a plurality of hierarchies according to a finger or hand vein pattern and a second index having a plurality of hierarchies according to finger fingerprint data. A registration step of registering may be included.

  In this case, since registration is performed using the first index having a plurality of hierarchies and the second index having a plurality of hierarchies, the biometric data registered in the registration process can be registered with an index (index).

(12)
The biometrics authentication method according to still another invention is registered using a first index having a plurality of layers according to a finger or hand vein pattern and a second index having a plurality of layers according to finger fingerprint data. According to the registration process and the first index and the second index of the vein pattern and fingerprint data to be collated, the registration data in the registration process of the first index and the second index, and the vein pattern and fingerprint data to be collated And a verification process for performing verification.

In this case, since registration is performed using the first index having a plurality of hierarchies and the second index having a plurality of hierarchies, the biometric data registered in the registration process can be registered with an index (index).
Further, the collation result can be obtained only by collating the biometric data to be collated with the biometric data registered in accordance with the first index and the second index.
As a result, since it is not necessary to collate with all biometric data that has been registered, high-speed processing can be achieved.

(13)
The biometric authentication system according to a thirteenth invention is the biometric authentication system according to the eighth invention from one aspect, wherein the first index data and the second index data may include at least GPS information and time zone information. .

  In this case, GPS information or time zone information may be added to the first index data and the second index data. In this case, biometric data can be grouped according to one or both of GPS information and time zone information.

(14)
The biometrics authentication program according to the fourteenth invention is the biometrics authentication program according to the ninth or tenth invention, wherein the registration process includes at least a plurality of hierarchy levels of the first index and a plurality of hierarchy levels of the second index. One may include a registration adjustment process that is adjusted according to at least one of the registered population and the number of registrations of each registration unit.

  In this case, since the registration process includes a registration adjustment process, the number of registrations can be adjusted according to the number of registered parameters and the number of registrations after the hierarchy. As a result, the verification time can be shortened regardless of whether the parameter is large or small.

(15)
The biometric authentication method according to a fifteenth aspect of the invention is the biometric authentication method according to the eleventh or twelfth aspect of the invention, wherein the registration step includes at least one of a plurality of hierarchical levels of the first index and a plurality of hierarchical levels of the second index. One of them may include a registration adjustment step that is adjusted according to at least one of the registered population number and the registered number after the hierarchy.

  In this case, since the registration process includes a registration adjustment process, the number of registrations can be adjusted according to the number of registered parameters and the number of registrations after the hierarchy. As a result, the verification time can be shortened regardless of whether the parameter is large or small.

It is a schematic diagram which shows an example of schematic structure of a biometrics authentication system. It is a schematic diagram which shows an example of a biometrics registration apparatus. It is a flowchart which shows the operation | movement of the biometrics registration process in this Embodiment. It is a schematic diagram for demonstrating the pattern in fingerprint data. It is a schematic diagram for demonstrating an example of the characteristic or characteristic in fingerprint data. It is a schematic diagram for demonstrating an example of the characteristic or characteristic in vein data. It is a flowchart which shows the operation | movement of the biometrics collation process in this Embodiment. It is a schematic diagram which shows an example of the collation in a biometrics collation process.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the following description, the same parts are denoted by the same reference numerals. Their names and functions are also the same. Therefore, detailed description thereof will not be repeated.

<First embodiment>
(Biometrics authentication system 100)
FIG. 1 is a schematic diagram illustrating an example of a schematic configuration of a biometric authentication system 100.

  As shown in FIG. 1, the biometrics authentication system 100 includes a biometric data acquisition device 200, first to nth index determination devices 300, a registration unit 400, a selection data acquisition device 500, a verification device 600, and a determination result display unit. 700 is included.

(Outline of biometrics data registration process)
First, biometric data registration processing will be described.
In the biometric registration process, a biometric data registration apparatus 900 is used. The biometric data registration device 900 includes a biometric data acquisition device 200, first to nth index determination devices 300, and a registration unit 400.
In the present embodiment, biometric data acquisition apparatus 200 is an apparatus that can acquire fingerprint data FD and vein data VD at a time. Specifically, palm vein data and fingertip fingerprint data can be acquired simultaneously. Note that the fingertip vein data VD and fingerprint data FD may be acquired simultaneously. That is, the vein data VD and the fingerprint data FD may be acquired only with the fingertip.

In the case of biometric data registration processing in the present embodiment, biometric data BD is acquired by the biometric data acquisition device 200.
In the present embodiment, palm vein data VD and fingertip fingerprint data FD are collectively referred to as biometric data BD. The biometric data acquisition device 200 gives the acquired biometric data BD to the first to nth index determination device 300.

The first to n-th index determination devices 300 determine the biometric data BD according to a first index and a second index having a plurality of stages to be described later.
First to n-th index determination apparatus 300 links index information (hereinafter referred to as index data) including both first index data and second index data and biometrics data BD, and provides them to registration unit 400. The registration unit 400 registers the biometric data BD as biometric data TBD in a group corresponding to the index data. The group will be described later.

(Outline of biometrics verification process)
Next, the biometric matching process will be described. In the biometric verification process, the biometric authentication system 100 is used.
Therefore, in the biometrics collation processing, the biometric data acquisition device 200, the first to nth index determination devices 300, the registration unit 400, the selection data acquisition device 500, the verification device 600, and the determination result display unit 700 are used.
In the case of biometric collation processing, biometric data BD is acquired by the biometric data acquisition device 200. The biometric data acquisition device 200 gives the acquired biometric data BD to the first to nth index determination device 300.

The first to n-th index determination devices 300 determine biometric data BD according to first index data having a plurality of stages and second index data having a plurality of stages, which will be described later. The first to nth index determination devices 300 list and determine the index data from the biometric data BD. The first to n-th index determination devices 300 provide the selected data acquisition device 500 with the index data.
The selection data acquisition device 500 extracts the registered biometric data TBD corresponding to the index data in the registration unit 400 according to the index data (first index data and second index data).

The selection data acquisition device 500 gives the biometric data TBD extracted from the registration unit 400 and the biometric data BD from the biometric data acquisition device 200 to the verification device 600.
The collation device 600 collates the biometric data TBD extracted from the registration unit 400 with the biometric data BD from the biometric data acquisition device 200 and gives the determination result to the determination result display unit 700.
The determination result display unit 700 displays the determination result on a built-in display unit (not shown).
In addition, in the above, the display part incorporated in the determination result display part 700 was illustrated, However, It is not limited to this, You may have a signal output part which outputs a determination result as a signal.

(Example of biometrics registration device)
Next, FIG. 2 is a schematic diagram illustrating an example of a biometric registration device. As shown in FIG. 2, the first to n-th index determination device 300 (n is an arbitrary positive integer) includes an index determination device having n + 1 stages.
In the present embodiment, the first index determination device 310 and the second index determination devices 320, 321, and 322 are composed of second index data related to fingerprint data, and the third index determination devices 331 to ˜33P (P is Arbitrary positive integers) to n-th index determination devices 341 to 34Q (Q is an arbitrary positive integer) includes first index data related to vein data.

For example, the first index determination device 310 receives the fingerprint data FD from the biometric data BD from the biometric data acquisition device 200, determines the pattern of the pattern, and transmits the pattern.
For example, the first index determination device 310 classifies the fingerprint data FD into one of the patterns of the fingerprint data FD, LOOP, WHORL, or ARCH. Details of the classification will be described later.

As shown in FIG. 2, a second index determination device 320, a second index determination device 321, and a second index determination device 322 are provided below the first index determination device 310.
Furthermore, a third index determining device 331 and a third index determining device 332 are provided below the second index determining device 320, and an nth index determining device 341 and a third index determining device 332 are provided below the third index determining device 331. An n index determination device 342 is provided.

Similarly, a plurality of third index determination devices (not shown) are similarly provided at the lower portion of the second index determination device 321, and a third index determination device 33 </ b> P (P is the lower portion of the second index determination device 322). , Any positive integer).
Subsequently, an nth index determination device 34Q (Q is an arbitrary positive integer) is provided below the third index determination device 33P.
Thus, in the first to n-th index determination devices 300, a plurality of index determination devices are provided in a plurality of stages (n + 1 stages).

  Subsequently, as illustrated in FIG. 1, a registration unit 400 is provided below the first to n-th index determination devices 300. As illustrated in FIG. 2, the registration unit 400 includes a plurality of registration units from the first group 401 to the m + 2 group 40m + 2 (m is an arbitrary positive integer).

A first group 401, a second group 402, and a third group 403 of the registration unit 400 are provided below the n-th index determination device 341.
Similarly, a fourth group 404, a fifth group 405, and a sixth group 406 of the registration unit 400 are provided below the nth index determination device 342.
Similarly, the mth group 40m, the m + 1 group 40m + 1, and the m + 2 group 40m + 2 of the registration unit 400 are provided below the nth index determination device 34Q.

(Flowchart showing the operation of biometrics registration processing)
FIG. 3 is a flowchart showing the operation of biometric registration processing according to the present embodiment. FIG. 4 is a schematic diagram for explaining a pattern in fingerprint data, and FIG. 5 is a schematic diagram for explaining an example of characteristics or features in fingerprint data.
Furthermore, FIG. 6 is a schematic diagram for explaining an example of characteristics or features in vein data.

First, as shown in FIG. 3, in the fingerprint registration process of the biometric registration process, biometric data BD is acquired by the biometric data acquisition apparatus 200 (step S1).
Next, the fingerprint data FD is extracted from the biometric data BD acquired by the biometric data acquisition device 200, is determined by the first index determination device 310, the vein data VD is extracted from the biometric data BD, and the third index determination is performed. The determination is made by the devices 331 to 33p.
The first index determination device 310 determines whether the first index determination result is a fingerprint data pattern corresponding to LOOP, WHORL, or ARCH (step S2).

Further, as shown in FIG. 4, the LOOP of the fingerprint data FD has a fingerprint pattern in a loop shape, and the WHORL of the fingerprint data FD has a circular pattern of the fingerprint, and the ARCH of the fingerprint data FD. The fingerprint pattern is bow-shaped.
The first index determination device 310 determines which of the fingerprint data FD corresponds to the process in step S2.

  Here, for example, if it is determined in step S2 that the fingerprint data FD corresponds to LOOP, the second index determination device 320 further corresponds to the 2A condition, 2B condition, and 2C condition for the characteristics or features in the fingerprint data FD. (Step S3).

Here, as shown in FIG. 5, in the fingerprint data FD, a convex portion appears as a ridge and a concave portion appears as a ridge groove in the skin cross section. As shown in FIG. 5, the fingerprint data FD includes features or characteristics of the hair line C1, the end point C2, the branch point C3, the short line C4, the bar line C5, the point C6, the start point C7, the junction point C8, the island line C9, and the like. Have
Here, the hair line C1 means that the thickness of the ridge is less than half, the short line C4 means a ridge of less than 5 mm, the bar line C5 means a ridge of 5 mm or more, and the point C6 is thick. Means a ridge with the same length.

  In the process of step S3, the second index determination device 320 determines that the 2A condition is less than 30 bars, the 2B condition is 30 or more and less than 70 bars, the 2C condition is that the bar is It is determined that the number is 70 or more, and the fingerprint data FD is determined.

Subsequently, when it is determined in step S3 that the fingerprint data FD satisfies the 2A condition, the third index determination device 331 determines whether the vein data VD corresponds to any of the 3A condition, the 3B condition, and the 3C condition. Determine (step Sp).
Here, the second index data (LOOP, less than 30 bar lines) in the processing of step S2 and step S3 is included in the biometric data BD sent to the third index determination device 331.

  Here, as shown in FIG. 6, the vein data VD is obtained by extracting the palm vein from an image by near infrared rays. In this case, since the vein data VD includes the palm outline HA, the vein line BL, and the vein branch point CS, at least any position of the palm outline HA, vein line BL, and vein branch point CS. Or it is determined by the number.

In the present embodiment, the third index determination device 331 assumes that the number of vein lines BL that are part of the palm is less than 3 as the 3A condition.
Further, as an example, the 3B condition is a case where the number of vein lines BL that are part of the palm is 3 or more and less than 8, and the condition of 3C is that the number of vein lines BL that is part of the palm is 8 or more. Suppose that

  Next, when the third index determination device 331 determines that the vein data VD satisfies the 3A condition in the processing of step Sp, the nth index determination device 341 determines that the qA condition (q is an arbitrary positive integer), qB It is determined whether the condition or qC condition is met (step Sn).

In the present embodiment, in the n-th index determination device 341, as the qA condition, the number of vein branch points CS that are part of the palm is less than three.
Further, as an example, the qB condition is a case where the number of vein branch points CS that are part of the palm is 3 or more and less than 8, and the condition of qC is that the number of vein branch points CS that are part of the palm is 8 It is assumed that there are more than one.

  In the present embodiment, the number of vein lines BL that are part of the palm and the number of vein branch points CS that are part of the palm are determined. However, the present invention is not limited to this. Alternatively, the length and width of the venous line BL, the position of the venous branch point CS, and the like may be determined by an arbitrary method.

  Finally, when it is determined in step Sn that the vein data VD satisfies the qA condition, the n-th index determination device 341 determines the second index data (LOOP, 2A condition), the first index data (index data). 3A condition and qA condition) and biometric data BD are registered in the first group 401 as biometric data TBD (step Sn + 1).

  Similarly, the n-th index determination device 341 registers the biometric data BD as the biometric data TBD in the second group 402 when the qB condition is met, and the third group when the qC condition is met. Biometric data BD is registered as biometric data TBD in 403 (step Sn + 1).

In this way, the biometric registration device 900 finally divides the biometric data BD into the m + 2 group 40m + 2 from the first group 401 and registers it as the biometric data TBD.
As a result, the number of biometric data TBD registered individually from the first group 401 to the m + 2 group 40m + 2 can be reduced. For example, by using hundreds of millions of biometric data BD and tens of stages of index data, the number of biometric data TBD registered in one group can be reduced to several thousand or less.
In particular, by using the first index data and the second index data, hundreds of thousands, hundreds of millions or hundreds of millions of biometric data BD can be grouped into tens, hundreds, thousands of biometric data TBD. Can be divided.

(Flowchart showing the operation of biometrics verification processing)
FIG. 7 is a flowchart showing the operation of the biometric matching process in the present embodiment, and FIG. 8 is a schematic diagram showing an example of matching in the biometric matching process.

First, as shown in FIG. 7, in the biometric collation process, biometric data BD is acquired by the biometric data acquisition device 200 (step S1).
Next, the fingerprint data FD of the biometric data BD acquired by the biometric data acquisition device 200 is transmitted to the first index determination device 300, and whether the first index determination result corresponds to the LOOP of the fingerprint pattern or WHORL Or whether it corresponds to ARCH (see FIG. 4) (step S2).

  Here, for example, if it is determined in step S2 that the fingerprint data FD corresponds to LOOP, the second index determination device 320 further corresponds to the 2A condition, 2B condition, and 2C condition for the characteristics or features in the fingerprint data FD. (See FIG. 5) is determined (step S3).

  Subsequently, when it is determined in step S3 that the fingerprint data FD satisfies the 2A condition, the third index determination device 331 determines whether the vein data VD corresponds to any of the 3A condition, the 3B condition, and the 3C condition. Determine (step Sq).

  Next, the n-th index determination device 341 determines whether the vein data VD satisfies the qA condition, the qB condition, and the qC condition (step Sn).

If the n-th index determination device 341 determines that the vein data VD satisfies the qA condition, the n-th index determination device 341 sends the selected data acquisition device 500 the fingerprint data FD and vein data VD of the biometrics data BD, the LOOP, the 2A condition, the 3A condition, and the qA. Pass the condition index data. That is, the second index data is a LOOP, 2A condition, and the first index data is a 3A condition, a qA condition.
Then, the selected data acquisition apparatus 500 registers in one corresponding group from the first group 401 to the m + 2 group 40m + 2 of the registration unit 400 according to the first index data and the second index data. All the biometric data TBD thus obtained is acquired (step Sn + 1).

Subsequently, the selection acquisition device 500 delivers all the biometric data TBD of the registered predetermined group and the biometric data BD to be verified to the verification device 600.
As shown in FIG. 8, collation apparatus 600 performs pattern matching collation between fingerprint data TFD of registered biometric data TBD of a predetermined group and fingerprint data FD of biometric data BD to be collated (step S21). .

In the present embodiment, for the sake of explanation, all registered biometric data TBD is transferred. However, the present invention is not limited to this, and the biometric data TBD registered in the group is not limited to this. The verification device 600 may perform verification.
In the present embodiment, the collation apparatus 600 collates the fingerprint data TFD and the fingerprint data FD. However, the present invention is not limited to this, and a predetermined group of vein data TVD and vein data VD are collated. May be.

Next, the collation apparatus 600 determines in the process of step S21 that the fingerprint data TFD of all biometrics data TBD registered in the predetermined group and the fingerprint data FD of the biometrics data TBD to be collated do not match. In this case, a mismatch display is displayed on the determination result display unit 700 (step S23).
On the other hand, when the collation apparatus 600 determines in step S21 that the fingerprint data FD matches the fingerprint data FD of the biometric data BD to be collated from the fingerprint data TFD of all biometrics data TBD registered in the predetermined group. Then, the coincidence display is displayed on the determination result display unit 700 (step S22).

  As described above, the matching device 600 performs pattern matching using the fingerprint data TFD of a predetermined number of biometrics data TBD registered by dividing into groups according to the index data including the first index data and the second index data. Since the processing is performed, it is possible to prevent the processing speed from taking a long time. That is, tens, hundreds, and thousands of registered fingerprint data TFD and fingerprint data FD to be verified can be verified in a few seconds.

  If the index data including the first index data and the second index data is not classified and registered for each group, biometric data to be collated with hundreds of millions or tens of millions of registered biometric data TBD. Since collation with BD takes tens of thousands of seconds, that is, it takes about 3 hours as collation time, it cannot be used as a substitute for personal authentication or a card.

  In the above-described embodiment, the determination result display unit 700 is used. However, the present invention is not limited to this, and an arbitrary method such as outputting the determination result as a signal output may be used.

  Furthermore, the constituent elements of the biometric authentication system 100 and the constituent elements of the biometric registration device 900 do not have to be arranged at the same place, and may be connected via the Internet, the cloud, or the like.

In the present embodiment, pattern matching processing, which is an example of fingerprint authentication, is exemplified in collation device 600, but the present invention is not limited to this, and a minutia method, frequency analysis method, hybrid fingerprint authentication method, or the like may be used. .
Further, although the case of using fingerprint authentication has been described, the present invention is not limited to this, and vein authentication may be used.

Furthermore, fingerprint data and / or vein data is used as the index data, but the index data is not limited to this, and the index data may include any country, region, address, GPS position, time zone, etc. Information may be used.
Note that iris data which is other biometric data may be used.

<Second Embodiment>
In the second embodiment, only differences from the first embodiment will be described. The second embodiment differs from the first embodiment in the following points.

  In the second embodiment, the condition of the first index determination device 310 in the first embodiment is replaced with the condition of the third index determination device 331, and the condition of the second index determination device 320 is changed to the nth index determination device 341. The above conditions have been replaced.

  That is, in the first embodiment, the determination is made based on the vein data VD after the determination is made based on the fingerprint data FD. However, in the second embodiment, the determination is made based on the vein data VD and the fingerprint is later made. The determination is based on the data FD.

  In the first embodiment and the second embodiment, the case where a plurality of fingerprint data FD and vein data VD are provided has been described. However, the present invention is not limited to this, and any one of them, that is, one index. It may be data.

  In the first embodiment or the second embodiment, a registration adjustment device may be provided in the registration unit 400. The registration adjustment device may adjust the number n of the first to nth index determination devices 300. For example, the adjustment may be made according to the individual parameters of the fingerprint data FD or the vein data VD of the registered biometric data TBD of each group of the registration unit 400. As a result, the parameters in each group can be adjusted, so that the collation time can be maintained below a predetermined time.

  As described above, in the biometric authentication system 100 according to the present invention, the index data (index) is formed by a plurality of hierarchies (n + 1). As a result, the biometric data BD in the registration unit 400 can be effectively grouped and registered as biometric data TBD.

  Further, in the collation device 600, biometric data BD to be collated is classified by a plurality of hierarchies (n + 1), and collated with biometric data TBD registered in advance in the registration unit 400 according to the index data. Thus, the biometric data BD can be collated in a short time.

  In particular, by forming index data of the (n + 1) th stage (n: positive integer), even when the biometric data TBD has hundreds of millions or tens of millions of parameters, the first index data and the first index data Since collation processing can be performed only by collating with the fingerprint data FD or vein data VD of thousands of biometrics data TBD grouped by two index data, the collation speed can be shortened.

  In addition, since the index data is based on the characteristics or characteristics of the biometric data BD, the biometric data BD can be easily grouped.

  In the present invention, the first index data corresponds to “index data of vein data VD”, the second index data is “index data of fingerprint data FD”, biometric data BD, and biometric data TBD are “biological data”. It corresponds to “metric data”, the registration unit 400 corresponds to “registration unit”, the biometrics authentication system 100 corresponds to “biometrics authentication system”, the verification device 600 corresponds to “verification unit”, and the first group The second group to m + 2 group correspond to “a group of registered data corresponding to index data”, and the flowchart corresponds to “a biometrics authentication program or a biometrics authentication program”.

  A preferred embodiment of the present invention is as described above, but the present invention is not limited thereto. It will be understood that various other embodiments may be made without departing from the spirit and scope of the invention. Furthermore, in this embodiment, although the effect | action and effect by the structure of this invention are described, these effect | actions and effects are examples and do not limit this invention.

100 Biometrics Authentication System 331, ˜, 33P, 341, ˜, 34Q nth Index Determination Device 400 Registration Unit 600 Verification Device VD, TVD Vein Data FD, TFD Fingerprint Data BD, TBD Biometric Data

Claims (15)

A first index having a plurality of hierarchies according to a finger or hand vein pattern;
A biometrics authentication system including a registration unit that registers using a second index having a plurality of hierarchies according to fingerprint data of the finger. A registration unit for registering using a first index having a plurality of layers according to a finger or hand vein pattern and a second index having a plurality of layers according to fingerprint data of the finger;
In accordance with the first index and the second index of the biometric data to be collated, the registration data of the registration unit of the first index and the second index, and a collation unit that collates the biometric data, Biometrics authentication system. A first index having one hierarchy according to a finger or hand vein pattern and a second index having a plurality of hierarchies according to the fingerprint data of the finger, or a plurality of indices according to a finger or hand vein pattern A registration unit for registering using a first index having a hierarchy and a second index having a hierarchy according to fingerprint data of the finger;
In accordance with the first index and the second index of the biometric data to be collated, the registration data of the registration unit of the first index and the second index, and a collation unit that collates the biometric data, Biometrics authentication system.   4. The registration unit according to claim 1, wherein the registration unit performs registration using index data in which one of the first index and the second index has a hierarchical structure in the lower order. 5. The biometric authentication system described.   The registration unit is configured such that at least one of the number of hierarchies of the first index and the number of hierarchies of the second index is adjusted according to at least one of a registered number and the number of registrations of each registration unit. The biometrics authentication system according to any one of claims 1 to 4, further comprising a registration adjustment unit.   The biometric authentication system according to any one of claims 1 to 5, wherein the first index includes at least one of the number, angle, and branch point of a vascular axis of a part of the vein.   The biometrics authentication system according to any one of claims 1 to 6, wherein the second index includes at least one of a fingerprint pattern, a feature, and a characteristic of the fingerprint.   The collation unit makes a determination using index data in which the other of the first index and the second index has a hierarchical structure below one of the first index and collates with registered data corresponding to the index data. 8. The biometric authentication system according to any one of items 7. A first index having a plurality of hierarchies according to a finger or hand vein pattern;
A biometrics authentication program including a registration process for registering using a second index having a plurality of hierarchies according to fingerprint data of the finger. A registration process for registering using a first index having a plurality of layers according to a finger or hand vein pattern and a second index having a plurality of layers according to fingerprint data of the finger;
Collation for collating the registration data in the registration process of the first index and the second index with the vein pattern and fingerprint data to be collated according to the first index and the second index of the vein pattern and fingerprint data to be collated And a biometrics authentication program. A first index having a plurality of hierarchies according to a finger or hand vein pattern;
A biometrics authentication method including a registration step of registering using a second index having a plurality of hierarchies according to fingerprint data of the finger. A registration step of registering using a first index having a plurality of layers according to a finger or hand vein pattern and a second index having a plurality of layers according to fingerprint data of the finger;
In accordance with the first index and the second index of the vein pattern to be collated and the fingerprint data, the collation for collating the registration data in the registration process of the first index and the second index with the vein pattern to be collated and the fingerprint data And a biometrics authentication method.   The biometrics authentication system according to any one of claims 1 to 8, wherein the first index data and the second index data include at least GPS information and time zone information.   In the registration process, at least one of the number of hierarchies of the first index and the number of hierarchies of the second index is adjusted according to at least one of a registered number and the number of registrations of each registration unit. The biometrics authentication program according to claim 9 or 10, including registration adjustment processing. In the registration step, at least one of the number of hierarchies of the first index and the number of hierarchies of the second index is adjusted according to at least one of a registered number and the number of registrations of each registration unit. The biometrics authentication method according to claim 11 or 12, comprising a registration adjustment step.

Images