JPH11104112A - Individual recognition device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an individual recognition device which can recognize individuals effectively by absorbing a change in characteristic amount of a user with time when performing individual recognition based on physical characteristic. SOLUTION: A characteristic amount extraction part 12 extracts a characteristic amount from a user's finger print image to be recognized, a similarity comparison part 18 compares the characteristic amount with that stored in a registered characteristic amount storage part 14, and a judgment part 20 checks if the user to be recognized is an accepted person by comparing the similarity with a threshold value which is dynamically changed corresponding to the history of judged results stored in a threshold value storage part 16.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a personal identification device for performing personal identification based on physical characteristics such as fingerprints, and more particularly to a personal identification device that efficiently absorbs differences in characteristic values due to the temporal change of the same person. The present invention relates to a personal authentication device that performs the following.

[0002]

2. Description of the Related Art Conventionally, security techniques such as a personal identification number (ID) and an ID card have been employed to control access to important facilities and access to important data.

However, in the basic security technology such as a personal identification number and an ID card, an unauthorized user who intends to enter or leave or access (hereinafter, referred to as an “illegal user”).
May not be able to respond to fraudulent acts impersonating a legitimate user.

[0004] For example, if an unauthorized user steals or forges the password or ID card of a valid user and performs an entry / exit operation by impersonating the user, the security system cannot exclude such an unauthorized user.

[0005] For this reason, recently, personal authentication technology which applies physical characteristics possessed by humans, such as fingerprints, palm shapes, and irises, to authentication technology and regards all users who do not have physical characteristics registered in advance as unauthorized users has been developed. Attention has been paid.

For example, when a fingerprint is used as a physical feature, the feature amount of a fingerprint image of a valid user is registered in advance, and when performing personal authentication, the feature of a fingerprint image of a user who makes an entry / exit request is registered. The similarity between the amount and the feature amount registered in advance is calculated, and if the similarity is equal to or greater than a predetermined threshold, the user is determined to be a valid user.

Therefore, in performing personal authentication using such physical characteristics, how to set the above-mentioned predetermined threshold is a very important factor, and this threshold is fixed to a common value for each user. If the value is used, the accuracy of personal authentication for each user varies.

[0008] The reason is that the physical characteristics of each user vary, and there are users who have a characteristic amount that is easy to identify as a person and users who have a characteristic amount that is difficult to identify as the person.

[0009] For this reason, Japanese Patent Laid-Open No. 6-208611 discloses that when performing personal authentication using a fingerprint, a threshold is set for each individual so that the type 2 error rate that mistakes another person for himself is a predetermined value. A personal authentication device is disclosed in which a threshold is changed for each user based on an ID number input by the user.

As described above, according to the related art, the threshold value is changed in response to a static feature value that differs for each user, so that a difference in feature value for each user can be absorbed.

[0011]

However, the above-mentioned prior art merely absorbs only the difference between the static feature amounts of different users, and the feature amount generated when the same user tries a plurality of times. It does not absorb the differences.

Therefore, even when the same legitimate user performs personal authentication, there are cases where the user is recognized as a legitimate user and a case where the same legitimate user is recognized as an unauthorized user, depending on the situation.

[0013] For example, variations in placement of the user's finger for performing fingerprint authentication and changes in the finger surface due to physiological phenomena or environmental changes such as temperature and humidity occur. This is because it is impossible to input fingerprint images having the same feature amount.

Therefore, even if the above-mentioned conventional technique is used, it is not possible to absorb the difference in the characteristic amount due to the change over time between the same users, and as a result, a legitimate user who performs personal authentication and a security manager are bothered. .

[0015] For these reasons, when performing personal authentication using physical characteristics, it is an extremely important issue how to absorb the difference in the characteristic amount due to the temporal change between the same users.

Therefore, the present invention solves the above problems,
It is an object of the present invention to provide a personal authentication device capable of efficiently performing personal authentication by absorbing a difference in a feature amount due to a temporal change between the same users when performing personal authentication using physical characteristics.

[0017]

In order to achieve the above object, a first aspect of the present invention is to calculate a difference between a feature detected from a physical feature of a user to be authenticated and a reference feature registered in advance by the user to be authenticated. In the personal authentication device that determines whether or not the authenticated user is the authenticated user by comparing the obtained difference with a predetermined threshold, from the history of past authentication results related to the authenticated user, Calculating means for calculating a pass rate of the authenticated user authenticated as a valid user, a pass rate calculated by the calculating means, a threshold used at the time of authentication, and a predetermined value set as a target. Setting means for setting a threshold value to be used in the next authentication of the user to be authenticated based on the personal pass rate.

According to a second aspect of the present invention, there is provided a detecting means for detecting a physical characteristic of an individual, a characteristic amount extracting means for extracting an individual characteristic amount from the physical characteristic detected by the detecting means, Registered feature value storage means for storing the physical feature value of the individual as a reference feature value, and a ratio determined to be the person based on the matching result of the past predetermined number of times for each individual, and a predetermined ratio for each individual. Threshold value control means for variably controlling the threshold value, threshold value storage means for storing a threshold value for each individual generated by the threshold value control means, A similarity calculating means for calculating a similarity between the feature quantity extracted by the quantity extracting means and the feature quantity stored in the registered feature quantity storing means; and a calculation result of the similarity calculating means and the threshold control means. Set personal threshold Characterized by comprising a determining means for determining the person or another person from the.

In a third aspect of the present invention, the threshold value control means includes a personal pass rate generating means for generating a ratio determined to be an individual from a predetermined number of past determination results for each individual; Target personal pass rate setting means for setting a target personal pass rate; and for each collation operation, a result generated by the personal pass rate generation means and a target personal pass rate set by the target personal pass rate setting means. Comparison means for generating a difference; correction amount generation means for generating a correction amount of a threshold value from a difference between the true pass rate and the target true pass rate generated by the comparison means; And a threshold value updating unit for generating a threshold value for the next matching operation from the threshold value correction amount generated by the correction amount generating unit.

In a fourth aspect of the present invention, the threshold value updating means includes a limit means for limiting the threshold value to at least an upper limit or a lower limit.

According to a fifth aspect of the present invention, the correction amount generation means multiplies a difference between the true pass rate and the target true pass rate generated by the comparison means by a predetermined gain each time a collation operation is performed, thereby obtaining a correction amount. It is characterized by generating.

In a sixth aspect of the present invention, the threshold value control means monitors a history of the personal pass rate generated by the personal pass rate generation means and a threshold value generated by the threshold update means. A threshold monitoring unit, wherein the threshold monitoring unit detects that the determination result that the true pass rate exceeds the target true pass rate continues for a predetermined number of times, or the threshold value is set to the upper limit or the lower limit by the limit means. Is detected, the gain used by the correction means is varied for each individual.

[0023]

Embodiments of the present invention will be described below with reference to the drawings. In this embodiment, a case will be described in which the present invention is applied to a personal authentication device that performs personal authentication using a fingerprint.

FIG. 1 is a block diagram showing the configuration of the personal authentication device used in the first embodiment.

The personal authentication apparatus shown in FIG. 1 has a registration mode for registering a feature amount of a fingerprint of a legitimate user who is permitted to enter or leave, and an operation mode for authenticating the authenticity of a user to be authenticated in actual operation. Consists of

In order to perform user authentication in this operation mode, in the registration mode, the feature amount of the fingerprint of a predetermined finger of each valid user must be stored in the registered feature amount storage unit 14 as a reference feature amount. I have to.

The reason is that in this personal authentication apparatus, a similarity is obtained from a reference feature amount of a valid user registered in advance and a feature amount of a user to be authenticated, and whether or not the user to be authenticated is a valid user is determined. It is for verifying.

Switching between the registration mode and the operation mode is performed by a mode switch or a mode switch command (not shown).

As shown in FIG. 1, this personal authentication device
Physical feature detection unit 10, operation unit 11, feature amount extraction unit 12, registered feature amount storage unit 14, threshold value storage unit 16
, A similarity calculation unit 18, a determination unit 20, a determination result storage unit 21, and a threshold control unit 22.

The physical characteristic detecting unit 10 includes a prism and a C
An input unit for optically acquiring fingerprint image data from a predetermined finger of the user to be authenticated by using a CD camera or the like. The feature amount extracting unit 12 performs space extraction from the fingerprint image acquired by the physical feature detecting unit 10. A frequency characteristic is extracted as a feature value.

In the registration mode, the feature extraction unit 12 stores the extracted feature as a reference feature in the registered feature storage 14 in association with the ID number of a valid user. In the mode, the extracted feature amount is output to the similarity calculation unit 18.

The operation unit 11 has an ID for specifying a valid user.
An operation unit for inputting a number.
It consists of a numeric keypad for inputting a D number or a card reader for reading an ID card. Note that the authentication process in the operation mode is not started unless an ID number or a correct ID card already registered as a valid user is input.

The registered feature storage unit 14 stores the feature extraction unit 1
Reference numeral 2 denotes a storage unit that stores the extracted reference feature amounts of the valid user in association with the valid user ID number input from the operation unit 11.

The similarity calculating section 18 is a processing section that operates only in the above-mentioned operation mode. If the characteristic amount of the user to be authenticated is acquired from the characteristic amount extracting section 12, the similarity calculating section 18 adds the ID number input from the operating section 11 to The reference feature value of the corresponding authorized user is read from the registered feature value storage unit 14.

Then, a correlation value between the feature quantity extracted by the feature quantity extraction unit 12 and the reference feature quantity read from the registered feature quantity storage unit 14 is calculated as a similarity, and the calculated similarity is sent to the determination unit 20. Output.

The threshold storage unit 16 is a storage unit that stores, for each ID number, a threshold used for authenticating whether or not the user to be authenticated is a valid user in the operation mode.

The threshold value stored in the threshold value storage unit 16 is sequentially updated by a threshold value control unit 22 described later based on past determination results stored in the determination result storage unit 21.

The determination unit 20 reads a threshold value corresponding to the ID number of a valid user from the threshold value storage unit 16 and compares the read threshold value with the similarity calculated by the similarity calculation unit 18. Is a processing unit that determines whether or not.

It should be noted that the result of the judgment by the judgment unit 20 is as follows.
Not only output to the outside, but also stored in the determination result storage unit 21.

The judgment result storage unit 21 stores the ID of the valid user.
This is a storage unit that stores a history of the past N determination results for each number.

The threshold control unit 22 reads the history of the determination result corresponding to the ID number of the valid user received from the operation unit 11 from the determination result storage unit 21 and performs the next authentication based on the history of the determination result. The threshold to be used is updated and stored in the threshold storage 16.

By using the personal authentication device having the above configuration, the threshold value stored in the threshold value storage unit 16 dynamically fluctuates in response to the past determination history of the valid user, and fluctuates. The determination unit 20 authenticates the user to be authenticated based on the threshold value.

Next, the threshold controller 22 shown in FIG. 1 will be specifically described.

FIG. 2 is a block diagram showing a detailed configuration of the threshold control unit 22 shown in FIG.

As shown in FIG.
2 is a personal pass rate generation unit 30, a target personal pass rate setting unit 32, a comparison unit 34, a threshold correction amount generation unit 36,
And a threshold updating unit 38.

The principal pass rate generation unit 30 reads out the history of the past N determination results stored in the determination result storage unit 21,
Rate at which the user to be authenticated is determined to be a valid user who has an ID number (hereinafter, referred to as “person pass rate”).
This is a processing unit that generates P [i]. This personal pass rate generation unit 30 corresponds to the calculating means of claim 1.

For example, a certain valid user has performed authentication L times in the past, and n times (N ≧ N) in the latest N times (L ≧ N).
If n) is determined to be “the person”, the person's pass rate P [i] of the legitimate user at that time i is P [i] = n / N.

However, in the present embodiment, since N is fixed, the principal pass rate generation unit 30 directly calculates the “number of times n determined to be a valid user” by the principal pass rate P.
It will be used as [i].

The target personal pass rate setting section 32 is a processing section for setting a desired target personal pass rate Pref to be a preset target value. However, in the present embodiment, in order to ensure consistency with the personal pass rate P [i], the target personal pass count is used.

The comparing section 34 includes the personal pass rate P [i] generated by the personal pass rate generating section 30 and the target personal pass rate setting section 32.
Is a processing unit that compares the set target personal pass rate Pref with the target personal pass rate Pref to determine the difference (P [i] −Pref).

The threshold correction amount generating section 36 includes a comparing section 34
Generating a threshold correction amount δT [i] to be used at the next authentication based on the difference (P [i] −Pref) between the principal pass rate P [i] and the target principal pass rate Pref obtained by Department.

The threshold updating unit 38 obtains a threshold T [i + 1] to be used next time to authenticate the same user to be authenticated, and updates the threshold stored in the threshold storage 16. This is a processing unit. It should be noted that the comparing unit 34, the threshold correction amount generating unit 36, and the threshold updating unit 38 constitute the calculating means of claim 1.

Specifically, the threshold used at the time of the i-th authentication is T [i], the threshold used at the time of the (i + 1) -th authentication is T [i + 1], and the threshold correction is performed. When the correction amount generated by the amount generation unit 36 is δT [i], T [i + 1] = T [i] + δT [i] is stored in the threshold value storage unit 16.

However, the threshold storage unit 16 stores a different threshold for each ID number of a valid user.

By using the threshold value control unit 22 having the above configuration, the principal pass rate P [i] and the target principal pass rate Pr are obtained.
Based on the difference (P [i] -Pref) from ef, the threshold value used in the next authentication can be dynamically corrected.

Next, a processing procedure in the operation mode of the personal authentication device shown in FIG. 1 will be described. Here, the threshold correction amount generation unit 36 generates a correction amount δT [i] proportional to the difference (P [i] −Pref) between the true pass rate P [i] and the target true pass rate Pref. The case will be shown.

FIG. 3 is a flowchart showing a processing procedure of the personal authentication device shown in FIG.

As shown in the figure, this personal authentication device
First, after setting an initial value to the threshold value T [i] (step 301), the operation unit 11 waits for input of an ID number (step 302).

Here, when the ID number is input or the ID card is inserted in the operation unit 11 and the finger of the person to be authenticated is placed on the physical characteristic detecting unit 10, the physical characteristic detecting unit 10 captures the fingerprint image. Then, the feature amount extraction unit 12 extracts a feature amount from the fingerprint image.

After that, the similarity calculating section 18 sends the operation section 11
The registered reference feature amount corresponding to the ID number input to the feature amount is extracted from the registered feature amount storage unit 14, and the similarity S [i] with the feature amount received from the feature amount extraction unit 12 is calculated (step). 303).

If the similarity S [i] is larger than the threshold T [i] stored in the threshold storage 16 (S [i]> T [i]), the determination result R [ i] is "the person"
(Step 305), and if it is equal to or smaller than the threshold value T [i] (S [i] ≦ T [i]), the determination result R [i] becomes “other” (step 306).

The determination result R [i] is not only output to the outside, but also stored in the determination result storage unit 21.

Here, in this personal authentication apparatus, the history of the determination results of the past N times is reflected in the next correction amount. Steps 306 are repeated (step 307).

On the other hand, if the determination has been made N times or more, the threshold value control unit 22 obtains the principal pass rate P [i] regarded as the “principal” in the past N times (step 308). ).

Then, the difference between the i-th personal pass rate P [i] and the target personal pass rate Pref is multiplied by α, and the threshold T [i] used for the i-th pass is added, T [i]. + Α (P [i] −Pref) is set as a threshold value T [i + 1] for the next collation (step 309). However, the gain α is a positive constant.

Then, the variable i is incremented (step 310), and the process ends after preparing for the next authentication.

Next, a description will be given of a change in threshold value that occurs when the above-described series of processing is performed, using a specific example.

FIG. 4 is a diagram showing an example of a change in threshold value when the personal authentication device shown in FIG. 1 is used. However, here, the predetermined number N is set to four times, and the target number of passes (rate) is set to three times.

As shown in the figure, when the results of the first to fourth (i = 1 to 4) determinations are all “the person”, the result at the time when the fourth determination is completed is completed. Number of passes P
[4] becomes P [4] = 4.

Here, since the target personal pass rate Pref = 3, the threshold value T [5] used at the time of the fifth authentication is: And becomes higher by the gain α.

Next, using the threshold value T [5], the fifth
If the result of the second authentication is “other”, P [5] = 3.

Therefore, the threshold value T [6] used at the time of the sixth authentication is And does not fluctuate.

Similarly, the threshold value T [7] used at the time of the seventh authentication does not change according to the result of the sixth determination, but the threshold value T used at the time of the eighth and ninth authentications is changed.
[8] and T [9] are each reduced by the gain α.

As described above, the threshold value used at the time of the next authentication sequentially changes according to the determination results of the past N times.
The threshold is increased if the personal pass rate of the past is high, and the threshold is lowered if the personal pass rate of the past N times is low.

Next, control of the threshold control unit 22 shown in FIG. 1 will be described. However, here, the threshold T
[I] is provided with a limiter, and a threshold T is set only within a predetermined range.
[I] is controlled to fluctuate.

FIG. 5 is a control block diagram of threshold control section 22 shown in FIG.

As shown in FIG.
Generates the personal pass rate P [i] from the determination history stored in the determination result storage unit 21 and inputs the generated personal pass rate to the plus terminal of the comparator.

Here, the target number of passes Pref is input to the minus side terminal of this comparator, and the difference (P
[I] −Pref) is output from the comparator, and a value α (P [i] −Pref) obtained by multiplying the output result by the gain α is added to the output and output.

Since the threshold value T [i] stored in the threshold value storage section 16 is fed back to the addition point, the limiter calculates T [i] + α (P [i] − Pref) is output.

When the input value exceeds a predetermined upper limit value or does not reach a predetermined lower limit value, the limiter performs a process of setting the value to an upper limit value or a lower limit value, and determines a processing result. Output to the value storage unit 16.

The reason for providing such a limiter is that if the threshold T [i] is allowed to drop indefinitely, if an unauthorized user repeatedly tries authentication using the ID number of another person, he / she will be mistaken as "the person". If the threshold T [i] keeps rising unnecessarily, an authentication error frequently occurs in which the authenticated user is not authenticated as "the person".

As described above, in the first embodiment, the feature amount extracting unit 12 extracts the feature amount from the fingerprint image of the user to be authenticated, and the similarity calculating unit 18 stores the feature amount and the registered feature amount. The similarity with the reference feature quantity stored in the storage unit 14 is obtained, and the determination unit 20 determines the similarity and the threshold storage unit 1
6 is compared with a threshold value that dynamically fluctuates in response to the history of the determination result stored in No. 6 to authenticate whether the user to be authenticated is a valid user. can get.

1) Even if the characteristic amount changes due to a temporal change between the same users, the personal authentication can be performed efficiently.

2) The ratio of users to be authenticated being regarded as valid users can be kept constant, and uniform convenience can be provided to each user.

3) It is possible to reduce the load on the threshold value adjustment of the security manager.

The first embodiment has been described above.

In the first embodiment, the gain α used by the threshold correction amount generator 36 is common to all users. However, the gain α can be changed for each valid user.

Therefore, a second embodiment for optimizing the gain used by the threshold correction amount generator for each valid user will be described below. Also in this case, since the entire configuration of the personal authentication device is the same as that shown in FIG. 1, the description is omitted.

FIG. 6 is a block diagram showing the configuration of the threshold control unit 60 used in the second embodiment. Parts having functions similar to those of the threshold control unit 22 shown in FIG. 2 are denoted by the same reference numerals, and description thereof will be omitted.

As shown in FIG.
0 indicates that the threshold value updating unit 38 uses the threshold value monitoring unit 61
Monitoring the history of the update result and the comparison result of the comparison unit 34,
As a result of this monitoring, when it is determined that the threshold value should be changed, an instruction to change the threshold value is sent to the threshold correction amount generation unit 36.

Then, upon receiving this notification, the threshold correction amount generating section 36 sets the gain α to be used for the next collation for each individual.
To update.

That is, the threshold control unit 60 obtains the relationship between the true pass rate P [i] obtained from the comparison result of the comparing unit 34 and the target true pass rate Pref, and the threshold update unit 38. The magnitude of the gain α is dynamically updated based on the relationship between the threshold value and the limit value.

Next, control of the threshold control unit 60 shown in FIG. 6 will be described.

FIG. 7 is a control block diagram of threshold control section 60 shown in FIG. However, description of portions common to the control block diagram shown in FIG. 5 will be omitted.

As shown in FIG.
Monitors the output of the comparator (P [i] -Pref) and the variation of the threshold value fed back from the threshold value storage unit 16 to the addition point, and controls the gain α.

Specifically, the output from the comparator (P
When [i] -Pref) is positive for M consecutive times, the tracking response is determined to be too slow, and the gain α is increased.

When the threshold value is limited to the upper and lower limits by the limiter, it is determined that the threshold value is in the oscillation state, and the gain α is reduced.

As described above, by using the threshold value controller 60, the gain for correcting the threshold value can be controlled to an appropriate value according to the situation.

Next, the processing procedure of the personal authentication device having the threshold control unit 60 will be described.

FIG. 8 is a flowchart showing a processing procedure of the personal authentication device having the threshold control unit 60 shown in FIG. However, steps 801 to 809 and step 8
Step 15 corresponds to steps 301 to 309 and step 310 shown in FIG.

As shown in the figure, if the threshold value T [i + 1] to be used at the next collation is obtained (step 809),
It is determined whether the personal pass rate P [i] exceeds the target personal pass rate Pref M times in a row (step 810).

If the principal pass rate P [i] exceeds the target principal pass rate Pref M times consecutively, a predetermined correction amount B is added to the gain α to increase the gain α itself (step 811). ).

That is, as shown in FIG. 9A, the reason that the principal pass rate P [i] exceeds the target principal pass rate Pref M times in succession is that the threshold value cannot follow the authentication result history. Therefore, the gain α is increased to solve this problem.

Thereafter, the threshold value T used for the next authentication is determined.
It is determined whether or not [i + 1] has exceeded the limit value of the limiter (step 812). If it exceeds the limit value, the threshold value T [i + 1] is set to the limit value (step 813), and the gain is set. α is reduced by the correction amount B (step 814).

That is, as shown in FIG. 9C, the fluctuation of the threshold value is extremely large and exceeds a predetermined limit value, which means that the gain α is too large.
By reducing the gain α, an appropriate threshold value variation as shown in FIG. 9B is achieved.

As described above, in the second embodiment, the threshold value control unit 60 determines the correlation between the true pass rate P [i] and the target true pass rate Pref, the threshold value and the limit value. Is configured to dynamically control the magnitude of the gain α on the basis of the above relationship, it is possible to improve the responsiveness of following the threshold.

Next, the relationship between the personal authentication device used in the present embodiment and the pass rate of the individual will be described.

FIG. 10 is a conceptual diagram showing the relationship between the personal authentication device shown in FIG. 1 and the pass rate of the individual.

As shown in the figure, even if the optimum threshold value is strictly set in consideration of, for example, the collation distribution (A) of the principal and the collation distribution of another person, the collation distribution of the principal due to the change over time can be reduced. In some cases, the distribution (A) shifts to the distribution (B), and conversely, the distribution (B) shifts to the distribution (A).

In such a case, if the threshold value is fixed and operated as in the conventional personal authentication apparatus, the user may be authenticated as an unauthorized user or as an unauthorized user despite being a valid user. Nevertheless, there is a case where the user is authenticated as a valid user.

However, in the personal authentication device shown in FIG. 1, if the verification collation of the individual shifts from the distribution (A) to the distribution (B) or from the distribution (B) to the distribution (A), the verification is followed. By varying the threshold, a constant pass rate can be maintained.

Note that the threshold shown in FIG. 1 does not fall below the lower limit and is always operated at a threshold higher than the lower limit. Security is also improved compared to.

In the present embodiment, the case where the present invention is applied to a personal authentication device using a fingerprint has been described. However, the present invention is not limited to this. For example, a face, an iris, a palm shape, etc. The present invention can also be applied to various personal authentication devices that use the physical characteristics of.

[0114]

As described above in detail, the first aspect of the present invention is based on the history of the past authentication result of the user to be authenticated, and determines the pass rate of the individual who has been authenticated as the valid user. Based on the calculated pass rate, the threshold value used at the time of authentication, and the predetermined pass rate set as a target, a threshold value used for the next authentication of the user to be authenticated is set. With the configuration, the following effects can be obtained.

1) Even if the characteristic amount changes due to a temporal change between the same users, the individual authentication can be performed efficiently.

2) It is possible to make the rate at which the user to be authenticated is regarded as the authorized user constant, and to provide uniform convenience to each user.

3) The burden of adjusting the threshold value of the security manager can be reduced.

In the second invention, when performing a collation operation, a similarity between a feature amount extracted from a physical feature of an individual and a reference feature amount registered in advance is obtained. Is configured to determine whether or not the user is a user based on a threshold value set based on the ratio of the user being determined to be the user in the past. Can be.

Further, in the third aspect of the present invention, a ratio determined to be an individual is generated from a predetermined number of past determination results for each individual, and a threshold is determined from a difference between the generation result and a predetermined target individual pass rate. Since the correction amount is generated and the threshold value for the next collation operation is generated from the correction amount and the threshold value for the previous collation operation, the threshold value is set so as to achieve the target personal pass rate. Can be varied.

Further, since the fourth invention is provided with the limit means for limiting the threshold value to at least the upper limit or the lower limit, it is possible to eliminate a situation where the threshold value is extremely lowered and the security is reduced. it can.

Further, in the fifth invention, the correction amount is generated by multiplying the difference between the true pass rate and the target true pass rate by a predetermined gain every time the matching operation is performed, so that the threshold value can be efficiently set. Can be corrected.

Further, the sixth invention monitors the history of the true pass rate and the threshold value, and detects that the judgment result that the true pass rate exceeds the target true pass rate continues for a predetermined number of times, or Is detected by the limit means, the gain is varied for each individual, so that the optimal gain can be set for each individual.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of a personal authentication device used in a first embodiment.

FIG. 2 is a block diagram showing a detailed configuration of a threshold control unit shown in FIG. 1;

FIG. 3 is a flowchart showing a processing procedure of the personal authentication device shown in FIG. 1;

FIG. 4 is a diagram showing an example of a change in threshold value when the personal authentication device shown in FIG. 1 is used.

FIG. 5 is a control block diagram of a threshold control unit shown in FIG. 1;

FIG. 6 is a block diagram showing a configuration of a threshold control unit used in the second embodiment.

FIG. 7 is a control block diagram of a threshold control unit shown in FIG. 6;

8 is a flowchart showing a processing procedure of the personal authentication device having the threshold control unit shown in FIG.

FIG. 9 is a diagram showing the relationship between the similarity and the number of times of matching when the gain is too small, proper, and too large.

FIG. 10 is a conceptual diagram showing the relationship between the personal authentication device shown in FIG. 1 and the pass rate of the principal.

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 10 ... Physical feature detection part, 11 ... Operation part, 12 ... Feature quantity extraction part, 14 ... Registered feature quantity storage part, 16 ... Threshold value storage part, 18 ... Similarity calculation part, 20 ... Judgment part, 2
1 ... determination result storage unit, 22 ... threshold control unit, 30 ...
Principal pass rate generation unit, 32 ... Target pass rate setting unit, 3
4 Comparison section, 36 Threshold correction amount generation section, 38 Threshold update section, 60 Threshold control section, 61 Threshold monitoring section

Claims (6)

[Claims] 1. A method for determining a difference between a feature value detected from a physical feature of a user to be authenticated and a reference feature value registered in advance by the user to be authenticated, and comparing the obtained difference with a predetermined threshold value. A personal authentication device that authenticates whether a target user is a valid user or not, based on a history of past authentication results related to the user to be authenticated, a pass rate of the person authenticated that the user to be authenticated is a valid user. Calculating means for calculating the personal pass rate calculated by the calculating means, a threshold value used at the time of authentication, and a predetermined personal pass rate set as a target to authenticate the user to be authenticated next time. And a setting means for setting a threshold value used at that time. 2. A detecting means for detecting a physical characteristic of an individual; a characteristic amount extracting means for extracting a characteristic amount of the individual from the physical characteristic detected by the detecting means; A registered feature quantity storage unit that stores the quantity as a reference feature quantity; and a threshold value such that a rate determined as the principal based on the matching result of the past predetermined number of times for each individual is a predetermined rate for each individual. Threshold value control means for variably controlling; threshold value storage means for storing a threshold value for each individual generated by the threshold value control means; A similarity calculating means for calculating a similarity between the feature quantity and the feature quantity stored in the registered feature quantity storing means; and a calculation result of the similarity calculating means and a calculation for each individual set by the threshold control means. From the threshold Is a personal authentication device comprising: a determination unit for determining the identity of another person. 3. A personal pass rate generating means for generating a ratio determined to be an individual based on a predetermined number of past determination results for each individual, and a target personal pass rate for each individual. And a comparison means for generating a difference between a result generated by the personal pass rate generation means and a target personal pass rate set by the target personal pass rate setting means each time a matching operation is performed. Correction amount generating means for generating a correction amount of a threshold value from a difference between a true pass rate and a target true pass rate generated by the comparing means; and a threshold value at the time of a previous collation operation and the correction amount generating means. 3. The personal authentication apparatus according to claim 2, further comprising: a threshold updating unit configured to generate a threshold value for a next matching operation from the threshold correction amount generated by the control unit. 4. The personal authentication device according to claim 3, wherein said threshold value updating means includes limit means for limiting a threshold value to at least an upper limit or a lower limit. 5. The correction amount generating means generates a correction amount by multiplying a predetermined gain by a difference between the true pass rate and the target true pass rate generated by the comparing means each time a matching operation is performed. The personal authentication device according to claim 3, which performs the authentication. 6. The threshold value control means includes threshold value monitoring means for monitoring a history of a personal pass rate generated by the personal pass rate generation means and a threshold value generated by the threshold value update means. The threshold monitoring unit detects that the determination result that the principal pass ratio exceeds the target principal pass ratio continues for a predetermined number of times, or the threshold is limited to the upper limit or the lower limit by the limit unit. 4. The personal authentication apparatus according to claim 3, wherein when detecting that the gain is used, the gain used by the correction means is varied for each individual.