JP2019057284A - Checking system - Google Patents

Abstract

To prevent a wrong recognition of an object passing through a gate.SOLUTION: The checking system according to the present invention includes: first imaging means for acquiring a first image, which is an image taken of a before-passage region to a gate; second imaging means for acquiring a second image, which is an image taken of a region including at least a part of the before-passage region; and checking means for checking a target registered in advance and a target in the first image against each other, using the second image.SELECTED DRAWING: Figure 17

Description

  The present invention relates to a collation system, and more particularly to a collation system that collates an object about to pass through a gate.

  As a means for restricting and managing the persons who enter and leave a specific place such as an office or an event venue, a collation system that collates whether or not the person to be passed is a person registered in advance is used. In particular, in recent years, with the development of human face authentication technology, a walk-through face authentication system that performs face authentication from a human face image taken by a camera installed at a gate is used.

JP2015-1790A

  Here, in the walk-through face authentication system, there are cases where a plurality of gates are adjacent to each other and lanes through which a person heading to each gate passes are adjacent. In this case, a person heading for an adjacent gate in an adjacent lane may be reflected in an image of a person passing through a lane of a certain gate. Then, a person passing through an adjacent lane may be misrecognized as a person passing through the own lane, which may hinder verification of a person passing through the own gate ahead of the own lane. For this reason, in the situation where a plurality of gates are installed, it is required to suppress erroneous recognition of a person heading to each gate.

  Moreover, there exists a technique of patent document 1 as a technique relevant to a walk-through face authentication system. Japanese Patent Application Laid-Open No. 2004-151867 raises a problem that authentication is completed when a person is far from the gate, and the gate is opened before the person reaches the gate. And in order to solve such a problem, in Patent Document 1, the face image of the photographed person and the registered face image are collated, and based on the size of the collated person on the input image, to the person's gate. The approach of is detected. Further, in Patent Document 1, an attempt is made to prevent erroneous recognition of a person heading to an adjacent gate by setting different determination reference values for the size of the face area for each captured image area.

  However, in the technique described in Patent Document 1, only the photographed image by the camera installed corresponding to the gate through which the person is going to pass is used, and the size of the person set for each region of the photographed image is determined. The reference value is used to detect the approach of a person to the gate. For this reason, when the area of the person shown in the photographed image is not appropriate, or when the determination reference value is not appropriate, there is a problem that a person who is heading for another gate is still erroneously recognized.

  Further, the above-described problem of erroneous recognition of a person heading to each gate is not limited to the case where the object passing through the gate is a person, but can occur when any object is collated.

  Therefore, an object of the present invention is to provide a collation system that can solve the above-described problem of erroneously recognizing an object that is going to pass through a gate.

The collation system which is one form of the present invention,
Imaging means for acquiring each captured image of each pre-passage region for each gate installed in parallel;
For each of the gates, a matching unit that performs a matching process between a target registered in advance and a target included in the captured image with respect to each of the captured images in each of the pre-passage areas,
With
The collation means performs the collation processing based on a target in the captured image corresponding to the predetermined gate and a target in the captured image corresponding to another gate.
The configuration is as follows.

In addition, an information processing apparatus which is one embodiment of the present invention
For each of the captured images of each pre-passage region for each gate installed in parallel, a collation unit that performs collation processing between a pre-registered target and a target included in the captured image,
The collation means performs the collation processing based on a target in the captured image corresponding to the predetermined gate and a target in the captured image corresponding to another gate.
The configuration is as follows.

In addition, a program which is one embodiment of the present invention is
In the information processing device,
A program for realizing collation means for performing collation processing between a pre-registered target and a target included in the captured image with respect to each captured image of each pre-passage region for each gate installed in parallel And
The collation means performs the collation processing based on a target in the captured image corresponding to the predetermined gate and a target in the captured image corresponding to another gate.
The configuration is as follows.

Moreover, the collation method which is one form of this invention is the following.
A method of performing a collation process between a pre-registered target and a target included in the captured image for each captured image of each pre-passage region for each gate installed in parallel,
Performing the matching process based on a target in the captured image corresponding to a predetermined gate and a target in the captured image corresponding to another gate;
The configuration is as follows.

  According to the present invention configured as described above, it is possible to suppress erroneous recognition of an object about to pass through a gate.

It is a figure which shows the use condition of the face authentication system in Embodiment 1 of this invention. It is a block diagram which shows the structure of the face authentication system in Embodiment 1 of this invention. It is a figure which shows the imaging condition by the face authentication system disclosed in FIG. It is a figure which shows the picked-up image image | photographed in the imaging condition of FIG. 3 with the face authentication system disclosed in FIG. It is a figure which shows the imaging condition by the face authentication system disclosed in FIG. It is a figure which shows the picked-up image image | photographed in the imaging condition of FIG. 5 with the face authentication system disclosed in FIG. It is a flowchart which shows the processing operation by the face authentication system disclosed in FIG. It is a figure which shows the imaging condition by the face authentication system in Embodiment 2 of this invention. It is a figure which shows the picked-up image image | photographed in the imaging condition of FIG. 8 with the face authentication system in Embodiment 2 of this invention. It is a figure which shows the imaging condition by the face authentication system in Embodiment 2 of this invention. It is a figure which shows the picked-up image image | photographed in the imaging condition of FIG. 10 with the face authentication system in Embodiment 2 of this invention. It is a flowchart which shows the processing operation by the face authentication system in Embodiment 2 of this invention. It is a block diagram which shows the structure of the face authentication system in Embodiment 4 of this invention. It is a figure which shows the imaging condition by the face authentication system in Embodiment 4 of this invention. It is a figure which shows the picked-up image image | photographed in the imaging condition of FIG. 12 with the face authentication system in Embodiment 4 of this invention. It is a figure which shows the mode of the image processing by the face authentication system in Embodiment 4 of this invention. It is a block diagram which shows the structure of the collation system in Embodiment 5 of this invention. It is a block diagram which shows the structure of the information processing apparatus in Embodiment 5 of this invention.

<Embodiment 1>
A first embodiment of the present invention will be described with reference to FIGS. FIG. 1 is a diagram illustrating a usage state of the face authentication system. FIG. 2 is a diagram illustrating the configuration of the face authentication system. 3 to 7 are diagrams for explaining the processing operation of the face authentication system.

[overall structure]
The face authentication system 10 (collation system) according to the present invention is a system used to limit or manage entry / exit of a person (target) in a specific place such as an office or an event venue. For example, the imaging device constituting the face authentication system 10 is installed in the vicinity of the gate location for each gate that is opened and closed when a person enters and exits.

  In the example shown in FIG. 1, three gates G1, G2, G3 are arranged adjacent to each other in parallel, and a person passes in the direction indicated by the arrow from the right side of FIG. 1 toward each gate G1, G2, G3. It is configured to For this reason, the right area of FIG. 1 with respect to each gate G1, G2, G3 is a front area (pre-passage area) where a person passes through the gate. In the pre-passage region of each gate G1, G2, G3, each lane R1, R2, R3 through which a person who wants to pass through each gate G1, G2, G3 passes side by side has each gate G1, G2, Corresponding to G3, they are located in parallel. Each lane R1, R2, R3 may be partitioned by some member or may not be partitioned.

  In the situation shown in FIG. 1, the imaging devices C1, C2, and C3 constituting the face authentication system 10 in the present embodiment are in the vicinity of the corresponding gates G1, G2, and G3, and the persons heading to the gates G1, G2, and G3. It is installed on the right side. However, the installation position of the imaging device is not limited to the position shown in FIG. 1, and may be installed at any position such as the left side of the gate or above the gate. Note that the face authentication system 10 also includes a display device in the vicinity of the imaging devices C1, C2, and C3.

  For example, in the gate G1, the face authentication system 10 captures an image of a person heading for the gate G1 with the imaging device C1 equipped. Then, from the face image of the person shown in the photographed image, it is verified whether or not the person is a person registered in advance. If the verification is successful, the gate G1 is opened so that the person can pass. A face authentication system and imaging devices C2 and C3 constituting the system are also installed corresponding to the other gates G2 and G3, respectively, and a person who goes to each of the gates G2 and G3 is collated. Hereinafter, the configuration of the face authentication system 10 will be described in detail. In the following, the face authentication system 10 installed mainly corresponding to the gate G1 will be described, but the face authentication system installed corresponding to the other gates G2 and G3 has the same configuration.

[Face recognition system configuration]
The face authentication system 10 according to the present embodiment is an information processing apparatus that includes an arithmetic device and a storage device that are integrated with an imaging device C1 (camera) and a display device D1 (display). In other words, the information processing apparatus including the arithmetic device and the storage device that perform face authentication processing and the display device D1 are mounted on the imaging device C1. However, the face authentication system 10 is not necessarily limited to being configured integrally with the imaging device C1 and the display device D1. For example, the imaging device C1, the display device D1, and the information processing device that processes the captured image may be configured as separate devices, and may be installed at different locations.

  Specifically, as shown in FIG. 2, the face authentication system 10 includes an imaging device C1, a display device D1, and a communication unit 16, and an object extraction unit constructed by an arithmetic device executing a program. 11, a target determination unit 12, a collation unit 13, and a gate control unit 14. In addition, the face authentication system 10 includes a collation data storage unit 17 constructed in a storage device.

  The imaging device C1 (imaging means) includes a camera and a camera control unit that acquire a photographed image of a pre-passage area with respect to the gate G1, that is, a captured image of the corresponding area in front of the gate G1 of the lane R1 at a predetermined frame rate. is there. For example, as illustrated in FIG. 3, the imaging device C <b> 1 has a shooting area in a range sandwiched by the C <b> 1 a line. At this time, the imaging is performed so that the person P10 who passes through the lane R1 (own lane) corresponding to the gate G1 where the imaging device C1 is located is located in the central area in the horizontal direction sandwiched by the line C1b in the imaging area. The imaging area of the device C1 is set. Note that the captured image is set so as to be substantially in focus within a predetermined distance range in the perspective direction with respect to the imaging device C1, for example, a distance between the line L1 and the line L2 shown in FIG.

  As described above, the imaging region of the imaging device C1 is set, so that, in the imaging region, in the end region in the horizontal direction with respect to the central region that is sandwiched between the code C1a line and the code C1b line. In the situation shown in FIG. 3, a person P20 passing through the lane R2 corresponding to the adjacent gate G2 may appear. Further, in the situation shown in FIG. 5, in the situation shown in FIG. 5, the person P12 located in the own lane R1 corresponding to the own gate G1 in which the imaging device C1 is installed may be shown in the end region. Even if such a situation occurs, the face authentication system 10 of the present invention excludes the person P20 who is about to pass through the adjacent gate G2 from the verification processing target as will be described below, and the self-gate G1. The person P12 who is going to pass through is properly recognized so as to be able to determine whether or not the gate can pass.

  The target extraction unit 11 acquires a captured image from the imaging device C1, and extracts a person to be processed from the captured image. The person is extracted by, for example, extracting a moving object, or determining from a position of a characteristic shape portion or a color position with respect to the entire shape of the object or the entire image. At this time, the target extraction unit 11 also identifies an area in the captured image where the extracted person is located. In particular, in the present embodiment, it is specified whether the extracted person is located in the center region or the left and right end regions in the horizontal direction of the captured image described above. For example, in the situation of FIG. 3, in the captured image by the imaging device C1 corresponding to the gate G1, as shown in FIG. 4A, the person P10 located in the central area is extracted and the person P20 located in the right end area is extracted. Is done.

  The target determination unit 12 (collation means) determines whether or not the persons P10 and P20 extracted by the target extraction unit 11 are heading toward the own gate G1. At this time, when the person P20 is located in the end region (first region), the target determination unit 12 captures an image captured by the imaging device C2 of the face authentication system 20 corresponding to the other gate G2. Based on the above, it is determined whether or not the person P20 is heading toward the own gate G1. In this example, since the person P20 is shown in the right end region of the captured image corresponding to the own gate G1 shown in FIG. 4A, the person P20 is captured by the imaging device C2 of the gate G2 adjacent to the right side of the gate G1. Acquire a captured image. Specifically, the target determination unit 12 communicates with the face authentication system 20 of the adjacent gate G2 via the communication unit 16, and at the same timing (for example, the same time) when the captured image is captured by the gate G1. A photographed image photographed by the gate G2 is acquired. It is assumed that the positional relationships of the face authentication systems (imaging devices C1, C2, C3) respectively corresponding to the gates G1, G2, G3 are registered in advance in each system.

  Then, the target determination unit 12 checks whether or not the person P20 located in the end region of the captured image of the own gate G1 is reflected in the central region (second region) of the captured image of the adjacent gate G2. In the present embodiment, if any person appears in the central area of the captured image of the adjacent gate G2, it is determined that the person is the person P20 located in the end area of the captured image of the own gate G1. To do. In this case, the face authentication system 10 of the own gate G1 determines that the person P20 located in the end region of the captured image is excluded from the comparison target. Note that the end region (first region) of the captured image of the own gate G1 and the central region (second region) of the captured image of the adjacent gate G2 are mutually different regions on the captured image, but in real space. Are overlapping spaces.

  For example, in the situation of FIG. 3, the person P20 located in the end region of the captured image of the own gate G1 shown in FIG. 4A is located in the central region of the captured image of the adjacent gate G2 shown in FIG. Therefore, the person P20 is excluded from the verification target by the face authentication system 10 of the own gate G1. That is, the face authentication system 10 of the self-gate G1 sets only the person P10 located in the center area of the captured image as a comparison target. Further, in the situation of FIG. 5, the person P12 located in the end region of the captured image of the own gate G1 shown in FIG. 6A is positioned in the central region of the captured image of the adjacent gate G2 shown in FIG. Not done. For this reason, the person P12 is set as a verification target by the face authentication system 10 of the own gate G1. That is, the face authentication system 10 of the self-gate G1 uses the person P10 located in the center area of the captured image and the person P12 located in the end area as collation targets.

  Note that the target determination unit 12 may determine whether or not a person is a verification target in the own gate by a method different from that described above. As an example, when the person is located in the end area (first area) of the photographed image, the target determination unit 12 determines that the person himself / herself with respect to the face authentication system 20 corresponding to the other gate G2. An inquiry may be made as to whether or not the person is a G1 person. Specifically, in the example of FIGS. 3 and 4, since the person P20 is shown in the right end region of the captured image corresponding to the own gate G1 shown in FIG. 4A, the gate adjacent to the right side of the gate G1. The G2 face authentication system 20 is inquired as to whether or not the person P20 is reflected in the central area of the adjacent gate G2. Similarly, in the example of FIGS. 5 and 6, since the person P12 is shown in the right end region of the captured image corresponding to the own gate G1 shown in FIG. 6A, the gate G2 adjacent to the right side of the gate G1. Is inquired whether the person P12 is reflected in the central area of the adjacent gate G2. At this time, the target determination unit 12 communicates with the face authentication system 20 of the adjacent gate G2 via the communication unit 16, and the gate G2 at the same timing (for example, the same time) when the captured image is captured by the gate G1. An inquiry is made as to whether or not a person is shown in the central area of the photographed image.

  Then, the face authentication system 20 of the adjacent gate G2 that has received the inquiry checks whether or not any person is reflected in the central area (second area) from its captured image, and receives the inquiry as a result. The target determination unit 12 of the face authentication system 10 of the gate G1 is notified. Specifically, the face authentication system 20 of the adjacent gate G2 has the same function as the target extraction unit 11 described above, acquires a captured image from the imaging device C2, and extracts a person to be processed from the captured image. Then, an area in the captured image where the extracted person is located is also specified. Then, the face authentication system 20 of the adjacent gate G2 notifies the face authentication system 10 of the gate G1 as a response result to the inquiry as to whether or not a person is reflected in the central area.

  The target determination unit 12 of the face authentication system 10 of the gate G1 that has received the notification of the response result to the inquiry from the face authentication system of the adjacent gate G20 determines as follows according to the response result. When the target determination unit 12 receives a notification that any person is shown in the central region of the captured image of the adjacent gate G2 (example in FIGS. 3 and 4), the person is captured by the own gate G1. It is determined that the person P20 is located in the edge region of the image. In this case, the face authentication system 10 of the own gate G1 determines that the person P20 located in the end region of the captured image is excluded from the comparison target. On the other hand, when the target determination unit 12 receives a notification that no person is shown in the central area of the captured image of the adjacent gate G2 (example in FIGS. 5 and 6), the captured image of the own gate G1. It is determined that the person P12 located in the edge region is the target for collation.

  By determining whether or not a person is an object to be collated by the method as described above, each face authentication system 10 and 20 performs a person extraction process, so that the process concentrates on one face authentication system. And there is no image transfer. Therefore, the processing load of one face authentication system 10 can be suppressed, the communication amount between the face authentication systems 10 and 20 can be suppressed, and a quick determination can be performed.

  The collation unit 13 (collation unit) performs collation processing on the person determined by the target determination unit 12 as a verification target in the captured image of the own gate G1. In other words, the collation unit 13 does not perform the collation process for the person excluded from the collation target by the target determination unit 12 even if the person is in the captured image of the own gate G1. Here, the collation process is performed as follows, for example. First, a face area of a person to be collated is specified, and a feature amount necessary for collation is generated from the face area. Then, a collation score such as a similarity between the generated feature amount and the feature amount of the person registered in the collation data storage unit 17 in advance is calculated, and it is determined whether or not the collation score is higher than a threshold value. If the matching score is higher than the threshold value, it is determined that the matching is successful, and the person who is going to pass through the gate G1 is determined to be a person registered in advance. At this time, the feature amount of the person detected for matching may be a feature amount used in the existing face matching technique, or may be a feature amount calculated by any method. The collation method may be any method.

  The gate control unit 14 first determines whether or not a person can pass through the gate G <b> 1 based on the collation result by the collation unit 13. Specifically, it is determined that a person who has been verified by the verification unit 13 can pass. Further, the gate control unit 14 has a function of displaying the collation result, that is, the success or failure of the collation, on the display device D1. Furthermore, the gate control unit 14 also has a gate control function for opening and closing the gate G1, and controls the gate G1 to be opened for a person who is determined to be able to pass through.

  In addition, the display device D1 is disposed with a display surface facing a pre-passage region of the gate G1 so that a person who wants to pass through the gate G1 is visible. However, the display device D1 is not necessarily equipped.

[Operation]
Next, the operation of the face authentication system 10 described above will be described with reference to the flowchart of FIG. Here, the operation of the face authentication system 10 corresponding to the gate G1 will be described, and the case where the shooting situation by the imaging device C1 is the situation shown in FIGS. 3 to 6 will be described as an example.

  The imaging device C1 corresponding to the gate G1 continues to capture an image of the region before passing through the gate G1. Then, the face authentication system 10 always performs the following processing on the captured image.

  First, the target extraction unit 11 extracts a person (target) to be processed from the captured image (step S1). Then, when the person P20 is located in the end region of the captured image, the target determination unit 12 acquires a captured image captured by the imaging device C2 of the face authentication system 20 corresponding to the adjacent gate G2 ( Step S2). At this time, the captured image of the adjacent gate G2 is acquired at the same timing as the captured image of the own gate G1.

  Subsequently, the target determination unit 12 checks whether or not the person P20 located in the end region of the captured image of the own gate G1 is reflected in the central region of the captured image of the adjacent gate G2 (step S3). Then, when any person is shown in the central area of the captured image of the adjacent gate G2, the target determining unit 12 is the person P20 located in the end area of the captured image of the own gate G1. Judge that there is. In this case, the face authentication system 10 of the own gate G1 determines that the person P20 located in the end region is excluded from the verification target.

  For example, in the situation of FIG. 3, the person P20 located in the end region of the captured image of the own gate G1 shown in FIG. 4A is located in the central region of the captured image of the adjacent gate G2 shown in FIG. Therefore, the person P20 is excluded from the verification target by the face authentication system 10 of the own gate G1 (Yes in step S3). Further, in the situation of FIG. 5, the person P12 located in the end region of the captured image of the own gate G1 shown in FIG. 6A is positioned in the central region of the captured image of the adjacent gate G2 shown in FIG. Not done. For this reason, this person P12 is not excluded from the verification target by the face authentication system 10 of the own gate G1, but is set as the verification target (No in step S3).

  Subsequently, the collation unit 13 performs collation processing on the person determined as the collation target in the captured image of the own gate G1 by the target determination unit 12 (step S4). 3 and FIG. 4, the collation process for only the person P10 is started. In the examples of FIG. 5 and FIG. 6, the collation process for the person P10 and the person P12 is started. In the collation process, first, a feature amount necessary for collation is detected from the face area of the person to be collated, and collated with the feature amount of the person registered in the collation data storage unit 17 in advance to obtain a collation score. To do. And it is determined whether a collation score is more than a threshold value.

  As a result of the collation processing by the collation unit, when the person who is going to pass is successfully collated (Yes in step S5), the gate control unit 14 permits the passage of the person to the gate G1 and controls to open the gate G1 (step S6). ).

  As described above, according to the face authentication system 10 of the present embodiment, it is possible to suppress the matching process for the person P20 who is going to pass through the adjacent gate G2, and to appropriately match the persons P10 and P12 who are going to pass through the own gate G1. can do. For example, in the example of FIGS. 3 and 4, the person P10 who is going to pass through the own gate G1 is collated, but the person P20 who is going through the adjacent gate G2 is not collated. In the example of FIGS. 5 and 6, even the person P12 shown in the end region of the captured image is about to pass through the own gate G1, and therefore the matching process is appropriately performed. As a result, erroneous recognition of a person who tries to pass through another gate can be suppressed.

  In the above, the captured image of the adjacent gate G2 is compared with the captured image of the own gate G1, but not only the captured image of the adjacent gate G2, but the captured image of another gate (for example, the gate G3) is compared. May be. In the above description, the end region of the captured image of the own gate G1 is compared with the central region of the adjacent gate G2, but the region to be compared is not limited to the above-described regions. You may compare between any area | regions of the picked-up image in a different gate.

  In the above description, the face authentication system 10 corresponding to the self-gate G1 acquires a captured image of the adjacent gate G2 and determines whether or not a person is a collation target. It may be performed by the face authentication system of the gate G2. That is, the face authentication system 10 of the own gate G1 provides the captured image to the face authentication system 20 of the adjacent gate G2, and the face authentication system 20 of the adjacent gate G2 returns the determination result to the face authentication system 10 of the own gate G1. Also good. Further, such a determination process may be performed by another information processing apparatus.

  Further, as described above, the face authentication system 10 inquires of the face authentication system 20 of the adjacent gate G2 whether or not a person is reflected in the central area of the photographed image at the adjacent gate G2, and the response result is as follows. Accordingly, it may be determined whether or not a person is a target for verification. In this case, when a notice that any person is reflected in the central area of the captured image of the adjacent gate G2 is received, the person located in the end area of the captured image of the own gate G1 is excluded from the verification target. Judge that. On the other hand, when a notification is received that no person is shown in the central region of the captured image of the adjacent gate G2, it is determined that the person located in the end region of the captured image of the own gate G1 is to be collated.

  Moreover, although the case where the object which is going to pass the gate G1 was a person was illustrated above, it is not limited to a person and may be any object. For example, it may be an object such as luggage.

<Embodiment 2>
Next, a second embodiment of the present invention will be described with reference to FIGS. 8 to 12 are diagrams for explaining the processing operation of the face authentication system. In particular, FIG. 12 is a flowchart showing the operation of the face authentication system.

  The face authentication system 10 according to the present embodiment has the same configuration as that according to the first embodiment described above, but the determination process for determining whether or not a person appearing in a captured image of the own gate G1 is to be collated is different. Hereinafter, the configuration different from the first embodiment will be mainly described in detail.

  In the present embodiment, when the target extraction unit 11 extracts the person P20 from the edge region of the captured image of the own gate G1 by the target extraction unit 11 (step S11), the same person as the person P20 is captured by the other gate G2. It is determined whether or not it is located in the central area of the image. In the example of FIGS. 8 and 10, since the person P20 is shown in the right end region of the captured image corresponding to the own gate G1, the target determination unit 12 has the imaging device C2 of the gate G2 adjacent to the right side of the gate G1. The photographed image photographed at is acquired (step S12). Specifically, the target determination unit 12 communicates with the face authentication system 20 of the adjacent gate G2 via the communication unit 16, and at the same timing (for example, the same time) when the captured image is captured by the gate G1. A photographed image photographed by the gate G2 is acquired. It is assumed that the positional relationships of the face authentication systems (imaging devices C1, C2, C3) respectively corresponding to the gates G1, G2, G3 are registered in advance in each system.

  Then, the target determination unit 12 includes a person P20 located in the end area of the captured image of the own gate G1 and a person P20 located in the center area (second area) of the captured image of the adjacent gate G2. Determine identity. In the present embodiment, first, a face area of each person is specified, and a feature amount necessary for collation is detected from the face area (step S13). Then, it is determined from the feature amounts of both persons whether or not both persons are the same person (step S14). It should be noted that the process for determining whether or not the person matches may be a process with lower accuracy than the collation process described later. For example, only the feature amount of a part of a person may be detected, or gender and age may be detected from the feature amount, and the identity may be determined from these pieces of information. However, the process for determining the identity of a person may be any process.

  When the target determination unit 12 determines that the same person as the person P20 located in the end region of the captured image of the own gate G1 is located in the central region of the captured image of the adjacent gate G2, It is determined that the person P20 is a person heading to the adjacent gate G2 (Yes in step S15). In this case, the face authentication system 10 of the own gate G1 determines that the person P20 located in the end region is excluded from the verification target. On the other hand, when the target determination unit 12 determines that the same person as the person P12 positioned in the end region of the captured image of the own gate G1 is not positioned in the central region of the captured image of the adjacent gate G2. The person P12 is determined to be the person heading to the own gate G1 (No in step S15). In this case, the face authentication system 10 of the own gate G1 determines that the person P12 located in the end region is the target of collation. Note that the end region (first region) of the captured image of the own gate G1 and the central region (second region) of the captured image of the adjacent gate G2 are regions different from each other when compared with the captured images. In FIG. 2, the regions overlap each other.

  For example, in the situation of FIG. 8, the same person as the person P20 located in the end region of the captured image of the own gate G1 shown in FIG. 9A is the central region of the captured image of the adjacent gate G2 shown in FIG. Therefore, the person P20 is excluded from the verification target by the face authentication system 10 of the own gate G1. That is, the face authentication system 10 of the self-gate G1 sets only the person P10 located in the center area of the captured image as a comparison target. In the situation of FIG. 10, the same person as the person P12 located in the end region of the captured image of the own gate G1 shown in FIG. 11A is the central region of the captured image of the adjacent gate G2 shown in FIG. Is not located. For this reason, the person P12 is a collation target by the face authentication system 10 of the own gate G1. That is, the face authentication system 10 of the own gate G1 sets the person P10 located in the central area of the captured image and the person P12 located in the end area as the collation targets.

  The collation unit 13 (collation unit) performs collation processing on the person determined as the collation target in the captured image of the own gate G1 by the object determination unit 12 (step S16). In other words, the collation unit 13 does not perform the collation process for the person excluded from the collation target by the target determination unit 12 even if the person is in the captured image of the own gate G1. Here, the collation process is performed as follows, for example. First, a face area of a person to be collated is specified, and a feature amount necessary for collation is generated from the face area. Then, a collation score such as a similarity between the generated feature amount and the feature amount of the person registered in the collation data storage unit 17 in advance is calculated, and it is determined whether or not the collation score is higher than a threshold value. If the matching score is higher than the threshold value, it is determined that the matching is successful, and the person who is going to pass through the gate G1 is determined to be a person registered in advance. Note that any verification method may be used.

  The gate control unit 14 determines whether or not a person can pass through the gate G <b> 1 based on the collation result by the collation unit 13. Specifically, it is determined that a person who has been successfully verified by the verification unit 13 can pass (step S17), and control is performed to open the gate G1 (step S18).

  As described above, in the face authentication system according to the present embodiment, by extracting and comparing the feature amount of the person in the captured image corresponding to each gate, the same object is duplicated in the captured image of each gate. It is possible to more reliably determine whether or not Then, it is possible to exclude from the collation process an object that is duplicated in a predetermined gate and another gate, and to suppress erroneous recognition of the object that attempts to pass through the gate. Furthermore, it is possible to use the feature amount of the object extracted for determining the overlap of the objects for the collation process, and to improve the efficiency of the process.

  In addition, although the case where the object which is going to pass the gate G1 was a person was illustrated above, it is not limited to a person and may be any object. For example, it may be an object such as luggage.

<Embodiment 3>
Next, a third embodiment of the present invention will be described. The face authentication system 10 according to the present embodiment basically determines whether or not the person appearing in the edge area of the captured image is the person facing the own gate G1, as in the first embodiment described above. To do. That is, depending on whether or not the person shown in the edge area of the captured image of the own gate G1 is reflected in the central area of the captured image taken by the face authentication system 20 corresponding to the other gate G2, It is determined whether the person is heading to the gate G1. However, in this embodiment, the determination process is different as follows. Hereinafter, the configuration different from the first embodiment will be mainly described in detail.

  First, as in the first embodiment, the target extraction unit 11 in the present embodiment acquires a captured image from the imaging device C1, and extracts a person to be processed from within the captured image. At this time, the target extraction unit 11 also identifies an area in the captured image where the extracted person is located. Then, the target extraction unit 11 according to the present embodiment determines whether or not the feature, which is the determination information of the person shown in the end region, exceeds the reference value, and according to the determination result, the person extracts his / her own gate. A process of determining whether or not the person is heading for G1 is performed.

  As an example, the target extraction unit 11 first extracts a face area of a person located in the end area of the captured image. The extraction of the person's face area is performed, for example, by determining the position or color of the moving person relative to the whole image. Then, the target extraction unit 11 detects the characteristics of the person as the determination information from the face area. In the present embodiment, the feature of a person as determination information is a distance between eyes of the person (inter-eye distance).

  And the object determination part 12 in this embodiment investigates whether the distance between eyes which is the determination information detected by the object extraction part 11 exceeds the reference value. Here, in the present embodiment, the reference value is set to a value with which it is possible to determine whether or not the person shown in the end region of the captured image of the own gate G1 is located in the lane R1 of the own gate G1. Has been. For example, in the situation of FIG. 10 described above, the distance between the eyes of the person P12 that appears in the edge region of the captured image of the own gate G1 and goes toward the own gate G1 is considered to be larger than the distance between the eyes of the person P20 of the adjacent gate G2. It is done. In consideration of this, the reference value is reflected in the edge region of the captured image of the own gate G1, and is between the distance between the eyes of the person P12 proceeding to the own gate G1 and the distance between the eyes of the person P20 of the adjacent gate G2. Set to a value.

  Then, when the distance between the eyes of the person shown in the edge region of the captured image of the gate G1 detected by the target extraction unit 11 exceeds the reference value, the target determination unit 12 goes to the own gate G1. It is determined that the person is a person and is subjected to collation processing. That is, when the distance between the eyes of the person exceeds the reference value, the comparison process is performed as a person who goes directly to the own gate G1 without comparing with the captured image of the adjacent gate G2.

  On the other hand, when the distance between the eyes of the person shown in the edge region of the captured image of the own gate G1 detected by the target extraction unit 11 is equal to or less than the reference value, the target determination unit 12 goes to the adjacent gate G2. Since there is a possibility of being a person, a comparison is made with the captured image of the adjacent gate G2. That is, as described in the first embodiment, it is checked whether any person is shown in the central area of the captured image of the adjacent gate G2. If a person is shown in the center area of the captured image of the adjacent gate G2, it is determined that the person shown in the end area of the captured image of the own gate G1 is a person heading to the adjacent gate G2, and is excluded from the target of the matching process To do. When a person is not shown in the center area of the captured image of the adjacent gate G2, it is determined that the person shown in the end area of the captured image of the own gate G1 is a person heading to the own gate G1, and To do.

  For example, in the case of the example of FIGS. 10 and 11, the person P12 is first shown in the end region of the captured image of the own gate G1, but the person P12 is close to the imaging device C1 of the own gate G1. Therefore, the distance between eyes, which is the determination information indicating the size of the person P12, becomes larger than the reference value. For this reason, it is determined that the person P12 is a person heading to the own gate G1, and is set as a target for the matching process. That is, even if there is a person P20 heading to the adjacent gate G2, the person P12 of the own gate G1 can be the target of the matching process.

  On the other hand, for example, in the case of the examples of FIGS. 8 and 9, first, a person P20 appears in the end region of the captured image of the own gate G1, but the person P20 is far away from the imaging device C1 of the own gate G1. The distance between eyes, which is determination information indicating the size of the person P20, is equal to or less than the reference value. Therefore, it is checked whether or not the person P20 is reflected in the central area of the captured image of the adjacent gate G2. In this case, since a person is reflected in the central area of the captured image of the adjacent gate G2, it is determined that the person reflected in the end area of the captured image of the own gate G1 is a person heading to the adjacent gate G2, and the matching processing is performed. exclude.

  In the above, the case where the determination information of the person shown in the edge region of the captured image of the own gate G1 is the distance between eyes is exemplified, but the feature of the person as the determination information is that other than that constituting the face of the person The distance between the parts may be a value representing the size of another part of the person. However, the characteristic of the person as the determination information is not necessarily limited to a value representing the size of the part of the person.

<Embodiment 4>
Next, a fourth embodiment of the present invention will be described with reference to FIGS. FIG. 13 is a block diagram showing the configuration of the face authentication system in this embodiment, and FIGS. 14 to 16 are diagrams for explaining the processing operation of the face authentication system.

  The face authentication system 10 in the present embodiment has the same configuration as that in the first embodiment described above, but further, as described in the first and second embodiments, the captured images of adjacent gates overlap each other. , It has a function of setting an overlapping area, which is an area for comparing whether or not the same person is located. Hereinafter, the configuration different from the first and second embodiments will be mainly described in detail.

  As shown in FIG. 13, the face authentication system 10 according to the present embodiment includes an area setting unit 15 (area setting means) that is constructed by an arithmetic device executing a program. The area setting unit 15 first acquires a captured image from the imaging device C1 of its own gate G1, and also acquires a captured image from the imaging device C2 of the adjacent gate G2. At this time, the area setting unit 15 communicates with the face authentication system 20 of the adjacent gate G2 via the communication unit 16, and at the gate G2 at the same timing (for example, at the same time) when the captured image is captured by the gate G1. Acquire the captured image.

  Subsequently, the area setting unit 15 extracts a person from the acquired captured image of the gate G1 and the acquired captured image of the gate G2. The person is extracted by, for example, extracting a moving object, or determining from a position of a characteristic shape portion or a color position with respect to the entire shape of the object or the entire image. Then, the area setting unit 15 checks whether or not the same person appears in both captured images. At this time, the area setting unit 15 identifies the face area of each person shown in each captured image, and detects a feature amount necessary for collation from the face area. And it is investigated from the feature-value of each person whether each person is the same person. The process for determining the identity of a person may be any process.

  If the area setting unit 15 determines that the same person is reflected in each captured image, the area surrounding the portion where the same person is reflected in each captured image is included in each captured image. Set as overlapping areas that overlap each other. At this time, the overlapping region to be set is a region in which the portion where the same person is detected is expanded to the upper and lower ends of the captured image, and the region is further expanded by a predetermined range in the horizontal direction of the captured image. In particular, in the captured image of the own gate G1, it is conceivable that the extracted portion of the same person is located near one end in the horizontal direction of the captured image, but it is slightly expanded in the horizontal direction with respect to the extracted portion of the person. The range is set as an overlapping area (first area), and an overlapping area (first area) having the same width is also set near the opposite end. On the other hand, regarding the captured image of the adjacent gate G2, it is conceivable that the extracted portion of the same person is located near the center in the horizontal direction of the captured image, but is wider than the overlapping region of the end region with respect to the extracted portion of the person. A range expanded in the horizontal direction is set as an overlapping region (second region). That is, in the present embodiment, the central region is set wider than the end region described above. However, the method for setting the width of the end region and the center region is not limited to the method described above.

  As an example, in the situation shown in FIG. 14, first, a captured image of a shooting region sandwiched by the reference C1a line can be acquired from the imaging device C1 of the own gate G1, and sandwiched by the reference C2a line from the imaging device C2 of the adjacent gate G2. A captured image of the captured image area can be acquired. By extracting the same person from both the captured images of FIGS. 15A and 15B, the same person P20 is placed in the end region of the captured image of the own gate G1 and the central region of the captured image of the adjacent gate G2. Is detected. In this case, as for the photographed image of the own gate G1, as shown in FIG. 16 (a), a code C1a in which the extracted area of the person P20 is expanded in the vertical direction (shaded area) is slightly expanded in the horizontal direction. , C1b is set as an overlapping area. In addition, an overlapping region sandwiched between C1a and C1b is also set in the opposite end region in the horizontal direction. On the other hand, as shown in FIG. 16B, the photographed image of the adjacent gate G2 is represented by a reference C2b in which a region (hatched region) obtained by extending the extracted person P20 in the vertical direction is further widened in the horizontal direction. The sandwiched area is set as an overlapping area.

  As described above, in the present embodiment, the region setting unit 15 of the face authentication system 10 corresponding to the gate G1 determines the end region of the captured image of the own gate G1 and the central region of the captured image of the adjacent gate G2. Automatically set as overlapping area. Then, as described in the first and second embodiments, the face authentication system 10 extracts a person from the set end region of the captured image of the own gate G1 and the central region of the captured image of the adjacent gate G2, Processing such as determining whether or not the same person exists in both areas is performed.

  According to the face authentication system 10 of the fourth embodiment described above, each photographing corresponding to each gate is based on the person in the photographed image corresponding to the predetermined gate and the person in the photographed image corresponding to the other gate. It is possible to automatically set an overlapping area between images. As a result, the overlapping area between the imaging devices C1 and C2 of the gates G1 and G2 adjacent to each other can be set appropriately, facilitating the use of the collation system, and suppressing erroneous recognition with higher accuracy. it can.

  In the above, the case where the overlapping range is set using the image of the person who is going to pass through the gates G1 and G2 has been illustrated. However, the overlapping range is set using any object in which the captured image is displayed, not limited to the person. Also good. For example, it is possible to determine the identity of articles and landscapes that appear in each captured image, and set the overlapping range of each captured image based on the determination result.

<Embodiment 5>
Next, a fifth embodiment of the present invention will be described with reference to FIGS. FIG. 17 is a block diagram illustrating a configuration of a verification system according to the fifth embodiment. FIG. 18 is a block diagram illustrating a configuration of the information processing apparatus according to the fifth embodiment. In the present embodiment, an outline of the configuration of the face authentication system described in the first to fourth embodiments is shown.

As shown in FIG. 17, the collation system 100 in this embodiment is
An imaging means 110 for acquiring a captured image of each pre-passage region for each gate installed in parallel;
For each gate, for each of the captured images of each pre-passage area, a matching unit 120 that performs a matching process between a target registered in advance and a target included in the captured image;
Is provided.
And the collation means 120 performs collation processing based on the object in the photographed image corresponding to the predetermined gate and the object in the photographed image corresponding to the other gate.
The configuration is as follows.

Moreover, in this embodiment, you may remove the imaging means 110 from the collation system 100 shown in FIG.
That is, the information processing apparatus 200 in the present embodiment is
A collating unit 210 is provided for performing collation processing between a pre-registered target and a target included in the captured image with respect to each captured image of each pre-passage region for each gate installed in parallel.
The collation unit 210 performs collation processing based on a target in a captured image corresponding to a predetermined gate and a target in a captured image corresponding to another gate.
The configuration is as follows.

  In addition, the collation means 120 and 210 mentioned above may be constructed | assembled when an arithmetic unit runs a program, and may be constructed | assembled with an electronic circuit.

Then, according to the collation system 100 or the information processing apparatus 200 configured as described above,
There is provided a collation method for performing collation processing between a pre-registered target and a target included in the captured image for each of the captured images of the pre-passage region for each gate installed in parallel.
In the verification method, the verification process is further performed based on the target in the captured image corresponding to the predetermined gate and the target in the captured image corresponding to the other gate.
The configuration is as follows.

  According to the verification system 100 or the information processing apparatus 200 described above, the target verification process is performed based on the target in the captured image corresponding to the predetermined gate and the target in the captured image corresponding to the other gate. For this reason, even when a target image that passes through another gate is shown in a captured image corresponding to a predetermined gate, it is possible to determine that the target is a target that attempts to pass through another gate. Can be excluded from the verification process at a predetermined gate. As a result, it is possible to suppress misrecognition of an object that attempts to pass through the gate.

<Appendix>
Part or all of the above-described embodiment can be described as in the following supplementary notes. The outline of the configuration of the collation system, information processing apparatus, program, and collation method in the present invention will be described below. However, the present invention is not limited to the following configuration.

(Appendix 1)
Imaging means for acquiring each captured image of each pre-passage region for each gate installed in parallel;
For each of the gates, a matching unit that performs a matching process between a target registered in advance and a target included in the captured image with respect to each of the captured images in each of the pre-passage areas,
With
The collation means performs the collation processing based on a target in the captured image corresponding to the predetermined gate and a target in the captured image corresponding to another gate.
Matching system.

  According to the above configuration, the matching system performs target matching processing based on the target in the captured image corresponding to the predetermined gate and the target in the captured image corresponding to the other gate. For this reason, even when a target image that passes through another gate is shown in a captured image corresponding to a predetermined gate, it is possible to determine that the target is a target that attempts to pass through another gate. Can be excluded from the verification process at a predetermined gate. As a result, it is possible to suppress misrecognition of an object that attempts to pass through the gate.

(Appendix 2)
A verification system according to attachment 1, wherein
The collation means performs the collation processing based on a target located in a predetermined region of the captured image corresponding to the predetermined gate and a target in the captured image corresponding to the other gate.
Matching system.

(Appendix 3)
A verification system according to attachment 2, wherein
The collating means is based on an object located in the first region of the photographed image corresponding to the predetermined gate and an object located in the second region in the photographed image corresponding to the other gate, Performing the matching process;
Matching system.

(Appendix 4)
A verification system according to attachment 3, wherein
In the case where the object located in the first region of the photographed image corresponding to the predetermined gate is also located in the second region of the photographed image corresponding to the other gate, Excluding the object located in the first region of the captured image corresponding to the predetermined gate from the matching process;
Matching system.

(Appendix 5)
A verification system according to appendix 4, wherein
In the collating means, a target located in an end region in the horizontal direction that is the first region of the photographed image corresponding to the predetermined gate is the second region of the photographed image corresponding to the other gate. Exclude from the collation process the object located in the horizontal end region of the captured image corresponding to the predetermined gate when located in the central region in the horizontal direction;
Matching system.

(Appendix 6)
The verification system according to appendix 4 or 5,
The collating means is configured to detect an object located in the first area of the photographed image corresponding to the predetermined gate at a timing when the object is located in the first area of the photographed image corresponding to the other gate. Excluding the object located in the first region of the captured image corresponding to the predetermined gate from the matching process when located in the second region;
Matching system.

  According to the above configuration, the collation system compares the object shown in the predetermined area in the photographed image corresponding to the predetermined gate with the object shown in the photographed image corresponding to the other gate. The target to be displayed is excluded from the verification process, and only the target to be viewed alone is verified. In particular, an object located in the horizontal end region (first region) in the captured image corresponding to a predetermined gate appears in the horizontal central region (second region) in the captured image corresponding to another gate. If it is, the target collation process is not performed. On the other hand, the object located in the horizontal end region (first region) in the captured image corresponding to the predetermined gate is the horizontal central region (second region) in the captured image corresponding to the other gate. If it is not reflected, the target is collated. As a result, if the target image is duplicated in the captured image corresponding to the predetermined gate and the captured image corresponding to another gate, it can be excluded from the verification process, and the target to pass through the gate Misrecognition can be suppressed.

(Appendix 7)
The verification system according to appendix 4 or 5,
The collating means includes a feature amount of an object located in the first region of the photographed image corresponding to the predetermined gate and a feature of the object located in the second region of the photographed image corresponding to the other gate. Based on the amount, it is determined that an object located in the first region of the photographed image corresponding to the predetermined gate is located in the second region of the photographed image corresponding to the other gate. A target located in the first region of the captured image corresponding to the predetermined gate is excluded from the matching process,
Matching system.

(Appendix 8)
The verification system according to appendix 7,
The collating means includes a feature amount of a part constituting a face of a person who is a target located in the first region of the photographed image corresponding to the predetermined gate, and the photographed image corresponding to the other gate. A target located in the first region of the captured image corresponding to the predetermined gate is based on the feature amount of a part constituting the face of the person who is the target located in the second region, and the other gate If it is determined that the object is located in the second region of the photographed image corresponding to the object, the object located in the first region of the photographed image corresponding to the predetermined gate is excluded from the matching process.
Matching system.

  According to the above configuration, the collation system extracts and compares the feature amount of the target in the captured image corresponding to each gate, thereby more reliably confirming that the same target is duplicated in the captured image of each gate. Can be determined. Then, it is possible to exclude from the collation process an object that is duplicated in a predetermined gate and another gate, and to suppress erroneous recognition of the object that attempts to pass through the gate. Furthermore, it is possible to use the feature amount of the object extracted for determining the overlap of the objects for the collation process, and to improve the efficiency of the process.

(Appendix 9)
A verification system according to any one of appendices 3 to 8,
A target in the captured image corresponding to the predetermined gate, and a target in the captured image corresponding to the other gate acquired at a timing when the target is positioned in the captured image corresponding to the predetermined gate. And an area setting means for setting the first area of the captured image corresponding to the predetermined gate and the second area of the captured image corresponding to the other gate, based on
Matching system.

(Appendix 10)
A verification system according to appendix 9, wherein
The area setting unit corresponds to a target in the captured image corresponding to the predetermined gate and the other gate acquired at a timing when the target is positioned in the captured image corresponding to the predetermined gate. When the target in the captured image is the same, the position of the target in the captured image corresponding to the predetermined gate and the position of the target in the captured image corresponding to the other gate Based on this, the periphery of the target position in the captured image corresponding to the predetermined gate is set as the first region, and the periphery of the target position in the captured image corresponding to the other gate is set to the second region. Set as area,
Matching system.

  According to the above configuration, the collation system overlaps each captured image corresponding to each gate based on the target in the captured image corresponding to the predetermined gate and the target in the captured image corresponding to the other gate. The area to be set can be set automatically. As a result, the use of the verification system can be facilitated, and erroneous recognition can be suppressed with high accuracy.

(Appendix 11)
For each of the captured images of each pre-passage region for each gate installed in parallel, a collation unit that performs collation processing between a pre-registered target and a target included in the captured image,
The collation means performs the collation processing based on a target in the captured image corresponding to the predetermined gate and a target in the captured image corresponding to another gate.
Information processing device.

(Appendix 12)
An information processing apparatus according to appendix 11, wherein
The collation means performs the collation processing based on a target located in a predetermined region of the captured image corresponding to the predetermined gate and a target in the captured image corresponding to the other gate.
Information processing device.

(Appendix 13)
In the information processing device,
A program for realizing collation means for performing collation processing between a pre-registered target and a target included in the captured image with respect to each captured image of each pre-passage region for each gate installed in parallel And
The collation means performs the collation processing based on a target in the captured image corresponding to the predetermined gate and a target in the captured image corresponding to another gate.
program.

(Appendix 14)
The program according to attachment 13, wherein
The collation means performs the collation processing based on a target located in a predetermined region of the captured image corresponding to the predetermined gate and a target in the captured image corresponding to the other gate.
program.

(Appendix 15)
A method of performing a collation process between a pre-registered target and a target included in the captured image for each captured image of each pre-passage region for each gate installed in parallel,
Performing the matching process based on a target in the captured image corresponding to a predetermined gate and a target in the captured image corresponding to another gate;
Matching method.

(Appendix 16)
The verification method according to attachment 15, wherein
Performing the matching process based on an object located in a predetermined area of the captured image corresponding to the predetermined gate and an object in the captured image corresponding to the other gate;
Matching method.

(Appendix 17)
The verification method according to attachment 16, wherein
The matching process is performed based on an object located in the first region of the captured image corresponding to the predetermined gate and an object located in the second region in the captured image corresponding to the other gate. ,
Matching method.

(Appendix 18)
The verification method according to attachment 17, wherein
A target in the captured image corresponding to the predetermined gate, and a target in the captured image corresponding to the other gate acquired at a timing when the target is positioned in the captured image corresponding to the predetermined gate. And setting the first region of the captured image corresponding to the predetermined gate and the second region of the captured image corresponding to the other gate,
An object located in the set first area of the photographed image corresponding to the predetermined gate and an object located in the set second area in the photographed image corresponding to the other gate; Based on the matching process,
Matching method.

  Note that the above-described program is stored in a storage device or recorded on a computer-readable recording medium. For example, the recording medium is a portable medium such as a flexible disk, an optical disk, a magneto-optical disk, and a semiconductor memory.

  Although the present invention has been described with reference to the above-described embodiment and the like, the present invention is not limited to the above-described embodiment. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

DESCRIPTION OF SYMBOLS 10 Face authentication system 11 Object extraction part 12 Object determination part 13 Collation part 14 Gate control part 15 Area | region setting part 16 Communication part 17 Collation data storage part 20 Face authentication system 100 Collation system 110 Imaging means 120 Collation means 200 Information processing apparatus 210 Collation Means C1, C2, C3 Imaging device D1 Display device G1, G2, G3 Gate

Claims (16)

A first imaging means for acquiring a first photographed image that is a photographed image of a pre-passage region with respect to the gate;
A second imaging means for acquiring a second photographed image that is a photographed image of an area including at least a part of the pre-passage area;
Collation means that uses the second captured image in a collation process between a pre-registered target and a target included in the first captured image;
A collation system comprising: The verification system according to claim 1,
The collation means determines a collation target to be subjected to the collation process based on a target located in a predetermined region of the first captured image and a target in the second captured image.
Matching system. The verification system according to claim 2,
The collation means determines the collation target based on an object located in the first area of the first captured image and an object located in the second area of the second captured image.
Matching system. The verification system according to claim 3,
The collation means is configured such that an object located in the first area of the first photographed image is located in the second area of the second photographed image at a timing when the object is located in the first area. In this case, a collation system that excludes a target located in the first region of the first captured image from the collation target. The verification system according to claim 4,
The collating means is based on the feature amount of the object located in the first region of the first photographed image and the feature amount of the object located in the second region of the second photographed image. When it is determined that an object located in the first area of the first photographed image is located in the second area of the second photographed image, the object is located in the first area of the first photographed image. Excluding the located object from the matching object;
Matching system. The verification system according to claim 5,
The collating means includes a distance between eyes of a person who is a target located in the first area of the first photographed image and a distance between eyes of a person who is a subject located in the second area of the second photographed image. And when the target located in the first region of the first photographed image is located in the second region of the second photographed image based on the distance, Excluding the object located in the first region of the captured image from the verification target;
Matching system. The collation system according to any one of claims 3 to 6,
Based on the target in the first captured image and the target in the second captured image acquired at a timing when the target is located in the first captured image, the first captured image An area setting means for setting the first area and the second area of the second photographed image;
Matching system. The collation system according to claim 7,
In the area setting means, the target in the first captured image is the same as the target in the second captured image acquired at the timing when the target is positioned in the first captured image. In this case, based on the position of the target in the first captured image and the position of the target in the second captured image, the periphery of the position of the target in the first captured image is Set as a region, and set the periphery of the target position in the second captured image as the second region,
Matching system. First acquisition means for acquiring a first photographed image that is a photographed image of the pre-passage region with respect to the gate;
Second acquisition means for acquiring a second captured image that is a captured image of an area including at least a part of the pre-passage area;
A collation unit that uses the second photographed image in a collation process between a pre-registered object and a target included in the first photographed image;
An information processing apparatus comprising: The information processing apparatus according to claim 9,
The collation means determines a collation target to be subjected to the collation process based on a target located in a predetermined region of the first captured image and a target in the second captured image.
Information processing device. In the information processing device,
First acquisition means for acquiring a first photographed image that is a photographed image of the pre-passage region with respect to the gate;
Second acquisition means for acquiring a second captured image that is a captured image of an area including at least a part of the pre-passage area;
A collation unit that uses the second photographed image in a collation process between a pre-registered object and a target included in the first photographed image;
A program to realize The program according to claim 11,
The collation means determines a collation target to be subjected to the collation process based on a target located in a predetermined region of the first captured image and a target in the second captured image.
program. A first acquisition step of acquiring a first photographed image that is a photographed image of the pre-passage region with respect to the gate;
A second acquisition step of acquiring a second captured image that is a captured image of an area including at least a part of the pre-passage area;
A collation step using the second captured image in a collation process between a pre-registered target and a target included in the first captured image,
Matching method. The collation method according to claim 13,
Determining a collation target for performing the collation process based on a target located in a predetermined region of the first captured image and a target in the second captured image;
Matching method. The verification method according to claim 14, comprising:
The collation target is determined based on a target located in the first region of the first captured image and a target located in the second region in the second captured image.
Matching method. The collation method according to claim 15,
When the object located in the first area of the first photographed image is also located in the second area of the second photographed image at the timing when the object is located in the first area, Excluding the object located in the first region of the first photographed image from the verification target;
Matching method.

Images