JP2016035675A - Collation device and collation method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a collation device and a collation method that can achieve collation with higher accuracy.SOLUTION: A collation device 1 includes an image acquisition part 11, a parameter calculation part 12, an image evaluation part 13, an evaluation result notification part 14, a collation part 15, a storage part 16, and a collation result notification part 17. The parameter calculation part 12 includes a face position calculation part 121, a face size calculation part 122, a standing position calculation part 123, and a blur degree calculation part 124 to calculate, as parameters, the position of a face, the size of a face, a standing position, and the degree of blur. The image evaluation part 13 evaluates whether or not image data is suitable for collation on the basis of the parameters calculated by the parameter calculation part 12.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a collation apparatus and a collation method that perform collation based on face image data.

  Conventionally, a person to be authenticated is photographed, and the acquired face image data is compared with the face image data registered in advance, and whether the photographed person is a person registered in advance. Personal authentication is performed to verify whether. In such personal authentication, the acquired image data is not suitable for collation, and collation could not be performed or misidentified as another person. Thus, it has been proposed to evaluate the acquired image data (see, for example, Patent Documents 1 and 2).

For example, in Patent Literature 1, three-dimensional data of the face area of the person to be authenticated is acquired at multiple points, the quality of the three-dimensional data is evaluated for each acquisition point, and quality data is generated. It has been proposed to grasp the lack of three-dimensional data by obtaining the quality distribution in the face area.
Further, in Patent Document 2, quality data that is a quality evaluation value of 3D data is generated based on 2D image data, and lack of 3D data is grasped based on the quality data.

JP 2008-009769 A JP 2008-198193 A

  However, since the quality parameter of the image data is related not only to the lack of 3D data but also to other parameters, it is difficult to collate with higher accuracy by the conventional method as described above.

  Therefore, an object of the present invention is to provide a collation apparatus and a collation method that can realize collation with higher accuracy.

  In order to solve the above-described problems, a collation device according to the present invention captures a person to be collated, generates a plurality of image units of the image of the person to be collated, and based on the image data, Based on the face position calculation unit that calculates the position of the face of the person to be collated in the image, the face size calculation unit that calculates the size of the face of the person to be collated in the image, based on the image data, A standing position calculation unit that calculates the standing position of the person to be collated, a blur condition calculation unit that calculates the degree of blur of the image based on the image data, and a face position and a face size calculation unit that are calculated by the face position calculation unit Whether or not the image data is suitable for collation is evaluated based on the face size calculated by the above, the standing position calculated by the standing position calculation unit, and the blur condition of the image calculated by the blur condition calculation unit. When the evaluation unit evaluates that the image data is not suitable for collation, the image capturing unit stores a re-shooting instruction unit that causes the image of the person to be collated again, and stores image data of the image of the person to be collated And a collation unit that collates the image data captured by the imaging unit and the image data stored in the storage unit when the evaluation unit evaluates that the image data is suitable for collation. It is characterized by.

  The collation apparatus further includes a movement speed calculation unit that calculates a movement speed of the verification target person based on the time when the imaging unit images the verification target person and the position of the verification target person in the image. Further, it may be evaluated whether or not re-acquisition of the image is necessary based on the movement speed of the person to be collated calculated by the movement speed calculation unit.

  The collation apparatus further includes a direction calculation unit that calculates a direction of the face of the person to be collated based on the image data, and the evaluation unit performs image processing based on the direction of the face of the person to be collated calculated by the direction calculation unit. It may be possible to evaluate whether or not reacquisition is necessary.

  Further, in the collation method according to the present invention, an imaging step in which a plurality of imaging units captures a person to be collated and generates image data of an image of the person to be collated, and a face position calculation unit is generated by the imaging unit. A face position calculating step for calculating the position of the face of the person to be verified in the image based on the obtained image data, and a face size calculating unit based on the image data generated by the imaging part. A face size calculating step for calculating the size of the face, a standing position calculating unit for calculating a standing position of the person to be verified based on the image data generated by the imaging unit, and a blur condition calculating unit A blur condition calculating step for calculating a blur condition of the image based on the image data generated by the imaging unit, and the evaluation unit calculating the face position and the face size calculated by the face position calculating unit. Whether or not the image data is suitable for collation is evaluated based on the face size calculated by the above, the standing position calculated by the standing position calculation unit, and the blur condition of the image calculated by the blur condition calculation unit. When the evaluation step and the re-shooting instruction unit evaluate that the image data is not suitable for matching by the evaluation unit, the re-shooting instruction step for causing the imaging unit to re-capture the person to be checked and the storage unit The storage step for storing the image data of the image of the subject and the collation unit store the image data captured by the imaging unit and the storage unit when the evaluation unit evaluates that the image data is suitable for collation. And a collation step for collating with the image data.

  According to the present invention, whether image data is suitable for collation is evaluated based on the face position, face size, standing position, and degree of blur, and collation is performed using image data that is evaluated as suitable for collation. As a result, collation with higher accuracy can be realized.

FIG. 1 is a block diagram showing the configuration of the verification system. FIG. 2 is a diagram for explaining a method for calculating the position and size of a face. FIG. 3 is a diagram for explaining a method of calculating the standing position. FIG. 4 is a flowchart for explaining the operation of the collation system. FIG. 5 is a flowchart for explaining the image data evaluation operation. FIG. 6 is a flowchart for explaining a method of calculating the moving speed. FIG. 7 is a diagram for explaining a method of calculating the orientation of the face.

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

<Configuration of verification system>
FIG. 1 is a block diagram showing a configuration of a verification system including a verification device according to the present embodiment. The verification system shown in FIG. 1 includes, for example, a verification device 1 installed in a building management room, a reception device 2 installed at the entrance of the building, a room entrance in the building, and the reception device. 2, a camera 3 that transmits captured image data to the reception device 2, a monitor 4 that is installed in the vicinity of the reception device 2 and displays various information based on instructions from the reception device 2, And an electric lock 5 for locking and unlocking the entrance and the door of the room based on the instruction.
Such a collation system transmits image data of the face of a user who wishes to enter or enter the room (hereinafter referred to as “verification target person”) captured by the camera 3 to the collation device 1 via the accepting device 2. Then, the collation device 1 confirms whether the person included in the image data is a person permitted to enter the building or room where the reception device 2 is installed. The electric lock 5 is locked and unlocked based on the result confirmed by the above.

<< Configuration of collation device 1 >>
The collation device 1 includes an image acquisition unit 11, a parameter calculation unit 12, an image evaluation unit 13, an evaluation result notification unit 14, a collation unit 15, a storage unit 16, and a collation result notification unit 17. .

  The image acquisition unit 11 is a functional unit that acquires image data captured by the camera 3 via the reception device 2. The image data acquired by the image acquisition unit 11 is sent to the parameter calculation unit 12 and the collation unit 15.

  The parameter calculation unit 12 is a functional unit that calculates various parameters of the image data acquired by the image acquisition unit 11. The parameter calculation unit 12 includes a face position calculation unit 121, a face size calculation unit 122, a standing position calculation unit 123, and a blur condition calculation unit 124. As parameters, the face position, face size, standing position, and Calculate the degree of blur. The calculated parameters are sent to the image evaluation unit 13.

  The face position calculation unit 121 is a functional unit that calculates the position of the face of the person to be collated in the image data (hereinafter also referred to as “face position”). For example, as shown in FIG. 2, the position of the face is a rectangular shape including the face of the person to be collated from one of the two pieces of image data d captured by the camera 3 that is a stereo camera, as will be described later. This is done by detecting the area b and calculating the diagonal coordinates of this rectangular area. In the case of FIG. 2, assuming that the horizontal direction is the x axis and the vertical direction is the y axis, the diagonal coordinates (x1, y1), (x2, y2) of the rectangular region b are calculated as the face position.

  The face size calculation unit 122 is a functional unit that calculates the size of the face of the person to be verified in the image data (hereinafter also referred to as “face size”). For example, as shown in FIG. 2, the size of the face is set to the width when the diagonal coordinates of the rectangular area b including the face of the person to be collated are (x1, y1), (x2, y2) from the image data d. Calculated as x2-x1 and height as y2-y1.

  The standing position calculation unit 123 is a functional unit that calculates the standing position of the verification target person with respect to the camera 3. For example, as shown in FIG. 3, the standing position is created by creating three-dimensional data d3 of the face of the person to be collated consisting of point groups from two image data d1 and d2 captured by the camera 3 consisting of a stereo camera. The average value (center of gravity) of the group or the coordinates (x, y, z) of the middle point between the left and right pupils are calculated as the standing position from the camera 3. The z-axis coordinate represents the distance from the camera 3.

The blur condition calculation unit 124 is a functional unit that calculates the degree of blur of image data. The degree of blur is calculated by, for example, blur degree = Σ (attention pixel−adjacent pixel) ² . Here, the adjacent pixels may be either four pixels adjacent in the vertical and horizontal directions of the target pixel or eight pixels adjacent in the vertical and horizontal diagonal directions. Further, the target pixel is set to a pixel corresponding to the face of the person to be verified. According to the above equation, when there is blur, the difference between the target pixel and the adjacent pixel is small, and the calculated numerical value is small.

  The image evaluation unit 13 is a functional unit that evaluates whether or not the image data is suitable for collation based on each parameter calculated by the parameter calculation unit 12. The evaluation result by the image evaluation unit 13 is sent to the evaluation result notification unit 14 and the collation unit 15.

  The evaluation result notification unit 14 is a functional unit that notifies the reception device 2 of the evaluation result by the image evaluation unit 13.

  When the image evaluation unit 13 evaluates that re-acquisition of the image is not necessary, the collation unit 15 acquires the image data acquired by the image acquisition unit 11 and the person who is permitted to enter the room stored in the storage unit 16 in advance. It is a functional unit that collates with image data. The collation result by the collation unit 15 is sent to the collation result notification unit 17.

  The storage unit 16 is a functional unit that stores various data necessary for the operation of the verification device 1 such as image data of a person permitted to enter the room, which is used for verification by the verification unit 15.

  The verification result notification unit 17 is a functional unit that notifies the reception device 2 of the verification result by the verification unit 15.

<< Configuration of Reception Device 2 >>
The accepting device 2 includes an imaging control unit 21, a display control unit 22, and a lock control unit 23.

  The imaging control unit 21 is a functional unit that instructs the camera 3 to perform imaging based on an instruction from the verification device 1 and acquires image data captured by the camera 3. The acquired image data is transmitted to the verification device 1.

  The display control unit 22 is a functional unit that transmits information to be displayed on the monitor 4 based on an instruction from the verification device 1.

  The lock control unit 23 is a functional unit that controls locking and unlocking of the electric lock 5 based on an instruction from the verification device 1.

≪Configuration of camera 3≫
The camera 3 is composed of a digital camera that records an image captured by an image sensor as digital data. In the present embodiment, the camera 3 is a stereo camera. Such a camera 3 captures an image based on an instruction from the receiving device 2 and transmits the acquired image data to the receiving device 2.

<< Configuration of Monitor 4 >>
The monitor 4 is provided in the vicinity of the door, and includes a display device such as an LCD (Liquid Crystal Display). Such a monitor 4 displays various information based on instructions from the receiving device 2.

≪Configuration of electric lock 5≫
The electric lock 5 includes a lock system that electrically locks and unlocks a lock provided on the door. Such an electric lock 5 locks and unlocks a lock provided on the door based on an instruction from the receiving device 2.

[Operation of verification system]
Next, the operation of the verification system will be described with reference to FIG.

  First, when a user who wants to enter or enter a room appears, the imaging control unit 21 of the reception apparatus 2 images the user with the camera 3 (step S1). The user image data generated by the camera 3 is sent to the image acquisition unit 11 of the collation device 1 via the imaging control unit 21 of the reception device.

  When the image acquisition unit 11 of the verification device 1 acquires image data from the imaging control unit 21 of the reception device 2 (step S2), the image acquisition unit 11 sends the image data to the parameter calculation unit 12 and the verification unit 15.

  When the image data is acquired, the parameter calculation unit 12 of the collation device 1 calculates various parameters based on the image data (step S3). In the present embodiment, the parameter calculation unit 12 calculates the parameters of the face position, the face size, the standing position, and the degree of blur.

When the parameters are calculated, the image evaluation unit 13 of the collation apparatus 1 evaluates whether the image data generated by the camera 3 is suitable for collation based on the parameters (step S4). This evaluation result is sent to the evaluation result notification unit 14 and the verification unit 15. Here, when it is evaluated that the image data is not suitable for collation, the evaluation result notification unit 14 may be notified of the reason for the evaluation such as a parameter not exceeding the threshold value.
The image data evaluation method by the image evaluation unit 13 will be described later.

When the image evaluation unit 13 evaluates that the image data is not suitable for collation (step S5: NG), the evaluation result notification unit 14 of the collation device 1 sends the image data to the display control unit 22 of the reception device 2. Notification is made that it is not suitable for collation (step 9). Then, since the image data is not suitable for collation, the display control unit 22 causes the monitor 4 to display that the camera 3 will perform re-acquisition. At this time, when the reason for the evaluation result is also notified from the evaluation result notification unit 14, the display control unit 22 may display the reason on the monitor 4.
And it returns to the process of step S1 and a user is made to image with the camera 3 again.

  On the other hand, when the image evaluation unit 13 evaluates that the image data is suitable for collation (step S5: OK), the collation unit 15 of the collation apparatus 1 includes the image data evaluated as suitable for the collation, The image data of the person permitted to enter the room stored in the storage unit 16 is collated (step S6). The collation result by the collation unit 15 is transmitted to the accepting device 2 by the collation result notification unit 17.

  When there is image data to be collated with the image data evaluated to be suitable for collation among the image data of the person permitted to enter the room stored in the storage unit 16 (step S7: OK), the accepting device 2 The lock control unit 23 unlocks the electric lock 5 (step 8). As a result, the person to be verified can enter the room or building that the user wishes to enter or enter.

  On the other hand, when there is no image data to be collated with the image data evaluated to be suitable for collation among the image data of the person permitted to enter the room stored in the storage unit 16 (step S7: NG) The display control unit 22 of the device 2 causes the monitor 4 to display that entry is not permitted (step 9). Then, the lock control unit 23 does not unlock the electric lock 5. Thereby, it is possible to prevent a person who is not registered in the storage unit 16 from entering or entering the building.

As described above, according to the present embodiment, before collation is performed using the image data from the camera 3, whether or not the image data is suitable for collation is evaluated, and collation is performed using image data suitable for collation. I do.
Thereby, since image data not suitable for collation is not used, the accuracy of collation can be improved.
Further, conventionally, when image data that is not suitable for collation is used, image data is re-taken after collation is completed, so in this embodiment, re-photographing is performed before collation. Time can be saved by the amount of non-matching using unsuitable image data.

<Evaluation action>
Next, an image data evaluation method performed by the image evaluation unit 13 will be described with reference to FIG.

  First, the image evaluation unit 13 acquires various parameters from the parameter calculation unit 12, and in this embodiment, the parameters of the face position, the face size, the standing position, and the degree of blur (step S41). Determine whether.

  Specifically, the image evaluation unit 13 determines whether the face position is appropriate (step S42). As described above, for the face position, the face position calculation unit 121 calculates the diagonal coordinates of the rectangular area including the face in the image data. Therefore, for example, when the coordinate range of the area corresponding to the center in the image data is designated in advance and the coordinate of the face position acquired from the parameter calculation unit 12 is included in this range, the face position is appropriate. You may make it determine with it. The coordinate range may be stored in the storage unit 16 in advance.

  When the face position is not appropriate (step S42: NO), the image evaluation unit 13 evaluates that the image data acquired by the camera 3 is not suitable for collation (step S48), and the evaluation result is sent to the evaluation result notification unit 14. (Step S47).

  On the other hand, when the face position is appropriate (step S42: YES), the image evaluation unit 13 determines whether or not the face size is appropriate (step S43). As described above, the face size is calculated by the face size calculation unit 122 by the width and height values of the rectangular area including the face in the image data. Therefore, for example, when an appropriate face size numerical range is specified in advance and the face size value acquired from the parameter calculation unit 12 is included in the numerical range, it is determined that the face position is appropriate. You may do it. The numerical range of the appropriate face size may be stored in the storage unit 16 in advance.

  When the face size is not appropriate (step S43: NO), the image evaluation unit 13 evaluates that the image data acquired by the camera 3 is not suitable for collation (step S48), and the evaluation result is notified to the evaluation result notification unit 14. (Step S47).

  On the other hand, when the face size is appropriate (step S43: YES), the image evaluation unit 13 determines whether the standing position is appropriate (step S44). As described above, the standing position is calculated by coordinates from the camera 3 by the standing position calculation unit 123. Therefore, for example, an appropriate standing position numerical range is specified in advance, and when the standing position value acquired from the parameter calculation unit 12 is included in the numerical range, it is determined that the standing position is appropriate. You may do it. The numerical range of the appropriate standing position may be stored in the storage unit 16 in advance.

  When the standing position is not appropriate (step S44: NO), the image evaluation unit 13 evaluates that the image data acquired by the camera 3 is not suitable for collation (step S48), and the evaluation result is notified to the evaluation result notification unit 14. (Step S47).

  On the other hand, when the standing position is appropriate (step S44: YES), the image evaluation unit 13 determines whether the degree of blur is appropriate (step S45). As described above, the degree of blur is calculated as a numerical value by the blur degree calculation unit 124, and when there is a degree of blur, the numerical value is small. For example, an appropriate blur condition threshold value may be set in advance, and if it is equal to or greater than this threshold value, it may be determined that the blur condition is appropriate. The threshold value may be stored in the storage unit 16 in advance.

  When the degree of blur is not appropriate (step S45: NO), the image evaluation unit 13 evaluates that the image data acquired by the camera 3 is not suitable for collation (step S48), and the evaluation result is notified to the evaluation result notification unit 14. (Step S47).

  On the other hand, when the degree of blur is appropriate (step S45: YES), the image evaluation unit 13 evaluates that the image data acquired by the camera 3 is suitable for collation (step S49), and the evaluation result is notified to the evaluation result notification unit. 14 (step S47).

  As described above, according to the present embodiment, it is evaluated whether image data is suitable for collation based on the face position, face size, standing position, and degree of blur, and is evaluated as suitable for collation. Since collation is performed using the obtained image data, as a result, collation with higher accuracy can be realized.

  In the present embodiment, the face position, the face size, the standing position, and the degree of blur are calculated as parameters, and the case of evaluating whether these are appropriate is described as an example. The quantity is not limited to this, and can be set freely as appropriate. For example, the parameter calculation unit 12 is further provided with a movement speed calculation unit that calculates the movement speed of the person to be verified and a direction calculation unit that calculates the direction of the face, and the movement speed and the direction of the face are calculated as parameters, and these are used. Then, the image data may be evaluated. Hereinafter, an example of a method for calculating the movement speed and the face direction by the movement speed calculation unit and the direction calculation unit will be described.

<Movement speed calculation method>
With reference to FIG. 6, the calculation method of the movement speed by a movement speed calculation part is demonstrated.

  First, when image data is acquired from the image acquisition unit 11 of the collation apparatus 1 (step S61), the moving speed calculation unit acquires the time when the image data was acquired as current_time (step S62).

  When the standing position is calculated by the standing position calculation unit 123 based on the image data (step S63), the moving speed calculation unit acquires the standing position as current_3D (step S64).

  When acquiring current_time and current_3D, the moving speed calculation unit acquires the acquisition time previous_time and the standing position previous_3D of the image data generated based on the image data of the same person to be collated acquired last time, current_time, current_3D, previous_time Based on the previous_3D, the movement speed of the person to be verified is calculated (step S65). Specifically, the previous_time and previous_3D stored in the storage unit 16 are acquired, the time from the previous shooting to the current shooting is calculated from the difference between the current_time and previous_time, and the previous time is calculated from the difference between the current_3D and previous_3D. The moving speed from the time of shooting to the time of the current shooting is calculated, and the moving speed obtained by dividing the moving distance by the time can be obtained. This moving speed is sent to the image evaluation unit 13.

  When the moving speed is calculated, the moving speed calculating unit updates the current_time acquired this time as previous_time and current_3D as previous_3D (step S66). The updated previous_time and previous_3D are stored in the storage unit 16.

  By using such a moving speed, for example, when the camera 3 continuously captures images, it can be detected whether or not the person to be collated is moving. By instructing the person to be collated as described above, image data suitable for collation can be acquired.

<Face orientation calculation method>
Next, with reference to FIG. 7, a method of calculating the face orientation by the orientation calculation unit will be described.

First, a template as indicated by a symbol t in FIG. 7 is prepared in advance. This template is composed of three-dimensional data of a specific face and x-axis, y-axis, and z-axis data set on this three-dimensional data.
Then, the three-dimensional data equivalent to the three-dimensional data generated by the standing position calculation unit 123 as indicated by reference sign d4 in FIG. 7 and the template are overlapped to calculate the differences Δx, Δy, Δz of each axis, This is sent to the image evaluation unit 13 as a face orientation parameter. At this time, if the orientation of the face is significantly different from the orientation of the face of the template, the value of each difference is increased.

  By using such face orientation as a parameter and obtaining image data with a small difference value, it is possible to obtain image data with a face orientation suitable for collation with respect to the camera 3.

  Further, in the present embodiment, the case where the standing position calculation unit 123 calculates the standing position of the verification target person with respect to the camera 3 has been described as an example, but the size of the face in the image data is calculated from the calculated standing position. You may make it do. Here, the face size can be calculated based on the standing position from the camera 3 and the ratio between the distance from the camera 3 and the face size.

  For example, when a photograph of a face is captured by the camera 3 and the face size calculated by the face size calculation unit 122 becomes an appropriate value, it is evaluated as image data suitable for collation or the like. There is a possibility. However, when a photograph of a face is captured by the camera 3, the actual face size is different, so the face size calculated from the standing position and the face size calculated by the face size calculation unit 122 There is a difference between Therefore, the face size is calculated by the standing position calculation unit 123 and compared with the face size calculated by the face size calculation unit 122. For example, when the difference between the sizes exceeds a predetermined range, the size of the face size is calculated. If the image data is significantly different, the image evaluation unit 13 may evaluate that the image data acquired by the camera 3 is not suitable for collation. Thereby, the act of causing the camera 3 to capture an image such as a photograph can be prevented.

  The present invention can be applied to various verification devices that perform identity verification.

  DESCRIPTION OF SYMBOLS 1 ... Verification apparatus, 2 ... Reception apparatus, 3 ... Camera, 4 ... Monitor, 5 ... Electric lock, 11 ... Image acquisition part, 12 ... Parameter calculation part, 13 ... Image evaluation part, 14 ... Evaluation result notification part, 15 ... Collation unit, 16 ... storage unit, 17 ... collation result notification unit, 21 ... imaging control unit, 22 ... display control unit, 23 ... lock control unit, 121 ... face position calculation unit, 122 ... face size calculation unit, 123 ... standing Position calculation unit, 124... Blur condition calculation unit.

Claims (4)

A plurality of imaging units that image the verification target person and generate image data of the verification target person image;
A face position calculation unit that calculates the position of the face of the person to be verified in the image based on the image data;
A face size calculation unit that calculates the size of the face of the person to be verified in the image based on the image data;
Based on the image data, a standing position calculation unit that calculates the standing position of the person to be verified,
Based on the image data, a blur condition calculation unit that calculates the blur condition of the image,
Calculated by the face position calculated by the face position calculation unit, the size of the face calculated by the face size calculation unit, the standing position calculated by the standing position calculation unit, and the blur condition calculation unit An evaluation unit that evaluates whether the image data is suitable for collation based on the degree of blur of the image that has been
If the evaluation unit evaluates that the image data is not suitable for collation, a re-shooting instruction unit that causes the image-capturing unit to recapture the person to be collated,
A storage unit that stores image data of the image of the person to be verified;
And a collation unit that collates the image data captured by the imaging unit and the image data stored in the storage unit when the evaluation unit evaluates that the image data is suitable for collation. Characteristic verification device. The verification device according to claim 1,
A moving speed calculating unit that calculates a moving speed of the verification target person based on the time when the imaging unit images the verification target person and the position of the verification target person in the image;
The said evaluation part evaluates whether the re-acquisition of the said image is required based on the moving speed of the said collation subject calculated by the said moving speed calculation part. The collation apparatus characterized by the above-mentioned. In the collation device according to claim 1 or 2,
A direction calculating unit that calculates the direction of the face of the person to be verified based on the image data;
The said evaluation part evaluates whether the re-acquisition of the said image is required based on the direction of the face of the said collation target person calculated by the said direction calculation part. The collation apparatus characterized by the above-mentioned. An imaging step in which a plurality of imaging units captures the person to be collated and generates image data of the image of the person to be collated;
A face position calculating unit that calculates a position of the face of the person to be verified in the image based on the image data generated by the imaging unit;
A face size calculating unit that calculates a size of the face of the person to be verified in the image based on the image data generated by the imaging unit;
A standing position calculating unit that calculates a standing position of the person to be collated based on the image data generated by the imaging unit;
A blur condition calculating unit that calculates a blur condition of the image based on the image data generated by the imaging unit;
The evaluation unit calculates the face position calculated by the face position calculation unit, the face size calculated by the face size calculation unit, the standing position calculated by the standing position calculation unit, and the blur condition An evaluation step for evaluating whether or not the image data is suitable for collation based on the degree of blur of the image calculated by the calculation unit;
When the re-photographing support unit evaluates that the image data is not suitable for collation by the evaluation unit, a re-photographing instruction step for causing the image-capturing unit to recapture the person to be collated,
A storage step in which the storage unit stores the image data of the image of the person to be verified;
A collation step for collating the image data captured by the imaging unit and the image data stored in the storage unit when the collation unit evaluates that the image data is suitable for collation by the evaluation unit; The collation method characterized by having.