JP2000148690A - Device for recognizing individuals - Google Patents

Abstract

PROBLEM TO BE SOLVED: To reduce mis-recognition of an operator at log-in of an individual recognizing device. SOLUTION: A fingerprint collating device 4 verifies an operator by collating fingerprint data obtained by reading the fingerprint of an operator 1 with the registered data of the fingerprint, and when a password 5 matches, a first operator verifying means 7 permits a log-in processing 8. Also, the first operator verifying means 7 detects that the number of times of the mis-recognition of the operator 1 exceeds a stipulated number of times, and then requests for the re-registration of the fingerprint data of another finger to re-registration processing 9.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an apparatus for permitting login by collating fingerprint data.

[0002]

2. Description of the Related Art In order to prohibit anyone other than persons concerned from entering a specific area in a building, a door which is opened and closed by an electric lock is provided at a passage or an entrance to the specific area. There is a case where a personal recognition device for determining whether or not the person is authorized is installed. FIG. 10 is an overall configuration diagram showing a conventional personal recognition device.

The operator 1 has a password 29,
The password 29 is input to the personal identification device 31.
The password discriminating means 32 outputs the inputted password 29
Against the password registered in advance. If the password 29 matches the registered password, the operator mode determination means 33 determines the operator mode corresponding to the password 29. The operator mode includes a maintenance mode, a manager mode, and an operator mode.

[0004] Thus, a login process 8 corresponding to the operator mode is executed. The permitted contents of the operation after login differ depending on the determined mode.

[0005]

In the conventional personal recognition apparatus as described above, since the operator is identified based on the password 29 of the operator 1, an operator other than the operator 1 can use the password 29 of the operator 1. May be entered to log in. Therefore, in order to further enhance security, fingerprint collation is performed instead of password discrimination. But,
If the fingerprint data registered as the operator 1 is very similar to the fingerprint data of another operator, there is a problem that the fingerprint data may be erroneously recognized as another operator.

SUMMARY OF THE INVENTION The present invention has been made to solve the above problems, and has as its object to provide a personal identification device that enables an operator to correctly recognize when an operator performs fingerprint collation.

[0007]

According to a first aspect of the present invention, there is provided a personal recognition apparatus which records data indicating a degree of misrecognition of an operator, and performs an operation based on the recorded data when collating fingerprint data. The person is decided.

Further, the personal recognition apparatus according to the second invention records the number of times that the matching result of the fingerprint data is not recognized, and when the number of erroneous recognitions exceeds the specified number in the fingerprint data matching, another finger recognition is performed. Is required to re-register the fingerprint data.

Further, the personal recognition device according to the third aspect of the present invention, when an operator is erroneously recognized as another operator, accumulates data of the erroneously recognized other operator and data of the number of times of erroneous recognition. In collating fingerprint data, an operator is recognized using the stored data.

A personal recognition device according to a fourth aspect of the present invention records an operator's login information and uses the recorded login tendency data to recognize the operator when comparing fingerprint data. It is.

The personal identification device according to a fifth aspect of the present invention is the personal identification device according to the second to fourth aspects, wherein the input personal identification number is
A means for determining whether the password matches a registered password is added.

[0012]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Embodiment 1 1 to 3 show an embodiment of the first, second and fifth aspects of the present invention. FIG. 1 is an overall configuration diagram, and FIG. 2 is a diagram showing the contents of the misrecognition frequency database of FIG. Reference numeral 3 denotes an operation flowchart, in which the same reference numerals denote the same parts (the same applies to the following embodiments).

1 and 2, reference numeral 1 denotes an operator, reference numeral 2 denotes a fingerprint of the operator 1, reference numeral 3 denotes a personal identification device constituting a security system, and reference numeral 4 denotes a fingerprint 2 to calculate fingerprint data. The fingerprint collating device 5 for collation, the passwords registered for the plurality of operators 1 respectively, 6
Is a misrecognition count database that records the number of times that the operator 1 has been misrecognized as another operator. As shown in FIG. 2, the registered operator list 6a and the misrecognized operator list 6a are not recognized. The number of times of misrecognition is recorded.

Reference numeral 7 denotes a first for determining the operator and the belonging mode (any one of the maintenance mode, the manager mode, and the operator mode) based on the output from the fingerprint collation device 4, the password 5 and the number of times of incorrect recognition database 6. The operator determining means 8 accepts the operator determined by the first operator determining means 7 and performs a login process for logging in to the system (procedure for starting use). This is a re-registration process for prompting re-registration.

Next, the operation of this embodiment will be described with reference to FIG. In step S1, the operator 1 places the registered finger on an image input unit (not shown) of the fingerprint matching device 4. In step S2, the fingerprint collation device 4 reads the fingerprint 2, calculates fingerprint data, collates the fingerprint data with the registered data, and selects and confirms the operator and the belonging mode. Next, the operator 1 inputs a personal identification number using a keyboard (not shown) or the like, compares it with the personal identification number 5 in step S4, and determines whether or not it matches the operator's one determined in step S2.

If the passwords match, the flow advances to step S5 to permit login and execute login processing 8, and the processing ends. If the passwords do not match, step S6
To the operator 1, the number of incorrect recognition times database 6
Is added to the false recognition count data 6b. For example, the operator A in the operator list 6a performs fingerprint collation, is selected as the operator B in step S2, and if the passwords do not match in step S4, 1 is added to the number of times of the operator A misrecognition. Can be

Then, it is determined in step S7 whether the number of erroneous recognitions has exceeded a prescribed number. If not, the process is terminated. If it exceeds, the process proceeds to step S8, and requests the operator 1 to re-register the fingerprint with another finger.
This request is indicated by a display (not shown) or the like,
The operation of the operator 1 is guided, but detailed description is omitted.
In this way, when the operator 1 is erroneously recognized as another operator and the number of times exceeds the specified number, the re-registration is requested with another finger, so that the operator 1 can be correctly recognized. It becomes possible.

Embodiment 2 FIG. 4 to 6 are views showing an embodiment of the third and fifth aspects of the present invention. FIG. 4 is an overall configuration diagram, FIG. 5 is a content diagram of a database of the number of times of recognition of other operators, and FIG. It is. In FIGS. 4 and 5, reference numeral 11 denotes another operator recognition number database that records which operator has been confirmed when the operator 1 has collated, and records the number of times for the operator 1. It is configured as shown in FIG.

That is, the list of operators 11a and the number-of-times-of-other-users recognition data 11b record which operator 1 is determined as the operator and the number of times.
For example, assuming that the operator A is recognized by fingerprint collation,
For example, with respect to A in the operator list 11a, B is performed five times,
C indicates that the content was incorrectly recognized once. 1
Reference numeral 2 denotes a second operator that determines the operator and the belonging mode (one of the maintenance personnel mode, the manager mode, and the operator mode) based on the fingerprint collation device 4, the password 5, and the output from the other operation recognition number database 11. This is a determination means.

Next, the operation of this embodiment will be described with reference to FIG. In step S11, the operator 1 places the registered finger on an image input unit (not shown) of the fingerprint matching device 4.
In step S12, the operator and the belonging mode are selected as in the first embodiment. At step S13, the operator list 11a of the other operator recognition count database 11 and step S1
From the other operator recognition count data 11b obtained by comparing the operator selected in step 2, the operator who has the largest count in the past is re-collated with the fingerprint data.

For example, when the operator A is selected as the operator A in step S12, the operator A
It is assumed that the operator B has been recognized once as the operator C and zero times as the other operator.
Is compared with the fingerprint data input in step S11. In step S14, it is determined whether or not the matching in step S13 matches. If they match, the process proceeds to step S16. If not, the process proceeds to step S15.

In step S15, the operator selected in step S12 is determined, and the flow advances to step S17. In step S16, the operator selected in step S13 is determined, and the process proceeds to step S17. Next, step S17
To input the password 5 and then to step S1 in step S18.
Other operation recognition count data 11b of the operator selected in 2
Then, the operator determined by the password 5 and the number of times of recognition are recorded.

For example, if the operator A is selected as the operator A in step S12 and is determined as the operator B in step S16, the operator A is erroneously recognized as the operator B in the fingerprint collation, and The number of false recognitions for B is increased by one. In step S19, it is determined whether or not the password 5 matches that of the determined operator. If the passwords match, the process proceeds to step S20 to execute a login process, and the process ends. If the passwords 5 do not match, the process ends.

In this way, by referring to the other operator recognition count database 11 for the operator 1, if the operator 1 is erroneously recognized, the fingerprint data is re-collated with the fingerprint data that seems to be the operator 1. , The operator 1 can be more correctly recognized. In addition, since the other operator recognition count database 11 is modified for each login, it can be expected that the operator 1 is further correctly recognized.

Embodiment 3 FIGS. 7 to 9 show an embodiment of the fourth and fifth aspects of the present invention. FIG. 7 is an overall configuration diagram, FIG. 8 is a content diagram of a login tendency database, and FIG. 9 is an operation flowchart. 7 and 8, reference numeral 21 denotes the day of the week, time, and the like when the operator 1 logs in.
This is a login tendency database that records events and the like and holds the probability of logging in for each operator based on the conditions at that time, and is configured as shown in FIG.

That is, an operator list 21a and log-in tendency data 21b are provided, and the operator 1 is notified of the operator information (the day of the week, time,
Event, etc.), the login probability for each operator 1 is recorded. Also, for example, assuming that the login tendency data 21b is recognized as the operator A by the fingerprint collation, the user is logged in with a probability of 90% as the operator A, 7% as the operator B, and 3% as the operator C under the conditions at that time. It indicates that it is.

Reference numeral 22 denotes a third operation for determining the operator and the belonging mode (any one of the maintenance mode, the manager mode, and the operator mode) based on the fingerprint collation device 4, the password 5, and the output from the login tendency database 21. This is a means for determining a person.

Next, the operation of this embodiment will be described with reference to FIG. In step S31, the operator 1 places the registered finger on an image input unit (not shown) of the fingerprint matching device 4.
In step S32, as in the first embodiment, the operator and the belonging mode are selected. At step S33, the operator with the highest login probability is selected from the operator list 21a of the login tendency database 21 and the login tendency data 21b obtained by comparing the operators selected at step S32.

For example, if the operator A is selected as the operator A in step S32, the condition (the day of the week, the time, the event, etc.) in which the operator A has logged in the past is matched with the current condition.
Assuming that the probability that the operator A is logged in is 9%, the probability that the operator A is B is 88%, and the probability that the operator A is C is 3%, the operator B having the highest probability is determined as the operator 1. I do.

Next, in step S34, the password 5 is input, and in step S35, the operator determined by the password 5 and the login probability are recorded in the login tendency data 21b of the operator 1 selected in step S32. . For example, when the operator A is selected as the operator A in step S32 and is determined as the operator B in step S33, it is recorded in the login tendency data 21b of the operator A as the operator B has logged in under the current login condition.

In step S36, it is determined whether or not the password 5 matches the password of the operator 1 determined in step S33, and if they match, the flow advances to step S37 to execute a login process, and the process ends. If the passwords 5 do not match, the process ends. In this way, by referring to the login tendency database 21 for the operator 1, the operator 1 with the highest login probability is determined, so that the operator 1 can be more correctly recognized. . Further, since the login tendency database 21 is modified for each login, it is expected that the operator 1 can be further correctly recognized.

[0032]

As described above, according to the first aspect of the present invention, data indicating the degree of misrecognition of an operator is recorded, and when collating fingerprint data, the operator is determined based on the recorded data. In the second invention, the number of times that the matching result of the fingerprint data is not recognized is recorded.
At the time of fingerprint data collation, if the number of times of recognition exceeds the specified number of times, a request is made to re-register the fingerprint data with another finger, so that the operator can be correctly recognized.

In the third invention, when an operator is erroneously recognized as another operator, data of the erroneously recognized other operator and data of the number of times of erroneous recognition are accumulated to collate the fingerprint data. In this case, the operator is recognized using the stored data, and in the fourth invention, the login information of the operator is recorded, and when collating the fingerprint date, the recorded login tendency data is used. Since the operator is recognized, the operator can be correctly recognized at any time.

According to the fifth aspect of the present invention, since a means for determining whether the inputted password matches the registered password is added, confidentiality can be further enhanced.

[Brief description of the drawings]

FIG. 1 is an overall configuration diagram showing a first embodiment of the present invention.

FIG. 2 is a diagram showing the contents of a misrecognition frequency database of FIG. 1;

FIG. 3 is an operation flowchart showing the first embodiment of the present invention.

FIG. 4 is an overall configuration diagram showing a second embodiment of the present invention.

FIG. 5 is a diagram showing the contents of another operator recognition frequency database in FIG. 4;

FIG. 6 is an operation flowchart showing a second embodiment of the present invention.

FIG. 7 is an overall configuration diagram showing a third embodiment of the present invention.

FIG. 8 is a diagram showing the contents of the login tendency database shown in FIG. 7;

FIG. 9 is an operation flowchart showing a third embodiment of the present invention.

FIG. 10 is an overall configuration diagram showing a conventional personal recognition device.

[Description of Signs] 1 Operator, 2 Fingerprints, 3 Personal Recognition Device, 4 Fingerprint Verification Device, 5 PIN, 6 False Recognition Number Database,
6b Number of times of misrecognition, 7 First operator determination means, 8
Login processing, 9 re-registration processing, 11 other operator recognition count database, 11b other operator recognition count data,
12 second operator determination means, 21 login tendency database, 21b login tendency data, 22 third operator determination means.

Claims (5)

[Claims] 1. An apparatus for collating read fingerprint data of an operator and registered fingerprint data and, if a match between the two is recognized, in a device permitting login, the degree of misrecognition of the operator is determined. A personal recognition device, comprising: a database in which data shown is recorded; and operator determination means for determining the operator based on the recorded data when collating the fingerprint data. 2. An apparatus for collating read fingerprint data of an operator with registered fingerprint data and, if a match is found between the two, recognizing the matching result of the fingerprint data in a device permitting login. A first operator requesting re-registration of fingerprint data by another finger when the number of erroneous recognitions exceeds a specified number of times in the collation of the fingerprint data. An individual recognizing device comprising a determination means. 3. The apparatus according to claim 1, wherein the read fingerprint data of the operator and the registered fingerprint data are collated, and if a match between the two is recognized, in the apparatus permitting login, the operator is erroneously identified as another operator. In the case of recognition, a database of the number of other operators recognized is stored in which data of the erroneously recognized other operator and data of the number of times of erroneous recognition are stored. A personal recognition device comprising a second operator determination unit for recognizing the operator by using a personal computer. 4. An apparatus for collating read fingerprint data of an operator with registered fingerprint data, and permitting login if a match between the fingerprint data and the registered fingerprint data is recognized, wherein the login information of the operator is recorded. A personal identification apparatus comprising: a login tendency database; and a third operator determination unit for recognizing the operator by using the recorded login tendency data when collating the fingerprint data. 5. A personal identification number input device for inputting a personal identification number, wherein a personal identification number determining means for determining whether the input personal identification number matches a registered personal identification number is provided by a first operator determining means, The personal recognition device according to any one of claims 2 to 4, wherein the personal recognition device is added to the second operator determination unit or the third operator determination unit.