Authentication system, authentication method, and computer program

Abstract

In order to enable images of a subject of authentication who is walking to be captured at an appropriate image-capture timing corresponding to the walking state of the subject of authentication, and to acquire a clear image in which blurring of the subject of authentication is suppressed, an authentication system according to the present invention detects the position of the subject of authentication, the blurring of the body of the same being suppressed by a blurring suppressing means that suppresses blurring of the body of the subject of authentication. On the basis of the detection results, the authentication system controls an image-capture operation of an image-capture means for capturing images of the subject of authentication, and determines, on the basis of biometric information acquired from a captured image of the subject of authentication captured by the image-capture means, whether or not to authenticate the subject of authentication.

Description

[Technical field]

[0001] This disclosure relates to a biometric authentication technology that utilizes biometric information that represents an individual's characteristics. [Background technology]

[0002] Biometric authentication is authentication that uses biometric information such as personal characteristics such as face, fingerprint, iris, vein patterns of fingers, palms, and backs of hands, walking habits, etc. In biometric authentication, for example, by comparing feature amounts extracted from the biometric information of the person to be authenticated with feature amounts of the biometric information of a pre-registered person, if the feature amounts of the person to be authenticated match the feature amounts of the enrolled person, the person to be authenticated is authenticated as the enrolled person.

[0003] Patent Document 1 (JP Patent Publication No. 2007-159762) relates to a biometric authentication device that uses an image of the eyes of a person to be authenticated, and discloses a technique for guiding the person to be authenticated (subject) to an optimal shooting position in order to obtain an eye image suitable for authentication.

[0004] Moreover, Patent Document 2 (Japanese Patent Laid-Open Publication No. 4-153799) discloses a technique for detecting the location of a person by detecting a load or a contact. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2007-159762 A [Patent Document 2] Japanese Patent Application Publication No. 4-153799 Summary of the Invention [Problem to be solved by the invention]

[0006] One type of biometric authentication system is a biometric authentication system also called a walk-through type. The walk-through type biometric authentication system is an authentication system that determines whether or not to authenticate a person to be authenticated while walking, for example, without making the person to be authenticated stop in front of a camera. In the walk-through type biometric authentication system, for example, a fixed camera captures an image of the eyes of the person to be authenticated while walking, and the captured image of the eyes is used as biometric information in the authentication process. The timing for capturing an image of the eyes of the person to be authenticated while walking by the fixed camera is predetermined, for example, when a predetermined time has elapsed since the person to be authenticated passed a predetermined trigger point. The predetermined time is the time expected to be required to reach the capture point of the fixed camera after passing the trigger point, and is set, for example, based on the results of a survey of the walking conditions of many people, such as their walking speed.

[0007] However, there are cases where the walking state of the person to be authenticated is different from the expected walking state, such as when the person to be authenticated has an injury to his / her leg and walks very slowly. In such a case, even if the fixed camera takes a picture at a preset shooting timing, the person to be authenticated has not reached the shooting point of the fixed camera, so that a problem may occur in which an image of the person's eyes cannot be obtained. In addition, there may be a problem in that even if an image of the person's eyes can be captured, the image of the eyes is blurred and inappropriate for authentication processing because the head of the person to be authenticated while walking may shake more than the expected walking state due to an injury to the leg or the like.

[0008] This disclosure has been devised to solve the above problems. That is, the main objective of this disclosure is to provide a technology that can capture an image of a person to be authenticated while walking at an appropriate capture timing according to the walking state of the person to be authenticated, and can obtain a clear image with reduced blurring of the person to be authenticated. [Means for solving the problem]

[0009] In order to achieve the above object, the authentication system includes, as one aspect thereof: a shake suppression means for suppressing body shake of the person to be authenticated; A detection means for detecting a position of the person to be authenticated; an imaging means for imaging the person to be authenticated; a control means for controlling an image capturing operation of the image capturing means for capturing an image of the person to be authenticated based on a detection result of the detection means; an authentication means for determining whether or not to authenticate the person to be authenticated based on biometric information acquired from the photographed image of the person to be authenticated taken by the photographing means; Equipped with.

[0010] In addition, the authentication method includes, as one aspect thereof, By computer, Detecting a position of the person to be authenticated whose body shake is suppressed by a shake suppression means for suppressing the body shake of the person to be authenticated; Controlling an image capturing operation of an image capturing means for capturing an image of the person to be authenticated based on the detection result; A determination is made as to whether or not to authenticate the person to be authenticated based on biometric information acquired from an image of the person to be authenticated captured by the imaging means.

[0011] Furthermore, the program storage medium, as one aspect thereof, A process of detecting a position of a person to be authenticated whose body shake is suppressed by a shake suppression means for suppressing the body shake of the person to be authenticated; A process of controlling an image capturing operation of an image capturing means for capturing an image of the person to be authenticated based on a detection result; a process of determining whether or not to authenticate the person to be authenticated based on biometric information acquired from a photographed image of the person to be authenticated taken by the photographing means; The computer program for causing a computer to execute the above is stored. [Brief description of the drawings]

[0012] [Figure 1] 1 is a block diagram showing a general configuration of an authentication system according to this disclosure. [Diagram 2] 2 is a flowchart illustrating an example of an operation related to an authentication process of the authentication system shown in FIG. 1. [Diagram 3]FIG. 1 is a diagram illustrating an authentication system according to a first embodiment. [Figure 4] FIG. 2 is a diagram illustrating a configuration of a computer device that constitutes the authentication system of the first embodiment. [Diagram 5] 4 is a flowchart illustrating an example of an operation related to an authentication process of the authentication system of the first embodiment. [Figure 6] FIG. 13 is a diagram illustrating an authentication system according to a second embodiment. [Figure 7] FIG. 13 is a diagram illustrating an authentication system according to a third embodiment. [Figure 8] 11A to 11C are diagrams illustrating other examples of the detection device. [Figure 9] 10A to 10C are diagrams illustrating other examples of the vibration suppression device. [Figure 10] 11A and 11B are diagrams illustrating still another example of the vibration suppression device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

[0014] First, the general configuration of the authentication system in this disclosure will be described. Fig. 1 is a block diagram showing the general configuration of the authentication system in this disclosure. The authentication system 1 in this disclosure is a system having a function of determining whether or not to authenticate the person to be authenticated based on the biometric information of the person to be authenticated acquired by an image capture device, and having a function of acquiring the biometric information of the person to be authenticated without making the person to be authenticated stop. The authentication system 1 is a so-called walk-through biometric authentication system. The authentication system 1 includes a shake suppression device 11, a detection device 12, an image capture device 13, a control device 14, and an authentication device 15.

[0015] The vibration suppression device 11 has a configuration for suppressing the vibration of the body of the person to be authenticated. The detection device 12 has a detection function for detecting the position of the person to be authenticated. The photographing device 13 is a device for photographing the person to be authenticated. The control device 14 has a control function for controlling the photographing operation of the photographing device 13 based on the detection result of the detection device 12. The authentication device 15 has an authentication function for determining whether or not to authenticate the person to be authenticated based on biometric information acquired from the photographed image of the person to be authenticated taken by the photographing device 13.

[0016] An example of the operation of the authentication process in the authentication system 1 will be described below with reference to Fig. 2. Fig. 2 is a flowchart illustrating an example of the operation of the authentication process in the authentication system 1. In this example, the detection function of the detection device 12, the control function of the control device 14, and the authentication function of the authentication device 15 are realized by a computer device executing a computer program.

[0017] First, when the detection device 12 detects the position of the person to be authenticated (step 101 in FIG. 2), the control device 14 controls the imaging device 13 based on the detection result to capture an image of the person to be authenticated (step 102).

[0018] Thereafter, authentication device 15 determines whether or not to authenticate the person to be authenticated based on the biometric information acquired from the image of the person to be authenticated captured by imaging device 13 (step 103).

[0019] In the authentication system 1 described above, the shake suppression device 11 is provided to suppress shaking of the body of the person to be authenticated, thereby preventing blurring of the image of the person to be authenticated captured by the imaging device 13. The authentication system 1 also includes a control device 14 that controls the imaging operation of the imaging device 13 based on the detection result of the detection device 12. This allows the control device 14 to control the imaging operation of the imaging device 13 that captures the person to be authenticated according to the state of movement of the person to be authenticated.

[0020] Therefore, the authentication system 1 can capture an image of the person to be authenticated at an appropriate timing according to the walking state of the person to be authenticated while walking, and can obtain a clear image of the person to be authenticated with reduced blurring. This enables the authentication system 1 to increase the accuracy of the authentication result for the person to be authenticated, and improve the reliability of the authentication result.

[0021] An embodiment that is a specific example of such an authentication system 1 will be described below.

[0022] First Embodiment Fig. 3 is a diagram for explaining the authentication system of the first embodiment. In the explanation of the first embodiment, the same reference numerals are given to the components having the same names as those of the authentication system shown in Fig. 1, and the duplicated explanation of the common parts is omitted.

[0023] The authentication system 1 of the first embodiment is located in a passageway leading to the entrance of a facility or the like (hereinafter also referred to as an entrance monitoring area) where only registered persons who are permitted entry can enter, and determines whether or not to permit entry of a person 10, who is attempting to enter the entrance monitoring area, as an authenticated person. The authentication system 1 is a biometric authentication system that uses the iris of the authenticated person 10 as biometric information, and includes a computer device 2, a lighting unit 3, a full-view camera 5, an alarm device 6, a handrail 7, a human detection sensor 8, and an image capturing device 13.

[0024] The photographing device 13 is a camera that photographs the iris of the person to be authenticated, and photographs at least the eye region of the person to be authenticated 10 passing through a depth of field region of, for example, about 1 cm, with a fixed focus, a high frame rate, and high resolution. Here, the high frame rate is, for example, a frame rate higher than 30 fps (frames per second). Also, the high resolution is, for example, a resolution higher than 350 dpi (dots per inch).

[0025] In the first embodiment, it is assumed that there are a plurality of persons 10 who are different in height, and in order to photograph the irises of persons 10 of all heights, a plurality of image capturing devices 13 are arranged in a height direction within a range in the height direction taking into consideration the difference in height of the persons 10. In the example of Fig. 3, the plurality of image capturing devices 13 are arranged in a height direction and fixed to, for example, a support 32. This support 32 is fixed to a road surface 31 of a passage leading to the entrance of the entrance monitoring area. The image capturing operation of such image capturing devices 13 is controlled by a computer device 2.

[0026] The illumination unit 3 includes a light source 4 that irradiates light (e.g., infrared light) toward the face of the person to be authenticated 10 so that the iris of the person to be authenticated is clearly shown in the image captured by the photographing device 13. As with the photographing device 13, the illumination unit 3 also assumes that there are multiple people to be authenticated 10 of different heights, and has multiple light sources 4 arranged in a vertical direction. The light emission and stopping of these light sources 4 is controlled by the computer device 2.

[0027] The overall camera 5 is a camera that captures images of people approaching the entrance of the entrance monitoring area. The camera parameters of the overall camera 5 are set so as to capture an image of the entire body of a person (person to be authenticated 10) located in a predetermined area (hereinafter also referred to as the imaging area of ​​the overall camera 5) including the fixed focal position of the imaging device 13 (for example, the position of the imaging point F in FIG. 3).

[0028] The notification device 6 is a device that notifies information visually or audibly. For example, the notification device 6 is configured with a display device with a speaker, and notifies the result of the determination of whether or not the person to be authenticated is permitted to enter the entrance monitoring area to the person to be authenticated 10. The operation of the notification device 6 is controlled by the computer device 2.

[0029] In the first embodiment, the handrail 7 constitutes the shake suppression device 11. That is, the handrail 7 is provided in at least the following areas along the passage toward the entrance of the entrance monitoring area, and assists the walking of the person (person to be authenticated 10) who is photographed by the photographing device 13. The areas where the handrail 7 is provided are, for example, the photographing area Zp and the photographing preparation area Zq as shown in FIG. 3. The photographing area Zp is a photographing area including the photographing point F of the photographing device 13 (hereinafter, also referred to as the photographing area of ​​the photographing device 13). The photographing preparation area Zq is an area before the person (person to be authenticated 10) heading toward the entrance of the entrance monitoring area reaches the photographing area Zp, and is an area used by the authentication system 1 to determine the timing of starting photographing by the photographing device 13.

[0030] Handrail 7 assists person-to-be-authenticated 10 in walking, thereby suppressing shaking of the body of person-to-be-authenticated 10 , and thereby preventing blurring of person-to-be-authenticated 10 in the image captured by imaging device 13 .

[0031] The human detection sensor 8 is provided in a passageway leading to the entrance of the entrance monitoring area, and is a sensor that detects people passing through the passageway. In the first embodiment, as shown in Fig. 3, a plurality of human detection sensors 8 are arranged at intervals along the passageway leading to the entrance of the entrance monitoring area, at least in the shooting preparation area Zq. There are a plurality of types of human detection sensors, and here, the type of human detection sensor adopted as the human detection sensor 8 is appropriately selected in consideration of the state of the passageway, and the type is not limited, but as an example, there is a type that detects people in a non-contact manner using infrared rays, ultrasonic waves, visible light, etc.

[0032] Furthermore, the interval between adjacent human detection sensors 8 is set taking into consideration the performance of human detection sensors 8, for example, so that person-to-be-authenticated 10 walking down a passageway is not detected by multiple human detection sensors 8.

[0033] The computer device 2 has a control function for controlling the operation of the image capturing device 13 and the lighting unit 3, and an authentication function for determining whether or not to permit the authenticated person 10 to enter the entrance monitoring area by using an image captured by the image capturing device 13. The computer device 2 may be disposed near the entrance to the entrance monitoring area, or may be disposed in another location (for example, a server room of a facility), and the location of the computer device 2 is not limited.

[0034] 4 is a block diagram for explaining the configuration of the computer device 2. The computer device 2 includes a processor 20 such as a CPU (Central Processing Unit), and a storage device 30. Here, the processor 20 may be one of a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field-Programmable Gate Array), a DSP (Demand-Side Platform), and an ASIC (Application Specific Integrated Circuit), or may be a plurality of processors used in parallel.

[0035] The storage device 30 is a storage medium that stores various data and computer programs (hereinafter also referred to as programs). There are various types of storage devices 30, such as a magnetic disk device and a semiconductor memory, and here, the storage device 30 may be composed of any type of storage device. In addition, the storage device constituting the storage device 30 is not limited to one type, and the storage device 30 may be composed of multiple types of storage devices.

[0036] In the first embodiment, an identification model is stored in the storage device 30. This identification model is generated by machine learning of biometric information (here, the iris, more specifically, a feature amount extracted from an iris image) acquired from the person to be authenticated, and is a model used to determine whether the person to be authenticated is permitted to enter.

[0037] The processor 20 is an arithmetic circuit, and can provide the computer device 2 with functions based on the programs by reading out the programs stored in the storage device 30 and executing the programs. That is, the processor 20 includes, as functional units, an acquisition unit 21, an extraction unit 22, an imaging control unit 23, a detection unit 24, an output unit 25, and an authentication unit 26.

[0038] The acquisition unit 21 acquires captured images captured by the photographing device 13 and the overall camera 5. The acquisition unit 21 also acquires sensor output output from the human detection sensor 8. Note that in the first embodiment, a plurality of human detection sensors 8 and a plurality of photographing devices 13 are provided, but in Fig. 4, only one each of the human detection sensors 8 and photographing devices 13 are illustrated, and the illustration of the other person detection sensors 8 and photographing devices 13 is omitted.

[0039] Each of the multiple photographing devices 13 is set with a photographing device ID (IDentification) as identification information, and an image photographed by the photographing device 13 acquired by the acquisition unit 21 is associated with the photographing device ID of the photographing device 13 that captured the image.

[0040] Further, a sensor ID (IDentification) as identification information is set for each of the human detection sensors 8. The sensor output of the human detection sensor 8 acquired by the acquisition unit 21 is associated with the sensor ID of the human detection sensor 8 that outputs the sensor output. Further, the sensor output of the human detection sensor 8 acquired by the acquisition unit 21 is associated with, for example, information on the time when the sensor output is acquired by the acquisition unit 21.

[0041] The extraction unit 22 detects an image area of ​​the iris, which is biometric information, from the captured image of the photographing device 13 acquired by the acquisition unit 21, and extracts iris feature amounts from the iris image area. There are various methods for extracting feature amounts, and here, an extraction method of feature amounts appropriately selected in consideration of the performance of the computer device 2 and the image quality of the captured image is adopted, and a description of the extraction method of feature amounts will be omitted.

[0042] Detection unit 24 detects the position of person-to-be-authenticated 10 by using the sensor output of human detection sensor 8 acquired by acquisition unit 21. That is, information indicating the installation position of human detection sensor 8 is stored, for example, in storage device 30 in association with the sensor ID of that human detection sensor 8. When detection unit 24 detects that one of the multiple human detection sensors 8 has output a sensor output indicating that a person has been detected, detection unit 24 acquires the installation position of that human detection sensor 8 based on the sensor ID of the human detection sensor 8 that output the sensor output. Then, detection unit 24 detects the acquired installation position of human detection sensor 8 as the position of person-to-be-authenticated 10.

[0043] Furthermore, the detection unit 24 calculates the speed of movement (walking) of the person to be authenticated 10 as information related to the movement of the position of the person to be authenticated. That is, the person to be authenticated 10 heading toward the entrance of the entrance monitoring area is detected by a plurality of human detection sensors 8 arranged in an array in a passage leading to the entrance of the entrance monitoring area, in order from the person farthest from the entrance of the entrance monitoring area. Based on time information associated with the sensor output of such human detection sensors 8, the detection unit 24 can calculate the movement time from when the person to be authenticated 10 is detected by one of the human detection sensors 8 to when the person to be authenticated 10 is detected by the human detection sensor 8 adjacent thereto. Furthermore, the detection unit 24 can calculate the distance between adjacent human detection sensors 8 based on information on the installation positions of the human detection sensors 8 given in advance. The detection unit 24 calculates the movement speed of the person to be authenticated 10 based on such distance and movement time. When three or more human detection sensors 8 are arranged in an array, the detection unit 24 can calculate multiple movement speeds, such as a movement speed based on the sensor output of the first and second human detection sensors 8 in the array, and a movement speed based on the sensor output of the second and third human detection sensors 8 in the array. In such a case, the detection unit 24 may determine one of the calculated movement speeds (e.g., a median value) as the movement speed of the person to be authenticated 10, or may further calculate an average value of the calculated movement speeds and determine the average value as the movement speed of the person to be authenticated 10.

[0044] In the first embodiment, the detection device 12 is configured by the detection unit 24 and the human detection sensor 8.

[0045] The photographing control unit 23 executes control related to photographing of the photographing device 13. For example, when the photographing control unit 23 detects that the person to be authenticated 10 has entered the photographing preparation area Zq based on the sensor output of the human detection sensor 8, the photographing control unit 23 detects the height of the eye region of the person to be authenticated 10 from the photographed image of the whole view camera 5. In addition, information on the height at which each of the photographing devices 13 is installed, or information on the height from the road surface 31 at the focal point of each of the photographing devices 13, is stored in the storage device 30 in association with the photographing device ID. Based on such height information related to the photographing device 13 and information on the height of the eye region of the person to be authenticated 10, the photographing control unit 23 selects, from among the multiple photographing devices 13, a photographing device 13 that is suitable for photographing the eye region of the person to be authenticated 10. In addition, the photographing control unit 23 causes the light source 4 of the illumination unit 3 to start emitting light.

[0046] Furthermore, the photographing control unit 23 determines the photographing start timing for starting photographing of the photographing device 13 selected for photographing, using the detection information by the detection unit 24 (i.e., information on the position and moving speed of the person to be authenticated 10). For example, the photographing control unit 23 acquires information on the distance between the installation position (trigger point) of the human detection sensor 8 closest to the photographing point F among the human detection sensors 8 arranged in an array and the photographing point F, and the moving speed of the person to be authenticated 10 calculated by the detection unit 24. Then, the photographing control unit 23 calculates the estimated required time required for the person to be authenticated 10 to reach the photographing point F from the installation position of the human detection sensor 8 closest to the photographing point F, using the acquired information. In other words, the photographing control unit 23 estimates the time to reach the photographing point F. Furthermore, the photographing control unit 23 determines the photographing start timing of the photographing device 13 based on the time obtained by subtracting a predetermined time (for example, 1 second) from the estimated required time and the time when the person to be authenticated 10 is detected by the human detection sensor 8 closest to the photographing point F. Furthermore, the photographing control unit 23 controls the photographing operation of the photographing device 13 so that photographing is started at the determined photographing start timing and is ended when a predetermined photographing time (e.g., 1 second) has elapsed since the start of photographing.

[0047] In the first embodiment, the imaging control unit 23 corresponds to the control device 14 .

[0048] The captured image taken by the photographing device 13 based on the control of the photographing control unit 23 as described above is acquired by the acquisition unit 21 as described above, and the iris features, which are biometric information of the person to be authenticated 10 shown in the captured image, are extracted by the extraction unit 22.

[0049] Authentication unit 26 uses the identification model in storage device 30 to determine whether or not person-to-be-authenticated 10 is permitted to enter the entrance monitoring area (entry permission or not) based on iris features extracted from biometric information of person-to-be-authenticated 10. In other words, authentication unit 26 determines whether or not to authenticate person-to-be-authenticated 10. In the first embodiment, such authentication unit 26 corresponds to authentication device 15.

[0050] The output unit 25 outputs the judgment result of the authentication unit 26 to a predetermined output destination. For example, the output destination is the notification device 6 or the entrance / exit management system 34 connected to the authentication system 1. The notification device 6, which receives the information on the judgment result, notifies the authentication subject 10 of the judgment result. The entrance / exit management system 34 is a system that manages entry to the entrance monitoring area and exit from the entrance monitoring area, and controls, for example, the opening and closing operation of a passage blocking bar installed at the entrance of the entrance monitoring area and the locking and unlocking operation of the door. When the entrance / exit management system 34 receives information of "authenticate (entry permitted)" from the output unit 25 as the judgment result of the authentication unit 26, it executes device operations to permit entry, such as opening the passage blocking bar and unlocking the door.

[0051] An example of the operation of the computer device 2 regarding the authentication process will be described below with reference to Fig. 5. Fig. 5 is a flowchart illustrating an example of the operation of the computer device 2 regarding the authentication process.

[0052] For example, first, based on the sensor output of the human detection sensor 8, the detection unit 24 determines whether or not the human detection sensor 8 has detected a person (i.e., the person to be authenticated 10) in the photographing preparation area Zq (step 201 in FIG. 5). If it is determined that a person has not been detected, the detection unit 24 repeats the determination operation of step 201. In contrast, if it is determined that a person has been detected, the detection unit 24 detects the position of the person to be authenticated 10 based on the sensor output of the human detection sensor 8 (step 202). Furthermore, the detection unit 24 calculates the moving speed of the person to be authenticated 10 using time information associated with the sensor output of the multiple human detection sensors 8 acquired by the acquisition unit 21 and the distance between the installation positions of the human detection sensors 8 (step 203).

[0053] Thereafter, the photographing control unit 23 determines the photographing start timing of the photographing device 13 selected as the photographing device to perform photographing, based on the moving speed of the person to be authenticated 10 and the information on the position of the photographing point F (step 204). Then, the photographing control unit 23 controls the photographing operation of the photographing device 13 so that photographing starts at the determined photographing start timing and ends when a predetermined photographing time has elapsed since the photographing start (step 205). As a result, the eye area of ​​the person to be authenticated 10 is photographed by the photographing device 13.

[0054] The acquisition unit 21 acquires the captured image including the eye region of the person to be authenticated 10 captured by the image capture device 13 in this manner, and the extraction unit 22 extracts the iris feature of the person to be authenticated 10 from the image portion of the eye region in the captured image (step 206). Furthermore, the authentication unit 26 uses a discrimination model to determine whether or not the person to be authenticated 10 is permitted to enter the entrance monitoring area based on the extracted feature (step 207). Then, the output unit 25 outputs the determination result to a predetermined output destination (step 208).

[0055] The authentication system 1 of the first embodiment is configured as described above. In this authentication system 1, handrails 7 are provided along the passageway as shake suppression devices 11 in the photographing area Zp and the photographing preparation area Zq related to photographing by the photographing device 13 in the passageway leading to the entrance of the entrance monitoring area. As a result, the walking of the person to be authenticated 10 can be stabilized by the person to be authenticated walking toward the entrance of the entrance monitoring area using the handrails 7, and the authentication system 1 can obtain an effect of being able to obtain a clear image of the person to be authenticated with suppressed shake.

[0056] Furthermore, authentication system 1 uses the sensor output of human detection sensor 8 constituting detection device 12 to calculate the moving speed indicating the walking state of person-to-be-authenticated 10, and determines the timing to start photographing person-to-be-authenticated 10 by imaging device 13 based on the moving speed. In other words, authentication system 1 determines the timing to start photographing person-to-be-authenticated 10 by imaging device 13 according to the walking state of person-to-be-authenticated 10, and can therefore photograph person-to-be-authenticated 10 at an appropriate timing according to the walking state of person-to-be-authenticated 10.

[0057] In this way, authentication system 1 of the first embodiment can photograph person 10 at an appropriate timing according to the walking state of person 10, and can obtain a clear image with reduced blur of person 10. Therefore, authentication system 1 can increase the accuracy of authentication results for the person to be authenticated, and can improve the reliability of the authentication results.

[0058] Furthermore, when determining the timing to start photographing person 10 by imaging device 13, authentication system 1 of the first embodiment calculates the moving speed indicating the walking state of person 10, and calculates and uses information on the estimated time to reach imaging point F based on the moving speed. This allows authentication system 1 (imaging control unit 23) to improve the calculation accuracy (estimation accuracy) of the estimated time to reach imaging point F compared to when a predetermined fixed time is used to calculate the time. This allows imaging control unit 23 to accurately determine an appropriate timing to start photographing person 10 before he reaches imaging point F.

[0059] Furthermore, in the first embodiment, handrail 7 is provided as shake suppression device 11. Handrail 7 has a simple configuration and can effectively suppress body shake of person-to-be-authenticated 10. Moreover, handrail 7 can smoothly guide person-to-be-authenticated 10 to shooting point F.

[0060] Furthermore, authentication system 1 performs authentication processing of person to be authenticated 10 by utilizing the iris, which is biometric information. Since the iris has clear individual differences, is said to remain unchanged throughout a person's life, and is covered by the cornea and is difficult to damage, authentication system 1 can increase the reliability of the determination of whether or not person to be authenticated 10 can be authenticated by performing authentication processing using the iris. Furthermore, as described above, authentication system 1 is an effective system for iris authentication because it can obtain a clear image of the eye region (iris) of person to be authenticated 10 even when he or she is walking, by controlling the photographing of the eye region of person to be authenticated 10 by photographing device 13.

[0061] <Second embodiment> Fig. 6 is a diagram for explaining the configuration of an authentication system according to a second embodiment. In the explanation of the second embodiment, the components constituting the authentication system 1 shown in Fig. 1 and the components constituting the authentication system 1 according to the first embodiment are given the same reference numerals, and a duplicate explanation of the common parts is omitted.

[0062] In the second embodiment, a plurality of pressure sensors 9 are provided on the handrail 7, and instead of providing a plurality of human detection sensors 8, one human detection sensor 8 is provided in the shooting preparation area Zq.

[0063] The pressure sensor 9 is a sensor whose output sensor value changes depending on the pressure of contact. In the second embodiment, multiple pressure sensors 9 are arranged at intervals on the part of the handrail 7 that is held by a person (holding portion) along the passage leading to the entrance of the entrance monitoring area (i.e., along the moving direction of the authenticated person 10). Note that the multiple pressure sensors 9 need only be provided in at least the image capture preparation area Zq of the handrail 7, but may also be provided, for example, along the entire length of the handrail 7 in the direction along the passage.

[0064] Since the pressure sensor 9 is provided in the gripping portion of the handrail 7, when the person to be authenticated 10 grips the gripping portion of the handrail 7 on which the pressure sensor 9 is provided, the sensor output value of the pressure sensor 9 in the gripped portion changes. The installation position of the pressure sensor 9 where the sensor output value changes in this manner can also be said to be the position of the person to be authenticated 10. In the second embodiment, the spacing between the multiple pressure sensors 9 is set taking into consideration the size of an average human palm, etc., so that when the hand of the person to be authenticated 10 grips the handrail 7, the hand does not grip multiple pressure sensors 9 at the same time.

[0065] The sensor output value of the pressure sensor 9 is acquired by the acquisition unit 21 of the computer device 2. The acquired sensor output value of the pressure sensor 9 is associated with a pressure ID (IDentification) unique to the pressure sensor 9 that output the sensor output value, and time information indicating the time when the sensor output value was acquired. The storage device 30 also stores information indicating the installation positions of each of the multiple pressure sensors 9 in association with the pressure ID of the corresponding pressure sensor 9.

[0066] When the detection unit 24 of the computer device 2 detects a pressure sensor 9 whose sensor output value has changed from a predetermined reference value, the detection unit 24 reads out information on the installation position of the pressure sensor 9 from the storage device 30 as the position of the person to be authenticated 10 based on the pressure ID of the pressure sensor 9. The detection unit 24 also calculates the movement speed of the person to be authenticated 10 using a method similar to the method of calculating the movement speed of the person to be authenticated 10 using the multiple human detection sensors 8 described in the first embodiment. That is, the detection unit 24 can calculate the movement time from when the person to be authenticated 10 is detected by one of the pressure sensors 9 to when the person to be authenticated 10 is detected by the adjacent pressure sensor 9 using time information associated with the sensor output value of the pressure sensor 9. The detection unit 24 can also calculate the distance between adjacent pressure sensors 9 based on information on the installation positions of the pressure sensors 9 given in advance. The detection unit 24 calculates the movement speed of the person to be authenticated 10 based on such distance and movement time. That is, in the second embodiment, the detection device 12 is configured by such a detection unit 24 and pressure sensor 9.

[0067] In the second embodiment, when determining the image capture start timing of the image capture device 13, the image capture control unit 23 uses the detection of the person to be authenticated 10 by the human detection sensor 8 and the distance from the installation position of the human detection sensor 8 to the image capture point F, as in the first embodiment. However, the image capture control unit 23 uses the movement speed of the person to be authenticated 10 calculated by the detection unit 24 using the multiple pressure-sensitive sensors 9 as the movement speed of the person to be authenticated 10. That is, the image capture control unit 23 calculates the estimated required time required to reach the image capture point F from the installation position of the human detection sensor 8 based on the distance from the installation position of the human detection sensor 8 to the image capture point F and the movement speed of the person to be authenticated 10 calculated by the detection unit 24. Then, the image capture control unit 23 determines the image capture start timing of the image capture device 13 based on the time obtained by subtracting a predetermined time from the estimated required time and the time when the person to be authenticated 10 is detected by the human detection sensor 8, as in the first embodiment. Using the image capture start timing determined in this way, the image capture control unit 23 controls the image capture operation of the image capture device 13.

[0068] The configuration of the authentication system 1 of the second embodiment other than the above is similar to that of the authentication system 1 of the first embodiment, and therefore a description thereof will be omitted.

[0069] As in the first embodiment, the authentication system 1 of the second embodiment is provided with a handrail 7 as a shake suppression device 11, thereby stabilizing the walking of the person to be authenticated 10 and achieving the effect of obtaining a clear image of the person to be authenticated 10 with reduced shaking.

[0070] Moreover, authentication system 1 of the second embodiment is provided with a plurality of pressure sensors 9, calculates the moving speed of person-to-be-authenticated 10 using the plurality of pressure sensors 9, and determines the timing to start photographing using the moving speed, thereby controlling image capturing device 13 in the same manner as in the first embodiment. In other words, authentication system 1 of the second embodiment can also capture an image of person-to-be-authenticated 10 at an appropriate timing according to the walking state of person-to-be-authenticated 10.

[0071] Therefore, the authentication system 1 of the second embodiment can also photograph the person to be authenticated 10 at an appropriate timing according to the walking state of the person to be authenticated 10, and can obtain a clear image of the person to be authenticated 10 with reduced blurring, thereby improving the accuracy of the authentication results.

[0072] Furthermore, a configuration in which multiple pressure sensors 9 are installed on the handrail 7 and the position of the person to be authenticated 10 is detected based on the sensor output of the pressure sensors 9 makes it possible to detect the position of the person to be authenticated 10 without the person to be authenticated 10 being aware that his or her position is being detected.

[0073] However, there may be cases where the person to be authenticated 10 does not hold the handrail 7 because his / her hands are full of luggage or the person to be authenticated 10 is walking steadily and does not need the assistance of the handrail 7. In such a case, the moving speed of the person to be authenticated 10 cannot be calculated using the pressure sensor 9. This raises the concern that the timing to start shooting by the image capture device 13 cannot be determined and the image capture device 13 cannot capture the iris of the person to be authenticated 10. In order to avoid such a situation, for example, the whole camera 5 may be configured as a stereo camera. That is, a stereo camera is a camera that can output a captured image including information on the distance in the depth direction relative to the camera. By configuring the whole camera 5 as a stereo camera, for example, the detection unit 24 can calculate the moving distance of a person (person to be authenticated 10) moving through the image capture preparation area Zq toward the entrance of the entrance management area from a plurality of captured images (frame images) by the whole camera 5. In addition, the detection unit 24 can calculate the moving time required for the movement from the frame rate. This allows detection unit 24 to calculate the movement speed of person-to-be-authenticated 10 who is moving through photography preparation area Zq toward the entrance of the entrance control area by using overall camera 5. Detection unit 24 may be provided with a function for calculating the movement speed of person-to-be-authenticated 10 using such overall camera 5.

[0074] When the detection unit 24 is provided with a function for calculating the movement speed of the person to be authenticated 10 using the overall camera 5, for example, the detection unit 24 also has a function for detecting that the person to be authenticated 10 is in the image preparation area Zq from the image captured by the overall camera 5. Furthermore, when the detection unit 24 detects that the person to be authenticated 10 is in the image preparation area Zq from the image captured by the overall camera 5 but the pressure sensor 9 does not detect the person to be authenticated 10, the detection unit 24 calculates the movement speed of the person to be authenticated 10 using the overall camera 5 instead of the pressure sensor 9.

[0075] Alternatively, the detection unit 24 may not have a function of detecting the presence of the person to be authenticated 10 in the photographing preparation area Zq from the image captured by the overall camera 5, and may calculate the movement speed of the person to be authenticated 10 using the overall camera 5 regardless of whether the person to be authenticated 10 is detected by the pressure sensor 9. In this case, the detection unit 24 may calculate both the movement speed of the person to be authenticated 10 using the pressure sensor 9 and the movement speed of the person to be authenticated 10 using the overall camera 5. In this case, for example, the detection unit 24 determines the average value of the movement speed of the person to be authenticated 10 using the pressure sensor 9 and the movement speed of the person to be authenticated 10 using the overall camera 5 as the movement speed of the person to be authenticated 10. Alternatively, the detection unit 24 may prioritize the pressure sensor 9 over the overall camera 5 and determine the movement speed of the person to be authenticated 10 using the pressure sensor 9 as the movement speed of the person to be authenticated 10.

[0076] In the second embodiment, an example is described in which the pressure sensor 9 is provided on the handrail 7, but the pressure sensor 9 may be provided, for example, on the road surface 31 of the shooting preparation area Zq in the passage leading to the entrance of the entrance monitoring area. In this case, similarly to the above, the detection unit 24 can detect the position of the person to be authenticated 10 and can also calculate the moving speed of the person to be authenticated 10 by using the sensor output of the pressure sensor 9 provided on the road surface 31.

[0077] <Third embodiment> In the third embodiment, an example in which the position of the person to be authenticated is detected and the moving speed of the person to be authenticated is calculated by a method different from that of the first and second embodiments, that is, another specific example of the detection device 12 in Fig. 1 will be described. In the description of the third embodiment, the components constituting the authentication system 1 shown in Fig. 1 and the components constituting the authentication system 1 of the first and second embodiments are given the same reference numerals as those, and a duplicate description of the common parts will be omitted.

[0078] FIG. 7 is a plan view of the passage leading to the entrance of the entrance monitoring area, seen from above. In the third embodiment, a passageway leading to the entrance of the entrance monitoring area is provided with a passageway blocking bar 36 that is slidable from the shooting preparation area Zq to the entrance of the entrance monitoring area. The passageway blocking bar 36 is configured to slide in the direction toward the entrance of the entrance monitoring area by receiving a pressing force in the direction toward the entrance of the entrance monitoring area. The passageway blocking bar 36 is also configured to block passage through the passageway in a closed state, and to release the blockage of passageway (blockage of the passageway) in an open state. For example, the basic state of the passageway blocking bar 36 is a closed state, and the opening operation from the closed state to the open state is controlled by the entrance / exit management system 34. In the third embodiment, a sensor 37 is provided to detect the position of the passageway blocking bar 36. For example, the sensor 37 is provided near the entrance of the entrance monitoring area, and is a sensor that outputs a sensor output according to the distance from the passageway blocking bar 36 as information regarding the position of the passageway blocking bar 36.

[0079] In the third embodiment, the person to be authenticated 10 moves together with the traffic blocking bar 36 while pushing the traffic blocking bar 36 from the photographing preparation area Zq to the entrance of the entrance monitoring area. Therefore, the position of the traffic blocking bar 36 can be said to be the position of the person to be authenticated 10, and the moving distance and moving speed of the traffic blocking bar 36 can be said to be the moving distance and moving speed of the person to be authenticated 10. The acquisition unit 21 of the computer device 2 acquires the sensor output of the sensor 37. The acquired sensor output of the sensor 37 is associated with time information indicating the time at which it was acquired. The detection unit 24 can calculate the moving distance of the traffic blocking bar 36 using the sensor output of the sensor 37, and can calculate the moving speed of the traffic blocking bar 36 using the time information associated with the sensor output and the calculated moving distance. That is, the detection unit 24 can calculate the moving distance and moving speed of the person to be authenticated 10 using the sensor output of the sensor 37 and the time information associated with the sensor output. In the third embodiment, the detection device 12 is configured by the detection unit 24, the traffic blocking bar 36, and the sensor 37.

[0080] In the third embodiment, when determining the image capture start timing of the image capture device 13, the image capture control unit 23 uses the detection of the person to be authenticated 10 by the human detection sensor 8 and the distance from the installation position of the human detection sensor 8 to the image capture point F, as in the first embodiment. Also, unlike the first embodiment, the image capture control unit 23 uses the movement speed of the person to be authenticated 10 calculated by the detection unit 24 using the movement detection of the passage blocking bar 36 as the movement speed of the person to be authenticated 10. That is, the image capture control unit 23 calculates the estimated required time required to reach the image capture point F from the installation position of the human detection sensor 8 based on the distance from the installation position of the human detection sensor 8 to the image capture point F and the movement speed of the person to be authenticated 10 calculated by the detection unit 24. Then, the image capture control unit 23 determines the image capture start timing of the image capture device 13 based on the time obtained by subtracting a predetermined time from the estimated required time and the time when the person to be authenticated 10 is detected by the human detection sensor 8, as in the first embodiment. Using the image capture start timing determined in this way, the image capture control unit 23 controls the image capture operation of the image capture device 13.

[0081] The extraction unit 22 extracts iris features of the person to be authenticated 10 from an image of the iris of the person to be authenticated captured by the image capture device 13 based on the control operation of the image capture control unit 23, and the authentication unit 26 uses a discrimination model based on the extracted features to determine whether the person to be authenticated 10 is permitted to enter the entrance monitoring area. If the determination is that entry is permitted, the determination result is output by the output unit 25 to the entrance / exit management system 34. In this case, the entrance / exit management system 34 performs control to open the passage blocking bar 36, for example, when the passage blocking bar 36 has reached the entrance to the entrance monitoring area. This allows the person to be authenticated 10 to enter the entrance monitoring area without being hindered by the passage blocking bar 36.

[0082] The configuration of the authentication system 1 of the third embodiment other than the above is similar to that of the authentication system 1 of the first embodiment, and therefore a description thereof will be omitted.

[0083] As in the first embodiment, the authentication system 1 of the third embodiment is also provided with a handrail 7 as a shake suppression device 11, thereby stabilizing the walking of the person to be authenticated 10 and achieving the effect of obtaining a clear image of the person to be authenticated 10 with reduced shaking.

[0084] Furthermore, authentication system 1 of the third embodiment calculates the moving speed of person-to-be-authenticated 10 using information related to the movement of sliding passage blocking bar 36, and determines the timing to start photographing using the calculated moving speed, thereby controlling image capturing device 13 in the same manner as in the first embodiment. In other words, authentication system 1 of the third embodiment can also capture an image of person-to-be-authenticated 10 at an appropriate timing according to the walking state of person-to-be-authenticated 10.

[0085] Therefore, the authentication system 1 of the third embodiment can also photograph the person to be authenticated 10 at an appropriate timing according to the walking state of the person to be authenticated 10, and can obtain a clear image of the person to be authenticated 10 with reduced blurring, thereby improving the accuracy of the authentication result.

[0086] <Fourth embodiment> In the fourth embodiment, an example in which the position of the person to be authenticated is detected and the moving speed of the person to be authenticated is calculated by a method different from that of the first to third embodiments, that is, another specific example of the detection device 12 in Fig. 1 will be described. In the description of the fourth embodiment, the components constituting the authentication system 1 shown in Fig. 1 and the components constituting the authentication system 1 of the first to third embodiments are given the same reference numerals as those therein, and a duplicate description of the common parts will be omitted.

[0087] In the fourth embodiment, a plurality of marks are arranged at intervals in a direction toward the entrance of the entrance monitoring area on at least one of the surface of the handrail 7 and the road surface 31 in the shooting preparation area Zq in the passage leading to the entrance of the entrance monitoring area. Also, a camera 38 is provided as shown by the dotted line in Fig. 6 for shooting the plurality of marks. Based on the positions of the marks hidden by the hands or body of the person to be authenticated 10 in the image captured by this camera 38, the detection unit 24 can detect the position of the person to be authenticated 10.

[0088] That is, mark position information in which the positions of multiple marks in an image captured by camera 38 are associated with information indicating the positions of the marks in real space is stored, for example, in storage device 30. Also stored in storage device 30 is a detection model for detecting the body of person to be authenticated 10, which is generated by machine learning images of the hands and feet of person to be authenticated 10 that hide marks in the image captured by camera 38.

[0089] Using the detection model, detection unit 24 detects the positions of the hands and feet of person-to-be-authenticated 10 from the images captured by camera 38, and judges whether or not there is a mark overlapping with the detected hand or foot. If detection unit 24 judges that there is a mark overlapping with the hand or foot of person-to-be-authenticated 10, it detects the position of the mark in real space as the position of person-to-be-authenticated 10 based on the mark position information in storage device 30. Based on the position of person-to-be-authenticated 10 detected in this way, the change in position (movement distance) of person-to-be-authenticated 10 in multiple time-series images (frame images) captured by camera 38, and the time related to the change (movement time), detection unit 24 calculates the movement speed of person-to-be-authenticated 10. In the fourth embodiment, the multiple marks, camera 38, and detection unit 24 constitute detection device 12 in FIG. 1.

[0090] Using the moving speed of person-to-be-authenticated 10 calculated in this manner, photographing control unit 23 determines the photographing start timing of photographing device 13 , and further controls the photographing operation of photographing device 13 .

[0091] Other configurations of the authentication system 1 of the fourth embodiment than those described above are similar to those of the authentication system 1 of the first and second embodiments, and therefore a description thereof will be omitted.

[0092] As in the first to third embodiments, the authentication system 1 of the fourth embodiment is provided with a handrail 7 as a shake suppression device 11, thereby stabilizing the walking of the person to be authenticated 10 and achieving the effect of obtaining a clear image of the person to be authenticated 10 with reduced shaking.

[0093] Furthermore, in authentication system 1 of the fourth embodiment, detection unit 24 uses a plurality of marks in shooting preparation area Zq and an image captured by camera 38 that captures the marks to determine the timing at which shooting begins for shooting device 13, thereby controlling shooting device 13 in the same manner as in the first to third embodiments. That is, in authentication system 1 of the fourth embodiment as well, it is possible to capture an image of person to be authenticated 10 at an appropriate timing according to the walking state of person to be authenticated 10.

[0094] Therefore, the authentication system 1 of the fourth embodiment can also photograph the person to be authenticated 10 at an appropriate timing according to the walking state of the person to be authenticated 10, and can obtain a clear image of the person to be authenticated 10 with reduced blurring, thereby improving the accuracy of the authentication result.

[0095] In the first to fourth embodiments, various specific configurations of the detection device 12 that detects the position of the person to be authenticated 10 are described, but the configuration of the detection device 12 is not limited to the above specific configurations. For example, a plurality of receiving sensors that receive a beacon signal transmitted from a mobile terminal such as a smartphone carried by the person to be authenticated 10 may be arranged at intervals in the photographing preparation area Zq along a passage leading to the entrance of the entrance monitoring area. By receiving information indicating the installation position of the receiving sensor that received the beacon signal via the acquisition unit 21, the detection unit 24 can detect the position of the person to be authenticated 10 based on the information and calculate the moving speed of the person to be authenticated 10 in the same manner as described above. That is, in this case, the detection device 12 is composed of a plurality of receiving sensors and the detection unit 24.

[0096] 8, an unmanned aerial vehicle 40 also called a drone is flown in the image capture preparation area Zq. The unmanned aerial vehicle 40 has a function of detecting a person (authenticated person 10) in the image capture preparation area Zq, for example. There are various methods for detecting a person, such as a method using an infrared sensor or a method of mounting a camera and detecting a person from an image captured by the camera, and the method is appropriately selected taking into consideration the performance of a computer mounted on the unmanned aerial vehicle 40.

[0097] Furthermore, unmanned aerial vehicle 40 has a function of moving by following the movement of a person (person to be authenticated 10) detected in image capture preparation area Zq. Detection unit 24 detects the position of unmanned aerial vehicle 40 as the position of person to be authenticated 10, and calculates the movement speed of unmanned aerial vehicle 40 as the movement speed of person to be authenticated 10. Detection of the position of unmanned aerial vehicle 40 and calculation of the movement speed of unmanned aerial vehicle 40 are possible by applying, for example, the above-mentioned method of detecting the position of person to be authenticated 10 and the method of calculating the movement speed.

[0098] In such a case, the unmanned aerial vehicle 40 and the detection unit 24 form the detection device 12 .

[0099] Even when the position of person to be authenticated 10 is detected and the moving speed is calculated using a beacon signal from a mobile terminal or an unmanned aerial vehicle as described above, authentication system 1 can obtain the same effects as those of the first to fourth embodiments.

[0100] <Fifth embodiment> In the fifth embodiment, an example of suppressing the shaking of the body of the person to be authenticated by a method different from that of the first to fourth embodiments, that is, another specific example of the shaking suppression device 11 in Fig. 1 will be described. In the description of the third embodiment, the components constituting the authentication system 1 shown in Fig. 1 and the components constituting the authentication system 1 of the first and second embodiments are given the same reference numerals, and a duplicated description of the common parts will be omitted.

[0101] In the fifth embodiment, at least the passageway portion of the shooting preparation area Zq and the shooting area Zp in the passageway leading to the entrance of the entrance monitoring area is provided with a human transport device also called a moving walkway 41 as shown in Fig. 9 as a vibration suppression device 11. Note that there are multiple types of configuration of the moving walkway 41, and any type of moving walkway may be provided here, so the description thereof will be omitted. Also, a handrail that moves with the movement of the road surface 31 of the moving walkway 41 is provided, but the handrail 7 fixed to a wall or the like is omitted.

[0102] In this way, when moving walkway 41 is provided in the passage between shooting preparation area Zq and shooting area Zp, person-to-be-authenticated 10 can move in the passage without walking. Therefore, shaking of the body of person-to-be-authenticated 10 caused by walking is suppressed.

[0103] Furthermore, by suppressing the shaking of the body of the person to be authenticated 10 in this way, the image area in which the eye area of ​​the person to be authenticated 10 is expected to be captured in the image captured by the image capturing device 13 becomes narrower. That is, it becomes possible to set a narrow ROI (Region Of Interest) in the captured image, which is an area processed by the extraction unit 22, the detection unit 24, etc. As a result, the authentication system 1 can achieve the effect of reducing the processing load on the computer device 2.

[0104] Furthermore, in the fifth embodiment, the computer device 2 is connected to a drive system that controls the operation of the moving walkway 41, and has a function of acquiring information regarding the moving speed of the road surface 31 of the moving walkway 41. In this case, since the person to be authenticated 10 and the road surface 31 of the moving walkway 41 move in the same manner, the detection unit 24 of the computer device 2 can detect the moving speed of the person to be authenticated 10 based on the information regarding the moving speed of the road surface 31 of the moving walkway 41 acquired from the drive system.

[0105] Then, the photographing control unit 23 uses the detected moving speed of the person to be authenticated 10 to determine the photographing start timing of the photographing device 13, as in the first to fourth embodiments, and further controls the photographing operation of the photographing device 13. That is, the photographing control unit 23 calculates the estimated required time required for the person to reach the photographing point F from the installation position of the human detection sensor 8, based on the distance from the installation position of the human detection sensor 8 to the photographing point F and the moving speed of the person to be authenticated 10 calculated by the detection unit 24. Then, the photographing control unit 23 determines the photographing start timing of the photographing device 13, based on the time obtained by subtracting a predetermined time from the calculated required time and the time when the person to be authenticated 10 is detected by the human detection sensor 8, as in the first to fourth embodiments. The photographing control unit 23 controls the photographing operation of the photographing device 13 using the photographing start timing determined in this manner.

[0106] Other configurations of the authentication system 1 of the fifth embodiment than those described above are similar to those of the authentication systems 1 of the first to fourth embodiments, and therefore a description thereof will be omitted.

[0107] In the fifth embodiment, a moving walkway 41 is provided as the shake suppression device 11, so that the shaking of the body of the person to be authenticated 10 caused by walking can be suppressed, and a clear image of the person to be authenticated 10 with suppressed shaking can be obtained.

[0108] Furthermore, authentication system 1 of the fifth embodiment is connected to a drive system that controls the operation of moving walkway 41, and acquires information related to the moving speed of road surface 31 of moving walkway 41. As a result, detection unit 24 can detect the moving speed of person-to-be-authentication 10 based on the information related to the moving speed of road surface 31 of moving walkway 41 acquired from the drive system, thereby reducing the load related to the calculation process of the moving speed of person-to-be-authentication 10.

[0109] Furthermore, similarly to the first to fourth embodiments, authentication system 1 of the fifth embodiment determines the timing to start photographing by photographing device 13 in consideration of the moving speed of person-to-be-authenticated 10, and controls the photographing operation of photographing device 13. Therefore, similarly to the first to fourth embodiments, authentication system 1 of the fifth embodiment can also photograph person-to-be-authenticated 10 at an appropriate timing according to the moving state of person-to-be-authenticated 10.

[0110] Therefore, the authentication system 1 of the fifth embodiment can also photograph the person to be authenticated 10 at an appropriate timing according to the movement state of the person to be authenticated 10, and can obtain a clear image of the person to be authenticated 10 with reduced blurring, thereby improving the accuracy of the authentication result.

[0111] The road surface 31 of the moving walkway 41 may be horizontal, may be an inclined surface that rises toward the image capture device 13, or may be an inclined surface that falls toward the image capture device 13 as shown in FIG. 9. When the road surface 31 is an inclined surface, the line of sight of the person to be authenticated 10 is more likely to be fixed, such as when the person to be authenticated 10 looks at the area around his / her feet, than when the road surface 31 is a horizontal surface. Therefore, a configuration in which the road surface 31 is an inclined surface has the effect of making it easier to capture the eye area (iris) of the person to be authenticated 10. In addition, when a plurality of people to be authenticated 10 are lined up in the direction toward the image capture device 13, a configuration in which the road surface 31 is an inclined surface that falls down is likely to create a difference in height, such that the head of the person to be authenticated 10 at the back is higher than the head of the person to be authenticated 10 at the front. This reduces the occurrence of a situation in which a part or all of the face of the person to be authenticated 10 at the back is hidden by the head of the person to be authenticated 10 at the front, and the image capture device 13 cannot capture the image satisfactorily.

[0112] In the fifth embodiment, an example in which the moving walkway 41 is provided as the shake suppression device 11 has been described. However, for example, a transport device for carrying the person to be authenticated 10 in a seated state, such as a chair lift 42 or an automatic driving cart as shown in FIG. 10, may be provided as the shake suppression device 11 at least in the shooting preparation area Zq and the shooting area Zp. In this case, the person to be authenticated 10 passes through the shooting area Zp in a seated state, so that the shaking of the body of the person to be authenticated 10 in the shooting area Zp can be suppressed more than when the moving walkway 41 is provided. This allows the authentication system 1 to obtain the effect of narrowing the ROI in the captured image. In addition, the authentication system 1 can cooperate with a drive system that controls the operation of the transport device, such as the chair lift 42 or the automatic driving cart, and can, for example, control the orientation of the chair lift 42 or the automatic driving cart to make the face of the person to be authenticated 10 face the shooting device 13.

[0113] When a transport device such as the chair lift 42 or an autonomous cart is provided, the authentication system 1 of the fifth embodiment is connected to a drive system that controls the operation of the transport device and acquires information on the moving speed of the transport device in the same manner as described above. Then, the detection unit 24 detects the moving speed of the person to be authenticated 10 based on the acquired information on the moving speed. The photography control unit 23 uses the moving speed of the person to be authenticated 10 to determine the timing for starting photography by the photography device 13, and further controls the photography operation of the photography device 13.

[0114] In the above example, the authentication system 1 acquires information on the moving speed of the transport equipment from a drive system that drives the transport equipment such as the moving walkway 41, the chair lift 42, or the self-driving cart, and the detection unit 24 detects the moving speed of the person to be authenticated 10 based on the acquired information. Alternatively, the detection unit 24 may detect (calculate) the moving speed of the person to be authenticated 10 by the following configuration. For example, a mark is attached to the moving walkway 41, the chair lift 42, or the self-driving cart, and a camera (for example, a camera 38 as shown by a dotted line in FIG. 6) is provided to capture such a mark at least in the preparation area Zq for capture. Then, the detection unit 24 detects the position of the mark in the image captured by the camera 38 by using a detection model for mark detection stored in advance in the storage device 30. The detection model for mark detection is a model for detecting a mark from a captured image, which is generated by learning an image of the mark, and is generated in advance and stored in the storage device 30.

[0115] Furthermore, detection unit 24 calculates the movement speed of the mark as the movement speed of person-to-be-authenticated 10, based on the movement distance of the mark in a plurality of time-series captured images (frame images) by camera 38 and the movement time based on the frame rate. In this manner, detection unit 24 may calculate the movement speed of person-to-be-authenticated 10.

[0116] Furthermore, detection unit 24 may calculate the moving speed of person to be authenticated 10 by the following configuration. For example, a transmitter that emits a beacon signal may be attached to a chair of chairlift 42 or an automatically driven cart, and multiple receiving sensors that receive the beacon signal may be arranged at intervals in photographing preparation area Zq along a path leading to the entrance of the entrance monitoring area. As described above, detection unit 24 receives information indicating the installation position of the receiving sensor that received the beacon signal via acquisition unit 21, and detects the position of person to be authenticated 10 based on the information and calculates the moving speed of person to be authenticated 10.

[0117] <Other embodiments> The form of the authentication system 1 in this disclosure is not limited to the first to fifth embodiments, and various other forms may be adopted. For example, as yet another example of the vibration suppression device 11, a configuration in which a low-resilience mat is laid at least in the passage portion of the shooting preparation area Zq and the shooting area Zp can be cited. The low-resilience mat is a mat formed of a material with low resilience and high shock absorption, such as low-resilience urethane, and can suppress the shaking of the body of the person to be authenticated 10 due to walking. In addition, when the low-resilience mat is laid in the passage, a plurality of pressure-sensitive sensors 9 as described in the second embodiment may be arranged on the low-resilience mat at intervals along the movement and walking of the person to be authenticated 10. The position of the person to be authenticated 10 can be detected by such pressure-sensitive sensors 9 in the same manner as described above. Furthermore, when the low-resilience mat is laid in the passage, the handrail 7 described in the first embodiment may be omitted. In addition, both the low-resilience mat and the handrail 7 may be provided as the vibration suppression device 11.

[0118] Furthermore, in the second embodiment, an example in which the overall camera 5 is configured by a stereo camera has been described, but for example, a stereo camera may be provided in parallel to the overall camera 5 in addition to the overall camera 5. In such a case, the stereo camera is installed so as to capture, for example, a mark attached to a chair of a chairlift or an autonomous driving cart as described above. Then, using position information of the mark obtained from a plurality of time-series captured images by the stereo camera, the detection unit 24 may calculate the movement speed of the mark as the movement speed of the person to be authenticated 10.

[0119] Furthermore, as explained in the fourth embodiment, when a mark is attached to handrail 7, road surface 31, chairlift chair, or self-driving cart in order to detect the position of authenticated person 10, the mark may be made of a material that is easily reflective to light. The mark may also be made of a material that reacts to light of a predetermined wavelength. In such a case, a light source that irradiates light onto the mark may be further provided. With such a configuration, for example, the mark can be made to stand out in a captured image of the mark, making it easier to detect the mark.

[0120] Furthermore, in the first to fifth embodiments, the authentication system 1 is described as a system used to determine whether or not to permit entry to an entrance monitoring area, but the authentication system 1 in this disclosure can also be applied to authentication other than determining whether or not to permit entry.

[0121] The present invention has been described above by taking the above-mentioned embodiment as an exemplary example. However, the present invention is not limited to the above-mentioned embodiment. That is, the present invention can be applied in various aspects that can be understood by a person skilled in the art within the scope of the present invention.

[0122] This application claims priority based on Japanese Patent Application No. 2020-174914, filed on October 16, 2020, the disclosure of which is incorporated herein in its entirety. [Explanation of symbols]

[0123] 1 Authentication System 11 Vibration suppression device 12 Detection Device 13 Imaging Equipment 14 Control device 15 Authentication Device

Claims

1. An imaging means including a camera for imaging a person to be authenticated; a vibration suppression means configured by a transport device for carrying the person to be authenticated and configured to suppress vibration of the body of the person to be authenticated that is photographed by the photographing means; A detection means for detecting the location of the person to be authenticated by a computer device using a sensor or a camera; a control means for controlling, by a computer device, an image capturing operation of the image capturing means for capturing an image of the person to be authenticated based on a detection result of the detection means; an authentication means for determining, by a computer device, whether or not to authenticate the person to be authenticated based on biometric information acquired from the photographed image of the person to be authenticated taken by the photographing means; Equipped with An authentication system in which the transportation device is a moving walkway, and the road surface of the moving walkway is a slope that descends toward the imaging means.

2. The authentication system according to claim 1, wherein the control means controls the photographing operation based on information relating to the movement of the position of the person to be authenticated detected by the detection means and information on a predetermined photographing location where the photographing means photographs the person to be authenticated.

3. the information relating to the movement of the position of the person to be authenticated is a moving speed of the person to be authenticated; 3. The authentication system according to claim 2, wherein the control means estimates a time required for the person to reach the image capture point based on a moving speed of the person to be authenticated, and determines a timing for starting image capture by the image capture means based on the estimated time.

4. 4. The authentication system according to claim 1, wherein the vibration suppressing means includes a handrail that supports movement of the person to be authenticated in an area where the person to be authenticated is photographed by the photographing means.

5. The photographing means photographs the iris of the person to be authenticated, The authentication system according to any one of claims 1 to 4, wherein the authentication means determines whether or not to authenticate the person to be authenticated based on an iris, which is biometric information obtained from an image of the person to be authenticated captured by the photographing means.

6. By computer, Detecting, using a sensor or a camera, a position of the person to be authenticated whose body shake is suppressed by a shake suppression means configured in a transport device carrying the person to be authenticated, the shake suppression means suppressing the body shake of the person to be authenticated, the position being photographed by a photographing means configured in a camera; Controlling the photographing operation of the photographing means based on the detection result; determining whether or not to authenticate the person to be authenticated based on biometric information acquired from the photographed image of the person to be authenticated taken by the photographing means; The authentication method according to the present invention, wherein the transportation device is a moving walkway, and the road surface of the moving walkway is an inclined surface that slopes downward toward the photographing means.

7. A process of detecting, using a sensor or a camera, a position of the person to be authenticated whose body shake is suppressed by a shake suppression means configured in a transport device carrying the person to be authenticated, the person being photographed by a photographing means configured in a camera, and the shake suppression means suppressing the shake of the body of the person to be authenticated; A process of controlling a photographing operation of the photographing means based on a detection result; a process of determining whether or not to authenticate the person to be authenticated based on biometric information acquired from a photographed image of the person to be authenticated taken by the photographing means; on the computer, A computer program in which the transportation device is a moving walkway, and the surface of the moving walkway is a slope that descends toward the imaging means.

Images