JP2005004253A - Personal identification system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a personal identification system which changes access authorization according to a degree of a collation result or authorization information of a different system. <P>SOLUTION: The personal identification system comprises a ten key 13 for inputting ID number of a person, a fingerprint sensor 12 for reading a fingerprint image of the person, a registration personal database 14 which includes characteristics of the fingerprint at registration mode and matching rates indicating degrees of matching of the fingerprint on an ID number basis, and a collation indicator table 15 which stores collation indicators indicating degrees of collation result according to the matching rate. A controller 11 is provided which obtains a matching rate corresponding to the ID number from the registration personal database, refers to the collation indicator table to obtain a collation indicator corresponding the matching rate, determine the access authority according to the collation indicator, extracts characteristics from the read fingerprint image, and collates the characteristics with the characteristics obtained from the registration personal database to update the matching rate in the registration personal database, if the entered ID number of the person exists in the registration personal database. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a personal identification system that changes access authority according to the degree of collation results such as fingerprints and according to authentication information of another system.
[0002]
[Prior art]
Conventionally, the fingerprint image of each net user read by the fingerprint reader provided in each personal terminal, mobile phone, personal terminal in the company intranet, financial institution, certificate authority device is registered in the certificate authority device, and the terminal is used. The fingerprint image to be authenticated that is read by the fingerprint reading device of the terminal and sent to the certificate authority device in response to an authentication request from each corresponding terminal associated with the person's limitation or identity verification in online transactions is registered. The fingerprint image is collated and the identity is determined, the authentication OK / NG determination result is notified to the authentication request source terminal, and the terminal use enable / disable process and the net transaction establishment / disapproval process are performed. (For example, see Patent Document 1).
[0003]
[Patent Document 1]
Japanese Patent Laid-Open No. 2001-312476 (first page, FIG. 1)
[0004]
[Problems to be solved by the invention]
In the conventional system as described above, an object to be authenticated in another system is an individual, and if the authentication is OK, the service in the other system can be enjoyed. That is, even if the authentication is OK in a plurality of systems, for example, in a traffic management system, there is a problem that it is not possible to realize a high value-added service that changes access authority such as a specific door.
[0005]
In the conventional personal identification system, for example, whether or not doors are allowed to pass is determined according to the result of personal verification. For this reason, it can be used for people who have good matching results (a high degree of matching between the number of feature points during registration and matching), or for people with poor matching results (a low degree of matching between the number of feature points during registration and matching). However, there is a problem that only the same access authority can be given.
[0006]
The present invention has been made to solve the above-described problems, and its purpose is to identify individuals whose access authority can be changed according to the degree of the verification result and according to the authentication information of another system. Get the system.
[0007]
[Means for Solving the Problems]
A personal identification system according to the present invention includes a numeric keypad for inputting a personal ID number, a fingerprint sensor for reading the personal fingerprint image, a fingerprint feature point in the registration mode, and a fingerprint for each ID number. A registered personal database composed of a matching rate representing the degree of matching, a matching index table storing a matching index representing the degree of matching result according to the matching rate, and an individual ID number input by the numeric keypad If it is in the registered personal database, the matching rate corresponding to the ID number is acquired from the registered personal database, the matching index according to the acquired matching rate is acquired by referring to the matching index table, and the acquisition The access authority is determined according to the collation index, and the feature points are extracted from the fingerprint image read by the fingerprint sensor to register the registered personal data. By matching feature points acquired from the base is provided with a controller that updates the matching rate of the registered person database.
[0008]
DETAILED DESCRIPTION OF THE INVENTION
Embodiment 1 FIG.
A personal identification system according to Embodiment 1 of the present invention will be described with reference to the drawings. 1 is a diagram showing a configuration of a personal identification system according to Embodiment 1 of the present invention. In addition, in each figure, the same code | symbol shows the same or equivalent part.
[0009]
In FIG. 1, a personal identification system 1 inputs a controller 11 that determines access authority according to a collation index indicating the degree of collation results, a fingerprint sensor 12 for reading a personal fingerprint image, and an individual ID number. For each ID number, a registered personal database 14 composed of a fingerprint feature point in the registration mode and a matching rate representing the degree of matching of the fingerprint, and a matching index according to the matching rate are stored. And a collation index table 15.
[0010]
FIG. 2 is a diagram showing the configuration of the registered personal database of the personal identification system according to Embodiment 1 of the present invention.
[0011]
In FIG. 2, the registered personal database 14 includes “ID number”, “feature point”, “match rate”, and the like. The “coincidence rate” includes “data 1”, “data 2”, “data 3”, and “average value”.
[0012]
FIG. 3 is a diagram showing the configuration of the collation index table of the personal identification system according to Embodiment 1 of the present invention.
[0013]
In FIG. 3, for each “matching index”, the “matching rate A range” of feature points at the time of matching and “processing” in that case are stored in advance for each “matching index”.
[0014]
Next, the operation of the personal identification system according to the first embodiment will be described with reference to the drawings.
[0015]
FIG. 4 is a flowchart showing the operation of the personal identification system according to Embodiment 1 of the present invention.
[0016]
First, at the time of individual registration, the controller 11 operates in the “registration mode”, and inputs an ID number for each individual with the numeric keypad 13. Further, the fingerprint image of the finger of the registered fingerprint placed on the fingerprint sensor 12 is read.
[0017]
Next, the controller 11 extracts feature points such as end points and branch points of the corresponding fingerprint from the fingerprint image read by the fingerprint sensor 12. Thereafter, the extracted fingerprint feature points are stored in the registered personal database 14 as feature point data together with the ID number input by the numeric keypad 13.
[0018]
Subsequently, at the time of individual verification, in step 101, the controller 11 operates in the “verification mode” and inputs an ID number for each individual using the numeric keypad 13.
[0019]
Next, in step 102, it is determined whether or not the input ID number exists in the registered personal database 14. If the entered ID number exists in the registered personal database 14, the process proceeds to the next step 103, and if not, the process ends.
[0020]
Next, in step 103, match rate data corresponding to the ID number is acquired. That is, the average value data of the matching rate is acquired from the registered personal database 14.
[0021]
Next, in step 104, a fingerprint image of the individual is acquired. That is, the fingerprint image of the finger placed on the fingerprint sensor 12 is read.
[0022]
Next, in step 105, it is determined whether the collation index is level 2 or higher. Referring to the collation index table 15, it is determined to which level of the collation index the acquired match rate (average value) data corresponds. If the collation index is level 2 or higher, the process proceeds to step 111, and the level is less than level 2. In this case, the process proceeds to the next step 106 as normal access.
[0023]
Next, in step 106, feature points are extracted from the acquired fingerprint image. That is, feature points such as end points and branch points of the corresponding fingerprint are extracted from the fingerprint image read by the fingerprint sensor 12.
[0024]
Next, in step 107, the feature point acquired in step 106 is compared with the feature point stored in the registered personal database 14, and the matching process is performed. That is, here, the coincidence ratio between the two is obtained. For example, the matching rate is the ratio of the number of matching points to the total number of feature points.
Match rate = number of matches / total number of feature points
Next, in step 108, it is determined whether or not the collation result is OK. If the collation result is OK, the process proceeds to the next step 109, and if it is NG, the process is terminated. That is, referring to the collation index table 15, if the obtained matching rate is less than 30%, it is determined that collation has failed (NG), and the process ends. On the other hand, when the matching rate is 30% or more, it is determined that the collation result is OK.
[0026]
Next, in step 109, the controller 11 unlocks the corresponding door by a key control device (not shown).
[0027]
Next, in step 110, the matching rate data in the registered personal database 14 is updated. The oldest data of the matching rate data is erased, the latest data is recorded, and the matching rate data is updated. Data for the latest three times at the time of collation are cyclically stored, and for example, an average value thereof is recorded as coincidence rate data. Then, this process ends.
[0028]
In step 111, the controller 11 unlocks the corresponding door by a key control device (not shown) as a simple access (or special access) process before the collation process.
[0029]
Next, in step 112, feature points are extracted from the acquired fingerprint image. That is, feature points such as end points and branch points of the corresponding fingerprint are extracted from the fingerprint image read by the fingerprint sensor 12.
[0030]
Next, in step 113, the feature points acquired in step 112 are compared with the feature points stored in the registered personal database 14, and the matching process is performed. That is, here, the coincidence ratio between the two is obtained. For example, the matching rate is the ratio of the number of matching points to the total number of feature points.
Match rate = number of matches / total number of feature points
Next, in step 114, it is determined whether or not the collation result is OK. If the collation result is OK, the process proceeds to step 110, and if it is NG, the process proceeds to step 115. That is, referring to the collation index table 15, if the obtained matching rate is less than 30%, it is determined that collation has failed (NG), and the process ends. On the other hand, when the matching rate is 30% or more, it is determined that the collation result is OK.
[0032]
Next, in step 115, since the door unlocking process has been completed, a separate alarm process (such as a buzzer ringing at the door) is performed. Then, this process ends. In this case, since the matching result is NG, the matching rate data is not updated.
[0033]
In step 105, in the case of the first collation mode after registration processing in the registration mode, the matching rate data in the registered personal database 14 is not recorded. Normal collation processing such as is performed.
[0034]
Even when the collation index is level 2 or higher, as described above, after performing the unlocking process, the process after feature point extraction is performed, but the collated person enters the room because the door is unlocked. It becomes possible. Thereafter, only the processing in the controller 11 is performed up to the collation processing, and then the update of the matching rate data is processed separately from the access operation.
[0035]
In the flowchart shown in FIG. 4, only the case where the collation index is level 2 or higher is shown. However, the level is divided finely, and when the level is 2 or higher and 3 or lower, simple access is performed. Furthermore, in the case of level 3 or higher, the collation index table 15 may be set so as to perform services such as entering a special room.
[0036]
In other words, when biometric technology such as fingerprints is used to identify an individual when entering or leaving a room, an index indicating whether the matching result is good (feature points such as fingerprint endpoints and branch points are registered Is determined at the time of matching, and the number or ratio of matching (= the number of matched feature points / total feature points) is determined. Separately, it is stored in the identification system or the identification device unit of the entrance room. Access authority such as traffic to the room is determined according to the verification index. For example, for a person who has a good collation result, a high added-value personal identification system with improved service, such as increasing the access authority of the room, is obtained. Or, for a person who has a good collation result, the user can easily access the room (for example, the collation process is not performed to the end or the collation is OK only with the password), which is convenient. Get a personal identification system.
[0037]
Embodiment 2. FIG.
In the first embodiment, the example in which the access service is improved by the matching rate of the collation result in the personal identification system has been described. However, in the second embodiment, the access service is improved by the authentication process with another system. Is.
[0038]
A personal identification system according to Embodiment 2 of the present invention will be described with reference to the drawings. FIG. 5 is a diagram showing a configuration in which another system is connected to the personal identification system according to Embodiment 2 of the present invention.
[0039]
In FIG. 5, a personal identification system 1, a license renewal office 2, and a government office 3 are connected through a network 4 such as a telephone line or the Internet.
[0040]
The personal identification system 1 includes a controller 11, a fingerprint sensor 12, a numeric keypad 13, a registered personal database 14A, and a collation index table 15A (not shown) as in the first embodiment, A communication device 16 is provided. In addition, the license renewal office 2 includes a fingerprint collation device 21, a communication device 22, and authentication information 23 stored in a storage device. Further, the office 3 similarly includes a fingerprint collation device 31, a communication device 32, and authentication information 33 stored in a storage device. The fingerprint collation devices 21 and 31 are composed of a controller, a fingerprint sensor, a numeric keypad, a registered personal database, and the like.
[0041]
FIG. 6 is a diagram showing the configuration of the collation index table of the personal identification system according to Embodiment 2 of the present invention.
[0042]
In FIG. 6, the collation index table 15A is stored in advance for each “collation index” including the authenticated “other system” and “processing” in that case.
[0043]
FIG. 7 is a diagram showing a configuration of authentication information of the personal identification system according to Embodiment 2 of the present invention.
[0044]
This authentication information includes that the fingerprint information was registered at the time of registering the resident card at the government office, and a telephone number for recognizing the personal identification system. The registered personal database 14A includes “authentication information” and the like for each “ID number”.
[0045]
Next, the operation of the personal identification system according to the second embodiment will be described with reference to the drawings.
[0046]
The basic operation is the same as in the first embodiment. Processing in registration mode and verification processing are performed in separate systems.
[0047]
As shown in FIG. 5, the personal identification system 1 and the license renewal office 2 and the government office 3 which are systems different from the personal identification system 1 are connected to communication devices 16, 22, and the like through a network 4 such as a telephone line or the Internet. Tie between 32. Also in another system, fingerprint collation devices 21 and 31 are installed, and fingerprint information is registered when the license is renewed or when the resident's card is reported at the government office. At this time, authentication information 23 and 33 including a telephone number for recognizing the personal identification system is added and registered.
[0048]
After registering the resident's card at the government office 3 and registering the fingerprint (feature point) at the same time, the personal identification system 1 executes fingerprint verification on the fingerprint registered at the government office 3. Feature point data is registered for each ID number in the registered personal database of the government office 3. At this time, the government office 3 takes measures against impersonation such as specifying the telephone number of the personal identification system 1. The personal identification system 1 extracts a feature point from the fingerprint image read by the fingerprint sensor 12 and transmits it to the office 3 through the network 4 by the communication device 16 together with the ID number input by the numeric keypad 13. The fingerprint collation device 31 in the government office 3 performs collation processing with the feature points of the fingerprint registered at the time of registering the resident's card instead of the personal identification system 1. If the collation result is OK, the authentication information is transmitted to the personal identification system 1. The controller 11 of the personal identification system 1 updates the authentication information in the registered personal database 14A with the authentication information sent from the government office 3.
[0049]
If fingerprint information is not particularly required in another system, the registered fingerprint information may be deleted once the authentication process is successful.
[0050]
In the personal identification system 1, if the verification result with the registered fingerprint at the office 3 is OK, the authentication information recorded at the office 3 is acquired, and the registered fingerprint has a record of registering a resident card. I understand. The authentication information at the office 3 is recorded in the registered personal database 14A. Thereafter, when collating with the personal identification system 1, if the authentication at the government office 3 is registered in the registered personal database 14A from the ID number input, as shown in FIG. Do.
[0051]
In the above example, fingerprint data registered in another system is acquired using a communication means such as a telephone line, but it may be stored in an electronic medium such as an IC card issued by another system.
[0052]
That is, fingerprint verification processing is performed through the network 4 and the fingerprint registered in another system such as when registering a resident's card at the office 3, and the verification processing is performed between the other system. When the collation result is OK, a high added-value personal identification system is obtained that improves the service such as increasing the access authority of the authenticated person according to the level of the collation index. The level of the verification index is determined according to the authentication system (government> license renewal office> post office> bank, etc.), and the access authority is changed. Further, the access authority is increased as the number of systems that are authenticated is larger.
[0053]
【The invention's effect】
As described above, the personal identification system according to the present invention has an effect that the access authority can be changed according to the degree of the collation result.
[Brief description of the drawings]
FIG. 1 is a diagram showing a configuration of a personal identification system according to Embodiment 1 of the present invention.
FIG. 2 is a diagram showing a configuration of a registered personal database of the personal identification system according to Embodiment 1 of the present invention.
FIG. 3 is a diagram showing a configuration of a collation index table of the personal identification system according to Embodiment 1 of the present invention.
FIG. 4 is a flowchart showing the operation of the personal identification system according to Embodiment 1 of the present invention.
FIG. 5 is a diagram showing a configuration in which a personal identification system according to Embodiment 2 of the present invention and another system are connected.
FIG. 6 is a diagram showing a configuration of a collation index table of the personal identification system according to Embodiment 2 of the present invention.
FIG. 7 is a diagram showing authentication information of a personal identification system according to Embodiment 2 of the present invention.
[Explanation of symbols]
1 personal identification system, 2 license renewal office, 3 government office, 4 network, 11 controller, 12 fingerprint sensor, 13 numeric keypad, 14 registered personal database, 15, 15A collation index table, 16 communication device, 21 fingerprint collation device, 22 communication Device, 23 authentication information, 31 fingerprint verification device, 32 communication device, 33 authentication information.

Claims (4)

Numeric keypad for entering personal ID number,
A fingerprint sensor for reading the personal fingerprint image;
For each ID number, a registered personal database composed of fingerprint feature points in the registration mode and a matching rate indicating the degree of matching of the fingerprints;
A collation index table for storing a collation index representing the degree of the collation result according to the match rate;
When the personal ID number input by the numeric keypad is in the registered personal database, the matching rate corresponding to the ID number is acquired from the registered personal database, and the acquired matching rate is obtained by referring to the verification index table. A matching index is obtained, access authority is determined according to the obtained matching index, a feature point is extracted from a fingerprint image read by the fingerprint sensor, and is compared with the feature point acquired from the registered personal database. A personal identification system comprising: a controller for updating a matching rate of a registered personal database. The matching rate stored in the registered personal database is composed of the most recent data at the time of matching,
2. The personal identification system according to claim 1, wherein the update of the match rate is performed by deleting the oldest data and storing the newest data when the collation result is OK. Numeric keypad for entering personal ID number,
A fingerprint sensor for reading the personal fingerprint image;
A registered personal database consisting of authentication information of another system for each ID number;
A collation index table for storing a collation index representing the degree of the collation result according to the authentication information;
A communication device for communicating with another system that performs fingerprint verification processing through a network;
When the personal ID number input by the numeric keypad is in the registered personal database, the authentication information corresponding to the ID number is acquired from the registered personal database, and the acquired authentication information is referred to the verification index table. A matching index is obtained, access authority is determined according to the obtained matching index, a feature point is extracted from the fingerprint image read by the fingerprint sensor, and is transmitted to the other system by the communication device. A personal identification system comprising: a controller that updates authentication information in the registered personal database with authentication information according to a verification result sent from the system. 4. The personal identification system according to claim 1, wherein the controller sets the access authority high when the collation index is high.

Images