JP6360304B2 - Authentication database management method, authentication database management apparatus, and authentication database management program - Google Patents

Description

  According to the present invention, partial image data (for example, partial image data including a face portion) extracted from image data captured by an imaging device such as a camera is used. The present invention relates to an authentication database management method, an authentication database management apparatus, and an authentication database management program that are managed in association with user identification information (hereinafter referred to as “user ID”).

  Conventionally, ID cards (Identity Cards) such as membership cards and employee ID cards have been issued to users who are subject to authentication, and the user ID recorded on the ID card at the time of each user's entry / exit is read with a reader / writer. A personal authentication system that performs personal authentication by reading is known. Also, a personal authentication technique for performing personal authentication using a user's fingerprint or the like is known in order to deal with fraud such as forgery of the ID card.

  However, when the above personal authentication technology is used, every time a user is authenticated, the user must be stopped and a fingerprint or the like must be collected, which is not preferable from the viewpoint of user convenience. For this reason, recently, face authentication technology that can perform personal authentication without stopping a walking user has attracted attention. For example, in Patent Document 1, the feature amount of the user's face image data is registered as dictionary information in advance, and when the walking user approaches the camera, the user's face portion is captured by the camera. A technique is disclosed in which face image data is acquired, and the user's face authentication is performed by comparing the feature amount of the acquired user's face image data with the contents of dictionary information.

  However, according to the conventional face authentication system represented by this Patent Document 1, since the user's face image data must be registered in the face authentication database in advance, it is a burden on the user himself and the face authentication database operator. Result. This is because it takes time for the user and the operator to register the face image data obtained by capturing the face portion in the face authentication database, and the operator needs to manually edit the face image data. In particular, since the human face has the property of changing over time, the above-mentioned burden is periodically generated.

  For this reason, in Patent Document 2, when a card reader and a camera are installed near the entrance and an ID card to which a user ID is assigned is read by the card reader, the face of the person reflected in the camera An entrance / exit management device configured to automatically register image data in a face authentication database in association with a user ID is disclosed. If this patent document 2 is used, if face image data of a user is registered in association with a user ID only for the first time, the user can pass through the doorway without performing an ID card reading operation for the second and subsequent times. In addition, since the user's face image data is automatically registered in the face authentication database, the burden on the user and the operator can be reduced.

JP 2009-104599 A JP 2005-146709 A

  However, when the conventional technique represented by the above-mentioned Patent Document 2 is used, there arises a problem of erroneous registration in which the face of another person is erroneously registered. For example, when a plurality of persons appear on the camera when reading an ID card, the face image data of a person different from the original user is associated with the user ID, which may cause erroneous registration.

  If the misregistered face image data is used at the time of authentication, it causes misauthentication and causes a decrease in authentication accuracy. In order to avoid erroneous registration, it may be possible to tighten the registration conditions. However, if the registration conditions are tightened, the face image data to be registered is reduced, so that the database construction is delayed. That is, it is difficult to uniquely determine the severity of registration conditions because the database construction speed and the risk of erroneous registration have a trade-off relationship.

  Furthermore, even if the conditions are stricter, it is difficult to completely eliminate misregistration of another person's face. Once erroneous registration occurs, the prior art has a large work load because the administrator must manually delete the erroneously registered face image data.

  For these reasons, when constructing an authentication database, how to eliminate the problem of erroneous registration has become an important issue.

  The present invention has been made to solve the above-described problems of the prior art, and provides an authentication database management method, an authentication database management device, and an authentication database management program capable of solving the problem of erroneous registration in an authentication database. The purpose is to provide.

In order to solve the above-described problems and achieve the object, an invention according to claim 1 is an authentication database that stores user identification information for uniquely identifying a user and registered image data of the user in association with each other. An authentication database management method for managing, using a user identification information acquisition step for acquiring the user identification information, and an acquisition identification information that is a user identification information acquired by the user identification information acquisition step, A maturity level acquisition step of acquiring from the authentication database a maturity level that is associated with the acquired identification information together with the registered image data and indicates an evaluation of a registration state of the registered image data; The registered image data stored in the database is collated to correspond to the registered image data similar to the input image data. And image authentication step of outputting the user identity that is as image authentication identifying information, using at least the maturity, further use of the result of comparison between the acquired identification information and the image authentication identification information by the maturity value A database update step of updating the authentication database by registering the input image data as new registered face image data in association with the acquired identification information when a predetermined condition is satisfied. .

The invention according to claim 2 is the invention according to claim 1, wherein in the database update step, the maturity of the acquired identification information is within a range from a first maturity threshold to a second maturity threshold. If the acquired identification information matches the image authentication identification information, the input image data is registered as new registered face image data, and the maturity level of the acquired identification information is a first maturity threshold value. In the range of the second maturity threshold and the acquired identification information and the image authentication identification information do not match, the similarity between the input image data and the registered image data is equal to or less than the similarity threshold The input image data is registered as new registered face image data on the condition that

Further, in the invention described in claim 3, in the invention described in claim 2 , in the database update step, when the maturity level of the acquired identification information is equal to or less than the second maturity threshold value, the image is updated. Regardless of whether or not the authentication identification information matches the acquired identification information, the input image data is registered as new registered image data in association with the acquired identification information.

The invention according to claim 4 is the invention according to any one of claims 2 to 3, wherein in the database update step, the maturity of the acquired identification information is larger than the first maturity threshold. In the case, the acquired identification information and the image authentication identification information match, and the similarity between the input image data and the registered image data is greater than a similarity threshold value. It is characterized by registration.

The invention according to claim 5 is the invention according to any one of claims 1 to 4 , wherein the maturity is calculated using a registration record of the registered image data and / or a use record in authentication. It is characterized by being evaluated value.

The invention according to claim 6 is the invention according to any one of claims 1 to 5 , wherein the authentication database stores an image of the face portion of the user as registered image data, and the image The authentication step uses a partial image obtained by detecting a face portion from an image captured by the imaging device as the input image data.

Further, in the invention according to claim 7 , in the invention according to claim 6 , in the image authentication step, the input image data is respectively obtained from a plurality of images obtained by the imaging device continuously imaging a moving person. It is characterized by detecting.

The invention according to claim 8 is the invention according to any one of claims 1 to 7 , wherein the user identification information acquisition step reads and acquires the user identification information from a predetermined recording medium. It is characterized by doing.

Further, an invention according to claim 9, comprising an authentication database management apparatus which manages uniquely identifying user identification information user, the authentication database in association with the registered image data of a user, wherein The authentication database manages the maturity indicating the evaluation of the registration state of the registered image data in association with the user identification information , and manages the user identification information acquiring means for acquiring the user identification information, and imaging by the imaging device An image for collating the inputted image data and the registered image data stored in the authentication database and outputting user identification information associated with the registered image data similar to the input image data as image authentication identification information authentication means, the maturity associated with the acquired identification information is user identification information acquired by said user identifying information acquisition means small Ku and also used, the case by the maturity value satisfies a predetermined condition using further result of comparison between the acquired identification information and the image authentication identification information, the input image data as a new registered face image data Database updating means for updating the authentication database by registering in association with acquired identification information is provided.

The invention according to claim 10 is an authentication database management program for managing an authentication database for storing user identification information for uniquely identifying a user and registered image data of the user in association with each other. The user identification information acquisition procedure for acquiring the user identification information and the acquisition identification information that is the user identification information acquired by the user identification information acquisition procedure are used together with the registered image data. The maturity acquisition procedure for acquiring the maturity indicating the evaluation of the registration state of the registered image data from the authentication database and the input image data captured by the imaging device and the registered image data stored in the authentication database are collated Process the user identification information associated with the registered image data similar to the input image data into the image authentication identification information And image authentication procedure for and outputting, using at least the maturity, the case by the maturity value satisfies a predetermined condition using further result of comparison between the acquired identification information and the image authentication identification information, wherein The computer is caused to execute a database update procedure for updating the authentication database by registering the input image data as new registered face image data in association with the acquired identification information .

According to the present invention, the user identification information is acquired as the acquisition identification information, the maturity indicating the evaluation of the registration state of the registered image data with respect to the acquisition identification information is acquired, and the input image data captured by the imaging device The registered image data stored in the authentication database is collated, and user identification information associated with registered image data similar to the input image data is output as image authentication identification information. When at least a maturity level is used and a predetermined condition for further using the comparison result between the image authentication identification information and the acquired identification information is satisfied depending on the value of the maturity level , the input image data is set as new registered face image data. The authentication database is updated by registering in association with the acquired identification information . With this configuration, the problem of erroneous registration can be solved.

FIG. 1 is an explanatory diagram for explaining additional registration of face image data according to the first embodiment. FIG. 2 is a block diagram illustrating an internal configuration of the entrance / exit management device according to the first embodiment. FIG. 3 is an explanatory diagram for explaining data stored in the storage unit of the entry / exit management device shown in FIG. 2. FIG. 4 is a flowchart showing a process procedure of additional registration by the entrance / exit management device shown in FIG. FIG. 5 is a flowchart showing a gate control processing procedure performed by the entrance / exit management device shown in FIG. FIG. 6 is an explanatory diagram for explaining deletion of erroneously registered registered face image data according to the second embodiment. FIG. 7 is a block diagram illustrating an internal configuration of the entrance / exit management device according to the second embodiment. FIG. 8 is an explanatory diagram for explaining data stored in the storage unit of the entry / exit management device shown in FIG. 7. FIG. 9 is an explanatory diagram for explaining a case where no deletion chain occurs. FIG. 10 is an explanatory diagram for explaining a case in which a deletion chain occurs. FIG. 11 is a flowchart showing a processing procedure for deleting erroneous registration data by the entrance / exit management device shown in FIG.

  Exemplary embodiments of an authentication database management method, an authentication database management apparatus, and an authentication database management program according to the present invention will be described below in detail with reference to the accompanying drawings. In the following first and second embodiments, a case where the authentication database management method, the authentication database management device, and the authentication database management program according to the present invention are applied to an entrance / exit management device will be described.

  In the first embodiment, additional registration of face image data using ID reading from a card and image authentication will be described. FIG. 1 is an explanatory diagram for explaining additional registration of face image data according to the first embodiment.

  First, the card reader 10 is installed in front of the gate device 30 that is subject to entrance / exit management. The camera 20 is installed at a position where a person approaching the gate device 30 and the card reader 10 can be imaged.

  As shown in FIG. 1, when a user registered in advance approaches the card reader 10 and holds the ID card over the card reader 10, the card reader 10 reads the user ID from the ID card. FIG. 1 shows a case where the read user ID is “0001”.

  The camera 20 continuously captures images of users approaching the card reader 10. The entrance / exit management device 40 uses the output of the camera 20 to detect face images from a plurality of images with different imaging timings.

  The entrance / exit management device 40 uses the detected face image as input face image data, and performs an authentication process using the face authentication database 42a. The face authentication database 42a is a database in which the maturity level and registered face image data are associated with the user ID.

  The maturity level is an evaluation value obtained by evaluating the registration state of the registered face image data for the user ID. This maturity level is calculated by using the registration results of registered face image data (the number of registrations, the number of registrations, etc.) and the use results in authentication. For example, when the registered number of registered face image data is less than 10% of the upper limit number determined for the user ID, the maturity is “C”, and the maturity is 10% or more and less than 30%. When “B” is 30% or more, the maturity is “A”. In the following description, the maturity level associated with the user ID is referred to as a “user ID maturity level”.

  In the authentication process, each registered face image data registered in the face authentication database 42a is collated with the input face image data, and the user ID of the registered face image data having the highest similarity is set as the authentication ID.

  The entrance / exit management device 40 determines whether or not the user ID read by the card reader 10 matches the authentication ID, and whether to additionally register the input face image data as registered face image data based on the determination result. Decide whether or not.

  The criteria for additional registration are defined by the registration processing table 42b. Specifically, if the maturity of the read user ID is “A”, the read user ID matches the authentication ID, and the similarity at the time of authentication is a predetermined threshold (first registration) Only when it is equal to or greater than (threshold), additional registration is performed as registered face image data of the user ID that has read the input face image data.

If the read user ID has a maturity level of “B” and the read user ID matches the authentication ID, the user ID that has read the input face image data regardless of the similarity at the time of authentication. Are additionally registered as registered face image data. On the other hand, when the read user ID and the authentication ID do not match, the use of reading the input face image data only when the similarity at the time of authentication is less than a predetermined threshold (second registration threshold) Is additionally registered as registered face image data of the person ID. Here, the case where the degree of similarity at the time of authentication is low corresponds to the case where the registered face image data with the most similar input face image data is associated with another user ID, but the degree of similarity is low. . When the read user ID has a maturity level of “B”, such input face image data is additionally registered. Note that the second registration threshold may be the same as the first registration threshold. In the first embodiment, when the second registration threshold and the first registration threshold are the same, the case where the similarity exceeds the registration threshold is “high”, and the similarity is equal to or lower than the registration threshold. Is the similarity “low”.

  If the maturity of the read user ID is “C”, the input face image data regardless of whether or not the read user ID matches the authentication ID, and regardless of the similarity at the time of authentication. Is additionally registered as registered face image data of the user ID that has read.

  That is, according to the registration processing table 42b, when the maturity level is low, priority is given to increasing the registered face image data by loosening the additional registration condition, and the higher the maturity level, the stricter the additional registration condition. Careful selection of data that contributes to improved accuracy.

  In the example of FIG. 1, the user ID read by the card reader 10 is “0001”, and the maturity of the user ID “0001” is “B”. Therefore, if the authentication ID of the input face image data is “0001”, the input face image data is additionally registered as registered face image data of the user ID “0001” regardless of the similarity. If the authentication ID of the input face image data is “0002” and the similarity is low, the input face image data is additionally registered as registered face image data of the user ID “0001”. When the authentication ID of the input face image data is “0002” and the similarity is high, the registered face image data of the input face image data is not additionally registered.

  As described above, the entrance / exit management device 40 according to the first embodiment reads the user ID by the card reader 10, obtains the authentication ID by image authentication, compares the ID, and matures the read user ID. Depending on the degree, it is decided whether or not to register additional input face image data. Therefore, priority is given to increasing the number of registered face image data when the maturity level is low, and misregistration is strictly prevented as the maturity level increases. Thus, a highly accurate face authentication database can be constructed at an early stage.

  Next, the internal configuration of the entrance / exit management device 40 will be described. FIG. 2 is a block diagram showing an internal configuration of the entrance / exit management device 40. As shown in FIG. 2, the entrance / exit management device 40 is connected to the card reader 10, the camera 20, and the gate device 30. The entrance / exit management device 40 includes an input / output unit 41, a storage unit 42, and a control unit 43.

  The card reader 10 is a device for reading a user ID from an ID card. As the ID card, any recording medium such as a magnetic card or a short-distance wireless communication type card can be used regardless of the recording or reading / writing method. Further, it may be a recording medium having a shape other than the card.

  The camera 20 is an image pickup device including a CCD (Charge Coupled Device) element that picks up an image of a user and outputs the image to the entrance / exit management device 40. The camera 20 is set in advance to an angle of view that can capture the face portion of the user on the way to the card reader 10 and the gate device 30. The gate device 30 opens and closes under the control of the entry / exit management device 40.

  The input / output unit 41 is an input / output device group such as a liquid crystal panel, a keyboard, and a mouse. The storage unit 42 is a storage device such as a hard disk device or a nonvolatile memory, and stores a face authentication database 42a and a registration processing table 42b.

  The control unit 43 is a control unit that controls the entire entrance / exit management device 40, and includes a user ID acquisition unit 43a, a face image detection unit 43b, an authentication processing unit 43c, a gate control unit 43d, a registration processing unit 43e, and a selection processing unit. 43f. Actually, programs corresponding to these functional units are stored in a ROM (Read Only Memory) or a non-volatile memory (not shown), and these programs are loaded into a CPU (Central Processing Unit) and executed. The user ID acquisition unit 43a, the face image detection unit 43b, the authentication processing unit 43c, the gate control unit 43d, the registration processing unit 43e, and the selection processing unit 43f execute corresponding processes.

  The user ID acquisition unit 43a is a processing unit that acquires the user ID read by the card reader 10 from the ID card. The face image detection unit 43b uses the output of the camera 20 to detect a face image from a plurality of images having different imaging timings. Specifically, the face image detection unit 43b detects a face image existing in the image by using a template (mask pattern) indicating a general outline of a human face and shifting and matching the template. In addition to such template matching, various known face detection algorithms (image processing techniques) can be used. The face image detection unit 43b outputs the detected face image as input face image data.

  The authentication processing unit 43c collates the input face image data output from the face image detection unit 43b with each of the registered face image data registered in the face authentication database 42a, so that the registered face image data with the highest similarity is obtained. The user ID is output as the authentication ID.

  The gate control unit 43d instructs the gate device 30 to open the gate when either the authentication by the ID card or the authentication by the face image is established. Specifically, the gate control unit 43d opens the gate with respect to the gate device 30 when the user ID read by the user ID acquisition unit 43a is the user ID registered in the face authentication database 42a. Instruct. The gate control unit 43d also instructs the gate device 30 to open the gate when the authentication processing unit 43c outputs the authentication ID and the similarity is equal to or higher than the authentication threshold.

  The registration processing unit 43e is a processing unit that performs additional registration processing according to the registration processing table 42b when the user ID is acquired by the user ID acquisition unit 43a and the input face image data is output by the face image detection unit 43b. is there.

  The sorting processing unit 43f is a processing unit that sorts registered face image data. Specifically, the selection processing unit 43f deletes the registered face image data for a user ID having a maturity level A that has been registered for a predetermined time or more and has little contribution to authentication. Select registered face image data.

  Next, a specific example of data stored in the storage unit 42 of the entrance / exit management device 40 will be described. FIG. 3 is an explanatory diagram for explaining data stored in the storage unit 42 of the entrance / exit management device 40.

  As shown in FIG. 3, the face authentication database 42a is a database in which a maturity level, registered face image data, registration date and time, the number of times of authentication use, and a cumulative authentication score are associated with a user ID.

  The registration date / time, the number of times of authentication use, and the cumulative authentication score are associated with each registered face image data. The registration date / time indicates the date / time when the registered face image data was registered. The number of times of authentication use indicates the number of times that the similarity with the registered face image data is maximized at the time of authentication. The cumulative authentication score is a value obtained by adding the degree of similarity every time the degree of similarity with the registered face image data becomes maximum at the time of authentication.

  This cumulative authentication score becomes a larger value as the number of times of authentication use is larger and as the degree of similarity is higher, and thus becomes an index of the magnitude of contribution to authentication. Further, by dividing the cumulative authentication score by the number of times of authentication use, an average authentication score that is an average similarity when the similarity with the registered face image data is maximized can be obtained. Based on the average authentication score, it is possible to evaluate the accuracy of authentication when the registered face image data is used.

  For example, when the selection processing unit 43f selects the registered face image data, it is only necessary to delete the registered face image data that has passed a predetermined time from the registration date and the cumulative authentication score is equal to or lower than the selection threshold. Instead of the cumulative authentication score, whether or not deletion can be performed may be determined based on an average authentication score.

  Further, the cumulative authentication score and the average authentication score may be used for determination of maturity. By adding the cumulative authentication score and the average authentication score, the maturity can be determined in consideration of not only the number of registered face image data but also the quality thereof.

  The face authentication database 42a shown in FIG. 3 shows a state in which the maturity “B”, the registered face image data “G001001.jpg”, and the registered face image data “G001002.jpg” are associated with the user ID “0001”. Show. The registered face image data “G001001.jpg” has a registration date of “2011/05/02 11:42”, an authentication usage count of “9”, and a cumulative authentication score of “540”. The registration date and time of the registered face image data “G001002.jpg” is “2011/05/02 11:42”, the number of times of authentication use is “8”, and the cumulative authentication score is “640”.

  In the face authentication database 42a shown in FIG. 3, the maturity “A”, the registered face image data “G002001.jpg” and the registered face image data “G002002.jpg” are associated with the user ID “0002”. Indicates the state. The registration date and time of the registered face image data “G002001.jpg” is “2011/10/10 15:10”, the number of times of authentication use is “4”, and the cumulative authentication score is “320”. The registration date and time of the registered face image data “G002002.jpg” is “2011/10/11 09:30”, the number of times of authentication use is “7”, and the cumulative authentication score is “630”.

  As illustrated in FIG. 3, the registration processing table 42 b is a table that determines whether additional registration is possible according to the ID comparison result, the similarity of the authentication ID, and the maturity of the user ID. Here, as the maturity of the user ID, the maturity associated with the user ID read by the card reader 10 from the ID card is used. Specifically, if the maturity level of the user ID is “A”, the input is performed only when the read user ID matches the authentication ID and the similarity at the time of authentication is “high”. It is additionally registered as registered face image data of the user ID that has read the face image data.

  If the maturity level of the user ID is “B”, if the read user ID matches the authentication ID, registration of the user ID that read the input face image data regardless of the similarity at the time of authentication Additional registration as face image data. On the other hand, when the read user ID and the authentication ID do not match, the registered face image data of the user ID that has read the input face image data is used only when the similarity at the time of authentication is “low”. Register additional.

  If the maturity of the user ID is “C”, the input face image data is read regardless of whether or not the read user ID matches the authentication ID, and regardless of the similarity at the time of authentication. Are additionally registered as registered face image data of the user ID.

  Next, an additional registration processing procedure performed by the entry / exit management device 40 will be described. FIG. 4 is a flowchart showing the additional registration processing procedure performed by the entrance / exit management device 40. First, the user ID acquisition unit 43a acquires the user ID read by the card reader 10 from the ID card (step S101). In addition, the user ID acquisition unit 43a acquires the maturity level of the acquired user ID from the face authentication database 42a (step S102).

  The face image detection unit 43b uses the output of the camera 20 to detect a face image from a plurality of images having different imaging timings, and outputs the detected face image data as input face image data (step S103). The registration processing unit 43e selects one unprocessed input face image data (step S104). The registration processing unit 43e determines whether or not the maturity level of the user ID is “A” (step S105). If the maturity level is “A” (step S105; Yes), the process proceeds to step S106. .

  In step S106, the authentication processing unit 43c collates the input face image data and each registered face image data registered in the face authentication database 42a, and obtains the user ID of the registered face image data having the highest similarity. Output as authentication ID.

  After step S106, the registration processing unit 43e determines whether the user ID acquired in step S101 matches the authentication ID (step S107). If the IDs match (step S107; Yes), it is determined whether or not the similarity of the authentication ID obtained in step S106 is “high” (step S108). If the similarity is “high” (step S108; Yes), the input face image data is additionally registered as registered face image data of the user ID acquired in step S101 (step S109).

  If the maturity is not “A” (step S105; No), the registration processing unit 43e determines whether the maturity of the user ID is “B” (step S111), and the maturity is “B”. "(Step S111; Yes), the process proceeds to step S112.

  In step S112, the authentication processing unit 43c collates the input face image data and each registered face image data registered in the face authentication database 42a, and obtains the user ID of the registered face image data having the highest similarity. Output as authentication ID.

  After step S112, the registration processing unit 43e determines whether or not the user ID acquired in step S101 matches the authentication ID (step S113). If the IDs match (step S113; Yes), the input face image data is additionally registered as registered face image data of the user ID acquired in step S101 (step S114). If the IDs do not match (step S113; No), the registration processing unit 43e determines whether or not the similarity of the authentication ID obtained in step S112 is “high” (step S115). If the similarity is not “high” (step S115; No), the input face image data is additionally registered as registered face image data of the user ID acquired in step S101 (step S114).

  When the maturity level is not “B” (step S111; No), that is, when the maturity level is “C”, the registration processing unit 43e registers the registered face image data of the user ID acquired in step S101. Are additionally registered (step S116).

  After the input face image data is registered in step S109, step S114, or step S116, the process proceeds to step S110. If the IDs do not match in step S107 (step S107; No), the similarity is “low” in step S108 (step S108; No), or the similarity is “high” in step S115 (step S108). Also in S115; Yes, the process proceeds to step S110.

  In step S110, the registration processing unit 43e determines whether or not all input face image data has been processed. If unprocessed input face image data remains (step S110; No), the process proceeds to step S104. If all input face image data has been processed (step S110; Yes), additional registration processing is performed. Exit.

  Next, the process procedure of the gate control by the entrance / exit management device 40 will be described. FIG. 5 is a flowchart showing a gate control processing procedure performed by the entrance / exit management device 40. The gate control unit 43d determines whether the user ID acquisition unit 43a has acquired a user ID from the ID card (step S201).

  If the user ID acquisition unit 43a has acquired a user ID (step S201; Yes), the gate control unit 43d has the acquired user ID registered in the face authentication database 42a. It is verified whether or not (step S202). If it is not a registered user ID (step S202; No), the gate control unit 43d outputs an authentication error to notify the user (step S203), and ends the gate control process. On the other hand, if it is a registered user ID (step S202; Yes), the gate control unit 43d instructs the gate device 30 to open the gate (step S204), and ends the gate control process.

  If the user ID acquisition unit 43a has not acquired the user ID (step S201; No), the gate control unit 43d determines whether the face image detection unit 43b has detected a face image from the output of the camera 20. (Step S205). If the face image detection unit 43b has not detected a face image (step S205; No), the gate control unit 43d ends the gate control process.

  If the face image detection unit 43b detects a face image (step S205; Yes), the authentication processing unit 43c includes input face image data including the detected face image and a registered face image registered in the face authentication database 42a. Each data is collated, and the user ID of the registered face image data having the highest similarity is output as an authentication ID (step S206). Further, the authentication processing unit 43c determines whether or not the similarity of the registered face image data having the highest similarity is equal to or higher than an authentication threshold. If the authentication is successful (step S207; Yes), the gate control unit 43d instructs the gate device 30 to open the gate (step S204), and ends the gate control process. If the authentication is not successful (step S207; No), the gate control unit 43d ends the gate control process.

  As described above, the entrance / exit management device 40 according to the first embodiment reads the user ID by the card reader 10, obtains the authentication ID by image authentication, compares the ID, and the read user ID. Depending on the maturity level, it will be decided whether or not to register additional input face image data. If the maturity level is low, priority will be given to increasing the registered face image data. It is possible to construct a highly accurate face authentication database at an early stage while strictly preventing it.

  In the second embodiment, deletion of erroneously registered registered face image data will be described. FIG. 6 is an explanatory diagram for explaining deletion of erroneously registered registered face image data according to the second embodiment.

  First, the card reader 10 is installed in front of the gate device 30 that is subject to entrance / exit management. The camera 20 is installed at a position where a person approaching the gate device 30 and the card reader 10 can be imaged.

  As shown in FIG. 6, when a user registered in advance approaches the card reader 10 and holds the ID card over the card reader 10, the card reader 10 reads the user ID from the ID card. FIG. 6 shows a case where the read user ID is “0001”.

  The camera 20 continuously captures images of users approaching the card reader 10. The entrance / exit management device 140 uses the output of the camera 20 to detect face images from a plurality of images having different imaging timings.

  The entrance / exit management device 140 uses the detected face image as input face image data, and performs authentication processing using the face authentication database 142a. The face authentication database 142a is a database in which registered face image data and the like are associated with a user ID. Each registered face image data is associated with a match count NT and a mismatch count NF.

  In the authentication process, each registered face image data registered in the face authentication database 142a is collated with the input face image data, and the user ID of the registered face image data having the highest similarity is set as the authentication ID.

  The entrance / exit management device 140 determines whether the user ID read by the card reader 10 and the authentication ID match, and if the IDs match, the similarity to the input face image data is the highest. Add 1 to the match count NT of the registered face image data. If the IDs do not match, 1 is added to the mismatch count NF of the registered face image data having the highest similarity with the input face image data. Then, the registered face image data in which the mismatch count NF is larger than the match count NT is deleted.

  The registered face image data having a large mismatch count is not similar to the registered user ID but is highly similar to the registered face image data registered in another user ID. In other words, it is highly likely that an inappropriate face image has been registered by mistake. The registered face image data registered in error in this way causes a decrease in authentication accuracy. Therefore, the registered face image data having a large mismatch count is deleted.

  In the example of FIG. 6, the user ID read by the card reader 10 is “0001”. Therefore, if the authentication ID of the input face image data is “0001”, 1 is added to the match count NT of the registered face image data having the highest similarity. If the authentication ID of the input face image data is “0002”, 1 is added to the mismatch count NF of the registered face image data having the highest similarity.

  As described above, the entrance / exit management device 140 according to the second embodiment reads the user ID by the card reader 10, obtains the authentication ID by image authentication, and matches the registered face image data based on the comparison result of the ID. And the mismatch count are added. Since the registered face image data whose mismatch count NF is larger than the match count NT is deleted, erroneously registered registered face image data can be automatically deleted, which can contribute to improvement in authentication accuracy.

  Next, the internal configuration of the entrance / exit management device 140 will be described. FIG. 7 is a block diagram showing an internal configuration of the entrance / exit management device 140. As shown in FIG. 7, the entrance / exit management device 140 is connected to the card reader 10, the camera 20, and the gate device 30. Moreover, the entrance / exit management device 40 includes an input / output unit 41, a storage unit 42, and a control unit 143 therein.

  The storage unit 42 is different from the first embodiment in that it stores not the face authentication database 42a and the registration processing table 42b but the face authentication database 142a. The control unit 143 is different from the first embodiment in that the control unit 143 includes an erroneous registration deletion processing unit 143g instead of the registration processing unit 43e and the selection processing unit 43f. Since other configurations and operations are the same as those of the entrance / exit management device 40 shown in the first embodiment, the same components are denoted by the same components and the description thereof is omitted.

  As shown in FIG. 8, the face authentication database 142a is a database in which registered face image data, a match count NT, and a mismatch count NF are associated with a user ID. Specifically, the registered face image data “G001001.jpg” and the registered face image data “G001002.jpg” are associated with the user ID “0001”. The registered face image data “G001001.jpg” has a match count NT of “9” and a mismatch count NF of “1”. The registered face image data “G001002.jpg” has a match count NT of “8” and a mismatch count NF of “2”.

  Further, the face authentication database 142a shown in FIG. 8 shows a state where the registered face image data “G002001.jpg” and the registered face image data “G002002.jpg” are associated with the user ID “0002”. The registered face image data “G002001.jpg” has a match count NT of “4” and a mismatch count NF of “6”. The registered face image data “G002002.jpg” has a match count NT of “7” and a mismatch count NF of “3”.

  The erroneous registration deletion processing unit 143g is a processing unit that deletes erroneously registered registered face image data. Specifically, when the user ID is read by the card reader 10 and an authentication ID is obtained by image authentication, the IDs are compared, and the match count NT and the mismatch count NF of the registered face image data are calculated based on the comparison result. to add. Then, the registered face image data in which the mismatch count NF is larger than the match count NT is deleted.

  Here, the deletion of registered face image data will be further described. The erroneous registration deletion processing unit 143g uses the registered face image data in which the mismatch count NF is larger than the match count NT as deletion target data, and calculates the similarity between the deletion target data and each user ID.

  When the deletion target data is similar to a plurality of user IDs, the deletion target data is deleted from the face authentication database 142a. On the other hand, when the deletion target data shows a high degree of similarity with a specific user, the deletion target data is moved to the user ID.

  For example, when any of registered face image data with the user ID “0001” is the deletion target data, the similarity with the other registered face image data with the user ID “0001” of the deletion target data is 40, The similarity with the registered face image data with the user ID “0002” is 20, the similarity with the registered face image data with the user ID “0003” is 20, and the similarity with the registered face image data with the user ID “0004”. Is 20, the deletion target data is highly similar to various users, and is deleted from the face authentication database 142a.

  On the other hand, if the similarity of the deletion target data with the registered face image data of the user ID “0001” is 40 and the similarity with the registered face image data of the user ID “0002” is 60, the deletion source data The degree of similarity with the user ID “0002” is higher than the user ID “0001” and is not similar to other users. Therefore, the deletion target data is deleted from the user ID “0001” and moved to the user ID “0002”.

  9 and 10 are explanatory diagrams for explaining a deletion chain. Whether the erroneous registration deletion processing unit 143g deletes the deletion target data in a chained manner depending on how similar the registered face image data associated with the user ID of the deletion source are. Decide whether or not.

  Specifically, the misregistration deletion processing unit 143g calculates the degree of similarity for a plurality of registered face image data associated with the same user ID, and the degree of similarity becomes a predetermined value (for example, an authentication threshold) or more. Link between registered face image data. If there is isolated registered face image data due to deletion of the deletion target data, the isolated registered face image data is also deleted. This is because the isolated registered face image data has a high degree of similarity with the deletion target data, and thus has a high possibility of being registered by mistake.

  FIG. 9 shows a case where no deletion chain occurs. Even if the registered face image data is linked to the deletion target data, if the registered face image data is linked to other registered face image data, only the deletion target data needs to be deleted. . This is because the registration face image data is not isolated by such deletion.

  Specifically, the registered face image data “G001003.jpg” is linked to the registered face image data “G001001.jpg” and the registered face image data “G001002.jpg”. The registered face image data “G001001.jpg” and the registered face image data “G001002.jpg” are linked. For this reason, even if the registered face image data “G001003.jpg” is the data to be deleted, the registered face image data “G001001.jpg” and the registered face image data “G001002.jpg” are not isolated. Therefore, only the registered face image data “G001003.jpg” is deleted.

  In addition, when there is only one link between the deletion target data and the other registered face image data, that is, when the deletion target data is located at the end of the link relationship, only the deletion target data is deleted.

  Specifically, the registered face image data “G001004.jpg” is linked only to the registered face image data “G001001.jpg”. Therefore, when the registered face image data “G001004.jpg” is to be deleted, only the registered face image data “G001004.jpg” is deleted.

  FIG. 10 shows a case where a chain of deletion occurs. As shown in FIG. 10, when there is isolated registered face image data within the same user ID due to deletion of the deletion target data, the isolated registered face image data is also deleted in conjunction with the deletion of the deletion target data. To do.

  Specifically, the registered face image data “G001001.jpg” is linked to the registered face image data “G001002.jpg”, “G001003.jpg” and the registered face image data “G001004.jpg”. Also, the registered face image data “G001002.jpg” and the registered face image data “G001003.jpg” are linked. If the registered face image data “G001001.jpg” is to be deleted, the registered face image data “G001002.jpg” and the registered face image data “G001003.jpg” are not isolated, but the registered face image data “G001004.jpg” Isolated. Therefore, the registered face image data “G001004.jpg” is also deleted in conjunction with the deletion of the registered face image data “G001001.jpg”.

  Next, a processing procedure for deleting erroneous registration data by the entrance / exit management device 140 will be described. FIG. 11 is a flowchart showing a processing procedure for deleting erroneous registration data by the entrance / exit management device 140. First, the user ID acquisition unit 43a acquires the user ID read by the card reader 10 from the ID card (step S301).

  The face image detection unit 43b uses the output of the camera 20 to detect face images from a plurality of images having different imaging timings, and outputs the detected face images as input face image data (step S302). The erroneous registration deletion processing unit 143g selects one unprocessed input face image data (step S303). The authentication processing unit 43c collates the input face image data selected in step S303 with each registered face image data registered in the face authentication database 42a, and uses the registered face image data with the highest similarity. An authentication process for outputting the ID as an authentication ID is performed (step S304).

  The erroneous registration deletion processing unit 143g determines whether or not the user ID acquired in step S301 matches the authentication ID (step S305). If the IDs match (step S305; Yes), the erroneous registration deletion processing unit 143g adds 1 to the match count NT of the registered face image data having the highest similarity to the input face image data (step S306). .

  If the IDs do not match (step S305; No), the erroneous registration deletion processing unit 143g adds 1 to the mismatch count NF of the registered face image data having the highest similarity with the input face image data (step S308). . Then, it is determined whether or not the mismatch count NF of the registered face image data is larger than the match count NT (step S309).

  If the mismatch count NF is greater than the match count NT (step S309; Yes), the erroneous registration deletion processing unit 143g deletes the registered face image data as deletion target data (step S310). In step S310, it is determined whether or not deletion target data is to be moved to another user ID and deletion chain is necessary, and movement or chaining is performed as necessary.

  After step S306, after step S310, or when the mismatch count NF is equal to or less than the match count NT (step S309; No), the erroneous registration deletion processing unit 143g determines whether all input face image data has been processed. Is determined (step S307). If unprocessed input face image data remains (step S307; No), the process proceeds to step S303, and if all input face image data is processed (step S307; Yes), erroneous registration data. The deletion process ends. The processing procedure of the gate control is the same as that in the first embodiment, and thus the description thereof is omitted.

  As described above, the entrance / exit management device 140 according to the second embodiment reads the user ID by the card reader 10, obtains the authentication ID by image authentication, and compares the registered face image data based on the ID comparison result. The match count NT and the mismatch count NF are added. Since the registered face image data whose mismatch count NF is larger than the match count NT is deleted, erroneously registered registered face image data can be automatically deleted, which can contribute to improvement in authentication accuracy.

  In the second embodiment, the registered face image data is deleted on condition that the mismatch count NF is larger than the match count NT. However, the relationship between the mismatch count NF and the match count NT is appropriately defined and deleted. The conditions can be as follows. For example, the ratio of the mismatch count to the match count may be defined as the deletion condition. Further, a predetermined number of registered face image data having the highest matching count in the same user ID may not be deleted.

  For convenience of explanation, the first embodiment for explaining the additional registration and the second embodiment for explaining the deletion of erroneous registration data are individually described. However, both the additional registration and the deletion of erroneous registration data are both described. It goes without saying that the entry / exit management device may be implemented. In this case, in the entrance / exit management device 40 disclosed in the first embodiment, the face authentication database 42a may be further associated with the match count NT and the mismatch count NF, and the control unit 43 may further include an erroneous registration deletion processing unit 143g. .

  In the first and second embodiments, the case where the present invention is applied to the entrance / exit management device 40 and the entrance / exit management device 140 has been described, but a program for causing a computer to execute the processing units of the control unit 43 and the control unit 143. The present invention may be implemented as

  Moreover, in the said Example 1 and 2, although the case where this invention was applied to the entrance / exit management system was shown, this invention is not limited to this, It can apply to various systems, such as an attendance management system. . Thereby, face authentication can be introduced into entrance / exit management and attendance management. Moreover, you may implement as an apparatus and program which perform only management of a database, without performing entrance / exit management and attendance management.

  In the first and second embodiments, the case where an image of a face portion is used for authentication has been described as an example. However, the present invention is not limited to this, and a partial image other than a human face, The present invention can also be applied when an image, an upper body image, or the like is used for authentication.

  As described above, the authentication database management method, authentication database management device, and authentication database management program according to the present invention are suitable for solving the problem of erroneous registration in the authentication database.

DESCRIPTION OF SYMBOLS 10 Card reader 20 Camera 30 Gate apparatus 40,140 Entrance / exit management apparatus 41 Input / output part 42 Storage part 42a, 142a Face authentication database 42b Registration process table 43, 143 Control part 43a User ID acquisition part 43b Face image detection part 43c Authentication Processing unit 43d Gate control unit 43e Registration processing unit 43f Sorting processing unit 143g Incorrect registration deletion processing unit

Claims (10)

An authentication database management method for managing an authentication database for storing user identification information for uniquely identifying a user and registered image data of the user in association with each other,
A user identification information acquisition step for acquiring the user identification information;
Using the acquired identification information which is the user identification information acquired in the user identification information acquisition step, the maturity indicating the evaluation of the registration status of the registered image data is associated with the acquired identification information together with the registered image data. A maturity obtaining step to obtain from the authentication database;
The input image data captured by the imaging device is collated with the registered image data stored in the authentication database, and the user identification information associated with the registered image data similar to the input image data is displayed as the image authentication identification information. Image authentication step to output as
When at least the maturity level is used, and depending on the value of the maturity level, a predetermined condition for further using a comparison result between the image authentication identification information and the acquired identification information is satisfied, the input image data is newly registered as a face image. A database update step of updating the authentication database by registering it in association with the acquired identification information as data.   In the database update step, when the maturity level of the acquired identification information is within a range from a first maturity level threshold value to a second maturity level threshold value, and the acquired identification information and the image authentication identification information match. The input image data is registered as new registered face image data, and the maturity of the acquired identification information is within a range from a first maturity threshold to a second maturity threshold, and the acquired identification information and the image If the authentication identification information does not match, the input image data is registered as new registered face image data on the condition that the similarity between the input image data and the registered image data is not more than a similarity threshold. The authentication database management method according to claim 1, wherein: In the database update step, when the maturity level of the acquired identification information is equal to or less than the second maturity threshold value, the image authentication identification information and the acquired identification information are matched regardless of whether the acquired identification information matches. 3. The authentication database management method according to claim 2 , wherein the input image data is registered as new registered image data in association with the acquired identification information.
In the database update step, when the maturity level of the acquired identification information is larger than the first maturity level threshold, the acquired identification information and the image authentication identification information match, and the input image data and the registration The authentication database management method according to any one of claims 2 to 3, wherein the input image data is registered on the condition that a similarity with image data is larger than a similarity threshold.   The authentication database management according to any one of claims 1 to 4, wherein the maturity is an evaluation value calculated using a registration record and / or a use record in authentication of the registered image data. Method. The authentication database stores an image of the user's face part as registered image data,
The authentication database management according to any one of claims 1 to 5, wherein the image authentication step uses, as the input image data, a partial image obtained by detecting a face portion from an image captured by the imaging device. Method.   The authentication database management method according to claim 6, wherein in the image authentication step, the input image data is detected from a plurality of images in which the imaging device continuously captures a moving person.   The authentication database management method according to claim 1, wherein the user identification information acquisition step reads and acquires the user identification information from a predetermined recording medium. An authentication database management apparatus that manages an authentication database that stores user identification information that uniquely identifies a user and user registered image data in association with each other,
The authentication database further manages the user identification information in association with a maturity indicating an evaluation of a registration state of the registered image data,
User identification information acquisition means for acquiring the user identification information;
The input image data captured by the imaging device is collated with the registered image data stored in the authentication database, and the user identification information associated with the registered image data similar to the input image data is displayed as the image authentication identification information. Image authentication means for outputting as
At least the maturity level associated with the acquired identification information that is the user identification information acquired by the user identification information acquisition means is used, and depending on the value of the maturity level, the image authentication identification information and the acquired identification information may be compared. Database update means for updating the authentication database by registering the input image data as new registered face image data in association with the acquired identification information when a predetermined condition for further using the result is satisfied. An authentication database management device. An authentication database management program for managing an authentication database for storing user identification information for uniquely identifying a user and registered image data of the user in association with each other,
A user identification information acquisition procedure for acquiring the user identification information;
Using the acquired identification information which is the user identification information acquired by the user identification information acquisition procedure, the maturity indicating the evaluation of the registration status of the registered image data is associated with the acquired identification information together with the registered image data. A maturity acquisition procedure acquired from the authentication database;
The input image data captured by the imaging device is collated with the registered image data stored in the authentication database, and the user identification information associated with the registered image data similar to the input image data is displayed as the image authentication identification information. Image authentication procedure to output as
When at least the maturity level is used, and depending on the value of the maturity level, a predetermined condition for further using a comparison result between the image authentication identification information and the acquired identification information is satisfied, the input image data is newly registered as a face image. An authentication database management program that causes a computer to execute a database update procedure for updating the authentication database by registering it in association with the acquired identification information as data.

Images