JP2007286872A - Passage management system and passage management method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a passage management system and a passage management method for preventing occurrence of a queue due to personal identification without requiring any previous registration of companions even in use by a group for allowing efficient use and for preventing passage of an unauthorized interrupter during the use by a group for ensuring safety. <P>SOLUTION: In use by a group, a storage medium for ID information of a representative person is used in common among the group, and passage intervals of the respective persons are set for performance within a predetermined time. In this way, efficient use is allowed to the companions, and unauthorized interruption is prevented and safety can be ensured. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a traffic management system and a traffic management method for performing authentication of an individual who intends to pass based on ID information and biometric information, identifying a companion, and determining whether or not to pass based on the result.

  In recent years, personal authentication technology using an ID card or the like has been widely used to perform highly safe entrance / exit management in order to ensure the security of a specific facility. The person who has not obtained permission to enter and leave the room is excluded, and only the person who is authenticated by the ID information, that is, registered in advance is permitted to pass.

  A general procedure for personal authentication using ID information is that information recorded on an ID card is obtained by inserting the ID card acquired by the user in advance into an ID card reader attached to the traffic management gate. Is checked against registered personal information. When the match is confirmed, the traffic management gate is controlled to open.

  On the other hand, in the case of a person who does not have permission to enter or leave the room, that is, a person who is not registered, an appropriate ID card cannot be presented and the person cannot pass through the traffic management gate. This is higher in security than the case where a personal identification number or password is used alone, and it is possible to ensure safety.

  However, there is a risk that the ID card is forged or altered, or an unauthorized ID card is used. For this reason, not only a recording medium such as an ID card but also a technique for acquiring the user's biometric information together and collating it with biometric information registered in advance has been developed. This is more secure than personal identification numbers and passwords, and is less likely to be stolen.

  As biometric information, a method of acquiring a face image of a user by photographing, analyzing and analyzing a feature amount, etc., does not cause a physical burden on the user and is easily accepted socially. From the point of view, it is generally used.

  In this way, it is possible to prevent unauthorized persons from passing by authenticating individuals in various ways. On the other hand, a person who wants to pass through the traffic management gate must have an ID card in advance. It is necessary to possess and register personal information, which may be inconvenient and inefficient.

  For example, when a group of a plurality of people is a user, even if the ID card owner guarantees his / her identity, it cannot pass through the traffic management gate unless another accompanying person has an ID card. Accordingly, registration and ID card issuance are also required for the accompanying person, and there is a problem that it takes too much time in the case of a facility that is frequently used in a group. In addition, since personal authentication is performed for all accompanying persons at the time of use, it is conceivable that convenience is reduced such that an order queue is generated.

  In order to deal with such a problem, for example, in Patent Document 1, as a technique for enabling a companion to pass without prior registration, only a representative performs a normal authentication operation, and other companions are representatives. A method has been proposed that allows traffic by the person specified.

In order to allow a companion to pass, the representative presents an ID card held by the representative and obtains a passage permission upon receiving verification of biometric information and the like. Thereafter, when the representative inputs the number of companions using the installed number input button, the gate for blocking the passage can be rotated by the number of persons, and the designated companion can pass.
JP 2003-288625 A

  For example, according to the technique described in Patent Document 1, prior registration for a companion is not necessary, and personal authentication is not performed at the time of use, so that a decrease in convenience such as occurrence of a queue can be suppressed.

  However, since management is performed by the number of people, a gate device capable of managing the number of people is required. There is a possibility that the form and installation location of the apparatus may be limited. In addition, there is a high risk of allowing an interruption by a person who is not in a group and making it passable.

  The object of the present invention is to solve the above-mentioned problems, and even when used in groups, it does not require the effort of pre-registration of companions, suppresses the occurrence of queues due to personal authentication, and makes efficient use. It is also possible to provide a traffic management system and a traffic management method capable of preventing traffic of an illegal interrupting person even when using a group and ensuring safety.

  In order to solve the above problems, the present invention has the following features.

  1. Obtained by a first access information obtaining means for obtaining first access information including the ID information in response to presentation of a recording medium on which ID information for identifying an individual is recorded, and obtained by the first access information obtaining means Access information storage means for storing the access information thus obtained, second access information acquisition means for acquiring the latest access information from the access information storage means as second access information, and an individual who is the presenter of the recording medium First biological information acquisition means for acquiring the biological information as first biological information, biological information storage means for storing the biological information in association with the ID information, the biological information storage means, or the ID Second biological information acquisition means for acquiring corresponding biological information as second biological information from the recording medium for acquiring information based on the ID information; Based on the first access information obtained by the access information obtaining means and the second access information obtained by the second access information obtaining means, the individual who is the presenter of the recording medium is an accompanying person. Companion determination means for determining whether there is a first biological information acquired by the first biological information acquisition means, and second biological information acquired by the second biological information acquisition means A collation processing means for comparing and collating and determining whether or not to match; a determination output means for determining whether or not the person can pass based on a determination result by the accompanying person determination means or a collation result by the collation processing means; Access information updating means for determining whether or not to update the latest access information in the access information storage means based on the result of the determination output means. Traffic management system for the butterflies.

  2. The companion determination means determines whether the accessed individual is a companion based on whether the ID information in the first access information and the second access information match. 2. The traffic management system according to 1.

  3. The first access information and the second access information include access time information, respectively, and the companion determination unit changes the time information in the second access information to the time information in the first access information. 3. The traffic management system according to 1 or 2, wherein it is determined whether or not the accessed individual is a companion based on the elapsed time.

  4). The determination output means determines that the person is not a companion when the companion determination means determines that the person is not a companion and the collation result by the collation processing means does not match. 4. The traffic management system according to any one of claims 1 to 3, wherein the traffic management system determines that the vehicle is allowed to pass when it is determined or when a collation result by the collation processing unit matches.

  5). The access information update unit updates and stores the first access information as the latest access information of the access information storage unit when the result of the determination output unit is passable. 5. The traffic management according to any one of 1 to 4, wherein the first access information is not updated and stored as the latest access information of the access information storage means when the result is a traffic denial. system.

  6). The traffic management system according to any one of 1 to 5, wherein the biological information storage unit stores the first biological information acquired by the first biological information acquisition unit.

  7). The traffic management system according to any one of 1 to 6, wherein the first biological information and the second biological information are facial image information.

  8). From a first access information acquisition step of receiving first access information including the ID information in response to presentation of a recording medium in which ID information for identifying an individual is recorded, and an access information storage means for storing the access information A second access information acquisition step for acquiring the latest access information as second access information, and first biological information for acquiring the biological information as first biological information from the individual who is the presenter of the recording medium Based on the ID information, the corresponding biometric information is set as the second biometric information from the obtaining step and the biometric information storage means for storing the biometric information in association with the ID information or the recording medium for obtaining the ID information. Second biometric information acquisition step to be acquired, first access information acquired in the first access information acquisition step, and second access information acquisition step Acquired in the companion determination step for determining whether the individual who is the presenter of the recording medium is a companion based on the second access information acquired in step 1 and the first biological information acquisition step The first biometric information and the second biometric information acquired in the second biometric information acquisition step are compared and collated to determine whether they match, and the determination in the companion determination step A determination output step for determining whether or not the person is allowed to pass based on a result or a verification result in the verification processing step, and updating the latest access information in the access information storage unit based on the result of the determination output step An access information update step for determining whether or not to perform the traffic management method.

  9. The companion determination step determines whether the accessed individual is a companion based on whether the ID information in the first access information and the second access information matches. 9. The traffic management method according to 8.

  10. The first access information and the second access information include access time information, respectively, and the companion determination step changes from time information in the second access information to time information in the first access information. 10. The traffic management method according to 8 or 9, wherein it is determined whether or not the accessed individual is a companion based on the elapsed time.

  11. When the determination output step is determined not to be a companion in the companion determination step and the collation result does not match in the collation processing step, it is determined that the vehicle is not allowed to pass, and the companion determination step is a companion 11. The traffic management method according to any one of claims 8 to 10, wherein it is determined that the vehicle is allowed to pass when it is determined or the collation result matches in the collation processing step.

  12 The access information update step updates and stores the first access information as the latest access information of the access information storage means when the result of the determination output step is passable, The traffic management according to any one of claims 8 to 11, wherein the first access information is not updated and stored as the latest access information of the access information storage means when the result is a traffic denial. Method.

  13. The traffic management method according to any one of claims 8 to 12, wherein the biological information storage unit stores the first biological information acquired by the first biological information acquisition unit.

  14 The traffic management method according to any one of 8 to 13, wherein the first biological information and the second biological information are facial image information.

  When using in a group, the representative's ID information is reused in the group, and each person's traffic is conducted according to the prescribed rules, so that the companion is authorized and illegal when using the group. It is possible to prevent the passage of interrupting persons and ensure safety, and also eliminate the need for pre-registration of companions, suppress the occurrence of queues due to personal authentication, and enable efficient use. A traffic management system and a traffic management method can be provided.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

(Functional configuration of traffic management system)
FIG. 1 is a block diagram showing a functional configuration of an embodiment of a traffic management system according to the present invention. An embodiment of a traffic management system will be described with reference to FIG.

  The traffic management system according to the present invention is generally configured using an information processing function by a computer or the like.

  In FIG. 1, reference numeral 1 denotes a traffic management system, which has various information processing functions for determining whether or not access for which traffic permission is requested. Specifically, the computer executes each processing program. By doing so, the function is realized.

  The ID reading device 2, the biometric information input device 3, and the traffic gate opening / closing device 4 correspond to interface devices for operating the functions of the traffic management system 1. These devices are configured to be connected to a traffic management system, but may be included in the traffic management system.

  The ID reading device 2 is a device having a function of reading ID information and the like recorded from an ID card possessed by a person who requests passage permission. The ID card may be a magnetic recording card, an IC card, or any other medium as long as it can record ID information. Based on the recorded ID information, the person who is possessed is specified, and data is read in order to determine whether or not the passage permission may be issued. There are various reading methods depending on the type of ID card. The read data is sent to the traffic management system 1 as access information and processed.

  The biometric information input device 3 is a device that obtains biometric information in order to confirm whether or not the person who seeks the passage permission is a specific person by using an ID card. is there. The biometric information may be anything such as fingerprints, palm prints, irises, faces, etc., as long as it can identify an individual. However, in this embodiment, there is no burden just by taking a picture, and commonly used face image information is taken as an example. The following explanation proceeds. The face image information is processed in the traffic management system 1 and used for personal identification.

  The traffic gate opening / closing device 4 is a device having a gate that opens and closes in response to the determination of whether or not the traffic management system makes a pass permission for a person who requests traffic permission. This notifies the person who asks for permission to pass or not, and realizes a physically passable or impossible state. Basically, it is assumed that an individual passes, and whether or not a single individual can pass is determined. Therefore, the gate also has a configuration in which a single individual passes.

  In this embodiment, even for a case where a specific individual is accompanied by a companion, so that the person can reasonably pass, that is, a companion who does not have an ID card can also obtain a passage permission, In addition, the traffic management system 1 performs determination processing that does not loosen the security too much, and controls the opening and closing of the traffic gate.

  The traffic management system 1 includes an input processing unit 10, a control unit 20, an output processing unit 30, and other storage units.

  The input processing unit 10 acquires each piece of information (recorded information such as ID information, directly collected biological information, etc.) from the ID reading device 2, the biological information input device 3, and the like and uses them for the determination processing.

  The control unit 20 executes a function of determining whether or not traffic is permitted using the acquired information. For this purpose, the exchange of information between the processing units and the overall processing sequence are controlled.

  The output processing unit 30 outputs based on the determined passage permission and operates the passage gate opening / closing device 4. In preparation for the next access, necessary post-processing (access information update, biometric information storage, etc.) is performed.

  More detailed functional elements of the traffic management system 1 will be described below.

  Reference numeral 11 denotes a first access information acquisition unit that acquires information read from the ID card presented by the ID reader 2 as first access information. That is, it functions as a first access information acquisition unit.

  The first access information is mainly ID information recorded on the ID card. If personal biometric information (face image) corresponding to the ID is recorded, it is also acquired as access information. Further, not only the recorded information but also information related to the access status such as the time when the ID card is presented for permission to pass is acquired.

  Reference numeral 12 denotes a first biometric information acquisition unit, which acquires biometric information (face image information and the like) obtained from an individual who is accessing the biometric information input device 3 by means such as photographing as first biometric information. That is, it functions as a first biological information acquisition unit.

  An access information storage unit 21 stores the previous access information (that is, the first access information acquired by the first access information acquisition unit 11 when the latest passage permission is given) for reference. That is, it functions as an access information storage unit.

  A biometric information storage unit 22 stores a face image as biometric information acquired by the first biometric information acquisition unit 12 as a log image. That is, it functions as a biological information storage means. The log image is effective as a reference for investigation when there is fraud. Further, for a specific individual who is permitted to pass, the face image information may be stored in association with ID information as registered biometric information.

  Reference numeral 15 denotes a second access information acquisition unit that acquires the previous access information stored in the access information storage unit 21 as the second access information. That is, it functions as a second access information acquisition unit. Based on this and the first access information, it is determined whether or not the person is a companion.

  Reference numeral 16 denotes a second biological information acquisition unit, which acquires biological information corresponding to the ID information acquired as the first access information as second biological information. That is, it functions as a second biological information acquisition unit. A collation process is performed between this and the first biological information.

  If the first access information acquisition unit 11 acquires the second biometric information recorded on the ID card as the first access information, the second biometric information is extracted and acquired. Further, if it is registered in the biological information storage unit 22 in association with the ID information, it is read out and acquired from there.

  Reference numeral 13 denotes a companion determination unit, which is based on the first access information acquired by the first access information acquisition unit 11 and the second access information acquired by the second access information acquisition unit 15. It is determined whether or not the individual who is traveling is a companion of a person who has previously passed. That is, it functions as a companion determination unit. The companion determination function will be described later with reference to FIG.

  Reference numeral 14 denotes a collation processing unit. When the companion determination unit 13 determines that the person is not a companion, the first biological information (face image) acquired by the first biological information acquisition unit 12 and the second biological information The second biological information (face image) acquired by the biological information acquisition unit 16 is collated, and it is determined whether or not the person corresponds to the ID information. That is, it functions as a collation processing means. The function of the collation process will be described later with reference to FIG.

  Reference numeral 18 denotes a determination output unit. When the companion determination unit 13 determines that the person is a companion, or when the collation processing unit 14 determines that the person corresponds to the acquired ID information, the passage permission is given. If not, pass otherwise. That is, it functions as a determination output unit.

  Further, it outputs to operate the passage gate opening / closing device 4 according to whether or not passage is possible. Further, the acquired first biological information (face image) is stored in the biological information storage unit 22 as a log image together with whether or not traffic is permitted. In addition, when the passage permission is given, an information update instruction is submitted to the information update unit 17 described later.

  Reference numeral 17 denotes an information update unit, which is a first access information acquired by the first access information acquisition unit 11 when the passage permission is given by the determination output unit 18 and the previous access information stored in the access information storage unit 21 is acquired. Replace and update with access information. That is, it functions as information updating means. Information is not updated when the judgment output unit 18 does not permit traffic.

  The operation of traffic management using the traffic management system will be described below.

(Operation flow of traffic management)
FIG. 2 is a flowchart showing an overall operation flow of traffic management by the traffic management system of this embodiment. A traffic management method using the traffic management system will be described with reference to FIG.

  The traffic management is generally realized by information processing by a computer or the like, and each process described below is performed in the traffic management system 1, specifically by the computer executing a processing program corresponding to each processing means. That function is realized.

  In this flow, by incorporating companion determination based on access information, it is easy and efficient for the companion's passage, and the function of preventing illegal passage by setting appropriate rules for companion determination is not impaired. I am doing so.

  That is, when using in a group, the representative first authenticates with the ID card held by the representative and passes. The accompanying person can use the ID card sequentially and access it within a predetermined time, and can easily pass with the permission of the accompanying person. If another user (other ID card) gets caught on the way, or if the time interval is too long, it is impossible to improperly pass as a companion thereafter. This is the flow.

  First, in step S11, the traffic management process starts when an individual who wants to pass presents a recording medium such as an ID card to the traffic management system 1 and requests permission for traffic. An ID card is read by the ID reading device 2, and face image information is input by photographing, for example, by the biometric information input device 3.

  Next, in step S12 which is a first access information acquisition step, the first access information acquisition unit 11 acquires ID information recorded on the ID card as first access information from the ID reading device 2. If a personal face image corresponding to the ID is recorded, it is also acquired. Further, not only the recorded information but also time information such as the time when the ID card is presented is acquired.

  In step S13, which is a first biological information acquisition step, the first biological information acquisition unit 12 uses the biological information input device 3 to acquire biological information (such as facial image information) obtained by means such as photographing, as the first biological information. Obtain as information. This step S13 may be executed in reverse order to the previous step S12.

  In step S14 which is the next second access information acquisition step, the second access information acquisition unit 15 stores the previous access information stored in the access information storage unit 21 (that is, the latest passage permission has been issued). Sometimes the first access information acquired by the first access information acquisition unit 11 is acquired as the second access information.

  Next, in step S15, which is a companion determination process, the companion determination unit 13 acquires the first access information acquired by the first access information acquisition unit 11 in step S12 and the second access information acquisition in step S14. Based on the second access information acquired by the unit 15, it is determined whether the accessing individual is a companion of a person who has previously passed.

  For the companion determination, ID information and time information are used. That is, if the ID is the same as the ID information presented by the individual who passed immediately before, and the time interval from that time is within a predetermined threshold, the person is determined to be a companion. A person who uses the same ID card and immediately follows it is regarded as a companion. The detailed determination method will be described later.

  If it is determined that the person is a companion (step S15: YES), the process proceeds to step S18. If it is determined that the person is not a companion (step S15: NO), the next step S16 is executed.

  In step S16, which is the second biological information acquisition step, the second biological information acquisition unit 16 acquires face image information corresponding to the ID information acquired as the first access information as second biological information. The second biometric information is face image information registered for collation, and is used for comparison and collation with the first biometric information obtained directly from the individual who wants to pass.

  Even if the second biometric information is recorded on the ID card so that the first access information acquiring unit 11 acquires the first biometric information as the first access information in step S12, the second biometric information may be extracted and acquired from the ID information card. Good. Alternatively, it may be registered in advance in the biological information storage unit 22 in association with the ID information, and may be read and acquired from there.

  Next, in step S17, which is a collation processing step, the collation processing unit 14 uses the face image as the first biometric information acquired by the first biometric information acquisition unit 12 in step S13, and the second biometric information in step S16. The face image as the second biological information acquired by the information acquisition unit 16 is collated, and it is determined whether or not the face of the accessing individual matches the face image registered with the ID. .

  In the collation processing of the face images as the first and second biological information, the ID information is obtained by performing the feature amount analysis processing on each face image, calculating the similarity between the two, and comparing with the threshold value. It is determined whether or not it matches the face of a specific individual indicated by. A detailed collation processing method will be described later.

  If it is determined that the collation processing results match (step S17: YES), step S18 is executed. If it is determined that they do not match (step S17: NO), step S20 is executed.

  From here, the processing flow is divided into the case where the passage is permitted and the case where the passage is not permitted. In step S18 and step S20 which are determination output processes, according to the determination of step S15 and step S17, a passage permission or a passage non-permission is output.

  In addition, the companion determination process of step S14 and step S15 may replace the collation process of step S16 and step S17. In either case, the branching by the determination proceeds to step S20 only when both are determined to be NO, and if either is YES, the processing result is the same if the processing immediately proceeds to step S18.

  Accordingly, in step S18, the determination output unit 18 sends a passage permission output to the passage gate opening / closing device 4, and in step S20, similarly, a passage nonpermission output is sent.

In the next step S19 and step S21, the passage gate opening / closing device 4 operates to open and close the gate in response to the output of the determination output unit 18 in step S18 or step S20, respectively. That is, in step S19, in response to the passage permission in step S18, the passage gate is opened to permit the passage. In step S21, the passage is not permitted in step S20, and the passage gate is kept closed so as not to pass. Next, in step S22 which is an access information update step, the information update unit 17 In response to the passage permission, the previous access information stored in the access information storage unit 21 is replaced with the current first access information acquired by the first access information acquisition unit 11 in step S12 and updated. Information is not updated when the judgment output unit 18 does not permit traffic.

  Updating the previous access information in the access information storage unit 21 prepares for companion determination when the next access occurs. That is, it is referred to as the second access information at the next access.

  Finally, in step S23, which is a biological information storage step, the first biological information (face image information) acquired in step S13 is stored in the biological information storage unit 22 as a log image together with the output of the determination output unit 18. This is intended to refer to the investigation when there is unauthorized traffic, etc., and may be stored together with the first access information acquired in step S12 and the determination results in step S15 and step S17. desirable.

  This completes the traffic management process for the access requesting the traffic permission. When the next passer-by accesses, the same flow is repeated.

<Flow for companion determination>
A detailed flow of step S15 in FIG. 2, that is, a companion determination process will be described with reference to FIG. FIG. 3 is a flowchart showing a companion determination process.

  The companion determination in FIG. 3 is based on the first access information acquired by the first access information acquisition unit 11 and the second access information acquired by the second access information acquisition unit 15. It is executed by the determination unit 13.

  First, in step S31, ID information included in the first and second access information is compared and collated. In step S32, it is determined whether the IDs are the same.

  If the IDs are the same (step S32: YES), step S33 is executed. If the IDs are different (step S32: NO), the process proceeds to step S36, and the immediate accompanying person determination result is NO.

  Next, in step S33, the difference between the time information included in the first and second access information is calculated. This indicates how late the next passer is about to pass with respect to the passer who has passed in advance, that is, the elapsed time since the previous access.

  In step S34, it is determined whether or not the above time information difference is within a predetermined threshold. This is based on the understanding that a companion will immediately follow and pass.

  If the time information difference is within the predetermined threshold (step S34: YES), step S35 is executed. In step S35, YES is submitted as a companion determination result. When the time information difference is not within the predetermined threshold (step S34: NO), step S36 is executed. In step S36, NO is submitted as a companion determination result.

  In this way, companion determination ends. Regardless of the number of companions, the simple rules of using the ID card of the registrant who accesses and passes first, and accesses and passes sequentially within a specified time, no registration process is required, and efficiency It is possible to pass through. In addition, it becomes difficult for an unauthorized passer-by to get mixed in by the above rules.

<Flow of verification processing>
The detailed flow of step S17 in FIG. 2, that is, the collation process, will be described with reference to FIG. FIG. 4 is a flowchart showing the collation process.

  4 includes a face image (hereinafter referred to as a first face image) as first biological information acquired by the first biological information acquisition unit 12 and a second biological information acquisition unit 16. Based on the acquired face image as the second biological information (hereinafter referred to as the second face image), the verification processing unit 14 executes the process.

  The collation process is for collating and determining whether or not the face (first face image) of the individual who is accessing matches the face (second face image) registered with the ID, A feature amount analysis process is performed on the face image, a similarity between the two is calculated, and a determination process is performed by comparing with a threshold value.

  First, in step S41, face parts are extracted from the first and second face images.

  The position (coordinate on the image) of the characteristic part of the face is calculated from the face area. The characteristic parts of the face are the eyes (center of the pupil, the corner of the eye, the top of the eye, the top and bottom of the pupil), the eyebrows (both ends and center), the nose (the edge of the nose, the center bottom, nostril), and the position of the tip of the lower jaw Can be mentioned.

  Next, in step S42, feature amounts are calculated for the first and second face images. As the feature amount, shape feature amount / texture information is extracted.

  The shape feature amount can be extracted from, for example, the correlation of the positions of the facial feature parts. The texture information can be used by selecting a characteristic local region and vectorizing the density distribution there, that is, a two-dimensional pattern. In general, dimensional compression processing is performed on these high-dimensional feature values. Details of the feature amount extraction will be described later.

  Next, in step S43, the similarity is calculated from each feature amount for each face image.

  The similarity of the shape feature amount can be calculated by the sum of the distances between the vertices indicating the positions of the feature portions of the respective faces. The similarity for each local texture feature amount is calculated using the distance of each local texture feature amount in each feature space. The overall similarity is calculated as a weighted sum of similarities calculated for each face feature amount group.

  As described above, the similarity between the face feature amounts in the first and second face images is expressed by the distance between the two in the feature space, and the similarity is higher as the distance is closer, and the similarity is lower as the distance is longer. Become. Details of the similarity calculation will be described later.

  In step S44, it is determined whether the calculated similarity between the first and second face images is within a predetermined threshold. If the degree of similarity is within a predetermined threshold, it can be considered that the distance is close, that is, the degree of similarity is high and the first and second face images match (same person).

  If the similarity is within a predetermined threshold (step S44: YES), step S45 is executed. In step S45, YES is submitted as the collation determination result. If the similarity is not within the predetermined threshold (step S44: NO), step S46 is executed. In step S46, NO is submitted as the collation determination result.

  In this way, the collation process ends. Since the matching process is not executed when it is determined that the person is a companion, the first registrant who accesses and passes is subjected to the matching process, but the companion is omitted because the matching process is omitted and no matter how many people pass. It becomes possible to do.

(Specific example 1 of traffic management)
FIG. 5 is a diagram showing a specific example 1 of traffic management. With reference to FIG. 5, a specific example of traffic management when a registered passer A passes along with accompanying persons B and C will be described.

  In FIG. 5, as shown at 51, the passer A registered first (access order 1) accesses the pass management system 1 and presents the ID card of the own A (access information is IDA). And time T1). In addition, a face image (biological information fA) is captured and input to the traffic management system 1. The traffic management system 1 determines that the person is not a companion based on the previous access information (IDX and time Tx) and the current access information. Therefore, the second face image (fA) is acquired and collated with the first face image (fA). The collation result is OK, A is allowed to pass, and the pass gate opens. The pass gate opens and closes one by one and closes after A passes. The previous access information is updated with the current access information.

  Next, as shown at 52, the accompanying person B uses the ID card of A again to access the traffic management system 1 (access information is IDA and time T2) as shown in 52. In addition, a face image (biological information fB) is taken and input to the traffic management system 1. In the traffic management system 1, it is determined that the person is a companion based on the access information (IDA and time T1) when A has passed last time, that is, the current access information (the difference between T1 and T2 is Within a predetermined threshold). Accordingly, there is no collation processing, and the first face image (fB) is not used. With companion determination YES, B is permitted to pass, the pass gate opens, and closes after B passes. The previous access information is updated with the current access information.

  Next, as shown at 53, finally (access order 3), companion C uses A's ID card for the third time to access traffic management system 1 (access information is IDA and time T3). In addition, a face image (biological information fC) is captured and input to the traffic management system 1. In the traffic management system 1, based on the access information (IDA and time T2) when B has passed the last time, that is, the current access information, it is determined that the person is a companion (the difference between T2 and T3). Is within a predetermined threshold). Therefore, there is no collation processing, and the first face image (fC) is not used. With companion determination YES, C is allowed to pass, the pass gate opens, and closes after C passes. The previous access information is updated with the current access information.

  In this way, even with a non-registered companion, it is possible to pass efficiently with a simple rule that the registrant's ID card is reused and accessed sequentially within a predetermined time. .

(Specific example 2 of traffic management)
FIG. 6 is a diagram showing a specific example 2 of traffic management. With reference to FIG. 6, a specific example of traffic management in the case where a registered passer A is accompanied by a companion B and then C who is unknown as to whether or not he is a companion will be described.

  In FIG. 6, as shown at 61, the passer A registered first (access order 1) accesses the pass management system 1 and passes through the same procedure as in the case of the registrant A of the first specific example. Yes, explanation is omitted.

  Next, as shown in 62, the companion person B uses the ID card of A again to access and pass the traffic management system 1 (access order 2). This is the same as B, and the description is omitted.

  Next, as shown in 63, finally (access order 3) C, who is unknown as to whether he or she is a companion, uses A's ID card for the third time to access the traffic management system 1 (access information includes IDA and time T3). In addition, a face image (biological information fC) is captured and input to the traffic management system 1. In the traffic management system 1, it is determined that the person is not a companion based on the access information (IDA and time T2) when B has passed last time, that is, the current access information (the difference between T2 and T3 is predetermined). Exceeds the threshold). Therefore, the second face image (fA) is acquired and collated with the first face image (fC). Naturally, the collation result is NG, C is not allowed to pass, and the pass gate remains closed. The previous access information is not updated.

  In this way, even a companion cannot be regarded as a companion unless he / she accesses within a certain time. This is a rule to prevent unauthorized passers. If an unauthorized passer has illegally obtained the registrant A's ID card and is trying to pass, it must be blocked. Keep the risk as low as possible from a security point of view while operating efficiently with simple rules.

(Specific example 3 of traffic management)
FIG. 7 is a diagram showing a specific example 3 of traffic management. Referring to FIG. 7, a specific example of traffic management when companion C tries to pass after registered passer A passes, but another registrant B tries to pass in between. Will be explained.

  In FIG. 7, as shown at 71, the passer A registered first (access order 1) accesses the pass management system 1 and passes through the procedure for the registrant A in specific examples 1 and 2. It is the same and description is omitted.

  Next, as shown at 72, another registrant B who is not a companion accesses the traffic management system 1 using his / her ID card (access information is IDB and time T2) as shown in 72. ). In addition, a face image (biological information fB) is taken and input to the traffic management system 1. In the traffic management system 1, it is determined that the person is not a companion (IDA and IDB are different) based on the access information (IDA and time T1) when A passes last time, that is, the access information of this time. Therefore, the second face image (fB) is acquired and collated with the first face image (fB). Naturally, the collation result is OK, B is allowed to pass, the pass gate opens, and closes after B passes. The previous access information is updated with the current access information.

  Next, as shown in 73, finally (access order 3) C who is a companion of A uses the ID card of A again to access the traffic management system 1 (access information is IDA and time T3). . In addition, a face image (biological information fC) is captured and input to the traffic management system 1. In the traffic management system 1, it is determined that the person is not a companion (IDB and IDC are different) based on the access information (IDB and time T 2) when B passes last time, that is, the current access information. Therefore, the second face image (fA) is acquired and collated with the first face image (fC). Naturally, the collation result is NG, C is not permitted to pass, and the pass gate remains closed. The previous access information is not updated.

  In this way, even a companion cannot be regarded as a companion unless he / she continues to access sequentially. Although this is somewhat inconvenient, it is a rule to prevent unauthorized passers-by. If C is trying to get a registrant A's ID card illegally, then these rules would be effective to keep that risk as small as possible.

(Example of facial image feature extraction)
A detailed example of face part extraction and feature amount calculation for the first and second face images will be described.

  First, the position (coordinate on the image) of the characteristic part of the face is calculated from the face area.

  The characteristic parts of the face are the eyes (center of the pupil, the corner of the eye, the top of the eye, the top and bottom of the pupil), the eyebrows (both ends and center), the nose (the edge of the nose, the center bottom, nostril), and the position of the tip of the lower jaw Can be mentioned. FIG. 8 shows an example of each part for obtaining the position with respect to the face image. For example, each point from P1 to P23 in FIG. 8 is a facial feature part to be obtained, and the position of these points is calculated.

  Next, feature amounts used for face matching processing are extracted from the face image and the position of the feature part. As the feature amount, shape feature amount / texture information is extracted.

  The shape feature amount can be extracted from, for example, the correlation between the positions of the facial feature parts. Since there are many relational elements, the shape feature amount is represented by a vector in a high-dimensional space. For texture information, a characteristic local region can be selected and the density distribution there, that is, a two-dimensional pattern can be vectorized. This is also a high-dimensional feature amount. When a plurality of more characteristic local regions are selected, a plurality of feature amount vectors are obtained.

  In general, dimensional compression processing is performed on these high-dimensional feature values.

  For example, sample data is experimentally collected for the feature quantity x to obtain an effective coordinate axis for dimensional compression. The feature quantity c in the new space is expressed by the following equation (1).

x = x _m + Pc (1)
x _m is an average of the feature quantity x, and P is a normal mode of change (a set of eigenvectors).

  P sets a new space effective for dimensional compression. c is a feature amount expressed in the space. It may be considered that the space represented by P has already been reduced from the original n dimension to the k dimension in the following manner.

  It is considered that the variation of the feature quantity x is divided into a partial space representing individuality and a partial space representing attribute variation. The transformation that divides the feature space and reduces the feature quantity x from n dimensions to k dimensions (feature vector d) can be expressed by the following equation (2) using the matrix A.

d = A ^t x (2)
Here, A is an n × k matrix. As a method for determining the conversion A, the following method is known.
(1) From the various components of the feature space, k main components having a large ratio of intra-class variance and inter-class variance (F ratio) are selected to obtain a subspace representing personality (PCA method).
(2) A projection space in which the difference between the interclass variance and the intraclass variance is large is obtained from the feature space (EM method).
(3) A projection space is obtained from the feature space so that the ratio between the inter-class variance and the intra-class variance is large. This is a multiple discriminant analysis method that generalizes the Fisher discriminant analysis method into a multi-class problem (MDA method).

  Inter-class variance is a variance in a subspace representing individuality, and intra-class variance is a variance in a subspace representing a change in attributes.

A combination of the shape feature quantity d ^s and the local texture feature quantity d ^(k) obtained by converting the shape feature quantity and texture information as described above is registered in the personal collation dictionary as the following face feature quantity. Or used for similarity calculation.

Facial features: (d ⁽⁰⁾ , d ⁽¹⁾ ,..., D ^(L) ),
L: Number of local features, d ⁽⁰⁾ is d ^s .

  Of course, the feature amount extraction for personal verification may be the shape feature amount / texture information alone.

(Example of similarity calculation)
Similarity between the face feature amount extracted from the first face image (hereinafter referred to as the first face feature amount) and the face feature amount extracted from the second face image (hereinafter referred to as the second face feature amount). Is calculated.

  The similarity of the shape feature amount is a sum of Euclidean distances between the vertices indicating the positions of the facial feature portions in the first and second face feature amounts, and can be calculated as the following equation (3). it can.

D ^s _ij = (d ^s _j −d ^s _i ) ^t (d ^s _j −d ^s _i ) (3)
Here, i and j are variables indicating the first and second facial feature amounts, respectively.

  It is assumed that there are as many local texture feature amounts L as the number of local features.

  The similarity for each local texture feature amount is the distance (for example, Euclidean distance) of each local texture feature amount k (k = 1... L) in the first and second face feature amounts in each feature space. ) Is used to calculate the following equation (4).

D ^(k) _ij = (d _j -d _i ) ^t (d _j -d _i ) (4)
Similarity calculation is performed for each face feature amount group as in the above equation, and the overall similarity is calculated as the following equation (5) by the weighted sum of the similarity of each face feature amount group. Is done.

D _ij = W ^s D ^s + ΣW _k D ^(k) _ij (5)
Σ is the total sum for k (k = 1... L).

  As another similarity calculation method, the similarity between the sample i and the sample j of the first and second facial feature quantities can be expressed by the Mahalanobis distance in the k-dimensional subspace. The similarity in that case can be calculated as in the following equation (6).

D _ij = (d _j −d _i ) ^t S ^d _m ⁻¹ (d _j −d _i ) (6)
S _m is a covariance matrix and is calculated as in the following equation (7).

S ^d _m = (1 / M) ΣΣ (d _fm −d _c ) (d _fm −d _c ) ^t (7)
Here, ΣΣ is the sum of f and m. f is a variable representing each individual, m is a variable representing each sample for each individual, and M is the total number of samples, that is, the total number of f × the total number of m. d _c is the average of all the d f, relates m, is expressed by the following equation (8).

d _c = (1 / M) ΣΣd _fm (8)
Here, ΣΣ is also the sum of f and m.

  As described above, the similarity between the first face feature value and the second face feature value is expressed by the distance between the two in the feature space. The closer the distance, the higher the similarity degree, and the farther the distance, the higher the similarity degree. It will be low.

  As described above, according to the present embodiment, even when used in a group, the representative ID information recording medium is reused in the group, and the passing interval of each person is performed within a predetermined time. This eliminates the need for pre-registration of companions, suppresses the occurrence of queues due to personal authentication, enables efficient use, and prevents unauthorized persons from interrupting when using groups. A traffic management system and a traffic management method that can ensure safety can be provided.

  Further, the scope of the present invention is not limited to the above embodiment. Unless it deviates from the meaning of this invention, those changed forms are also included in the range.

It is a block diagram which shows the function structure about one Embodiment of the traffic management system which concerns on this invention. It is a flowchart which shows the whole operation | movement flow of the traffic management by the traffic management system of this embodiment. It is a flowchart which shows the accompanying person determination process in FIG. It is a flowchart which shows the collation process process in FIG. It is a figure which shows the specific example 1 of traffic management. It is a figure which shows the specific example 2 of traffic management. It is a figure which shows the specific example 3 of traffic management. It is a figure which shows the example of the position of the face feature part for extracting feature-value from a face image.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Traffic management system 2 ID reader 3 Biometric information input device 4 Passage gate opening / closing device 10 Input processing part 11 1st access information acquisition part 12 1st biometric information acquisition part 13 Accompanying person determination part 14 Collation process part 15 2nd Access information acquisition unit 16 second biological information acquisition unit 17 information update unit 18 determination output unit 20 control unit 21 access information storage unit 22 biological information storage unit 30 output processing unit

Claims (14)

First access information acquisition means for receiving first recording information containing ID information in response to presentation of a recording medium in which ID information for identifying an individual is recorded;
Access information storage means for storing the access information acquired by the first access information acquisition means;
Second access information acquisition means for acquiring latest access information as second access information from the access information storage means;
First biological information acquisition means for acquiring the biological information as first biological information from the individual who is the presenter of the recording medium;
Biometric information storage means for storing biometric information in association with the ID information;
Second biological information acquisition means for acquiring corresponding biological information as second biological information based on the ID information from the biological information storage means or a recording medium for acquiring the ID information;
Based on the first access information acquired by the first access information acquisition unit and the second access information acquired by the second access information acquisition unit, the individual who is the presenter of the recording medium A companion determination means for determining whether or not the person is a companion;
Collation for comparing and comparing the first biological information acquired by the first biological information acquisition means and the second biological information acquired by the second biological information acquisition means to match Processing means;
A determination output means for determining whether or not the person is allowed to pass based on a determination result by the companion determination means or a verification result by the verification processing means;
Access information update means for determining whether or not to update the latest access information in the access information storage means based on the result of the determination output means,
A traffic management system characterized by this. The companion determination means is
Determining whether the accessed individual is a companion based on whether the ID information in the first access information and the second access information match;
The traffic management system according to claim 1. Each of the first access information and the second access information includes access time information,
The companion determination means is
Determining whether the accessed individual is a companion based on the elapsed time from the time information in the second access information to the time information in the first access information;
The traffic management system according to claim 1 or 2, wherein The determination output means includes
When it is determined that the companion determination means is not a companion and the verification result by the verification processing means does not match, it is determined that the vehicle is not allowed to pass,
When it is determined by the accompanying person determination means that the person is a companion, or the matching result by the matching processing means is matched, the passage is determined to be permitted.
The traffic management system according to any one of claims 1 to 3, wherein The access information update means includes
When the result of the determination output means is passable, the first access information is updated and stored as the latest access information of the access information storage means,
When the result of the determination output means is non-passage, the first access information is not updated and stored as the latest access information of the access information storage means,
The traffic management system according to any one of claims 1 to 4, wherein The biological information storage means stores the first biological information acquired by the first biological information acquisition means;
The traffic management system according to any one of claims 1 to 5, wherein The first biological information and the second biological information are face image information.
The traffic management system according to any one of claims 1 to 6, wherein: A first access information obtaining step of obtaining first access information including the ID information in response to presentation of a recording medium in which ID information for identifying an individual is recorded;
A second access information acquisition step of acquiring the latest access information as the second access information from the access information storage means for storing the access information;
A first biological information acquisition step of acquiring the biological information as first biological information from an individual who is the presenter of the recording medium;
A second biological information is obtained as second biological information based on the ID information from a biological information storage means for storing biological information in association with the ID information or from a recording medium for obtaining the ID information. Biometric information acquisition process,
Based on the first access information acquired in the first access information acquisition step and the second access information acquired in the second access information acquisition step, the individual who is the presenter of the recording medium is A companion determination process for determining whether the person is a companion; and
Collation for comparing and comparing the first biological information acquired in the first biological information acquisition step with the second biological information acquired in the second biological information acquisition step. Processing steps;
A determination output step for determining whether or not the person is allowed to pass based on a determination result in the companion determination step or a verification result in the verification processing step;
An access information update step for determining whether or not to update the latest access information of the access information storage means based on the result of the determination output step,
A traffic management method characterized by that. The companion determination step includes
Determining whether the accessed individual is a companion based on whether the ID information in the first access information and the second access information match;
The traffic management method according to claim 8, wherein: Each of the first access information and the second access information includes access time information,
The companion determination step includes
Determining whether the accessed individual is a companion based on the elapsed time from the time information in the second access information to the time information in the first access information;
The traffic management method according to claim 8 or 9, characterized in that. The determination output step includes
When it is determined that the person is not a companion in the companion determination process and the collation result does not match in the collation process, it is determined that the vehicle is not allowed to pass.
When it is determined that it is a companion in the companion determination step, or when the collation result matches in the collation processing step, it is determined that the vehicle can pass.
The traffic management method according to any one of claims 8 to 10, wherein the traffic management method is described above. The access information update step includes:
When the result of the determination output step is passable, the first access information is updated and stored as the latest access information of the access information storage means,
When the result of the determination output step is non-passage, the first access information is not updated and stored as the latest access information of the access information storage unit,
The traffic management method according to any one of claims 8 to 11, wherein The biological information storage means stores the first biological information acquired by the first biological information acquisition means;
The traffic management method according to any one of claims 8 to 12, wherein the traffic management method is described above. The first biological information and the second biological information are face image information.
The traffic management method according to any one of claims 8 to 13, wherein the traffic management method is described above.

Images